mirror of
https://github.com/pewdiepie-archdaemon/odysseus.git
synced 2026-06-16 01:35:36 -04:00
Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Kenny Van de Maele
|
94d2754f41 |
@@ -10,12 +10,6 @@ dist/
|
||||
build/
|
||||
.env
|
||||
.env.bak.*
|
||||
# Secrets: keep plaintext and every transient secrets.env variant out of
|
||||
# the build context. If an encrypted secrets.env is used, it is mounted
|
||||
# at runtime — never baked into the image. Mirrored in .gitignore.
|
||||
secrets.env
|
||||
secrets.env.*
|
||||
!secrets.env.example
|
||||
/data/
|
||||
/logs/
|
||||
.git/
|
||||
|
||||
@@ -190,10 +190,3 @@ SEARXNG_INSTANCE=http://localhost:8080
|
||||
# These overlays only expose the GPU devices. The slim Odysseus image
|
||||
# still needs CUDA/ROCm userspace via Cookbook -> Dependencies (vLLM,
|
||||
# llama-cpp-python, etc.) before models can actually serve on GPU.
|
||||
|
||||
# ============================================================
|
||||
# Storage Paths (Docker Compose)
|
||||
# ============================================================
|
||||
|
||||
# APP_DATA_DIR=./data
|
||||
# APP_LOGS_DIR=./logs
|
||||
|
||||
@@ -1,9 +0,0 @@
|
||||
# Code owners.
|
||||
#
|
||||
# Intentionally empty for now. The catch-all rule that mapped every path to a
|
||||
# single owner froze all merges the moment "Require review from Code Owners"
|
||||
# was enabled, because no other maintainer's approval could satisfy the gate.
|
||||
# A per-area ownership map (security/auth, CI, frontend, agent internals, with
|
||||
# multiple named owners per line) is being worked out in issue #593; once
|
||||
# agreed it replaces this file. Until then, required reviews and the security
|
||||
# CI gate (docs/security-ci.md) remain in force via branch protection.
|
||||
@@ -1,48 +0,0 @@
|
||||
# Dependabot keeps dependencies and pinned action versions current.
|
||||
#
|
||||
# Why this matters for security: every workflow in this repo pins its GitHub
|
||||
# Actions to an exact commit (a SHA), which is safe but freezes them in time.
|
||||
# Dependabot opens a small, reviewable pull request whenever a newer version
|
||||
# exists -- for Python packages, npm packages, the Docker base image, and the
|
||||
# pinned Actions themselves -- so staying patched does not require manual work.
|
||||
# Updates are grouped so a week's bumps arrive as one PR per ecosystem, not a
|
||||
# flood of separate ones.
|
||||
|
||||
version: 2
|
||||
updates:
|
||||
# Python dependencies (requirements.txt + requirements-optional.txt).
|
||||
- package-ecosystem: pip
|
||||
directory: "/"
|
||||
schedule:
|
||||
interval: weekly
|
||||
open-pull-requests-limit: 5
|
||||
groups:
|
||||
python:
|
||||
patterns: ["*"]
|
||||
|
||||
# Frontend / tooling npm packages (package.json).
|
||||
- package-ecosystem: npm
|
||||
directory: "/"
|
||||
schedule:
|
||||
interval: weekly
|
||||
open-pull-requests-limit: 5
|
||||
groups:
|
||||
npm:
|
||||
patterns: ["*"]
|
||||
|
||||
# The pinned action SHAs used across .github/workflows.
|
||||
- package-ecosystem: github-actions
|
||||
directory: "/"
|
||||
schedule:
|
||||
interval: weekly
|
||||
open-pull-requests-limit: 5
|
||||
groups:
|
||||
actions:
|
||||
patterns: ["*"]
|
||||
|
||||
# The Docker base image in the Dockerfile.
|
||||
- package-ecosystem: docker
|
||||
directory: "/"
|
||||
schedule:
|
||||
interval: weekly
|
||||
open-pull-requests-limit: 5
|
||||
@@ -1,123 +0,0 @@
|
||||
# Pull Request Review Template
|
||||
|
||||
Use this shape as a copyable reference for substantive PR reviews; GitHub does
|
||||
not auto-apply this file to review comments. Omit sections that do not add
|
||||
useful signal. Lead with confirmed findings; keep speculative notes out of the
|
||||
public review unless they are framed as a concrete open question.
|
||||
|
||||
## Small PR Path
|
||||
|
||||
For narrow docs, typo, test-only, or obvious local fixes, a short review is
|
||||
enough:
|
||||
|
||||
```md
|
||||
LGTM after checking:
|
||||
- scope:
|
||||
- validation:
|
||||
- residual risk:
|
||||
```
|
||||
|
||||
Use the fuller structure below for larger, risky, multi-finding, or
|
||||
security-sensitive reviews.
|
||||
|
||||
## Findings
|
||||
|
||||
**<sub><sub></sub></sub> issue (test): Short issue title**
|
||||
|
||||
- **Problem:** Concrete broken flow, contract, input, or risk.
|
||||
|
||||
- **Impact:** Why this matters to users, CI, maintainers, data, security, or scale.
|
||||
|
||||
- **Ask:** Smallest practical correction or decision the author should make.
|
||||
|
||||
- **Location:** `path:line`
|
||||
|
||||
## Open Questions
|
||||
|
||||
- **question (scope, non-blocking): Short author question** Ask the concrete
|
||||
intent, scope, or tradeoff question.
|
||||
|
||||
## Validation
|
||||
|
||||
- Ran:
|
||||
- Not run:
|
||||
- Residual risk:
|
||||
|
||||
## PR Hygiene
|
||||
|
||||
- Target/template/checks:
|
||||
- Related, duplicate, or superseding context:
|
||||
|
||||
## No Findings Variant
|
||||
|
||||
```md
|
||||
## Findings
|
||||
|
||||
none confirmed
|
||||
|
||||
## Validation
|
||||
|
||||
- Ran:
|
||||
- Not run:
|
||||
- Residual risk:
|
||||
```
|
||||
|
||||
## Legend
|
||||
|
||||
- **Findings:** Verified, author-actionable issues that should be fixed or
|
||||
consciously accepted before merge.
|
||||
- **Priority badges:** The shields.io badges below are optional formatting for
|
||||
priority labels. Plain `P0`, `P1`, `P2`, or `P3` text is also acceptable when
|
||||
an external image dependency is undesirable or may not render.
|
||||
- **P0:** `` -
|
||||
release-blocking or actively dangerous.
|
||||
- **P1:** `` -
|
||||
serious bug, security risk, data-loss risk, or broken primary flow.
|
||||
- **P2:** `` -
|
||||
meaningful correctness, test, maintainability, or edge-case issue.
|
||||
- **P3:** `` -
|
||||
minor polish or low-risk cleanup.
|
||||
- **Intent labels:**
|
||||
- **`issue`:** A confirmed defect, regression, broken contract, or concrete
|
||||
risk.
|
||||
- **`suggestion`:** A non-blocking improvement that would make the PR clearer,
|
||||
safer, or easier to maintain.
|
||||
- **`nit`:** A tiny, non-blocking cleanup or style note. Use it only when the
|
||||
author can safely ignore it without changing the review outcome.
|
||||
- **`question`:** A real author-facing clarification about intent, scope, or
|
||||
tradeoffs. Do not use questions to hide an issue that should be stated
|
||||
directly.
|
||||
- **`LGTM`:** "Looks good to me." Use only when the review found no blocking
|
||||
issues, or when any remaining notes are clearly optional.
|
||||
- **Decorations:** Optional labels in parentheses that clarify the finding type,
|
||||
scope, or merge impact.
|
||||
- **`security`:** Auth, authorization, ownership, secrets, SSRF, injection,
|
||||
unsafe external input, or other trust-boundary concerns.
|
||||
- **`test`:** Missing, failing, misleading, brittle, or insufficient tests.
|
||||
- **`scope`:** PR scope, feature boundaries, unrelated churn, or work that
|
||||
should be split into a separate issue or PR.
|
||||
- **`ci`:** CI configuration, workflow failures, flaky checks, or validation
|
||||
signal quality.
|
||||
- **`api`:** Route, request/response, public function, schema, persistence, or
|
||||
integration contract changes.
|
||||
- **`docs`:** User-facing docs, contributor docs, examples, or comments that
|
||||
need to change with the code.
|
||||
- **`non-blocking`:** Useful feedback that should not prevent merge by
|
||||
itself.
|
||||
- **Finding fields:**
|
||||
- **Problem:** What is wrong, what contract is ambiguous, or what risk the PR
|
||||
introduces.
|
||||
- **Impact:** Why the problem matters in practical terms.
|
||||
- **Ask:** The smallest concrete fix, test, or decision requested from the PR
|
||||
author.
|
||||
- **Location:** The most useful repo-relative file and line reference for the
|
||||
finding, using `path:line`.
|
||||
- **Optional sections:**
|
||||
- **Open Questions:** Genuine scope or intent questions; omit when there are
|
||||
no real questions.
|
||||
- **Validation:** What the reviewer ran, what was intentionally not run, and
|
||||
what risk remains after review.
|
||||
- **PR Hygiene:** Target-branch, template, CI/check, duplicate, related-work,
|
||||
or superseding-PR notes.
|
||||
- **`none confirmed`:** Use only when no review-worthy findings were confirmed;
|
||||
still list validation gaps or residual risk when relevant.
|
||||
@@ -19,10 +19,10 @@ jobs:
|
||||
name: Python syntax (compileall)
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
|
||||
with:
|
||||
persist-credentials: false
|
||||
- uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
|
||||
- uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
|
||||
with:
|
||||
python-version: "3.11"
|
||||
# Byte-compile sources — catches syntax errors without installing deps.
|
||||
@@ -32,10 +32,10 @@ jobs:
|
||||
name: JS syntax (node --check)
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
|
||||
with:
|
||||
persist-credentials: false
|
||||
- uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
|
||||
- uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
|
||||
with:
|
||||
node-version: "20"
|
||||
# Syntax-check our own JS (skip vendored libs in static/lib).
|
||||
@@ -54,7 +54,7 @@ jobs:
|
||||
# ROADMAP "fresh install smoke tests" item; make this required once green.
|
||||
continue-on-error: true
|
||||
steps:
|
||||
- uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
persist-credentials: false
|
||||
@@ -81,7 +81,7 @@ jobs:
|
||||
echo "docs_only=false" >> "$GITHUB_OUTPUT"
|
||||
fi
|
||||
|
||||
- uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
|
||||
- uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
|
||||
if: steps.docs-check.outputs.docs_only != 'true'
|
||||
with:
|
||||
python-version: "3.11"
|
||||
|
||||
@@ -1,52 +0,0 @@
|
||||
# Container security: Dockerfile lint
|
||||
#
|
||||
# Purpose: the Docker image is how most people run Odysseus, so it is part of
|
||||
# the attack surface. hadolint lints the Dockerfile for mistakes and insecure
|
||||
# patterns (running as root longer than needed, unpinned base image, bad apt
|
||||
# usage). Blocking.
|
||||
#
|
||||
# The image vulnerability scan (Trivy, advisory) lives in its own file,
|
||||
# container-trivy.yml. Keeping it separate lets that advisory scan be
|
||||
# path-filtered and held to a read-only token on pull requests without
|
||||
# weakening this blocking gate, which must always report so a required check
|
||||
# never hangs.
|
||||
#
|
||||
# Note: a separate open PR (#120) proposes a local `scripts/scan_image.py`.
|
||||
# This job is complementary -- it is a CI gate, not a script a contributor has
|
||||
# to remember to run.
|
||||
|
||||
name: Container scan
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
push:
|
||||
branches: [main]
|
||||
workflow_dispatch:
|
||||
|
||||
permissions: {}
|
||||
|
||||
concurrency:
|
||||
group: container-scan-${{ github.workflow }}-${{ github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
hadolint:
|
||||
name: hadolint (Dockerfile lint)
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: read
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Lint Dockerfile
|
||||
uses: hadolint/hadolint-action@2332a7b74a6de0dda2e2221d575162eba76ba5e5 # v3.3.0
|
||||
with:
|
||||
dockerfile: Dockerfile
|
||||
# DL3008: pinning apt package versions is impractical on a -slim base
|
||||
# image. Debian purges old package versions from its repos, so a
|
||||
# pinned version breaks future rebuilds. The base image itself is
|
||||
# what should be pinned (tracked by Dependabot's docker ecosystem).
|
||||
ignore: DL3008
|
||||
@@ -1,125 +0,0 @@
|
||||
# Container image vulnerability scan (advisory)
|
||||
#
|
||||
# Trivy builds the application image and scans it for known-vulnerable OS and
|
||||
# Python packages. Advisory only -- it reports findings to the repo's Security
|
||||
# tab without blocking a merge, because the image inevitably contains
|
||||
# already-known CVEs in upstream packages that are not this project's bug.
|
||||
#
|
||||
# Split from the Dockerfile lint (container-scan.yml) for two reasons:
|
||||
#
|
||||
# - Least privilege. The image build runs Dockerfile instructions, which on a
|
||||
# pull request are attacker-influenceable. That path (the `scan` job) is
|
||||
# held to a read-only token and never publishes results. Only `publish`,
|
||||
# which runs on push to main (curated, fast-forwarded from reviewed dev),
|
||||
# gets security-events:write to upload SARIF.
|
||||
# - Cost. Docs-only changes do not rebuild the image (paths-ignore below),
|
||||
# matching docker-publish.yml. hadolint stays on the broad trigger in
|
||||
# container-scan.yml so the blocking gate always reports.
|
||||
|
||||
name: Container scan (Trivy)
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
paths-ignore:
|
||||
- '**.md'
|
||||
- 'docs/**'
|
||||
- '.github/ISSUE_TEMPLATE/**'
|
||||
push:
|
||||
branches: [main]
|
||||
paths-ignore:
|
||||
- '**.md'
|
||||
- 'docs/**'
|
||||
- '.github/ISSUE_TEMPLATE/**'
|
||||
workflow_dispatch:
|
||||
|
||||
permissions: {}
|
||||
|
||||
concurrency:
|
||||
group: container-trivy-${{ github.workflow }}-${{ github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
# Pull requests and manual runs: build and scan under a read-only token.
|
||||
# The build executes PR-supplied Dockerfile instructions, so this job must
|
||||
# not hold any write scope, and it does not upload to the Security tab.
|
||||
scan:
|
||||
name: Trivy (image scan, advisory)
|
||||
if: github.event_name != 'push'
|
||||
runs-on: ubuntu-latest
|
||||
# Advisory: a CVE in an upstream package must not block a PR.
|
||||
continue-on-error: true
|
||||
permissions:
|
||||
contents: read
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Set up Buildx
|
||||
uses: docker/setup-buildx-action@d7f5e7f509e45cec5c76c4d5afdd7de93d0b3df5 # v4.1.0
|
||||
|
||||
# Build without pushing so a broken Dockerfile is caught here, and the
|
||||
# exact image we ship is what gets scanned.
|
||||
- name: Build image
|
||||
uses: docker/build-push-action@f9f3042f7e2789586610d6e8b85c8f03e5195baf # v7.2.0
|
||||
with:
|
||||
context: .
|
||||
push: false
|
||||
load: true
|
||||
tags: odysseus:ci
|
||||
|
||||
- name: Scan image with Trivy
|
||||
uses: aquasecurity/trivy-action@ed142fd0673e97e23eac54620cfb913e5ce36c25 # v0.36.0
|
||||
with:
|
||||
image-ref: odysseus:ci
|
||||
format: table
|
||||
ignore-unfixed: true
|
||||
env:
|
||||
# Pin the vuln DB source to GHCR to avoid rate-limited Docker Hub
|
||||
# mirrors that flake on shared runners.
|
||||
TRIVY_DB_REPOSITORY: ghcr.io/aquasecurity/trivy-db:2
|
||||
|
||||
# Push to main only: build, scan, and publish SARIF to the Security tab.
|
||||
# This is the only path that runs trusted code, so it is the only one granted
|
||||
# security-events:write.
|
||||
publish:
|
||||
name: Trivy (image scan + SARIF upload)
|
||||
if: github.event_name == 'push'
|
||||
runs-on: ubuntu-latest
|
||||
continue-on-error: true
|
||||
permissions:
|
||||
contents: read
|
||||
security-events: write # upload SARIF to the Security tab
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Set up Buildx
|
||||
uses: docker/setup-buildx-action@d7f5e7f509e45cec5c76c4d5afdd7de93d0b3df5 # v4.1.0
|
||||
|
||||
- name: Build image
|
||||
uses: docker/build-push-action@f9f3042f7e2789586610d6e8b85c8f03e5195baf # v7.2.0
|
||||
with:
|
||||
context: .
|
||||
push: false
|
||||
load: true
|
||||
tags: odysseus:ci
|
||||
|
||||
- name: Scan image with Trivy
|
||||
uses: aquasecurity/trivy-action@ed142fd0673e97e23eac54620cfb913e5ce36c25 # v0.36.0
|
||||
with:
|
||||
image-ref: odysseus:ci
|
||||
format: sarif
|
||||
output: trivy-results.sarif
|
||||
ignore-unfixed: true
|
||||
env:
|
||||
TRIVY_DB_REPOSITORY: ghcr.io/aquasecurity/trivy-db:2
|
||||
|
||||
- name: Upload Trivy results
|
||||
uses: github/codeql-action/upload-sarif@8aad20d150bbac5944a9f9d289da16a4b0d87c1e # v4.36.2
|
||||
with:
|
||||
sarif_file: trivy-results.sarif
|
||||
category: trivy-image
|
||||
@@ -1,71 +0,0 @@
|
||||
# Supply-chain review
|
||||
#
|
||||
# Purpose: defend against "side-chain" / supply-chain attacks -- a pull request
|
||||
# that adds (or bumps) a dependency to a version with a known vulnerability or a
|
||||
# disallowed license. Two layers:
|
||||
#
|
||||
# - dependency-review: runs ONLY on pull requests. It compares the
|
||||
# dependencies before and after the PR and blocks the merge if the change
|
||||
# pulls in a package with a known security advisory. This is the gate.
|
||||
# - pip-audit: scans the project's current Python requirements against the
|
||||
# advisory database. Advisory only (it never blocks a merge), because it can
|
||||
# flag a pre-existing issue in an already-shipped dependency.
|
||||
|
||||
name: Dependency review
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
push:
|
||||
branches: [main]
|
||||
workflow_dispatch:
|
||||
|
||||
# Default-deny token; jobs grant only read access.
|
||||
permissions: {}
|
||||
|
||||
concurrency:
|
||||
group: dependency-review-${{ github.workflow }}-${{ github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
dependency-review:
|
||||
name: dependency-review (PR gate)
|
||||
# Only meaningful on a pull request -- it needs a base..head diff to review.
|
||||
if: github.event_name == 'pull_request'
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: read
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Review dependency changes
|
||||
uses: actions/dependency-review-action@a1d282b36b6f3519aa1f3fc636f609c47dddb294 # v5.0.0
|
||||
with:
|
||||
# Fail the PR on any newly introduced moderate-or-worse advisory.
|
||||
fail-on-severity: moderate
|
||||
|
||||
pip-audit:
|
||||
name: pip-audit (advisory)
|
||||
runs-on: ubuntu-latest
|
||||
# Advisory: report known-vulnerable Python deps without blocking the merge.
|
||||
continue-on-error: true
|
||||
permissions:
|
||||
contents: read
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
|
||||
with:
|
||||
python-version: '3.12'
|
||||
|
||||
- name: Run pip-audit on requirements
|
||||
run: |
|
||||
set -euo pipefail
|
||||
pip install pip-audit==2.10.0
|
||||
pip-audit -r requirements.txt -r requirements-optional.txt --strict
|
||||
@@ -1,60 +0,0 @@
|
||||
# Secret scanning
|
||||
#
|
||||
# Purpose: stop credentials (API keys, tokens, passwords, private keys) from
|
||||
# ever living in the Git history. Odysseus deliberately keeps real secrets in
|
||||
# files that are gitignored (.env, data/), but a slip in a future commit -- or a
|
||||
# malicious pull request that sneaks one in -- would otherwise go unnoticed.
|
||||
# This job reads the repository and the full commit history and fails if it
|
||||
# finds anything that looks like a secret.
|
||||
#
|
||||
# It runs the official gitleaks BINARY directly (pinned to an exact version and
|
||||
# verified against the project's published SHA-256 checksum) rather than the
|
||||
# gitleaks GitHub Action, because the Action asks for a paid license on
|
||||
# organization-owned repos. The binary is free and behaves identically.
|
||||
|
||||
name: Secret scan
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
push:
|
||||
branches: [main]
|
||||
workflow_dispatch:
|
||||
|
||||
# Start with zero permissions; the single job opts back in to read-only.
|
||||
permissions: {}
|
||||
|
||||
concurrency:
|
||||
group: secret-scan-${{ github.workflow }}-${{ github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
gitleaks:
|
||||
name: gitleaks
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: read
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
with:
|
||||
# Full history so a secret committed in an earlier commit (and later
|
||||
# deleted) is still caught -- deletion does not remove it from Git.
|
||||
fetch-depth: 0
|
||||
persist-credentials: false
|
||||
|
||||
# Pinned version + checksum so a tampered release binary cannot run here.
|
||||
# Bump VERSION/SHA256 together; the checksum comes from the matching
|
||||
# gitleaks_<version>_checksums.txt on the GitHub release.
|
||||
- name: Run gitleaks (pinned, checksum-verified)
|
||||
env:
|
||||
GITLEAKS_VERSION: 8.30.1
|
||||
GITLEAKS_SHA256: 551f6fc83ea457d62a0d98237cbad105af8d557003051f41f3e7ca7b3f2470eb
|
||||
run: |
|
||||
set -euo pipefail
|
||||
TARBALL="gitleaks_${GITLEAKS_VERSION}_linux_x64.tar.gz"
|
||||
curl -fsSL -o "${TARBALL}" \
|
||||
"https://github.com/gitleaks/gitleaks/releases/download/v${GITLEAKS_VERSION}/${TARBALL}"
|
||||
echo "${GITLEAKS_SHA256} ${TARBALL}" | sha256sum -c -
|
||||
tar -xzf "${TARBALL}" gitleaks
|
||||
# Scan the whole history. Findings print to the log and fail the job.
|
||||
./gitleaks git --no-banner --redact --verbose .
|
||||
@@ -1,80 +0,0 @@
|
||||
# Workflow security (CI that audits the CI)
|
||||
#
|
||||
# Purpose: the GitHub Actions workflows themselves are an attack surface. A
|
||||
# poorly written workflow can leak the repository token, run attacker-supplied
|
||||
# code from a pull request, or pull in a tampered third-party action. These two
|
||||
# tools check every workflow file in this repo for those mistakes:
|
||||
#
|
||||
# - actionlint: catches workflow syntax errors and shell-script bugs inside
|
||||
# `run:` steps before they reach main.
|
||||
# - zizmor: a security linter for Actions. Flags template-injection holes,
|
||||
# unpinned actions, credential persistence, and over-broad token
|
||||
# permissions -- exactly the patterns the rest of this CI is built to avoid.
|
||||
#
|
||||
# Add this early: it then audits every workflow added after it.
|
||||
|
||||
name: Workflow security
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
push:
|
||||
branches: [main]
|
||||
workflow_dispatch:
|
||||
|
||||
# Default-deny token; each job grants only read access to the code.
|
||||
permissions: {}
|
||||
|
||||
concurrency:
|
||||
group: workflow-security-${{ github.workflow }}-${{ github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
actionlint:
|
||||
name: actionlint
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: read
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
# Pinned version + checksum so a tampered binary cannot run here.
|
||||
- name: Run actionlint (pinned, checksum-verified)
|
||||
env:
|
||||
ACTIONLINT_VERSION: 1.7.12
|
||||
ACTIONLINT_SHA256: 8aca8db96f1b94770f1b0d72b6dddcb1ebb8123cb3712530b08cc387b349a3d8
|
||||
run: |
|
||||
set -euo pipefail
|
||||
TARBALL="actionlint_${ACTIONLINT_VERSION}_linux_amd64.tar.gz"
|
||||
curl -fsSL -o "${TARBALL}" \
|
||||
"https://github.com/rhysd/actionlint/releases/download/v${ACTIONLINT_VERSION}/${TARBALL}"
|
||||
echo "${ACTIONLINT_SHA256} ${TARBALL}" | sha256sum -c -
|
||||
tar -xzf "${TARBALL}" actionlint
|
||||
./actionlint -color
|
||||
|
||||
zizmor:
|
||||
name: zizmor (Actions SAST)
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: read
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
|
||||
with:
|
||||
python-version: '3.12'
|
||||
|
||||
# Pinned zizmor release. --offline keeps the audit hermetic (no network
|
||||
# calls about the actions it inspects); --min-severity=low surfaces
|
||||
# everything so nothing slips through under the gate.
|
||||
- name: Run zizmor
|
||||
run: |
|
||||
set -euo pipefail
|
||||
pip install zizmor==1.25.2
|
||||
zizmor --offline --min-severity=low .github/workflows/
|
||||
-13
@@ -14,15 +14,6 @@ venv/
|
||||
.env
|
||||
.env.bak.*
|
||||
!.env.example
|
||||
# Local uv lockfile (optional, per-platform — see "Faster installs with uv" in README)
|
||||
requirements.lock
|
||||
|
||||
# SOPS workflow — encrypted `secrets.env` is intentionally committable,
|
||||
# but every variant (plaintext, manual decrypt copy, editor backup)
|
||||
# must stay out of git. Mirrored in .dockerignore so the same artifacts
|
||||
# also cannot enter image build layers.
|
||||
secrets.env.*
|
||||
!secrets.env.example
|
||||
|
||||
# Data — all user data stays local
|
||||
data/
|
||||
@@ -70,9 +61,6 @@ output.txt.txt
|
||||
*.tiff
|
||||
*.pdf
|
||||
|
||||
# …except shipped static assets
|
||||
!static/icons/*.png
|
||||
|
||||
# …except shipped demo assets in docs/ that the README links to.
|
||||
!docs/*.jpg
|
||||
!docs/*.jpeg
|
||||
@@ -101,4 +89,3 @@ docs/windows-port/
|
||||
compound.config.json
|
||||
*.error.log
|
||||
_scratch/
|
||||
/odysseus/
|
||||
|
||||
+1
-1
@@ -1,4 +1,4 @@
|
||||
FROM python:3.14-slim
|
||||
FROM python:3.12-slim
|
||||
|
||||
# System deps. tmux is required by Cookbook for background downloads/serves.
|
||||
# openssh-client is required for Cookbook remote server tests, setup, probes,
|
||||
|
||||
@@ -1,235 +1,21 @@
|
||||
GNU AFFERO GENERAL PUBLIC LICENSE
|
||||
Version 3, 19 November 2007
|
||||
|
||||
Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
|
||||
|
||||
Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed.
|
||||
|
||||
Preamble
|
||||
|
||||
The GNU Affero General Public License is a free, copyleft license for software and other kinds of works, specifically designed to ensure cooperation with the community in the case of network server software.
|
||||
|
||||
The licenses for most software and other practical works are designed to take away your freedom to share and change the works. By contrast, our General Public Licenses are intended to guarantee your freedom to share and change all versions of a program--to make sure it remains free software for all its users.
|
||||
|
||||
When we speak of free software, we are referring to freedom, not price. Our General Public Licenses are designed to make sure that you have the freedom to distribute copies of free software (and charge for them if you wish), that you receive source code or can get it if you want it, that you can change the software or use pieces of it in new free programs, and that you know you can do these things.
|
||||
|
||||
Developers that use our General Public Licenses protect your rights with two steps: (1) assert copyright on the software, and (2) offer you this License which gives you legal permission to copy, distribute and/or modify the software.
|
||||
|
||||
A secondary benefit of defending all users' freedom is that improvements made in alternate versions of the program, if they receive widespread use, become available for other developers to incorporate. Many developers of free software are heartened and encouraged by the resulting cooperation. However, in the case of software used on network servers, this result may fail to come about. The GNU General Public License permits making a modified version and letting the public access it on a server without ever releasing its source code to the public.
|
||||
|
||||
The GNU Affero General Public License is designed specifically to ensure that, in such cases, the modified source code becomes available to the community. It requires the operator of a network server to provide the source code of the modified version running there to the users of that server. Therefore, public use of a modified version, on a publicly accessible server, gives the public access to the source code of the modified version.
|
||||
|
||||
An older license, called the Affero General Public License and published by Affero, was designed to accomplish similar goals. This is a different license, not a version of the Affero GPL, but Affero has released a new version of the Affero GPL which permits relicensing under this license.
|
||||
|
||||
The precise terms and conditions for copying, distribution and modification follow.
|
||||
|
||||
TERMS AND CONDITIONS
|
||||
|
||||
0. Definitions.
|
||||
|
||||
"This License" refers to version 3 of the GNU Affero General Public License.
|
||||
|
||||
"Copyright" also means copyright-like laws that apply to other kinds of works, such as semiconductor masks.
|
||||
|
||||
"The Program" refers to any copyrightable work licensed under this License. Each licensee is addressed as "you". "Licensees" and "recipients" may be individuals or organizations.
|
||||
|
||||
To "modify" a work means to copy from or adapt all or part of the work in a fashion requiring copyright permission, other than the making of an exact copy. The resulting work is called a "modified version" of the earlier work or a work "based on" the earlier work.
|
||||
|
||||
A "covered work" means either the unmodified Program or a work based on the Program.
|
||||
|
||||
To "propagate" a work means to do anything with it that, without permission, would make you directly or secondarily liable for infringement under applicable copyright law, except executing it on a computer or modifying a private copy. Propagation includes copying, distribution (with or without modification), making available to the public, and in some countries other activities as well.
|
||||
|
||||
To "convey" a work means any kind of propagation that enables other parties to make or receive copies. Mere interaction with a user through a computer network, with no transfer of a copy, is not conveying.
|
||||
|
||||
An interactive user interface displays "Appropriate Legal Notices" to the extent that it includes a convenient and prominently visible feature that (1) displays an appropriate copyright notice, and (2) tells the user that there is no warranty for the work (except to the extent that warranties are provided), that licensees may convey the work under this License, and how to view a copy of this License. If the interface presents a list of user commands or options, such as a menu, a prominent item in the list meets this criterion.
|
||||
|
||||
1. Source Code.
|
||||
The "source code" for a work means the preferred form of the work for making modifications to it. "Object code" means any non-source form of a work.
|
||||
|
||||
A "Standard Interface" means an interface that either is an official standard defined by a recognized standards body, or, in the case of interfaces specified for a particular programming language, one that is widely used among developers working in that language.
|
||||
|
||||
The "System Libraries" of an executable work include anything, other than the work as a whole, that (a) is included in the normal form of packaging a Major Component, but which is not part of that Major Component, and (b) serves only to enable use of the work with that Major Component, or to implement a Standard Interface for which an implementation is available to the public in source code form. A "Major Component", in this context, means a major essential component (kernel, window system, and so on) of the specific operating system (if any) on which the executable work runs, or a compiler used to produce the work, or an object code interpreter used to run it.
|
||||
|
||||
The "Corresponding Source" for a work in object code form means all the source code needed to generate, install, and (for an executable work) run the object code and to modify the work, including scripts to control those activities. However, it does not include the work's System Libraries, or general-purpose tools or generally available free programs which are used unmodified in performing those activities but which are not part of the work. For example, Corresponding Source includes interface definition files associated with source files for the work, and the source code for shared libraries and dynamically linked subprograms that the work is specifically designed to require, such as by intimate data communication or control flow between those
|
||||
subprograms and other parts of the work.
|
||||
|
||||
The Corresponding Source need not include anything that users can regenerate automatically from other parts of the Corresponding Source.
|
||||
|
||||
The Corresponding Source for a work in source code form is that same work.
|
||||
|
||||
2. Basic Permissions.
|
||||
All rights granted under this License are granted for the term of copyright on the Program, and are irrevocable provided the stated conditions are met. This License explicitly affirms your unlimited permission to run the unmodified Program. The output from running a covered work is covered by this License only if the output, given its content, constitutes a covered work. This License acknowledges your rights of fair use or other equivalent, as provided by copyright law.
|
||||
|
||||
You may make, run and propagate covered works that you do not convey, without conditions so long as your license otherwise remains in force. You may convey covered works to others for the sole purpose of having them make modifications exclusively for you, or provide you with facilities for running those works, provided that you comply with the terms of this License in conveying all material for which you do not control copyright. Those thus making or running the covered works for you must do so exclusively on your behalf, under your direction and control, on terms that prohibit them from making any copies of your copyrighted material outside their relationship with you.
|
||||
|
||||
Conveying under any other circumstances is permitted solely under the conditions stated below. Sublicensing is not allowed; section 10 makes it unnecessary.
|
||||
|
||||
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
|
||||
No covered work shall be deemed part of an effective technological measure under any applicable law fulfilling obligations under article 11 of the WIPO copyright treaty adopted on 20 December 1996, or similar laws prohibiting or restricting circumvention of such measures.
|
||||
|
||||
When you convey a covered work, you waive any legal power to forbid circumvention of technological measures to the extent such circumvention is effected by exercising rights under this License with respect to the covered work, and you disclaim any intention to limit operation or modification of the work as a means of enforcing, against the work's users, your or third parties' legal rights to forbid circumvention of technological measures.
|
||||
|
||||
4. Conveying Verbatim Copies.
|
||||
You may convey verbatim copies of the Program's source code as you receive it, in any medium, provided that you conspicuously and appropriately publish on each copy an appropriate copyright notice; keep intact all notices stating that this License and any non-permissive terms added in accord with section 7 apply to the code; keep intact all notices of the absence of any warranty; and give all recipients a copy of this License along with the Program.
|
||||
|
||||
You may charge any price or no price for each copy that you convey, and you may offer support or warranty protection for a fee.
|
||||
|
||||
5. Conveying Modified Source Versions.
|
||||
You may convey a work based on the Program, or the modifications to produce it from the Program, in the form of source code under the terms of section 4, provided that you also meet all of these conditions:
|
||||
|
||||
a) The work must carry prominent notices stating that you modified it, and giving a relevant date.
|
||||
|
||||
b) The work must carry prominent notices stating that it is released under this License and any conditions added under section 7. This requirement modifies the requirement in section 4 to "keep intact all notices".
|
||||
|
||||
c) You must license the entire work, as a whole, under this License to anyone who comes into possession of a copy. This License will therefore apply, along with any applicable section 7 additional terms, to the whole of the work, and all its parts, regardless of how they are packaged. This License gives no permission to license the work in any other way, but it does not invalidate such permission if you have separately received it.
|
||||
|
||||
d) If the work has interactive user interfaces, each must display Appropriate Legal Notices; however, if the Program has interactive interfaces that do not display Appropriate Legal Notices, your work need not make them do so.
|
||||
|
||||
A compilation of a covered work with other separate and independent works, which are not by their nature extensions of the covered work, and which are not combined with it such as to form a larger program, in or on a volume of a storage or distribution medium, is called an "aggregate" if the compilation and its resulting copyright are not used to limit the access or legal rights of the compilation's users beyond what the individual works permit. Inclusion of a covered work in an aggregate does not cause this License to apply to the other parts of the aggregate.
|
||||
|
||||
6. Conveying Non-Source Forms.
|
||||
You may convey a covered work in object code form under the terms of sections 4 and 5, provided that you also convey the machine-readable Corresponding Source under the terms of this License, in one of these ways:
|
||||
|
||||
a) Convey the object code in, or embodied in, a physical product (including a physical distribution medium), accompanied by the Corresponding Source fixed on a durable physical medium customarily used for software interchange.
|
||||
|
||||
b) Convey the object code in, or embodied in, a physical product (including a physical distribution medium), accompanied by a written offer, valid for at least three years and valid for as long as you offer spare parts or customer support for that product model, to give anyone who possesses the object code either (1) a copy of the Corresponding Source for all the software in the product that is covered by this License, on a durable physical medium customarily used for software interchange, for a price no more than your reasonable cost of physically performing this conveying of source, or (2) access to copy the Corresponding Source from a network server at no charge.
|
||||
|
||||
c) Convey individual copies of the object code with a copy of the written offer to provide the Corresponding Source. This alternative is allowed only occasionally and noncommercially, and only if you received the object code with such an offer, in accord with subsection 6b.
|
||||
|
||||
d) Convey the object code by offering access from a designated place (gratis or for a charge), and offer equivalent access to the Corresponding Source in the same way through the same place at no further charge. You need not require recipients to copy the Corresponding Source along with the object code. If the place to copy the object code is a network server, the Corresponding Source may be on a different server (operated by you or a third party) that supports equivalent copying facilities, provided you maintain clear directions next to the object code saying where to find the Corresponding Source. Regardless of what server hosts the Corresponding Source, you remain obligated to ensure that it is available for as long as needed to satisfy these requirements.
|
||||
|
||||
e) Convey the object code using peer-to-peer transmission, provided you inform other peers where the object code and Corresponding Source of the work are being offered to the general public at no charge under subsection 6d.
|
||||
|
||||
A separable portion of the object code, whose source code is excluded from the Corresponding Source as a System Library, need not be included in conveying the object code work.
|
||||
|
||||
A "User Product" is either (1) a "consumer product", which means any tangible personal property which is normally used for personal, family, or household purposes, or (2) anything designed or sold for incorporation into a dwelling. In determining whether a product is a consumer product, doubtful cases shall be resolved in favor of coverage. For a particular product received by a particular user, "normally used" refers to a typical or common use of that class of product, regardless of the status of the particular user or of the way in which the particular user actually uses, or expects or is expected to use, the product. A product is a consumer product regardless of whether the product has substantial commercial, industrial or non-consumer uses, unless such uses represent the only significant mode of use of the product.
|
||||
|
||||
"Installation Information" for a User Product means any methods, procedures, authorization keys, or other information required to install and execute modified versions of a covered work in that User Product from a modified version of its Corresponding Source. The information must suffice to ensure that the continued functioning of the modified object code is in no case prevented or interfered with solely because modification has been made.
|
||||
|
||||
If you convey an object code work under this section in, or with, or specifically for use in, a User Product, and the conveying occurs as part of a transaction in which the right of possession and use of the User Product is transferred to the recipient in perpetuity or for a fixed term (regardless of how the transaction is characterized), the Corresponding Source conveyed under this section must be accompanied by the Installation Information. But this requirement does not apply if neither you nor any third party retains the ability to install modified object code on the User Product (for example, the work has been installed in ROM).
|
||||
|
||||
The requirement to provide Installation Information does not include a requirement to continue to provide support service, warranty, or updates for a work that has been modified or installed by the recipient, or for the User Product in which it has been modified or installed. Access to a network may be denied when the modification itself materially and adversely affects the operation of the network or violates the rules and protocols for communication across the network.
|
||||
|
||||
Corresponding Source conveyed, and Installation Information provided, in accord with this section must be in a format that is publicly documented (and with an implementation available to the public in source code form), and must require no special password or key for unpacking, reading or copying.
|
||||
|
||||
7. Additional Terms.
|
||||
"Additional permissions" are terms that supplement the terms of this License by making exceptions from one or more of its conditions. Additional permissions that are applicable to the entire Program shall be treated as though they were included in this License, to the extent that they are valid under applicable law. If additional permissions apply only to part of the Program, that part may be used separately under those permissions, but the entire Program remains governed by this License without regard to the additional permissions.
|
||||
|
||||
When you convey a copy of a covered work, you may at your option remove any additional permissions from that copy, or from any part of it. (Additional permissions may be written to require their own removal in certain cases when you modify the work.) You may place additional permissions on material, added by you to a covered work, for which you have or can give appropriate copyright permission.
|
||||
|
||||
Notwithstanding any other provision of this License, for material you add to a covered work, you may (if authorized by the copyright holders of that material) supplement the terms of this License with terms:
|
||||
|
||||
a) Disclaiming warranty or limiting liability differently from the terms of sections 15 and 16 of this License; or
|
||||
|
||||
b) Requiring preservation of specified reasonable legal notices or author attributions in that material or in the Appropriate Legal Notices displayed by works containing it; or
|
||||
|
||||
c) Prohibiting misrepresentation of the origin of that material, or requiring that modified versions of such material be marked in reasonable ways as different from the original version; or
|
||||
|
||||
d) Limiting the use for publicity purposes of names of licensors or authors of the material; or
|
||||
|
||||
e) Declining to grant rights under trademark law for use of some trade names, trademarks, or service marks; or
|
||||
|
||||
f) Requiring indemnification of licensors and authors of that material by anyone who conveys the material (or modified versions of it) with contractual assumptions of liability to the recipient, for any liability that these contractual assumptions directly impose on those licensors and authors.
|
||||
|
||||
All other non-permissive additional terms are considered "further restrictions" within the meaning of section 10. If the Program as you received it, or any part of it, contains a notice stating that it is governed by this License along with a term that is a further restriction, you may remove that term. If a license document contains a further restriction but permits relicensing or conveying under this License, you may add to a covered work material governed by the terms of that license document, provided that the further restriction does not survive such relicensing or conveying.
|
||||
|
||||
If you add terms to a covered work in accord with this section, you must place, in the relevant source files, a statement of the additional terms that apply to those files, or a notice indicating where to find the applicable terms.
|
||||
|
||||
Additional terms, permissive or non-permissive, may be stated in the form of a separately written license, or stated as exceptions; the above requirements apply either way.
|
||||
|
||||
8. Termination.
|
||||
|
||||
You may not propagate or modify a covered work except as expressly provided under this License. Any attempt otherwise to propagate or modify it is void, and will automatically terminate your rights under this License (including any patent licenses granted under the third paragraph of section 11).
|
||||
|
||||
However, if you cease all violation of this License, then your license from a particular copyright holder is reinstated (a) provisionally, unless and until the copyright holder explicitly and finally terminates your license, and (b) permanently, if the copyright holder fails to notify you of the violation by some reasonable means prior to 60 days after the cessation.
|
||||
|
||||
Moreover, your license from a particular copyright holder is reinstated permanently if the copyright holder notifies you of the violation by some reasonable means, this is the first time you have received notice of violation of this License (for any work) from that copyright holder, and you cure the violation prior to 30 days after your receipt of the notice.
|
||||
|
||||
Termination of your rights under this section does not terminate the licenses of parties who have received copies or rights from you under this License. If your rights have been terminated and not permanently reinstated, you do not qualify to receive new licenses for the same material under section 10.
|
||||
|
||||
9. Acceptance Not Required for Having Copies.
|
||||
|
||||
You are not required to accept this License in order to receive or run a copy of the Program. Ancillary propagation of a covered work occurring solely as a consequence of using peer-to-peer transmission to receive a copy likewise does not require acceptance. However, nothing other than this License grants you permission to propagate or modify any covered work. These actions infringe copyright if you do not accept this License. Therefore, by modifying or propagating a covered work, you indicate your acceptance of this License to do so.
|
||||
|
||||
10. Automatic Licensing of Downstream Recipients.
|
||||
|
||||
Each time you convey a covered work, the recipient automatically receives a license from the original licensors, to run, modify and propagate that work, subject to this License. You are not responsible for enforcing compliance by third parties with this License.
|
||||
|
||||
An "entity transaction" is a transaction transferring control of an organization, or substantially all assets of one, or subdividing an organization, or merging organizations. If propagation of a covered work results from an entity transaction, each party to that transaction who receives a copy of the work also receives whatever licenses to the work the party's predecessor in interest had or could give under the previous paragraph, plus a right to possession of the Corresponding Source of the work from the predecessor in interest, if the predecessor has it or can get it with reasonable efforts.
|
||||
|
||||
You may not impose any further restrictions on the exercise of the rights granted or affirmed under this License. For example, you may not impose a license fee, royalty, or other charge for exercise of rights granted under this License, and you may not initiate litigation (including a cross-claim or counterclaim in a lawsuit) alleging that any patent claim is infringed by making, using, selling, offering for sale, or importing the Program or any portion of it.
|
||||
|
||||
11. Patents.
|
||||
|
||||
A "contributor" is a copyright holder who authorizes use under this License of the Program or a work on which the Program is based. The work thus licensed is called the contributor's "contributor version".
|
||||
|
||||
A contributor's "essential patent claims" are all patent claims owned or controlled by the contributor, whether already acquired or hereafter acquired, that would be infringed by some manner, permitted by this License, of making, using, or selling its contributor version, but do not include claims that would be infringed only as a consequence of further modification of the contributor version. For purposes of this definition, "control" includes the right to grant patent sublicenses in a manner consistent with the requirements of this License.
|
||||
|
||||
Each contributor grants you a non-exclusive, worldwide, royalty-free patent license under the contributor's essential patent claims, to make, use, sell, offer for sale, import and otherwise run, modify and propagate the contents of its contributor version.
|
||||
|
||||
In the following three paragraphs, a "patent license" is any express agreement or commitment, however denominated, not to enforce a patent (such as an express permission to practice a patent or covenant not to sue for patent infringement). To "grant" such a patent license to a party means to make such an agreement or commitment not to enforce a patent against the party.
|
||||
|
||||
If you convey a covered work, knowingly relying on a patent license, and the Corresponding Source of the work is not available for anyone to copy, free of charge and under the terms of this License, through a publicly available network server or other readily accessible means, then you must either (1) cause the Corresponding Source to be so available, or (2) arrange to deprive yourself of the benefit of the patent license for this particular work, or (3) arrange, in a manner consistent with the requirements of this License, to extend the patent
|
||||
license to downstream recipients. "Knowingly relying" means you have actual knowledge that, but for the patent license, your conveying the covered work in a country, or your recipient's use of the covered work in a country, would infringe one or more identifiable patents in that country that you have reason to believe are valid.
|
||||
|
||||
If, pursuant to or in connection with a single transaction or arrangement, you convey, or propagate by procuring conveyance of, a covered work, and grant a patent license to some of the parties receiving the covered work authorizing them to use, propagate, modify or convey a specific copy of the covered work, then the patent license you grant is automatically extended to all recipients of the covered work and works based on it.
|
||||
|
||||
A patent license is "discriminatory" if it does not include within the scope of its coverage, prohibits the exercise of, or is conditioned on the non-exercise of one or more of the rights that are specifically granted under this License. You may not convey a covered work if you are a party to an arrangement with a third party that is in the business of distributing software, under which you make payment to the third party based on the extent of your activity of conveying the work, and under which the third party grants, to any of the parties who would receive the covered work from you, a discriminatory patent license (a) in connection with copies of the covered work conveyed by you (or copies made from those copies), or (b) primarily for and in connection with specific products or compilations that contain the covered work, unless you entered into that arrangement, or that patent license was granted, prior to 28 March 2007.
|
||||
|
||||
Nothing in this License shall be construed as excluding or limiting any implied license or other defenses to infringement that may otherwise be available to you under applicable patent law.
|
||||
|
||||
12. No Surrender of Others' Freedom.
|
||||
|
||||
If conditions are imposed on you (whether by court order, agreement or otherwise) that contradict the conditions of this License, they do not excuse you from the conditions of this License. If you cannot convey a covered work so as to satisfy simultaneously your obligations under this License and any other pertinent obligations, then as a consequence you may
|
||||
not convey it at all. For example, if you agree to terms that obligate you to collect a royalty for further conveying from those to whom you convey the Program, the only way you could satisfy both those terms and this License would be to refrain entirely from conveying the Program.
|
||||
|
||||
13. Remote Network Interaction; Use with the GNU General Public License.
|
||||
|
||||
Notwithstanding any other provision of this License, if you modify the Program, your modified version must prominently offer all users interacting with it remotely through a computer network (if your version supports such interaction) an opportunity to receive the Corresponding Source of your version by providing access to the Corresponding Source from a network server at no charge, through some standard or customary means of facilitating copying of software. This Corresponding Source shall include the Corresponding Source for any work covered by version 3 of the GNU General Public License that is incorporated pursuant to the following paragraph.
|
||||
|
||||
Notwithstanding any other provision of this License, you have permission to link or combine any covered work with a work licensed under version 3 of the GNU General Public License into a single combined work, and to convey the resulting work. The terms of this License will continue to apply to the part which is the covered work, but the work with which it is combined will remain governed by version 3 of the GNU General Public License.
|
||||
|
||||
14. Revised Versions of this License.
|
||||
|
||||
The Free Software Foundation may publish revised and/or new versions of the GNU Affero General Public License from time to time. Such new versions will be similar in spirit to the present version, but may differ in detail to address new problems or concerns.
|
||||
|
||||
Each version is given a distinguishing version number. If the Program specifies that a certain numbered version of the GNU Affero General Public License "or any later version" applies to it, you have the option of following the terms and conditions either of that numbered version or of any later version published by the Free Software Foundation. If the Program does not specify a version number of the GNU Affero General Public License, you may choose any version ever published by the Free Software Foundation.
|
||||
|
||||
If the Program specifies that a proxy can decide which future versions of the GNU Affero General Public License can be used, that proxy's public statement of acceptance of a version permanently authorizes you to choose that version for the Program.
|
||||
|
||||
Later license versions may give you additional or different permissions. However, no additional obligations are imposed on any author or copyright holder as a result of your choosing to follow a later version.
|
||||
|
||||
15. Disclaimer of Warranty.
|
||||
|
||||
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
|
||||
|
||||
16. Limitation of Liability.
|
||||
|
||||
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
|
||||
|
||||
17. Interpretation of Sections 15 and 16.
|
||||
|
||||
If the disclaimer of warranty and limitation of liability provided above cannot be given local legal effect according to their terms, reviewing courts shall apply local law that most closely approximates an absolute waiver of all civil liability in connection with the Program, unless a warranty or assumption of liability accompanies a copy of the Program in return for a fee.
|
||||
|
||||
END OF TERMS AND CONDITIONS
|
||||
|
||||
How to Apply These Terms to Your New Programs
|
||||
|
||||
If you develop a new program, and you want it to be of the greatest possible use to the public, the best way to achieve this is to make it free software which everyone can redistribute and change under these terms.
|
||||
|
||||
To do so, attach the following notices to the program. It is safest to attach them to the start of each source file to most effectively state the exclusion of warranty; and each file should have at least the "copyright" line and a pointer to where the full notice is found.
|
||||
|
||||
<one line to give the program's name and a brief idea of what it does.>
|
||||
Copyright (C) <year> <name of author>
|
||||
|
||||
This program is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
|
||||
|
||||
This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public License for more details.
|
||||
|
||||
You should have received a copy of the GNU Affero General Public License along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
Also add information on how to contact you by electronic and paper mail.
|
||||
|
||||
If your software can interact with users remotely through a computer network, you should also make sure that it provides a way for users to get its source. For example, if your program is a web application, its interface could display a "Source" link that leads users to an archive of the code. There are many ways you could offer source, and different solutions will be better for different programs; see section 13 for the specific requirements.
|
||||
|
||||
You should also get your employer (if you work as a programmer) or school, if any, to sign a "copyright disclaimer" for the program, if necessary. For more information on this, and how to apply and follow the GNU AGPL, see <http://www.gnu.org/licenses/>.
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2025 Odysseus Contributors
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
|
||||
@@ -1,65 +1,444 @@
|
||||
<p align="center">
|
||||
<img src="docs/odysseus-wordmark.png" alt="Odysseus" width="280">
|
||||
</p>
|
||||
# Odysseus
|
||||
|
||||
<p align="center">
|
||||
A self-hosted AI workspace for chat, agents, research, documents, email, notes, calendar, and local model workflows.
|
||||
</p>
|
||||
> **Branch note:** `dev` is the default branch and contains the latest development changes, but it may be unstable. For the more stable curated branch, use [`main`](https://github.com/pewdiepie-archdaemon/odysseus/tree/main).
|
||||
|
||||
<p align="center">
|
||||
<a href="#quick-start">Quick Start</a> ·
|
||||
<a href="docs/setup.md">Setup Guide</a> ·
|
||||
<a href="CONTRIBUTING.md">Contributing</a> ·
|
||||
<a href="ROADMAP.md">Roadmap</a>
|
||||
</p>
|
||||
```
|
||||
───────────────────────────────────────────────
|
||||
⊹ ࣪ ˖ ૮( ˶ᵔ ᵕ ᵔ˶ )っ Odysseus vers. 1.0
|
||||
───────────────────────────────────────────────
|
||||
```
|
||||
|
||||
<p align="center">
|
||||
<a href="https://repology.org/project/odysseus-ai/versions"><img src="https://repology.org/badge/vertical-allrepos/odysseus-ai.svg" alt="Packaging status"></a>
|
||||
</p>
|
||||
|
||||
|
||||
<p align="center">
|
||||
<img src="docs/odysseus.jpg" alt="Odysseus interface">
|
||||
</p>
|
||||
A self-hosted AI workspace -- meant to be the self-hosted version of the UI experience you get from ChatGPT and Claude. But with more jank and fun. Running on your own hardware, with your own data -- local-first, privacy-first, and no trojan.
|
||||
|
||||
---
|
||||
## Features
|
||||
- **Chat** -- chat with any local model or API; adding them is super simple.<br> <sub>vLLM · llama.cpp · Ollama · OpenRouter · OpenAI · GitHub Copilot</sub>
|
||||
- **Agent** -- hand it tools and let it run the whole task itself.<br> <sub>built on [opencode](https://github.com/anomalyco/opencode) · MCP · web · files · shell · skills · memory</sub>
|
||||
- **Cookbook** -- Scans your hardware, recommends models, click to download and serve.. easy!<br> <sub>built on [llmfit](https://github.com/AlexsJones/llmfit) · VRAM-aware · GGUF / FP8 / AWQ · fit scoring · vLLM / llama.cpp serving</sub>
|
||||
- **Deep Research** -- multi-step runs that gather, read, and synthesize sources into a nice visual report.<br> <sub>adapted from [Tongyi DeepResearch](https://github.com/Alibaba-NLP/DeepResearch)</sub>
|
||||
- **Compare** -- a fun tool to compare models side by side. Test completely blind, no bias!<br> <sub>multi-model · blind test · synthesis</sub>
|
||||
- **Documents** -- YOU write the text, AI is there to assist, not the opposite.<br> <sub>multi-tab editor · markdown · HTML · CSV · syntax highlighting · AI edits · suggestions</sub>
|
||||
- **Memory / Skills** -- Persistent memory and skills, your agent evolves over time as it better understands you and your tasks!<br> <sub>ChromaDB · fastembed (ONNX) · vector + keyword retrieval · import/export</sub>
|
||||
- **Email** -- IMAP/SMTP inbox with AI triage built in: urgency reminders, auto-tag, auto-summary, auto-reply drafts, auto-spam.<br> <sub>IMAP · SMTP · per-account routing · CalDAV-aware</sub>
|
||||
- **Notes & Tasks** -- Quick notes with reminders, a todo list, and scheduled tasks the agent can act on.<br> <sub>note pings · checklist · cron-style tasks · ntfy / browser / email channels</sub>
|
||||
- **Calendar** -- Local-first calendar with CalDAV sync to Radicale / Nextcloud / Apple / Fastmail.<br> <sub>CalDAV pull · .ics import/export · per-calendar colors · agent-aware</sub>
|
||||
- **Works on mobile** -- looks and runs great on your phone, not just desktop.<br> <sub>responsive · installable (PWA) · touch gestures</sub>
|
||||
- **Extras** -- more to explore, happy if you give it a go!<br> <sub>image editor · theme editor · file uploads (vision + PDF) · web search · presets · sessions · 2FA</sub>
|
||||
|
||||
## Demo
|
||||
A full, hover-to-play tour lives on the landing page (`docs/index.html`).
|
||||
|
||||
<details>
|
||||
<summary>Screenshots / clips</summary>
|
||||
|
||||
### Chat & Agents
|
||||
|
||||
### Deep Research
|
||||
|
||||
### Compare
|
||||
|
||||
### Documents
|
||||
|
||||
### Notes & Tasks
|
||||
|
||||
|
||||
</details>
|
||||
|
||||
## Quick Start
|
||||
|
||||
> `dev` is the default branch and gets the newest changes first. Use [`main`](https://github.com/pewdiepie-archdaemon/odysseus/tree/main) if you want the more curated branch.
|
||||
Defaults work out of the box: clone, run, then configure models/search/email
|
||||
inside **Settings**. Only edit `.env` for deployment-level overrides like
|
||||
`APP_BIND`, `APP_PORT`, `AUTH_ENABLED`, `DATABASE_URL`, or a pre-seeded admin password.
|
||||
|
||||
On first setup, Odysseus creates an admin account (`admin` unless
|
||||
`ODYSSEUS_ADMIN_USER` is set) and prints a temporary password in the terminal.
|
||||
For Docker installs, the same line is in `docker compose logs odysseus`.
|
||||
Use that for the first login, then change it in **Settings**.
|
||||
|
||||
Contributing? See [CONTRIBUTING.md](CONTRIBUTING.md) for setup, testing, and
|
||||
pull request guidelines.
|
||||
|
||||
### Docker (recommended)
|
||||
```bash
|
||||
git clone https://github.com/pewdiepie-archdaemon/odysseus.git
|
||||
cd odysseus
|
||||
cp .env.example .env # optional, but recommended for explicit defaults
|
||||
docker compose up -d --build
|
||||
```
|
||||
To include optional extras in the image (PDF viewer, Office extraction; includes AGPL PyMuPDF), build with `docker compose build --build-arg INSTALL_OPTIONAL=true` before `up`.
|
||||
|
||||
Open `http://localhost:7000` when the containers are healthy. Docker Compose
|
||||
binds the web UI to `127.0.0.1` by default. If the port is taken, set
|
||||
`APP_PORT=7001` in `.env` and recreate the container. Set `APP_BIND=0.0.0.0`
|
||||
only when you intentionally want LAN/reverse-proxy access.
|
||||
|
||||
### Native Linux / macOS
|
||||
```bash
|
||||
git clone https://github.com/pewdiepie-archdaemon/odysseus.git
|
||||
cd odysseus
|
||||
python3 -m venv venv
|
||||
source venv/bin/activate
|
||||
pip install -r requirements.txt
|
||||
python setup.py
|
||||
python -m uvicorn app:app --host 127.0.0.1 --port 7000
|
||||
```
|
||||
Requirements: Python 3.11+. Cookbook also needs `tmux` for background model
|
||||
downloads and serves. The app itself is lightweight; local model serving is the
|
||||
heavy part and depends on the model, runtime, GPU, and VRAM, so small hosts can
|
||||
connect to API or remote model servers instead. Use `--host 0.0.0.0` only when you intentionally want LAN/reverse-proxy access.
|
||||
|
||||
### Apple Silicon
|
||||
Docker on macOS cannot use the Metal GPU. For GPU-accelerated Cookbook on an
|
||||
M-series Mac, run Odysseus natively:
|
||||
|
||||
```bash
|
||||
git clone https://github.com/pewdiepie-archdaemon/odysseus.git
|
||||
cd odysseus
|
||||
cp .env.example .env
|
||||
docker compose up -d --build
|
||||
./start-macos.sh
|
||||
```
|
||||
|
||||
Open `http://localhost:7000` when the containers are healthy. The first admin password is printed in `docker compose logs odysseus`.
|
||||
It launches at `http://127.0.0.1:7860`. To expose it to your phone over a trusted LAN/VPN such as Tailscale, bind all interfaces:
|
||||
|
||||
Native installs, GPU notes, Windows/macOS instructions, HTTPS, and configuration live in the [setup guide](docs/setup.md).
|
||||
```bash
|
||||
ODYSSEUS_HOST=0.0.0.0 ./start-macos.sh
|
||||
# then open http://<tailscale-ip>:7860
|
||||
```
|
||||
|
||||
## Features
|
||||
The script also reads `.env` at startup, so `APP_BIND=0.0.0.0` and `APP_PORT`
|
||||
set there are picked up automatically without a command-line override each run.
|
||||
|
||||
- **Chat + Agents** — local/API models, tools, MCP, files, shell, skills, and memory.
|
||||
- **Cookbook** — hardware-aware model recommendations, downloads, and serving.
|
||||
- **Deep Research** — multi-step web research with source reading and report generation.
|
||||
- **Compare** — blind side-by-side model testing and synthesis.
|
||||
- **Documents** — writing-first editor with AI edits, suggestions, Markdown, HTML, CSV, and syntax highlighting.
|
||||
- **Email** — IMAP/SMTP inbox with triage, tags, summaries, reminders, and reply drafts.
|
||||
- **Notes, Tasks + Calendar** — reminders, todos, scheduled agent tasks, and CalDAV sync.
|
||||
- **Extras** — gallery/image editor, themes, uploads, web search, presets, sessions, and 2FA.
|
||||
Keep `AUTH_ENABLED=true` (the default) before binding outside loopback. Do not
|
||||
expose this port directly to the public internet. To build a clickable app wrapper:
|
||||
|
||||
## Demo
|
||||
```bash
|
||||
./build-macos-app.sh
|
||||
```
|
||||
|
||||
A full hover-to-play tour lives on the landing page: [`docs/index.html`](docs/index.html).
|
||||
<details>
|
||||
<summary>Cookbook, GPU, Ollama, and troubleshooting notes</summary>
|
||||
|
||||
**Docker bundled services.** Compose starts Odysseus, ChromaDB, SearXNG, and
|
||||
ntfy. Odysseus and the bundled service ports bind to `127.0.0.1` by default, so
|
||||
they are reachable from the host but not exposed to your LAN/public internet
|
||||
unless you opt in.
|
||||
|
||||
**Cookbook storage in Docker.** Downloads live in `./data/huggingface`
|
||||
(`~/.cache/huggingface` in the container). Cookbook-installed Python CLIs and
|
||||
serve engines live in `./data/local` (`~/.local` in the container), so they
|
||||
survive container recreation.
|
||||
|
||||
**Remote servers.** In **Cookbook -> Settings -> Servers**, generate the
|
||||
Odysseus SSH key and add the public key to the remote server's
|
||||
`~/.ssh/authorized_keys`. From the host you can also run:
|
||||
|
||||
```bash
|
||||
ssh-copy-id -i data/ssh/id_ed25519.pub user@server
|
||||
```
|
||||
|
||||
**Docker GPU overlays.** CPU-only users can skip this section. Cookbook can
|
||||
only detect GPUs that Docker exposes to the container — if the host runtime or
|
||||
device passthrough is not configured, Cookbook sees the iGPU, another card, or
|
||||
CPU instead of your intended GPU.
|
||||
|
||||
For NVIDIA, `scripts/check-docker-gpu.sh` diagnoses GPU passthrough and can
|
||||
optionally install the host runtime or update `.env`.
|
||||
|
||||
```bash
|
||||
# Read-only diagnostic (default — installs nothing, never edits .env):
|
||||
scripts/check-docker-gpu.sh
|
||||
|
||||
# Print OS-specific install commands without running them:
|
||||
scripts/check-docker-gpu.sh --print-install-commands
|
||||
|
||||
# Install NVIDIA Container Toolkit on Ubuntu/Debian (requires sudo):
|
||||
scripts/check-docker-gpu.sh --install-nvidia-toolkit
|
||||
|
||||
# Write COMPOSE_FILE to .env (only when GPU passthrough is confirmed working):
|
||||
scripts/check-docker-gpu.sh --enable-nvidia-overlay
|
||||
|
||||
# Full assisted setup — install toolkit, then enable overlay if passthrough works:
|
||||
scripts/check-docker-gpu.sh --install-nvidia-toolkit --enable-nvidia-overlay
|
||||
```
|
||||
|
||||
Safety notes:
|
||||
- The app never installs host GPU runtime automatically.
|
||||
- The app never edits `.env` automatically.
|
||||
- `.env` is only modified when `--enable-nvidia-overlay` is explicitly passed,
|
||||
and only after GPU passthrough succeeds. `--yes` skips prompts but does not
|
||||
bypass the passthrough gate.
|
||||
- `.env.bak.*` backups created by `--enable-nvidia-overlay` are ignored by
|
||||
Git and the Docker build context.
|
||||
|
||||
To enable manually without the script, add this to `.env`:
|
||||
|
||||
```bash
|
||||
COMPOSE_FILE=docker-compose.yml:docker/gpu.nvidia.yml
|
||||
```
|
||||
|
||||
**AMD / ROCm.** AMD setup is read-only diagnostic plus manual `.env` edit. Run:
|
||||
|
||||
```bash
|
||||
scripts/check-docker-amd-gpu.sh
|
||||
```
|
||||
|
||||
Then add the reported values to `.env`, replacing `RENDER_GID` with your host's
|
||||
numeric render group id:
|
||||
|
||||
```bash
|
||||
COMPOSE_FILE=docker-compose.yml:docker/gpu.amd.yml
|
||||
RENDER_GID=989
|
||||
```
|
||||
|
||||
For NVIDIA/AMD GPU support, also read the comments in the selected overlay file: docker/gpu.nvidia.yml or docker/gpu.amd.yml.
|
||||
|
||||
**Stack-management UIs (Portainer, Coolify, Dockhand, etc.).** These tools
|
||||
often accept only a single Compose file and do not reliably honor `COMPOSE_FILE`
|
||||
or multiple `-f` overlays. CLI users should keep using the `COMPOSE_FILE`
|
||||
overlay workflow above. For stack UIs, point the stack at one of the standalone
|
||||
files instead, which bundle the base stack plus the GPU settings:
|
||||
|
||||
- `docker-compose.gpu-nvidia.yml` — still requires the NVIDIA Container Toolkit
|
||||
on the host.
|
||||
- `docker-compose.gpu-amd.yml` — still requires host ROCm/kfd/DRI setup, the
|
||||
`video`/`render` group membership, and `RENDER_GID` when needed.
|
||||
|
||||
The base `docker-compose.yml` plus the `docker/gpu.*.yml` overlays remain the
|
||||
source of truth; the standalone files mirror them for single-file deployments.
|
||||
|
||||
Verify after enabling either overlay:
|
||||
|
||||
```bash
|
||||
docker compose exec odysseus nvidia-smi -L # NVIDIA
|
||||
docker compose exec odysseus sh -lc 'test -e /dev/kfd && test -d /dev/dri && ls -l /dev/kfd /dev/dri/renderD*' # AMD
|
||||
```
|
||||
|
||||
> **GPU passthrough ≠ llama.cpp CUDA.** `nvidia-smi` passing inside the
|
||||
> container confirms Docker GPU access, but llama.cpp also needs `cudart` and
|
||||
> the CUDA Toolkit at runtime. If Cookbook logs show `Unable to find cudart
|
||||
> library`, `Could NOT find CUDAToolkit`, `CUDA Toolkit not found`, or
|
||||
> tensors/layers assigned to CPU, that is a Cookbook/llama.cpp build issue —
|
||||
> not a Docker passthrough failure. Re-install the serve engine via
|
||||
> **Cookbook → Dependencies** to get a CUDA-enabled build.
|
||||
>
|
||||
> The same split applies to AMD/ROCm: seeing `/dev/kfd` and `/dev/dri` inside
|
||||
> the container confirms device passthrough, not ROCm userspace or a
|
||||
> ROCm-enabled vLLM/llama.cpp build. `rocm-smi` and `rocminfo` are not expected
|
||||
> inside the slim Odysseus image.
|
||||
|
||||
**Ollama with Docker.** If Ollama runs on the host, add this endpoint in
|
||||
Settings:
|
||||
|
||||
```text
|
||||
http://host.docker.internal:11434/v1
|
||||
```
|
||||
|
||||
Ollama must listen outside its own loopback interface:
|
||||
|
||||
```bash
|
||||
OLLAMA_HOST=0.0.0.0:11434 ollama serve
|
||||
```
|
||||
|
||||
This connects Odysseus in Docker to an Ollama server that is already running on
|
||||
your host machine; it does not start Ollama inside the container.
|
||||
`host.docker.internal` is Docker's hostname for the host machine from inside the
|
||||
container. Cookbook **Serve** is a separate workflow for serving downloaded
|
||||
models through Odysseus/llama.cpp, so Windows users with an existing Ollama
|
||||
install usually only need to add the endpoint in Settings.
|
||||
|
||||
**Useful checks.**
|
||||
|
||||
```bash
|
||||
docker compose ps
|
||||
docker compose logs --tail=120 odysseus
|
||||
docker compose logs odysseus | grep -E 'ChromaDB|MemoryVectorStore|DEGRADED'
|
||||
```
|
||||
|
||||
**macOS details.** `start-macos.sh` installs Homebrew deps, creates the venv,
|
||||
runs setup, and starts uvicorn on port `7860` because AirPlay often holds
|
||||
`7000`. It uses llama.cpp/Ollama for Metal. vLLM/SGLang are CUDA/ROCm-only and
|
||||
do not run on macOS. MLX-only models are not served by Odysseus.
|
||||
|
||||
</details>
|
||||
|
||||
### Native Windows
|
||||
|
||||
**One-command launcher** (creates the venv, installs deps, runs setup, starts the
|
||||
server; safe to re-run):
|
||||
|
||||
```powershell
|
||||
git clone https://github.com/pewdiepie-archdaemon/odysseus.git
|
||||
cd odysseus
|
||||
powershell -ExecutionPolicy Bypass -File .\launch-windows.ps1
|
||||
```
|
||||
|
||||
Or do it by hand:
|
||||
|
||||
```powershell
|
||||
git clone https://github.com/pewdiepie-archdaemon/odysseus.git
|
||||
cd odysseus
|
||||
py -3.11 -m venv venv
|
||||
venv\Scripts\Activate.ps1
|
||||
pip install -r requirements.txt
|
||||
python setup.py
|
||||
python -m uvicorn app:app --host 127.0.0.1 --port 7000
|
||||
```
|
||||
|
||||
If `python` points at an older interpreter, use `py -3.12` (or another installed
|
||||
3.11+ version) for the venv step.
|
||||
|
||||
**Requirements:** Python 3.11+. The core app (chat, agent, memory, documents,
|
||||
email, calendar, deep research) runs fully native. For full **Cookbook** background
|
||||
model downloads and the agent shell tool, also install
|
||||
[Git for Windows](https://git-scm.com/download/win) (provides `bash.exe`).
|
||||
Local GPU *serving* of vLLM/SGLang needs Linux/WSL2; for a local model on Windows,
|
||||
[Ollama](https://ollama.com/download) is the easiest path — point Odysseus at
|
||||
`http://localhost:11434/v1` in Settings.
|
||||
|
||||
Open `http://localhost:7000`, log in with the generated admin password,
|
||||
and configure everything else inside **Settings**.
|
||||
|
||||
## Troubleshooting & Advanced Setup
|
||||
|
||||
### `chromadb-client` conflicts with embedded ChromaDB
|
||||
If `chromadb-client` (the lightweight HTTP-only package) is installed alongside the full `chromadb` package, Odysseus starts but ChromaDB silently falls back to HTTP-only mode and fails.
|
||||
|
||||
**Fix:** uninstall `chromadb-client` and force-reinstall the full package:
|
||||
```bash
|
||||
./venv/bin/pip uninstall chromadb-client -y
|
||||
./venv/bin/pip install --force-reinstall chromadb
|
||||
```
|
||||
|
||||
### HTTPS + LAN/Tailscale exposure
|
||||
To expose Odysseus on a local network or Tailscale with HTTPS:
|
||||
1. Change the bind address to `0.0.0.0` in `.env` (`APP_BIND=0.0.0.0` or `ODYSSEUS_HOST=0.0.0.0`).
|
||||
2. Generate a locally-trusted cert for your LAN/Tailscale IPs using [mkcert](https://github.com/FiloSottile/mkcert):
|
||||
```bash
|
||||
mkcert -install
|
||||
mkcert -cert-file cert.pem -key-file key.pem 192.168.1.100 tailscale-ip
|
||||
```
|
||||
3. Run `uvicorn` with the generated certs:
|
||||
```bash
|
||||
python -m uvicorn app:app --host 0.0.0.0 --port 7000 --ssl-certfile=cert.pem --ssl-keyfile=key.pem
|
||||
```
|
||||
4. Install the `mkcert` CA on any other device you want to access Odysseus from (e.g., for iOS, email the `rootCA.pem` to yourself, install the profile, and trust it in Certificate Trust Settings).
|
||||
|
||||
### Optional Dependencies
|
||||
`requirements-optional.txt` contains packages that unlock extra features. It is not installed by default.
|
||||
|
||||
| Package | Feature unlocked |
|
||||
|---------|-----------------|
|
||||
| `faster-whisper` | Local speech-to-text (microphone -> text) via the "local" STT provider. |
|
||||
| `duckduckgo-search` | DuckDuckGo as a search provider option. |
|
||||
| `PyMuPDF` | PDF page rendering in the side viewer panel and form-filling. (Note: AGPL-3.0) |
|
||||
| `markitdown` | Office/EPUB document text extraction (converts .docx/.xlsx/.pptx/.xls/.epub to Markdown). |
|
||||
|
||||
### Outlook / Office 365 email
|
||||
Odysseus email accounts currently use IMAP/SMTP username-password auth. Outlook
|
||||
and Microsoft 365 generally require OAuth instead, so normal Microsoft mailbox
|
||||
passwords will fail. See [docs/email-outlook.md](docs/email-outlook.md) for the
|
||||
current limitation and the planned integration direction.
|
||||
|
||||
## Security Notes
|
||||
Odysseus is a self-hosted workspace with powerful local tools: shell access, file uploads, model downloads, web research, email/calendar integrations, and API tokens. Treat it like an admin console.
|
||||
|
||||
- Keep `AUTH_ENABLED=true` for any network-accessible deployment.
|
||||
- Keep `LOCALHOST_BYPASS=false` outside local development.
|
||||
- Use `SECURE_COOKIES=true` when Odysseus is served through HTTPS by a trusted reverse proxy or private access gateway.
|
||||
- Do not expose it directly to the public internet without HTTPS and a trusted reverse proxy or private access layer.
|
||||
- Keep `.env`, `data/`, `logs/`, databases, uploads, generated media, backups, auth/session files, API keys, and model/provider tokens out of Git and private shares. They are ignored by default.
|
||||
- Review `data/auth.json` after first boot: disable open signup unless you intentionally want it, make only your own account admin, and keep demo/test accounts non-admin.
|
||||
- Non-admin users do not get shell/Python/file read/write by default, and admin-only routes/tools such as MCP management, API tokens, webhooks, model/cookbook serving, backup/vault, and app settings are admin-gated. Other features are controlled by per-user privileges, so review each user's privileges before exposing a deployment.
|
||||
- Rotate any API keys or tokens that were ever pasted into a shared chat, demo, screenshot, or log.
|
||||
- If you enable API tokens or webhooks, create separate tokens per integration and delete unused ones.
|
||||
- Prefer binding manual development runs to `127.0.0.1`; bind to `0.0.0.0` only when you intentionally want LAN/reverse-proxy access.
|
||||
- Keep ChromaDB, SearXNG, ntfy, Ollama, vLLM, llama.cpp, databases, and raw model/provider APIs internal-only. Expose only the authenticated Odysseus web/API entrypoint through your trusted proxy or private access layer.
|
||||
- Before publishing a fork, run `git status --short` and confirm no private files from `.env`, `data/`, `logs/`, uploads, backups, or local databases are staged.
|
||||
|
||||
### Private or proxied deployments
|
||||
Odysseus serves plain HTTP on its app port. Docker Compose binds Odysseus and the bundled services to `127.0.0.1` by default, so a typical production/private setup is:
|
||||
|
||||
1. Keep Odysseus on localhost, for example `127.0.0.1:7000`.
|
||||
2. Terminate HTTPS at a trusted reverse proxy or private access gateway.
|
||||
3. Put the authenticated Odysseus web/API entrypoint behind that layer.
|
||||
4. Keep raw service and model ports internal-only.
|
||||
|
||||
Cloudflare Access, Tailscale, Caddy, nginx, and Traefik can all fit this pattern; none are required by Odysseus. If your access layer reaches Odysseus on the same host, proxy to `http://127.0.0.1:7000` and keep `AUTH_ENABLED=true`, `LOCALHOST_BYPASS=false`, and `SECURE_COOKIES=true`.
|
||||
|
||||
Common internal-only ports from the default docs/compose setup:
|
||||
|
||||
| Port | Service |
|
||||
|---|---|
|
||||
| `7000` | Odysseus raw app port |
|
||||
| `8080` | SearXNG |
|
||||
| `8091` | ntfy |
|
||||
| `8100` | ChromaDB host port for manual/compose access |
|
||||
| `11434` | Ollama |
|
||||
| `8000-8020` | Common local model/provider APIs |
|
||||
|
||||
## Contributing
|
||||
Help is welcome. The best entry points are fresh-install testing, provider setup
|
||||
bugs, mobile/editor polish, docs, and small focused refactors. See
|
||||
[ROADMAP.md](ROADMAP.md) for the current help-wanted list.
|
||||
|
||||
Help is welcome. The best entry points are fresh-install testing, provider setup bugs, mobile/editor polish, docs, and small focused refactors. See [CONTRIBUTING.md](CONTRIBUTING.md) and [ROADMAP.md](ROADMAP.md).
|
||||
## Configuration
|
||||
Most setup is done inside the app with `/setup` or **Settings**. Use `.env`
|
||||
for deployment-level defaults and secrets you want present before first boot.
|
||||
Key settings:
|
||||
|
||||
## Security
|
||||
| Variable | Default | Description |
|
||||
|---|---|---|
|
||||
| `LLM_HOST` | `localhost` | Your LLM server (e.g. `llm-host.local:8000`) |
|
||||
| `LLM_HOSTS` | -- | Comma-separated list for model discovery |
|
||||
| `OPENAI_API_KEY` | -- | Optional OpenAI key. Prefer adding providers in the app unless pre-seeding. |
|
||||
| `SEARXNG_INSTANCE` | `http://localhost:8080` | SearXNG URL. Docker overrides this to `http://searxng:8080`. |
|
||||
| `SEARXNG_SECRET` | generated on first Docker boot | Optional SearXNG cookie/CSRF secret. Leave blank unless you need to pin it. |
|
||||
| `APP_BIND` | `127.0.0.1` | Docker Compose host bind address for the web UI. Use `0.0.0.0` only for intentional LAN/reverse-proxy access. |
|
||||
| `APP_PORT` | `7000` | Docker Compose host port for the web UI. |
|
||||
| `AUTH_ENABLED` | `true` | Enable/disable login |
|
||||
| `LOCALHOST_BYPASS` | `false` | Development-only auth bypass for loopback requests. Keep false for shared/network deployments. |
|
||||
| `SECURE_COOKIES` | `false` | Set true when serving Odysseus through HTTPS at a trusted proxy or private access gateway. |
|
||||
| `DATABASE_URL` | `sqlite:///./data/app.db` | Database connection string |
|
||||
| `CHROMADB_HOST` | `localhost` | ChromaDB host for vector memory. Docker overrides this to `chromadb`. |
|
||||
| `CHROMADB_PORT` | `8100` | ChromaDB port for manual host runs. Docker overrides this to `8000`. |
|
||||
| `EMBEDDING_URL` | -- | OpenAI-compatible embeddings endpoint |
|
||||
| `ODYSSEUS_CHAT_UPLOAD_MAX_BYTES` | `10485760` | Chat/agent attachment cap in bytes. Raise for larger local PDFs or text documents. |
|
||||
| `ODYSSEUS_GALLERY_UPLOAD_MAX_BYTES` | `104857600` | Gallery image upload cap in bytes (100 MB). |
|
||||
| `ODYSSEUS_GALLERY_TRANSFORM_UPLOAD_MAX_BYTES` | `26214400` | Gallery transform input cap in bytes (25 MB). |
|
||||
| `ODYSSEUS_MEMORY_IMPORT_MAX_BYTES` | `10485760` | Memory import file cap in bytes (10 MB). |
|
||||
| `ODYSSEUS_PERSONAL_UPLOAD_MAX_BYTES` | `26214400` | Personal document upload cap in bytes (25 MB). |
|
||||
| `ODYSSEUS_EMAIL_COMPOSE_UPLOAD_MAX_BYTES` | `26214400` | Email compose attachment cap in bytes (25 MB). |
|
||||
| `ODYSSEUS_STT_MAX_AUDIO_BYTES` | `26214400` | Speech-to-text audio cap in bytes (25 MB). |
|
||||
| `ODYSSEUS_ICS_MAX_BYTES` | `10485760` | Calendar `.ics` import cap in bytes (10 MB). |
|
||||
|
||||
Odysseus is a self-hosted workspace with powerful local tools. Keep auth enabled, keep private data out of Git, and do not expose raw model/service ports publicly. Deployment details are in the [setup guide](docs/setup.md#security-notes).
|
||||
All upload-limit vars are validated (must be a positive integer) and optional; an invalid value fails fast at startup.
|
||||
|
||||
### Built-in MCP servers (optional setup)
|
||||
|
||||
Odysseus auto-registers a few built-in MCP servers at startup. The npx-based ones (currently the browser server, `@playwright/mcp`) only start when their npm package is already in the local npx cache. If a package isn't cached, that server is skipped with a startup log message explaining what to do, so a fresh install does not block on a multi-minute npm download or hang if Playwright system deps are missing.
|
||||
|
||||
To enable the browser MCP (page navigation, screenshots, vision), run once:
|
||||
|
||||
```bash
|
||||
npx -y @playwright/mcp@latest --version
|
||||
```
|
||||
|
||||
That installs `@playwright/mcp` plus Playwright (~300MB total). Restart Odysseus and the server will register at startup.
|
||||
|
||||
## Architecture
|
||||
```
|
||||
app.py # FastAPI entry point
|
||||
core/ auth, database, middleware, constants
|
||||
src/ llm_core, agent_loop, agent_tools, chat_processor, search/
|
||||
routes/ chat, session, document, memory, model … endpoints
|
||||
services/ docs, memory, search, hwfit (Cookbook) …
|
||||
static/ index.html + app.js + style.css + js/ (modular front-end)
|
||||
docs/ landing page (index.html) + preview clips
|
||||
```
|
||||
|
||||
## Data
|
||||
All user data lives in `data/` (gitignored): `app.db` (sessions, messages, documents),
|
||||
`memory.json`, `presets.json`, `uploads/`, `personal_docs/`, `chroma/`, `settings.json`.
|
||||
|
||||
## Star History
|
||||
|
||||
@@ -72,5 +451,19 @@ Odysseus is a self-hosted workspace with powerful local tools. Keep auth enabled
|
||||
</a>
|
||||
|
||||
## License
|
||||
MIT -- see [LICENSE](LICENSE) and [ACKNOWLEDGMENTS.md](ACKNOWLEDGMENTS.md).
|
||||
|
||||
AGPL-3.0-or-later -- see [LICENSE](LICENSE) and [ACKNOWLEDGMENTS.md](ACKNOWLEDGMENTS.md).
|
||||
```
|
||||
|
|
||||
|||
|
||||
|||||
|
||||
| | | |||||||
|
||||
)_) )_) )_) ~|~
|
||||
)___))___))___)\ |
|
||||
)____)____)_____)\\|
|
||||
_____|____|____|_____\\\__
|
||||
\ /
|
||||
~^~^~~^~^~~^~^~~^~^~~^~^~~^~^~~^~^~~^~^~
|
||||
~^~ all aboard! ~^~
|
||||
~^~^~~^~^~~^~^~~^~^~~^~^~~^~^~~^~^~~^~^~
|
||||
```
|
||||
|
||||
@@ -47,7 +47,6 @@ from fastapi.responses import JSONResponse, FileResponse, HTMLResponse
|
||||
from fastapi.middleware.cors import CORSMiddleware
|
||||
from fastapi.staticfiles import StaticFiles
|
||||
from starlette.middleware.base import BaseHTTPMiddleware
|
||||
from starlette.middleware.gzip import GZipMiddleware
|
||||
|
||||
# Core imports
|
||||
from core.constants import (
|
||||
@@ -56,7 +55,7 @@ from core.constants import (
|
||||
)
|
||||
from core.database import SessionLocal, ApiToken
|
||||
from core.middleware import SecurityHeadersMiddleware, is_cors_preflight
|
||||
from core.auth import AuthManager, normalize_known_username
|
||||
from core.auth import AuthManager
|
||||
from core.exceptions import (
|
||||
SessionNotFoundError, InvalidFileUploadError,
|
||||
LLMServiceError, WebSearchError,
|
||||
@@ -69,37 +68,10 @@ from src.generated_images import GENERATED_IMAGE_HEADERS, resolve_generated_imag
|
||||
from starlette.responses import RedirectResponse
|
||||
|
||||
# ========= LOGGING =========
|
||||
import logging.handlers
|
||||
from core.constants import DATA_DIR
|
||||
|
||||
_root_logger = logging.getLogger()
|
||||
_root_logger.setLevel(logging.INFO)
|
||||
_formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
|
||||
|
||||
# Clear existing handlers to avoid duplicates
|
||||
for _h in list(_root_logger.handlers):
|
||||
_root_logger.removeHandler(_h)
|
||||
|
||||
_console_h = logging.StreamHandler()
|
||||
_console_h.setFormatter(_formatter)
|
||||
_root_logger.addHandler(_console_h)
|
||||
|
||||
try:
|
||||
_log_dir = os.path.join(DATA_DIR, "logs")
|
||||
os.makedirs(_log_dir, exist_ok=True)
|
||||
_log_file = os.path.join(_log_dir, "app.log")
|
||||
|
||||
# RotatingFileHandler is not multi-process safe (e.g. if uvicorn is run with --workers N).
|
||||
# Odysseus is single-process by convention, so this is acceptable, but be aware that
|
||||
# concurrent log rotation issues can arise if multiple workers are configured.
|
||||
_file_h = logging.handlers.RotatingFileHandler(
|
||||
_log_file, maxBytes=5 * 1024 * 1024, backupCount=3, encoding="utf-8"
|
||||
)
|
||||
_file_h.setFormatter(_formatter)
|
||||
_root_logger.addHandler(_file_h)
|
||||
except Exception as e:
|
||||
_root_logger.warning(f"Failed to initialize file logging handler (falling back to console-only): {e}")
|
||||
|
||||
logging.basicConfig(
|
||||
level=logging.INFO,
|
||||
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
|
||||
)
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# ========= APP =========
|
||||
@@ -132,16 +104,6 @@ app.add_middleware(
|
||||
],
|
||||
)
|
||||
|
||||
# ========= RESPONSE COMPRESSION (gzip) =========
|
||||
# The frontend's text assets (style.css, index.html, the JS bundles) shipped
|
||||
# uncompressed on every cold load. gzip cuts CSS/JS/HTML by ~75-85% on the wire
|
||||
# with no behavioural change. Starlette's GZipMiddleware excludes
|
||||
# `text/event-stream` by default, so the SSE streams (chat, shell, research,
|
||||
# model-probe — all served with media_type="text/event-stream") are never
|
||||
# compressed or buffered; only complete bodies over minimum_size are. The
|
||||
# security-header middleware composes cleanly on top.
|
||||
app.add_middleware(GZipMiddleware, minimum_size=1024, compresslevel=6)
|
||||
|
||||
# ========= SECURITY HEADERS MIDDLEWARE =========
|
||||
app.add_middleware(SecurityHeadersMiddleware)
|
||||
|
||||
@@ -167,7 +129,6 @@ _TIMEOUT_EXEMPT_PREFIXES = (
|
||||
"/api/cookbook/setup", # remote pacman/apt installs
|
||||
"/api/upload", # large files
|
||||
"/api/image", # diffusion proxies (inpaint/harmonize/upscale/etc.) — own 120s httpx timeout
|
||||
"/api/memory/audit", # retains own 120s LLM inactivity timeout
|
||||
)
|
||||
|
||||
|
||||
@@ -256,16 +217,8 @@ if AUTH_ENABLED:
|
||||
try:
|
||||
rows = db.query(ApiToken).filter(ApiToken.is_active == True).all()
|
||||
for r in rows:
|
||||
owner_key = normalize_known_username(auth_manager.users, getattr(r, "owner", None))
|
||||
if not owner_key:
|
||||
logger.warning(
|
||||
"Ignoring active API token '%s' for unknown auth user '%s'",
|
||||
getattr(r, "id", ""),
|
||||
getattr(r, "owner", None),
|
||||
)
|
||||
continue
|
||||
scopes = [s.strip() for s in (getattr(r, "scopes", "") or "chat").split(",") if s.strip()]
|
||||
new_map[r.token_prefix].append((r.id, r.token_hash, owner_key, scopes))
|
||||
new_map[r.token_prefix].append((r.id, r.token_hash, getattr(r, "owner", None), scopes))
|
||||
finally:
|
||||
db.close()
|
||||
_token_cache.clear()
|
||||
@@ -331,8 +284,8 @@ if AUTH_ENABLED:
|
||||
request.state.current_user = "internal-tool"
|
||||
request.state.api_token = False
|
||||
return await call_next(request)
|
||||
except Exception as _e:
|
||||
logger.warning("Internal tool auth header check failed", exc_info=_e)
|
||||
except Exception:
|
||||
pass
|
||||
# Allow DIRECT localhost requests (internal service calls from
|
||||
# heartbeats etc.). Tunnel/proxy-forwarded requests are excluded by
|
||||
# _is_trusted_loopback so LOCALHOST_BYPASS can't be abused over a
|
||||
@@ -385,10 +338,11 @@ if AUTH_ENABLED:
|
||||
_db.close()
|
||||
try:
|
||||
await _asyncio.to_thread(_do)
|
||||
except Exception as _e:
|
||||
logger.debug("Failed to update token last_used_at", exc_info=_e)
|
||||
except Exception:
|
||||
pass
|
||||
_asyncio.create_task(_touch_last_used(matched_id))
|
||||
# Keep bearer-token callers out of normal cookie/user
|
||||
# routes. API-aware routes can read api_token_owner.
|
||||
request.state.current_user = "api"
|
||||
request.state.api_token = True
|
||||
request.state.api_token_id = matched_id
|
||||
@@ -463,8 +417,8 @@ async def serve_generated_image(filename: str, request: Request):
|
||||
_db.close()
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as _e:
|
||||
logger.warning("Image ownership verification failed for %r", filename, exc_info=_e)
|
||||
except Exception:
|
||||
pass
|
||||
ext = filename.rsplit('.', 1)[-1].lower()
|
||||
mime = {
|
||||
"png": "image/png", "jpg": "image/jpeg", "jpeg": "image/jpeg",
|
||||
@@ -518,20 +472,14 @@ components = initialize_managers(BASE_DIR, rag_manager)
|
||||
session_manager = components["session_manager"]
|
||||
from src.assistant_log import set_session_manager as _set_asst_sm
|
||||
_set_asst_sm(session_manager)
|
||||
# Set the global session manager singleton (used by core.models.Session.add_message)
|
||||
from core.models import set_session_manager_instance
|
||||
set_session_manager_instance(session_manager)
|
||||
app.state.session_manager = session_manager
|
||||
memory_manager = components["memory_manager"]
|
||||
memory_vector = components.get("memory_vector")
|
||||
upload_handler = components["upload_handler"]
|
||||
app.state.upload_handler = upload_handler
|
||||
personal_docs_mgr = components["personal_docs_manager"]
|
||||
api_key_manager = components["api_key_manager"]
|
||||
preset_manager = components["preset_manager"]
|
||||
chat_processor = components["chat_processor"]
|
||||
research_handler = components["research_handler"]
|
||||
app.state.research_handler = research_handler
|
||||
chat_handler = components["chat_handler"]
|
||||
model_discovery = components["model_discovery"]
|
||||
skills_manager = components["skills_manager"]
|
||||
@@ -581,6 +529,9 @@ upload_cleanup_task = None
|
||||
from routes.emoji_routes import setup_emoji_routes
|
||||
app.include_router(setup_emoji_routes())
|
||||
|
||||
from routes.workspace_routes import setup_workspace_routes
|
||||
app.include_router(setup_workspace_routes())
|
||||
|
||||
# Sessions
|
||||
from routes.session_routes import setup_session_routes
|
||||
session_config = {"REQUEST_TIMEOUT": REQUEST_TIMEOUT, "OPENAI_API_KEY": OPENAI_API_KEY, "SESSIONS_FILE": SESSIONS_FILE}
|
||||
@@ -625,7 +576,7 @@ app.include_router(setup_preset_routes(preset_manager))
|
||||
|
||||
# Diagnostics
|
||||
from routes.diagnostics_routes import setup_diagnostics_routes
|
||||
app.include_router(setup_diagnostics_routes(rag_manager, rag_available, research_handler, memory_vector))
|
||||
app.include_router(setup_diagnostics_routes(rag_manager, rag_available, research_handler))
|
||||
|
||||
# Cleanup
|
||||
from routes.cleanup_routes import setup_cleanup_routes
|
||||
@@ -703,9 +654,6 @@ app.include_router(setup_shell_routes())
|
||||
from routes.cookbook_routes import setup_cookbook_routes
|
||||
app.include_router(setup_cookbook_routes())
|
||||
|
||||
from routes.workspace_routes import setup_workspace_routes
|
||||
app.include_router(setup_workspace_routes())
|
||||
|
||||
# Hardware model fitting (cookbook "What Fits?" tab)
|
||||
from routes.hwfit_routes import setup_hwfit_routes
|
||||
app.include_router(setup_hwfit_routes())
|
||||
@@ -978,21 +926,16 @@ async def _startup_event():
|
||||
async def _warmup_endpoints():
|
||||
try:
|
||||
import httpx
|
||||
# model_discovery has no get_endpoints(); that call raised
|
||||
# AttributeError every run and silently disabled warmup/keepalive.
|
||||
# Resolve the /models probe URLs via the real discovery API, off the
|
||||
# event loop since discovery does a blocking port scan.
|
||||
urls = (
|
||||
await asyncio.to_thread(model_discovery.warmup_ping_urls)
|
||||
if model_discovery else []
|
||||
)
|
||||
for url in urls:
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=5.0) as client:
|
||||
await client.get(url)
|
||||
logger.info(f"Warmup ping OK: {url}")
|
||||
except Exception as e:
|
||||
logger.debug(f"Warmup ping failed for endpoint: {e}")
|
||||
endpoints = model_discovery.get_endpoints() if model_discovery else []
|
||||
for ep in endpoints[:5]:
|
||||
url = ep.get("url", "").replace("/chat/completions", "/models")
|
||||
if url:
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=5.0) as client:
|
||||
await client.get(url)
|
||||
logger.info(f"Warmup ping OK: {url}")
|
||||
except Exception as e:
|
||||
logger.debug(f"Warmup ping failed for endpoint: {e}")
|
||||
except Exception as e:
|
||||
logger.debug(f"Warmup ping skipped: {e}")
|
||||
|
||||
|
||||
+3
-17
@@ -5,9 +5,8 @@ offers and pair to it, without duplicating any LLM logic.
|
||||
|
||||
Auth is enforced globally by AuthMiddleware (app.py), so reaching a handler here
|
||||
means the caller is authenticated by either a cookie session or a Bearer `ody_`
|
||||
API token. Ping/info accept either credential type, models requires a chat-
|
||||
scoped API token for bearer callers, and the pairing endpoints are admin-cookie
|
||||
only.
|
||||
API token. The read endpoints (ping/info/models) accept either; the pairing
|
||||
endpoints are admin-cookie only.
|
||||
|
||||
Pairing CSRF posture: minting happens ONLY on POST. The session cookie is
|
||||
SameSite=Lax (routes/auth_routes.py), which a browser does not send on a
|
||||
@@ -19,7 +18,7 @@ on a GET would be unsafe (Lax cookies ride top-level GET navigations), so GET
|
||||
|
||||
import html
|
||||
|
||||
from fastapi import APIRouter, HTTPException, Request
|
||||
from fastapi import APIRouter, Request
|
||||
from fastapi.responses import HTMLResponse
|
||||
|
||||
from core.middleware import require_admin
|
||||
@@ -53,18 +52,6 @@ def owner_can_see(row_owner, owner) -> bool:
|
||||
return row_owner is None or row_owner == owner
|
||||
|
||||
|
||||
def require_models_scope(request: Request) -> None:
|
||||
"""Require the companion chat scope for bearer-token model inventory."""
|
||||
if not getattr(request.state, "api_token", False):
|
||||
return
|
||||
scopes = getattr(request.state, "api_token_scopes", None) or []
|
||||
if isinstance(scopes, str):
|
||||
scopes = [scope.strip() for scope in scopes.split(",")]
|
||||
scope_set = {str(scope).strip() for scope in scopes if str(scope).strip()}
|
||||
if _pairing.COMPANION_SCOPE not in scope_set:
|
||||
raise HTTPException(403, "API token requires chat scope")
|
||||
|
||||
|
||||
def mint_pairing_token(owner: str, invalidate=None) -> tuple[str, str]:
|
||||
"""Mint a pairing token AND invalidate the auth middleware's in-memory token
|
||||
cache, so the new token is accepted on the very next request without a server
|
||||
@@ -116,7 +103,6 @@ def setup_companion_routes() -> APIRouter:
|
||||
rows -- the same rule as owner_filter. Read-only; never returns api_key
|
||||
material.
|
||||
"""
|
||||
require_models_scope(request)
|
||||
import json as _json
|
||||
|
||||
from core.database import SessionLocal, ModelEndpoint
|
||||
|
||||
+13
-129
@@ -3,7 +3,6 @@ Authentication module — multi-user password hashing, session tokens, config pe
|
||||
Config stored in data/auth.json. Uses bcrypt directly.
|
||||
"""
|
||||
|
||||
import enum
|
||||
import json
|
||||
import os
|
||||
import secrets
|
||||
@@ -68,14 +67,6 @@ TOKEN_TTL = 60 * 60 * 24 * 7 # 7 days
|
||||
RESERVED_USERNAMES = frozenset({"internal-tool", "api", "demo", "system"})
|
||||
|
||||
|
||||
def normalize_known_username(users: Dict[str, Any], username: str | None) -> Optional[str]:
|
||||
"""Return a normalized username only when it exists in the auth user map."""
|
||||
key = str(username or "").strip().lower()
|
||||
if not key or key not in users:
|
||||
return None
|
||||
return key
|
||||
|
||||
|
||||
def _hash_password(password: str) -> str:
|
||||
return bcrypt.hashpw(password.encode("utf-8"), bcrypt.gensalt()).decode("utf-8")
|
||||
|
||||
@@ -84,15 +75,6 @@ def _verify_password(password: str, hashed: str) -> bool:
|
||||
return bcrypt.checkpw(password.encode("utf-8"), hashed.encode("utf-8"))
|
||||
|
||||
|
||||
class SetAdminResult(enum.Enum):
|
||||
"""Outcome of AuthManager.set_admin, so callers can map each case to a
|
||||
precise response instead of guessing from a bare bool."""
|
||||
OK = "ok"
|
||||
USER_NOT_FOUND = "user_not_found"
|
||||
NOT_AUTHORIZED = "not_authorized" # requester is not an admin
|
||||
LAST_ADMIN = "last_admin" # would remove the last remaining admin
|
||||
|
||||
|
||||
class AuthManager:
|
||||
"""Manages multi-user password + session-token auth system."""
|
||||
|
||||
@@ -114,7 +96,6 @@ class AuthManager:
|
||||
self._load()
|
||||
self._load_sessions()
|
||||
self._migrate_single_user()
|
||||
self._drop_reserved_loaded_users()
|
||||
self._migrate_legacy_admin_role()
|
||||
|
||||
def _load(self):
|
||||
@@ -167,13 +148,7 @@ class AuthManager:
|
||||
def _migrate_single_user(self):
|
||||
"""Migrate old single-user format to multi-user format."""
|
||||
if "password_hash" in self._config and "users" not in self._config:
|
||||
old_user = str(self._config.get("username", "admin") or "admin").strip().lower()
|
||||
if old_user in RESERVED_USERNAMES:
|
||||
logger.warning(
|
||||
"Migrating legacy single-user reserved username '%s' to 'admin'",
|
||||
old_user,
|
||||
)
|
||||
old_user = "admin"
|
||||
old_user = self._config.get("username", "admin")
|
||||
old_hash = self._config["password_hash"]
|
||||
self._config = {
|
||||
"users": {
|
||||
@@ -187,30 +162,6 @@ class AuthManager:
|
||||
self._save()
|
||||
logger.info(f"Migrated single-user auth to multi-user (admin: {old_user})")
|
||||
|
||||
def _drop_reserved_loaded_users(self):
|
||||
"""Fail closed for legacy/manual auth rows that collide with sentinels."""
|
||||
users = self._config.get("users")
|
||||
if not isinstance(users, dict):
|
||||
return
|
||||
normalized = {}
|
||||
removed = []
|
||||
for username, data in users.items():
|
||||
key = str(username or "").strip().lower()
|
||||
if not key:
|
||||
continue
|
||||
if key in RESERVED_USERNAMES:
|
||||
removed.append(key)
|
||||
continue
|
||||
normalized[key] = data
|
||||
if removed or normalized != users:
|
||||
self._config["users"] = normalized
|
||||
self._save()
|
||||
if removed:
|
||||
logger.warning(
|
||||
"Removed reserved username(s) from auth config: %s",
|
||||
", ".join(sorted(set(removed))),
|
||||
)
|
||||
|
||||
def _migrate_legacy_admin_role(self):
|
||||
"""Normalize setup.py's old role='admin' marker to is_admin=True."""
|
||||
changed = False
|
||||
@@ -293,22 +244,6 @@ class AuthManager:
|
||||
return False
|
||||
if not self.users.get(requesting_user, {}).get("is_admin"):
|
||||
return False
|
||||
# Revoke API bearer tokens before removing the auth row. The bearer
|
||||
# path authenticates from ApiToken rows and does not require the
|
||||
# owner to still exist, so a successful delete must not leave active
|
||||
# rows behind. If the token store is unavailable, fail closed and
|
||||
# keep the user/session state intact so the admin can retry.
|
||||
try:
|
||||
from core.database import get_db_session, ApiToken
|
||||
with get_db_session() as db:
|
||||
removed_tokens = db.query(ApiToken).filter(ApiToken.owner == username).delete()
|
||||
if removed_tokens:
|
||||
logger.info(
|
||||
f"Revoked {removed_tokens} API token(s) owned by deleted user '{username}'"
|
||||
)
|
||||
except Exception:
|
||||
logger.warning(f"Failed to revoke API tokens for deleted user '{username}'")
|
||||
return False
|
||||
del self._config["users"][username]
|
||||
self._save()
|
||||
# Purge all sessions belonging to this user. validate_token doesn't
|
||||
@@ -323,6 +258,18 @@ class AuthManager:
|
||||
revoked += 1
|
||||
if revoked:
|
||||
self._save_sessions()
|
||||
# Also revoke API bearer tokens owned by this user. The bearer auth
|
||||
# path authenticates straight against ApiToken rows and never
|
||||
# re-checks that the owner still exists, so leaving the rows behind
|
||||
# would let a deleted user keep full API access indefinitely.
|
||||
try:
|
||||
from core.database import get_db_session, ApiToken
|
||||
with get_db_session() as db:
|
||||
removed = db.query(ApiToken).filter(ApiToken.owner == username).delete()
|
||||
if removed:
|
||||
logger.info(f"Revoked {removed} API token(s) owned by deleted user '{username}'")
|
||||
except Exception:
|
||||
logger.warning(f"Failed to revoke API tokens for deleted user '{username}'")
|
||||
logger.info(f"Deleted user '{username}' (by {requesting_user}); revoked {revoked} active session(s)")
|
||||
return True
|
||||
|
||||
@@ -397,69 +344,6 @@ class AuthManager:
|
||||
logger.info(f"Updated privileges for '{username}': {current}")
|
||||
return True
|
||||
|
||||
def set_admin(self, username: str, is_admin: bool,
|
||||
requesting_user: str) -> SetAdminResult:
|
||||
"""Promote/demote an existing user to/from admin. Admin only.
|
||||
|
||||
Refuses to remove the last remaining admin so the instance can never
|
||||
be locked out of admin access; self-demotion is allowed as long as
|
||||
another admin remains. Admin status is re-checked live on every
|
||||
request, so unlike delete/rename no session or token revocation is
|
||||
needed — a demoted admin simply fails the next is_admin() gate.
|
||||
|
||||
Promotion stashes the user's current privilege map and demotion
|
||||
restores it, so a temporary admin stint can't silently broaden a
|
||||
user's non-admin access; users without a stash (created as admin,
|
||||
or promoted before stashing existed) demote to DEFAULT_PRIVILEGES.
|
||||
|
||||
Counting admins and flipping the flag happen in one critical section
|
||||
so two concurrent demotions can't race the admin count to zero.
|
||||
"""
|
||||
username = (username or "").strip().lower()
|
||||
requesting_user = (requesting_user or "").strip().lower()
|
||||
is_admin = bool(is_admin)
|
||||
with self._config_lock:
|
||||
target = self._config.get("users", {}).get(username)
|
||||
if target is None:
|
||||
return SetAdminResult.USER_NOT_FOUND
|
||||
if not self.users.get(requesting_user, {}).get("is_admin"):
|
||||
return SetAdminResult.NOT_AUTHORIZED
|
||||
currently_admin = bool(target.get("is_admin"))
|
||||
if currently_admin == is_admin:
|
||||
return SetAdminResult.OK # no-op; leave privileges untouched
|
||||
if currently_admin and not is_admin:
|
||||
admin_count = sum(1 for d in self.users.values() if d.get("is_admin"))
|
||||
if admin_count <= 1:
|
||||
return SetAdminResult.LAST_ADMIN
|
||||
# Write order matters for lock-free readers: get_privileges()
|
||||
# reads without _config_lock and trusts is_admin, so the admin
|
||||
# flag must be flipped while the stored map is safe to expose —
|
||||
# before writing admin privileges on promote, after restoring
|
||||
# the pre-admin map on demote.
|
||||
if is_admin:
|
||||
target["is_admin"] = True
|
||||
# Stash the pre-admin map so a later demotion can restore it.
|
||||
# While is_admin is set the stored map is inert: get_privileges
|
||||
# short-circuits to ADMIN_PRIVILEGES and set_privileges refuses
|
||||
# admins, so only set_admin ever touches the stash.
|
||||
target["privileges_before_admin"] = dict(
|
||||
target.get("privileges") or DEFAULT_PRIVILEGES
|
||||
)
|
||||
target["privileges"] = dict(ADMIN_PRIVILEGES)
|
||||
else:
|
||||
# Restore the stashed pre-admin map. Fall back to defaults for
|
||||
# users created as admins (their stored map is ADMIN_PRIVILEGES,
|
||||
# which must not leak past demotion — e.g. can_use_bash) and
|
||||
# for admins promoted before the stash existed.
|
||||
target["privileges"] = dict(
|
||||
target.pop("privileges_before_admin", None)
|
||||
or DEFAULT_PRIVILEGES
|
||||
)
|
||||
target["is_admin"] = False
|
||||
self._save()
|
||||
logger.info("Set is_admin=%s for '%s' (by '%s')", is_admin, username, requesting_user)
|
||||
return SetAdminResult.OK
|
||||
|
||||
def change_password(self, username: str, current_password: str, new_password: str) -> bool:
|
||||
username = username.strip().lower()
|
||||
if username not in self.users:
|
||||
|
||||
+27
-243
@@ -2,15 +2,12 @@ import os
|
||||
import logging
|
||||
import sqlite3
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from sqlalchemy import event, create_engine, Column, String, Text, Boolean, DateTime, Integer, ForeignKey, JSON, Index, func, text
|
||||
from sqlalchemy.engine import Engine
|
||||
from sqlalchemy.types import TypeDecorator
|
||||
from sqlalchemy.ext.declarative import declarative_base, declared_attr
|
||||
from sqlalchemy.orm import relationship, sessionmaker, backref
|
||||
|
||||
from src.runtime_paths import get_app_root
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Create base class for declarative models
|
||||
@@ -32,26 +29,9 @@ class TimestampMixin:
|
||||
def updated_at(cls):
|
||||
return Column(DateTime, default=utcnow_naive, onupdate=utcnow_naive, nullable=False)
|
||||
|
||||
# Ensure the writable data directory exists before SQLite connects.
|
||||
from src.constants import DATA_DIR, AUTH_FILE, MEMORY_FILE, USER_PREFS_FILE, SETTINGS_FILE
|
||||
Path(DATA_DIR).mkdir(parents=True, exist_ok=True)
|
||||
|
||||
|
||||
def _default_database_url() -> str:
|
||||
return f"sqlite:///{Path(DATA_DIR) / 'app.db'}"
|
||||
|
||||
|
||||
def _normalize_sqlite_url(url: str) -> str:
|
||||
if not url.startswith("sqlite:///"):
|
||||
return url
|
||||
db_path = url.replace("sqlite:///", "", 1)
|
||||
if db_path == ":memory:" or os.path.isabs(db_path):
|
||||
return url
|
||||
return f"sqlite:///{(Path(get_app_root()) / db_path).resolve().as_posix()}"
|
||||
|
||||
|
||||
# Get database URL from environment, default to SQLite in DATA_DIR
|
||||
DATABASE_URL = _normalize_sqlite_url(os.getenv("DATABASE_URL", _default_database_url()))
|
||||
from src.constants import DATA_DIR, AUTH_FILE, MEMORY_FILE, USER_PREFS_FILE, SETTINGS_FILE
|
||||
DATABASE_URL = os.getenv("DATABASE_URL", f"sqlite:///{DATA_DIR}/app.db")
|
||||
|
||||
# Create engine
|
||||
engine = create_engine(
|
||||
@@ -344,13 +324,6 @@ class EmailAccount(TimestampMixin, Base):
|
||||
smtp_password = Column(String, default="")
|
||||
|
||||
from_address = Column(String, default="")
|
||||
display_name = Column(String, nullable=True) # "Hriday Ranka" — used in From: header
|
||||
|
||||
# OAuth2 (Google / Google Workspace). Tokens stored encrypted via secret_storage.
|
||||
oauth_provider = Column(String, nullable=True) # "google" or None
|
||||
oauth_access_token = Column(String, nullable=True) # encrypted
|
||||
oauth_refresh_token = Column(String, nullable=True) # encrypted
|
||||
oauth_token_expiry = Column(String, nullable=True) # unix timestamp string
|
||||
|
||||
__table_args__ = (
|
||||
Index('ix_email_accounts_owner_default', 'owner', 'is_default'),
|
||||
@@ -715,7 +688,6 @@ def _migrate_add_last_message_at_column():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(sessions)")
|
||||
@@ -741,14 +713,10 @@ def _migrate_add_last_message_at_column():
|
||||
"ON sessions(archived, last_message_at)"
|
||||
)
|
||||
conn.commit()
|
||||
conn.close()
|
||||
logging.getLogger(__name__).info("Migrated: added + backfilled 'last_message_at' on sessions")
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"last_message_at migration failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _migrate_add_document_archived_column():
|
||||
"""Add `archived` to documents (soft-archive flag). Guarded + idempotent."""
|
||||
@@ -756,7 +724,6 @@ def _migrate_add_document_archived_column():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(documents)")
|
||||
@@ -765,13 +732,9 @@ def _migrate_add_document_archived_column():
|
||||
conn.execute("ALTER TABLE documents ADD COLUMN archived BOOLEAN DEFAULT 0")
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info("Migrated: added 'archived' to documents")
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"documents.archived migration failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
|
||||
def _migrate_add_owner_column():
|
||||
@@ -780,7 +743,6 @@ def _migrate_add_owner_column():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(sessions)")
|
||||
@@ -790,13 +752,9 @@ def _migrate_add_owner_column():
|
||||
conn.execute("CREATE INDEX IF NOT EXISTS ix_sessions_owner ON sessions(owner)")
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info("Migrated: added 'owner' column to sessions")
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"Migration check failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _migrate_model_endpoints():
|
||||
"""Recreate model_endpoints table if schema changed (url->base_url)."""
|
||||
@@ -804,7 +762,6 @@ def _migrate_model_endpoints():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(model_endpoints)")
|
||||
@@ -813,13 +770,9 @@ def _migrate_model_endpoints():
|
||||
conn.execute("DROP TABLE IF EXISTS model_endpoints")
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info("Migrated: dropped old model_endpoints table (schema change)")
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"model_endpoints migration check failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _migrate_add_hidden_models_column():
|
||||
"""Add hidden_models column to model_endpoints if it doesn't exist."""
|
||||
@@ -827,7 +780,6 @@ def _migrate_add_hidden_models_column():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(model_endpoints)")
|
||||
@@ -836,13 +788,9 @@ def _migrate_add_hidden_models_column():
|
||||
conn.execute("ALTER TABLE model_endpoints ADD COLUMN hidden_models TEXT")
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info("Migrated: added 'hidden_models' column to model_endpoints")
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"hidden_models migration failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _migrate_add_model_endpoint_owner_column():
|
||||
"""Add owner column to model_endpoints if it doesn't exist.
|
||||
@@ -857,7 +805,6 @@ def _migrate_add_model_endpoint_owner_column():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(model_endpoints)")
|
||||
@@ -867,13 +814,9 @@ def _migrate_add_model_endpoint_owner_column():
|
||||
conn.execute("CREATE INDEX IF NOT EXISTS ix_model_endpoints_owner ON model_endpoints(owner)")
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info("Migrated: added 'owner' column + index to model_endpoints")
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"model_endpoints.owner migration failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
|
||||
def _migrate_add_provider_auth_id_column():
|
||||
@@ -882,7 +825,6 @@ def _migrate_add_provider_auth_id_column():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(model_endpoints)")
|
||||
@@ -892,13 +834,9 @@ def _migrate_add_provider_auth_id_column():
|
||||
conn.execute("CREATE INDEX IF NOT EXISTS ix_model_endpoints_provider_auth_id ON model_endpoints(provider_auth_id)")
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info("Migrated: added 'provider_auth_id' column + index to model_endpoints")
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"model_endpoints.provider_auth_id migration failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
|
||||
def _migrate_add_model_type_column():
|
||||
@@ -907,7 +845,6 @@ def _migrate_add_model_type_column():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(model_endpoints)")
|
||||
@@ -916,13 +853,9 @@ def _migrate_add_model_type_column():
|
||||
conn.execute("ALTER TABLE model_endpoints ADD COLUMN model_type TEXT DEFAULT 'llm'")
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info("Migrated: added 'model_type' column to model_endpoints")
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"model_type migration failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _migrate_add_model_endpoint_refresh_columns():
|
||||
"""Add endpoint classification / refresh policy columns if missing."""
|
||||
@@ -930,7 +863,6 @@ def _migrate_add_model_endpoint_refresh_columns():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(model_endpoints)")
|
||||
@@ -944,13 +876,9 @@ def _migrate_add_model_endpoint_refresh_columns():
|
||||
if columns and "model_refresh_timeout" not in columns:
|
||||
conn.execute("ALTER TABLE model_endpoints ADD COLUMN model_refresh_timeout INTEGER")
|
||||
conn.commit()
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"model_endpoints refresh-policy migration failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _migrate_add_task_run_model_column():
|
||||
"""Add model column to task_runs if it doesn't exist (records which model ran)."""
|
||||
@@ -958,7 +886,6 @@ def _migrate_add_task_run_model_column():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(task_runs)")
|
||||
@@ -967,13 +894,9 @@ def _migrate_add_task_run_model_column():
|
||||
conn.execute("ALTER TABLE task_runs ADD COLUMN model TEXT")
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info("Migrated: added 'model' column to task_runs")
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"task_runs model migration failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _migrate_add_supports_tools_column():
|
||||
"""Add supports_tools column to model_endpoints if it doesn't exist."""
|
||||
@@ -981,7 +904,6 @@ def _migrate_add_supports_tools_column():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(model_endpoints)")
|
||||
@@ -990,13 +912,9 @@ def _migrate_add_supports_tools_column():
|
||||
conn.execute("ALTER TABLE model_endpoints ADD COLUMN supports_tools BOOLEAN")
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info("Migrated: added 'supports_tools' column to model_endpoints")
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"supports_tools migration failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
|
||||
def _migrate_add_cached_models_column():
|
||||
@@ -1005,7 +923,6 @@ def _migrate_add_cached_models_column():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(model_endpoints)")
|
||||
@@ -1013,13 +930,9 @@ def _migrate_add_cached_models_column():
|
||||
if columns and "cached_models" not in columns:
|
||||
conn.execute("ALTER TABLE model_endpoints ADD COLUMN cached_models TEXT")
|
||||
conn.commit()
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"cached_models migration failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _migrate_add_pinned_models_column():
|
||||
"""Add pinned_models column to model_endpoints if it doesn't exist."""
|
||||
@@ -1027,7 +940,6 @@ def _migrate_add_pinned_models_column():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(model_endpoints)")
|
||||
@@ -1036,13 +948,9 @@ def _migrate_add_pinned_models_column():
|
||||
conn.execute("ALTER TABLE model_endpoints ADD COLUMN pinned_models TEXT")
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info("Migrated: added 'pinned_models' column to model_endpoints")
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"pinned_models migration failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _migrate_add_notes_sort_order():
|
||||
"""Add sort_order, image_url, repeat columns to notes if they don't exist."""
|
||||
@@ -1050,7 +958,6 @@ def _migrate_add_notes_sort_order():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(notes)")
|
||||
@@ -1068,13 +975,9 @@ def _migrate_add_notes_sort_order():
|
||||
if columns and "agent_session_id" not in columns:
|
||||
conn.execute("ALTER TABLE notes ADD COLUMN agent_session_id TEXT")
|
||||
conn.commit()
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"notes migration failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _migrate_add_mode_column():
|
||||
"""Add mode column to sessions table if it doesn't exist."""
|
||||
@@ -1082,7 +985,6 @@ def _migrate_add_mode_column():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(sessions)")
|
||||
@@ -1091,13 +993,9 @@ def _migrate_add_mode_column():
|
||||
conn.execute("ALTER TABLE sessions ADD COLUMN mode TEXT")
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info("Migrated: added 'mode' column to sessions")
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"Migration check for mode failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _migrate_add_folder_column():
|
||||
"""Add folder column to sessions table if it doesn't exist."""
|
||||
@@ -1105,7 +1003,6 @@ def _migrate_add_folder_column():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(sessions)")
|
||||
@@ -1114,13 +1011,9 @@ def _migrate_add_folder_column():
|
||||
conn.execute("ALTER TABLE sessions ADD COLUMN folder TEXT")
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info("Migrated: added 'folder' column to sessions")
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"Migration check for folder failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _migrate_add_token_columns():
|
||||
"""Add cumulative token tracking columns to sessions table."""
|
||||
@@ -1128,7 +1021,6 @@ def _migrate_add_token_columns():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(sessions)")
|
||||
@@ -1138,13 +1030,9 @@ def _migrate_add_token_columns():
|
||||
conn.execute("ALTER TABLE sessions ADD COLUMN total_output_tokens INTEGER DEFAULT 0")
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info("Migrated: added token tracking columns to sessions")
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"Migration check for token columns failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _migrate_add_owner_to_table(table_name: str, index_name: str):
|
||||
"""Generic helper: add owner TEXT column + index to a table if missing."""
|
||||
@@ -1152,7 +1040,6 @@ def _migrate_add_owner_to_table(table_name: str, index_name: str):
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute(f"PRAGMA table_info({table_name})")
|
||||
@@ -1162,13 +1049,9 @@ def _migrate_add_owner_to_table(table_name: str, index_name: str):
|
||||
conn.execute(f"CREATE INDEX IF NOT EXISTS {index_name} ON {table_name}(owner)")
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info(f"Migrated: added 'owner' column to {table_name}")
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"Migration owner column for {table_name} failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _migrate_add_multiuser_owner_columns():
|
||||
"""Add owner column to memories, gallery_images, user_tools, comparisons."""
|
||||
@@ -1193,7 +1076,6 @@ def _migrate_add_api_token_scopes_column():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
columns = [row[1] for row in conn.execute("PRAGMA table_info(api_tokens)").fetchall()]
|
||||
@@ -1202,13 +1084,9 @@ def _migrate_add_api_token_scopes_column():
|
||||
conn.execute("UPDATE api_tokens SET scopes = 'chat' WHERE scopes IS NULL OR scopes = ''")
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info("Migrated: added scopes column to api_tokens")
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"api_tokens.scopes migration failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _migrate_assign_legacy_owner():
|
||||
"""Assign all null-owner data to the first (admin) user.
|
||||
@@ -1250,7 +1128,6 @@ def _migrate_assign_legacy_owner():
|
||||
return
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
# Every table with an `owner` column. New tables added later will be
|
||||
@@ -1275,13 +1152,9 @@ def _migrate_assign_legacy_owner():
|
||||
except Exception as e:
|
||||
logger.warning(f"Legacy owner assignment for {table} failed: {e}")
|
||||
conn.commit()
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logger.warning(f"Legacy owner migration failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Also migrate memory.json
|
||||
mem_path = MEMORY_FILE
|
||||
@@ -1454,25 +1327,6 @@ def _migrate_add_task_automation_columns():
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"task automation migration: {e}")
|
||||
|
||||
def _migrate_add_email_oauth_columns():
|
||||
"""Add Google OAuth and display_name columns to email_accounts if missing."""
|
||||
try:
|
||||
with engine.connect() as conn:
|
||||
cols = [r[1] for r in conn.execute(text("PRAGMA table_info(email_accounts)"))]
|
||||
for col, typedef in [
|
||||
("oauth_provider", "TEXT"),
|
||||
("oauth_access_token", "TEXT"),
|
||||
("oauth_refresh_token", "TEXT"),
|
||||
("oauth_token_expiry", "TEXT"),
|
||||
("display_name", "TEXT"),
|
||||
]:
|
||||
if col not in cols:
|
||||
conn.execute(text(f"ALTER TABLE email_accounts ADD COLUMN {col} {typedef}"))
|
||||
conn.commit()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"email oauth columns migration: {e}")
|
||||
|
||||
|
||||
def _migrate_add_oauth_config():
|
||||
"""Add oauth_config column to mcp_servers table if missing."""
|
||||
try:
|
||||
@@ -1648,7 +1502,6 @@ class CalendarCal(TimestampMixin, Base):
|
||||
# NULL for local calendars and for CalDAV calendars created before
|
||||
# multi-account support was added (treated as "use any configured account").
|
||||
account_id = Column(String, nullable=True, index=True)
|
||||
caldav_base_url = Column(String, nullable=True)
|
||||
|
||||
events = relationship("CalendarEvent", back_populates="calendar", cascade="all, delete-orphan")
|
||||
|
||||
@@ -1679,27 +1532,10 @@ class CalendarEvent(TimestampMixin, Base):
|
||||
# vanishes upstream). NULL/local = created locally (agent, email triage, or
|
||||
# a UI event whose write-back failed) and must NOT be pruned by the sync.
|
||||
origin = Column(String, nullable=True, index=True)
|
||||
remote_href = Column(String, nullable=True) # CalDAV object URL for updates/deletes
|
||||
remote_etag = Column(String, nullable=True) # Last seen CalDAV ETag, when available
|
||||
caldav_sync_pending = Column(String, nullable=True) # create | update | delete retry marker
|
||||
|
||||
calendar = relationship("CalendarCal", back_populates="events")
|
||||
|
||||
|
||||
class CalendarDeletedEvent(TimestampMixin, Base):
|
||||
"""Hidden CalDAV delete tombstone retained until remote delete succeeds."""
|
||||
__tablename__ = "caldav_deleted_events"
|
||||
|
||||
uid = Column(String, primary_key=True, index=True)
|
||||
owner = Column(String, nullable=True, index=True)
|
||||
calendar_id = Column(String, nullable=True, index=True)
|
||||
remote_href = Column(String, nullable=True)
|
||||
remote_etag = Column(String, nullable=True)
|
||||
caldav_base_url = Column(String, nullable=True)
|
||||
summary = Column(String, nullable=True)
|
||||
last_error = Column(Text, nullable=True)
|
||||
|
||||
|
||||
class Integration(TimestampMixin, Base):
|
||||
"""An external service connection (email, RSS, webhook, etc.)."""
|
||||
__tablename__ = "integrations"
|
||||
@@ -1817,7 +1653,6 @@ def init_db():
|
||||
_migrate_add_tidy_verdict()
|
||||
_migrate_add_doc_source_email_cols()
|
||||
_migrate_add_oauth_config()
|
||||
_migrate_add_email_oauth_columns()
|
||||
_migrate_add_task_automation_columns()
|
||||
_migrate_add_disabled_tools()
|
||||
_migrate_add_mcp_oauth_tokens_column()
|
||||
@@ -1832,7 +1667,6 @@ def init_db():
|
||||
_migrate_add_calendar_is_utc()
|
||||
_migrate_add_calendar_origin()
|
||||
_migrate_add_calendar_account_id()
|
||||
_migrate_add_caldav_sync_columns()
|
||||
_migrate_chat_messages_fts()
|
||||
_migrate_encrypt_email_passwords()
|
||||
_migrate_encrypt_signatures()
|
||||
@@ -1939,7 +1773,6 @@ def _migrate_add_email_smtp_security():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(email_accounts)")
|
||||
@@ -1955,13 +1788,9 @@ def _migrate_add_email_smtp_security():
|
||||
)
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info("Migrated: added smtp_security column to email_accounts")
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"smtp_security migration skipped: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
|
||||
def _migrate_encrypt_endpoint_keys():
|
||||
@@ -2062,7 +1891,6 @@ def _migrate_add_calendar_is_utc():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(calendar_events)")
|
||||
@@ -2071,13 +1899,9 @@ def _migrate_add_calendar_is_utc():
|
||||
conn.execute("ALTER TABLE calendar_events ADD COLUMN is_utc BOOLEAN DEFAULT 0 NOT NULL")
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info("Migrated: added 'is_utc' column to calendar_events")
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"is_utc migration failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
|
||||
def _migrate_add_calendar_origin():
|
||||
@@ -2088,7 +1912,6 @@ def _migrate_add_calendar_origin():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(calendar_events)")
|
||||
@@ -2098,13 +1921,9 @@ def _migrate_add_calendar_origin():
|
||||
conn.execute("CREATE INDEX IF NOT EXISTS ix_calendar_events_origin ON calendar_events(origin)")
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info("Migrated: added 'origin' column to calendar_events")
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"calendar_events.origin migration failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
|
||||
def _migrate_add_calendar_account_id():
|
||||
@@ -2114,7 +1933,6 @@ def _migrate_add_calendar_account_id():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(calendars)")
|
||||
@@ -2124,38 +1942,9 @@ def _migrate_add_calendar_account_id():
|
||||
conn.execute("CREATE INDEX IF NOT EXISTS ix_calendars_account_id ON calendars(account_id)")
|
||||
conn.commit()
|
||||
logging.getLogger(__name__).info("Migrated: added 'account_id' column to calendars")
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"calendars.account_id migration failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
|
||||
def _migrate_add_caldav_sync_columns():
|
||||
"""Add remote CalDAV metadata used for bidirectional sync."""
|
||||
import sqlite3
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
ev_columns = [row[1] for row in conn.execute("PRAGMA table_info(calendar_events)").fetchall()]
|
||||
if ev_columns and "remote_href" not in ev_columns:
|
||||
conn.execute("ALTER TABLE calendar_events ADD COLUMN remote_href TEXT")
|
||||
if ev_columns and "remote_etag" not in ev_columns:
|
||||
conn.execute("ALTER TABLE calendar_events ADD COLUMN remote_etag TEXT")
|
||||
if ev_columns and "caldav_sync_pending" not in ev_columns:
|
||||
conn.execute("ALTER TABLE calendar_events ADD COLUMN caldav_sync_pending TEXT")
|
||||
|
||||
cal_columns = [row[1] for row in conn.execute("PRAGMA table_info(calendars)").fetchall()]
|
||||
if cal_columns and "caldav_base_url" not in cal_columns:
|
||||
conn.execute("ALTER TABLE calendars ADD COLUMN caldav_base_url TEXT")
|
||||
conn.commit()
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"CalDAV sync metadata migration failed: {e}")
|
||||
logging.getLogger(__name__).warning(f"calendars.account_id migration failed: {e}")
|
||||
|
||||
|
||||
def _migrate_add_calendar_metadata():
|
||||
@@ -2164,7 +1953,6 @@ def _migrate_add_calendar_metadata():
|
||||
db_path = DATABASE_URL.replace("sqlite:///", "")
|
||||
if not os.path.exists(db_path):
|
||||
return
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
cursor = conn.execute("PRAGMA table_info(calendar_events)")
|
||||
@@ -2176,13 +1964,9 @@ def _migrate_add_calendar_metadata():
|
||||
if columns and "last_pinged" not in columns:
|
||||
conn.execute("ALTER TABLE calendar_events ADD COLUMN last_pinged DATETIME")
|
||||
conn.commit()
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"calendar_events migration failed: {e}")
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def get_db():
|
||||
"""
|
||||
|
||||
+13
-48
@@ -11,24 +11,14 @@ from typing import Dict, List, Any, Optional, TYPE_CHECKING
|
||||
if TYPE_CHECKING:
|
||||
from .session_manager import SessionManager
|
||||
|
||||
# Module-level session manager singleton (single source of truth)
|
||||
_SESSION_MANAGER_INSTANCE: Optional["SessionManager"] = None
|
||||
# Module-level session manager reference (set at app startup)
|
||||
_session_manager: Optional["SessionManager"] = None
|
||||
|
||||
|
||||
def set_session_manager_instance(manager: "SessionManager"):
|
||||
"""Set the global SessionManager singleton."""
|
||||
global _SESSION_MANAGER_INSTANCE
|
||||
_SESSION_MANAGER_INSTANCE = manager
|
||||
|
||||
|
||||
def get_session_manager_instance() -> Optional["SessionManager"]:
|
||||
"""Get the global SessionManager singleton."""
|
||||
return _SESSION_MANAGER_INSTANCE
|
||||
|
||||
|
||||
# Keep legacy name for backward compatibility
|
||||
set_session_manager = set_session_manager_instance
|
||||
get_session_manager = get_session_manager_instance
|
||||
def set_session_manager(manager: "SessionManager"):
|
||||
"""Set the global session manager reference."""
|
||||
global _session_manager
|
||||
_session_manager = manager
|
||||
|
||||
|
||||
@dataclass
|
||||
@@ -52,17 +42,7 @@ class ChatMessage:
|
||||
|
||||
@dataclass
|
||||
class Session:
|
||||
"""A chat session — pure data container.
|
||||
|
||||
``.history`` is the authoritative mutable message list. Callers may
|
||||
read, append, pop, or reassign it directly — these changes take
|
||||
effect immediately. ``_history`` remains a compatibility alias that
|
||||
always resolves to the authoritative ``history`` list.
|
||||
|
||||
Each session gets its own unique history list at construction time
|
||||
(the dataclass default is never shared between instances).
|
||||
"""
|
||||
|
||||
"""A chat session — pure data container."""
|
||||
id: str
|
||||
name: str
|
||||
endpoint_url: str
|
||||
@@ -76,35 +56,24 @@ class Session:
|
||||
message_count: int = 0
|
||||
|
||||
def __post_init__(self):
|
||||
if self.headers is None:
|
||||
self.headers = {}
|
||||
# Ensure each session gets its OWN list (not the shared dataclass default)
|
||||
if self.history is None:
|
||||
self.history = []
|
||||
|
||||
@property
|
||||
def _history(self) -> List[ChatMessage]:
|
||||
"""Compatibility alias for callers that still reference ``_history``."""
|
||||
return self.history
|
||||
|
||||
@_history.setter
|
||||
def _history(self, messages: List[ChatMessage]):
|
||||
self.history = messages
|
||||
if self.headers is None:
|
||||
self.headers = {}
|
||||
|
||||
def add_message(self, message: ChatMessage):
|
||||
"""
|
||||
Add a message to this session.
|
||||
|
||||
Appends to the authoritative history list and increments
|
||||
message_count. Delegates to SessionManager for persistence
|
||||
if available.
|
||||
Delegates to SessionManager for persistence if available,
|
||||
otherwise just appends to history.
|
||||
"""
|
||||
self.history.append(message)
|
||||
self.message_count = len(self.history)
|
||||
|
||||
# Delegate to session manager for persistence
|
||||
if _SESSION_MANAGER_INSTANCE:
|
||||
_SESSION_MANAGER_INSTANCE._persist_message(self.id, message)
|
||||
if _session_manager:
|
||||
_session_manager._persist_message(self.id, message)
|
||||
|
||||
def get_context_messages(self) -> List[Dict[str, Any]]:
|
||||
"""Get messages in format for LLM API.
|
||||
@@ -125,7 +94,3 @@ class Session:
|
||||
def get(self, key: str, default=None):
|
||||
"""Dict-like access for compatibility."""
|
||||
return getattr(self, key, default)
|
||||
|
||||
def __getitem__(self, key: str):
|
||||
"""Allow session['field'] syntax."""
|
||||
return getattr(self, key)
|
||||
|
||||
@@ -191,8 +191,6 @@ def _windows_bash_fallbacks() -> List[str]:
|
||||
base = os.environ.get(env_name)
|
||||
if base:
|
||||
roots.append(ntpath.join(base, "Git"))
|
||||
if env_name == "LocalAppData":
|
||||
roots.append(ntpath.join(base, "Programs", "Git"))
|
||||
roots.extend(_WINDOWS_BASH_DEFAULT_ROOTS)
|
||||
|
||||
paths: List[str] = []
|
||||
@@ -300,7 +298,7 @@ def is_wsl() -> bool:
|
||||
import sys
|
||||
if sys.platform.startswith("linux") or os.name == "posix":
|
||||
try:
|
||||
with open("/proc/version", "r", encoding="utf-8", errors="ignore") as f:
|
||||
with open("/proc/version", "r") as f:
|
||||
if "microsoft" in f.read().lower():
|
||||
return True
|
||||
except Exception:
|
||||
@@ -368,10 +366,6 @@ def _ssh_exec_argv(
|
||||
strict_host_key_checking: bool | None = None,
|
||||
) -> list[str]:
|
||||
"""Build a consistent ssh argv for remote command execution."""
|
||||
remote_value = str(remote or "").strip()
|
||||
remote_host = remote_value.rsplit("@", 1)[-1]
|
||||
if not remote_value or remote_value.startswith("-") or not remote_host or remote_host.startswith("-"):
|
||||
raise ValueError("Invalid SSH remote host")
|
||||
argv = ["ssh"]
|
||||
if connect_timeout is not None:
|
||||
argv.extend(["-o", f"ConnectTimeout={int(connect_timeout)}"])
|
||||
|
||||
+4
-45
@@ -17,9 +17,6 @@ from typing import Dict, Optional
|
||||
from .database import Session as DbSession, ChatMessage as DbChatMessage, Document as DbDocument, SessionLocal, utcnow_naive
|
||||
from .models import Session, ChatMessage
|
||||
|
||||
# Re-export singleton accessors from models for convenience
|
||||
from .models import set_session_manager_instance, get_session_manager_instance
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@@ -191,17 +188,12 @@ class SessionManager:
|
||||
"""
|
||||
Add a message to a session and persist to database.
|
||||
|
||||
Updates the authoritative history list and persists through this
|
||||
manager directly so tests and temporary managers do not depend on the
|
||||
process-wide session-manager singleton.
|
||||
|
||||
Args:
|
||||
session_id: Session ID
|
||||
message: ChatMessage to add
|
||||
"""
|
||||
session = self.get_session(session_id)
|
||||
session.history.append(message)
|
||||
session._history = session.history
|
||||
session.message_count = len(session.history)
|
||||
|
||||
self._persist_message(session_id, message)
|
||||
@@ -240,10 +232,7 @@ class SessionManager:
|
||||
)
|
||||
db.add(db_message)
|
||||
|
||||
if session_id in self.sessions:
|
||||
db_session.message_count = len(self.sessions[session_id].history)
|
||||
else:
|
||||
db_session.message_count = 0
|
||||
db_session.message_count = len(self.sessions.get(session_id, {}).history) if session_id in self.sessions else 0
|
||||
_now = datetime.now(timezone.utc)
|
||||
db_session.last_accessed = _now
|
||||
# Clean "last conversation" timestamp — only bumped here on a
|
||||
@@ -294,7 +283,6 @@ class SessionManager:
|
||||
|
||||
# Update in-memory
|
||||
session.history = session.history[:keep_count]
|
||||
session._history = session.history
|
||||
|
||||
logger.info(f"Truncated session {session_id} to {keep_count} messages")
|
||||
return True
|
||||
@@ -345,7 +333,6 @@ class SessionManager:
|
||||
|
||||
db.commit()
|
||||
session.history = list(messages)
|
||||
session._history = session.history
|
||||
session.message_count = len(messages)
|
||||
logger.info("Replaced session %s history with %d messages", session_id, len(messages))
|
||||
return True
|
||||
@@ -621,52 +608,24 @@ class SessionManager:
|
||||
def save_sessions(self):
|
||||
"""No-op for DB compatibility."""
|
||||
|
||||
def ensure_task_session(self, session_id: str, name: str, endpoint_url: str, model: str, owner: str = None, task: object = None) -> Session:
|
||||
"""Create a task session if it doesn't exist, or return the existing one.
|
||||
|
||||
Unlike create_session, this checks the cache first and does NOT
|
||||
overwrite an existing in-memory session. The task scheduler must
|
||||
use this instead of direct dict assignment.
|
||||
"""
|
||||
if session_id in self.sessions:
|
||||
return self.sessions[session_id]
|
||||
|
||||
session = self.create_session(session_id, name, endpoint_url, model, owner=owner)
|
||||
if task is not None:
|
||||
task.session_id = session_id
|
||||
return session
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Cleanup
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def cleanup_empty_sessions(self, auto_archive_days: int = 30, min_age_hours: int = 1) -> dict:
|
||||
"""Clean up empty and old sessions.
|
||||
|
||||
Args:
|
||||
auto_archive_days: Age in days before non-important sessions are archived.
|
||||
min_age_hours: Minimum age in hours before an empty session can be deleted.
|
||||
Prevents deleting sessions that were just created.
|
||||
"""
|
||||
def cleanup_empty_sessions(self, auto_archive_days: int = 30) -> dict:
|
||||
"""Clean up empty and old sessions."""
|
||||
db = SessionLocal()
|
||||
stats = {'deleted_empty': 0, 'archived_old': 0, 'total_checked': 0}
|
||||
|
||||
try:
|
||||
all_sessions = db.query(DbSession).all()
|
||||
cutoff_date = utcnow_naive() - timedelta(days=auto_archive_days)
|
||||
min_age = utcnow_naive() - timedelta(hours=min_age_hours)
|
||||
|
||||
for db_session in all_sessions:
|
||||
stats['total_checked'] += 1
|
||||
|
||||
# Delete empty sessions only if older than min_age_hours
|
||||
# Delete empty sessions
|
||||
if db_session.message_count == 0:
|
||||
if db_session.created_at is not None:
|
||||
created = db_session.created_at
|
||||
if created.tzinfo is None:
|
||||
created = created.replace(tzinfo=timezone.utc)
|
||||
if created > min_age:
|
||||
continue # Too young to delete
|
||||
if db_session.id in self.sessions:
|
||||
del self.sessions[db_session.id]
|
||||
db.delete(db_session)
|
||||
|
||||
@@ -16,18 +16,18 @@ services:
|
||||
ports:
|
||||
- "${APP_BIND:-127.0.0.1}:${APP_PORT:-7000}:7000"
|
||||
volumes:
|
||||
- ${APP_DATA_DIR:-./data}:/app/data:z
|
||||
- ${APP_LOGS_DIR:-./logs}:/app/logs:z
|
||||
- ./data:/app/data:z
|
||||
- ./logs:/app/logs:z
|
||||
# Cookbook remote-server SSH identity. Odysseus can generate a key here;
|
||||
# add the shown public key to each remote server's authorized_keys.
|
||||
- ${APP_DATA_DIR:-./data}/ssh:/app/.ssh:z
|
||||
- ./data/ssh:/app/.ssh:z
|
||||
# Cookbook local model cache. Inside Docker, "Local" means the Odysseus
|
||||
# container, so persist its HuggingFace cache under ./data/huggingface.
|
||||
- ${APP_DATA_DIR:-./data}/huggingface:/app/.cache/huggingface:z
|
||||
- ./data/huggingface:/app/.cache/huggingface:z
|
||||
# Cookbook-installed Python CLIs/packages (vLLM, llama-cpp-python, etc.)
|
||||
# land under /app/.local for the odysseus user. Persist them so a
|
||||
# container recreate does not silently remove installed serve engines.
|
||||
- ${APP_DATA_DIR:-./data}/local:/app/.local:z
|
||||
- ./data/local:/app/.local:z
|
||||
extra_hosts:
|
||||
# Lets the container reach local services on the Docker host, including
|
||||
# Ollama at http://host.docker.internal:11434.
|
||||
|
||||
@@ -15,18 +15,18 @@ services:
|
||||
ports:
|
||||
- "${APP_BIND:-127.0.0.1}:${APP_PORT:-7000}:7000"
|
||||
volumes:
|
||||
- ${APP_DATA_DIR:-./data}:/app/data:z
|
||||
- ${APP_LOGS_DIR:-./logs}:/app/logs:z
|
||||
- ./data:/app/data:z
|
||||
- ./logs:/app/logs:z
|
||||
# Cookbook remote-server SSH identity. Odysseus can generate a key here;
|
||||
# add the shown public key to each remote server's authorized_keys.
|
||||
- ${APP_DATA_DIR:-./data}/ssh:/app/.ssh:z
|
||||
- ./data/ssh:/app/.ssh:z
|
||||
# Cookbook local model cache. Inside Docker, "Local" means the Odysseus
|
||||
# container, so persist its HuggingFace cache under ./data/huggingface.
|
||||
- ${APP_DATA_DIR:-./data}/huggingface:/app/.cache/huggingface:z
|
||||
- ./data/huggingface:/app/.cache/huggingface:z
|
||||
# Cookbook-installed Python CLIs/packages (vLLM, llama-cpp-python, etc.)
|
||||
# land under /app/.local for the odysseus user. Persist them so a
|
||||
# container recreate does not silently remove installed serve engines.
|
||||
- ${APP_DATA_DIR:-./data}/local:/app/.local:z
|
||||
- ./data/local:/app/.local:z
|
||||
extra_hosts:
|
||||
# Lets the container reach local services on the Docker host, including
|
||||
# Ollama at http://host.docker.internal:11434.
|
||||
|
||||
+5
-5
@@ -4,18 +4,18 @@ services:
|
||||
ports:
|
||||
- "${APP_BIND:-127.0.0.1}:${APP_PORT:-7000}:7000"
|
||||
volumes:
|
||||
- ${APP_DATA_DIR:-./data}:/app/data:z
|
||||
- ${APP_LOGS_DIR:-./logs}:/app/logs:z
|
||||
- ./data:/app/data:z
|
||||
- ./logs:/app/logs:z
|
||||
# Cookbook remote-server SSH identity. Odysseus can generate a key here;
|
||||
# add the shown public key to each remote server's authorized_keys.
|
||||
- ${APP_DATA_DIR:-./data}/ssh:/app/.ssh:z
|
||||
- ./data/ssh:/app/.ssh:z
|
||||
# Cookbook local model cache. Inside Docker, "Local" means the Odysseus
|
||||
# container, so persist its HuggingFace cache under ./data/huggingface.
|
||||
- ${APP_DATA_DIR:-./data}/huggingface:/app/.cache/huggingface:z
|
||||
- ./data/huggingface:/app/.cache/huggingface:z
|
||||
# Cookbook-installed Python CLIs/packages (vLLM, llama-cpp-python, etc.)
|
||||
# land under /app/.local for the odysseus user. Persist them so a
|
||||
# container recreate does not silently remove installed serve engines.
|
||||
- ${APP_DATA_DIR:-./data}/local:/app/.local:z
|
||||
- ./data/local:/app/.local:z
|
||||
extra_hosts:
|
||||
# Lets the container reach local services on the Docker host, including
|
||||
# Ollama at http://host.docker.internal:11434.
|
||||
|
||||
@@ -1,194 +0,0 @@
|
||||
# Agent migration manifests
|
||||
|
||||
Odysseus should be able to learn from another agent without blindly trusting
|
||||
that agent's whole state. The safe migration path is:
|
||||
|
||||
```text
|
||||
source agent export -> source adapter -> agent-migration.v1 manifest -> preview -> apply
|
||||
```
|
||||
|
||||
The manifest is intentionally source-neutral. OpenClaw, Hermes, a folder of
|
||||
Markdown notes, or any other agent can have its own adapter, but Odysseus only
|
||||
needs to understand the normalized manifest.
|
||||
|
||||
## Why not import everything as memory?
|
||||
|
||||
Durable memory should stay compact and useful. Long notes, logs, session
|
||||
transcripts, and project archives are useful context, but they are not all
|
||||
memories. A good migration keeps two layers separate:
|
||||
|
||||
- **Archive documents** preserve source material for search, reading, and later
|
||||
extraction.
|
||||
- **Memory candidates** are short facts or preferences that can be reviewed
|
||||
before being saved into Odysseus memory.
|
||||
|
||||
This keeps Odysseus' existing memory-review flow intact while giving it better
|
||||
source material to review.
|
||||
|
||||
## Manifest shape
|
||||
|
||||
`agent-migration.v1` is a JSON object:
|
||||
|
||||
```json
|
||||
{
|
||||
"schema_version": "agent-migration.v1",
|
||||
"generated_at": "2026-06-06T00:00:00Z",
|
||||
"source": {
|
||||
"name": "example-agent",
|
||||
"kind": "generic"
|
||||
},
|
||||
"summary": {
|
||||
"item_count": 3,
|
||||
"counts_by_kind": {
|
||||
"memory": 1,
|
||||
"skill": 1,
|
||||
"conversation_thread": 1,
|
||||
"archive_document": 1
|
||||
},
|
||||
"warning_count": 0
|
||||
},
|
||||
"items": [],
|
||||
"warnings": []
|
||||
}
|
||||
```
|
||||
|
||||
Each item has a stable `id`, a `kind`, source metadata, and enough content for a
|
||||
future importer to preview it before applying.
|
||||
|
||||
Supported item kinds in the first pass:
|
||||
|
||||
- `memory` — a candidate memory with `text`, `category`, `source`, and
|
||||
provenance metadata.
|
||||
- `skill` — a `SKILL.md` file with content and parsed frontmatter metadata.
|
||||
- `conversation_thread` — a normalized transcript thread from an exported chat
|
||||
history. Message content is optional; adapters can preserve only thread
|
||||
metadata, message counts, timestamps, and hashes when a manifest should stay
|
||||
small or avoid embedding private transcript text.
|
||||
- `archive_document` — long-form source material. Content is optional; adapters
|
||||
can preserve only path/hash/size metadata when a manifest should stay small.
|
||||
|
||||
## Build a manifest
|
||||
|
||||
Use the read-only helper:
|
||||
|
||||
```bash
|
||||
python3 scripts/agent_migration_manifest.py \
|
||||
--source-name old-agent \
|
||||
--source-kind generic \
|
||||
--memory-json /path/to/memories.json \
|
||||
--skills-dir /path/to/skills \
|
||||
--conversation-json /path/to/conversations.json \
|
||||
--archive /path/to/notes \
|
||||
--output /tmp/agent-migration.json
|
||||
```
|
||||
|
||||
The helper does not write to `data/`, call an LLM, import Odysseus modules, or
|
||||
modify the source. It only writes JSON.
|
||||
|
||||
Memory JSON may be:
|
||||
|
||||
```json
|
||||
[
|
||||
"A plain memory string",
|
||||
{
|
||||
"text": "A categorized memory",
|
||||
"category": "preference",
|
||||
"source": "old-agent"
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
or an object containing a list under `memories`, `memory`, `items`, or `data`.
|
||||
|
||||
Skills are scanned recursively for `SKILL.md`:
|
||||
|
||||
```bash
|
||||
python3 scripts/agent_migration_manifest.py \
|
||||
--source-name hermes \
|
||||
--source-kind hermes \
|
||||
--skills-dir ~/.hermes/skills \
|
||||
--output /tmp/hermes-skills-manifest.json
|
||||
```
|
||||
|
||||
Archive documents are metadata-only by default. To embed text content:
|
||||
|
||||
```bash
|
||||
python3 scripts/agent_migration_manifest.py \
|
||||
--source-name notes-export \
|
||||
--archive /path/to/markdown-notes \
|
||||
--include-archive-content \
|
||||
--output /tmp/notes-manifest.json
|
||||
```
|
||||
|
||||
Conversation exports are also metadata-only by default:
|
||||
|
||||
```bash
|
||||
python3 scripts/agent_migration_manifest.py \
|
||||
--source-name chatgpt-export \
|
||||
--source-kind chatgpt \
|
||||
--conversation-json /path/to/conversations.json \
|
||||
--output /tmp/chatgpt-conversations-manifest.json
|
||||
```
|
||||
|
||||
The first pass supports generic conversation JSON such as:
|
||||
|
||||
```json
|
||||
[
|
||||
{
|
||||
"id": "thread-1",
|
||||
"title": "Project plan",
|
||||
"messages": [
|
||||
{"role": "user", "content": "Can we design this?"},
|
||||
{"role": "assistant", "content": "Yes, start with a narrow slice."}
|
||||
]
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
It also recognizes ChatGPT-style `mapping` exports from `conversations.json`.
|
||||
To embed normalized messages:
|
||||
|
||||
```bash
|
||||
python3 scripts/agent_migration_manifest.py \
|
||||
--source-name chatgpt-export \
|
||||
--source-kind chatgpt \
|
||||
--conversation-json /path/to/conversations.json \
|
||||
--include-conversation-content \
|
||||
--max-conversation-messages 2000 \
|
||||
--output /tmp/chatgpt-conversations-with-content.json
|
||||
```
|
||||
|
||||
Content embedding is explicit because exported chat histories can be huge and
|
||||
private. A future source-specific adapter can add ZIP traversal, attachment
|
||||
metadata, and provider-specific project/workspace fields while still emitting
|
||||
the same `conversation_thread` manifest item.
|
||||
|
||||
## Recommended apply behavior
|
||||
|
||||
A future Odysseus importer should treat the manifest as untrusted user-provided
|
||||
data and apply it in stages:
|
||||
|
||||
1. Show a dry-run summary with counts, warnings, duplicates, and sample items.
|
||||
2. Back up current `data/` state before writing anything.
|
||||
3. Import archive documents as documents or another searchable source, not as
|
||||
memory.
|
||||
4. Import conversation threads as searchable archived context first, with
|
||||
citations back to the source thread. Do not turn whole transcripts into
|
||||
memory.
|
||||
5. Show memory candidates for review before saving through the normal memory
|
||||
path.
|
||||
6. Import skills only after name/category conflict checks.
|
||||
7. Skip secrets by default. Credentials need explicit, provider-specific flows.
|
||||
|
||||
## What belongs in source adapters?
|
||||
|
||||
Adapters can be source-specific. The core manifest should not be.
|
||||
|
||||
For example, an OpenClaw adapter may know about OpenClaw's workspace files. A
|
||||
Hermes adapter may know about `~/.hermes/config.yaml` and `~/.hermes/skills`.
|
||||
A ChatGPT adapter may know about `conversations.json`, uploaded-file metadata,
|
||||
and image attachment directories. A Claude adapter may know about Claude's
|
||||
export shape and project boundaries. A generic adapter may only know about
|
||||
memory JSON, conversation JSON, `SKILL.md`, and Markdown folders.
|
||||
|
||||
Nonstandard folders should be adapter details, not required Odysseus concepts.
|
||||
@@ -1,129 +0,0 @@
|
||||
# Backup & Restore
|
||||
|
||||
Odysseus keeps all of your state in the `data/` directory — the SQLite database
|
||||
(`app.db`), the Fernet encryption key (`data/.app_key`), the vault, memory, RAG
|
||||
indexes, personal documents, and uploads. The `scripts/odysseus-backup` tool
|
||||
snapshots that directory into a single gzip tarball and restores it later.
|
||||
|
||||
Snapshots are safe to take while the app is running: SQLite databases are copied
|
||||
through SQLite's own `.backup` API rather than a raw file copy, so an in-flight
|
||||
write can't corrupt the snapshot.
|
||||
|
||||
> **A snapshot contains your secrets.** The tarball includes the Fernet
|
||||
> encryption key (`data/.app_key`), the vault, sessions, and any stored
|
||||
> provider/API tokens — so treat it like a password. Store backups somewhere
|
||||
> private, never commit them to Git, and prefer an encrypted destination when
|
||||
> copying them offsite.
|
||||
|
||||
## Quick start
|
||||
|
||||
Run the tool from the repository root:
|
||||
|
||||
```bash
|
||||
# Create a snapshot → backups/odysseus-backup-<YYYYMMDD-HHMMSS>.tar.gz
|
||||
./scripts/odysseus-backup snapshot
|
||||
|
||||
# List existing snapshots (most recent first)
|
||||
./scripts/odysseus-backup list
|
||||
|
||||
# Check a tarball's integrity without extracting it
|
||||
./scripts/odysseus-backup verify backups/odysseus-backup-20260101-120000.tar.gz
|
||||
|
||||
# Restore (destructive — see the warning below)
|
||||
./scripts/odysseus-backup restore backups/odysseus-backup-20260101-120000.tar.gz --yes
|
||||
```
|
||||
|
||||
The script depends only on the Python standard library, so any `python3` on your
|
||||
`PATH` will run it — you don't need the app's virtualenv active.
|
||||
|
||||
Every command prints a JSON result. Add `--pretty` for indented output.
|
||||
|
||||
## Commands
|
||||
|
||||
### `snapshot`
|
||||
|
||||
Writes a `tar.gz` of `data/` to `backups/<timestamp>.tar.gz`.
|
||||
|
||||
| Flag | Effect |
|
||||
| --- | --- |
|
||||
| `--out PATH` | Write to a specific path instead of the default `backups/` location. Must be **outside** `data/`. |
|
||||
| `--include-research` | Include `data/deep_research/` (skipped by default — research runs are large). |
|
||||
| `--include-attachments` | Include `data/mail-attachments/` (skipped by default — cached IMAP extractions, re-derivable). |
|
||||
|
||||
By default the snapshot includes everything under `data/` **except**
|
||||
`deep_research/` and `mail-attachments/`. Personal uploads and documents are
|
||||
included.
|
||||
|
||||
```bash
|
||||
# Snapshot straight to a mounted NAS path
|
||||
./scripts/odysseus-backup snapshot --out /mnt/nas/odysseus-$(date +%F).tar.gz
|
||||
|
||||
# Full snapshot including research runs and mail attachments
|
||||
./scripts/odysseus-backup snapshot --include-research --include-attachments
|
||||
```
|
||||
|
||||
### `list`
|
||||
|
||||
Lists the tarballs in `backups/`, most recent first, with size and modification
|
||||
time.
|
||||
|
||||
### `verify PATH`
|
||||
|
||||
Opens the tarball read-only and walks every member to confirm it is intact and
|
||||
safe to restore. Nothing is extracted. Use this before relying on an old backup
|
||||
or after copying one across machines.
|
||||
|
||||
### `restore PATH --yes`
|
||||
|
||||
Overwrites `data/` from a tarball.
|
||||
|
||||
> **Restore is destructive.** It replaces the current `data/` directory. `--yes`
|
||||
> is required so a mistyped command can't wipe your live state.
|
||||
|
||||
Restore is not a blind delete: before extracting, the tool **renames your current
|
||||
`data/` to `data.before-restore-<timestamp>`** in the repository root. If a
|
||||
restore turns out to be wrong, your previous state is still there — delete the
|
||||
restored `data/` and rename the stashed directory back. The restore path is also
|
||||
validated entry-by-entry: archives containing absolute paths, `..` segments,
|
||||
symlinks, or anything outside `data/` are rejected.
|
||||
|
||||
## Scheduling offsite backups
|
||||
|
||||
The tarball output composes cleanly with cron and any copy tool. For example, a
|
||||
nightly snapshot copied offsite:
|
||||
|
||||
```cron
|
||||
0 3 * * * cd /path/to/odysseus && ./scripts/odysseus-backup snapshot --out "/mnt/nas/odysseus-$(date +\%F).tar.gz"
|
||||
```
|
||||
|
||||
Swap the `--out` target for `scp`, `rclone`, `s3cmd`, or similar to push the
|
||||
snapshot to remote storage.
|
||||
|
||||
## Docker vs native installs
|
||||
|
||||
The tool reads `data/` and writes `backups/` relative to the repository root, so
|
||||
where you run it matters:
|
||||
|
||||
- **Native installs** — run it from the repo root as shown above. `data/` and
|
||||
`backups/` are both in the repo directory.
|
||||
- **Docker** — `docker-compose.yml` bind-mounts the host's `./data` to
|
||||
`/app/data`, so the live data is also present on the host. **Run the tool on
|
||||
the host** from the repo root; the snapshot reads the bind-mounted `./data` and
|
||||
writes to `./backups` on the host. Running it *inside* the container is not
|
||||
recommended, because `backups/` is not a mounted volume and the tarball would
|
||||
be lost when the container is recreated.
|
||||
|
||||
> **ChromaDB caveat (Docker only).** In the Docker setup, ChromaDB stores its
|
||||
> vectors in a separate Compose-managed volume (declared as `chromadb-data`),
|
||||
> **not** under `./data`. `odysseus-backup` therefore does not capture the Docker
|
||||
> ChromaDB store. Back it up separately if you need it. Compose prefixes the
|
||||
> volume with the project name, so find the real name first
|
||||
> (`docker volume ls | grep chromadb`), then archive it — for example:
|
||||
>
|
||||
> ```bash
|
||||
> docker run --rm -v <project>_chromadb-data:/data -v "$PWD":/backup \
|
||||
> alpine tar czf /backup/chromadb.tar.gz -C /data .
|
||||
> ```
|
||||
>
|
||||
> On native installs ChromaDB lives at `data/chroma/` and is included in the
|
||||
> snapshot normally.
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 3.0 MiB |
Binary file not shown.
|
After Width: | Height: | Size: 3.4 MiB |
Binary file not shown.
|
After Width: | Height: | Size: 1.1 MiB |
+3
-10
@@ -25,16 +25,9 @@
|
||||
--radius: 8px;
|
||||
}
|
||||
* { box-sizing: border-box; }
|
||||
html { scroll-behavior: smooth; scroll-padding-top: 60px; }
|
||||
/* REMOVED: "scroll-snap-type: y proximity"
|
||||
The idea was: >>Each section is a full-viewport "page" with its content centered,
|
||||
so only one shows at a time and the snap is obvious.<<
|
||||
|
||||
PROBLEM: sections easily grow taller than 100vh IRL
|
||||
This cause forced jumps mid-read. It's intrusive UX.
|
||||
The landing-page is not a PowerPoint presentation!
|
||||
|
||||
Preserved: CSS snap-points to avoid destroying code meta-data*/
|
||||
html { scroll-behavior: smooth; scroll-snap-type: y proximity; scroll-padding-top: 60px; }
|
||||
/* Each section is a full-viewport "page" with its content centered, so only
|
||||
one shows at a time and the snap is obvious. */
|
||||
.hero, section {
|
||||
scroll-snap-align: start; min-height: 100vh;
|
||||
display: flex; flex-direction: column; justify-content: center;
|
||||
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 1003 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 16 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 52 KiB After Width: | Height: | Size: 45 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 2.5 MiB |
@@ -1,107 +0,0 @@
|
||||
# Security CI guide
|
||||
|
||||
This project runs a set of automated security checks on pull requests and
|
||||
selected branch pushes. This page explains what each one does, whether it can
|
||||
block a merge, and the few one-time settings you should turn on to get the full
|
||||
benefit.
|
||||
|
||||
## What runs, and why
|
||||
|
||||
Most checks live in files under `.github/workflows/`. CodeQL is configured
|
||||
through GitHub's code scanning default setup, so it appears as a dynamic GitHub
|
||||
workflow instead of a checked-in workflow file. They run automatically; you do
|
||||
not start them.
|
||||
|
||||
| Check | What it protects against | Blocks a merge? |
|
||||
|---|---|---|
|
||||
| **Secret scan** (gitleaks) | An API key, token, or password being committed by mistake or on purpose | Yes |
|
||||
| **Workflow security** (actionlint + zizmor) | A broken or insecure automation file that could leak the repo's access token | Yes |
|
||||
| **Dependency review** | A pull request that adds a software library with a known security hole | Yes |
|
||||
| **pip-audit** | Known security holes in the Python libraries already used | No (advisory) |
|
||||
| **Container scan: hadolint** | Mistakes and insecure patterns in the `Dockerfile` | Yes |
|
||||
| **Container scan: Trivy** | Known security holes in the Docker image | No (advisory) |
|
||||
| **CodeQL** | Real bugs in the app's own code: injection, auth mistakes, path traversal | No (advisory) |
|
||||
|
||||
"Blocks a merge" means a red X appears on the pull request and, once you enable
|
||||
the setting below, the **Merge** button is disabled until it is fixed.
|
||||
|
||||
"Advisory" means it reports problems into the repository's **Security** tab so
|
||||
you can review them on your own schedule, but it never stops a merge. These are
|
||||
advisory on purpose: they often flag long-standing issues in other people's
|
||||
libraries, not something a given pull request introduced.
|
||||
|
||||
## Where results appear
|
||||
|
||||
- **Checks tab of a pull request**: the pass/fail of each check. A green tick is
|
||||
good; a red X needs attention.
|
||||
- **Security tab of the repository**: detailed findings from the advisory
|
||||
scanners (Trivy and CodeQL). This is your dashboard.
|
||||
|
||||
## If a check fails
|
||||
|
||||
- **Secret scan failed**: a real credential may have been committed. Treat it as
|
||||
leaked: rotate (regenerate) that key or token immediately, then remove it from
|
||||
the file. Do not just delete the commit; assume it was seen.
|
||||
- **Dependency review failed**: the pull request adds a library with a known
|
||||
vulnerability. Ask the contributor to use a patched version, or decline the
|
||||
change.
|
||||
- **hadolint / workflow security failed**: the contributor changed the
|
||||
`Dockerfile` or an automation file in a way the linter rejects. Ask them to
|
||||
address the message shown in the failed check.
|
||||
|
||||
## One-time settings to turn on
|
||||
|
||||
These two settings unlock the full value. You only do them once.
|
||||
|
||||
### 1. Require the blocking checks before merging
|
||||
|
||||
This makes the **Merge** button refuse to work until the gating checks pass.
|
||||
|
||||
1. Go to the repository on GitHub.
|
||||
2. Click **Settings** (top right of the repo).
|
||||
3. In the left sidebar, click **Branches**.
|
||||
4. Under **Branch protection rules**, click **Add branch ruleset** (or **Add
|
||||
rule**), and set the branch name pattern to `dev` (this is the branch all
|
||||
pull requests target; `main` is fast-forwarded at releases).
|
||||
5. Enable **Require status checks to pass before merging**.
|
||||
6. In the search box that appears, add these checks by name:
|
||||
- `Python syntax (compileall)`
|
||||
- `JS syntax (node --check)`
|
||||
- `gitleaks`
|
||||
- `actionlint`
|
||||
- `zizmor (Actions SAST)`
|
||||
- `hadolint (Dockerfile lint)`
|
||||
- `dependency-review (PR gate)`
|
||||
|
||||
The first two come from the correctness CI (`ci.yml`); the rest are this
|
||||
security suite. Leave pytest, pip-audit, Trivy, and CodeQL unchecked so they
|
||||
stay advisory.
|
||||
7. Also enable **Require a pull request before merging** and **Require review
|
||||
from Code Owners** (this uses the `.github/CODEOWNERS` file so every change
|
||||
needs your sign-off).
|
||||
8. Click **Create** / **Save changes**.
|
||||
|
||||
Note: a check name only appears in the list after it has run at least once, so
|
||||
let the workflows run on one pull request first, then add them here.
|
||||
|
||||
### 2. Turn on the Security tab features
|
||||
|
||||
1. **Settings -> Code security** (or **Code security and analysis**).
|
||||
2. Turn on **Dependency graph** (usually on by default for public repos) -- this
|
||||
powers Dependency review and Dependabot.
|
||||
3. Turn on **Dependabot alerts** and **Dependabot security updates**.
|
||||
4. Under **Code scanning**, use **Set up -> Default** for CodeQL. GitHub then
|
||||
runs CodeQL as a dynamic workflow without the fork-token limitations that
|
||||
affect checked-in advanced workflows.
|
||||
|
||||
Do not also add a checked-in CodeQL workflow while default setup is enabled:
|
||||
GitHub rejects advanced CodeQL uploads when default setup is active. If the
|
||||
project later needs an advanced CodeQL workflow, disable default setup first
|
||||
and keep only one CodeQL publishing path active.
|
||||
|
||||
## Keeping it current
|
||||
|
||||
`.github/dependabot.yml` opens small weekly pull requests to update Python and
|
||||
npm packages, the Docker base image, and the pinned automation actions
|
||||
themselves. Review and merge those like any other pull request; they keep the
|
||||
project patched without manual tracking.
|
||||
-425
@@ -1,425 +0,0 @@
|
||||
# Odysseus Setup Guide
|
||||
|
||||
This page keeps the detailed install, deployment, troubleshooting, and configuration notes out of the front README.
|
||||
|
||||
## Quick Start
|
||||
|
||||
> **Branch note:** `dev` is the default branch and contains the latest development changes, but it may be unstable. For the more stable curated branch, use [`main`](https://github.com/pewdiepie-archdaemon/odysseus/tree/main).
|
||||
|
||||
Defaults work out of the box: clone, run, then configure models/search/email
|
||||
inside **Settings**. Only edit `.env` for deployment-level overrides like
|
||||
`APP_BIND`, `APP_PORT`, `AUTH_ENABLED`, `DATABASE_URL`, or a pre-seeded admin password.
|
||||
|
||||
On first setup, Odysseus creates an admin account (`admin` unless
|
||||
`ODYSSEUS_ADMIN_USER` is set) and prints a temporary password in the terminal.
|
||||
For Docker installs, the same line is in `docker compose logs odysseus`.
|
||||
Use that for the first login, then change it in **Settings**.
|
||||
|
||||
Contributing? See [CONTRIBUTING.md](CONTRIBUTING.md) for setup, testing, and
|
||||
pull request guidelines.
|
||||
|
||||
### Docker (recommended)
|
||||
```bash
|
||||
git clone https://github.com/pewdiepie-archdaemon/odysseus.git
|
||||
cd odysseus
|
||||
cp .env.example .env # optional, but recommended for explicit defaults
|
||||
docker compose up -d --build
|
||||
```
|
||||
To include optional extras in the image (PDF viewer, Office extraction; includes AGPL PyMuPDF), build with `docker compose build --build-arg INSTALL_OPTIONAL=true` before `up`.
|
||||
|
||||
Open `http://localhost:7000` when the containers are healthy. Docker Compose
|
||||
binds the web UI to `127.0.0.1` by default. If the port is taken, set
|
||||
`APP_PORT=7001` in `.env` and recreate the container. Set `APP_BIND=0.0.0.0`
|
||||
only when you intentionally want LAN/reverse-proxy access.
|
||||
|
||||
> **On Apple Silicon (M-series) Macs:** Docker can't reach the Metal GPU, so
|
||||
> Cookbook serves local models on CPU only. For GPU-accelerated model serving,
|
||||
> run natively instead — see [Apple Silicon](#apple-silicon) below.
|
||||
|
||||
### Native Linux / macOS
|
||||
```bash
|
||||
git clone https://github.com/pewdiepie-archdaemon/odysseus.git
|
||||
cd odysseus
|
||||
python3 -m venv venv
|
||||
source venv/bin/activate
|
||||
pip install -r requirements.txt
|
||||
python setup.py
|
||||
python -m uvicorn app:app --host 127.0.0.1 --port 7000
|
||||
```
|
||||
Requirements: Python 3.11+. Cookbook also needs `tmux` for background model
|
||||
downloads and serves. The app itself is lightweight; local model serving is the
|
||||
heavy part and depends on the model, runtime, GPU, and VRAM, so small hosts can
|
||||
connect to API or remote model servers instead. Use `--host 0.0.0.0` only when you intentionally want LAN/reverse-proxy access.
|
||||
|
||||
### Apple Silicon
|
||||
Docker on macOS cannot use the Metal GPU. For GPU-accelerated Cookbook on an
|
||||
M-series Mac, run Odysseus natively:
|
||||
|
||||
```bash
|
||||
git clone https://github.com/pewdiepie-archdaemon/odysseus.git
|
||||
cd odysseus
|
||||
./start-macos.sh
|
||||
```
|
||||
|
||||
It launches at `http://127.0.0.1:7860`. To expose it to your phone over a trusted LAN/VPN such as Tailscale, bind all interfaces:
|
||||
|
||||
```bash
|
||||
ODYSSEUS_HOST=0.0.0.0 ./start-macos.sh
|
||||
# then open http://<tailscale-ip>:7860
|
||||
```
|
||||
|
||||
The script also reads `.env` at startup, so `APP_BIND=0.0.0.0` and `APP_PORT`
|
||||
set there are picked up automatically without a command-line override each run.
|
||||
|
||||
Keep `AUTH_ENABLED=true` (the default) before binding outside loopback. Do not
|
||||
expose this port directly to the public internet. To build a clickable app wrapper:
|
||||
|
||||
```bash
|
||||
./build-macos-app.sh
|
||||
```
|
||||
|
||||
<details>
|
||||
<summary>Cookbook, GPU, Ollama, and troubleshooting notes</summary>
|
||||
|
||||
**Docker bundled services.** Compose starts Odysseus, ChromaDB, SearXNG, and
|
||||
ntfy. Odysseus and the bundled service ports bind to `127.0.0.1` by default, so
|
||||
they are reachable from the host but not exposed to your LAN/public internet
|
||||
unless you opt in.
|
||||
|
||||
**Cookbook storage in Docker.** Downloads live in `./data/huggingface`
|
||||
(`~/.cache/huggingface` in the container). Cookbook-installed Python CLIs and
|
||||
serve engines live in `./data/local` (`~/.local` in the container), so they
|
||||
survive container recreation.
|
||||
|
||||
**Remote servers.** In **Cookbook -> Settings -> Servers**, generate the
|
||||
Odysseus SSH key and add the public key to the remote server's
|
||||
`~/.ssh/authorized_keys`. From the host you can also run:
|
||||
|
||||
```bash
|
||||
ssh-copy-id -i data/ssh/id_ed25519.pub user@server
|
||||
```
|
||||
|
||||
**Docker GPU overlays.** CPU-only users can skip this section. Cookbook can
|
||||
only detect GPUs that Docker exposes to the container — if the host runtime or
|
||||
device passthrough is not configured, Cookbook sees the iGPU, another card, or
|
||||
CPU instead of your intended GPU.
|
||||
|
||||
For NVIDIA, `scripts/check-docker-gpu.sh` diagnoses GPU passthrough and can
|
||||
optionally install the host runtime or update `.env`.
|
||||
|
||||
```bash
|
||||
# Read-only diagnostic (default — installs nothing, never edits .env):
|
||||
scripts/check-docker-gpu.sh
|
||||
|
||||
# Print OS-specific install commands without running them:
|
||||
scripts/check-docker-gpu.sh --print-install-commands
|
||||
|
||||
# Install NVIDIA Container Toolkit on Ubuntu/Debian (requires sudo):
|
||||
scripts/check-docker-gpu.sh --install-nvidia-toolkit
|
||||
|
||||
# Write COMPOSE_FILE to .env (only when GPU passthrough is confirmed working):
|
||||
scripts/check-docker-gpu.sh --enable-nvidia-overlay
|
||||
|
||||
# Full assisted setup — install toolkit, then enable overlay if passthrough works:
|
||||
scripts/check-docker-gpu.sh --install-nvidia-toolkit --enable-nvidia-overlay
|
||||
```
|
||||
|
||||
Safety notes:
|
||||
- The app never installs host GPU runtime automatically.
|
||||
- The app never edits `.env` automatically.
|
||||
- `.env` is only modified when `--enable-nvidia-overlay` is explicitly passed,
|
||||
and only after GPU passthrough succeeds. `--yes` skips prompts but does not
|
||||
bypass the passthrough gate.
|
||||
- `.env.bak.*` backups created by `--enable-nvidia-overlay` are ignored by
|
||||
Git and the Docker build context.
|
||||
|
||||
To enable manually without the script, add this to `.env`:
|
||||
|
||||
```bash
|
||||
COMPOSE_FILE=docker-compose.yml:docker/gpu.nvidia.yml
|
||||
```
|
||||
|
||||
**AMD / ROCm.** AMD setup is read-only diagnostic plus manual `.env` edit. Run:
|
||||
|
||||
```bash
|
||||
scripts/check-docker-amd-gpu.sh
|
||||
```
|
||||
|
||||
Then add the reported values to `.env`, replacing `RENDER_GID` with your host's
|
||||
numeric render group id:
|
||||
|
||||
```bash
|
||||
COMPOSE_FILE=docker-compose.yml:docker/gpu.amd.yml
|
||||
RENDER_GID=989
|
||||
```
|
||||
|
||||
For NVIDIA/AMD GPU support, also read the comments in the selected overlay file: docker/gpu.nvidia.yml or docker/gpu.amd.yml.
|
||||
|
||||
**Stack-management UIs (Portainer, Coolify, Dockhand, etc.).** These tools
|
||||
often accept only a single Compose file and do not reliably honor `COMPOSE_FILE`
|
||||
or multiple `-f` overlays. CLI users should keep using the `COMPOSE_FILE`
|
||||
overlay workflow above. For stack UIs, point the stack at one of the standalone
|
||||
files instead, which bundle the base stack plus the GPU settings:
|
||||
|
||||
- `docker-compose.gpu-nvidia.yml` — still requires the NVIDIA Container Toolkit
|
||||
on the host.
|
||||
- `docker-compose.gpu-amd.yml` — still requires host ROCm/kfd/DRI setup, the
|
||||
`video`/`render` group membership, and `RENDER_GID` when needed.
|
||||
|
||||
The base `docker-compose.yml` plus the `docker/gpu.*.yml` overlays remain the
|
||||
source of truth; the standalone files mirror them for single-file deployments.
|
||||
|
||||
Verify after enabling either overlay:
|
||||
|
||||
```bash
|
||||
docker compose exec odysseus nvidia-smi -L # NVIDIA
|
||||
docker compose exec odysseus sh -lc 'test -e /dev/kfd && test -d /dev/dri && ls -l /dev/kfd /dev/dri/renderD*' # AMD
|
||||
```
|
||||
|
||||
> **GPU passthrough ≠ llama.cpp CUDA.** `nvidia-smi` passing inside the
|
||||
> container confirms Docker GPU access, but llama.cpp also needs `cudart` and
|
||||
> the CUDA Toolkit at runtime. If Cookbook logs show `Unable to find cudart
|
||||
> library`, `Could NOT find CUDAToolkit`, `CUDA Toolkit not found`, or
|
||||
> tensors/layers assigned to CPU, that is a Cookbook/llama.cpp build issue —
|
||||
> not a Docker passthrough failure. Reinstall the serve engine via
|
||||
> **Cookbook → Dependencies** to get a CUDA-enabled build.
|
||||
>
|
||||
> The same split applies to AMD/ROCm: seeing `/dev/kfd` and `/dev/dri` inside
|
||||
> the container confirms device passthrough, not ROCm userspace or a
|
||||
> ROCm-enabled vLLM/llama.cpp build. `rocm-smi` and `rocminfo` are not expected
|
||||
> inside the slim Odysseus image.
|
||||
|
||||
**Ollama with Docker.** If Ollama runs on the host, add this endpoint in
|
||||
Settings:
|
||||
|
||||
```text
|
||||
http://host.docker.internal:11434/v1
|
||||
```
|
||||
|
||||
Ollama must listen outside its own loopback interface:
|
||||
|
||||
```bash
|
||||
OLLAMA_HOST=0.0.0.0:11434 ollama serve
|
||||
```
|
||||
|
||||
This connects Odysseus in Docker to an Ollama server that is already running on
|
||||
your host machine; it does not start Ollama inside the container.
|
||||
`host.docker.internal` is Docker's hostname for the host machine from inside the
|
||||
container. Cookbook **Serve** is a separate workflow for serving downloaded
|
||||
models through Odysseus/llama.cpp, so Windows users with an existing Ollama
|
||||
install usually only need to add the endpoint in Settings.
|
||||
|
||||
**Useful checks.**
|
||||
|
||||
```bash
|
||||
docker compose ps
|
||||
docker compose logs --tail=120 odysseus
|
||||
docker compose logs odysseus | grep -E 'ChromaDB|MemoryVectorStore|DEGRADED'
|
||||
```
|
||||
|
||||
**macOS details.** `start-macos.sh` installs Homebrew deps, creates the venv,
|
||||
runs setup, and starts uvicorn on port `7860` because AirPlay often holds
|
||||
`7000`. It uses llama.cpp/Ollama for Metal. vLLM/SGLang are CUDA/ROCm-only and
|
||||
do not run on macOS. MLX-only models are not served by Odysseus.
|
||||
|
||||
</details>
|
||||
|
||||
### Native Windows
|
||||
|
||||
**One-command launcher** (creates the venv, installs deps, runs setup, starts the
|
||||
server; safe to re-run):
|
||||
|
||||
```powershell
|
||||
git clone https://github.com/pewdiepie-archdaemon/odysseus.git
|
||||
cd odysseus
|
||||
powershell -ExecutionPolicy Bypass -File .\launch-windows.ps1
|
||||
```
|
||||
|
||||
Or do it by hand:
|
||||
|
||||
```powershell
|
||||
git clone https://github.com/pewdiepie-archdaemon/odysseus.git
|
||||
cd odysseus
|
||||
py -3.11 -m venv venv
|
||||
venv\Scripts\Activate.ps1
|
||||
pip install -r requirements.txt
|
||||
python setup.py
|
||||
python -m uvicorn app:app --host 127.0.0.1 --port 7000
|
||||
```
|
||||
|
||||
If `python` points at an older interpreter, use `py -3.12` (or another installed
|
||||
3.11+ version) for the venv step.
|
||||
|
||||
**Requirements:** Python 3.11+. The core app (chat, agent, memory, documents,
|
||||
email, calendar, deep research) runs fully native. For full **Cookbook** background
|
||||
model downloads and the agent shell tool, also install
|
||||
[Git for Windows](https://git-scm.com/download/win) (provides `bash.exe`).
|
||||
Local GPU *serving* of vLLM/SGLang needs Linux/WSL2; for a local model on Windows,
|
||||
[Ollama](https://ollama.com/download) is the easiest path — point Odysseus at
|
||||
`http://localhost:11434/v1` in Settings.
|
||||
|
||||
Open `http://localhost:7000`, log in with the generated admin password,
|
||||
and configure everything else inside **Settings**.
|
||||
|
||||
## Troubleshooting & Advanced Setup
|
||||
|
||||
### `chromadb-client` conflicts with embedded ChromaDB
|
||||
If `chromadb-client` (the lightweight HTTP-only package) is installed alongside the full `chromadb` package, Odysseus starts but ChromaDB silently falls back to HTTP-only mode and fails.
|
||||
|
||||
**Fix:** uninstall `chromadb-client` and force-reinstall the full package:
|
||||
```bash
|
||||
./venv/bin/pip uninstall chromadb-client -y
|
||||
./venv/bin/pip install --force-reinstall chromadb
|
||||
```
|
||||
|
||||
### HTTPS + LAN/Tailscale exposure
|
||||
To expose Odysseus on a local network or Tailscale with HTTPS:
|
||||
1. Change the bind address to `0.0.0.0` in `.env` (`APP_BIND=0.0.0.0` or `ODYSSEUS_HOST=0.0.0.0`).
|
||||
2. Generate a locally-trusted cert for your LAN/Tailscale IPs using [mkcert](https://github.com/FiloSottile/mkcert):
|
||||
```bash
|
||||
mkcert -install
|
||||
mkcert -cert-file cert.pem -key-file key.pem 192.168.1.100 tailscale-ip
|
||||
```
|
||||
3. Run `uvicorn` with the generated certs:
|
||||
```bash
|
||||
python -m uvicorn app:app --host 0.0.0.0 --port 7000 --ssl-certfile=cert.pem --ssl-keyfile=key.pem
|
||||
```
|
||||
4. Install the `mkcert` CA on any other device you want to access Odysseus from (e.g., for iOS, email the `rootCA.pem` to yourself, install the profile, and trust it in Certificate Trust Settings).
|
||||
|
||||
### Optional Dependencies
|
||||
`requirements-optional.txt` contains packages that unlock extra features. It is not installed by default.
|
||||
|
||||
| Package | Feature unlocked |
|
||||
|---------|-----------------|
|
||||
| `faster-whisper` | Local speech-to-text (microphone -> text) via the "local" STT provider. |
|
||||
| `ddgs` | DuckDuckGo as a search provider option. |
|
||||
| `PyMuPDF` | PDF page rendering in the side viewer panel and form-filling. (Note: AGPL-3.0) |
|
||||
| `markitdown` | Office/EPUB document text extraction (converts .docx/.xlsx/.pptx/.xls/.epub to Markdown). |
|
||||
|
||||
### Faster, reproducible installs with uv (optional)
|
||||
[uv](https://docs.astral.sh/uv/) works as a drop-in replacement for the
|
||||
venv + pip steps in the native install guides, no project changes are needed but this change results in faster installs along with a lockfile for reproducible environments. After [installing `uv`](https://docs.astral.sh/uv/getting-started/installation/), use:
|
||||
|
||||
```bash
|
||||
uv venv venv --python 3.13
|
||||
uv pip install -r requirements.txt
|
||||
# then continue as usual: python setup.py, uvicorn, ...
|
||||
```
|
||||
|
||||
`requirements.txt` is intentionally unpinned, so two installs at different times can produce different package versions. If you want a reproducible environment (e.g. across your own machines, or to roll back after a bad upgrade), snapshot and restore exact versions with:
|
||||
|
||||
```bash
|
||||
uv pip compile requirements.txt -o requirements.lock # snapshot current resolution
|
||||
uv pip sync requirements.lock # reproduce it exactly later
|
||||
```
|
||||
|
||||
`requirements.lock` is gitignored and platform-specific (compile it on the OS you deploy to). Regenerate it deliberately when you want to take upgrades. The plain `uv pip install -r requirements.txt` keeps following the unpinned requirements like pip does.
|
||||
|
||||
### Outlook / Office 365 email
|
||||
Odysseus email accounts currently use IMAP/SMTP username-password auth. Outlook
|
||||
and Microsoft 365 generally require OAuth instead, so normal Microsoft mailbox
|
||||
passwords will fail. See [docs/email-outlook.md](docs/email-outlook.md) for the
|
||||
current limitation and the planned integration direction.
|
||||
|
||||
## Security Notes
|
||||
Odysseus is a self-hosted workspace with powerful local tools: shell access, file uploads, model downloads, web research, email/calendar integrations, and API tokens. Treat it like an admin console.
|
||||
|
||||
- Keep `AUTH_ENABLED=true` for any network-accessible deployment.
|
||||
- Keep `LOCALHOST_BYPASS=false` outside local development.
|
||||
- Use `SECURE_COOKIES=true` when Odysseus is served through HTTPS by a trusted reverse proxy or private access gateway.
|
||||
- Do not expose it directly to the public internet without HTTPS and a trusted reverse proxy or private access layer.
|
||||
- Keep `.env`, `data/`, `logs/`, databases, uploads, generated media, backups, auth/session files, API keys, and model/provider tokens out of Git and private shares. They are ignored by default.
|
||||
- Review `data/auth.json` after first boot: disable open signup unless you intentionally want it, make only your own account admin, and keep demo/test accounts non-admin.
|
||||
- Non-admin users do not get shell/Python/file read/write by default, and admin-only routes/tools such as MCP management, API tokens, webhooks, model/cookbook serving, backup/vault, and app settings are admin-gated. Other features are controlled by per-user privileges, so review each user's privileges before exposing a deployment.
|
||||
- Rotate any API keys or tokens that were ever pasted into a shared chat, demo, screenshot, or log.
|
||||
- If you enable API tokens or webhooks, create separate tokens per integration and delete unused ones.
|
||||
- Prefer binding manual development runs to `127.0.0.1`; bind to `0.0.0.0` only when you intentionally want LAN/reverse-proxy access.
|
||||
- Keep ChromaDB, SearXNG, ntfy, Ollama, vLLM, llama.cpp, databases, and raw model/provider APIs internal-only. Expose only the authenticated Odysseus web/API entrypoint through your trusted proxy or private access layer.
|
||||
- Before publishing a fork, run `git status --short` and confirm no private files from `.env`, `data/`, `logs/`, uploads, backups, or local databases are staged.
|
||||
|
||||
### Private or proxied deployments
|
||||
Odysseus serves plain HTTP on its app port. Docker Compose binds Odysseus and the bundled services to `127.0.0.1` by default, so a typical production/private setup is:
|
||||
|
||||
1. Keep Odysseus on localhost, for example `127.0.0.1:7000`.
|
||||
2. Terminate HTTPS at a trusted reverse proxy or private access gateway.
|
||||
3. Put the authenticated Odysseus web/API entrypoint behind that layer.
|
||||
4. Keep raw service and model ports internal-only.
|
||||
|
||||
Cloudflare Access, Tailscale, Caddy, nginx, and Traefik can all fit this pattern; none are required by Odysseus. If your access layer reaches Odysseus on the same host, proxy to `http://127.0.0.1:7000` and keep `AUTH_ENABLED=true`, `LOCALHOST_BYPASS=false`, and `SECURE_COOKIES=true`.
|
||||
`ALLOWED_ORIGINS` lists exact permitted origins for cross-origin browser/API clients; ordinary same-origin reverse-proxy access usually does not need a special CORS entry.
|
||||
|
||||
Common internal-only ports from the default docs/compose setup:
|
||||
|
||||
| Port | Service |
|
||||
|---|---|
|
||||
| `7000` | Odysseus raw app port |
|
||||
| `8080` | SearXNG |
|
||||
| `8091` | ntfy |
|
||||
| `8100` | ChromaDB host port for manual/compose access |
|
||||
| `11434` | Ollama |
|
||||
| `8000-8020` | Common local model/provider APIs |
|
||||
|
||||
## Configuration
|
||||
Most setup is done inside the app with `/setup` or **Settings**. Use `.env`
|
||||
for deployment-level defaults and secrets you want present before first boot.
|
||||
Key settings:
|
||||
|
||||
| Variable | Default | Description |
|
||||
|---|---|---|
|
||||
| `LLM_HOST` | `localhost` | Your LLM server (e.g. `llm-host.local:8000`) |
|
||||
| `LLM_HOSTS` | -- | Comma-separated list for model discovery |
|
||||
| `OPENAI_API_KEY` | -- | Optional OpenAI key. Prefer adding providers in the app unless pre-seeding. |
|
||||
| `SEARXNG_INSTANCE` | `http://localhost:8080` | SearXNG URL. Docker overrides this to `http://searxng:8080`. |
|
||||
| `SEARXNG_SECRET` | generated on first Docker boot | Optional SearXNG cookie/CSRF secret. Leave blank unless you need to pin it. |
|
||||
| `APP_BIND` | `127.0.0.1` | Docker Compose host bind address for the web UI. Use `0.0.0.0` only for intentional LAN/reverse-proxy access. |
|
||||
| `APP_PORT` | `7000` | Docker Compose host port for the web UI. |
|
||||
| `APP_DATA_DIR` | `./data` | Docker Compose host directory for application data volumes. |
|
||||
| `APP_LOGS_DIR` | `./logs` | Docker Compose host directory for application logs. |
|
||||
| `AUTH_ENABLED` | `true` | Enable/disable login |
|
||||
| `LOCALHOST_BYPASS` | `false` | Development-only auth bypass for loopback requests. Keep false for shared/network deployments. |
|
||||
| `ALLOWED_ORIGINS` | `http://localhost,http://127.0.0.1` | Comma-separated exact permitted origins for cross-origin browser/API clients. |
|
||||
| `SECURE_COOKIES` | `false` | Set true when serving Odysseus through HTTPS at a trusted proxy or private access gateway. |
|
||||
| `DATABASE_URL` | `sqlite:///./data/app.db` | Database connection string |
|
||||
| `CHROMADB_HOST` | `localhost` | ChromaDB host for vector memory. Docker overrides this to `chromadb`. |
|
||||
| `CHROMADB_PORT` | `8100` | ChromaDB port for manual host runs. Docker overrides this to `8000`. |
|
||||
| `EMBEDDING_URL` | -- | OpenAI-compatible embeddings endpoint |
|
||||
| `ODYSSEUS_CHAT_UPLOAD_MAX_BYTES` | `10485760` | Chat/agent attachment cap in bytes. Raise for larger local PDFs or text documents. |
|
||||
| `ODYSSEUS_GALLERY_UPLOAD_MAX_BYTES` | `104857600` | Gallery image upload cap in bytes (100 MB). |
|
||||
| `ODYSSEUS_GALLERY_TRANSFORM_UPLOAD_MAX_BYTES` | `26214400` | Gallery transform input cap in bytes (25 MB). |
|
||||
| `ODYSSEUS_MEMORY_IMPORT_MAX_BYTES` | `10485760` | Memory import file cap in bytes (10 MB). |
|
||||
| `ODYSSEUS_PERSONAL_UPLOAD_MAX_BYTES` | `26214400` | Personal document upload cap in bytes (25 MB). |
|
||||
| `ODYSSEUS_EMAIL_COMPOSE_UPLOAD_MAX_BYTES` | `26214400` | Email compose attachment cap in bytes (25 MB). |
|
||||
| `ODYSSEUS_STT_MAX_AUDIO_BYTES` | `26214400` | Speech-to-text audio cap in bytes (25 MB). |
|
||||
| `ODYSSEUS_ICS_MAX_BYTES` | `10485760` | Calendar `.ics` import cap in bytes (10 MB). |
|
||||
|
||||
All upload-limit vars are validated (must be a positive integer) and optional; an invalid value fails fast at startup.
|
||||
|
||||
### Built-in MCP servers (optional setup)
|
||||
|
||||
Odysseus auto-registers a few built-in MCP servers at startup. The npx-based ones (currently the browser server, `@playwright/mcp`) only start when their npm package is already in the local npx cache. If a package isn't cached, that server is skipped with a startup log message explaining what to do, so a fresh install does not block on a multi-minute npm download or hang if Playwright system deps are missing.
|
||||
|
||||
To enable the browser MCP (page navigation, screenshots, vision), run once:
|
||||
|
||||
```bash
|
||||
npx -y @playwright/mcp@latest --version
|
||||
```
|
||||
|
||||
That installs `@playwright/mcp` plus Playwright (~300MB total). Restart Odysseus and the server will register at startup.
|
||||
|
||||
## Architecture
|
||||
```
|
||||
app.py # FastAPI entry point
|
||||
core/ auth, database, middleware, constants
|
||||
src/ llm_core, agent_loop, agent_tools, chat_processor, search/
|
||||
routes/ chat, session, document, memory, model … endpoints
|
||||
services/ docs, memory, search, hwfit (Cookbook) …
|
||||
static/ index.html + app.js + style.css + js/ (modular front-end)
|
||||
docs/ landing page (index.html) + preview clips
|
||||
```
|
||||
|
||||
## Data
|
||||
All user data lives in `data/` (gitignored): `app.db` (sessions, messages, documents),
|
||||
`memory.json`, `presets.json`, `uploads/`, `personal_docs/`, `chroma/`, `settings.json`.
|
||||
|
||||
To back up or restore everything in `data/`, see the
|
||||
[Backup & Restore guide](docs/backup-restore.md).
|
||||
@@ -102,7 +102,6 @@ python3 ~/.claude/skills/odysseus/scripts/odysseus_api.py POST /api/codex/memory
|
||||
|
||||
## Email draft + send
|
||||
|
||||
- Prefer `POST /api/codex/emails/draft-document` for agent-written email replies. It creates an editable Odysseus Document with `language: "email"` and does not touch IMAP/send.
|
||||
- `POST /api/codex/emails/draft` — body matches `SendEmailRequest` (`to`, `cc`, `bcc`, `subject`, `body`, `body_html`, `attachments`, `account_id`, `in_reply_to`, `references`). Requires `email:draft` (or `email:send`).
|
||||
- `POST /api/codex/emails/send` — same body. Requires `email:send`. Never send without explicit user instruction.
|
||||
|
||||
|
||||
@@ -17,11 +17,6 @@ def _usage() -> int:
|
||||
print(" odysseus_api.py todos add TITLE", file=sys.stderr)
|
||||
print(" odysseus_api.py emails list [limit]", file=sys.stderr)
|
||||
print(" odysseus_api.py emails read UID", file=sys.stderr)
|
||||
print(" odysseus_api.py emails draft-doc JSON_PAYLOAD", file=sys.stderr)
|
||||
print(" odysseus_api.py documents list [limit]", file=sys.stderr)
|
||||
print(" odysseus_api.py documents read DOC_ID", file=sys.stderr)
|
||||
print(" odysseus_api.py documents create JSON_PAYLOAD", file=sys.stderr)
|
||||
print(" odysseus_api.py documents delete DOC_ID", file=sys.stderr)
|
||||
print(" odysseus_api.py cookbook tasks", file=sys.stderr)
|
||||
print(" odysseus_api.py cookbook servers", file=sys.stderr)
|
||||
print(" odysseus_api.py cookbook cached [HOST]", file=sys.stderr)
|
||||
@@ -84,33 +79,6 @@ def main() -> int:
|
||||
method = "GET"
|
||||
path = f"/api/codex/emails/{sys.argv[3]}"
|
||||
body = None
|
||||
elif action in ("draft-doc", "draft_document") and len(sys.argv) >= 4:
|
||||
method = "POST"
|
||||
path = "/api/codex/emails/draft-document"
|
||||
body = " ".join(sys.argv[3:])
|
||||
else:
|
||||
return _usage()
|
||||
elif command in ("documents", "docs"):
|
||||
if len(sys.argv) < 3:
|
||||
return _usage()
|
||||
action = sys.argv[2].lower()
|
||||
if action == "list":
|
||||
method = "GET"
|
||||
limit = sys.argv[3] if len(sys.argv) >= 4 else "50"
|
||||
path = f"/api/codex/documents?limit={limit}"
|
||||
body = None
|
||||
elif action == "read" and len(sys.argv) >= 4:
|
||||
method = "GET"
|
||||
path = f"/api/codex/documents/{sys.argv[3]}"
|
||||
body = None
|
||||
elif action == "create" and len(sys.argv) >= 4:
|
||||
method = "POST"
|
||||
path = "/api/codex/documents"
|
||||
body = " ".join(sys.argv[3:])
|
||||
elif action == "delete" and len(sys.argv) >= 4:
|
||||
method = "DELETE"
|
||||
path = f"/api/codex/documents/{sys.argv[3]}"
|
||||
body = None
|
||||
else:
|
||||
return _usage()
|
||||
elif command == "cookbook":
|
||||
|
||||
@@ -17,11 +17,6 @@ def _usage() -> int:
|
||||
print(" odysseus_api.py todos add TITLE", file=sys.stderr)
|
||||
print(" odysseus_api.py emails list [limit]", file=sys.stderr)
|
||||
print(" odysseus_api.py emails read UID", file=sys.stderr)
|
||||
print(" odysseus_api.py emails draft-doc JSON_PAYLOAD", file=sys.stderr)
|
||||
print(" odysseus_api.py documents list [limit]", file=sys.stderr)
|
||||
print(" odysseus_api.py documents read DOC_ID", file=sys.stderr)
|
||||
print(" odysseus_api.py documents create JSON_PAYLOAD", file=sys.stderr)
|
||||
print(" odysseus_api.py documents delete DOC_ID", file=sys.stderr)
|
||||
print(" odysseus_api.py cookbook tasks", file=sys.stderr)
|
||||
print(" odysseus_api.py cookbook servers", file=sys.stderr)
|
||||
print(" odysseus_api.py cookbook cached [HOST]", file=sys.stderr)
|
||||
@@ -84,33 +79,6 @@ def main() -> int:
|
||||
method = "GET"
|
||||
path = f"/api/codex/emails/{sys.argv[3]}"
|
||||
body = None
|
||||
elif action in ("draft-doc", "draft_document") and len(sys.argv) >= 4:
|
||||
method = "POST"
|
||||
path = "/api/codex/emails/draft-document"
|
||||
body = " ".join(sys.argv[3:])
|
||||
else:
|
||||
return _usage()
|
||||
elif command in ("documents", "docs"):
|
||||
if len(sys.argv) < 3:
|
||||
return _usage()
|
||||
action = sys.argv[2].lower()
|
||||
if action == "list":
|
||||
method = "GET"
|
||||
limit = sys.argv[3] if len(sys.argv) >= 4 else "50"
|
||||
path = f"/api/codex/documents?limit={limit}"
|
||||
body = None
|
||||
elif action == "read" and len(sys.argv) >= 4:
|
||||
method = "GET"
|
||||
path = f"/api/codex/documents/{sys.argv[3]}"
|
||||
body = None
|
||||
elif action == "create" and len(sys.argv) >= 4:
|
||||
method = "POST"
|
||||
path = "/api/codex/documents"
|
||||
body = " ".join(sys.argv[3:])
|
||||
elif action == "delete" and len(sys.argv) >= 4:
|
||||
method = "DELETE"
|
||||
path = f"/api/codex/documents/{sys.argv[3]}"
|
||||
body = None
|
||||
else:
|
||||
return _usage()
|
||||
elif command == "cookbook":
|
||||
|
||||
@@ -102,7 +102,6 @@ python3 integrations/codex/scripts/odysseus_api.py POST /api/codex/memory '{"tex
|
||||
|
||||
## Email draft + send
|
||||
|
||||
- Prefer `POST /api/codex/emails/draft-document` for Codex-written email replies. It creates an editable Odysseus Document with `language: "email"` and does not touch IMAP/send.
|
||||
- `POST /api/codex/emails/draft` — body matches `SendEmailRequest` (`to`, `cc`, `bcc`, `subject`, `body`, `body_html`, `attachments`, `account_id`, `in_reply_to`, `references`). Requires `email:draft` (or `email:send`).
|
||||
- `POST /api/codex/emails/send` — same body. Requires `email:send`. Never send without explicit user instruction.
|
||||
|
||||
|
||||
+3
-28
@@ -30,26 +30,14 @@ function Fail($msg) {
|
||||
exit 1
|
||||
}
|
||||
|
||||
function Test-WindowsBashStub($path) {
|
||||
if (-not $path) { return $false }
|
||||
$lowered = $path.ToLowerInvariant()
|
||||
foreach ($stub in @("system32\bash.exe", "sysnative\bash.exe", "windowsapps\bash.exe")) {
|
||||
if ($lowered.Contains($stub)) { return $true }
|
||||
}
|
||||
return $false
|
||||
}
|
||||
|
||||
function Find-GitBash {
|
||||
$cmd = Get-Command bash -ErrorAction SilentlyContinue
|
||||
if ($cmd -and -not (Test-WindowsBashStub $cmd.Source)) { return $cmd.Source }
|
||||
if ($cmd) { return $cmd.Source }
|
||||
|
||||
$roots = @()
|
||||
foreach ($name in @("ProgramFiles", "ProgramW6432", "ProgramFiles(x86)", "LocalAppData")) {
|
||||
$base = [Environment]::GetEnvironmentVariable($name)
|
||||
if ($base) {
|
||||
$roots += (Join-Path $base "Git")
|
||||
if ($name -eq "LocalAppData") { $roots += (Join-Path $base "Programs\Git") }
|
||||
}
|
||||
if ($base) { $roots += (Join-Path $base "Git") }
|
||||
}
|
||||
$roots += @("C:\Program Files\Git", "C:\Program Files (x86)\Git")
|
||||
|
||||
@@ -141,20 +129,7 @@ if (-not (Find-GitBash)) {
|
||||
Write-Host " https://git-scm.com/download/win" -ForegroundColor Yellow
|
||||
}
|
||||
|
||||
# 6. Point CUDA_PATH at a real CUDA toolkit so GPU llama-cpp-python can import.
|
||||
$cudaBase = "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA"
|
||||
if (Test-Path $cudaBase) {
|
||||
$cudaBest = Get-ChildItem $cudaBase -Directory -ErrorAction SilentlyContinue |
|
||||
Where-Object { Test-Path (Join-Path $_.FullName "bin") } |
|
||||
Sort-Object { try { [version]($_.Name -replace "^v", "") } catch { [version]"0.0" } } -Descending |
|
||||
Select-Object -First 1
|
||||
if ($cudaBest) {
|
||||
$env:CUDA_PATH = $cudaBest.FullName
|
||||
Write-Host ("Using CUDA_PATH = " + $cudaBest.FullName) -ForegroundColor Cyan
|
||||
}
|
||||
}
|
||||
|
||||
# 7. Start the server (use `python -m uvicorn` - bare `uvicorn` may not be on PATH)
|
||||
# 6. Start the server (use `python -m uvicorn` - bare `uvicorn` may not be on PATH)
|
||||
Write-Step ("Starting Odysseus at http://{0}:{1}" -f $BindHost, $Port)
|
||||
Write-Host "Press Ctrl+C to stop."
|
||||
Write-Host ""
|
||||
|
||||
+2
-634
@@ -22,7 +22,6 @@ import os
|
||||
import os.path
|
||||
from pathlib import Path
|
||||
from datetime import datetime, timedelta
|
||||
import uuid
|
||||
|
||||
from mcp.server import Server
|
||||
from mcp.server.stdio import stdio_server
|
||||
@@ -68,59 +67,6 @@ def _db_path() -> Path:
|
||||
return Path(APP_DB)
|
||||
|
||||
|
||||
def _load_email_writing_style() -> str:
|
||||
"""Return the existing Settings > Email > Writing Style value."""
|
||||
try:
|
||||
settings_path = DATA_DIR / "settings.json"
|
||||
if not settings_path.exists():
|
||||
return ""
|
||||
settings = json.loads(settings_path.read_text(encoding="utf-8"))
|
||||
return str(settings.get("email_writing_style") or "").strip()
|
||||
except Exception:
|
||||
return ""
|
||||
|
||||
|
||||
def _writing_style_guidance() -> str:
|
||||
style = _load_email_writing_style()
|
||||
if not style:
|
||||
return (
|
||||
"No saved writing style is configured in Settings > Email > Writing Style. "
|
||||
"Use a concise, natural tone and do not invent facts."
|
||||
)
|
||||
return (
|
||||
"Use this saved writing style from Settings > Email > Writing Style when "
|
||||
"drafting the body. It overrides generic tone guidance:\n"
|
||||
f"{style}"
|
||||
)
|
||||
|
||||
|
||||
def _default_document_owner() -> str | None:
|
||||
"""Best-effort owner for MCP-created documents.
|
||||
|
||||
MCP stdio tools do not receive the browser request's authenticated user,
|
||||
but the document library is owner-filtered. Stamp drafts to the configured
|
||||
single/default admin so assistant-created email drafts are visible.
|
||||
"""
|
||||
owner = os.environ.get("ODYSSEUS_DOCUMENT_OWNER", "").strip()
|
||||
if owner:
|
||||
return owner
|
||||
try:
|
||||
auth_path = DATA_DIR / "auth.json"
|
||||
if not auth_path.exists():
|
||||
return None
|
||||
users = (json.loads(auth_path.read_text(encoding="utf-8")).get("users") or {})
|
||||
if not isinstance(users, dict) or not users:
|
||||
return None
|
||||
admins = [name for name, data in users.items() if isinstance(data, dict) and data.get("is_admin")]
|
||||
if len(admins) == 1:
|
||||
return admins[0]
|
||||
if len(users) == 1:
|
||||
return next(iter(users))
|
||||
return admins[0] if admins else next(iter(users))
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
|
||||
def _list_accounts_raw() -> list:
|
||||
"""Return list of dicts from the email_accounts table. Empty list if table
|
||||
missing or empty. Never raises."""
|
||||
@@ -885,109 +831,8 @@ def _smtp_connect(account=None, cfg=None):
|
||||
return conn
|
||||
|
||||
|
||||
def _read_agent_email_confirm_setting() -> bool:
|
||||
"""True if the user wants agent send_email/reply_to_email calls to be
|
||||
queued for manual approval instead of SMTPed immediately. Defaults to
|
||||
True so a fresh install is safe — agents have been observed inventing
|
||||
signatures and sending to real recipients without the user's review."""
|
||||
try:
|
||||
from src.settings import get_setting
|
||||
return bool(get_setting("agent_email_confirm", True))
|
||||
except Exception:
|
||||
return True
|
||||
|
||||
|
||||
def _stash_agent_draft(*, to, subject, body, in_reply_to=None, references=None,
|
||||
cc=None, bcc=None, account=None) -> dict:
|
||||
"""Insert the composed email into scheduled_emails with status
|
||||
'agent_draft' and a far-future send_at so the scheduled-send poller
|
||||
never picks it up. Returns the pending payload the model surfaces to
|
||||
the user (and that the chat UI can render as an approval card)."""
|
||||
try:
|
||||
from src.constants import SCHEDULED_EMAILS_DB
|
||||
except Exception:
|
||||
return {"success": False, "error": "Pending-email storage unavailable"}
|
||||
pending_id = uuid.uuid4().hex[:16]
|
||||
far_future = "9999-12-31T00:00:00"
|
||||
now = datetime.utcnow().isoformat()
|
||||
try:
|
||||
conn = sqlite3.connect(SCHEDULED_EMAILS_DB)
|
||||
# Touch the schema in case the email-routes init hasn't run yet
|
||||
# (MCP server can boot independently).
|
||||
conn.execute("""
|
||||
CREATE TABLE IF NOT EXISTS scheduled_emails (
|
||||
id TEXT PRIMARY KEY,
|
||||
to_addr TEXT NOT NULL,
|
||||
cc TEXT,
|
||||
bcc TEXT,
|
||||
subject TEXT,
|
||||
body TEXT NOT NULL,
|
||||
in_reply_to TEXT,
|
||||
references_hdr TEXT,
|
||||
attachments TEXT,
|
||||
send_at TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL,
|
||||
status TEXT NOT NULL DEFAULT 'pending',
|
||||
error TEXT,
|
||||
owner TEXT DEFAULT '',
|
||||
account_id TEXT,
|
||||
odysseus_kind TEXT
|
||||
)
|
||||
""")
|
||||
conn.execute("""
|
||||
INSERT INTO scheduled_emails
|
||||
(id, to_addr, cc, bcc, subject, body, in_reply_to, references_hdr,
|
||||
attachments, send_at, created_at, status, account_id, odysseus_kind, owner)
|
||||
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, 'agent_draft', ?, ?, ?)
|
||||
""", (
|
||||
pending_id,
|
||||
to if isinstance(to, str) else ", ".join(to),
|
||||
cc if isinstance(cc, str) else (", ".join(cc) if cc else None),
|
||||
bcc if isinstance(bcc, str) else (", ".join(bcc) if bcc else None),
|
||||
subject or "",
|
||||
body or "",
|
||||
in_reply_to or None,
|
||||
references if isinstance(references, str) else (" ".join(references) if references else None),
|
||||
"[]",
|
||||
far_future,
|
||||
now,
|
||||
account or None,
|
||||
"agent_draft",
|
||||
"",
|
||||
))
|
||||
conn.commit()
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
return {"success": False, "error": f"Failed to stash draft: {e}"}
|
||||
return {
|
||||
"success": True,
|
||||
"pending": True,
|
||||
"pending_id": pending_id,
|
||||
"to": to if isinstance(to, str) else ", ".join(to),
|
||||
"subject": subject or "",
|
||||
"body": body or "",
|
||||
"message": (
|
||||
"✋ Draft staged for your approval — nothing has been sent yet.\n"
|
||||
"Review the To/Subject/Body above. Reply 'send' to deliver, or "
|
||||
"'cancel' to discard."
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
def _send_email(to, subject, body, in_reply_to=None, references=None, cc=None, bcc=None, account=None):
|
||||
"""Send an email via SMTP. Returns dict with status.
|
||||
|
||||
When the `agent_email_confirm` setting is on (the default), the email
|
||||
is NOT SMTPed — instead it lands in scheduled_emails as an
|
||||
`agent_draft` row and the user reviews + approves it from the chat
|
||||
UI. This closes the auto-send hole that let earlier models invent
|
||||
signatures and ship them to real recipients without confirmation."""
|
||||
if _read_agent_email_confirm_setting():
|
||||
return _stash_agent_draft(
|
||||
to=to, subject=subject, body=body,
|
||||
in_reply_to=in_reply_to, references=references,
|
||||
cc=cc, bcc=bcc, account=account,
|
||||
)
|
||||
"""Send an email via SMTP. Returns dict with status."""
|
||||
send_account, cfg = _resolve_send_config(account)
|
||||
msg = EmailMessage()
|
||||
msg["From"] = _clean_header_value(cfg["from_address"])
|
||||
@@ -1051,340 +896,6 @@ def _send_email(to, subject, body, in_reply_to=None, references=None, cc=None, b
|
||||
}
|
||||
|
||||
|
||||
def _build_email_document_content(
|
||||
to,
|
||||
subject,
|
||||
body,
|
||||
*,
|
||||
cc=None,
|
||||
bcc=None,
|
||||
in_reply_to=None,
|
||||
references=None,
|
||||
source_uid=None,
|
||||
source_folder=None,
|
||||
):
|
||||
header_lines = [f"To: {to or ''}"]
|
||||
if cc:
|
||||
header_lines.append(f"Cc: {cc}")
|
||||
if bcc:
|
||||
header_lines.append(f"Bcc: {bcc}")
|
||||
header_lines.append(f"Subject: {subject or ''}")
|
||||
if in_reply_to:
|
||||
header_lines.append(f"In-Reply-To: {in_reply_to}")
|
||||
if references:
|
||||
header_lines.append(f"References: {references}")
|
||||
if source_uid:
|
||||
header_lines.append(f"X-Source-UID: {source_uid}")
|
||||
if source_folder:
|
||||
header_lines.append(f"X-Source-Folder: {source_folder}")
|
||||
return "\n".join(header_lines) + "\n---\n" + (body or "")
|
||||
|
||||
|
||||
def _merge_email_reply_body(existing_content: str, reply_body: str) -> str:
|
||||
"""Preserve email headers and quoted chain while replacing the editable reply body."""
|
||||
if "\n---\n" not in (existing_content or ""):
|
||||
return reply_body or ""
|
||||
head, body = existing_content.split("\n---\n", 1)
|
||||
quote_markers = (
|
||||
"---------- Previous message ----------",
|
||||
"-----Original Message-----",
|
||||
"----- Original Message -----",
|
||||
)
|
||||
quote_index = -1
|
||||
for marker in quote_markers:
|
||||
idx = body.find(marker)
|
||||
if idx != -1 and (quote_index == -1 or idx < quote_index):
|
||||
quote_index = idx
|
||||
quote = body[quote_index:].strip() if quote_index != -1 else ""
|
||||
merged_body = (reply_body or "").strip()
|
||||
if quote:
|
||||
merged_body = f"{merged_body}\n\n{quote}" if merged_body else quote
|
||||
return f"{head}\n---\n{merged_body}"
|
||||
|
||||
|
||||
def _create_email_draft_document(
|
||||
*,
|
||||
to,
|
||||
subject,
|
||||
body,
|
||||
title=None,
|
||||
cc=None,
|
||||
bcc=None,
|
||||
in_reply_to=None,
|
||||
references=None,
|
||||
source_uid=None,
|
||||
source_folder=None,
|
||||
account=None,
|
||||
source_message_id=None,
|
||||
):
|
||||
"""Create an Odysseus email compose document for user review. Does not send."""
|
||||
from core.database import SessionLocal, Document, DocumentVersion
|
||||
try:
|
||||
from src.event_bus import fire_event
|
||||
except Exception:
|
||||
fire_event = None
|
||||
|
||||
cfg = _load_config(account) if account else _load_config(None)
|
||||
content = _build_email_document_content(
|
||||
to,
|
||||
subject,
|
||||
body,
|
||||
cc=cc,
|
||||
bcc=bcc,
|
||||
in_reply_to=in_reply_to,
|
||||
references=references,
|
||||
source_uid=source_uid,
|
||||
source_folder=source_folder,
|
||||
)
|
||||
doc_id = str(uuid.uuid4())
|
||||
ver_id = str(uuid.uuid4())
|
||||
doc_title = (title or subject or "Email draft").strip() or "Email draft"
|
||||
doc_owner = _default_document_owner()
|
||||
|
||||
db = SessionLocal()
|
||||
try:
|
||||
if source_uid and source_folder:
|
||||
existing = (
|
||||
db.query(Document)
|
||||
.filter(Document.is_active == True)
|
||||
.filter(Document.language == "email")
|
||||
.filter(Document.owner == doc_owner)
|
||||
.filter(Document.source_email_uid == str(source_uid))
|
||||
.filter(Document.source_email_folder == source_folder)
|
||||
.order_by(Document.updated_at.desc())
|
||||
.first()
|
||||
)
|
||||
if existing and "\n---\n" in (existing.current_content or ""):
|
||||
existing.current_content = _merge_email_reply_body(existing.current_content, body or "")
|
||||
existing.version_count = (existing.version_count or 0) + 1
|
||||
ver = DocumentVersion(
|
||||
id=ver_id,
|
||||
document_id=existing.id,
|
||||
version_number=existing.version_count,
|
||||
content=existing.current_content,
|
||||
summary="Updated by email MCP draft tool",
|
||||
source="ai",
|
||||
)
|
||||
db.add(ver)
|
||||
db.commit()
|
||||
if fire_event:
|
||||
try:
|
||||
fire_event("document_updated", doc_owner)
|
||||
except Exception:
|
||||
pass
|
||||
return {
|
||||
"draft": True,
|
||||
"updated": True,
|
||||
"doc_id": existing.id,
|
||||
"title": existing.title,
|
||||
"language": existing.language,
|
||||
"account": cfg.get("account_name"),
|
||||
"account_id": cfg.get("account_id"),
|
||||
"to": to,
|
||||
"subject": subject,
|
||||
}
|
||||
|
||||
doc = Document(
|
||||
id=doc_id,
|
||||
session_id=None,
|
||||
title=doc_title,
|
||||
language="email",
|
||||
current_content=content,
|
||||
version_count=1,
|
||||
is_active=True,
|
||||
owner=doc_owner,
|
||||
source_email_uid=source_uid,
|
||||
source_email_folder=source_folder,
|
||||
source_email_account_id=cfg.get("account_id"),
|
||||
source_email_message_id=source_message_id,
|
||||
)
|
||||
ver = DocumentVersion(
|
||||
id=ver_id,
|
||||
document_id=doc_id,
|
||||
version_number=1,
|
||||
content=content,
|
||||
summary="Created by email MCP draft tool",
|
||||
source="ai",
|
||||
)
|
||||
db.add(doc)
|
||||
db.add(ver)
|
||||
db.commit()
|
||||
if fire_event:
|
||||
try:
|
||||
fire_event("document_created", doc_owner)
|
||||
except Exception:
|
||||
pass
|
||||
return {
|
||||
"draft": True,
|
||||
"doc_id": doc_id,
|
||||
"title": doc_title,
|
||||
"language": "email",
|
||||
"account": cfg.get("account_name"),
|
||||
"account_id": cfg.get("account_id"),
|
||||
"to": to,
|
||||
"subject": subject,
|
||||
}
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
|
||||
def _draft_reply_to_email(uid, body, folder="INBOX", reply_all=False, account=None, title=None):
|
||||
"""Create a threaded Odysseus reply draft document. Does not send."""
|
||||
conn = _imap_connect(account)
|
||||
conn.select(_q(folder), readonly=True)
|
||||
status, msg_data = conn.uid("FETCH", _b(uid), "(BODY.PEEK[])")
|
||||
conn.logout()
|
||||
if status != "OK" or not msg_data or not msg_data[0]:
|
||||
return {"error": f"Failed to fetch email UID {uid}"}
|
||||
raw = msg_data[0][1]
|
||||
orig = email.message_from_bytes(raw)
|
||||
|
||||
orig_subject = _decode_header(orig.get("Subject", ""))
|
||||
reply_subject = orig_subject if orig_subject.lower().startswith("re:") else f"Re: {orig_subject}"
|
||||
orig_message_id = orig.get("Message-ID", "")
|
||||
orig_references = orig.get("References", "")
|
||||
new_references = (orig_references + " " + orig_message_id).strip() if orig_references else orig_message_id
|
||||
|
||||
sender = _decode_header(orig.get("From", ""))
|
||||
_, sender_addr = email.utils.parseaddr(sender)
|
||||
to_addrs = sender_addr
|
||||
|
||||
cc = None
|
||||
if reply_all:
|
||||
cc_addrs = []
|
||||
cfg = _load_config(account)
|
||||
own_addrs = {
|
||||
(cfg.get("imap_user") or "").strip().lower(),
|
||||
(cfg.get("from_address") or "").strip().lower(),
|
||||
}
|
||||
for header_name in ("To", "Cc"):
|
||||
for _, addr in email.utils.getaddresses([orig.get(header_name, "")]):
|
||||
addr_l = (addr or "").strip().lower()
|
||||
if addr and addr != sender_addr and addr_l not in own_addrs:
|
||||
cc_addrs.append(addr)
|
||||
if cc_addrs:
|
||||
cc = ", ".join(dict.fromkeys(cc_addrs))
|
||||
|
||||
return _create_email_draft_document(
|
||||
to=to_addrs,
|
||||
subject=reply_subject,
|
||||
body=body,
|
||||
title=title or reply_subject,
|
||||
cc=cc,
|
||||
in_reply_to=orig_message_id,
|
||||
references=new_references,
|
||||
source_uid=uid,
|
||||
source_folder=folder,
|
||||
account=account,
|
||||
source_message_id=orig_message_id,
|
||||
)
|
||||
|
||||
|
||||
async def _ai_draft_reply_to_email(uid, folder="INBOX", reply_all=False, account=None, title=None):
|
||||
"""Generate a reply with Odysseus' AI-reply prompt/style, then create a compose doc."""
|
||||
read_result = _read_email(uid=uid, folder=folder, account=account)
|
||||
if "error" in read_result:
|
||||
return read_result
|
||||
|
||||
to_addr = read_result.get("from_address") or email.utils.parseaddr(read_result.get("from") or "")[1]
|
||||
subject = read_result.get("subject") or ""
|
||||
reply_subject = subject if subject.lower().startswith("re:") else f"Re: {subject}"
|
||||
original_body = read_result.get("body") or ""
|
||||
message_id = read_result.get("message_id") or ""
|
||||
|
||||
if not original_body.strip():
|
||||
return {"error": "No email body available for AI reply"}
|
||||
|
||||
try:
|
||||
from routes.email_helpers import (
|
||||
_EMAIL_REPLY_SYS_PROMPT_BASE,
|
||||
_apply_email_style_mechanics,
|
||||
_extract_reply,
|
||||
_load_settings,
|
||||
)
|
||||
from src.endpoint_resolver import (
|
||||
resolve_endpoint,
|
||||
resolve_utility_fallback_candidates,
|
||||
resolve_chat_fallback_candidates,
|
||||
)
|
||||
from src.llm_core import llm_call_async_with_fallback
|
||||
except Exception as exc:
|
||||
return {"error": f"AI reply helpers unavailable: {exc}"}
|
||||
|
||||
settings = _load_settings()
|
||||
style = settings.get("email_writing_style", "")
|
||||
system_prompt = _EMAIL_REPLY_SYS_PROMPT_BASE
|
||||
if style:
|
||||
system_prompt += f"\n\nWRITING STYLE TO MATCH:\n{style}"
|
||||
|
||||
user_msg = (
|
||||
f"Recipient: {to_addr}\nSubject: {reply_subject}\n\n"
|
||||
f"Original email and any current draft:\n{original_body[:6000]}\n\n"
|
||||
"Draft a reply. Return only the reply body text."
|
||||
)
|
||||
|
||||
candidates = []
|
||||
seen = set()
|
||||
|
||||
def _add(url, model, headers):
|
||||
key = (url or "", model or "")
|
||||
if not url or not model or key in seen:
|
||||
return
|
||||
seen.add(key)
|
||||
candidates.append((url, model, headers))
|
||||
|
||||
try:
|
||||
_add(*resolve_endpoint("utility", owner=None))
|
||||
except Exception:
|
||||
pass
|
||||
try:
|
||||
_add(*resolve_endpoint("default", owner=None))
|
||||
except Exception:
|
||||
pass
|
||||
try:
|
||||
utility_fallbacks = resolve_utility_fallback_candidates(owner=None) or []
|
||||
except TypeError:
|
||||
utility_fallbacks = resolve_utility_fallback_candidates() or []
|
||||
for cand in utility_fallbacks:
|
||||
_add(*cand)
|
||||
try:
|
||||
chat_fallbacks = resolve_chat_fallback_candidates(owner=None) or []
|
||||
except TypeError:
|
||||
chat_fallbacks = resolve_chat_fallback_candidates() or []
|
||||
for cand in chat_fallbacks:
|
||||
_add(*cand)
|
||||
|
||||
if not candidates:
|
||||
return {"error": "No LLM endpoint configured for AI reply"}
|
||||
|
||||
try:
|
||||
raw_reply = await llm_call_async_with_fallback(
|
||||
candidates,
|
||||
messages=[
|
||||
{"role": "system", "content": system_prompt},
|
||||
{"role": "user", "content": user_msg},
|
||||
],
|
||||
temperature=0.7,
|
||||
max_tokens=1024,
|
||||
timeout=60,
|
||||
)
|
||||
except Exception as exc:
|
||||
return {"error": f"AI reply generation failed: {exc}"}
|
||||
|
||||
reply = _apply_email_style_mechanics(_extract_reply(raw_reply or ""))
|
||||
if not reply:
|
||||
return {"error": "AI reply generation returned an empty response"}
|
||||
|
||||
return _draft_reply_to_email(
|
||||
uid=uid,
|
||||
body=reply,
|
||||
folder=folder,
|
||||
reply_all=reply_all,
|
||||
account=account,
|
||||
title=title or reply_subject,
|
||||
)
|
||||
|
||||
|
||||
def _reply_to_email(uid, body, folder="INBOX", reply_all=False, account=None):
|
||||
"""Reply to an existing email by UID. Threads via In-Reply-To/References."""
|
||||
conn = None
|
||||
@@ -1678,8 +1189,6 @@ async def list_tools() -> list[Tool]:
|
||||
name="send_email",
|
||||
description=(
|
||||
"Send a new email via SMTP. Provide recipient(s), subject, and body. "
|
||||
"This sends immediately; for normal assistant-written email, prefer "
|
||||
"draft_email so the user can review and send from Odysseus. "
|
||||
"For replying to an existing thread, use reply_to_email instead. "
|
||||
"Pass `account` to send from a non-default mailbox."
|
||||
),
|
||||
@@ -1696,35 +1205,10 @@ async def list_tools() -> list[Tool]:
|
||||
"required": ["to", "subject", "body"],
|
||||
},
|
||||
),
|
||||
Tool(
|
||||
name="draft_email",
|
||||
description=(
|
||||
"Create a new Odysseus email compose draft document. This DOES NOT send. "
|
||||
"Use this as the default way to write an email for the user: it opens "
|
||||
"a reviewable email document with To/Cc/Bcc/Subject/body, and the user "
|
||||
"can edit or press Send in Odysseus. "
|
||||
f"{_writing_style_guidance()}"
|
||||
),
|
||||
inputSchema={
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"to": {"type": "string", "description": "Recipient email address(es), comma-separated"},
|
||||
"subject": {"type": "string", "description": "Email subject line"},
|
||||
"body": {"type": "string", "description": "Draft body"},
|
||||
"cc": {"type": "string", "description": "CC address(es), comma-separated (optional)"},
|
||||
"bcc": {"type": "string", "description": "BCC address(es), comma-separated (optional)"},
|
||||
"title": {"type": "string", "description": "Optional Odysseus document title"},
|
||||
**ACCOUNT_PROP,
|
||||
},
|
||||
"required": ["to", "subject", "body"],
|
||||
},
|
||||
),
|
||||
Tool(
|
||||
name="reply_to_email",
|
||||
description=(
|
||||
"Reply to an existing email by UID. This sends immediately; for normal "
|
||||
"assistant-written replies, prefer draft_email_reply so the user can "
|
||||
"review and send from Odysseus. Automatically threads the reply with "
|
||||
"Reply to an existing email by UID. Automatically threads the reply with "
|
||||
"In-Reply-To and References headers, prefixes 'Re:' on the subject, and "
|
||||
"uses the original sender as the recipient. Set reply_all=true to also CC "
|
||||
"the original To/Cc recipients. For follow-up 'reply ...' requests, use "
|
||||
@@ -1742,49 +1226,6 @@ async def list_tools() -> list[Tool]:
|
||||
"required": ["uid", "body"],
|
||||
},
|
||||
),
|
||||
Tool(
|
||||
name="draft_email_reply",
|
||||
description=(
|
||||
"Create an Odysseus email reply draft document for an existing email UID. "
|
||||
"This DOES NOT send. It threads the draft with In-Reply-To/References, "
|
||||
"prefills the recipient and subject, and stores source email metadata so "
|
||||
"the user can review and send from the normal email composer. "
|
||||
f"{_writing_style_guidance()}"
|
||||
),
|
||||
inputSchema={
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"uid": {"type": "string", "description": "Exact Email UID from list_emails/read_email; never invent UID 1"},
|
||||
"body": {"type": "string", "description": "Draft reply body text"},
|
||||
"folder": {"type": "string", "description": "IMAP folder (default: INBOX)", "default": "INBOX"},
|
||||
"reply_all": {"type": "boolean", "description": "Reply to all recipients (default: false)", "default": False},
|
||||
"title": {"type": "string", "description": "Optional Odysseus document title"},
|
||||
**ACCOUNT_PROP,
|
||||
},
|
||||
"required": ["uid", "body"],
|
||||
},
|
||||
),
|
||||
Tool(
|
||||
name="ai_draft_email_reply",
|
||||
description=(
|
||||
"Generate an AI reply using Odysseus' existing AI Reply behavior, "
|
||||
"including Settings > Email > Writing Style, then create an email "
|
||||
"compose document for review. This DOES NOT send and does NOT save "
|
||||
"to the mailbox Drafts folder. Use this when the user asks you to "
|
||||
"write or draft a reply to an email without dictating the exact body."
|
||||
),
|
||||
inputSchema={
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"uid": {"type": "string", "description": "Exact Email UID from list_emails/read_email; never invent UID 1"},
|
||||
"folder": {"type": "string", "description": "IMAP folder (default: INBOX)", "default": "INBOX"},
|
||||
"reply_all": {"type": "boolean", "description": "Reply to all recipients (default: false)", "default": False},
|
||||
"title": {"type": "string", "description": "Optional Odysseus document title"},
|
||||
**ACCOUNT_PROP,
|
||||
},
|
||||
"required": ["uid"],
|
||||
},
|
||||
),
|
||||
Tool(
|
||||
name="archive_email",
|
||||
description="Move an email out of the inbox into the Archive folder. Use after handling an email you want to keep but no longer need in the inbox.",
|
||||
@@ -2111,31 +1552,6 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
|
||||
acct_note = f" (from {result['account']})" if result.get("account") else ""
|
||||
return [TextContent(type="text", text=f"Sent email to {result['to']} with subject '{result['subject']}'{acct_note}.")]
|
||||
|
||||
elif name == "draft_email":
|
||||
to = arguments.get("to")
|
||||
subject = arguments.get("subject")
|
||||
body = arguments.get("body")
|
||||
if not to or not subject or body is None:
|
||||
return [TextContent(type="text", text="Error: to, subject, and body are required")]
|
||||
result = _create_email_draft_document(
|
||||
to=to,
|
||||
subject=subject,
|
||||
body=body,
|
||||
title=arguments.get("title"),
|
||||
cc=arguments.get("cc"),
|
||||
bcc=arguments.get("bcc"),
|
||||
account=acct,
|
||||
)
|
||||
acct_note = f" from {result['account']}" if result.get("account") else ""
|
||||
return [TextContent(
|
||||
type="text",
|
||||
text=(
|
||||
f"Created Odysseus email draft `{result['title']}` "
|
||||
f"(document ID: {result['doc_id']}){acct_note}. "
|
||||
"It has not been sent; open the document in Odysseus to review and send."
|
||||
),
|
||||
)]
|
||||
|
||||
elif name == "reply_to_email":
|
||||
uid = arguments.get("uid")
|
||||
body = arguments.get("body")
|
||||
@@ -2157,54 +1573,6 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
|
||||
pass
|
||||
return [TextContent(type="text", text=f"Replied to UID {uid}: '{result['subject']}' → {result['to']}")]
|
||||
|
||||
elif name == "draft_email_reply":
|
||||
uid = arguments.get("uid")
|
||||
body = arguments.get("body")
|
||||
if not uid or body is None:
|
||||
return [TextContent(type="text", text="Error: uid and body are required")]
|
||||
result = _draft_reply_to_email(
|
||||
uid=uid,
|
||||
body=body,
|
||||
folder=arguments.get("folder", "INBOX"),
|
||||
reply_all=bool(arguments.get("reply_all", False)),
|
||||
account=acct,
|
||||
title=arguments.get("title"),
|
||||
)
|
||||
if "error" in result:
|
||||
return [TextContent(type="text", text=f"Error: {result['error']}")]
|
||||
acct_note = f" from {result['account']}" if result.get("account") else ""
|
||||
return [TextContent(
|
||||
type="text",
|
||||
text=(
|
||||
f"Created Odysseus reply draft `{result['title']}` for UID {uid} "
|
||||
f"(document ID: {result['doc_id']}){acct_note}. "
|
||||
"It has not been sent; open the document in Odysseus to review and send."
|
||||
),
|
||||
)]
|
||||
|
||||
elif name == "ai_draft_email_reply":
|
||||
uid = arguments.get("uid")
|
||||
if not uid:
|
||||
return [TextContent(type="text", text="Error: uid is required")]
|
||||
result = await _ai_draft_reply_to_email(
|
||||
uid=uid,
|
||||
folder=arguments.get("folder", "INBOX"),
|
||||
reply_all=bool(arguments.get("reply_all", False)),
|
||||
account=acct,
|
||||
title=arguments.get("title"),
|
||||
)
|
||||
if "error" in result:
|
||||
return [TextContent(type="text", text=f"Error: {result['error']}")]
|
||||
acct_note = f" from {result['account']}" if result.get("account") else ""
|
||||
return [TextContent(
|
||||
type="text",
|
||||
text=(
|
||||
f"Generated AI reply and created Odysseus compose draft "
|
||||
f"`{result['title']}` for UID {uid} (document ID: {result['doc_id']}){acct_note}. "
|
||||
"It has not been sent; open the document in Odysseus to review and send."
|
||||
),
|
||||
)]
|
||||
|
||||
elif name == "archive_email":
|
||||
uid = arguments.get("uid")
|
||||
if not uid:
|
||||
|
||||
@@ -6,7 +6,6 @@ Imports MemoryManager and MemoryVectorStore from the Odysseus codebase.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import sys
|
||||
import time
|
||||
from pathlib import Path
|
||||
@@ -24,55 +23,6 @@ _memory_manager = None
|
||||
_memory_vector = None
|
||||
_initialized = False
|
||||
|
||||
_OWNER_ENV_KEYS = ("ODYSSEUS_MCP_MEMORY_OWNER", "ODYSSEUS_MEMORY_OWNER")
|
||||
_OWNER_SCOPE_ERROR = (
|
||||
"Error: Memory MCP owner is not configured for an owner-scoped memory store. "
|
||||
"Set ODYSSEUS_MCP_MEMORY_OWNER for this server or use the owner-aware native memory tool."
|
||||
)
|
||||
|
||||
|
||||
def _configured_owner() -> str | None:
|
||||
for key in _OWNER_ENV_KEYS:
|
||||
owner = os.environ.get(key, "").strip()
|
||||
if owner:
|
||||
return owner
|
||||
return None
|
||||
|
||||
|
||||
def _entry_owner(entry: dict) -> str | None:
|
||||
owner = entry.get("owner")
|
||||
if owner is None:
|
||||
return None
|
||||
owner_text = str(owner).strip()
|
||||
return owner_text or None
|
||||
|
||||
|
||||
def _owner_scoped_store(entries: list[dict]) -> bool:
|
||||
return any(_entry_owner(entry) for entry in entries if isinstance(entry, dict))
|
||||
|
||||
|
||||
def _scope_entries() -> tuple[str | None, list[dict], list[dict], str | None]:
|
||||
"""Return configured owner, all entries, visible entries, and optional error."""
|
||||
entries = _memory_manager.load_all()
|
||||
owner = _configured_owner()
|
||||
if owner is None and _owner_scoped_store(entries):
|
||||
return None, entries, [], _OWNER_SCOPE_ERROR
|
||||
if owner is None:
|
||||
visible = [
|
||||
entry for entry in entries
|
||||
if isinstance(entry, dict) and _entry_owner(entry) is None
|
||||
]
|
||||
else:
|
||||
visible = [
|
||||
entry for entry in entries
|
||||
if isinstance(entry, dict) and _entry_owner(entry) == owner
|
||||
]
|
||||
return owner, entries, visible, None
|
||||
|
||||
|
||||
def _text_result(text: str) -> list[TextContent]:
|
||||
return [TextContent(type="text", text=text)]
|
||||
|
||||
|
||||
def _ensure_init():
|
||||
"""Lazy-init memory managers on first use."""
|
||||
@@ -125,46 +75,43 @@ async def list_tools() -> list[Tool]:
|
||||
@server.call_tool()
|
||||
async def call_tool(name: str, arguments: dict) -> list[TextContent]:
|
||||
if name != "manage_memory":
|
||||
return _text_result(f"Unknown tool: {name}")
|
||||
return [TextContent(type="text", text=f"Unknown tool: {name}")]
|
||||
|
||||
_ensure_init()
|
||||
if not _memory_manager:
|
||||
return _text_result("Error: Memory manager not available")
|
||||
return [TextContent(type="text", text="Error: Memory manager not available")]
|
||||
|
||||
action = arguments.get("action", "")
|
||||
|
||||
if action == "list":
|
||||
category_filter = arguments.get("category", "")
|
||||
_owner, _all_memories, memories, scope_error = _scope_entries()
|
||||
if scope_error:
|
||||
return _text_result(scope_error)
|
||||
memories = _memory_manager.load()
|
||||
if category_filter:
|
||||
memories = [m for m in memories if m.get("category", "").lower() == category_filter.lower()]
|
||||
if not memories:
|
||||
msg = "No memories found"
|
||||
if category_filter:
|
||||
msg += f" in category '{category_filter}'"
|
||||
return _text_result(msg + ".")
|
||||
|
||||
return [TextContent(type="text", text=msg + ".")]
|
||||
lines = [f"Found {len(memories)} memory entries:\n"]
|
||||
for m in memories:
|
||||
for m in memories[:100]:
|
||||
cat = m.get("category", "fact")
|
||||
mid = m.get("id", "?")[:8]
|
||||
text = m.get("text", "")
|
||||
if len(text) > 150:
|
||||
text = text[:150] + "..."
|
||||
lines.append(f"- [{cat}] `{mid}` — {text}")
|
||||
return _text_result("\n".join(lines))
|
||||
if len(memories) > 100:
|
||||
lines.append(f"... and {len(memories) - 100} more")
|
||||
return [TextContent(type="text", text="\n".join(lines))]
|
||||
|
||||
elif action == "add":
|
||||
text = arguments.get("text", "")
|
||||
category = arguments.get("category", "fact")
|
||||
if not text:
|
||||
return _text_result("Error: Memory text cannot be empty")
|
||||
owner, memories, _visible, scope_error = _scope_entries()
|
||||
if scope_error:
|
||||
return _text_result(scope_error)
|
||||
entry = _memory_manager.add_entry(text, source="ai_agent", category=category, owner=owner)
|
||||
return [TextContent(type="text", text="Error: Memory text cannot be empty")]
|
||||
entry = _memory_manager.add_entry(text, source="ai_agent", category=category)
|
||||
memories = _memory_manager.load_all()
|
||||
memories.append(entry)
|
||||
_memory_manager.save(memories)
|
||||
if _memory_vector and _memory_vector.healthy:
|
||||
@@ -172,28 +119,25 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
|
||||
_memory_vector.add(entry["id"], text)
|
||||
except Exception:
|
||||
pass
|
||||
return _text_result(f"Memory added: [{category}] {text} (id: {entry['id'][:8]})")
|
||||
return [TextContent(type="text", text=f"Memory added: [{category}] {text} (id: {entry['id'][:8]})")]
|
||||
|
||||
elif action == "edit":
|
||||
memory_id = arguments.get("memory_id", "")
|
||||
new_text = arguments.get("text", "")
|
||||
if not memory_id or not new_text:
|
||||
return _text_result("Error: edit needs memory_id and text")
|
||||
_owner, memories, visible, scope_error = _scope_entries()
|
||||
if scope_error:
|
||||
return _text_result(scope_error)
|
||||
return [TextContent(type="text", text="Error: edit needs memory_id and text")]
|
||||
memories = _memory_manager.load_all()
|
||||
found = False
|
||||
full_id = None
|
||||
for m in visible:
|
||||
if m.get("id", "").startswith(memory_id):
|
||||
full_id = m["id"]
|
||||
break
|
||||
if not full_id:
|
||||
return _text_result(f"Error: Memory '{memory_id}' not found")
|
||||
for m in memories:
|
||||
if m.get("id") == full_id:
|
||||
if m.get("id", "").startswith(memory_id):
|
||||
m["text"] = new_text
|
||||
m["timestamp"] = int(time.time())
|
||||
found = True
|
||||
full_id = m["id"]
|
||||
break
|
||||
if not found:
|
||||
return [TextContent(type="text", text=f"Error: Memory '{memory_id}' not found")]
|
||||
_memory_manager.save(memories)
|
||||
if _memory_vector and _memory_vector.healthy and full_id:
|
||||
try:
|
||||
@@ -201,26 +145,24 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
|
||||
_memory_vector.add(full_id, new_text)
|
||||
except Exception:
|
||||
pass
|
||||
return _text_result(f"Memory updated: {new_text}")
|
||||
return [TextContent(type="text", text=f"Memory updated: {new_text}")]
|
||||
|
||||
elif action == "delete":
|
||||
memory_id = arguments.get("memory_id", "")
|
||||
if not memory_id:
|
||||
return _text_result("Error: delete needs memory_id")
|
||||
_owner, memories, visible, scope_error = _scope_entries()
|
||||
if scope_error:
|
||||
return _text_result(scope_error)
|
||||
return [TextContent(type="text", text="Error: delete needs memory_id")]
|
||||
memories = _memory_manager.load_all()
|
||||
full_id = None
|
||||
deleted_text = ""
|
||||
deleted_category = ""
|
||||
for m in visible:
|
||||
for m in memories:
|
||||
if m.get("id", "").startswith(memory_id):
|
||||
full_id = m["id"]
|
||||
deleted_text = m.get("text", "")
|
||||
deleted_category = m.get("category", "")
|
||||
break
|
||||
if not full_id:
|
||||
return _text_result(f"Error: Memory '{memory_id}' not found")
|
||||
return [TextContent(type="text", text=f"Error: Memory '{memory_id}' not found")]
|
||||
memories = [m for m in memories if m.get("id") != full_id]
|
||||
_memory_manager.save(memories)
|
||||
if _memory_vector and _memory_vector.healthy and full_id:
|
||||
@@ -230,32 +172,30 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
|
||||
pass
|
||||
cat = f"[{deleted_category}] " if deleted_category else ""
|
||||
snippet = deleted_text if len(deleted_text) <= 120 else deleted_text[:117] + "..."
|
||||
return _text_result(f"Memory deleted: {cat}{snippet} (id: {memory_id})")
|
||||
return [TextContent(type="text", text=f"Memory deleted: {cat}{snippet} (id: {memory_id})")]
|
||||
|
||||
elif action == "search":
|
||||
query = arguments.get("text", "")
|
||||
if not query:
|
||||
return _text_result("Error: search needs text (query)")
|
||||
_owner, _all_memories, memories, scope_error = _scope_entries()
|
||||
if scope_error:
|
||||
return _text_result(scope_error)
|
||||
return [TextContent(type="text", text="Error: search needs text (query)")]
|
||||
memories = _memory_manager.load()
|
||||
if hasattr(_memory_manager, 'get_relevant_memories'):
|
||||
results = _memory_manager.get_relevant_memories(query, memories, threshold=0.05, max_items=20)
|
||||
else:
|
||||
query_lower = query.lower()
|
||||
results = [m for m in memories if query_lower in m.get("text", "").lower()][:20]
|
||||
if not results:
|
||||
return _text_result(f"No memories found matching '{query}'.")
|
||||
return [TextContent(type="text", text=f"No memories found matching '{query}'.")]
|
||||
lines = [f"Found {len(results)} matching memories:\n"]
|
||||
for m in results:
|
||||
cat = m.get("category", "fact")
|
||||
mid = m.get("id", "?")[:8]
|
||||
text = m.get("text", "")
|
||||
lines.append(f"- [{cat}] `{mid}` — {text}")
|
||||
return _text_result("\n".join(lines))
|
||||
return [TextContent(type="text", text="\n".join(lines))]
|
||||
|
||||
else:
|
||||
return _text_result(f"Error: Unknown action '{action}'. Use: list, add, edit, delete, search")
|
||||
return [TextContent(type="text", text=f"Error: Unknown action '{action}'. Use: list, add, edit, delete, search")]
|
||||
|
||||
|
||||
async def run():
|
||||
|
||||
Generated
+9
-12
@@ -5,16 +5,16 @@
|
||||
"packages": {
|
||||
"": {
|
||||
"dependencies": {
|
||||
"@anthropic-ai/sdk": "^0.104.1"
|
||||
"@anthropic-ai/sdk": "^0.98.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@antithesishq/bombadil": "^0.5.0"
|
||||
"@antithesishq/bombadil": "^0.3.2"
|
||||
}
|
||||
},
|
||||
"node_modules/@anthropic-ai/sdk": {
|
||||
"version": "0.104.1",
|
||||
"resolved": "https://registry.npmjs.org/@anthropic-ai/sdk/-/sdk-0.104.1.tgz",
|
||||
"integrity": "sha512-gGACa/+IaiXzRRmF96aOhamoBgapKRBiFWbmmTFP8aMkpaEcuStF+Q61bjo4vPxBM7gqWJNZqsngslRdnLHv0Q==",
|
||||
"version": "0.98.0",
|
||||
"resolved": "https://registry.npmjs.org/@anthropic-ai/sdk/-/sdk-0.98.0.tgz",
|
||||
"integrity": "sha512-N7aXtCvC5g6T1Y4V29lJjceu/zTkVkIZF0jdBvagr0TRFHuKeImffalGWEfqZKrvjH+IQbzJWw6TmSmUzrlMgg==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"json-schema-to-ts": "^3.1.1",
|
||||
@@ -33,14 +33,11 @@
|
||||
}
|
||||
},
|
||||
"node_modules/@antithesishq/bombadil": {
|
||||
"version": "0.5.0",
|
||||
"resolved": "https://registry.npmjs.org/@antithesishq/bombadil/-/bombadil-0.5.0.tgz",
|
||||
"integrity": "sha512-s0zImmr0iyvSP6QcVLvf40CUiZYIdWBAxiq20uhzujwvfitYa3PGJN652k/pLtVccHM/JrGQxZdvLnihZpltHA==",
|
||||
"version": "0.3.2",
|
||||
"resolved": "https://registry.npmjs.org/@antithesishq/bombadil/-/bombadil-0.3.2.tgz",
|
||||
"integrity": "sha512-ATy1w9ZY5gbny1H8DFc7rxZitT7DLLLFDiGcRZe+8TQiUrV5tLO+IJGOVNNLp3RpCqjZqSsxGiKoQsx31ipV1g==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"bin": {
|
||||
"bombadil": "bin/bombadil.js"
|
||||
}
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/@babel/runtime": {
|
||||
"version": "7.29.7",
|
||||
|
||||
+2
-2
@@ -4,9 +4,9 @@
|
||||
"url": "https://github.com/pewdiepie-archdaemon/odysseus.git"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@antithesishq/bombadil": "^0.5.0"
|
||||
"@antithesishq/bombadil": "^0.3.2"
|
||||
},
|
||||
"dependencies": {
|
||||
"@anthropic-ai/sdk": "^0.104.1"
|
||||
"@anthropic-ai/sdk": "^0.98.0"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -15,8 +15,4 @@ markers = [
|
||||
"area_helpers: self-tests for the shared test helpers in tests/helpers/",
|
||||
"area_unit: pure parser / utility tests that do not clearly belong elsewhere",
|
||||
"area_uncategorized: tests not yet matched by the taxonomy (fallback)",
|
||||
# Fast-lane marker (issue #3443). Opt-in and orthogonal to the area_*/sub_*
|
||||
# taxonomy. The fast lane runs `not slow`; mark a test slow only with
|
||||
# duration evidence (see tests/run_focus.py --durations and tests/README.md).
|
||||
"slow: opt-in marker for known-slow tests; excluded by the fast lane (not slow)",
|
||||
]
|
||||
|
||||
@@ -15,7 +15,7 @@ faster-whisper
|
||||
# DuckDuckGo as a search provider option.
|
||||
# Install if you want DDG in the search-provider dropdown.
|
||||
# Alternatives: SearXNG, Brave, Tavily, Serper, Google PSE.
|
||||
ddgs
|
||||
duckduckgo-search
|
||||
|
||||
# PDF form-filling feature (fillable AcroForm detection, field extraction,
|
||||
# value/annotation/signature stamping, page rendering for the form overlay).
|
||||
@@ -33,4 +33,4 @@ PyMuPDF
|
||||
# magika (onnxruntime), already a core dep via fastembed. We avoid the
|
||||
# [all]/Azure/audio extras (cloud + heavy). Pinned to a release >30 days old per
|
||||
# the dependency-age discussion in issue #485.
|
||||
markitdown[docx,pptx,xlsx,xls]==0.1.6
|
||||
markitdown[docx,pptx,xlsx,xls]==0.1.5
|
||||
|
||||
+2
-6
@@ -3,8 +3,8 @@ uvicorn
|
||||
python-multipart
|
||||
python-dotenv
|
||||
httpx
|
||||
pydantic>=2.13.4
|
||||
pydantic-settings>=2.14.1
|
||||
pydantic>=2.0
|
||||
pydantic-settings>=2.0
|
||||
SQLAlchemy
|
||||
pypdf
|
||||
beautifulsoup4
|
||||
@@ -43,7 +43,3 @@ qrcode[pil]
|
||||
croniter
|
||||
pytest
|
||||
pytest-asyncio
|
||||
# starlette.testclient prefers httpx2 since Starlette 1.2.0 and warns on every
|
||||
# TestClient import when only classic httpx is present. Runtime code keeps
|
||||
# using `httpx` above; this is test-client only.
|
||||
httpx2
|
||||
|
||||
@@ -1,31 +0,0 @@
|
||||
import re
|
||||
|
||||
from fastapi import HTTPException
|
||||
|
||||
|
||||
_REMOTE_HOST_RE = re.compile(
|
||||
r"^(?:[A-Za-z0-9][A-Za-z0-9._-]*@)?[A-Za-z0-9][A-Za-z0-9._-]*$"
|
||||
)
|
||||
_SSH_PORT_RE = re.compile(r"^\d{1,5}$")
|
||||
|
||||
|
||||
def validate_remote_host(v: str | None) -> str | None:
|
||||
if v is None or v == "":
|
||||
return None
|
||||
if not _REMOTE_HOST_RE.match(v):
|
||||
raise HTTPException(
|
||||
400,
|
||||
"Invalid remote_host — must be host or user@host, no SSH option syntax",
|
||||
)
|
||||
return v
|
||||
|
||||
|
||||
def validate_ssh_port(v: str | None) -> str | None:
|
||||
if v is None or v == "":
|
||||
return None
|
||||
if not _SSH_PORT_RE.fullmatch(str(v)):
|
||||
raise HTTPException(400, "Invalid ssh_port")
|
||||
port = int(v)
|
||||
if port < 1 or port > 65535:
|
||||
raise HTTPException(400, "Invalid ssh_port")
|
||||
return str(port)
|
||||
@@ -25,13 +25,10 @@ ALLOWED_SCOPES = {
|
||||
"calendar:write",
|
||||
"memory:read",
|
||||
"memory:write",
|
||||
"cookbook:read",
|
||||
"cookbook:launch",
|
||||
}
|
||||
TOKEN_PROFILES = {
|
||||
"chat": ["chat"],
|
||||
"codex_todos": ["todos:read", "todos:write"],
|
||||
"codex_documents": ["documents:read", "documents:write"],
|
||||
"codex_email_drafts": ["email:read", "email:draft", "documents:read", "documents:write"],
|
||||
}
|
||||
|
||||
@@ -68,7 +65,6 @@ def _normalize_scopes(scopes: str | list[str] | None = None, profile: str | None
|
||||
ensure_before("calendar:write", "calendar:read")
|
||||
ensure_before("memory:write", "memory:read")
|
||||
ensure_before("email:draft", "email:read")
|
||||
ensure_before("cookbook:launch", "cookbook:read")
|
||||
|
||||
return normalized or [DEFAULT_SCOPES]
|
||||
|
||||
@@ -155,19 +151,14 @@ def setup_api_token_routes() -> APIRouter:
|
||||
@router.patch("/tokens/{token_id}")
|
||||
async def update_token(request: Request, token_id: str):
|
||||
require_admin(request)
|
||||
current_user = get_current_user(request)
|
||||
try:
|
||||
payload = await request.json()
|
||||
except Exception:
|
||||
payload = {}
|
||||
if not isinstance(payload, dict):
|
||||
payload = {}
|
||||
with get_db_session() as db:
|
||||
token = db.query(ApiToken).filter(ApiToken.id == token_id).first()
|
||||
if not token:
|
||||
raise HTTPException(404, "Token not found")
|
||||
if current_user and token.owner != current_user:
|
||||
raise HTTPException(403, "Not your token")
|
||||
if isinstance(payload.get("name"), str) and payload["name"].strip():
|
||||
token.name = payload["name"].strip()[:MAX_NAME_LEN]
|
||||
# Only touch scopes when the caller actually sent them. A partial
|
||||
@@ -195,14 +186,10 @@ def setup_api_token_routes() -> APIRouter:
|
||||
@router.delete("/tokens/{token_id}")
|
||||
def delete_token(request: Request, token_id: str):
|
||||
require_admin(request)
|
||||
current_user = get_current_user(request)
|
||||
with get_db_session() as db:
|
||||
token = db.query(ApiToken).filter(ApiToken.id == token_id).first()
|
||||
if not token:
|
||||
deleted = db.query(ApiToken).filter(ApiToken.id == token_id).delete()
|
||||
if not deleted:
|
||||
raise HTTPException(404, "Token not found")
|
||||
if current_user and token.owner != current_user:
|
||||
raise HTTPException(403, "Not your token")
|
||||
db.delete(token)
|
||||
_invalidate_cache(request)
|
||||
return {"status": "deleted"}
|
||||
|
||||
|
||||
+13
-193
@@ -7,13 +7,7 @@ import asyncio
|
||||
import logging
|
||||
import os
|
||||
|
||||
import json
|
||||
import re
|
||||
from pathlib import Path
|
||||
|
||||
from core.atomic_io import atomic_write_json, atomic_write_text
|
||||
from core.auth import AuthManager, SetAdminResult
|
||||
from src.constants import DEEP_RESEARCH_DIR, MEMORY_FILE, SKILLS_DIR
|
||||
from core.auth import AuthManager
|
||||
from src.rate_limiter import RateLimiter
|
||||
from src.settings_scrub import scrub_settings
|
||||
from src.settings import (
|
||||
@@ -73,11 +67,6 @@ class DeleteUserRequest(BaseModel):
|
||||
class RenameUserRequest(BaseModel):
|
||||
username: str
|
||||
|
||||
|
||||
class SetAdminRequest(BaseModel):
|
||||
is_admin: bool
|
||||
|
||||
|
||||
class SetOpenRegistrationRequest(BaseModel):
|
||||
enabled: bool
|
||||
|
||||
@@ -302,30 +291,9 @@ def setup_auth_routes(auth_manager: AuthManager) -> APIRouter:
|
||||
if new_username in auth_manager.users:
|
||||
raise HTTPException(409, "Username already taken")
|
||||
|
||||
# Gate on auth first. Every mutation below is contingent on this
|
||||
# succeeding — doing it last meant a rejected rename (e.g. reserved
|
||||
# username) left file-backed owner fields already rewritten with no
|
||||
# way to roll them back.
|
||||
ok = auth_manager.rename_user(old_username, new_username, user)
|
||||
if not ok:
|
||||
raise HTTPException(400, "Cannot rename user")
|
||||
|
||||
def _rollback_auth_rename() -> bool:
|
||||
# On self-rename the admin session has already moved to the new
|
||||
# username, so the rollback must authenticate as the new user.
|
||||
rollback_user = new_username if user == old_username else user
|
||||
try:
|
||||
return bool(auth_manager.rename_user(new_username, old_username, rollback_user))
|
||||
except Exception as rollback_err:
|
||||
logger.error(
|
||||
"Failed to roll back auth rename %s -> %s after owner migration failure: %s",
|
||||
new_username, old_username, rollback_err,
|
||||
)
|
||||
return False
|
||||
|
||||
# Usernames are ownership keys for user data. Rename the common
|
||||
# owner-scoped DB rows so the account keeps access to its sessions,
|
||||
# docs, email accounts, tasks, etc.
|
||||
# owner-scoped DB rows before changing auth so the account keeps
|
||||
# access to its sessions, docs, email accounts, tasks, etc.
|
||||
try:
|
||||
from sqlalchemy import func
|
||||
from core.database import Base, SessionLocal
|
||||
@@ -348,11 +316,6 @@ def setup_auth_routes(auth_manager: AuthManager) -> APIRouter:
|
||||
db.close()
|
||||
except Exception as e:
|
||||
logger.error("Failed to rename owner references %s -> %s: %s", old_username, new_username, e)
|
||||
if not _rollback_auth_rename():
|
||||
logger.error(
|
||||
"Auth rename %s -> %s could not be rolled back after owner migration failure",
|
||||
old_username, new_username,
|
||||
)
|
||||
raise HTTPException(500, "Failed to rename user data")
|
||||
|
||||
# Per-user prefs are JSON-backed, not SQL-backed.
|
||||
@@ -372,116 +335,9 @@ def setup_auth_routes(auth_manager: AuthManager) -> APIRouter:
|
||||
except Exception as e:
|
||||
logger.warning("Failed to rename user prefs %s -> %s: %s", old_username, new_username, e)
|
||||
|
||||
# In-flight deep-research tasks live in the process-local
|
||||
# ResearchHandler registry. They are not covered by the persisted JSON
|
||||
# migration above, but the research routes filter and cancel by this
|
||||
# owner field while the job is running. Do this before sweeping
|
||||
# completed JSON files so a job that finishes during the rename saves
|
||||
# with the new owner or is caught by the disk sweep below.
|
||||
try:
|
||||
rh = getattr(request.app.state, "research_handler", None)
|
||||
rename_owner = getattr(rh, "rename_owner", None)
|
||||
if callable(rename_owner):
|
||||
rename_owner(old_username, new_username)
|
||||
except Exception as e:
|
||||
logger.warning("Failed to rename active research tasks %s -> %s: %s", old_username, new_username, e)
|
||||
|
||||
# deep_research: each completed report is a standalone JSON file with
|
||||
# an `owner` field. research_routes filters by d.get("owner") == user,
|
||||
# so a stale owner makes every report invisible to the renamed user.
|
||||
try:
|
||||
dr_dir = Path(DEEP_RESEARCH_DIR)
|
||||
if dr_dir.is_dir():
|
||||
for p in dr_dir.glob("*.json"):
|
||||
try:
|
||||
d = json.loads(p.read_text(encoding="utf-8"))
|
||||
if str(d.get("owner", "")).strip().lower() == old_username:
|
||||
d["owner"] = new_username
|
||||
atomic_write_json(str(p), d)
|
||||
except Exception as err:
|
||||
logger.warning("Failed to update research owner in %s: %s", p.name, err)
|
||||
except Exception as e:
|
||||
logger.warning("Failed to rename research owner references %s -> %s: %s", old_username, new_username, e)
|
||||
|
||||
# memory.json: a flat JSON array where each entry carries an `owner`
|
||||
# field. memory_manager.load(owner=user) filters on it, so stale
|
||||
# entries disappear from the memory panel.
|
||||
try:
|
||||
if os.path.isfile(MEMORY_FILE):
|
||||
with open(MEMORY_FILE, encoding="utf-8") as fh:
|
||||
entries = json.loads(fh.read())
|
||||
if isinstance(entries, list):
|
||||
changed = False
|
||||
for entry in entries:
|
||||
if isinstance(entry, dict) and str(entry.get("owner", "")).strip().lower() == old_username:
|
||||
entry["owner"] = new_username
|
||||
changed = True
|
||||
if changed:
|
||||
atomic_write_json(MEMORY_FILE, entries)
|
||||
except Exception as e:
|
||||
logger.warning("Failed to rename memory.json owner references %s -> %s: %s", old_username, new_username, e)
|
||||
|
||||
# uploads.json: upload rows use owner metadata for access checks and
|
||||
# owner-prefixed index keys for dedupe. Rename both so attachments keep
|
||||
# resolving after the account username changes.
|
||||
try:
|
||||
upload_handler = getattr(request.app.state, "upload_handler", None)
|
||||
rename_owner = getattr(upload_handler, "rename_owner", None)
|
||||
if callable(rename_owner):
|
||||
rename_owner(old_username, new_username)
|
||||
except Exception as e:
|
||||
logger.warning("Failed to rename upload owner references %s -> %s: %s", old_username, new_username, e)
|
||||
|
||||
# skills: SKILL.md frontmatter carries owner: <username>; the usage
|
||||
# sidecar (_usage.json) keys entries as owner::skill-name. Both must
|
||||
# be updated or the renamed user's Skills panel goes empty.
|
||||
try:
|
||||
skills_root = Path(SKILLS_DIR)
|
||||
if skills_root.is_dir():
|
||||
_owner_re = re.compile(
|
||||
r'(?m)^(owner:\s*)' + re.escape(old_username) + r'\s*$',
|
||||
re.IGNORECASE,
|
||||
)
|
||||
for p in skills_root.rglob("SKILL.md"):
|
||||
try:
|
||||
text = p.read_text(encoding="utf-8")
|
||||
new_text = _owner_re.sub(r'\g<1>' + new_username, text)
|
||||
if new_text != text:
|
||||
atomic_write_text(str(p), new_text)
|
||||
except Exception as err:
|
||||
logger.warning("Failed to update skill owner in %s: %s", p, err)
|
||||
usage_path = skills_root / "_usage.json"
|
||||
if usage_path.is_file():
|
||||
try:
|
||||
usage = json.loads(usage_path.read_text(encoding="utf-8"))
|
||||
if isinstance(usage, dict):
|
||||
new_usage = {}
|
||||
changed = False
|
||||
for k, v in usage.items():
|
||||
owner_part, sep, skill_part = k.partition("::")
|
||||
if sep and owner_part.lower() == old_username:
|
||||
new_usage[new_username + "::" + skill_part] = v
|
||||
changed = True
|
||||
else:
|
||||
new_usage[k] = v
|
||||
if changed:
|
||||
atomic_write_json(str(usage_path), new_usage)
|
||||
except Exception as err:
|
||||
logger.warning("Failed to update skills usage keys %s -> %s: %s", old_username, new_username, err)
|
||||
except Exception as e:
|
||||
logger.warning("Failed to rename skills owner references %s -> %s: %s", old_username, new_username, e)
|
||||
|
||||
# The in-memory session cache (session_manager.sessions) stores each
|
||||
# session's owner at load time. Without this patch the renamed user's
|
||||
# sessions are invisible on the next /api/sessions call because
|
||||
# get_sessions_for_user does an exact `s.owner == username` comparison
|
||||
# against stale in-memory values.
|
||||
sm = getattr(request.app.state, "session_manager", None)
|
||||
if sm is not None:
|
||||
for sess in list(getattr(sm, "sessions", {}).values()):
|
||||
if str(getattr(sess, "owner", None) or "").strip().lower() == old_username:
|
||||
sess.owner = new_username
|
||||
|
||||
ok = auth_manager.rename_user(old_username, new_username, user)
|
||||
if not ok:
|
||||
raise HTTPException(400, "Cannot rename user")
|
||||
# The owner-rename loop above updated ApiToken.owner in the DB, but the
|
||||
# bearer-token cache still maps each token to the OLD owner. Without
|
||||
# refreshing it, the renamed user's API tokens resolve to the old (now
|
||||
@@ -492,31 +348,6 @@ def setup_auth_routes(auth_manager: AuthManager) -> APIRouter:
|
||||
invalidator()
|
||||
return {"ok": True, "username": new_username, "renamed_self": old_username == user}
|
||||
|
||||
@router.put("/users/{username}/admin")
|
||||
async def set_user_admin(username: str, body: SetAdminRequest, request: Request):
|
||||
"""Promote/demote a user to/from admin. Admin only.
|
||||
|
||||
The last remaining admin can't be demoted (no lockout). Self-demotion
|
||||
is allowed while another admin exists; the `self` flag tells the UI to
|
||||
reload the acting user into the normal-user view.
|
||||
"""
|
||||
user = _get_current_user(request)
|
||||
if not user or not auth_manager.is_admin(user):
|
||||
raise HTTPException(403, "Admin only")
|
||||
result = auth_manager.set_admin(username, body.is_admin, user)
|
||||
if result is SetAdminResult.USER_NOT_FOUND:
|
||||
raise HTTPException(404, "User not found")
|
||||
if result is SetAdminResult.NOT_AUTHORIZED:
|
||||
raise HTTPException(403, "Admin only")
|
||||
if result is SetAdminResult.LAST_ADMIN:
|
||||
raise HTTPException(400, "Cannot demote the last admin")
|
||||
target = (username or "").strip().lower()
|
||||
return {
|
||||
"ok": True,
|
||||
"is_admin": body.is_admin,
|
||||
"self": target == (user or "").strip().lower(),
|
||||
}
|
||||
|
||||
@router.post("/signup-toggle", deprecated=True)
|
||||
async def toggle_signup(request: Request):
|
||||
"""
|
||||
@@ -547,23 +378,7 @@ def setup_auth_routes(auth_manager: AuthManager) -> APIRouter:
|
||||
user = _get_current_user(request)
|
||||
if not user or not auth_manager.is_admin(user):
|
||||
raise HTTPException(403, "Admin only")
|
||||
|
||||
def _invalidate_api_token_cache():
|
||||
try:
|
||||
invalidator = getattr(request.app.state, "invalidate_token_cache", None)
|
||||
if invalidator:
|
||||
invalidator()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
try:
|
||||
ok = auth_manager.delete_user(body.username, user)
|
||||
except Exception:
|
||||
# delete_user can touch ApiToken rows before a later auth-store write
|
||||
# fails. Dirty the bearer cache anyway so a partial token purge does
|
||||
# not leave already-cached tokens authenticating until restart.
|
||||
_invalidate_api_token_cache()
|
||||
raise
|
||||
ok = auth_manager.delete_user(body.username, user)
|
||||
if not ok:
|
||||
raise HTTPException(400, "Cannot delete user")
|
||||
# delete_user removes the user's ApiToken rows, but the bearer-auth
|
||||
@@ -571,7 +386,12 @@ def setup_auth_routes(auth_manager: AuthManager) -> APIRouter:
|
||||
# rebuilds when flagged dirty. Without this, a deleted user's already
|
||||
# cached token keeps authenticating until some other token op or a
|
||||
# restart clears the cache. Mirror what the token routes do.
|
||||
_invalidate_api_token_cache()
|
||||
try:
|
||||
invalidator = getattr(request.app.state, "invalidate_token_cache", None)
|
||||
if invalidator:
|
||||
invalidator()
|
||||
except Exception:
|
||||
pass
|
||||
return {"ok": True}
|
||||
|
||||
# ---- Feature visibility (admin-managed) ----
|
||||
|
||||
@@ -101,17 +101,11 @@ def setup_backup_routes(memory_manager, preset_manager, skills_manager) -> APIRo
|
||||
# ── Skills ──
|
||||
if "skills" in body and isinstance(body["skills"], list):
|
||||
existing = skills_manager.load_all()
|
||||
# Dedup against THIS user's own skills only. Using every tenant's
|
||||
# rows (load_all) meant a skill whose id/name/title matched any
|
||||
# other user's was silently skipped, so the importing user lost
|
||||
# their own data — same cross-tenant bug fixed for memories above.
|
||||
# The full store is still saved back below.
|
||||
own = [s for s in existing if s.get("owner") == user]
|
||||
existing_names = {s.get("name") for s in own if s.get("name")}
|
||||
existing_ids = {s.get("id") for s in own if s.get("id")}
|
||||
existing_names = {s.get("name") for s in existing if s.get("name")}
|
||||
existing_ids = {s.get("id") for s in existing if s.get("id")}
|
||||
existing_titles = {
|
||||
(s.get("title") or s.get("description") or "").strip().lower()
|
||||
for s in own
|
||||
for s in existing
|
||||
}
|
||||
added = 0
|
||||
for skill in body["skills"]:
|
||||
|
||||
+53
-71
@@ -11,7 +11,7 @@ from pydantic import BaseModel
|
||||
from sqlalchemy import or_, and_
|
||||
from dateutil.rrule import rrulestr
|
||||
|
||||
from core.database import SessionLocal, CalendarCal, CalendarDeletedEvent, CalendarEvent
|
||||
from core.database import SessionLocal, CalendarCal, CalendarEvent
|
||||
from src.auth_helpers import require_user
|
||||
from src.upload_limits import read_upload_limited, ICS_MAX_BYTES
|
||||
|
||||
@@ -126,54 +126,6 @@ def _resolve_base_uid(uid: str) -> str:
|
||||
raise ValueError("malformed compound UID: missing base before ::")
|
||||
return base
|
||||
|
||||
|
||||
async def _push_caldav_event_after_commit(owner: str, uid: str, action: str):
|
||||
"""Best-effort CalDAV write-through. Local writes stay authoritative if
|
||||
the remote server is unreachable; pending flags let /sync retry later."""
|
||||
try:
|
||||
result = {"ok": True}
|
||||
if action == "create":
|
||||
from src.caldav_sync import push_event_create
|
||||
result = await push_event_create(owner, uid)
|
||||
elif action == "update":
|
||||
from src.caldav_sync import push_event_update
|
||||
result = await push_event_update(owner, uid)
|
||||
elif action == "delete":
|
||||
from src.caldav_sync import push_event_delete
|
||||
result = await push_event_delete(owner, uid)
|
||||
if result and not result.get("ok") and not result.get("skipped"):
|
||||
raise RuntimeError(result.get("error") or result)
|
||||
except Exception as e:
|
||||
logger.warning("CalDAV %s push failed for uid=%s: %s", action, uid, e)
|
||||
if action in {"create", "update"}:
|
||||
db = SessionLocal()
|
||||
try:
|
||||
ev = _get_or_404_event(db, uid, owner)
|
||||
ev.caldav_sync_pending = action
|
||||
db.commit()
|
||||
except Exception:
|
||||
db.rollback()
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
|
||||
def _record_caldav_delete_tombstone(db, ev: CalendarEvent, owner: str) -> None:
|
||||
if not (ev.calendar and ev.calendar.source == "caldav"):
|
||||
return
|
||||
tombstone = db.query(CalendarDeletedEvent).filter(
|
||||
CalendarDeletedEvent.uid == ev.uid,
|
||||
CalendarDeletedEvent.owner == owner,
|
||||
).first()
|
||||
if not tombstone:
|
||||
tombstone = CalendarDeletedEvent(uid=ev.uid, owner=owner)
|
||||
db.add(tombstone)
|
||||
tombstone.calendar_id = ev.calendar_id
|
||||
tombstone.remote_href = ev.remote_href
|
||||
tombstone.remote_etag = ev.remote_etag
|
||||
tombstone.caldav_base_url = getattr(ev.calendar, "caldav_base_url", None)
|
||||
tombstone.summary = ev.summary or ""
|
||||
tombstone.last_error = None
|
||||
|
||||
# ── Pydantic models ──
|
||||
|
||||
class EventCreate(BaseModel):
|
||||
@@ -891,35 +843,36 @@ def setup_calendar_routes() -> APIRouter:
|
||||
return {"ok": False, "error": str(e)[:200]}
|
||||
|
||||
@router.post("/sync")
|
||||
async def sync_caldav_endpoint(request: Request, direction: str = "pull"):
|
||||
"""Sync events with the configured CalDAV server.
|
||||
async def sync_caldav_endpoint(request: Request):
|
||||
"""Pull events from the configured CalDAV server into local DB.
|
||||
Returns counts + any per-calendar errors. Called by the frontend
|
||||
on calendar open and by the periodic scheduler loop."""
|
||||
owner = _require_user(request)
|
||||
from src.caldav_sync import sync_caldav_direction
|
||||
return await sync_caldav_direction(owner, direction)
|
||||
|
||||
from src.caldav_sync import sync_caldav
|
||||
return await sync_caldav(owner)
|
||||
|
||||
@router.delete("/calendars/{cal_id}")
|
||||
async def delete_calendar(request: Request, cal_id: str):
|
||||
async def delete_calendar(cal_id: str, request: Request):
|
||||
owner = _require_user(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
cal = _get_or_404_calendar(db, cal_id, owner)
|
||||
db.query(CalendarEvent).filter(CalendarEvent.calendar_id == cal_id).delete()
|
||||
cal = db.query(CalendarCal).filter(
|
||||
CalendarCal.id == cal_id,
|
||||
CalendarCal.owner == owner,
|
||||
).first()
|
||||
if not cal:
|
||||
raise HTTPException(404, "Calendar not found")
|
||||
db.delete(cal)
|
||||
db.commit()
|
||||
return {"ok": True}
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
db.rollback()
|
||||
logger.error("Failed to delete calendar %s: %s", cal_id, e)
|
||||
raise HTTPException(500, "Failed to delete calendar")
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
|
||||
@router.get("/calendars")
|
||||
async def list_calendars(request: Request):
|
||||
owner = _require_user(request)
|
||||
@@ -1050,12 +1003,19 @@ def setup_calendar_routes() -> APIRouter:
|
||||
is_utc=_is_utc and not data.all_day,
|
||||
rrule=data.rrule or "",
|
||||
color=data.color or None,
|
||||
caldav_sync_pending="create" if cal.source == "caldav" else None,
|
||||
)
|
||||
db.add(ev)
|
||||
db.commit()
|
||||
if cal.source == "caldav":
|
||||
await _push_caldav_event_after_commit(owner, uid, "create")
|
||||
# Push the new event to the remote so it appears on the user's
|
||||
# other devices — the sync is otherwise pull-only (#800).
|
||||
from src.caldav_writeback import writeback_event
|
||||
await writeback_event(owner, cal.source, cal.id, {
|
||||
"uid": uid, "summary": data.summary, "description": data.description,
|
||||
"location": data.location, "dtstart": dtstart, "dtend": dtend,
|
||||
"all_day": data.all_day, "is_utc": _is_utc and not data.all_day,
|
||||
"rrule": data.rrule or "",
|
||||
})
|
||||
return {"ok": True, "uid": uid}
|
||||
except HTTPException:
|
||||
raise
|
||||
@@ -1101,12 +1061,15 @@ def setup_calendar_routes() -> APIRouter:
|
||||
ev.rrule = data.rrule
|
||||
if data.color is not None:
|
||||
ev.color = data.color if data.color else None
|
||||
is_caldav = ev.calendar and ev.calendar.source == "caldav"
|
||||
if is_caldav:
|
||||
ev.caldav_sync_pending = "update"
|
||||
db.commit()
|
||||
if is_caldav:
|
||||
await _push_caldav_event_after_commit(owner, base_uid, "update")
|
||||
cal = db.query(CalendarCal).filter(CalendarCal.id == ev.calendar_id).first()
|
||||
if cal and cal.source == "caldav":
|
||||
from src.caldav_writeback import writeback_event
|
||||
await writeback_event(owner, cal.source, cal.id, {
|
||||
"uid": ev.uid, "summary": ev.summary, "description": ev.description,
|
||||
"location": ev.location, "dtstart": ev.dtstart, "dtend": ev.dtend,
|
||||
"all_day": ev.all_day, "is_utc": ev.is_utc, "rrule": ev.rrule or "",
|
||||
})
|
||||
return {"ok": True}
|
||||
except HTTPException:
|
||||
raise
|
||||
@@ -1127,13 +1090,15 @@ def setup_calendar_routes() -> APIRouter:
|
||||
db = SessionLocal()
|
||||
try:
|
||||
ev = _get_or_404_event(db, base_uid, owner)
|
||||
is_caldav = ev.calendar and ev.calendar.source == "caldav"
|
||||
if is_caldav:
|
||||
_record_caldav_delete_tombstone(db, ev, owner)
|
||||
# Capture what the remote push needs BEFORE the row is gone.
|
||||
_cal = db.query(CalendarCal).filter(CalendarCal.id == ev.calendar_id).first()
|
||||
_is_caldav = bool(_cal and _cal.source == "caldav")
|
||||
_cal_id, _ev_uid = ev.calendar_id, ev.uid
|
||||
db.delete(ev)
|
||||
db.commit()
|
||||
if is_caldav:
|
||||
await _push_caldav_event_after_commit(owner, base_uid, "delete")
|
||||
if _is_caldav:
|
||||
from src.caldav_writeback import writeback_event
|
||||
await writeback_event(owner, "caldav", _cal_id, {"uid": _ev_uid}, delete=True)
|
||||
return {"ok": True}
|
||||
except HTTPException:
|
||||
raise
|
||||
@@ -1187,6 +1152,23 @@ def setup_calendar_routes() -> APIRouter:
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
@router.delete("/calendars/{cal_id}")
|
||||
async def delete_calendar(request: Request, cal_id: str):
|
||||
owner = _require_user(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
cal = _get_or_404_calendar(db, cal_id, owner)
|
||||
db.query(CalendarEvent).filter(CalendarEvent.calendar_id == cal_id).delete()
|
||||
db.delete(cal)
|
||||
db.commit()
|
||||
return {"ok": True}
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
db.rollback()
|
||||
return {"error": str(e)}
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
# Hard cap on ICS upload (ICS_MAX_BYTES, default 10 MB). Loading the whole
|
||||
# file into memory is unavoidable with python-icalendar, so an unbounded
|
||||
|
||||
+18
-143
@@ -14,7 +14,7 @@ from core.database import Session as DBSession, ModelEndpoint
|
||||
from src.llm_core import normalize_model_id
|
||||
from src.endpoint_resolver import normalize_base
|
||||
from src.context_compactor import maybe_compact, trim_for_context
|
||||
from src.auth_helpers import effective_user
|
||||
from src.auth_helpers import get_current_user
|
||||
from src.prompt_security import untrusted_context_message
|
||||
from routes.prefs_routes import _load_for_user as load_prefs_for_user
|
||||
|
||||
@@ -78,7 +78,7 @@ def _enforce_chat_privileges(request, sess) -> None:
|
||||
which means unrestricted allowed_models / zero cap -> no-op for them.
|
||||
"""
|
||||
try:
|
||||
user = effective_user(request)
|
||||
user = get_current_user(request)
|
||||
except Exception:
|
||||
user = None
|
||||
if not user:
|
||||
@@ -159,17 +159,9 @@ async def auto_name_session(session_manager, sess):
|
||||
return
|
||||
|
||||
owner = getattr(sess, "owner", None)
|
||||
t_url, t_model, t_headers = resolve_task_endpoint(owner=owner)
|
||||
if not t_model:
|
||||
# If no task/utility model is configured at all, fall back to
|
||||
# the session's own model so auto-naming still works even on
|
||||
# minimal setups.
|
||||
from src.endpoint_resolver import resolve_endpoint
|
||||
_fallback = resolve_endpoint("default", owner=owner)
|
||||
if _fallback and _fallback[1]:
|
||||
t_url, t_model, t_headers = _fallback
|
||||
else:
|
||||
t_url, t_model, t_headers = sess.endpoint_url, sess.model, sess.headers
|
||||
t_url, t_model, t_headers = resolve_task_endpoint(
|
||||
sess.endpoint_url, sess.model, sess.headers, owner=owner,
|
||||
)
|
||||
if not t_model:
|
||||
logger.debug("[auto-name] No model provided, skipping")
|
||||
return
|
||||
@@ -346,11 +338,11 @@ def add_user_message(sess, chat_handler, preprocessed: PreprocessedMessage, inco
|
||||
def fire_message_event(request, webhook_manager, session_id: str, sess, message: str, compare_mode: bool = False):
|
||||
"""Fire webhook and event_bus events for a new user message."""
|
||||
if webhook_manager and not compare_mode:
|
||||
webhook_manager.fire_and_forget("chat.message", {
|
||||
asyncio.create_task(webhook_manager.fire("chat.message", {
|
||||
"session_id": session_id, "model": sess.model, "message": message[:2000],
|
||||
})
|
||||
}))
|
||||
from src.event_bus import fire_event
|
||||
user = effective_user(request)
|
||||
user = get_current_user(request)
|
||||
fire_event("message_sent", user)
|
||||
|
||||
|
||||
@@ -505,29 +497,6 @@ def _normalize_model_id_from_cache(sess) -> Optional[str]:
|
||||
return None
|
||||
|
||||
|
||||
def _session_is_research_spinoff(sess) -> bool:
|
||||
"""True if this session was created via research "Discuss" spin-off.
|
||||
|
||||
Detected by the primer system message the spin-off endpoint seeds into
|
||||
history (metadata ``research_spinoff_from``). Such sessions are grounded
|
||||
on the seeded report, so global memory + personal-doc RAG injection is
|
||||
suppressed for them (the report is the sole knowledge base). Handles both
|
||||
ChatMessage objects and plain dicts.
|
||||
"""
|
||||
for m in getattr(sess, "history", []) or []:
|
||||
role = getattr(m, "role", None)
|
||||
if role is None and isinstance(m, dict):
|
||||
role = m.get("role")
|
||||
if role != "system":
|
||||
continue
|
||||
md = getattr(m, "metadata", None)
|
||||
if md is None and isinstance(m, dict):
|
||||
md = m.get("metadata")
|
||||
if (md or {}).get("research_spinoff_from"):
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
async def build_chat_context(
|
||||
sess,
|
||||
request,
|
||||
@@ -577,7 +546,7 @@ async def build_chat_context(
|
||||
fire_message_event(request, webhook_manager, session_id, sess, message, compare_mode)
|
||||
|
||||
# Resolve user prefs
|
||||
user = effective_user(request)
|
||||
user = get_current_user(request)
|
||||
uprefs = load_prefs_for_user(user)
|
||||
|
||||
# Memory enabled?
|
||||
@@ -593,17 +562,9 @@ async def build_chat_context(
|
||||
mem_enabled, user, incognito, no_memory, uprefs.get("memory_enabled", "NOT_SET"),
|
||||
)
|
||||
|
||||
# Research-spinoff ("Discuss") sessions are grounded on the seeded report:
|
||||
# the primer system message IS the knowledge base. Injecting global memory
|
||||
# or personal-doc RAG on every turn pulls in keyword-matched but off-topic
|
||||
# facts ("wrong data") and competes with the report, so suppress both here.
|
||||
is_research_spinoff = _session_is_research_spinoff(sess)
|
||||
if is_research_spinoff:
|
||||
mem_enabled = False
|
||||
|
||||
# Use RAG?
|
||||
use_rag_val = (str(use_rag).lower() != "false") if use_rag is not None else True
|
||||
if incognito or not allow_tool_preprocessing or is_research_spinoff:
|
||||
if incognito or not allow_tool_preprocessing:
|
||||
use_rag_val = False
|
||||
|
||||
# If pre-fetched search context was provided (compare mode), skip live web search
|
||||
@@ -626,7 +587,7 @@ async def build_chat_context(
|
||||
incognito=incognito,
|
||||
use_skills=skills_enabled,
|
||||
)
|
||||
if use_rag is not None or is_research_spinoff:
|
||||
if use_rag is not None:
|
||||
_preface_kwargs["use_rag"] = use_rag_val
|
||||
preface, rag_sources, web_sources = chat_processor.build_context_preface(**_preface_kwargs)
|
||||
|
||||
@@ -654,26 +615,6 @@ async def build_chat_context(
|
||||
# Build messages
|
||||
messages = preface + sess.get_context_messages()
|
||||
|
||||
# Current date/time — injected as a standalone *user*-role context message
|
||||
# placed immediately before the latest user turn, NOT folded into the
|
||||
# system prompt. Its text changes every minute, and local OpenAI-compatible
|
||||
# backends (llama.cpp / LM Studio) key their KV-cache prefix off the
|
||||
# system message byte-for-byte; mixing ever-changing timestamp text into
|
||||
# it would invalidate the cached prefix on every request (issue #2927).
|
||||
# Placing it at the tail also keeps it out of the stable
|
||||
# preface+history prefix, so that prefix stays byte-identical turn over
|
||||
# turn (modulo the genuinely new history entries) and the cache survives.
|
||||
if not agent_mode:
|
||||
try:
|
||||
from src.user_time import current_datetime_context_message
|
||||
_dt_msg = current_datetime_context_message()
|
||||
if messages and messages[-1].get("role") == "user":
|
||||
messages.insert(len(messages) - 1, _dt_msg)
|
||||
else:
|
||||
messages.append(_dt_msg)
|
||||
except Exception:
|
||||
logger.debug("Failed to add current date/time context", exc_info=True)
|
||||
|
||||
# Auto-compact
|
||||
messages, context_length, was_compacted = await maybe_compact(
|
||||
sess, sess.endpoint_url, sess.model, messages, sess.headers, owner=user,
|
||||
@@ -970,54 +911,6 @@ def save_assistant_response(
|
||||
return None
|
||||
|
||||
|
||||
def _is_session_stream_active(session_id: str) -> bool:
|
||||
"""Best-effort check for "is a chat completion currently streaming for
|
||||
this session?" — used to keep background extraction from overlapping a
|
||||
main completion and competing for the local backend's processing slots
|
||||
(issue #2927). Lazily imports the route module's live registry to avoid
|
||||
a circular import (chat_routes imports this module at load time)."""
|
||||
try:
|
||||
from routes import chat_routes as _cr
|
||||
return session_id in getattr(_cr, "_active_streams", {})
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
|
||||
async def _run_extraction_jobs_sequentially(session_id: str, jobs: list, max_wait_s: float = 120.0):
|
||||
"""Run queued background-extraction coroutines one at a time, only once
|
||||
no chat completion is actively streaming for this session.
|
||||
|
||||
As diagnosed in issue #2927, firing memory/skill extraction concurrently
|
||||
with the main chat completion (or with each other) makes them compete for
|
||||
the local backend's limited processing slots, evicting the main
|
||||
conversation's cached KV-cache checkpoint and forcing a full prompt
|
||||
re-evaluation on the next turn. Waiting for the stream to go idle and then
|
||||
running the jobs strictly in sequence keeps at most one "side" request in
|
||||
flight against the backend at any time, and never alongside the user's
|
||||
own conversation.
|
||||
"""
|
||||
# Wait for the triggering turn's own stream to finish winding down (it
|
||||
# almost always already has by the time this task gets scheduled — this
|
||||
# is a small safety margin, not the primary mechanism).
|
||||
waited = 0.0
|
||||
poll = 0.25
|
||||
while _is_session_stream_active(session_id) and waited < max_wait_s:
|
||||
await asyncio.sleep(poll)
|
||||
waited += poll
|
||||
|
||||
for name, job in jobs:
|
||||
# Re-check before each job: a fast follow-up message from the user
|
||||
# may have started a new stream for this session while we waited.
|
||||
waited = 0.0
|
||||
while _is_session_stream_active(session_id) and waited < max_wait_s:
|
||||
await asyncio.sleep(poll)
|
||||
waited += poll
|
||||
try:
|
||||
await job
|
||||
except Exception:
|
||||
logger.warning("[bg-extract] %s extraction job failed for session %s", name, session_id, exc_info=True)
|
||||
|
||||
|
||||
def run_post_response_tasks(
|
||||
sess,
|
||||
session_manager,
|
||||
@@ -1040,22 +933,7 @@ def run_post_response_tasks(
|
||||
extract_skills: bool = True,
|
||||
allow_background_extraction: bool = True,
|
||||
):
|
||||
"""Fire background tasks after a completed response: memory extraction, webhooks, auto-name, skill extraction.
|
||||
|
||||
Memory/skill extraction are queued to run *sequentially*, after the main
|
||||
completion stream for this session has fully wound down — never
|
||||
concurrently with it or with each other. As diagnosed in issue #2927,
|
||||
firing these "side" LLM calls in parallel with the main chat completion
|
||||
makes them compete for the local backend's limited processing slots
|
||||
(llama.cpp defaults to 4), evicting the main conversation's cached
|
||||
checkpoint and forcing a full prompt re-evaluation on the next turn. By
|
||||
the time this function runs the main response is already saved, but the
|
||||
extraction calls themselves are still async — queuing them through
|
||||
``_queue_background_extraction`` keeps them from overlapping the *next*
|
||||
turn's request too.
|
||||
"""
|
||||
_extraction_jobs: list = []
|
||||
|
||||
"""Fire background tasks after a completed response: memory extraction, webhooks, auto-name, skill extraction."""
|
||||
# Memory extraction — only every 4th message pair to avoid excess LLM calls
|
||||
_msg_count = len(sess.history) if hasattr(sess, 'history') else 0
|
||||
_should_extract = (_msg_count >= 4) and (_msg_count % 4 == 0)
|
||||
@@ -1065,10 +943,10 @@ def run_post_response_tasks(
|
||||
t_url, t_model, t_headers = resolve_task_endpoint(
|
||||
sess.endpoint_url, sess.model, sess.headers, owner=owner,
|
||||
)
|
||||
_extraction_jobs.append(("memory", extract_and_store(
|
||||
asyncio.create_task(extract_and_store(
|
||||
sess, memory_manager, memory_vector,
|
||||
t_url, t_model, t_headers,
|
||||
)))
|
||||
))
|
||||
|
||||
# Skill extraction from complex agent runs. Only when the user actually
|
||||
# chose agent mode — not a chat we auto-escalated for a notes/calendar
|
||||
@@ -1104,15 +982,12 @@ def run_post_response_tasks(
|
||||
sess.endpoint_url, sess.model, sess.headers, owner=owner,
|
||||
)
|
||||
logger.debug("[skill-extract] dispatching extractor (model=%s)", s_model)
|
||||
_extraction_jobs.append(("skill", maybe_extract_skill(
|
||||
asyncio.create_task(maybe_extract_skill(
|
||||
sess, skills_manager,
|
||||
s_url, s_model, s_headers,
|
||||
agent_rounds, agent_tool_calls,
|
||||
owner=owner,
|
||||
)))
|
||||
|
||||
if _extraction_jobs:
|
||||
asyncio.create_task(_run_extraction_jobs_sequentially(session_id, _extraction_jobs))
|
||||
))
|
||||
|
||||
# Token accumulation
|
||||
if last_metrics:
|
||||
@@ -1120,10 +995,10 @@ def run_post_response_tasks(
|
||||
|
||||
# Webhook
|
||||
if webhook_manager and not compare_mode:
|
||||
webhook_manager.fire_and_forget("chat.completed", {
|
||||
asyncio.create_task(webhook_manager.fire("chat.completed", {
|
||||
"session_id": session_id, "model": sess.model,
|
||||
"user_message": message, "response": full_response[:2000],
|
||||
})
|
||||
}))
|
||||
|
||||
# Auto-name
|
||||
if needs_auto_name(sess.name):
|
||||
|
||||
+34
-172
@@ -6,7 +6,7 @@ import os
|
||||
import time
|
||||
import logging
|
||||
from datetime import datetime
|
||||
from typing import Dict, Any, AsyncGenerator, List, Optional
|
||||
from typing import Dict, Any, AsyncGenerator, List
|
||||
|
||||
from fastapi import APIRouter, Request, HTTPException, Form, Query
|
||||
from fastapi.responses import StreamingResponse
|
||||
@@ -23,7 +23,7 @@ from src.endpoint_resolver import normalize_base as _normalize_base, build_chat_
|
||||
from src.session_search import search_session_messages
|
||||
from src.prompt_security import untrusted_context_message
|
||||
from core.exceptions import SessionNotFoundError
|
||||
from src.auth_helpers import effective_user, get_current_user
|
||||
from src.auth_helpers import get_current_user
|
||||
from routes.session_routes import _verify_session_owner
|
||||
from routes.document_helpers import _owner_session_filter
|
||||
from core.database import SessionLocal, get_session_mode, set_session_mode
|
||||
@@ -62,33 +62,6 @@ def _stream_set(session_id: str, **fields) -> None:
|
||||
rec.update(fields)
|
||||
|
||||
|
||||
def _resolve_request_workspace(request, raw_value) -> tuple:
|
||||
"""Resolve the posted workspace for this request: (workspace, rejected).
|
||||
|
||||
Privilege is checked BEFORE the path ever touches the filesystem. Only
|
||||
admin/single-user callers can use the workspace-backed file/shell tools,
|
||||
so only they get vet_workspace() and the workspace_rejected signal. For
|
||||
any other caller the submitted value is dropped uniformly, with no vetting
|
||||
and no event: otherwise the presence/absence of workspace_rejected would
|
||||
let a non-admin chat caller probe which host paths exist.
|
||||
|
||||
vet_workspace rejects non-directories, sensitive roots (.ssh, .gnupg,
|
||||
...), and filesystem roots; on rejection there is no confinement and the
|
||||
default tool-path allowlist applies. The rejected value is surfaced so the
|
||||
stream can tell an admin client (which believes a workspace is active)
|
||||
that it was dropped.
|
||||
"""
|
||||
requested = (raw_value or "").strip()
|
||||
if not requested:
|
||||
return "", ""
|
||||
from src.tool_security import owner_is_admin_or_single_user
|
||||
if not owner_is_admin_or_single_user(get_current_user(request)):
|
||||
return "", ""
|
||||
from src.tool_execution import vet_workspace
|
||||
workspace = vet_workspace(requested) or ""
|
||||
return workspace, (requested if not workspace else "")
|
||||
|
||||
|
||||
def _session_url_matches_endpoint(session_url: str, endpoint_base: str) -> bool:
|
||||
if not session_url or not endpoint_base:
|
||||
return False
|
||||
@@ -126,8 +99,7 @@ def _clear_orphaned_session_endpoint(sess, owner: str | None = None) -> bool:
|
||||
sess.model = ""
|
||||
sess.headers = {}
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.warning("Failed to clear orphaned session endpoint", exc_info=e)
|
||||
except Exception:
|
||||
db.rollback()
|
||||
return False
|
||||
finally:
|
||||
@@ -145,8 +117,7 @@ def _endpoint_cache_contains_model(endpoint, model: str) -> bool:
|
||||
return True
|
||||
try:
|
||||
models = json.loads(raw) if isinstance(raw, str) else raw
|
||||
except Exception as e:
|
||||
logger.warning("Failed to parse cached models list, treating as containing model", exc_info=e)
|
||||
except Exception:
|
||||
return True
|
||||
if not isinstance(models, list) or not models:
|
||||
return True
|
||||
@@ -238,8 +209,7 @@ def _recover_empty_session_model(sess, session_id: str, owner: str | None = None
|
||||
is_chatgpt_subscription = False
|
||||
try:
|
||||
cached = json.loads(ep.cached_models) if isinstance(ep.cached_models, str) else (ep.cached_models or [])
|
||||
except Exception as e:
|
||||
logger.warning("Failed to parse cached_models for endpoint %r", getattr(ep, "id", "?"), exc_info=e)
|
||||
except Exception:
|
||||
cached = []
|
||||
if not cached:
|
||||
visible = []
|
||||
@@ -363,7 +333,7 @@ def setup_chat_routes(
|
||||
sess = session_manager.get_session(session)
|
||||
except KeyError:
|
||||
raise HTTPException(404, f"Session '{session}' not found")
|
||||
owner = effective_user(request)
|
||||
owner = get_current_user(request)
|
||||
if _clear_orphaned_session_endpoint(sess, owner=owner):
|
||||
raise HTTPException(400, "Selected model endpoint was removed. Pick another model in Settings.")
|
||||
|
||||
@@ -430,7 +400,6 @@ def setup_chat_routes(
|
||||
temperature=ctx.preset.temperature,
|
||||
max_tokens=ctx.preset.max_tokens,
|
||||
prompt_type=preset_id,
|
||||
session_id=session,
|
||||
)
|
||||
_clean_reply, _clean_md = clean_thinking_for_save(reply, {"model": sess.model})
|
||||
sess.add_message(ChatMessage("assistant", _clean_reply, metadata=_clean_md))
|
||||
@@ -477,23 +446,20 @@ def setup_chat_routes(
|
||||
use_research = form_data.get("use_research")
|
||||
time_filter = form_data.get("time_filter")
|
||||
preset_id = form_data.get("preset_id")
|
||||
# Issue #3229: API callers send JSON, not FormData. Read from the
|
||||
# JSON body as fallback so callers who send {"allow_bash": true}
|
||||
# actually get bash enabled.
|
||||
allow_bash = form_data.get("allow_bash") or (body or {}).get("allow_bash")
|
||||
allow_web_search = form_data.get("allow_web_search") or (body or {}).get("allow_web_search")
|
||||
allow_bash = form_data.get("allow_bash")
|
||||
allow_web_search = form_data.get("allow_web_search")
|
||||
use_rag = form_data.get("use_rag")
|
||||
search_context = form_data.get("search_context") # pre-fetched web search results (compare mode)
|
||||
compare_mode = str(form_data.get("compare_mode", "")).lower() == "true"
|
||||
incognito = str(form_data.get("incognito", "")).lower() == "true"
|
||||
# Plan mode is not part of the merge-ready UI. Ignore stale clients or
|
||||
# manual form posts that still send plan_mode=true.
|
||||
plan_mode = False
|
||||
plan_mode = str(form_data.get("plan_mode", "")).lower() == "true"
|
||||
chat_mode = str(form_data.get("mode", "")).lower() # 'chat' or 'agent'
|
||||
# Workspace: confine the agent's file/shell tools to this folder.
|
||||
workspace, workspace_rejected = _resolve_request_workspace(
|
||||
request, form_data.get("workspace")
|
||||
)
|
||||
# Workspace: confine the agent's file/shell tools to this folder. Validate
|
||||
# it's a real directory; ignore (no confinement) otherwise.
|
||||
workspace = (form_data.get("workspace") or "").strip()
|
||||
if workspace:
|
||||
_ws_real = os.path.realpath(os.path.expanduser(workspace))
|
||||
workspace = _ws_real if os.path.isdir(_ws_real) else ""
|
||||
# Plan mode is a modifier on agent mode — it only makes sense with tools.
|
||||
if plan_mode:
|
||||
chat_mode = "agent"
|
||||
@@ -529,66 +495,6 @@ def setup_chat_routes(
|
||||
active_doc_id = form_data.get("active_doc_id", "").strip()
|
||||
logger.info(f"[doc-inject] chat_mode={chat_mode}, active_doc_id={active_doc_id!r}")
|
||||
|
||||
# Active email reader — when the user has an email open in the UI, the
|
||||
# frontend passes its uid/folder/account so "reply", "summarize this",
|
||||
# etc. resolve to the real email instead of the agent inventing a
|
||||
# fake markdown draft.
|
||||
active_email_uid = form_data.get("active_email_uid", "").strip()
|
||||
active_email_folder = form_data.get("active_email_folder", "INBOX").strip() or "INBOX"
|
||||
active_email_account = form_data.get("active_email_account", "").strip()
|
||||
active_email_ctx: Optional[Dict[str, str]] = None
|
||||
# Always reset between requests so a stale active-email pointer from
|
||||
# a previous turn (different reader closed, different account, etc.)
|
||||
# can't leak in when the user has no email open this turn.
|
||||
try:
|
||||
from src.tool_implementations import clear_active_email
|
||||
clear_active_email()
|
||||
except Exception:
|
||||
pass
|
||||
if active_email_uid:
|
||||
active_email_ctx = {
|
||||
"uid": active_email_uid,
|
||||
"folder": active_email_folder,
|
||||
"account": active_email_account,
|
||||
}
|
||||
# Try to enrich with subject + from so the agent's system prompt
|
||||
# block can quote them. Best-effort: a stale cache is fine, a
|
||||
# missing email just means we pass uid/folder/account only.
|
||||
try:
|
||||
from routes.email_routes import _read_cache_get, _read_cache_key
|
||||
_ck = _read_cache_key(active_email_account or None, active_email_folder, active_email_uid, owner=get_current_user(request))
|
||||
_cached_email = _read_cache_get(_ck)
|
||||
if _cached_email and isinstance(_cached_email, dict):
|
||||
active_email_ctx["subject"] = str(_cached_email.get("subject") or "")
|
||||
active_email_ctx["from"] = str(
|
||||
_cached_email.get("from_address")
|
||||
or _cached_email.get("from")
|
||||
or _cached_email.get("from_name")
|
||||
or ""
|
||||
)
|
||||
_body_preview = (_cached_email.get("body") or "")[:2000]
|
||||
if _body_preview:
|
||||
active_email_ctx["body_preview"] = _body_preview
|
||||
except Exception as _e:
|
||||
logger.debug(f"[email-inject] cache enrich skipped: {_e}")
|
||||
# Stash so email tools can resolve "this email" without UID guessing.
|
||||
try:
|
||||
from src.tool_implementations import set_active_email
|
||||
set_active_email(
|
||||
uid=active_email_uid,
|
||||
folder=active_email_folder,
|
||||
account=active_email_account or None,
|
||||
subject=active_email_ctx.get("subject"),
|
||||
sender=active_email_ctx.get("from"),
|
||||
)
|
||||
except Exception as _e:
|
||||
logger.debug(f"[email-inject] set_active_email failed: {_e}")
|
||||
logger.info(
|
||||
"[email-inject] active_email uid=%s folder=%s account=%s subject=%r",
|
||||
active_email_uid, active_email_folder, active_email_account or "(default)",
|
||||
active_email_ctx.get("subject", ""),
|
||||
)
|
||||
|
||||
try:
|
||||
# Attachment-only sends: skip the message-required check when the
|
||||
# user has attached one or more files (the attachment IS the action).
|
||||
@@ -603,7 +509,7 @@ def setup_chat_routes(
|
||||
# but BEFORE loading. Prevents cross-user session hijack.
|
||||
_verify_session_owner(request, session)
|
||||
sess = session_manager.get_session(session)
|
||||
owner = effective_user(request)
|
||||
owner = get_current_user(request)
|
||||
if _clear_orphaned_session_endpoint(sess, owner=owner):
|
||||
raise HTTPException(400, "Selected model endpoint was removed. Pick another model in Settings.")
|
||||
# Issue #587: picker shows a model from the endpoint cache but
|
||||
@@ -634,7 +540,7 @@ def setup_chat_routes(
|
||||
_enforce_chat_privileges(request, sess)
|
||||
|
||||
# Ensure session has auth headers
|
||||
resolve_session_auth(sess, session, owner=effective_user(request))
|
||||
resolve_session_auth(sess, session, owner=get_current_user(request))
|
||||
|
||||
# Check for research_pending BEFORE mode persist overwrites it
|
||||
do_research = str(use_research).lower() == "true"
|
||||
@@ -649,8 +555,8 @@ def setup_chat_routes(
|
||||
elif attachments:
|
||||
try:
|
||||
att_ids = [str(x) for x in json.loads(attachments)]
|
||||
except Exception as e:
|
||||
logger.warning("Failed to parse attachments JSON, ignoring attachments", exc_info=e)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
no_memory = str(form_data.get("no_memory", "")).lower() == "true"
|
||||
pre_context_tool_policy = build_effective_tool_policy(
|
||||
@@ -704,27 +610,15 @@ def setup_chat_routes(
|
||||
active_doc_id,
|
||||
)
|
||||
active_doc = None
|
||||
elif doc_session and doc_session != session:
|
||||
logger.warning(
|
||||
"[doc-inject] ignoring stale active_doc_id %s from session %s while in session %s",
|
||||
active_doc_id,
|
||||
doc_session,
|
||||
session,
|
||||
)
|
||||
active_doc = None
|
||||
else:
|
||||
# NOTE: previously dropped the doc when doc.session_id
|
||||
# != current chat session — but that broke the common
|
||||
# case of "open an email draft from one chat, ask a
|
||||
# different chat to write into it". The frontend only
|
||||
# sends active_doc_id for docs currently visible in
|
||||
# the UI, and we already owner-checked above, so trust
|
||||
# the explicit signal. We just log the mismatch and
|
||||
# re-bind the doc to the current session so future
|
||||
# turns find it via the session-fallback path too.
|
||||
if doc_session and doc_session != session:
|
||||
logger.info(
|
||||
"[doc-inject] cross-session active_doc_id %s (was session %s, now %s) — accepting and rebinding",
|
||||
active_doc_id, doc_session, session,
|
||||
)
|
||||
try:
|
||||
active_doc.session_id = session
|
||||
_doc_db.commit()
|
||||
except Exception as _e:
|
||||
_doc_db.rollback()
|
||||
logger.warning(f"[doc-inject] session rebind failed: {_e}")
|
||||
logger.info(f"[doc-inject] found by ID: title={active_doc.title!r}, lang={active_doc.language!r}, is_active={active_doc.is_active}, content_len={len(active_doc.current_content or '')}")
|
||||
else:
|
||||
logger.warning(f"[doc-inject] NOT FOUND by ID {active_doc_id}")
|
||||
@@ -744,7 +638,7 @@ def setup_chat_routes(
|
||||
# leak a doc that belongs to a DIFFERENT session.
|
||||
if not active_doc:
|
||||
try:
|
||||
from src.agent_tools.document_tools import get_active_document
|
||||
from src.tool_implementations import get_active_document
|
||||
_mem_id = get_active_document()
|
||||
if _mem_id:
|
||||
_mem_q = _doc_db.query(DBDocument).filter(DBDocument.id == _mem_id)
|
||||
@@ -765,18 +659,9 @@ def setup_chat_routes(
|
||||
|
||||
# Build disabled-tools set from frontend toggles + user privileges
|
||||
disabled_tools = set()
|
||||
# Only disable bash/web_search when the caller *explicitly* set them
|
||||
# to a falsy value. When unset (None), defer to per-user privilege
|
||||
# checks below — this lets admins with can_use_bash=True use bash
|
||||
# by default without having to send allow_bash in every request.
|
||||
if allow_bash is not None and str(allow_bash).lower() != "true":
|
||||
if str(allow_bash).lower() != "true":
|
||||
disabled_tools.add("bash")
|
||||
_explicit_web_intent = bool(_tool_intent and _tool_intent.category == "web")
|
||||
if (
|
||||
allow_web_search is not None
|
||||
and str(allow_web_search).lower() != "true"
|
||||
and not _explicit_web_intent
|
||||
):
|
||||
if str(allow_web_search).lower() != "true":
|
||||
disabled_tools.add("web_search")
|
||||
disabled_tools.add("web_fetch")
|
||||
|
||||
@@ -789,21 +674,6 @@ def setup_chat_routes(
|
||||
"manage_skills", # skill presets tied to user
|
||||
})
|
||||
|
||||
# Active email reader open → strip the tools that let the agent
|
||||
# "drift" to a new compose: create_document (writes a fake email-
|
||||
# shaped .md file) and send_email (sends fresh to a recipient the
|
||||
# agent invented). With those gone, the only paths left for "write
|
||||
# email saying X" are ui_control open_email_reply (draft) and
|
||||
# reply_to_email (immediate send) — both of which use the open
|
||||
# email's UID. Code-level enforcement instead of relying on a
|
||||
# prompt rule the model can ignore.
|
||||
if active_email_ctx and active_email_ctx.get("uid"):
|
||||
disabled_tools.update({
|
||||
"create_document",
|
||||
"send_email",
|
||||
"mcp__email__send_email",
|
||||
})
|
||||
|
||||
# Enforce per-user privileges
|
||||
_privs = {}
|
||||
_user = ctx.user
|
||||
@@ -894,13 +764,6 @@ def setup_chat_routes(
|
||||
# Register active stream for partial-save safety net
|
||||
_active_streams[session] = {"status": "streaming", "partial": "", "query": message, "is_research": effective_do_research, "mode": _effective_mode}
|
||||
|
||||
# The client sent a workspace the server refused to bind (deleted
|
||||
# folder, file path, sensitive dir, filesystem root). Tell it up
|
||||
# front so the UI can clear the pill instead of displaying a
|
||||
# confinement that is not actually in effect.
|
||||
if workspace_rejected:
|
||||
yield f"data: {json.dumps({'type': 'workspace_rejected', 'data': {'path': workspace_rejected}})}\n\n"
|
||||
|
||||
if ctx.preprocessed.attachment_meta:
|
||||
yield f"data: {json.dumps({'type': 'attachments', 'data': ctx.preprocessed.attachment_meta})}\n\n"
|
||||
|
||||
@@ -1129,7 +992,6 @@ def setup_chat_routes(
|
||||
max_tokens=ctx.preset.max_tokens,
|
||||
prompt_type=preset_id,
|
||||
tools=None,
|
||||
session_id=session,
|
||||
):
|
||||
if chunk.startswith("data: ") and not chunk.startswith("data: [DONE]"):
|
||||
try:
|
||||
@@ -1271,15 +1133,14 @@ def setup_chat_routes(
|
||||
max_rounds=_max_rounds,
|
||||
context_length=ctx.context_length,
|
||||
active_document=active_doc,
|
||||
active_email=active_email_ctx,
|
||||
session_id=session,
|
||||
disabled_tools=disabled_tools if disabled_tools else None,
|
||||
tool_policy=tool_policy,
|
||||
owner=_user,
|
||||
fallbacks=_fallback_candidates,
|
||||
workspace=workspace or None,
|
||||
plan_mode=plan_mode,
|
||||
approved_plan=approved_plan or None,
|
||||
workspace=workspace or None,
|
||||
):
|
||||
if chunk.startswith("data: ") and not chunk.startswith("data: [DONE]"):
|
||||
try:
|
||||
@@ -1409,7 +1270,8 @@ def setup_chat_routes(
|
||||
# without waiting on the next streamed chunk.
|
||||
#
|
||||
# Normal chat/agent streams keep the DETACHED behavior below: they
|
||||
# survive the client closing the tab / navigating away. The SSE response just subscribes (replay
|
||||
# survive the client closing the tab / navigating away (true
|
||||
# terminal-agent semantics). The SSE response just subscribes (replay
|
||||
# buffered output + live); dropping the SSE only removes a subscriber —
|
||||
# the run keeps going and saves the assistant message on completion
|
||||
# regardless. Reconnect via /api/chat/resume.
|
||||
@@ -1485,7 +1347,7 @@ def setup_chat_routes(
|
||||
if not q or not q.strip():
|
||||
return []
|
||||
|
||||
_user = effective_user(request)
|
||||
_user = get_current_user(request)
|
||||
return [
|
||||
result.to_dict()
|
||||
for result in search_session_messages(
|
||||
|
||||
+8
-84
@@ -18,7 +18,6 @@ from fastapi.responses import StreamingResponse
|
||||
from src.auth_helpers import require_authenticated_request, require_user
|
||||
from src.tool_implementations import do_manage_notes
|
||||
from src.constants import COOKBOOK_STATE_FILE
|
||||
from routes._validators import validate_remote_host, validate_ssh_port
|
||||
|
||||
|
||||
COOKBOOK_READ_SCOPES = {"cookbook:read", "cookbook:launch"}
|
||||
@@ -37,21 +36,6 @@ DOCS_WRITE_SCOPES = {"documents:write"}
|
||||
WRITE_ACTIONS = {"add", "create", "new", "save", "remind", "update", "delete", "toggle_item", "remove", "remove_item"}
|
||||
|
||||
|
||||
def _ssh_prefix_for_task(task: dict) -> tuple[str, str]:
|
||||
"""Resolve a cookbook task's stored SSH target into ``(host, port_flag)``.
|
||||
|
||||
``host`` is ``""`` for a local task. ``remoteHost`` / ``sshPort`` come from
|
||||
cookbook_state.json and get interpolated into an ``ssh`` command string, so
|
||||
validate them the same way the cookbook routes do. A tampered entry with
|
||||
shell metacharacters in ``remoteHost`` is rejected with 400 rather than
|
||||
injected.
|
||||
"""
|
||||
host = validate_remote_host((task.get("remoteHost") or "").strip() or None) or ""
|
||||
ssh_port = validate_ssh_port((task.get("sshPort") or "").strip() or None) or ""
|
||||
port_flag = f"-p {ssh_port} " if ssh_port and ssh_port != "22" else ""
|
||||
return host, port_flag
|
||||
|
||||
|
||||
async def _as_owner(request: Request, owner: str, fn, *args, **kwargs):
|
||||
"""Run an existing route handler with request.state.current_user temporarily
|
||||
set to ``owner`` so its internal get_current_user/require_user calls see
|
||||
@@ -91,20 +75,6 @@ def _scope_owner(request: Request, allowed: set[str]) -> str:
|
||||
return require_user(request)
|
||||
|
||||
|
||||
def _scope_owner_all(request: Request, required: set[str]) -> str:
|
||||
"""Return owner only when an API token has every required scope."""
|
||||
if getattr(request.state, "api_token", False):
|
||||
scopes = set(getattr(request.state, "api_token_scopes", []) or [])
|
||||
missing = required - scopes
|
||||
if missing:
|
||||
raise HTTPException(403, f"API token missing required scope: {' and '.join(sorted(missing))}")
|
||||
owner = getattr(request.state, "api_token_owner", None)
|
||||
if not owner:
|
||||
raise HTTPException(403, "API token has no owner")
|
||||
return owner
|
||||
return require_user(request)
|
||||
|
||||
|
||||
def _find_endpoint(router: APIRouter | None, method: str, path: str):
|
||||
if router is None:
|
||||
return None
|
||||
@@ -152,7 +122,7 @@ def setup_codex_routes(
|
||||
"read": scoped(EMAIL_READ_SCOPES),
|
||||
"draft": scoped(EMAIL_DRAFT_SCOPES),
|
||||
"send": scoped(EMAIL_SEND_SCOPES),
|
||||
"actions": ["list", "read", "draft_document", "draft", "send"],
|
||||
"actions": ["list", "read", "draft", "send"],
|
||||
},
|
||||
"memory": {
|
||||
"read": scoped(MEMORY_READ_SCOPES),
|
||||
@@ -276,56 +246,6 @@ def setup_codex_routes(
|
||||
# Both handlers in routes/email_routes.py already accept `owner=` via
|
||||
# FastAPI Depends, so we call them directly without patching state.
|
||||
|
||||
def _email_draft_document_content(body: dict[str, Any]) -> str:
|
||||
def clean(v: Any) -> str:
|
||||
if isinstance(v, list):
|
||||
return ", ".join(str(x).strip() for x in v if str(x).strip())
|
||||
return str(v or "").strip()
|
||||
|
||||
to = clean(body.get("to"))
|
||||
cc = clean(body.get("cc"))
|
||||
bcc = clean(body.get("bcc"))
|
||||
subject = clean(body.get("subject"))
|
||||
in_reply_to = clean(body.get("in_reply_to"))
|
||||
references = clean(body.get("references"))
|
||||
body_text = str(body.get("body") or body.get("body_html") or "").strip()
|
||||
lines = [
|
||||
f"To: {to}",
|
||||
]
|
||||
if cc:
|
||||
lines.append(f"Cc: {cc}")
|
||||
if bcc:
|
||||
lines.append(f"Bcc: {bcc}")
|
||||
lines.append(f"Subject: {subject}")
|
||||
if in_reply_to:
|
||||
lines.append(f"In-Reply-To: {in_reply_to}")
|
||||
if references:
|
||||
lines.append(f"References: {references}")
|
||||
lines.extend(["---", body_text])
|
||||
return "\n".join(lines).rstrip() + "\n"
|
||||
|
||||
@router.post("/emails/draft-document")
|
||||
async def codex_email_draft_document(request: Request, body: dict[str, Any] = Body(default_factory=dict)):
|
||||
owner = _scope_owner_all(request, {"email:draft", "documents:write"})
|
||||
if documents_create_endpoint is None:
|
||||
raise HTTPException(503, "Documents integration is not available")
|
||||
from routes.document_routes import DocumentCreate
|
||||
|
||||
subject = str(body.get("subject") or "Email draft").strip() or "Email draft"
|
||||
title = str(body.get("title") or subject).strip() or "Email draft"
|
||||
req = DocumentCreate(
|
||||
session_id=body.get("session_id"),
|
||||
title=title,
|
||||
language="email",
|
||||
content=_email_draft_document_content(body),
|
||||
)
|
||||
result = await _as_owner(request, owner, documents_create_endpoint, request, req)
|
||||
if isinstance(result, dict):
|
||||
result = dict(result)
|
||||
result["draft_type"] = "document"
|
||||
result["send_required_confirmation"] = True
|
||||
return result
|
||||
|
||||
@router.post("/emails/draft")
|
||||
async def codex_email_draft(request: Request, body: dict[str, Any] = Body(default_factory=dict)):
|
||||
owner = _scope_owner(request, EMAIL_DRAFT_SCOPES)
|
||||
@@ -566,7 +486,8 @@ def setup_codex_routes(
|
||||
task = next((t for t in tasks if t.get("sessionId") == session_id), None)
|
||||
if task is None:
|
||||
raise HTTPException(404, "task not found")
|
||||
host, port_flag = _ssh_prefix_for_task(task)
|
||||
host = (task.get("remoteHost") or "").strip()
|
||||
ssh_port = (task.get("sshPort") or "").strip()
|
||||
# Prefer the persisted log file over the tmux pane. The pane gets
|
||||
# overwritten by the post-crash neofetch banner + bash prompt the
|
||||
# moment vllm exits; the log file is the raw stdout/stderr and
|
||||
@@ -578,6 +499,7 @@ def setup_codex_routes(
|
||||
f"else tmux capture-pane -t {session_id} -p -S -{tail}; fi"
|
||||
)
|
||||
if host:
|
||||
port_flag = f"-p {ssh_port} " if ssh_port and ssh_port != "22" else ""
|
||||
import shlex
|
||||
cmd = f"ssh {port_flag}{host} {shlex.quote(inner)}"
|
||||
else:
|
||||
@@ -639,8 +561,10 @@ def setup_codex_routes(
|
||||
state = _read_cookbook_state()
|
||||
tasks = state.get("tasks") or []
|
||||
task = next((t for t in tasks if t.get("sessionId") == session_id), None)
|
||||
host, port_flag = _ssh_prefix_for_task(task or {})
|
||||
host = ((task or {}).get("remoteHost") or "").strip()
|
||||
ssh_port = ((task or {}).get("sshPort") or "").strip()
|
||||
if host:
|
||||
port_flag = f"-p {ssh_port} " if ssh_port and ssh_port != "22" else ""
|
||||
cmd = f"ssh {port_flag}{host} \"tmux kill-session -t {session_id}\""
|
||||
else:
|
||||
cmd = f"tmux kill-session -t {session_id}"
|
||||
@@ -790,7 +714,7 @@ def setup_codex_routes(
|
||||
norm = dict(body or {})
|
||||
sess = (norm.get("tmux_session") or norm.get("session_id") or "").strip()
|
||||
model = (norm.get("model") or norm.get("repo_id") or "").strip()
|
||||
host = validate_remote_host((norm.get("host") or norm.get("remote_host") or "").strip() or None) or ""
|
||||
host = (norm.get("host") or norm.get("remote_host") or "").strip()
|
||||
port = norm.get("port") or 8000
|
||||
import re as _re
|
||||
if not sess or not _re.fullmatch(r"[a-zA-Z0-9_-]+", sess):
|
||||
|
||||
+23
-80
@@ -12,7 +12,6 @@ import json
|
||||
import csv
|
||||
import io
|
||||
import os
|
||||
import inspect
|
||||
import httpx
|
||||
from pathlib import Path
|
||||
from datetime import datetime
|
||||
@@ -46,14 +45,10 @@ def _save_settings(settings):
|
||||
def _get_carddav_config():
|
||||
import os
|
||||
settings = _load_settings()
|
||||
password = settings.get("carddav_password", os.environ.get("CARDDAV_PASSWORD", ""))
|
||||
if password and "carddav_password" in settings:
|
||||
from src.secret_storage import decrypt
|
||||
password = decrypt(password)
|
||||
return {
|
||||
"url": settings.get("carddav_url", os.environ.get("CARDDAV_URL", "")),
|
||||
"username": settings.get("carddav_username", os.environ.get("CARDDAV_USERNAME", "")),
|
||||
"password": password,
|
||||
"password": settings.get("carddav_password", os.environ.get("CARDDAV_PASSWORD", "")),
|
||||
}
|
||||
|
||||
|
||||
@@ -91,13 +86,11 @@ def _normalize_contact(contact: Dict) -> Dict:
|
||||
name = str(contact.get("name") or "").strip()
|
||||
if not name and emails:
|
||||
name = emails[0].split("@")[0]
|
||||
address = str(contact.get("address") or "").strip()
|
||||
return {
|
||||
"uid": str(contact.get("uid") or uuid.uuid4()),
|
||||
"name": name,
|
||||
"emails": emails,
|
||||
"phones": phones,
|
||||
"address": address,
|
||||
}
|
||||
|
||||
|
||||
@@ -153,7 +146,7 @@ def _parse_vcards(text: str) -> List[Dict]:
|
||||
for block in re.split(r"BEGIN:VCARD", text):
|
||||
if not block.strip():
|
||||
continue
|
||||
contact = {"name": "", "emails": [], "phones": [], "uid": "", "address": ""}
|
||||
contact = {"name": "", "emails": [], "phones": [], "uid": ""}
|
||||
for line in block.split("\n"):
|
||||
line = line.strip()
|
||||
# Strip an optional RFC 6350 group prefix (e.g. "item1.EMAIL;...")
|
||||
@@ -176,15 +169,6 @@ def _parse_vcards(text: str) -> List[Dict]:
|
||||
phone = _vunesc(name_part.split(":", 1)[1])
|
||||
if phone and phone not in contact["phones"]:
|
||||
contact["phones"].append(phone)
|
||||
elif name_part.startswith("ADR"):
|
||||
# vCard ADR is 7 semicolon-separated components:
|
||||
# post-office-box;extended-address;street;locality;region;postal-code;country.
|
||||
# Recover a human-readable string by joining non-empty
|
||||
# components with ", ".
|
||||
if ":" in name_part:
|
||||
raw = name_part.split(":", 1)[1]
|
||||
parts = [_vunesc(p).strip() for p in raw.split(";")]
|
||||
contact["address"] = ", ".join(p for p in parts if p)
|
||||
elif name_part.startswith("UID:"):
|
||||
contact["uid"] = _vunesc(name_part[4:])
|
||||
if contact["name"] or contact["emails"]:
|
||||
@@ -209,8 +193,7 @@ def _vesc(value: str) -> str:
|
||||
|
||||
def _build_vcard(name: str, email: str, uid: Optional[str] = None,
|
||||
emails: Optional[List[str]] = None,
|
||||
phones: Optional[List[str]] = None,
|
||||
address: Optional[str] = None) -> str:
|
||||
phones: Optional[List[str]] = None) -> str:
|
||||
"""Build a vCard. Accepts either a single `email` (legacy callers) or
|
||||
full `emails`/`phones` lists (edit path). The first email is marked
|
||||
PREF=1. All values are RFC-6350-escaped."""
|
||||
@@ -243,12 +226,6 @@ def _build_vcard(name: str, email: str, uid: Optional[str] = None,
|
||||
lines.append(f"EMAIL;PREF=1:{_vesc(em)}" if i == 0 else f"EMAIL:{_vesc(em)}")
|
||||
for ph in phone_list:
|
||||
lines.append(f"TEL:{_vesc(ph)}")
|
||||
# Address: stuff the whole human-readable string into the street
|
||||
# component of ADR. vCard ADR has 7 semicolon-separated components:
|
||||
# post-office-box;extended-address;street;locality;region;postal-code;country.
|
||||
addr = (address or "").strip()
|
||||
if addr:
|
||||
lines.append(f"ADR:;;{_vesc(addr)};;;;")
|
||||
lines.append("END:VCARD")
|
||||
return "\r\n".join(lines) + "\r\n"
|
||||
|
||||
@@ -385,7 +362,7 @@ def _resolve_resource_url(uid: str) -> str:
|
||||
return _lookup() or _vcard_url(uid)
|
||||
|
||||
|
||||
def _create_contact(name: str, email: str, address: str = "") -> bool:
|
||||
def _create_contact(name: str, email: str) -> bool:
|
||||
"""Add a new contact via CardDAV or local contacts."""
|
||||
cfg = _get_carddav_config()
|
||||
if not _carddav_configured(cfg):
|
||||
@@ -394,12 +371,12 @@ def _create_contact(name: str, email: str, address: str = "") -> bool:
|
||||
for c in contacts:
|
||||
if email_l and email_l in [e.lower() for e in c.get("emails", [])]:
|
||||
return True
|
||||
contacts.append(_normalize_contact({"name": name, "emails": [email], "address": address}))
|
||||
contacts.append(_normalize_contact({"name": name, "emails": [email]}))
|
||||
_save_local_contacts(contacts)
|
||||
return True
|
||||
|
||||
contact_uid = str(uuid.uuid4())
|
||||
vcard = _build_vcard(name, email, contact_uid, address=address)
|
||||
vcard = _build_vcard(name, email, contact_uid)
|
||||
try:
|
||||
url = _carddav_base_url(cfg) + "/" + contact_uid + ".vcf"
|
||||
auth = None
|
||||
@@ -632,7 +609,7 @@ def _contacts_to_csv(contacts: List[Dict]) -> str:
|
||||
return out.getvalue()
|
||||
|
||||
|
||||
def _update_contact(uid: str, name: str, emails: List[str], phones: List[str], address: str = "") -> bool:
|
||||
def _update_contact(uid: str, name: str, emails: List[str], phones: List[str]) -> bool:
|
||||
"""Rewrite an existing contact via CardDAV or local contacts."""
|
||||
cfg = _get_carddav_config()
|
||||
if not _carddav_configured(cfg):
|
||||
@@ -641,19 +618,16 @@ def _update_contact(uid: str, name: str, emails: List[str], phones: List[str], a
|
||||
out = []
|
||||
for c in contacts:
|
||||
if c.get("uid") == uid:
|
||||
# Preserve existing address when caller passes "" (only
|
||||
# updating name/emails/phones, not touching address).
|
||||
addr = address if address else c.get("address", "")
|
||||
out.append(_normalize_contact({"uid": uid, "name": name, "emails": emails, "phones": phones, "address": addr}))
|
||||
out.append(_normalize_contact({"uid": uid, "name": name, "emails": emails, "phones": phones}))
|
||||
found = True
|
||||
else:
|
||||
out.append(c)
|
||||
if not found:
|
||||
out.append(_normalize_contact({"uid": uid, "name": name, "emails": emails, "phones": phones, "address": address}))
|
||||
out.append(_normalize_contact({"uid": uid, "name": name, "emails": emails, "phones": phones}))
|
||||
_save_local_contacts(out)
|
||||
return True
|
||||
|
||||
vcard = _build_vcard(name, "", uid=uid, emails=emails, phones=phones, address=address)
|
||||
vcard = _build_vcard(name, "", uid=uid, emails=emails, phones=phones)
|
||||
# Use the real resource href (handles externally-created contacts whose
|
||||
# filename != UID); falls back to the <uid>.vcf guess.
|
||||
try:
|
||||
@@ -740,49 +714,23 @@ def setup_contacts_routes():
|
||||
"""Add a new contact."""
|
||||
name = (data.get("name") or "").strip()
|
||||
email = (data.get("email") or "").strip()
|
||||
phone = (data.get("phone") or "").strip()
|
||||
address = (data.get("address") or "").strip()
|
||||
if not email:
|
||||
return {"success": False, "error": "Email required"}
|
||||
# Check if already exists by email
|
||||
if email:
|
||||
contacts = _fetch_contacts()
|
||||
for c in contacts:
|
||||
if email.lower() in [e.lower() for e in c["emails"]]:
|
||||
return {"success": True, "message": "Already exists", "contact": c}
|
||||
# Check if already exists
|
||||
contacts = _fetch_contacts()
|
||||
for c in contacts:
|
||||
if email.lower() in [e.lower() for e in c["emails"]]:
|
||||
return {"success": True, "message": "Already exists", "contact": c}
|
||||
if not name:
|
||||
name = email.split("@")[0]
|
||||
create_params = inspect.signature(_create_contact).parameters
|
||||
if len(create_params) >= 3:
|
||||
ok = _create_contact(name, email, address)
|
||||
else:
|
||||
ok = _create_contact(name, email)
|
||||
# If a phone was provided, do an immediate update to thread it
|
||||
# through (the simple _create_contact signature only takes name +
|
||||
# email + address; phones happen via update).
|
||||
if ok and phone:
|
||||
try:
|
||||
fresh = _fetch_contacts(force=True)
|
||||
created = next((c for c in fresh if name == c.get("name") and (not email or email in c.get("emails", []))), None)
|
||||
if created:
|
||||
_update_contact(
|
||||
created["uid"], name,
|
||||
created.get("emails", []),
|
||||
[phone],
|
||||
address,
|
||||
)
|
||||
except Exception:
|
||||
pass
|
||||
ok = _create_contact(name, email)
|
||||
return {"success": ok}
|
||||
|
||||
@router.post("/import")
|
||||
async def import_vcf(data: dict, _admin: str = Depends(require_admin)):
|
||||
"""Import contacts from .vcf or CSV. Body: {"vcf": "..."} or {"csv": "..."}."""
|
||||
# Coerce defensively: a non-string vcf/text/csv (e.g. a number or list
|
||||
# in the JSON body) would otherwise reach .strip() and 500 with an
|
||||
# AttributeError instead of degrading to a clean "no data" response.
|
||||
text = str(data.get("vcf") or data.get("text") or "")
|
||||
csv_text = str(data.get("csv") or "")
|
||||
text = data.get("vcf") or data.get("text") or ""
|
||||
csv_text = data.get("csv") or ""
|
||||
if text.strip():
|
||||
if "BEGIN:VCARD" not in text.upper():
|
||||
return {"success": False, "error": "No vCard data found"}
|
||||
@@ -834,11 +782,7 @@ def setup_contacts_routes():
|
||||
except ValueError as e:
|
||||
raise HTTPException(400, str(e))
|
||||
else:
|
||||
value = data[key]
|
||||
if key == "carddav_password" and value:
|
||||
from src.secret_storage import encrypt
|
||||
value = encrypt(value)
|
||||
settings[key] = value
|
||||
settings[key] = data[key]
|
||||
_save_settings(settings)
|
||||
# Force re-fetch
|
||||
_contact_cache["fetched_at"] = None
|
||||
@@ -855,7 +799,7 @@ def setup_contacts_routes():
|
||||
# match PUT /{uid} with uid="config".
|
||||
@router.put("/{uid}")
|
||||
async def edit_contact(uid: str, data: dict, _admin: str = Depends(require_admin)):
|
||||
"""Edit an existing contact — name / emails / phones / address."""
|
||||
"""Edit an existing contact — name / emails / phones."""
|
||||
name = (data.get("name") or "").strip()
|
||||
emails = data.get("emails")
|
||||
phones = data.get("phones")
|
||||
@@ -863,12 +807,11 @@ def setup_contacts_routes():
|
||||
emails = [data["email"]]
|
||||
emails = [e.strip() for e in (emails or []) if e and e.strip()]
|
||||
phones = [p.strip() for p in (phones or []) if p and p.strip()]
|
||||
address = (data.get("address") or "").strip()
|
||||
if not name and not emails and not address:
|
||||
return {"success": False, "error": "Name, email, or address required"}
|
||||
if not name and not emails:
|
||||
return {"success": False, "error": "Name or email required"}
|
||||
if not name and emails:
|
||||
name = emails[0].split("@")[0]
|
||||
ok = _update_contact(uid, name, emails, phones, address)
|
||||
ok = _update_contact(uid, name, emails, phones)
|
||||
return {"success": ok}
|
||||
|
||||
@router.delete("/{uid}")
|
||||
|
||||
+30
-112
@@ -1,19 +1,16 @@
|
||||
"""cookbook_helpers.py — validators + small helpers shared by the cookbook routes.
|
||||
Extracted from cookbook_routes.py; the routes module imports the symbols it needs."""
|
||||
|
||||
import json
|
||||
import logging
|
||||
import ntpath
|
||||
import os
|
||||
import posixpath
|
||||
import re
|
||||
import shlex
|
||||
from pathlib import Path
|
||||
|
||||
from fastapi import HTTPException
|
||||
from pydantic import BaseModel
|
||||
|
||||
from routes._validators import validate_remote_host, validate_ssh_port
|
||||
from core.platform_compat import _ssh_exec_argv
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -33,24 +30,20 @@ _LOCAL_MODEL_ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._-]*$")
|
||||
_OLLAMA_MODEL_ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:/-]{0,200}$")
|
||||
# Include pattern is a glob: allow typical safe glyphs only.
|
||||
_INCLUDE_RE = re.compile(r"^[A-Za-z0-9._\-*?/\[\]]+$")
|
||||
# Remote host: user@host (optionally with :port-free hostname parts).
|
||||
_REMOTE_HOST_RE = re.compile(r"^[A-Za-z0-9._-]+@[A-Za-z0-9._-]+$")
|
||||
# HF tokens and API tokens are url-safe base64-like.
|
||||
_TOKEN_RE = re.compile(r"^[A-Za-z0-9._~+/=-]+$")
|
||||
# Session IDs we mint look like "cookbook-deadbeef" or "serve-deadbeef".
|
||||
# Anything beyond plain alphanumerics + dash + underscore could break out
|
||||
# of the shell/PowerShell contexts the value lands in.
|
||||
_SESSION_ID_RE = re.compile(r"^[A-Za-z0-9_-]{1,64}$")
|
||||
_SSH_PORT_RE = re.compile(r"^\d{1,5}$")
|
||||
_GPU_LIST_RE = re.compile(r"^\d+(?:,\d+)*$")
|
||||
# A download target directory. Absolute or ~-relative path; safe path glyphs
|
||||
# only (no quotes or shell metacharacters). Spaces are allowed because command
|
||||
# builders pass the value through quoted shell/Python contexts. The character
|
||||
# class uses ``\w`` — Unicode word characters under Python 3's default str
|
||||
# matching — so non-ASCII folder names pass validation too: Cyrillic, accented
|
||||
# Latin, CJK, e.g. ``/Volumes/Модели`` or ``D:\AI Models\Модели``. This stays
|
||||
# shell-safe: none of ``; & | ` $ '' "" () {}`` newlines etc. are in ``[\w. -]``,
|
||||
# so injection vectors remain rejected. A leading ~ is expanded to $HOME at
|
||||
# command-build time. (Drive letters stay ASCII: ``[A-Za-z]:``.)
|
||||
_LOCAL_DIR_RE = re.compile(r"^~?(?:/[\w. -]*)+$|^~$")
|
||||
_WINDOWS_LOCAL_DIR_RE = re.compile(r"^[A-Za-z]:[\\/](?:[\w. -]+(?:[\\/][\w. -]+)*[\\/]?)?$")
|
||||
# only (no quotes, shell metacharacters, or spaces) since it lands in a shell
|
||||
# command. A leading ~ is expanded to $HOME at command-build time.
|
||||
_LOCAL_DIR_RE = re.compile(r"^~?/[A-Za-z0-9._/-]*$|^~$")
|
||||
_WINDOWS_DRIVE_PATH_RE = re.compile(r"^[A-Za-z]:[\\/]")
|
||||
|
||||
|
||||
@@ -84,6 +77,14 @@ def _validate_include(v: str | None) -> str | None:
|
||||
return v
|
||||
|
||||
|
||||
def _validate_remote_host(v: str | None) -> str | None:
|
||||
if v is None or v == "":
|
||||
return None
|
||||
if not _REMOTE_HOST_RE.match(v):
|
||||
raise HTTPException(400, "Invalid remote_host — must be user@host, no SSH option syntax")
|
||||
return v
|
||||
|
||||
|
||||
def _validate_token(v: str | None) -> str | None:
|
||||
if v is None or v == "":
|
||||
return None
|
||||
@@ -92,43 +93,26 @@ def _validate_token(v: str | None) -> str | None:
|
||||
return v
|
||||
|
||||
|
||||
def load_stored_hf_token(*, state_path: Path | str | None = None) -> str:
|
||||
"""Return the decrypted HF token from cookbook_state.json, else env fallback."""
|
||||
path = Path(state_path) if state_path else Path(os.environ.get("DATA_DIR", "data")) / "cookbook_state.json"
|
||||
token = ""
|
||||
if path.exists():
|
||||
try:
|
||||
state = json.loads(path.read_text(encoding="utf-8"))
|
||||
env = state.get("env") if isinstance(state, dict) else {}
|
||||
if isinstance(env, dict) and env.get("hfToken"):
|
||||
from src.secret_storage import decrypt
|
||||
token = decrypt(env.get("hfToken") or "")
|
||||
except Exception:
|
||||
token = ""
|
||||
if not token:
|
||||
token = (os.environ.get("HF_TOKEN") or os.environ.get("HUGGING_FACE_HUB_TOKEN") or "").strip()
|
||||
return token
|
||||
|
||||
|
||||
def _validate_local_dir(v: str | None) -> str | None:
|
||||
if v is None or v == "":
|
||||
return None
|
||||
if len(v) >= 2 and v[0] == v[-1] and v[0] in {"'", '"'}:
|
||||
v = v[1:-1]
|
||||
v = v.rstrip("/") or "/"
|
||||
if not (_LOCAL_DIR_RE.match(v) or _WINDOWS_LOCAL_DIR_RE.match(v)):
|
||||
raise HTTPException(400, "Invalid local_dir — must be an absolute or ~ path with no shell metacharacters")
|
||||
# Reject path segments that start with '-' (option injection). '-' is in the
|
||||
# allowlist, so a dir like ``/models/-rf`` or ``D:\models\-rf`` could be read
|
||||
# as a CLI flag by hf/etc. — and quoting does NOT stop a value from being
|
||||
# parsed as an option. This is the one residual that command-build-time
|
||||
# quoting can't cover, so the guard lives here, keeping the safety wholly
|
||||
# inside the validator rather than relying on consumers.
|
||||
if any(seg.startswith("-") for seg in re.split(r"[\\/]", v) if seg):
|
||||
raise HTTPException(400, "Invalid local_dir — path segments cannot start with '-'")
|
||||
if not _LOCAL_DIR_RE.match(v):
|
||||
raise HTTPException(400, "Invalid local_dir — must be an absolute or ~ path with no spaces or shell metacharacters")
|
||||
return v
|
||||
|
||||
|
||||
def _validate_ssh_port(v: str | None) -> str | None:
|
||||
if v is None or v == "":
|
||||
return None
|
||||
if not _SSH_PORT_RE.fullmatch(str(v)):
|
||||
raise HTTPException(400, "Invalid ssh_port")
|
||||
port = int(v)
|
||||
if port < 1 or port > 65535:
|
||||
raise HTTPException(400, "Invalid ssh_port")
|
||||
return str(port)
|
||||
|
||||
|
||||
def _validate_gpus(v: str | None) -> str | None:
|
||||
if v is None or v == "":
|
||||
return None
|
||||
@@ -140,7 +124,7 @@ def _validate_gpus(v: str | None) -> str | None:
|
||||
def _shell_path(p: str) -> str:
|
||||
"""Render a validated path for a double-quoted shell context, expanding a
|
||||
leading ~ to $HOME (single quotes wouldn't expand it). Safe because
|
||||
_validate_local_dir already rejects quotes and shell metacharacters."""
|
||||
_validate_local_dir already restricts the charset."""
|
||||
if p == "~":
|
||||
return '"$HOME"'
|
||||
if p.startswith("~/"):
|
||||
@@ -362,12 +346,7 @@ def _user_shell_path_bootstrap() -> list[str]:
|
||||
' ODYSSEUS_USER_PATH="$("$ODYSSEUS_USER_SHELL" -ic \'printf "__ODYSSEUS_PATH__%s\\n" "$PATH"\' 2>/dev/null | sed -n \'s/^__ODYSSEUS_PATH__//p\' | tail -n 1 || true)"',
|
||||
' if [ -n "$ODYSSEUS_USER_PATH" ]; then export PATH="$ODYSSEUS_USER_PATH:$PATH"; fi',
|
||||
'fi',
|
||||
# Windows can expose python3 as a Microsoft Store App Execution Alias
|
||||
# under WindowsApps. Git Bash sees that stub as present, but it exits
|
||||
# before running Python. A Windows venv usually has python.exe, not
|
||||
# python3.exe, so treat a missing or WindowsApps python3 as absent.
|
||||
'_odys_py3="$(command -v python3 2>/dev/null || true)"',
|
||||
'case "$_odys_py3" in ""|*[Ww]indows[Aa]pps*) python3() { python "$@"; } ;; esac',
|
||||
'command -v python3 >/dev/null 2>&1 || python3() { python "$@"; }',
|
||||
'command -v python >/dev/null 2>&1 || python() { python3 "$@"; }',
|
||||
]
|
||||
|
||||
@@ -406,7 +385,6 @@ def _cached_model_scan_script(model_dirs: list[str] | None = None, add_hf_cache:
|
||||
" for root, dirs, fns in safe_walk(base):",
|
||||
" for fn in sorted(fns):",
|
||||
" if not fn.lower().endswith('.gguf'): continue",
|
||||
" if fn.startswith('._'): continue # macOS AppleDouble sidecar, not a real GGUF",
|
||||
" fp = os.path.join(root, fn)",
|
||||
" try: size = os.path.getsize(fp)",
|
||||
" except Exception: size = 0",
|
||||
@@ -505,8 +483,6 @@ def _cached_model_scan_script(model_dirs: list[str] | None = None, add_hf_cache:
|
||||
" if u.startswith('KB'): return int(n * 1024)",
|
||||
" return int(n)",
|
||||
"def scan_ollama():",
|
||||
" if any(m.get('is_ollama') for m in models): return",
|
||||
" if os.name == 'nt' and not os.environ.get('ODYSSEUS_ALLOW_OLLAMA_CLI_SCAN'): return",
|
||||
" if not shutil.which('ollama'): return",
|
||||
" try:",
|
||||
" p = subprocess.run(['ollama', 'list'], stdout=subprocess.PIPE, stderr=subprocess.DEVNULL, text=True, timeout=6)",
|
||||
@@ -537,8 +513,8 @@ def _cached_model_scan_script(model_dirs: list[str] | None = None, add_hf_cache:
|
||||
" models.append({'repo_id':name,'size_bytes':size_bytes,'nb_files':1,'has_incomplete':False,'path':'ollama','backend':'ollama','is_ollama':True})",
|
||||
" return",
|
||||
"for _hf_cache in hf_cache_paths(): scan_hf(_hf_cache)",
|
||||
"scan_ollama_api()",
|
||||
"scan_ollama()",
|
||||
"scan_ollama_api()",
|
||||
]
|
||||
for model_dir in model_dirs or []:
|
||||
lines.append(f"scan_dir(os.path.expanduser({model_dir!r}))")
|
||||
@@ -580,36 +556,6 @@ _GGUF_PRELUDE_RE = re.compile(
|
||||
_OLLAMA_HOST_ASSIGNMENT_RE = re.compile(r"(?:^|\s)OLLAMA_HOST=([^\s]+)")
|
||||
_OLLAMA_BIND_RE = re.compile(r"^\[([^\]]+)\]:(\d+)$|^([^:]+):(\d+)$")
|
||||
_OLLAMA_BIND_HOST_RE = re.compile(r"^[A-Za-z0-9._:-]+$")
|
||||
_LLAMA_CPP_PYTHON_GGML_TYPES = {
|
||||
"f32": "0",
|
||||
"f16": "1",
|
||||
"q4_0": "2",
|
||||
"q4_1": "3",
|
||||
"q5_0": "6",
|
||||
"q5_1": "7",
|
||||
"q8_0": "8",
|
||||
"q8_1": "9",
|
||||
"q2_k": "10",
|
||||
"q3_k": "11",
|
||||
"q4_k": "12",
|
||||
"q5_k": "13",
|
||||
"q6_k": "14",
|
||||
"q8_k": "15",
|
||||
"iq2_xxs": "16",
|
||||
"iq2_xs": "17",
|
||||
"iq3_xxs": "18",
|
||||
"iq1_s": "19",
|
||||
"iq4_nl": "20",
|
||||
"iq3_s": "21",
|
||||
"iq2_s": "22",
|
||||
"iq4_xs": "23",
|
||||
"mxfp4": "39",
|
||||
"nvfp4": "40",
|
||||
"q1_0": "41",
|
||||
}
|
||||
_LLAMA_CPP_PYTHON_TYPE_FLAG_RE = re.compile(
|
||||
r"(?P<flag>--type_[kv])(?P<sep>\s+|=)(?P<quote>['\"]?)(?P<value>[A-Za-z0-9_]+)(?P=quote)"
|
||||
)
|
||||
|
||||
|
||||
def _ollama_bind_from_cmd(cmd: str | None, *, default_host: str = "127.0.0.1") -> tuple[str, str]:
|
||||
@@ -641,22 +587,6 @@ def _ollama_bind_from_cmd(cmd: str | None, *, default_host: str = "127.0.0.1") -
|
||||
return f"[{host}]" if bracketed_host else host, port
|
||||
|
||||
|
||||
def _normalize_llama_cpp_python_cache_types(cmd: str | None) -> str | None:
|
||||
"""Map llama.cpp KV cache type names to llama-cpp-python's integer enum."""
|
||||
if not cmd or "llama_cpp.server" not in cmd:
|
||||
return cmd
|
||||
|
||||
def repl(match: re.Match[str]) -> str:
|
||||
value = match.group("value")
|
||||
mapped = _LLAMA_CPP_PYTHON_GGML_TYPES.get(value.lower())
|
||||
if not mapped:
|
||||
return match.group(0)
|
||||
quote = match.group("quote")
|
||||
return f"{match.group('flag')}{match.group('sep')}{quote}{mapped}{quote}"
|
||||
|
||||
return _LLAMA_CPP_PYTHON_TYPE_FLAG_RE.sub(repl, cmd)
|
||||
|
||||
|
||||
def _check_serve_binary(seg: str) -> None:
|
||||
"""Validate that a single command segment starts with an allowlisted binary
|
||||
(after skipping leading env-var assignments like `CUDA_VISIBLE_DEVICES=0`)."""
|
||||
@@ -795,7 +725,6 @@ def _append_llama_cpp_linux_accel_build_lines(runner_lines: list[str]) -> None:
|
||||
runner_lines.append(' done')
|
||||
# rm -rf build so a prior poisoned CMakeCache.txt (e.g. from a failed CUDA
|
||||
# or HIP attempt) doesn't cause the next configure to reuse stale settings.
|
||||
runner_lines.append(' mkdir -p ~/bin')
|
||||
runner_lines.append(' cd ~/llama.cpp && rm -rf build')
|
||||
runner_lines.append(' if command -v hipconfig &>/dev/null || [ -d /opt/rocm ] || [ -n "$ROCM_PATH" ] || [ -n "$HIP_PATH" ]; then')
|
||||
runner_lines.append(' if command -v hipconfig &>/dev/null; then')
|
||||
@@ -858,7 +787,6 @@ def _llama_cpp_rebuild_cmd() -> str:
|
||||
|
||||
class ModelDownloadRequest(BaseModel):
|
||||
repo_id: str
|
||||
backend: str | None = None # "hf" (default) or "ollama"
|
||||
include: str | None = None # glob pattern e.g. "*Q4_K_M*"
|
||||
hf_token: str | None = None
|
||||
env_prefix: str | None = None # e.g. "source ~/venv/bin/activate"
|
||||
@@ -1100,16 +1028,6 @@ def _diagnose_serve_output(text: str) -> dict | None:
|
||||
"vLLM is not installed or not in PATH on this server.",
|
||||
[{"label": "install vLLM in Cookbook Dependencies", "op": "dependency", "package": "vllm"}],
|
||||
),
|
||||
(
|
||||
r"sgl_kernel[\s\S]*(Python\.h|libnuma\.so\.1|common_ops)|"
|
||||
r"(Python\.h|libnuma\.so\.1|common_ops)[\s\S]*sgl_kernel|"
|
||||
r"Please ensure sgl_kernel is properly installed",
|
||||
"SGLang native dependencies are missing on this server.",
|
||||
[
|
||||
{"label": "install OS packages: libnuma-dev python3.12-dev build-essential", "op": "manual"},
|
||||
{"label": "upgrade sglang-kernel after OS packages are installed", "op": "manual"},
|
||||
],
|
||||
),
|
||||
(
|
||||
r"sglang.*command not found|No module named sglang|SGLang is not installed",
|
||||
"SGLang is not installed or not in PATH on this server.",
|
||||
|
||||
@@ -1,75 +0,0 @@
|
||||
"""Pure helpers for shaping cookbook task output for the status response.
|
||||
|
||||
Kept dependency-free (no FastAPI / SQLAlchemy imports) so the behavior can be
|
||||
unit-tested without standing up the whole app.
|
||||
"""
|
||||
|
||||
import re
|
||||
|
||||
_FETCHING_ZERO_FILES_RE = re.compile(r"Fetching\s+0\s+files", re.IGNORECASE)
|
||||
|
||||
# Probe scripts for the dead-session download check, run as
|
||||
# `python3 -c <PROBE> <repo_id> <cache_root>` (locally or over SSH).
|
||||
# cache_root is the task's custom download dir, '' for the default HF cache.
|
||||
# It has to be passed explicitly: the download runner exports
|
||||
# HF_HOME=<local_dir>, so that task's cache lives under <local_dir>/hub, and
|
||||
# the probe process's own environment knows nothing about it.
|
||||
HF_CACHE_COMPLETE_PROBE = (
|
||||
"import os,sys;"
|
||||
"repo=sys.argv[1];"
|
||||
"root=os.path.expanduser(sys.argv[2]) if len(sys.argv)>2 and sys.argv[2] else '';"
|
||||
"base=os.path.join(root,'hub') if root else (os.environ.get('HUGGINGFACE_HUB_CACHE') or os.path.join(os.environ.get('HF_HOME', os.path.expanduser('~/.cache/huggingface')), 'hub'));"
|
||||
"d=os.path.join(base,'models--'+repo.replace('/','--'));"
|
||||
"snap=os.path.join(d,'snapshots');"
|
||||
"ok=os.path.isdir(snap) and any(os.path.isdir(os.path.join(snap,x)) and os.listdir(os.path.join(snap,x)) for x in os.listdir(snap));"
|
||||
"inc=False;"
|
||||
"blobs=os.path.join(d,'blobs');"
|
||||
"inc=os.path.isdir(blobs) and any(x.endswith('.incomplete') for x in os.listdir(blobs));"
|
||||
"sys.exit(0 if ok and not inc else 1)"
|
||||
)
|
||||
|
||||
HF_CACHE_INCOMPLETE_PROBE = (
|
||||
"import os,sys;"
|
||||
"repo=sys.argv[1];"
|
||||
"root=os.path.expanduser(sys.argv[2]) if len(sys.argv)>2 and sys.argv[2] else '';"
|
||||
"base=os.path.join(root,'hub') if root else (os.environ.get('HUGGINGFACE_HUB_CACHE') or os.path.join(os.environ.get('HF_HOME', os.path.expanduser('~/.cache/huggingface')), 'hub'));"
|
||||
"d=os.path.join(base,'models--'+repo.replace('/','--'));"
|
||||
"blobs=os.path.join(d,'blobs');"
|
||||
"inc=os.path.isdir(blobs) and any(x.endswith('.incomplete') for x in os.listdir(blobs));"
|
||||
"sys.exit(0 if inc else 1)"
|
||||
)
|
||||
|
||||
|
||||
def classify_dead_download(full_snapshot: str):
|
||||
"""Resolve a dead download session's status from its runner markers.
|
||||
|
||||
The runner prints DOWNLOAD_OK only after exiting 0 (and DOWNLOAD_FAILED
|
||||
otherwise), so the markers stay trustworthy after the tmux pane is gone.
|
||||
Returns (status, zero_files), or None when the snapshot carries no marker
|
||||
and the caller has to fall back to the cache probe. Same precedence as
|
||||
the live-session branch: DOWNLOAD_OK wins, except a "Fetching 0 files"
|
||||
run is an error (nothing matched the include/quant pattern).
|
||||
"""
|
||||
if not full_snapshot:
|
||||
return None
|
||||
if "DOWNLOAD_OK" in full_snapshot:
|
||||
if _FETCHING_ZERO_FILES_RE.search(full_snapshot):
|
||||
return ("error", True)
|
||||
return ("completed", False)
|
||||
if "DOWNLOAD_FAILED" in full_snapshot:
|
||||
return ("error", False)
|
||||
return None
|
||||
|
||||
|
||||
def error_aware_output_tail(full_snapshot: str, status: str) -> str:
|
||||
"""Return the trailing slice of a task log for the status response.
|
||||
|
||||
Failed tasks return the last 50 lines so the "Copy last 50 lines" action
|
||||
surfaces the actual error context (stack traces, build output). Running and
|
||||
other non-error tasks keep the cheaper 12-line tail to limit the payload on
|
||||
the 10s polling interval.
|
||||
"""
|
||||
if not full_snapshot:
|
||||
return ""
|
||||
tail_lines = 50 if status == "error" else 12
|
||||
return "\n".join(full_snapshot.splitlines()[-tail_lines:])
|
||||
+374
-1099
File diff suppressed because it is too large
Load Diff
@@ -1,13 +1,12 @@
|
||||
"""Diagnostics routes — /api/db/stats, /api/rag/stats, /api/test/youtube, /api/test-research."""
|
||||
|
||||
import logging
|
||||
import os
|
||||
from typing import Dict, Any
|
||||
|
||||
from fastapi import APIRouter, HTTPException, Form, Request
|
||||
|
||||
from services.youtube.youtube_handler import extract_youtube_id, extract_transcript_async
|
||||
from core.constants import DEFAULT_HOST, DATA_DIR
|
||||
from core.constants import DEFAULT_HOST
|
||||
from core.middleware import require_admin
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -17,42 +16,9 @@ def setup_diagnostics_routes(
|
||||
rag_manager,
|
||||
rag_available: bool,
|
||||
research_handler,
|
||||
memory_vector=None,
|
||||
) -> APIRouter:
|
||||
router = APIRouter(tags=["diagnostics"])
|
||||
|
||||
@router.get("/api/diagnostics/services")
|
||||
async def get_service_health(request: Request) -> Dict[str, Any]:
|
||||
"""Consolidated degraded-state report for ChromaDB, SearXNG, email,
|
||||
ntfy, and provider endpoints. Non-intrusive probes — safe to poll."""
|
||||
require_admin(request)
|
||||
from src.service_health import collect_service_health
|
||||
return await collect_service_health(rag_manager, memory_vector)
|
||||
|
||||
@router.get("/api/diagnostics/logs")
|
||||
async def get_diagnostics_logs(request: Request, limit: int = 200) -> Dict[str, Any]:
|
||||
require_admin(request)
|
||||
limit = max(1, min(limit, 1000))
|
||||
try:
|
||||
log_file = os.path.join(DATA_DIR, "logs", "app.log")
|
||||
if not os.path.exists(log_file):
|
||||
return {"status": "success", "logs": []}
|
||||
|
||||
# Safe tail read of the log file (max 5MB via rotation)
|
||||
with open(log_file, "r", encoding="utf-8", errors="ignore") as f:
|
||||
lines = f.readlines()
|
||||
|
||||
tail_lines = lines[-limit:] if len(lines) > limit else lines
|
||||
tail_lines = [line.rstrip('\r\n') for line in tail_lines]
|
||||
|
||||
return {
|
||||
"status": "success",
|
||||
"logs": tail_lines
|
||||
}
|
||||
except Exception as e:
|
||||
logger.error(f"Diagnostics logs retrieval error: {e}")
|
||||
raise HTTPException(500, f"Failed to retrieve logs: {str(e)}")
|
||||
|
||||
@router.get("/api/db/stats")
|
||||
async def get_database_stats(request: Request) -> Dict[str, Any]:
|
||||
require_admin(request)
|
||||
|
||||
@@ -108,10 +108,10 @@ def setup_document_routes(session_manager, upload_handler=None) -> APIRouter:
|
||||
# to markdown for prose.
|
||||
language = req.language
|
||||
if not language:
|
||||
from src.agent_tools.document_tools import _looks_like_email_document, _sniff_doc_language
|
||||
from src.tool_implementations import _looks_like_email_document, _sniff_doc_language
|
||||
language = _sniff_doc_language(req.content)
|
||||
else:
|
||||
from src.agent_tools.document_tools import _looks_like_email_document
|
||||
from src.tool_implementations import _looks_like_email_document
|
||||
if _looks_like_email_document(req.content, req.title):
|
||||
language = "email"
|
||||
|
||||
@@ -503,8 +503,7 @@ def setup_document_routes(session_manager, upload_handler=None) -> APIRouter:
|
||||
user = get_current_user(request)
|
||||
try:
|
||||
data = await request.json()
|
||||
except Exception as e:
|
||||
logger.warning("Failed to parse export request body, defaulting to empty", exc_info=e)
|
||||
except Exception:
|
||||
data = {}
|
||||
ids = data.get("ids") or []
|
||||
if not ids:
|
||||
@@ -644,10 +643,10 @@ def setup_document_routes(session_manager, upload_handler=None) -> APIRouter:
|
||||
# in-memory active-doc pointer so the last-resort injection
|
||||
# path doesn't re-surface this doc in a later chat (#1160).
|
||||
try:
|
||||
from src.agent_tools.document_tools import clear_active_document
|
||||
from src.tool_implementations import clear_active_document
|
||||
clear_active_document(doc_id)
|
||||
except Exception as e:
|
||||
logger.warning("Failed to clear active document %r on detach", doc_id, exc_info=e)
|
||||
except Exception:
|
||||
pass
|
||||
db.commit()
|
||||
db.refresh(doc)
|
||||
return _doc_to_dict(doc)
|
||||
@@ -673,7 +672,7 @@ def setup_document_routes(session_manager, upload_handler=None) -> APIRouter:
|
||||
# Closed/deleted — drop the in-memory active-doc pointer so it isn't
|
||||
# re-injected into a later, unrelated chat (#1160).
|
||||
try:
|
||||
from src.agent_tools.document_tools import clear_active_document
|
||||
from src.tool_implementations import clear_active_document
|
||||
clear_active_document(doc_id)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
+26
-194
@@ -13,8 +13,6 @@ and `email_pollers.py` (the background loops):
|
||||
"""
|
||||
|
||||
import os
|
||||
import base64
|
||||
import time
|
||||
import imaplib
|
||||
import smtplib
|
||||
import email as email_mod
|
||||
@@ -40,106 +38,6 @@ from src.secret_storage import decrypt as _decrypt
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _xoauth2_raw(user: str, access_token: str) -> str:
|
||||
"""The SASL XOAUTH2 initial-response string (unencoded).
|
||||
|
||||
Both smtplib.SMTP.auth() and imaplib.IMAP4.authenticate() base64-encode
|
||||
the value their callback returns, so callers pass this raw form — never
|
||||
pre-encoded — to avoid double base64.
|
||||
"""
|
||||
return f"user={user}\x01auth=Bearer {access_token}\x01\x01"
|
||||
|
||||
|
||||
def _xoauth2_bytes(user: str, access_token: str) -> bytes:
|
||||
"""Raw XOAUTH2 bytes for imaplib's authenticate() callback."""
|
||||
return _xoauth2_raw(user, access_token).encode()
|
||||
|
||||
|
||||
def make_oauth_state(account_id: str, owner: str) -> str:
|
||||
"""Return an HMAC-signed, base64-encoded OAuth state token.
|
||||
|
||||
Encodes account_id + owner + a random nonce, signed with the app secret
|
||||
so the callback can validate that the flow was initiated by an
|
||||
authenticated, owning user (CSRF / state-forgery protection).
|
||||
"""
|
||||
import hmac as _hmac, hashlib as _hl, secrets as _sec
|
||||
from src.secret_storage import _load_or_create_key
|
||||
nonce = _sec.token_hex(16)
|
||||
payload = json.dumps({"a": account_id, "o": owner, "n": nonce}, separators=(",", ":"))
|
||||
sig = _hmac.new(_load_or_create_key(), payload.encode(), _hl.sha256).hexdigest()
|
||||
return base64.urlsafe_b64encode(f"{payload}|{sig}".encode()).decode()
|
||||
|
||||
|
||||
def verify_oauth_state(state: str) -> dict | None:
|
||||
"""Verify an OAuth state token's HMAC signature.
|
||||
|
||||
Returns the decoded payload dict ({"a", "o", "n"}) on success, or None if
|
||||
the token is malformed, tampered, or signed with a different key.
|
||||
"""
|
||||
import hmac as _hmac, hashlib as _hl
|
||||
from src.secret_storage import _load_or_create_key
|
||||
try:
|
||||
decoded = base64.urlsafe_b64decode(state.encode()).decode()
|
||||
payload, sig = decoded.rsplit("|", 1)
|
||||
expected = _hmac.new(_load_or_create_key(), payload.encode(), _hl.sha256).hexdigest()
|
||||
if not _hmac.compare_digest(sig, expected):
|
||||
return None
|
||||
return json.loads(payload)
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
|
||||
def _refresh_google_token(account_id: str) -> str | None:
|
||||
"""Exchange the stored refresh token for a new access token and persist it."""
|
||||
import httpx
|
||||
from core.database import SessionLocal as _SL, EmailAccount as _EA
|
||||
from src.secret_storage import encrypt as _enc, decrypt as _dec
|
||||
client_id = os.environ.get("GOOGLE_OAUTH_CLIENT_ID", "")
|
||||
client_secret = os.environ.get("GOOGLE_OAUTH_CLIENT_SECRET", "")
|
||||
if not client_id or not client_secret:
|
||||
return None
|
||||
db = _SL()
|
||||
try:
|
||||
row = db.get(_EA, account_id)
|
||||
if not row or not row.oauth_refresh_token:
|
||||
return None
|
||||
refresh_token = _dec(row.oauth_refresh_token or "")
|
||||
if not refresh_token:
|
||||
return None
|
||||
resp = httpx.post("https://oauth2.googleapis.com/token", data={
|
||||
"client_id": client_id,
|
||||
"client_secret": client_secret,
|
||||
"refresh_token": refresh_token,
|
||||
"grant_type": "refresh_token",
|
||||
}, timeout=10)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
access_token = data["access_token"]
|
||||
row.oauth_access_token = _enc(access_token)
|
||||
row.oauth_token_expiry = str(int(time.time()) + data.get("expires_in", 3600))
|
||||
db.commit()
|
||||
return access_token
|
||||
except Exception:
|
||||
logger.warning(f"Google token refresh failed for account {account_id}")
|
||||
return None
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
|
||||
def _get_valid_google_token(account_id: str, cfg: dict) -> str | None:
|
||||
"""Return a valid Google access token, refreshing if expired or missing."""
|
||||
from src.secret_storage import decrypt as _dec
|
||||
access_token = _dec(cfg.get("oauth_access_token") or "")
|
||||
expiry_str = cfg.get("oauth_token_expiry") or ""
|
||||
if access_token and expiry_str:
|
||||
try:
|
||||
if int(expiry_str) - 60 > time.time():
|
||||
return access_token
|
||||
except (ValueError, TypeError):
|
||||
pass
|
||||
return _refresh_google_token(account_id)
|
||||
|
||||
|
||||
def _smtp_security_mode(cfg: dict) -> str:
|
||||
raw = str(cfg.get("smtp_security") or "").strip().lower()
|
||||
if raw in {"ssl", "starttls", "none"}:
|
||||
@@ -156,29 +54,20 @@ def _send_smtp_message(cfg: dict, from_addr: str, recipients: list[str], message
|
||||
port = int(cfg.get("smtp_port") or 465)
|
||||
user = cfg.get("smtp_user") or ""
|
||||
password = cfg.get("smtp_password") or ""
|
||||
|
||||
def _auth_smtp(smtp):
|
||||
if cfg.get("oauth_provider") == "google":
|
||||
token = _get_valid_google_token(cfg.get("account_id"), cfg)
|
||||
if not token:
|
||||
raise RuntimeError("Google OAuth token unavailable — reconnect the account")
|
||||
smtp.ehlo()
|
||||
smtp.auth("XOAUTH2", lambda challenge=None: _xoauth2_raw(user, token), initial_response_ok=True)
|
||||
elif user and password:
|
||||
smtp.login(user, password)
|
||||
|
||||
security = _smtp_security_mode(cfg)
|
||||
|
||||
if security == "ssl":
|
||||
with smtplib.SMTP_SSL(host, port, timeout=timeout) as smtp:
|
||||
_auth_smtp(smtp)
|
||||
if user and password:
|
||||
smtp.login(user, password)
|
||||
smtp.sendmail(from_addr, recipients, message)
|
||||
return
|
||||
|
||||
with smtplib.SMTP(host, port, timeout=timeout) as smtp:
|
||||
if security == "starttls":
|
||||
smtp.starttls()
|
||||
_auth_smtp(smtp)
|
||||
if user and password:
|
||||
smtp.login(user, password)
|
||||
smtp.sendmail(from_addr, recipients, message)
|
||||
|
||||
|
||||
@@ -415,7 +304,6 @@ OWNER_SCOPED_EMAIL_CACHE_TABLES = {
|
||||
"email_ai_replies",
|
||||
"email_calendar_extractions",
|
||||
"email_urgency_alerts",
|
||||
"sender_signatures",
|
||||
}
|
||||
|
||||
|
||||
@@ -453,55 +341,6 @@ def _ensure_owner_scoped_email_cache_table(conn, table: str, create_sql: str, co
|
||||
_lg.getLogger(__name__).warning(f"{table} owner-migration skipped: {_mig_e}")
|
||||
|
||||
|
||||
def _ensure_sender_signatures_table(conn):
|
||||
"""Create/migrate learned sender signatures to an owner-scoped cache."""
|
||||
create_sql = """
|
||||
CREATE TABLE IF NOT EXISTS sender_signatures (
|
||||
from_address TEXT,
|
||||
owner TEXT DEFAULT '',
|
||||
signature_text TEXT,
|
||||
sample_count INTEGER,
|
||||
last_built_at TEXT NOT NULL,
|
||||
model_used TEXT,
|
||||
source TEXT,
|
||||
PRIMARY KEY (from_address, owner)
|
||||
)
|
||||
"""
|
||||
conn.execute(create_sql)
|
||||
try:
|
||||
info = conn.execute("PRAGMA table_info(sender_signatures)").fetchall()
|
||||
cols = [r[1] for r in info]
|
||||
pk_cols = [r[1] for r in sorted((r for r in info if r[5]), key=lambda r: r[5])]
|
||||
if "owner" in cols and pk_cols == ["from_address", "owner"]:
|
||||
return
|
||||
|
||||
conn.execute("ALTER TABLE sender_signatures RENAME TO sender_signatures__old")
|
||||
conn.execute(create_sql)
|
||||
old_cols = [r[1] for r in conn.execute("PRAGMA table_info(sender_signatures__old)").fetchall()]
|
||||
copy_cols = [
|
||||
c for c in (
|
||||
"from_address",
|
||||
"signature_text",
|
||||
"sample_count",
|
||||
"last_built_at",
|
||||
"model_used",
|
||||
"source",
|
||||
)
|
||||
if c in old_cols
|
||||
]
|
||||
source_owner = "COALESCE(owner, '')" if "owner" in old_cols else "''"
|
||||
conn.execute(
|
||||
f"INSERT OR IGNORE INTO sender_signatures "
|
||||
f"({', '.join([*copy_cols, 'owner'])}) "
|
||||
f"SELECT {', '.join([*copy_cols, source_owner])} "
|
||||
f"FROM sender_signatures__old"
|
||||
)
|
||||
conn.execute("DROP TABLE sender_signatures__old")
|
||||
except Exception as _mig_e:
|
||||
import logging as _lg
|
||||
_lg.getLogger(__name__).warning(f"sender_signatures owner-migration skipped: {_mig_e}")
|
||||
|
||||
|
||||
def attachment_extract_dir(folder: str, uid: str) -> Path:
|
||||
"""Containment-safe extraction directory for an attachment.
|
||||
|
||||
@@ -720,10 +559,20 @@ def _init_scheduled_db():
|
||||
conn.execute("ALTER TABLE email_boundaries ADD COLUMN turns_json TEXT")
|
||||
except Exception:
|
||||
pass
|
||||
# Per-sender signature cache. Populated by `learn_sender_signatures`.
|
||||
# Message sender addresses are global, so signatures must be scoped to the
|
||||
# mailbox owner before `/read` returns them to the renderer.
|
||||
_ensure_sender_signatures_table(conn)
|
||||
# Per-sender signature cache. Populated by `learn_sender_signatures`
|
||||
# action: the LLM extracts the common trailing block across N emails
|
||||
# from each sender; the renderer folds it consistently for every
|
||||
# future email from that address.
|
||||
conn.execute("""
|
||||
CREATE TABLE IF NOT EXISTS sender_signatures (
|
||||
from_address TEXT PRIMARY KEY,
|
||||
signature_text TEXT,
|
||||
sample_count INTEGER,
|
||||
last_built_at TEXT NOT NULL,
|
||||
model_used TEXT,
|
||||
source TEXT
|
||||
)
|
||||
""")
|
||||
conn.commit()
|
||||
conn.close()
|
||||
|
||||
@@ -812,16 +661,10 @@ def _get_email_config(account_id: str | None = None, owner: str = "") -> dict:
|
||||
"imap_password": _decrypt(row.imap_password or ""),
|
||||
"imap_starttls": bool(row.imap_starttls),
|
||||
"from_address": row.from_address or row.imap_user or "",
|
||||
"oauth_provider": row.oauth_provider or "",
|
||||
"oauth_access_token": row.oauth_access_token or "",
|
||||
"oauth_refresh_token": row.oauth_refresh_token or "",
|
||||
"oauth_token_expiry": row.oauth_token_expiry or "",
|
||||
"display_name": row.display_name or "",
|
||||
}
|
||||
is_oauth = bool(cfg.get("oauth_provider"))
|
||||
if not is_oauth and not (cfg["smtp_host"] and cfg["smtp_user"] and cfg["smtp_password"]):
|
||||
if not (cfg["smtp_host"] and cfg["smtp_user"] and cfg["smtp_password"]):
|
||||
logger.warning(f"SMTP not configured for account {row.name!r}")
|
||||
if not is_oauth and not (cfg["imap_host"] and cfg["imap_user"] and cfg["imap_password"]):
|
||||
if not (cfg["imap_host"] and cfg["imap_user"] and cfg["imap_password"]):
|
||||
logger.warning(f"IMAP not configured for account {row.name!r}")
|
||||
return cfg
|
||||
finally:
|
||||
@@ -919,14 +762,10 @@ def _open_imap_connection(host: str, port: int, *, starttls: bool, timeout: int
|
||||
imaplib._MAXLINE = 50_000_000
|
||||
return conn
|
||||
|
||||
def _imap_connect(account_id: str | None = None, owner: str = "",
|
||||
timeout: int = _IMAP_TIMEOUT_SECONDS):
|
||||
def _imap_connect(account_id: str | None = None, owner: str = ""):
|
||||
# SECURITY: passing `owner` scopes the fallback config lookup so a brand
|
||||
# new user doesn't get connected against another user's default mailbox
|
||||
# when they have no account configured.
|
||||
#
|
||||
# `timeout` is overridable so short-lived callers (e.g. the service-health
|
||||
# probe) can impose a tighter budget than the default IMAP timeout.
|
||||
cfg = _get_email_config(account_id, owner=owner)
|
||||
# Connection mode:
|
||||
# STARTTLS on → plain + upgrade
|
||||
@@ -939,22 +778,15 @@ def _imap_connect(account_id: str | None = None, owner: str = "",
|
||||
cfg["imap_host"],
|
||||
cfg["imap_port"],
|
||||
starttls=bool(cfg.get("imap_starttls")),
|
||||
timeout=timeout,
|
||||
timeout=_IMAP_TIMEOUT_SECONDS,
|
||||
)
|
||||
try:
|
||||
if cfg.get("oauth_provider") == "google":
|
||||
token = _get_valid_google_token(cfg.get("account_id"), cfg)
|
||||
if not token:
|
||||
raise RuntimeError("Google OAuth token unavailable — reconnect the account in Settings → Integrations")
|
||||
conn.authenticate("XOAUTH2", lambda x: _xoauth2_bytes(cfg["imap_user"], token))
|
||||
else:
|
||||
conn.login(cfg["imap_user"], cfg["imap_password"])
|
||||
conn.login(cfg["imap_user"], cfg["imap_password"])
|
||||
except Exception:
|
||||
# A failed AUTHENTICATE (e.g. an Office 365 app password on an
|
||||
# MFA-enabled tenant, #3174, or an expired/revoked OAuth token)
|
||||
# otherwise orphans the already-connected socket; close it before
|
||||
# propagating so a misconfigured account can't leak one descriptor
|
||||
# per retry / background poller pass.
|
||||
# MFA-enabled tenant, #3174) otherwise orphans the already-connected
|
||||
# socket; close it before propagating so a misconfigured account
|
||||
# can't leak one descriptor per retry / background poller pass.
|
||||
try:
|
||||
conn.shutdown()
|
||||
except Exception:
|
||||
|
||||
+39
-340
@@ -13,9 +13,7 @@ handlers need. The split is mechanical — no behavior change.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import sqlite3 as _sql3
|
||||
import time
|
||||
import email as email_mod
|
||||
import email.header
|
||||
import email.utils
|
||||
@@ -45,7 +43,6 @@ from routes.email_helpers import (
|
||||
_load_settings, _save_settings, _get_email_config,
|
||||
_send_smtp_message, _smtp_security_mode,
|
||||
_IMAP_TIMEOUT_SECONDS, _open_imap_connection,
|
||||
make_oauth_state, verify_oauth_state,
|
||||
_imap_connect, _imap, _decode_header, _detect_sent_folder, _detect_drafts_folder,
|
||||
_extract_attachment_text, _list_attachments_from_msg,
|
||||
_extract_attachment_to_disk, _extract_html, _extract_text,
|
||||
@@ -79,16 +76,15 @@ def _email_tag_owner_aliases(account_id: str | None, owner: str = "") -> list[st
|
||||
cfg.get("smtp_user") or "",
|
||||
cfg.get("from_address") or "",
|
||||
])
|
||||
except Exception as _e:
|
||||
logger.warning("Failed to resolve email account alias", exc_info=_e)
|
||||
except Exception:
|
||||
resolved_account_id = None
|
||||
row = db.get(_EA, resolved_account_id) if resolved_account_id else None
|
||||
if row:
|
||||
aliases.extend([row.owner or "", row.imap_user or "", row.from_address or ""])
|
||||
finally:
|
||||
db.close()
|
||||
except Exception as _e:
|
||||
logger.warning("Failed to load email aliases", exc_info=_e)
|
||||
except Exception:
|
||||
pass
|
||||
out = []
|
||||
for a in aliases:
|
||||
a = (a or "").strip()
|
||||
@@ -253,45 +249,8 @@ def _uid_from_fetch_meta(meta_b: bytes) -> str:
|
||||
return m.group(1).decode() if m else ""
|
||||
|
||||
|
||||
_FETCH_SEQ_RE = re.compile(rb"^(\d+)\s+\(")
|
||||
|
||||
|
||||
def _group_uid_fetch_records(msg_data) -> list:
|
||||
"""Group an imaplib UID FETCH response into per-message (meta, payload).
|
||||
|
||||
imaplib yields an interleaved list: ``(meta, literal)`` tuples for
|
||||
attributes that carry a literal (``RFC822.HEADER {n}`` etc.) plus bare
|
||||
``bytes`` elements for everything the server sends outside a literal.
|
||||
Where each attribute lands is server-specific: Dovecot sends FLAGS
|
||||
*before* the header literal (so it ends up inside the tuple meta), while
|
||||
Gmail sends FLAGS *after* it, arriving as a bare ``b' FLAGS (\\Seen))'``
|
||||
element. Dropping bare elements therefore silently loses FLAGS on Gmail
|
||||
and every message renders as unread/unflagged.
|
||||
|
||||
A tuple whose meta starts with a sequence number opens a new record;
|
||||
every other part — continuation tuple or bare bytes — is folded into the
|
||||
current record's meta so attribute regexes see the full meta text.
|
||||
Plain ``b')'`` terminators get folded in too, which is harmless.
|
||||
"""
|
||||
grouped: list = [] # list of (meta_bytes, payload_bytes_or_None)
|
||||
for part in (msg_data or []):
|
||||
if isinstance(part, tuple):
|
||||
meta_b = part[0] if isinstance(part[0], (bytes, bytearray)) else str(part[0]).encode()
|
||||
if _FETCH_SEQ_RE.match(meta_b):
|
||||
grouped.append((meta_b, part[1]))
|
||||
elif grouped:
|
||||
cur_meta, cur_payload = grouped[-1]
|
||||
grouped[-1] = (cur_meta + b" " + meta_b, cur_payload or part[1])
|
||||
elif isinstance(part, (bytes, bytearray)) and grouped:
|
||||
cur_meta, cur_payload = grouped[-1]
|
||||
grouped[-1] = (cur_meta + b" " + bytes(part), cur_payload)
|
||||
return grouped
|
||||
|
||||
|
||||
def _smtp_ready(cfg: dict) -> bool:
|
||||
if not cfg.get("smtp_host") or not cfg.get("smtp_user"):
|
||||
return False
|
||||
return bool(cfg.get("smtp_password") or cfg.get("oauth_provider"))
|
||||
return bool(cfg.get("smtp_host") and cfg.get("smtp_user") and cfg.get("smtp_password"))
|
||||
|
||||
|
||||
def _resolve_send_config(account_id: str | None = None, owner: str = "") -> dict:
|
||||
@@ -840,11 +799,20 @@ def setup_email_routes():
|
||||
except Exception as e:
|
||||
logger.warning(f"Batch fetch failed, falling back to per-UID: {e}")
|
||||
status, msg_data = "NO", []
|
||||
# Group the batched response into per-message (meta, payload)
|
||||
# records. Bare bytes parts must be kept: Gmail returns FLAGS
|
||||
# after the header literal as a bare element, and dropping it
|
||||
# rendered every Gmail message as unread/unflagged.
|
||||
grouped = _group_uid_fetch_records(msg_data)
|
||||
# imaplib batch responses interleave (meta, payload) tuples and
|
||||
# `b')'` terminators. Group by message: each tuple where the
|
||||
# meta begins with a seq number starts a new message record.
|
||||
seq_re = re.compile(rb'^(\d+)\s+\(')
|
||||
grouped = [] # list of (meta_str, payload_bytes)
|
||||
for part in (msg_data or []):
|
||||
if isinstance(part, tuple):
|
||||
meta_b = part[0] if isinstance(part[0], (bytes, bytearray)) else str(part[0]).encode()
|
||||
if seq_re.match(meta_b):
|
||||
grouped.append((meta_b, part[1]))
|
||||
elif grouped:
|
||||
# continuation of previous message — concatenate meta info if any
|
||||
cur_meta, cur_payload = grouped[-1]
|
||||
grouped[-1] = (cur_meta + b" " + meta_b, cur_payload or part[1])
|
||||
|
||||
if status != "OK" and not grouped:
|
||||
conn.logout()
|
||||
@@ -1093,22 +1061,14 @@ def setup_email_routes():
|
||||
return {"contacts": [], "error": "Mail operation failed"}
|
||||
|
||||
@router.get("/search")
|
||||
# Sync def: the body is blocking IMAP I/O with no awaits. As `async def` it ran
|
||||
# directly on the event loop and stalled the whole app during a search; as a sync
|
||||
# def FastAPI runs it in a threadpool, keeping the loop responsive.
|
||||
def search_emails(
|
||||
async def search_emails(
|
||||
q: str = Query(""),
|
||||
folder: str = Query("INBOX"),
|
||||
limit: int = Query(50),
|
||||
account_id: str | None = Query(None),
|
||||
owner: str = Depends(require_owner),
|
||||
):
|
||||
"""Search emails server-side via IMAP SEARCH. Matches subject, from, or body text.
|
||||
|
||||
When the caller asks for INBOX and the account has an "All Mail"
|
||||
folder (Gmail does), we transparently swap to All Mail so the
|
||||
search surfaces archived / labelled emails too. Plain IMAP
|
||||
accounts fall back to whatever folder the caller specified."""
|
||||
"""Search emails server-side via IMAP SEARCH. Matches subject, from, or body text."""
|
||||
if not q or len(q) < 2:
|
||||
return {"emails": [], "total": 0, "query": q}
|
||||
# CRLF in q would terminate the IMAP command early — reject defensively.
|
||||
@@ -1116,27 +1076,7 @@ def setup_email_routes():
|
||||
raise HTTPException(400, "Invalid query")
|
||||
try:
|
||||
with _imap(account_id, owner=owner) as conn:
|
||||
# If the user asked for INBOX, try to upgrade to All Mail —
|
||||
# one folder == every email on Gmail-class servers.
|
||||
effective_folder = folder
|
||||
if (folder or "").upper() == "INBOX":
|
||||
try:
|
||||
status, folder_lines = conn.list()
|
||||
if status == "OK" and folder_lines:
|
||||
for raw in folder_lines:
|
||||
if isinstance(raw, bytes):
|
||||
raw = raw.decode("utf-8", errors="replace")
|
||||
m = re.match(r"\((?P<flags>[^)]*)\)\s+\"[^\"]*\"\s+(?P<name>.+)", raw)
|
||||
if not m:
|
||||
continue
|
||||
flags = (m.group("flags") or "").lower()
|
||||
name = m.group("name").strip().strip('"')
|
||||
if "\\all" in flags or "all mail" in name.lower():
|
||||
effective_folder = name
|
||||
break
|
||||
except Exception:
|
||||
pass
|
||||
conn.select(_q(effective_folder), readonly=True)
|
||||
conn.select(_q(folder), readonly=True)
|
||||
|
||||
# Escape backslash and quote for the IMAP-SEARCH quoted-string.
|
||||
q_escaped = q.replace('\\', '\\\\').replace('"', '\\"')
|
||||
@@ -1144,7 +1084,7 @@ def setup_email_routes():
|
||||
|
||||
status, data = _imap_uid_search(conn, search_cmd)
|
||||
if status != "OK" or not data[0]:
|
||||
return {"emails": [], "total": 0, "query": q, "folder": effective_folder}
|
||||
return {"emails": [], "total": 0, "query": q}
|
||||
|
||||
uid_list = data[0].split()
|
||||
total = len(uid_list)
|
||||
@@ -1158,15 +1098,14 @@ def setup_email_routes():
|
||||
continue
|
||||
raw_header = None
|
||||
flags = ""
|
||||
# Same Gmail caveat as the list route: FLAGS may
|
||||
# arrive after the header literal, so group bare
|
||||
# parts back into the message meta before scanning.
|
||||
for meta_b, payload in _group_uid_fetch_records(msg_data):
|
||||
if payload and b"RFC822.HEADER" in meta_b:
|
||||
raw_header = payload
|
||||
flag_match = re.search(rb'FLAGS \(([^)]*)\)', meta_b)
|
||||
if flag_match:
|
||||
flags = flag_match.group(1).decode(errors="replace")
|
||||
for part in msg_data:
|
||||
if isinstance(part, tuple):
|
||||
meta = part[0].decode() if isinstance(part[0], bytes) else str(part[0])
|
||||
if b"RFC822.HEADER" in part[0] if isinstance(part[0], bytes) else "RFC822.HEADER" in meta:
|
||||
raw_header = part[1]
|
||||
flag_match = re.search(r'FLAGS \(([^)]*)\)', meta)
|
||||
if flag_match:
|
||||
flags = flag_match.group(1)
|
||||
if not raw_header:
|
||||
continue
|
||||
msg = email_mod.message_from_bytes(raw_header)
|
||||
@@ -1209,13 +1148,6 @@ def setup_email_routes():
|
||||
"is_flagged": "\\Flagged" in flags,
|
||||
"flags": flags,
|
||||
"has_attachments": has_attachments,
|
||||
# Stamp the folder so the frontend opens each
|
||||
# email from the folder it actually lives in
|
||||
# (the search may have run against All Mail
|
||||
# even though the caller asked for INBOX),
|
||||
# otherwise clicks open whatever happens to
|
||||
# have the same UID in INBOX → wrong email.
|
||||
"folder": effective_folder,
|
||||
})
|
||||
except Exception as e:
|
||||
logger.warning(f"Error parsing search result {uid}: {e}")
|
||||
@@ -1315,9 +1247,8 @@ def setup_email_routes():
|
||||
try:
|
||||
if sender_addr:
|
||||
_rs = _c.execute(
|
||||
f"SELECT signature_text FROM sender_signatures "
|
||||
f"WHERE from_address = ? AND {owner_clause}",
|
||||
(sender_addr.lower().strip(), *owner_params),
|
||||
"SELECT signature_text FROM sender_signatures WHERE from_address = ?",
|
||||
(sender_addr.lower().strip(),),
|
||||
).fetchone()
|
||||
if _rs and _rs[0]:
|
||||
cached_sender_sig = _rs[0]
|
||||
@@ -1762,22 +1693,6 @@ def setup_email_routes():
|
||||
logger.error(f"Failed to mark unread {uid}: {e}")
|
||||
return {"success": False, "error": "Mail operation failed"}
|
||||
|
||||
@router.post("/flag/{uid}")
|
||||
async def flag_email(uid: str, folder: str = Query("INBOX"), account_id: str | None = Query(None),
|
||||
on: bool = Query(True), owner: str = Depends(require_owner)):
|
||||
"""Toggle the \\Flagged flag (a.k.a. favorite / star) on an email.
|
||||
Pass `on=true` to favorite, `on=false` to unfavorite."""
|
||||
try:
|
||||
with _imap(account_id, owner=owner) as conn:
|
||||
conn.select(_q(folder))
|
||||
if not _store_email_flag(conn, uid, "\\Flagged", add=bool(on)):
|
||||
return {"success": False, "error": "Email not found"}
|
||||
_invalidate_list_cache(account_id, folder)
|
||||
return {"success": True, "flagged": bool(on)}
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to flag {uid}: {e}")
|
||||
return {"success": False, "error": "Mail operation failed"}
|
||||
|
||||
@router.post("/mark-read/{uid}")
|
||||
async def mark_read(uid: str, folder: str = Query("INBOX"), account_id: str | None = Query(None), owner: str = Depends(require_owner)):
|
||||
"""Mark an email as read (set \\Seen flag)."""
|
||||
@@ -1793,9 +1708,7 @@ def setup_email_routes():
|
||||
return {"success": False, "error": "Mail operation failed"}
|
||||
|
||||
@router.post("/archive/{uid}")
|
||||
# Sync def: blocking IMAP I/O with no awaits — see search_emails above. Runs in a
|
||||
# threadpool instead of blocking the event loop.
|
||||
def archive_email(uid: str, folder: str = Query("INBOX"), account_id: str | None = Query(None), owner: str = Depends(require_owner)):
|
||||
async def archive_email(uid: str, folder: str = Query("INBOX"), account_id: str | None = Query(None), owner: str = Depends(require_owner)):
|
||||
"""Move email to Archive folder."""
|
||||
try:
|
||||
with _imap(account_id, owner=owner) as conn:
|
||||
@@ -2027,7 +1940,7 @@ def setup_email_routes():
|
||||
outer = MIMEMultipart("alternative")
|
||||
body_container = outer
|
||||
|
||||
outer["From"] = email.utils.formataddr((cfg.get("display_name") or "", cfg["from_address"]))
|
||||
outer["From"] = cfg["from_address"]
|
||||
outer["To"] = to
|
||||
if cc:
|
||||
outer["Cc"] = cc
|
||||
@@ -2158,79 +2071,6 @@ def setup_email_routes():
|
||||
logger.error(f"cancel_scheduled {sid!r} failed: {e}")
|
||||
return {"success": False, "error": "Mail operation failed"}
|
||||
|
||||
# ── Agent send-confirm: list/approve/cancel ──────────────────────────
|
||||
# When `agent_email_confirm` is on, the MCP send_email tool drops the
|
||||
# composed email into scheduled_emails with status='agent_draft' (a
|
||||
# far-future send_at so the poller never picks it up). These endpoints
|
||||
# let the chat UI surface them for the user and either approve (flip
|
||||
# to status='pending' with send_at=now so the poller delivers it) or
|
||||
# cancel (status='cancelled').
|
||||
@router.get("/pending")
|
||||
async def list_pending_agent_drafts(owner: str = Depends(require_owner)):
|
||||
import sqlite3
|
||||
try:
|
||||
conn = sqlite3.connect(SCHEDULED_DB)
|
||||
conn.row_factory = sqlite3.Row
|
||||
# The MCP server can't easily set owner, so it stores '' — fall
|
||||
# back to those rows in addition to the caller's owner.
|
||||
rows = conn.execute(
|
||||
"""SELECT id, to_addr, subject, body, created_at, account_id
|
||||
FROM scheduled_emails
|
||||
WHERE status = 'agent_draft' AND (owner = ? OR owner = '')
|
||||
ORDER BY created_at DESC""",
|
||||
(owner or "",),
|
||||
).fetchall()
|
||||
conn.close()
|
||||
return {"pending": [dict(r) for r in rows]}
|
||||
except Exception as e:
|
||||
logger.error(f"list_pending_agent_drafts failed: {e}")
|
||||
return {"pending": [], "error": "Mail operation failed"}
|
||||
|
||||
@router.post("/pending/{sid}/approve")
|
||||
async def approve_agent_draft(sid: str, owner: str = Depends(require_owner)):
|
||||
"""Approve a draft staged by the agent: flip status → pending and
|
||||
backdate send_at so the scheduled-send poller picks it up
|
||||
immediately."""
|
||||
import sqlite3
|
||||
try:
|
||||
conn = sqlite3.connect(SCHEDULED_DB)
|
||||
cur = conn.execute(
|
||||
"""UPDATE scheduled_emails
|
||||
SET status = 'pending', send_at = ?
|
||||
WHERE id = ? AND status = 'agent_draft' AND (owner = ? OR owner = '')""",
|
||||
(datetime.utcnow().isoformat(), sid, owner or ""),
|
||||
)
|
||||
conn.commit()
|
||||
affected = cur.rowcount
|
||||
conn.close()
|
||||
if not affected:
|
||||
return {"success": False, "error": "Draft not found or already handled"}
|
||||
return {"success": True}
|
||||
except Exception as e:
|
||||
logger.error(f"approve_agent_draft {sid!r} failed: {e}")
|
||||
return {"success": False, "error": "Mail operation failed"}
|
||||
|
||||
@router.delete("/pending/{sid}")
|
||||
async def cancel_agent_draft(sid: str, owner: str = Depends(require_owner)):
|
||||
"""Discard a draft the agent staged for approval."""
|
||||
import sqlite3
|
||||
try:
|
||||
conn = sqlite3.connect(SCHEDULED_DB)
|
||||
cur = conn.execute(
|
||||
"""UPDATE scheduled_emails SET status = 'cancelled'
|
||||
WHERE id = ? AND status = 'agent_draft' AND (owner = ? OR owner = '')""",
|
||||
(sid, owner or ""),
|
||||
)
|
||||
conn.commit()
|
||||
affected = cur.rowcount
|
||||
conn.close()
|
||||
if not affected:
|
||||
return {"success": False, "error": "Draft not found or already handled"}
|
||||
return {"success": True}
|
||||
except Exception as e:
|
||||
logger.error(f"cancel_agent_draft {sid!r} failed: {e}")
|
||||
return {"success": False, "error": "Mail operation failed"}
|
||||
|
||||
@router.get("/resolve-contact")
|
||||
async def resolve_contact(name: str = Query(..., description="Name to search for"), owner: str = Depends(require_owner)):
|
||||
"""Search Sent folder for a contact by name. Returns matching email addresses."""
|
||||
@@ -2291,7 +2131,6 @@ def setup_email_routes():
|
||||
try:
|
||||
cfg = _resolve_send_config(req.account_id, owner=owner)
|
||||
except Exception as e:
|
||||
logger.warning(f"No SMTP-capable account resolved: {e}")
|
||||
return {"success": False, "error": str(e) or "No SMTP-capable email account configured"}
|
||||
|
||||
# Use 'mixed' if we have attachments, 'alternative' otherwise
|
||||
@@ -2304,7 +2143,7 @@ def setup_email_routes():
|
||||
outer = MIMEMultipart("alternative")
|
||||
body_container = outer
|
||||
|
||||
outer["From"] = email.utils.formataddr((cfg.get("display_name") or "", cfg["from_address"]))
|
||||
outer["From"] = cfg["from_address"]
|
||||
outer["To"] = req.to
|
||||
if req.cc:
|
||||
outer["Cc"] = req.cc
|
||||
@@ -2355,10 +2194,6 @@ def setup_email_routes():
|
||||
|
||||
_account_id = cfg.get("account_id") or req.account_id # capture for the IMAP append in the closure
|
||||
_in_reply_to = (req.in_reply_to or "").strip()
|
||||
_oauth_provider = cfg.get("oauth_provider") or ""
|
||||
_oauth_access_token = cfg.get("oauth_access_token") or ""
|
||||
_oauth_refresh_token = cfg.get("oauth_refresh_token") or ""
|
||||
_oauth_token_expiry = cfg.get("oauth_token_expiry") or ""
|
||||
|
||||
def _deliver():
|
||||
try:
|
||||
@@ -2369,11 +2204,6 @@ def setup_email_routes():
|
||||
"smtp_security": _smtp_security,
|
||||
"smtp_user": _smtp_user,
|
||||
"smtp_password": _smtp_pw,
|
||||
"account_id": _account_id,
|
||||
"oauth_provider": _oauth_provider,
|
||||
"oauth_access_token": _oauth_access_token,
|
||||
"oauth_refresh_token": _oauth_refresh_token,
|
||||
"oauth_token_expiry": _oauth_token_expiry,
|
||||
},
|
||||
_from,
|
||||
_recipients,
|
||||
@@ -2486,7 +2316,7 @@ def setup_email_routes():
|
||||
msg.attach(MIMEText(_draft_html, "html", "utf-8"))
|
||||
else:
|
||||
msg = MIMEText(req.body, "plain", "utf-8")
|
||||
msg["From"] = email.utils.formataddr((cfg.get("display_name") or "", cfg["from_address"]))
|
||||
msg["From"] = cfg["from_address"]
|
||||
msg["To"] = req.to
|
||||
if req.cc:
|
||||
msg["Cc"] = req.cc
|
||||
@@ -2754,15 +2584,11 @@ def setup_email_routes():
|
||||
source_uid = (data.get("uid") or "").strip()
|
||||
source_folder = (data.get("folder") or "INBOX").strip()
|
||||
fast_reply = bool(data.get("fast", False))
|
||||
user_hint = (data.get("user_hint") or "").strip()
|
||||
|
||||
if not original_body:
|
||||
return {"success": False, "error": "No email body provided"}
|
||||
|
||||
# Skip cache lookup when the caller supplied a user_hint — the
|
||||
# cached generic reply doesn't reflect the instructions and
|
||||
# would silently override them.
|
||||
if message_id and not user_hint:
|
||||
if message_id:
|
||||
try:
|
||||
_c = _sql3.connect(SCHEDULED_DB)
|
||||
owner_clause, owner_params = _email_cache_owner_clause(owner)
|
||||
@@ -2902,13 +2728,8 @@ def setup_email_routes():
|
||||
user_msg = (
|
||||
f"Recipient: {to}\nSubject: {subject}\n\n"
|
||||
f"Original email and any current draft:\n{original_body[:6000]}\n\n"
|
||||
f"Draft a reply. Return only the reply body text."
|
||||
)
|
||||
if user_hint:
|
||||
user_msg += (
|
||||
f"User's instructions for THIS reply (follow these — they override "
|
||||
f"defaults like length/tone):\n{user_hint[:2000]}\n\n"
|
||||
)
|
||||
user_msg += "Draft a reply. Return only the reply body text."
|
||||
|
||||
# Build a candidate chain so a stale session-stored API key
|
||||
# (the most common cause of "authentication failed" here)
|
||||
@@ -3138,8 +2959,6 @@ def setup_email_routes():
|
||||
"from_address": r.from_address or "",
|
||||
"has_imap_password": bool(r.imap_password),
|
||||
"has_smtp_password": bool(r.smtp_password),
|
||||
"oauth_provider": r.oauth_provider or "",
|
||||
"display_name": r.display_name or "",
|
||||
})
|
||||
return {"accounts": out}
|
||||
finally:
|
||||
@@ -3172,7 +2991,6 @@ def setup_email_routes():
|
||||
smtp_user=(data.get("smtp_user") or "").strip(),
|
||||
smtp_password=_enc(data.get("smtp_password") or ""),
|
||||
from_address=(data.get("from_address") or "").strip(),
|
||||
display_name=(data.get("display_name") or "").strip(),
|
||||
# SECURITY: stamp the creator so all subsequent reads / mutations
|
||||
# can filter by user. Without this every new account leaks to
|
||||
# every other user.
|
||||
@@ -3207,7 +3025,7 @@ def setup_email_routes():
|
||||
if not row:
|
||||
return {"ok": False, "error": "Account not found"}
|
||||
# Simple fields
|
||||
for key in ("name", "imap_host", "imap_user", "smtp_host", "smtp_user", "from_address", "display_name"):
|
||||
for key in ("name", "imap_host", "imap_user", "smtp_host", "smtp_user", "from_address"):
|
||||
if key in data:
|
||||
setattr(row, key, (data[key] or "").strip())
|
||||
for key in ("imap_port", "smtp_port"):
|
||||
@@ -3396,123 +3214,4 @@ def setup_email_routes():
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
# ── Google OAuth2 routes ──
|
||||
|
||||
@router.get("/oauth/google/authorize")
|
||||
async def google_oauth_authorize(account_id: str = Query(...), request: Request = None, owner: str = Depends(require_user)):
|
||||
import urllib.parse
|
||||
_assert_owns_account(account_id, owner)
|
||||
client_id = os.environ.get("GOOGLE_OAUTH_CLIENT_ID", "")
|
||||
if not client_id:
|
||||
raise HTTPException(400, "GOOGLE_OAUTH_CLIENT_ID not set — add it to .env")
|
||||
redirect_uri = (
|
||||
os.environ.get("GOOGLE_OAUTH_REDIRECT_URI")
|
||||
or f"http://{request.headers.get('host', 'localhost:7000')}/api/email/oauth/google/callback"
|
||||
)
|
||||
state = make_oauth_state(account_id, owner)
|
||||
params = urllib.parse.urlencode({
|
||||
"client_id": client_id,
|
||||
"redirect_uri": redirect_uri,
|
||||
"response_type": "code",
|
||||
"scope": "https://mail.google.com/ email",
|
||||
"access_type": "offline",
|
||||
"prompt": "consent",
|
||||
"state": state,
|
||||
})
|
||||
from fastapi.responses import RedirectResponse as _RR
|
||||
return _RR(f"https://accounts.google.com/o/oauth2/v2/auth?{params}")
|
||||
|
||||
@router.get("/oauth/google/callback")
|
||||
async def google_oauth_callback(
|
||||
code: str = Query(None),
|
||||
state: str = Query(None),
|
||||
error: str = Query(None),
|
||||
request: Request = None,
|
||||
):
|
||||
import urllib.parse
|
||||
from fastapi.responses import RedirectResponse as _RR
|
||||
if error:
|
||||
return _RR("/?section=integrations&email_oauth_error=google_error")
|
||||
if not code or not state:
|
||||
return _RR("/?section=integrations&email_oauth_error=missing_code")
|
||||
state_data = verify_oauth_state(state)
|
||||
if not state_data:
|
||||
return _RR("/?section=integrations&email_oauth_error=invalid_state")
|
||||
account_id = state_data.get("a", "")
|
||||
owner = state_data.get("o", "")
|
||||
client_id = os.environ.get("GOOGLE_OAUTH_CLIENT_ID", "")
|
||||
client_secret = os.environ.get("GOOGLE_OAUTH_CLIENT_SECRET", "")
|
||||
redirect_uri = (
|
||||
os.environ.get("GOOGLE_OAUTH_REDIRECT_URI")
|
||||
or f"http://{request.headers.get('host', 'localhost:7000')}/api/email/oauth/google/callback"
|
||||
)
|
||||
import httpx as _httpx
|
||||
try:
|
||||
resp = _httpx.post("https://oauth2.googleapis.com/token", data={
|
||||
"code": code,
|
||||
"client_id": client_id,
|
||||
"client_secret": client_secret,
|
||||
"redirect_uri": redirect_uri,
|
||||
"grant_type": "authorization_code",
|
||||
}, timeout=10)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
except Exception:
|
||||
logger.warning("Google token exchange failed")
|
||||
return _RR("/?section=integrations&email_oauth_error=token_exchange_failed")
|
||||
access_token = data.get("access_token", "")
|
||||
refresh_token = data.get("refresh_token", "")
|
||||
expiry = str(int(time.time()) + data.get("expires_in", 3600))
|
||||
# Fetch the email address from userinfo so we can auto-fill imap_user.
|
||||
email_addr = ""
|
||||
display_name = ""
|
||||
try:
|
||||
ui = _httpx.get("https://www.googleapis.com/oauth2/v1/userinfo",
|
||||
headers={"Authorization": f"Bearer {access_token}"}, timeout=10)
|
||||
if ui.is_success:
|
||||
ui_data = ui.json()
|
||||
email_addr = ui_data.get("email", "")
|
||||
display_name = ui_data.get("name", "")
|
||||
except Exception:
|
||||
pass
|
||||
from core.database import SessionLocal, EmailAccount
|
||||
from src.secret_storage import encrypt as _enc
|
||||
db = SessionLocal()
|
||||
try:
|
||||
row = db.query(EmailAccount).filter(EmailAccount.id == account_id).first()
|
||||
if not row:
|
||||
return _RR("/?section=integrations&email_oauth_error=account_not_found")
|
||||
# SECURITY: verify the account belongs to the initiating user.
|
||||
if owner and row.owner and row.owner != owner:
|
||||
logger.warning("OAuth callback owner mismatch — rejecting token write")
|
||||
return _RR("/?section=integrations&email_oauth_error=ownership_error")
|
||||
row.oauth_provider = "google"
|
||||
row.oauth_access_token = _enc(access_token)
|
||||
if refresh_token:
|
||||
row.oauth_refresh_token = _enc(refresh_token)
|
||||
row.oauth_token_expiry = expiry
|
||||
# Auto-fill Google IMAP/SMTP settings if not already configured.
|
||||
if not row.imap_host:
|
||||
row.imap_host = "imap.gmail.com"
|
||||
row.imap_port = 993
|
||||
row.imap_starttls = False
|
||||
if not row.smtp_host:
|
||||
row.smtp_host = "smtp.gmail.com"
|
||||
row.smtp_port = 587
|
||||
if email_addr:
|
||||
if not row.imap_user:
|
||||
row.imap_user = email_addr
|
||||
if not row.smtp_user:
|
||||
row.smtp_user = email_addr
|
||||
if not row.from_address:
|
||||
row.from_address = email_addr
|
||||
if not row.name or row.name == row.id:
|
||||
row.name = email_addr
|
||||
if display_name and not row.display_name:
|
||||
row.display_name = display_name
|
||||
db.commit()
|
||||
finally:
|
||||
db.close()
|
||||
return _RR("/?section=integrations&email_oauth_success=1")
|
||||
|
||||
return router
|
||||
|
||||
@@ -9,7 +9,6 @@ from pathlib import Path
|
||||
from fastapi import APIRouter, HTTPException, Form, Depends
|
||||
from core.constants import EMBEDDING_ENDPOINT_FILE, FASTEMBED_CACHE_DIR
|
||||
from core.middleware import require_admin
|
||||
from src.runtime_paths import get_app_root
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@@ -11,7 +11,6 @@ from typing import Dict, Any, Optional
|
||||
from pydantic import BaseModel
|
||||
|
||||
from core.database import GalleryImage
|
||||
from src.auth_helpers import _auth_disabled
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -121,18 +120,19 @@ def _image_to_dict(img: GalleryImage, session_name: str = None) -> Dict[str, Any
|
||||
}
|
||||
|
||||
|
||||
def _owner_filter(q, user, model_cls=GalleryImage):
|
||||
def _owner_filter(q, user):
|
||||
"""Apply owner filtering to a gallery query.
|
||||
|
||||
``get_current_user`` returns None both in auth-disabled single-user mode
|
||||
and when auth is enabled but no current user was resolved. Preserve the
|
||||
single-user behavior, but fail closed for auth-enabled null-user states.
|
||||
When auth is disabled (single-user mode) get_current_user returns None
|
||||
and there is no per-user scoping. The main library list and stats already
|
||||
treat None as "show everything" (`if user is not None`), so this helper
|
||||
must too — otherwise the tag/model filter sidebars come back empty and the
|
||||
tag-cleanup endpoints (clear-user-tags, clear-ai-tags, dedupe-tags)
|
||||
silently affect zero rows in the most common self-hosted deployment.
|
||||
"""
|
||||
if user is not None:
|
||||
return q.filter(model_cls.owner == user)
|
||||
if _auth_disabled():
|
||||
if user is None:
|
||||
return q
|
||||
return q.filter(False)
|
||||
return q.filter(GalleryImage.owner == user)
|
||||
|
||||
|
||||
|
||||
|
||||
+35
-68
@@ -19,7 +19,6 @@ from src.upload_limits import (
|
||||
GALLERY_TRANSFORM_UPLOAD_MAX_BYTES,
|
||||
)
|
||||
from src.constants import GENERATED_IMAGES_DIR
|
||||
from src.optional_deps import patch_realesrgan_torchvision_compat
|
||||
|
||||
from routes.gallery_helpers import (
|
||||
GalleryPatch, _extract_exif, _image_to_dict, _owner_filter, _human_size,
|
||||
@@ -67,14 +66,6 @@ def _gallery_image_path(filename: str) -> Path:
|
||||
raise HTTPException(400, "Unsafe gallery filename")
|
||||
if safe_name != original:
|
||||
raise HTTPException(400, "Unsafe gallery filename")
|
||||
if not path.exists():
|
||||
cwd_root = (Path.cwd() / "data" / "generated_images").resolve()
|
||||
cwd_path = (cwd_root / safe_name).resolve()
|
||||
try:
|
||||
if os.path.commonpath([str(cwd_root), str(cwd_path)]) == str(cwd_root) and cwd_path.exists():
|
||||
return cwd_path
|
||||
except Exception:
|
||||
pass
|
||||
return path
|
||||
|
||||
|
||||
@@ -117,32 +108,6 @@ def _visible_image_endpoint_for_base(db, base: str, owner: str | None):
|
||||
return fallback
|
||||
|
||||
|
||||
async def _fetch_result_image_b64(url: str) -> Optional[str]:
|
||||
"""Fetch an image URL returned in an upstream response body, base64-encoded
|
||||
(or None on a non-200).
|
||||
|
||||
The URL comes from the diffusion/OpenAI server's response, not from our own
|
||||
config, so a malicious or compromised endpoint could otherwise steer this
|
||||
fetch at an internal or cloud-metadata address. Validate it the same way the
|
||||
client-supplied endpoint is validated before the first request.
|
||||
"""
|
||||
import base64
|
||||
import httpx
|
||||
from src.url_safety import check_outbound_url
|
||||
|
||||
ok, reason = check_outbound_url(
|
||||
url,
|
||||
block_private=os.getenv("IMAGE_BLOCK_PRIVATE_IPS", "false").lower() == "true",
|
||||
)
|
||||
if not ok:
|
||||
raise HTTPException(502, f"Upstream returned an unsafe image URL: {reason}")
|
||||
async with httpx.AsyncClient(timeout=60) as c2:
|
||||
ir = await c2.get(url)
|
||||
if ir.status_code == 200:
|
||||
return base64.b64encode(ir.content).decode()
|
||||
return None
|
||||
|
||||
|
||||
def setup_gallery_routes() -> APIRouter:
|
||||
router = APIRouter(tags=["gallery"])
|
||||
|
||||
@@ -232,6 +197,8 @@ def setup_gallery_routes() -> APIRouter:
|
||||
@router.post("/api/gallery/{image_id}/replace")
|
||||
async def gallery_replace(request: Request, image_id: str):
|
||||
"""Replace an existing gallery image file with a new one."""
|
||||
from pathlib import Path
|
||||
|
||||
user = get_current_user(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
@@ -247,8 +214,9 @@ def setup_gallery_routes() -> APIRouter:
|
||||
raise HTTPException(400, "No image provided")
|
||||
|
||||
content = await read_upload_limited(file, GALLERY_UPLOAD_MAX_BYTES, "Gallery replacement")
|
||||
GALLERY_IMAGE_DIR.mkdir(parents=True, exist_ok=True)
|
||||
img_path = _gallery_image_path(img.filename)
|
||||
img_dir = Path(GENERATED_IMAGES_DIR)
|
||||
img_dir.mkdir(parents=True, exist_ok=True)
|
||||
img_path = img_dir / _sanitize_gallery_filename(img.filename)
|
||||
img_path.write_bytes(content)
|
||||
|
||||
# Refresh dimensions in case the editor resized the canvas.
|
||||
@@ -508,7 +476,8 @@ def setup_gallery_routes() -> APIRouter:
|
||||
.outerjoin(DbSession, GalleryImage.session_id == DbSession.id)
|
||||
.filter(GalleryImage.is_active == True)
|
||||
)
|
||||
q = _owner_filter(q, user)
|
||||
if user is not None:
|
||||
q = q.filter(GalleryImage.owner == user)
|
||||
|
||||
# Search filter (prompt + tags + ai_tags)
|
||||
if search:
|
||||
@@ -610,26 +579,28 @@ def setup_gallery_routes() -> APIRouter:
|
||||
db = SessionLocal()
|
||||
try:
|
||||
q = db.query(GalleryAlbum)
|
||||
q = _owner_filter(q, user, GalleryAlbum)
|
||||
if user:
|
||||
q = q.filter(GalleryAlbum.owner == user)
|
||||
albums = q.order_by(GalleryAlbum.created_at.desc()).all()
|
||||
result = []
|
||||
for a in albums:
|
||||
_count_q = db.query(GalleryImage).filter(
|
||||
GalleryImage.album_id == a.id, GalleryImage.is_active == True
|
||||
)
|
||||
_count_q = _owner_filter(_count_q, user)
|
||||
if user:
|
||||
_count_q = _count_q.filter(GalleryImage.owner == user)
|
||||
count = _count_q.count()
|
||||
cover_url = None
|
||||
if a.cover_id:
|
||||
cover_q = db.query(GalleryImage).filter(GalleryImage.id == a.cover_id)
|
||||
cover = _owner_filter(cover_q, user).first()
|
||||
cover = db.query(GalleryImage).filter(GalleryImage.id == a.cover_id).first()
|
||||
if cover:
|
||||
cover_url = f"/api/generated-image/{cover.filename}"
|
||||
elif count > 0:
|
||||
_cover_q = db.query(GalleryImage).filter(
|
||||
GalleryImage.album_id == a.id, GalleryImage.is_active == True
|
||||
)
|
||||
_cover_q = _owner_filter(_cover_q, user)
|
||||
if user:
|
||||
_cover_q = _cover_q.filter(GalleryImage.owner == user)
|
||||
first = _cover_q.order_by(GalleryImage.created_at.desc()).first()
|
||||
if first:
|
||||
cover_url = f"/api/generated-image/{first.filename}"
|
||||
@@ -672,9 +643,10 @@ def setup_gallery_routes() -> APIRouter:
|
||||
base = db.query(GalleryImage).filter(GalleryImage.is_active == True)
|
||||
size_q = db.query(func.sum(GalleryImage.file_size)).filter(GalleryImage.is_active == True)
|
||||
album_q = db.query(GalleryAlbum)
|
||||
base = _owner_filter(base, user)
|
||||
size_q = _owner_filter(size_q, user)
|
||||
album_q = _owner_filter(album_q, user, GalleryAlbum)
|
||||
if user:
|
||||
base = base.filter(GalleryImage.owner == user)
|
||||
size_q = size_q.filter(GalleryImage.owner == user)
|
||||
album_q = album_q.filter(GalleryAlbum.owner == user)
|
||||
total = base.count()
|
||||
total_size = size_q.scalar() or 0
|
||||
fav_count = base.filter(GalleryImage.favorite == True).count()
|
||||
@@ -702,7 +674,8 @@ def setup_gallery_routes() -> APIRouter:
|
||||
GalleryImage.is_active == True,
|
||||
(GalleryImage.ai_tags == None) | (GalleryImage.ai_tags == ""),
|
||||
)
|
||||
q = _owner_filter(q, user)
|
||||
if user:
|
||||
q = q.filter(GalleryImage.owner == user)
|
||||
if album_id:
|
||||
q = q.filter(GalleryImage.album_id == album_id)
|
||||
untagged = q.count()
|
||||
@@ -936,23 +909,15 @@ def setup_gallery_routes() -> APIRouter:
|
||||
raise HTTPException(404, "Image not found")
|
||||
|
||||
img_filename = img.filename
|
||||
# Soft-delete the record first; the DB is the source of truth.
|
||||
# Remove the file from disk
|
||||
img_path = _gallery_image_path(img_filename)
|
||||
if img_path.exists():
|
||||
img_path.unlink()
|
||||
|
||||
# Soft-delete the record
|
||||
img.is_active = False
|
||||
db.commit()
|
||||
|
||||
# Only after the soft-delete commit succeeds do we remove the file.
|
||||
# If the file were deleted first and the commit then failed/rolled
|
||||
# back, the still-active record would point at a missing file.
|
||||
# Best-effort so a missing or locked file can't 500 a delete that
|
||||
# already succeeded logically. Uses the path-confined resolver so a
|
||||
# malformed stored filename can't escape generated_images.
|
||||
try:
|
||||
img_path = _gallery_image_path(img_filename)
|
||||
if img_path.exists():
|
||||
img_path.unlink()
|
||||
except Exception as e:
|
||||
logger.warning(f"Could not remove gallery image file for {img_filename}: {e}")
|
||||
|
||||
# Strip stale chat-history references so the image bubble
|
||||
# (and its prompt caption) doesn't come back after a server
|
||||
# reboot replays the session. We remove the matching tool
|
||||
@@ -1182,7 +1147,10 @@ def setup_gallery_routes() -> APIRouter:
|
||||
if item.get("b64_json"):
|
||||
raw_b64 = item["b64_json"]
|
||||
elif item.get("url"):
|
||||
raw_b64 = await _fetch_result_image_b64(item["url"])
|
||||
async with httpx.AsyncClient(timeout=60) as c2:
|
||||
img_r = await c2.get(item["url"])
|
||||
if img_r.status_code == 200:
|
||||
raw_b64 = base64.b64encode(img_r.content).decode()
|
||||
if not raw_b64:
|
||||
raise HTTPException(502, "OpenAI returned no image")
|
||||
|
||||
@@ -1243,7 +1211,7 @@ def setup_gallery_routes() -> APIRouter:
|
||||
original and regenerates `strength` fraction. With strength ~0.4
|
||||
you get edge blending + lighting unification while keeping the
|
||||
composition recognisable."""
|
||||
import httpx
|
||||
import httpx, base64 as _b64
|
||||
user = require_privilege(request, "can_generate_images")
|
||||
body = await request.json()
|
||||
|
||||
@@ -1419,9 +1387,10 @@ def setup_gallery_routes() -> APIRouter:
|
||||
if item.get("b64_json"):
|
||||
return {"image": item["b64_json"]}
|
||||
if item.get("url"):
|
||||
img_b64 = await _fetch_result_image_b64(item["url"])
|
||||
if img_b64:
|
||||
return {"image": img_b64}
|
||||
async with httpx.AsyncClient(timeout=60) as c2:
|
||||
ir = await c2.get(item["url"])
|
||||
if ir.status_code == 200:
|
||||
return {"image": _b64.b64encode(ir.content).decode()}
|
||||
last_err = f"{path}: server returned no image"
|
||||
except httpx.ConnectError as e:
|
||||
raise HTTPException(502, f"Can't reach diffusion server at {base}: {e}")
|
||||
@@ -1481,7 +1450,6 @@ def setup_gallery_routes() -> APIRouter:
|
||||
img_bytes = base64.b64decode(image_b64)
|
||||
src = Image.open(io.BytesIO(img_bytes)).convert("RGB")
|
||||
try:
|
||||
patch_realesrgan_torchvision_compat()
|
||||
from realesrgan import RealESRGANer
|
||||
except ImportError:
|
||||
return {"error": "realesrgan not installed. Install it from Cookbook → Dependencies (search 'realesrgan')."}
|
||||
@@ -1531,7 +1499,6 @@ def setup_gallery_routes() -> APIRouter:
|
||||
img_bytes = base64.b64decode(image_b64)
|
||||
src = Image.open(io.BytesIO(img_bytes)).convert("RGB")
|
||||
try:
|
||||
patch_realesrgan_torchvision_compat()
|
||||
from basicsr.archs.rrdbnet_arch import RRDBNet
|
||||
from realesrgan import RealESRGANer
|
||||
except ImportError:
|
||||
|
||||
+5
-42
@@ -1,9 +1,7 @@
|
||||
import re
|
||||
from copy import deepcopy
|
||||
|
||||
from fastapi import APIRouter, HTTPException
|
||||
|
||||
from routes._validators import validate_remote_host, validate_ssh_port
|
||||
from fastapi import APIRouter
|
||||
|
||||
|
||||
# Backends the manual hardware simulator accepts. Must stay a subset of what
|
||||
@@ -13,14 +11,6 @@ from routes._validators import validate_remote_host, validate_ssh_port
|
||||
_MANUAL_BACKENDS = {"cuda", "rocm", "metal", "cpu_x86", "cpu_arm"}
|
||||
|
||||
|
||||
def _validate_detection_target(host: str = "", ssh_port: str = "") -> tuple[str, str]:
|
||||
host_value = validate_remote_host(host) or ""
|
||||
port_value = validate_ssh_port(ssh_port) or ""
|
||||
if port_value and not host_value:
|
||||
raise HTTPException(400, "ssh_port requires host")
|
||||
return host_value, port_value
|
||||
|
||||
|
||||
def _apply_manual_hardware(system, manual_mode="", manual_gpu_count="", manual_vram_gb="", manual_ram_gb="", manual_backend=""):
|
||||
"""Manual hardware is a "what if I had this setup" simulator —
|
||||
REPLACES the detected hardware entirely instead of adding to it.
|
||||
@@ -115,11 +105,10 @@ def setup_hwfit_routes():
|
||||
"""Detect and return current system hardware info. Pass host=user@server for remote.
|
||||
fresh=true bypasses the per-host cache (the Rescan button)."""
|
||||
from services.hwfit.hardware import detect_system
|
||||
host, ssh_port = _validate_detection_target(host, ssh_port)
|
||||
return detect_system(host=host, ssh_port=ssh_port, platform=platform, fresh=fresh)
|
||||
|
||||
@router.get("/models")
|
||||
def get_models(use_case: str = "", sort: str = "newest", limit: int = 50, search: str = "", host: str = "", quant: str = "", ctx: str = "", gpu_count: str = "", gpu_group: str = "", ssh_port: str = "", platform: str = "", fresh: bool = False, manual_mode: str = "", manual_gpu_count: str = "", manual_vram_gb: str = "", manual_ram_gb: str = "", manual_backend: str = "", ignore_detected_gpu: bool = False, ignore_detected_ram: bool = False, fit_only: bool = False):
|
||||
def get_models(use_case: str = "", sort: str = "score", limit: int = 50, search: str = "", host: str = "", quant: str = "", ctx: str = "", gpu_count: str = "", gpu_group: str = "", ssh_port: str = "", platform: str = "", fresh: bool = False, manual_mode: str = "", manual_gpu_count: str = "", manual_vram_gb: str = "", manual_ram_gb: str = "", manual_backend: str = "", ignore_detected_gpu: bool = False, ignore_detected_ram: bool = False, fit_only: bool = False):
|
||||
"""Rank LLM models against detected hardware and return scored results.
|
||||
gpu_count: override GPU count (0 = CPU only, 1-N = simulate N GPUs of the
|
||||
active group). gpu_group: index into system.gpu_groups (the homogeneous
|
||||
@@ -129,7 +118,6 @@ def setup_hwfit_routes():
|
||||
from services.hwfit.hardware import detect_system
|
||||
from services.hwfit.fit import rank_models
|
||||
from services.hwfit.models import get_models, model_catalog_path
|
||||
host, ssh_port = _validate_detection_target(host, ssh_port)
|
||||
system = deepcopy(detect_system(host=host, ssh_port=ssh_port, platform=platform, fresh=fresh))
|
||||
if system.get("error"):
|
||||
return {"system": system, "models": [], "error": system["error"]}
|
||||
@@ -177,14 +165,8 @@ def setup_hwfit_routes():
|
||||
system["gpu_name"] = g["name"]
|
||||
system["active_group"] = {**g, "use_count": n}
|
||||
|
||||
# Parse the optional count defensively (matches the gpu_group guard
|
||||
# above): a non-numeric query param previously raised ValueError ->
|
||||
# HTTP 500. A malformed value is ignored, same as omitting it.
|
||||
try:
|
||||
n = int(gpu_count) if gpu_count != "" else None
|
||||
except ValueError:
|
||||
n = None
|
||||
if n is not None:
|
||||
if gpu_count != "":
|
||||
n = int(gpu_count)
|
||||
if n == 0:
|
||||
# RAM-only mode: rank against system memory, offload allowed.
|
||||
system["has_gpu"] = False
|
||||
@@ -214,24 +196,7 @@ def setup_hwfit_routes():
|
||||
if target_context is not None:
|
||||
target_context = max(1024, min(target_context, 1000000))
|
||||
|
||||
rank_kwargs = {
|
||||
"use_case": use_case or None,
|
||||
"limit": limit,
|
||||
"search": search or None,
|
||||
"sort": sort,
|
||||
"quant": quant or None,
|
||||
"fit_only": fit_only,
|
||||
}
|
||||
if target_context is not None:
|
||||
rank_kwargs["target_context"] = target_context
|
||||
try:
|
||||
import inspect
|
||||
supported = set(inspect.signature(rank_models).parameters)
|
||||
rank_kwargs = {k: v for k, v in rank_kwargs.items() if k in supported}
|
||||
except Exception:
|
||||
rank_kwargs.pop("target_context", None)
|
||||
rank_kwargs.pop("fit_only", None)
|
||||
results = rank_models(system, **rank_kwargs)
|
||||
results = rank_models(system, use_case=use_case or None, limit=limit, search=search or None, sort=sort, quant=quant or None, target_context=target_context, fit_only=fit_only)
|
||||
return {"system": system, "models": results}
|
||||
|
||||
@router.get("/profiles")
|
||||
@@ -247,7 +212,6 @@ def setup_hwfit_routes():
|
||||
from services.hwfit.hardware import detect_system
|
||||
from services.hwfit.models import get_models
|
||||
from services.hwfit.profiles import compute_serve_profiles
|
||||
host, ssh_port = _validate_detection_target(host, ssh_port)
|
||||
system = detect_system(host=host, ssh_port=ssh_port, platform=platform, fresh=fresh)
|
||||
if system.get("error"):
|
||||
return {"system": system, "profiles": [], "error": system["error"]}
|
||||
@@ -298,7 +262,6 @@ def setup_hwfit_routes():
|
||||
"""Rank image generation models against detected hardware."""
|
||||
from services.hwfit.hardware import detect_system
|
||||
from services.hwfit.image_models import rank_image_models
|
||||
host, ssh_port = _validate_detection_target(host, ssh_port)
|
||||
system = deepcopy(detect_system(host=host, ssh_port=ssh_port, platform=platform, fresh=fresh))
|
||||
if system.get("error"):
|
||||
return {"system": system, "models": [], "error": system["error"]}
|
||||
|
||||
+6
-18
@@ -108,12 +108,6 @@ def _load_disabled_map():
|
||||
db.close()
|
||||
|
||||
|
||||
def _mcp_oauth_redirect_uri() -> str:
|
||||
"""Shared callback URL for legacy Google and generic MCP OAuth flows."""
|
||||
from src.mcp_oauth import REDIRECT_URI
|
||||
return REDIRECT_URI
|
||||
|
||||
|
||||
def setup_mcp_routes(mcp_manager: McpManager):
|
||||
"""Setup MCP routes with the provided manager."""
|
||||
|
||||
@@ -451,9 +445,9 @@ def setup_mcp_routes(mcp_manager: McpManager):
|
||||
client_id = keys["client_id"]
|
||||
scopes = oauth_cfg.get("scopes", [])
|
||||
|
||||
# For Desktop App creds, default to localhost — the user will
|
||||
# For Desktop App creds, redirect to localhost — the user will
|
||||
# paste the resulting URL back if they're on a different device.
|
||||
redirect_uri = _mcp_oauth_redirect_uri()
|
||||
redirect_uri = "http://localhost:7000/api/mcp/oauth/callback"
|
||||
|
||||
params = {
|
||||
"client_id": client_id,
|
||||
@@ -475,7 +469,7 @@ def setup_mcp_routes(mcp_manager: McpManager):
|
||||
return RedirectResponse(auth_url)
|
||||
else:
|
||||
# Remote device — show paste-back page
|
||||
return HTMLResponse(_oauth_authorize_page(auth_url, server_id, host, redirect_uri))
|
||||
return HTMLResponse(_oauth_authorize_page(auth_url, server_id, host))
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
@@ -542,7 +536,7 @@ def setup_mcp_routes(mcp_manager: McpManager):
|
||||
client_id = keys["client_id"]
|
||||
client_secret = keys["client_secret"]
|
||||
|
||||
redirect_uri = _mcp_oauth_redirect_uri()
|
||||
redirect_uri = "http://localhost:7000/api/mcp/oauth/callback"
|
||||
|
||||
async with httpx.AsyncClient() as client:
|
||||
resp = await client.post(
|
||||
@@ -609,19 +603,13 @@ def setup_mcp_routes(mcp_manager: McpManager):
|
||||
return router
|
||||
|
||||
|
||||
def _oauth_authorize_page(
|
||||
auth_url: str,
|
||||
server_id: str,
|
||||
host: str,
|
||||
redirect_uri: str = "http://localhost:7000/api/mcp/oauth/callback",
|
||||
) -> str:
|
||||
def _oauth_authorize_page(auth_url: str, server_id: str, host: str) -> str:
|
||||
"""Page with Google sign-in link and URL paste-back form for remote access."""
|
||||
# Escape values interpolated into the page: `host` comes from the request
|
||||
# Host header and `server_id` from the OAuth state — neither is trusted.
|
||||
auth_url = html.escape(auth_url, quote=True)
|
||||
server_id = html.escape(server_id, quote=True)
|
||||
host = html.escape(host, quote=True)
|
||||
redirect_uri = html.escape(redirect_uri, quote=True)
|
||||
return f"""<!DOCTYPE html>
|
||||
<html><head>
|
||||
<meta charset="UTF-8"><title>Authorize — Odysseus</title>
|
||||
@@ -666,7 +654,7 @@ def _oauth_authorize_page(
|
||||
<div class="divider"></div>
|
||||
<form method="POST" action="http://{host}/api/mcp/oauth/exchange/{server_id}">
|
||||
<p>Paste the URL from your browser after signing in:</p>
|
||||
<input type="text" name="callback_url" placeholder="{redirect_uri}?code=..." required>
|
||||
<input type="text" name="callback_url" placeholder="http://localhost:7000/api/mcp/oauth/callback?code=..." required>
|
||||
<br><button type="submit">Connect</button>
|
||||
</form>
|
||||
</div></body></html>"""
|
||||
|
||||
+45
-75
@@ -29,7 +29,6 @@ from src.llm_core import llm_call_async
|
||||
from services.memory.memory_extractor import audit_memories
|
||||
from src.auth_helpers import get_current_user, require_user
|
||||
from src.endpoint_resolver import resolve_endpoint
|
||||
from src.task_endpoint import resolve_task_endpoint
|
||||
from src.upload_limits import read_upload_limited, MEMORY_IMPORT_MAX_BYTES
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -106,13 +105,6 @@ def setup_memory_routes(memory_manager: MemoryManager, session_manager: SessionM
|
||||
if memory_manager.find_duplicates(text, user_mem):
|
||||
return {"ok": True, "count": len(user_mem), "message": "Memory already exists"}
|
||||
|
||||
if memory_data.session_id:
|
||||
try:
|
||||
session_obj = session_manager.get_session(memory_data.session_id)
|
||||
except KeyError:
|
||||
raise HTTPException(404, "Session not found")
|
||||
_assert_session_owner(session_obj, user)
|
||||
|
||||
new_entry = memory_manager.add_entry(text, memory_data.source, memory_data.category, owner=user)
|
||||
if memory_data.session_id:
|
||||
new_entry["session_id"] = memory_data.session_id
|
||||
@@ -171,17 +163,8 @@ def setup_memory_routes(memory_manager: MemoryManager, session_manager: SessionM
|
||||
|
||||
session_id = memory.get("session_id")
|
||||
if session_id and session_id in session_manager.sessions:
|
||||
try:
|
||||
session = session_manager.get_session(session_id)
|
||||
if session:
|
||||
_assert_session_owner(session, user)
|
||||
memory["session_name"] = session.name if session else f"Session {session_id[:6]}"
|
||||
except KeyError:
|
||||
memory["session_name"] = "Unknown"
|
||||
except HTTPException as exc:
|
||||
if exc.status_code != 404:
|
||||
raise
|
||||
memory["session_name"] = "Unknown"
|
||||
session = session_manager.get_session(session_id)
|
||||
memory["session_name"] = session.name if session else f"Session {session_id[:6]}"
|
||||
else:
|
||||
memory["session_name"] = "Unknown"
|
||||
|
||||
@@ -241,18 +224,14 @@ def setup_memory_routes(memory_manager: MemoryManager, session_manager: SessionM
|
||||
}
|
||||
messages = [system_msg] + sess.get_context_messages()
|
||||
|
||||
t_url, t_model, t_headers = resolve_task_endpoint(
|
||||
sess.endpoint_url, sess.model, sess.headers, owner=_owner(request)
|
||||
)
|
||||
|
||||
try:
|
||||
suggestion_text = await llm_call_async(
|
||||
t_url,
|
||||
t_model,
|
||||
sess.endpoint_url,
|
||||
sess.model,
|
||||
messages,
|
||||
temperature=0.2,
|
||||
max_tokens=500,
|
||||
headers=t_headers,
|
||||
headers=sess.headers,
|
||||
)
|
||||
try:
|
||||
suggestions = json.loads(suggestion_text)
|
||||
@@ -283,50 +262,42 @@ def setup_memory_routes(memory_manager: MemoryManager, session_manager: SessionM
|
||||
endpoint_url = model = None
|
||||
headers = {}
|
||||
|
||||
# Try utility model from settings first — memory audit is a background
|
||||
# task and should prefer the lighter utility model over the main chat model.
|
||||
from src.task_endpoint import resolve_task_endpoint
|
||||
user = _owner(request)
|
||||
t_url, t_model, t_headers = resolve_task_endpoint(owner=user)
|
||||
if t_url and t_model:
|
||||
endpoint_url, model, headers = t_url, t_model, t_headers
|
||||
else:
|
||||
# Fall back to default model if no task/utility model configured
|
||||
settings = _load_settings()
|
||||
ep_id = settings.get("default_endpoint_id", "")
|
||||
default_model = settings.get("default_model", "")
|
||||
if ep_id:
|
||||
db = SessionLocal()
|
||||
try:
|
||||
ep = db.query(ModelEndpoint).filter(
|
||||
ModelEndpoint.id == ep_id, ModelEndpoint.is_enabled == True
|
||||
).first()
|
||||
if ep:
|
||||
base = _normalize_base(ep.base_url)
|
||||
endpoint_url = build_chat_url(base)
|
||||
model = default_model
|
||||
if not model and ep.models:
|
||||
try:
|
||||
models = _json.loads(ep.models) if isinstance(ep.models, str) else ep.models
|
||||
if models:
|
||||
model = models[0]
|
||||
except Exception:
|
||||
pass
|
||||
if ep.api_key:
|
||||
headers = {"Authorization": f"Bearer {ep.api_key}"}
|
||||
finally:
|
||||
db.close()
|
||||
# Try default model from settings first
|
||||
settings = _load_settings()
|
||||
ep_id = settings.get("default_endpoint_id", "")
|
||||
default_model = settings.get("default_model", "")
|
||||
if ep_id:
|
||||
db = SessionLocal()
|
||||
try:
|
||||
ep = db.query(ModelEndpoint).filter(
|
||||
ModelEndpoint.id == ep_id, ModelEndpoint.is_enabled == True
|
||||
).first()
|
||||
if ep:
|
||||
base = _normalize_base(ep.base_url)
|
||||
endpoint_url = build_chat_url(base)
|
||||
model = default_model
|
||||
if not model and ep.models:
|
||||
try:
|
||||
models = _json.loads(ep.models) if isinstance(ep.models, str) else ep.models
|
||||
if models:
|
||||
model = models[0]
|
||||
except Exception:
|
||||
pass
|
||||
if ep.api_key:
|
||||
headers = {"Authorization": f"Bearer {ep.api_key}"}
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
# Fall back to session model if no default configured
|
||||
if not endpoint_url and session:
|
||||
try:
|
||||
sess = session_manager.get_session(session)
|
||||
_assert_session_owner(sess, _owner(request))
|
||||
endpoint_url = sess.endpoint_url
|
||||
model = sess.model
|
||||
headers = sess.headers
|
||||
except KeyError:
|
||||
pass
|
||||
# Fall back to session model if no default configured
|
||||
if not endpoint_url and session:
|
||||
try:
|
||||
sess = session_manager.get_session(session)
|
||||
_assert_session_owner(sess, _owner(request))
|
||||
endpoint_url = sess.endpoint_url
|
||||
model = sess.model
|
||||
headers = sess.headers
|
||||
except KeyError:
|
||||
pass
|
||||
|
||||
if not endpoint_url or not model:
|
||||
raise HTTPException(400, "No default model configured — set one in Settings")
|
||||
@@ -373,14 +344,13 @@ def setup_memory_routes(memory_manager: MemoryManager, session_manager: SessionM
|
||||
try:
|
||||
sess = session_manager.get_session(session)
|
||||
_assert_session_owner(sess, _owner(request))
|
||||
endpoint_url, model, headers = resolve_task_endpoint(
|
||||
sess.endpoint_url, sess.model, sess.headers, owner=_owner(request)
|
||||
)
|
||||
endpoint_url = sess.endpoint_url
|
||||
model = sess.model
|
||||
headers = sess.headers
|
||||
except KeyError:
|
||||
logger.warning("Session %s not found, falling back to utility endpoint", session)
|
||||
endpoint_url, model, headers = resolve_endpoint("utility", owner=_owner(request))
|
||||
raise HTTPException(404, "Session not found — needed for LLM config")
|
||||
else:
|
||||
endpoint_url, model, headers = resolve_task_endpoint(owner=_owner(request))
|
||||
endpoint_url, model, headers = resolve_endpoint("utility", owner=_owner(request))
|
||||
|
||||
if not endpoint_url or not model:
|
||||
raise HTTPException(400, "No LLM model configured. Set a default model in Settings.")
|
||||
|
||||
+146
-210
@@ -4,8 +4,8 @@ import os
|
||||
import re
|
||||
import uuid
|
||||
import json
|
||||
import hashlib
|
||||
import socket
|
||||
import hashlib
|
||||
import time as _time
|
||||
import logging
|
||||
import httpx
|
||||
@@ -26,7 +26,7 @@ from src.endpoint_resolver import (
|
||||
build_models_url,
|
||||
build_headers,
|
||||
)
|
||||
from src.auth_helpers import _auth_disabled, effective_user, owner_filter
|
||||
from src.auth_helpers import _auth_disabled, owner_filter
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -123,21 +123,6 @@ def _clear_user_pref_endpoint_refs(all_prefs: dict, ep_id: str) -> int:
|
||||
return cleared_users
|
||||
|
||||
|
||||
def _default_endpoint_needs_assignment(current_default_id: str, enabled_endpoint_ids) -> bool:
|
||||
"""Whether the global default chat endpoint should be (re)assigned.
|
||||
|
||||
True when nothing is configured yet, or the configured default no longer
|
||||
resolves to an enabled endpoint (e.g. the user disabled it). Without the
|
||||
second case, adding a new endpoint after disabling the previous default
|
||||
leaves `default_endpoint_id` pointing at the disabled endpoint, so features
|
||||
that read the raw setting (Memory → Tidy) fail with "No default model
|
||||
configured" even though an enabled endpoint exists. See #3586.
|
||||
"""
|
||||
if not current_default_id:
|
||||
return True
|
||||
return current_default_id not in enabled_endpoint_ids
|
||||
|
||||
|
||||
# Loopback hosts a user might type for a local model server (LM Studio,
|
||||
# llama.cpp, vLLM, …). Inside Docker these point at the *container*, not the
|
||||
# host the server actually runs on.
|
||||
@@ -248,9 +233,6 @@ _PROVIDER_CURATED = {
|
||||
"zai-coding": [
|
||||
"glm-5.1", "glm-5v-turbo", "glm-5-turbo", "glm-4.7", "glm-4.5-air",
|
||||
],
|
||||
"kimi-code": [
|
||||
"kimi-for-coding",
|
||||
],
|
||||
"deepseek": [
|
||||
"deepseek-chat", "deepseek-reasoner",
|
||||
],
|
||||
@@ -301,9 +283,11 @@ _HOST_TO_CURATED = (
|
||||
("fireworks.ai", "fireworks"),
|
||||
("googleapis.com", "google"),
|
||||
("x.ai", "xai"),
|
||||
("nvidia.com", "nvidia"),
|
||||
|
||||
("openrouter.ai", "openrouter"),
|
||||
("ollama.com", "ollama"),
|
||||
("opencode.ai/zen/go", "opencode-go"),
|
||||
("opencode.ai/zen", "opencode-zen"),
|
||||
)
|
||||
|
||||
|
||||
@@ -318,8 +302,6 @@ def _match_provider_curated(base_url: str, provider: str) -> str:
|
||||
parsed = urlparse(base_url)
|
||||
if _host_match(base_url, "z.ai") and "/api/coding" in (parsed.path or ""):
|
||||
return "zai-coding"
|
||||
if _host_match(base_url, "kimi.com") and "/coding" in (parsed.path or ""):
|
||||
return "kimi-code"
|
||||
for domain, key in _HOST_TO_CURATED:
|
||||
if _host_match(base_url, domain):
|
||||
return key
|
||||
@@ -498,17 +480,10 @@ _NON_CHAT_PREFIXES = (
|
||||
"dall-e", "tts-", "whisper", "text-embedding", "embedding",
|
||||
"davinci", "babbage", "moderation", "omni-moderation",
|
||||
"sora", "gpt-image", "chatgpt-image",
|
||||
# embedding / retrieval / non-chat models (common across providers)
|
||||
"snowflake/arctic-embed", "nvidia/nv-embed", "embed",
|
||||
)
|
||||
_NON_CHAT_CONTAINS = (
|
||||
"-realtime", "-transcribe", "-tts", "-codex",
|
||||
"codex-", "content-safety", "-safety", "-reward", "nvclip",
|
||||
"kosmos", "fuyu", "deplot", "vila", "neva",
|
||||
"gliner", "riva", "-parse", "-embedqa", "-nemoretriever",
|
||||
"topic-control", "calibration",
|
||||
"ai-synthetic-video", "cosmos-reason2",
|
||||
"bge", "llama-guard",
|
||||
"codex-",
|
||||
)
|
||||
_NON_CHAT_EXACT_PREFIXES = (
|
||||
"gpt-audio", # gpt-audio, gpt-audio-mini etc. (not gpt-4o-audio-preview which is chat)
|
||||
@@ -519,6 +494,8 @@ _NON_CHAT_EXACT_PREFIXES = (
|
||||
def _is_chat_model(model_id: str) -> bool:
|
||||
"""Return True if the model ID looks like a chat/completions-capable model."""
|
||||
mid = model_id.lower()
|
||||
if mid in {"gpt-5.1-codex"}:
|
||||
return True
|
||||
for prefix in _NON_CHAT_PREFIXES:
|
||||
if mid.startswith(prefix):
|
||||
return False
|
||||
@@ -532,7 +509,15 @@ def _is_chat_model(model_id: str) -> bool:
|
||||
|
||||
|
||||
def _delete_orphaned_provider_auth(db, auth_id: Optional[str], exclude_ep_id: Optional[str] = None) -> bool:
|
||||
"""Delete a ProviderAuthSession once no endpoint still references it."""
|
||||
"""Delete a ProviderAuthSession once no endpoint still references it.
|
||||
|
||||
Subscription providers (e.g. ChatGPT Subscription) keep their refresh token
|
||||
in ProviderAuthSession rather than ModelEndpoint.api_key. When the last
|
||||
endpoint backed by that auth row is removed, the stored credentials should
|
||||
be cleared instead of lingering. Returns True if a row was deleted.
|
||||
``exclude_ep_id`` drops the endpoint currently being deleted from the
|
||||
reference count so it does not keep its own auth alive.
|
||||
"""
|
||||
if not auth_id:
|
||||
return False
|
||||
from core.database import ProviderAuthSession
|
||||
@@ -549,52 +534,40 @@ def _delete_orphaned_provider_auth(db, auth_id: Optional[str], exclude_ep_id: Op
|
||||
return True
|
||||
|
||||
|
||||
def _safe_detect_provider(base_url: str) -> str:
|
||||
"""Best-effort provider detection that must not break endpoint probing."""
|
||||
try:
|
||||
return _detect_provider(base_url)
|
||||
except Exception as exc:
|
||||
logger.debug("Provider detection failed for %s: %s", base_url, exc)
|
||||
return ""
|
||||
|
||||
|
||||
def _safe_build_models_url(base_url: str) -> str:
|
||||
"""Build a /models URL without letting optional provider imports break probes."""
|
||||
try:
|
||||
return build_models_url(base_url)
|
||||
except Exception as exc:
|
||||
logger.debug("Model URL detection failed for %s: %s", base_url, exc)
|
||||
return f"{(base_url or '').rstrip('/')}/models"
|
||||
|
||||
|
||||
def _safe_build_headers(api_key: Optional[str], base_url: str) -> dict:
|
||||
"""Build auth headers without letting optional provider imports break probes."""
|
||||
try:
|
||||
return build_headers(api_key, base_url)
|
||||
except Exception as exc:
|
||||
logger.debug("Header detection failed for %s: %s", base_url, exc)
|
||||
return {"Authorization": f"Bearer {api_key}"} if api_key else {}
|
||||
|
||||
|
||||
def _is_discovery_only_provider(provider: str) -> bool:
|
||||
"""Provider that only supports model discovery, not live probing.
|
||||
|
||||
ChatGPT Subscription speaks the Responses/Codex API and has no
|
||||
chat-completions or general health endpoint, so completion probes and
|
||||
reachability pings are skipped — status is derived from cached models.
|
||||
"""
|
||||
return provider == "chatgpt-subscription"
|
||||
|
||||
|
||||
def _resolve_probe_key(ep) -> Optional[str]:
|
||||
"""API key/bearer to probe an endpoint with."""
|
||||
"""API key/bearer to probe an endpoint with.
|
||||
|
||||
Delegates to ``resolve_endpoint_runtime``, which already returns the static
|
||||
``ModelEndpoint.api_key`` for keyed endpoints and resolves (and refreshes)
|
||||
the runtime bearer for session-backed providers (e.g. ChatGPT Subscription).
|
||||
Returns None if resolution fails (e.g. re-auth required) so probing skips
|
||||
rather than raising. Reads only already-loaded scalar attributes of ``ep``.
|
||||
"""
|
||||
try:
|
||||
from src.endpoint_resolver import resolve_endpoint_runtime
|
||||
_base, key = resolve_endpoint_runtime(ep, owner=getattr(ep, "owner", None))
|
||||
return key
|
||||
except Exception as exc:
|
||||
logger.warning("Probe key resolution failed for %s: %s", getattr(ep, "id", "?"), exc)
|
||||
except Exception as e:
|
||||
logger.warning("Probe key resolution failed for %s: %s", getattr(ep, "id", "?"), e)
|
||||
return None
|
||||
|
||||
|
||||
def _probe_single_model(base: str, api_key: str, model_id: str, timeout: int = 10, with_tools: bool = False) -> dict:
|
||||
def _probe_single_model(base: str, api_key: Optional[str], model_id: str, timeout: int = 10, with_tools: bool = False) -> dict:
|
||||
"""Send a realistic completion request to a single model. Returns {status, latency_ms, error?}."""
|
||||
provider = _safe_detect_provider(base)
|
||||
provider = _detect_provider(base)
|
||||
if _is_discovery_only_provider(provider):
|
||||
# Responses/Codex API, not chat-completions: a completion probe would
|
||||
# 400 and the re-probe flow would then hide every model. Discovery-only.
|
||||
return {"status": "ok", "latency_ms": 0, "skipped": True}
|
||||
messages = [
|
||||
{"role": "system", "content": "You are a helpful assistant."},
|
||||
@@ -614,12 +587,12 @@ def _probe_single_model(base: str, api_key: str, model_id: str, timeout: int = 1
|
||||
elif provider == "ollama":
|
||||
from src.llm_core import _build_ollama_payload
|
||||
target_url = build_chat_url(base)
|
||||
h = _safe_build_headers(api_key, base)
|
||||
h = build_headers(api_key, base)
|
||||
h["Content-Type"] = "application/json"
|
||||
payload = _build_ollama_payload(model_id, messages, 0.0, 5, stream=False, tools=_test_tools)
|
||||
else:
|
||||
target_url = build_chat_url(base)
|
||||
h = _safe_build_headers(api_key, base)
|
||||
h = build_headers(api_key, base)
|
||||
h["Content-Type"] = "application/json"
|
||||
from src.llm_core import _uses_max_completion_tokens, _restricts_temperature
|
||||
_max_key = "max_completion_tokens" if _uses_max_completion_tokens(model_id) else "max_tokens"
|
||||
@@ -708,17 +681,15 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
|
||||
"""Probe a base URL's /models endpoint and return list of model IDs.
|
||||
For Anthropic, queries their /v1/models API, falling back to hardcoded list."""
|
||||
from src.endpoint_resolver import resolve_url
|
||||
from src.llm_core import httpx_get_kimi_aware
|
||||
base = resolve_url(_normalize_base(base_url))
|
||||
provider = _safe_detect_provider(base)
|
||||
if provider == "chatgpt-subscription":
|
||||
if _detect_provider(base) == "chatgpt-subscription":
|
||||
from src.chatgpt_subscription import fetch_available_models
|
||||
if api_key:
|
||||
return fetch_available_models(api_key, timeout=timeout)
|
||||
return []
|
||||
if provider == "anthropic":
|
||||
if _detect_provider(base) == "anthropic":
|
||||
# Try Anthropic's /v1/models endpoint first
|
||||
url = _safe_build_models_url(base)
|
||||
url = build_models_url(base)
|
||||
headers = {"anthropic-version": "2023-06-01"}
|
||||
if api_key:
|
||||
headers["x-api-key"] = api_key
|
||||
@@ -741,10 +712,14 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
|
||||
return []
|
||||
logger.warning(f"Anthropic /v1/models failed, using hardcoded list: {e}")
|
||||
return list(ANTHROPIC_MODELS)
|
||||
url = _safe_build_models_url(base)
|
||||
headers = _safe_build_headers(api_key, base)
|
||||
url = build_models_url(base)
|
||||
if not url:
|
||||
curated_key = _match_provider_curated(base, None)
|
||||
fallback = _PROVIDER_CURATED.get(curated_key) if curated_key else None
|
||||
return list(fallback or [])
|
||||
headers = build_headers(api_key, base)
|
||||
try:
|
||||
r = httpx_get_kimi_aware(url, headers, timeout=timeout, verify=llm_verify())
|
||||
r = httpx.get(url, headers=headers, timeout=timeout, verify=llm_verify())
|
||||
r.raise_for_status()
|
||||
data = r.json()
|
||||
# OpenAI format: {"data": [{"id": "model-name"}]}
|
||||
@@ -760,12 +735,7 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
|
||||
for _e in _PROVIDER_CURATED.get(_ck, []):
|
||||
if _e not in set(models) and not any(m.startswith(_e) for m in models):
|
||||
models.append(_e)
|
||||
if _host_match(base, "kimi.com") and "/coding" in (urlparse(base).path or ""):
|
||||
_ck = _match_provider_curated(base, None)
|
||||
for _e in _PROVIDER_CURATED.get(_ck, []):
|
||||
if _e not in set(models) and not any(m.startswith(_e) for m in models):
|
||||
models.append(_e)
|
||||
return [m for m in models if _is_chat_model(m)]
|
||||
return models
|
||||
except httpx.HTTPStatusError as e:
|
||||
if api_key:
|
||||
status = e.response.status_code if e.response is not None else "unknown"
|
||||
@@ -789,7 +759,7 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
|
||||
data = r.json()
|
||||
models = [m.get("name") or m.get("model") for m in (data.get("models") or []) if m.get("name") or m.get("model")]
|
||||
if models:
|
||||
return [m for m in models if _is_chat_model(m)]
|
||||
return models
|
||||
except Exception as e:
|
||||
logger.debug(f"Ollama /api/tags probe failed for {base}: {e}")
|
||||
# Fall back to curated list if the provider has a URL-based match (e.g. z.ai has no /models endpoint)
|
||||
@@ -800,12 +770,11 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
|
||||
return list(fallback)
|
||||
return []
|
||||
|
||||
|
||||
def _ping_endpoint(base_url: str, api_key: str = None, timeout: float = 1.5) -> Dict[str, Any]:
|
||||
"""Reachability probe that does not require installed/listed models."""
|
||||
from src.endpoint_resolver import resolve_url
|
||||
base = resolve_url(_normalize_base(base_url))
|
||||
headers = _safe_build_headers(api_key, base)
|
||||
headers = build_headers(api_key, base)
|
||||
|
||||
# Ollama exposes /v1/models (OpenAI-compatible) AND native /api/version,
|
||||
# /api/tags. Probe native paths for Ollama-style endpoints, but avoid using
|
||||
@@ -816,6 +785,10 @@ def _ping_endpoint(base_url: str, api_key: str = None, timeout: float = 1.5) ->
|
||||
or "ollama" in (parsed_base.hostname or "").lower()
|
||||
)
|
||||
|
||||
# APFEL-specific detection
|
||||
host = (parsed_base.hostname or "").lower()
|
||||
looks_like_apfel = "apfel" in host or parsed_base.port == 11435
|
||||
|
||||
def _result_from_response(r) -> Dict[str, Any]:
|
||||
if 300 <= r.status_code < 400:
|
||||
loc = r.headers.get("location", "")
|
||||
@@ -837,7 +810,23 @@ def _ping_endpoint(base_url: str, api_key: str = None, timeout: float = 1.5) ->
|
||||
last_error: Optional[str] = None
|
||||
|
||||
try:
|
||||
if looks_like_ollama:
|
||||
# APFEL does not behave like Ollama; use its health endpoint.
|
||||
if looks_like_apfel:
|
||||
root = base
|
||||
for suffix in ("/v1", "/api"):
|
||||
if root.endswith(suffix):
|
||||
root = root[: -len(suffix)].rstrip("/")
|
||||
break
|
||||
try:
|
||||
r = httpx.get(root + "/health", timeout=timeout, verify=llm_verify())
|
||||
result = _result_from_response(r)
|
||||
if result["reachable"]:
|
||||
return result
|
||||
last_error = result.get("error")
|
||||
except Exception as e:
|
||||
last_error = str(e)[:120]
|
||||
|
||||
elif looks_like_ollama:
|
||||
root = base
|
||||
for suffix in ("/v1", "/api"):
|
||||
if root.endswith(suffix):
|
||||
@@ -858,11 +847,17 @@ def _ping_endpoint(base_url: str, api_key: str = None, timeout: float = 1.5) ->
|
||||
try:
|
||||
r = httpx.get(base, headers=headers, timeout=timeout, verify=llm_verify())
|
||||
result = _result_from_response(r)
|
||||
if result["reachable"]:
|
||||
return result
|
||||
sc = result.get("status_code") or 0
|
||||
if 400 <= sc < 500 and sc not in (401, 403):
|
||||
models_url = _safe_build_models_url(base)
|
||||
# If the bare base URL returns a non-auth 4xx (e.g. 404), try /models
|
||||
# as a fallback. OpenAI-compatible servers like llama-swap return 404
|
||||
# on the base /v1 prefix but 200 on /v1/models. Auth failures (401/403)
|
||||
# are definitive — probing /models would just repeat the same rejection.
|
||||
if (
|
||||
not result["reachable"]
|
||||
and result.get("status_code") is not None
|
||||
and 400 <= result["status_code"] < 500
|
||||
and result["status_code"] not in (401, 403)
|
||||
):
|
||||
models_url = build_models_url(base)
|
||||
try:
|
||||
r2 = httpx.get(models_url, headers=headers, timeout=timeout, verify=llm_verify())
|
||||
result2 = _result_from_response(r2)
|
||||
@@ -870,63 +865,22 @@ def _ping_endpoint(base_url: str, api_key: str = None, timeout: float = 1.5) ->
|
||||
return result2
|
||||
except Exception:
|
||||
pass
|
||||
if sc:
|
||||
return result
|
||||
last_error = result.get("error") or last_error
|
||||
return result
|
||||
except Exception as e:
|
||||
last_error = str(e)[:120]
|
||||
|
||||
return {"reachable": False, "status_code": None, "error": last_error}
|
||||
|
||||
|
||||
|
||||
def _model_endpoint_error_message(base_url: str, ping: Dict[str, Any] = None) -> str:
|
||||
"""Return a provider-aware error message for failed endpoint probes.
|
||||
|
||||
Surfaces the URL we actually probed and, when the endpoint looks like
|
||||
LM Studio (port 1234 or hostname match), adds a hint about loading a
|
||||
model and confirming the Developer Server is running. The user previously
|
||||
saw a generic "No models found for that provider/key" with no way to
|
||||
tell whether the URL was wrong, the server was down, or the server was
|
||||
reachable but had no model loaded (issue #25).
|
||||
"""
|
||||
"""Return a provider-aware error message for failed endpoint probes."""
|
||||
ping = ping or {}
|
||||
error = ping.get("error")
|
||||
from src.endpoint_resolver import build_models_url
|
||||
try:
|
||||
probed = build_models_url(base_url) or base_url
|
||||
except Exception:
|
||||
probed = base_url
|
||||
parsed = urlparse(base_url)
|
||||
host = (parsed.hostname or "").lower()
|
||||
is_ollama = parsed.port == 11434 or "ollama" in host or "ollama" in base_url.lower()
|
||||
is_lmstudio = (
|
||||
parsed.port == 1234
|
||||
or "lmstudio" in host
|
||||
or "lm-studio" in host
|
||||
or "lm_studio" in host
|
||||
)
|
||||
|
||||
if is_lmstudio:
|
||||
parts = [
|
||||
"LM Studio is reachable, but no models were reported.",
|
||||
f"Probed {probed}.",
|
||||
]
|
||||
if error:
|
||||
parts.append(f"Last probe error: {error}.")
|
||||
parts.append(
|
||||
"Open LM Studio, load at least one model, and confirm the "
|
||||
"Developer Server is running on port 1234."
|
||||
)
|
||||
parts.append(
|
||||
"Base URL should be http://localhost:1234/v1 (native) or "
|
||||
"http://host.docker.internal:1234/v1 (Docker)."
|
||||
)
|
||||
return " ".join(parts)
|
||||
|
||||
if is_ollama:
|
||||
parts = ["No Ollama models found for that endpoint."]
|
||||
parts.append(f"Probed {probed}.")
|
||||
if error:
|
||||
parts.append(f"Last probe error: {error}.")
|
||||
parts.append("Check that Ollama is running and that the base URL is correct.")
|
||||
@@ -936,9 +890,9 @@ def _model_endpoint_error_message(base_url: str, ping: Dict[str, Any] = None) ->
|
||||
return " ".join(parts)
|
||||
|
||||
if error:
|
||||
return f"No models found for that provider/key. Probed {probed}. Last probe error: {error}."
|
||||
return f"No models found for that provider/key. Last probe error: {error}."
|
||||
|
||||
return f"No models found for that provider/key. Probed {probed}."
|
||||
return "No models found for that provider/key."
|
||||
|
||||
|
||||
def _normalize_model_ids(value):
|
||||
@@ -1114,6 +1068,17 @@ def setup_model_routes(model_discovery):
|
||||
ok, info = _should_refresh_endpoint(ep, now, force=force)
|
||||
if not ok:
|
||||
continue
|
||||
if getattr(ep, "provider_auth_id", None):
|
||||
try:
|
||||
from src.endpoint_resolver import resolve_endpoint_runtime
|
||||
info["base"], info["api_key"] = resolve_endpoint_runtime(
|
||||
ep,
|
||||
owner=getattr(ep, "owner", None),
|
||||
)
|
||||
info["key"] = _refresh_key(info["base"], info["api_key"])
|
||||
except Exception as e:
|
||||
logger.warning("Skipping model refresh for %s: could not resolve provider auth: %s", getattr(ep, "name", ep.id), e)
|
||||
continue
|
||||
groups.setdefault(info["key"], {
|
||||
"base": info["base"],
|
||||
"api_key": info["api_key"],
|
||||
@@ -1191,7 +1156,7 @@ def setup_model_routes(model_discovery):
|
||||
|
||||
for ep in endpoints:
|
||||
base = _normalize_base(ep.base_url)
|
||||
provider = _safe_detect_provider(base)
|
||||
provider = _detect_provider(base)
|
||||
# Merge cached + pinned models, then filter out hidden ones
|
||||
ep_model_type = getattr(ep, "model_type", None) or "llm"
|
||||
model_ids = _visible_models(
|
||||
@@ -1255,24 +1220,21 @@ def setup_model_routes(model_discovery):
|
||||
# Require auth; "" is the unconfigured single-user mode, treated as
|
||||
# "see everything" by _fetch_models.
|
||||
try:
|
||||
if getattr(request.state, "api_token", False):
|
||||
scopes = set(getattr(request.state, "api_token_scopes", []) or [])
|
||||
if "chat" not in scopes:
|
||||
raise HTTPException(403, "API token is not scoped for chat")
|
||||
if not getattr(request.state, "api_token_owner", None):
|
||||
raise HTTPException(403, "API token has no owner")
|
||||
owner = effective_user(request) or ""
|
||||
|
||||
# Reject anonymous in configured deployments — no leaking the model
|
||||
# list to unauthenticated callers.
|
||||
from src.auth_helpers import get_current_user as _gcu
|
||||
owner = _gcu(request) or ""
|
||||
except Exception:
|
||||
owner = ""
|
||||
# Reject anonymous in configured deployments — no leaking the model
|
||||
# list to unauthenticated callers.
|
||||
try:
|
||||
auth_mgr = getattr(request.app.state, "auth_manager", None)
|
||||
if not owner and not _auth_disabled() and auth_mgr is not None and getattr(auth_mgr, "is_configured", False):
|
||||
raise HTTPException(401, "Not authenticated")
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error("Auth gate error in GET /api/models, failing closed: %s", e)
|
||||
raise HTTPException(status_code=500, detail="Internal error")
|
||||
logger.error('Auth gate error in GET /api/models, failing closed: %s', e)
|
||||
raise HTTPException(status_code=500, detail='Internal error')
|
||||
# Admins see every endpoint (they manage the global pool); regular
|
||||
# users get the owner-scoped view.
|
||||
_is_admin = False
|
||||
@@ -1336,14 +1298,7 @@ def setup_model_routes(model_discovery):
|
||||
t0 = _time.time()
|
||||
try:
|
||||
import asyncio as _asyncio
|
||||
# Bumped 1.5s → 3.5s. The previous 1.5s budget was clipping
|
||||
# local vLLM endpoints on Tailscale links where the model
|
||||
# server is still loading (Qwen3.5-122B takes 2–3 min to
|
||||
# warm); /v1/models can take 500–2500 ms on a busy box,
|
||||
# which pushed _ping_endpoint's full path-discovery sweep
|
||||
# past the cap and marked the row offline despite the
|
||||
# user actively chatting with it.
|
||||
ping = await _asyncio.to_thread(_ping_endpoint, data["base"], data.get("api_key"), 3.5)
|
||||
ping = await _asyncio.to_thread(_ping_endpoint, data["base"], data.get("api_key"), 1.5)
|
||||
lat = round((_time.time() - t0) * 1000)
|
||||
return {
|
||||
"alive": bool(ping.get("reachable")),
|
||||
@@ -1381,7 +1336,7 @@ def setup_model_routes(model_discovery):
|
||||
results = []
|
||||
for ep in endpoints:
|
||||
base = _normalize_base(ep.base_url)
|
||||
provider = _safe_detect_provider(base)
|
||||
provider = _detect_provider(base)
|
||||
kind = _effective_endpoint_kind(ep, base)
|
||||
cached_count = len(_cached_model_ids(ep))
|
||||
entry = {
|
||||
@@ -1393,12 +1348,20 @@ def setup_model_routes(model_discovery):
|
||||
"endpoint_kind": kind,
|
||||
}
|
||||
try:
|
||||
t0 = _time.time()
|
||||
ping = _ping_endpoint(base, ep.api_key, timeout=1.5)
|
||||
entry["latency_ms"] = round((_time.time() - t0) * 1000)
|
||||
entry["status"] = "online" if ping.get("reachable") or cached_count else "offline"
|
||||
entry["error"] = ping.get("error")
|
||||
entry["model_count"] = cached_count or (len(ANTHROPIC_MODELS) if provider == "anthropic" else 0)
|
||||
if _is_discovery_only_provider(provider):
|
||||
# No general health endpoint — an unauthenticated GET just
|
||||
# 401s. Report status from cached models instead of pinging.
|
||||
entry["latency_ms"] = None
|
||||
entry["status"] = "online" if cached_count else "offline"
|
||||
entry["error"] = None
|
||||
entry["model_count"] = cached_count
|
||||
else:
|
||||
t0 = _time.time()
|
||||
ping = _ping_endpoint(base, ep.api_key, timeout=1.5)
|
||||
entry["latency_ms"] = round((_time.time() - t0) * 1000)
|
||||
entry["status"] = "online" if ping.get("reachable") or cached_count else "offline"
|
||||
entry["error"] = ping.get("error")
|
||||
entry["model_count"] = cached_count or (len(ANTHROPIC_MODELS) if provider == "anthropic" else 0)
|
||||
except Exception as e:
|
||||
entry["latency_ms"] = None
|
||||
entry["status"] = "online" if cached_count else "offline"
|
||||
@@ -1431,7 +1394,7 @@ def setup_model_routes(model_discovery):
|
||||
if ep_id and ep_id not in endpoints_cache:
|
||||
ep = db.query(ModelEndpoint).filter(ModelEndpoint.id == ep_id).first()
|
||||
if ep:
|
||||
endpoints_cache[ep_id] = {"base_url": ep.base_url, "api_key": ep.api_key}
|
||||
endpoints_cache[ep_id] = {"base_url": ep.base_url, "api_key": _resolve_probe_key(ep)}
|
||||
ep_data = endpoints_cache.get(ep_id)
|
||||
if not ep_data:
|
||||
# Try to find by base_url from the model's endpoint field
|
||||
@@ -1470,7 +1433,7 @@ def setup_model_routes(model_discovery):
|
||||
"id": ep.id,
|
||||
"name": ep.name,
|
||||
"base_url": ep.base_url,
|
||||
"api_key": ep.api_key,
|
||||
"api_key": _resolve_probe_key(ep),
|
||||
})
|
||||
finally:
|
||||
db.close()
|
||||
@@ -1559,37 +1522,14 @@ def setup_model_routes(model_discovery):
|
||||
# Endpoint counts as reachable if it has any model — including
|
||||
# admin-pinned IDs that a probe would never surface.
|
||||
status = "online" if (all_models or pinned) else "offline"
|
||||
base = _normalize_base(r.base_url)
|
||||
ping = None
|
||||
# When cached_models is empty, do a quick reachability probe.
|
||||
# Bumped 1.0s → 3.5s because the user reported endpoints they
|
||||
# were ACTIVELY chatting with showed "offline" — the previous
|
||||
# 1s timeout was clipping live cloud endpoints (DeepSeek can
|
||||
# take 1.5–2.5s on /v1/models when their region is under load,
|
||||
# vLLM on a remote GPU box behind SSH can also push past 1s).
|
||||
# 3.5s still keeps the picker render snappy in the common
|
||||
# "everything's already cached" path because this branch only
|
||||
# runs for endpoints with an empty cached_models.
|
||||
if not all_models and not pinned and r.is_enabled:
|
||||
ping = _ping_endpoint(r.base_url, r.api_key, timeout=3.5)
|
||||
# Discovery-only providers have no health endpoint — an
|
||||
# unauthenticated ping just 401s, so don't bother.
|
||||
if not all_models and not pinned and r.is_enabled and not _is_discovery_only_provider(_detect_provider(base)):
|
||||
ping = _ping_endpoint(r.base_url, r.api_key, timeout=1.0)
|
||||
if ping.get("reachable"):
|
||||
status = "empty"
|
||||
# Best-effort: if the probe came back reachable, try
|
||||
# to populate cached_models in the background so the
|
||||
# NEXT picker load shows "online" instead of "empty".
|
||||
# Failure here is silent — we already returned the
|
||||
# "empty" status, and the existing background refresh
|
||||
# path will eventually fill it in too.
|
||||
try:
|
||||
probed = _probe_endpoint(r.base_url, r.api_key, timeout=5)
|
||||
if probed:
|
||||
r.cached_models = json.dumps(probed)
|
||||
db.commit()
|
||||
all_models = probed
|
||||
visible = _visible_models(all_models, r.hidden_models, pinned)
|
||||
status = "online"
|
||||
except Exception as _refill_err:
|
||||
logger.debug(f"opportunistic cached_models refill failed for {r.id}: {_refill_err!r}")
|
||||
base = _normalize_base(r.base_url)
|
||||
kind = _effective_endpoint_kind(r, base)
|
||||
results.append({
|
||||
"id": r.id,
|
||||
@@ -1663,10 +1603,11 @@ def setup_model_routes(model_discovery):
|
||||
)
|
||||
explicit_timeout = _explicit_model_list_timeout(base_url, requested_kind, refresh_timeout)
|
||||
|
||||
# Dedupe: if an endpoint with the same base_url already exists and
|
||||
# is reachable by the caller (shared or owned by them), return it
|
||||
# instead of creating a duplicate row. Fixes "Scan for Servers"
|
||||
# re-adding manually-added endpoints under their host:port name.
|
||||
# Dedupe: if an endpoint with the same base_url and compatible
|
||||
# credentials already exists and is reachable by the caller (shared or
|
||||
# owned by them), return it instead of creating a duplicate row. Keep
|
||||
# same-url/different-key rows distinct so users can group the same
|
||||
# provider URL under multiple credentials.
|
||||
from src.auth_helpers import get_current_user as _gcu_dedup
|
||||
_caller = _gcu_dedup(request) or None
|
||||
_incoming_api_key = api_key.strip()
|
||||
@@ -1793,19 +1734,12 @@ def setup_model_routes(model_discovery):
|
||||
)
|
||||
db.add(ep)
|
||||
db.commit()
|
||||
# Auto-set as default chat endpoint when none is usable yet — either
|
||||
# nothing is configured, or the configured default points at an
|
||||
# endpoint that is now missing/disabled (#3586). Seed the first CHAT
|
||||
# model (not raw model_ids[0]) so we don't pin the global default to
|
||||
# an embedding/tts/etc. entry a provider happens to list first.
|
||||
# Auto-set as default chat endpoint if none configured yet. Seed
|
||||
# the first CHAT model (not raw model_ids[0]) so we don't pin the
|
||||
# global default to an embedding/tts/etc. entry a provider happens
|
||||
# to list first.
|
||||
settings = _load_settings()
|
||||
enabled_ids = {
|
||||
e.id
|
||||
for e in db.query(ModelEndpoint).filter(
|
||||
ModelEndpoint.is_enabled == True # noqa: E712
|
||||
).all()
|
||||
}
|
||||
if _default_endpoint_needs_assignment(settings.get("default_endpoint_id") or "", enabled_ids):
|
||||
if not settings.get("default_endpoint_id"):
|
||||
from src.endpoint_resolver import _first_chat_model
|
||||
settings["default_endpoint_id"] = ep.id
|
||||
settings["default_model"] = _first_chat_model(model_ids) or ""
|
||||
@@ -1871,7 +1805,7 @@ def setup_model_routes(model_discovery):
|
||||
ep = db.query(ModelEndpoint).filter(ModelEndpoint.id == ep_id).first()
|
||||
if not ep:
|
||||
raise HTTPException(404, "Endpoint not found")
|
||||
ep_data = {"id": ep.id, "name": ep.name, "base_url": ep.base_url, "api_key": ep.api_key}
|
||||
ep_data = {"id": ep.id, "name": ep.name, "base_url": ep.base_url, "api_key": _resolve_probe_key(ep)}
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
@@ -1935,7 +1869,7 @@ def setup_model_routes(model_discovery):
|
||||
category = _classify_endpoint(base, kind)
|
||||
timeout = _manual_refresh_timeout(ep, category, refresh_timeout)
|
||||
try:
|
||||
probed = _probe_endpoint(base, ep.api_key, timeout=timeout)
|
||||
probed = _probe_endpoint(base, _resolve_probe_key(ep), timeout=timeout)
|
||||
except Exception as exc:
|
||||
logger.warning("Manual model refresh failed for endpoint %s at %s: %s", ep_id, base, exc)
|
||||
probed = []
|
||||
@@ -2171,6 +2105,8 @@ def setup_model_routes(model_discovery):
|
||||
"name": ep.name,
|
||||
"model_type": ep.model_type,
|
||||
"base_url": ep.base_url,
|
||||
"has_key": bool(ep.api_key),
|
||||
"api_key_fingerprint": _api_key_fingerprint(ep.api_key),
|
||||
"pinned_models": _normalize_model_ids(getattr(ep, "pinned_models", None)),
|
||||
"endpoint_kind": getattr(ep, "endpoint_kind", None) or "auto",
|
||||
"model_refresh_mode": getattr(ep, "model_refresh_mode", None) or "auto",
|
||||
|
||||
+5
-22
@@ -10,7 +10,7 @@ from fastapi import APIRouter, HTTPException, Request
|
||||
from pydantic import BaseModel
|
||||
|
||||
from core.database import SessionLocal, Note
|
||||
from src.auth_helpers import require_user
|
||||
from src.auth_helpers import get_current_user
|
||||
from src.constants import DATA_DIR
|
||||
from sqlalchemy.orm.attributes import flag_modified
|
||||
|
||||
@@ -208,17 +208,14 @@ async def dispatch_reminder(
|
||||
try:
|
||||
from src.endpoint_resolver import resolve_endpoint
|
||||
from src.llm_core import llm_call_async
|
||||
from src.reminder_personas import synthesis_system_prompt
|
||||
url, model, headers = resolve_endpoint("utility", owner=owner or None)
|
||||
if not url:
|
||||
url, model, headers = resolve_endpoint("default", owner=owner or None)
|
||||
if url and model:
|
||||
persona_id = (settings.get("reminder_llm_persona") or "").strip()
|
||||
sys_prompt = synthesis_system_prompt(persona_id)
|
||||
raw = await llm_call_async(
|
||||
url=url, model=model,
|
||||
messages=[
|
||||
{"role": "system", "content": sys_prompt},
|
||||
{"role": "system", "content": "You are a reminder assistant. Write a single short, warm, motivating sentence (max 25 words) reminding the user about the note below. Do not add greetings, preamble, or hashtags. Output only the sentence."},
|
||||
{"role": "user", "content": f"Title: {title}\n\n{note_body}".strip()},
|
||||
],
|
||||
temperature=0.7, max_tokens=200, headers=headers, timeout=30,
|
||||
@@ -570,16 +567,7 @@ def setup_note_routes(task_scheduler=None):
|
||||
router = APIRouter(prefix="/api/notes", tags=["notes"])
|
||||
|
||||
def _owner(request: Request) -> Optional[str]:
|
||||
# require_user, not bare get_current_user: a request that reaches
|
||||
# these owner-scoped routes with NO identity (auth-middleware
|
||||
# regression, SSRF from a sibling service) must fail closed (401)
|
||||
# when auth is configured — not be treated as the single-user mode
|
||||
# and handed blanket access to every account's notes. The documented
|
||||
# anonymous modes (AUTH_ENABLED=false, LOCALHOST_BYPASS on loopback,
|
||||
# unconfigured first-run) still resolve to None, the single-user
|
||||
# path. fire_reminder below already gated this way; the CRUD routes
|
||||
# did not.
|
||||
return require_user(request) or None
|
||||
return get_current_user(request)
|
||||
|
||||
def _is_admin_or_single_user(request: Request, user: str | None) -> bool:
|
||||
if user == "internal-tool":
|
||||
@@ -814,7 +802,8 @@ def setup_note_routes(task_scheduler=None):
|
||||
Returns {synthesis, email_sent}.
|
||||
"""
|
||||
# Gate against anonymous callers — LLM synthesis can burn tokens.
|
||||
user = require_user(request)
|
||||
from src.auth_helpers import require_user as _ru
|
||||
user = _ru(request)
|
||||
body = await request.json()
|
||||
note_id = str(body.get("note_id") or "").strip()
|
||||
if not note_id:
|
||||
@@ -837,12 +826,6 @@ def setup_note_routes(task_scheduler=None):
|
||||
_override["reminder_webhook_integration_id"] = body["webhook_integration_id"]
|
||||
if body.get("webhook_payload_template"):
|
||||
_override["reminder_webhook_payload_template"] = body["webhook_payload_template"]
|
||||
# Mirror the in-UI AI Synthesis toggle + persona so the test
|
||||
# actually exercises the synthesis path before/without a Save.
|
||||
if "llm_synthesis" in body:
|
||||
_override["reminder_llm_synthesis"] = bool(body["llm_synthesis"])
|
||||
if "llm_persona" in body:
|
||||
_override["reminder_llm_persona"] = str(body["llm_persona"] or "")
|
||||
else:
|
||||
db = SessionLocal()
|
||||
try:
|
||||
|
||||
@@ -160,11 +160,8 @@ def setup_personal_routes(personal_docs_manager, rag_manager, rag_available):
|
||||
JSON response confirming removal
|
||||
"""
|
||||
try:
|
||||
# Confine to PERSONAL_DIR — parity with add_directory_to_rag (which
|
||||
# resolves the path the same way). Without this, an arbitrary or
|
||||
# `..`-escaping path is passed straight to
|
||||
# personal_docs_manager.remove_directory / rag.remove_directory.
|
||||
directory = _resolve_allowed_personal_dir(directory)
|
||||
if not directory:
|
||||
raise HTTPException(400, "Directory path is required")
|
||||
|
||||
logger.info(f"Removing directory from RAG: {directory}")
|
||||
|
||||
@@ -278,8 +275,8 @@ def setup_personal_routes(personal_docs_manager, rag_manager, rag_available):
|
||||
# Delete file from disk if it's in uploads dir
|
||||
deleted_from_disk = False
|
||||
try:
|
||||
abs_target = os.path.realpath(filepath)
|
||||
base_abs = os.path.realpath(UPLOADS_DIR)
|
||||
abs_target = os.path.abspath(filepath)
|
||||
base_abs = os.path.abspath(UPLOADS_DIR)
|
||||
in_uploads = (
|
||||
abs_target == base_abs
|
||||
or os.path.commonpath([abs_target, base_abs]) == base_abs
|
||||
|
||||
+13
-21
@@ -10,9 +10,8 @@ import logging
|
||||
from core.session_manager import SessionManager
|
||||
from core.models import ChatMessage
|
||||
from src.request_models import SessionResponse
|
||||
from core.database import Session as DbSession, SessionLocal, Document, GalleryImage, utcnow_naive
|
||||
from src.auth_helpers import effective_user, _auth_disabled, owner_filter
|
||||
from src.session_actions import is_session_recently_active
|
||||
from core.database import Session as DbSession, SessionLocal, Document, GalleryImage
|
||||
from src.auth_helpers import get_current_user, effective_user, _auth_disabled
|
||||
|
||||
|
||||
def _sanitize_export_filename(name: str) -> str:
|
||||
@@ -258,9 +257,7 @@ def setup_session_routes(session_manager: SessionManager, config: dict, webhook_
|
||||
last_msg_map = {}
|
||||
mode_map = {}
|
||||
msg_count_map = {}
|
||||
q = db.query(DbSession.id, DbSession.folder, DbSession.total_input_tokens, DbSession.total_output_tokens, DbSession.is_important, DbSession.created_at, DbSession.updated_at, DbSession.last_message_at, DbSession.mode, DbSession.message_count).filter(DbSession.archived == False)
|
||||
q = owner_filter(q, DbSession, user)
|
||||
rows = q.all()
|
||||
rows = db.query(DbSession.id, DbSession.folder, DbSession.total_input_tokens, DbSession.total_output_tokens, DbSession.is_important, DbSession.created_at, DbSession.updated_at, DbSession.last_message_at, DbSession.mode, DbSession.message_count).filter(DbSession.archived == False, DbSession.owner == user).all()
|
||||
for row in rows:
|
||||
folder_map[row.id] = row.folder
|
||||
token_map[row.id] = (row.total_input_tokens or 0) + (row.total_output_tokens or 0)
|
||||
@@ -279,19 +276,17 @@ def setup_session_routes(session_manager: SessionManager, config: dict, webhook_
|
||||
# Sessions with active documents that have content
|
||||
from sqlalchemy import func
|
||||
doc_session_ids = set(
|
||||
r[0] for r in owner_filter(
|
||||
db.query(Document.session_id)
|
||||
.filter(Document.is_active == True,
|
||||
Document.current_content != None,
|
||||
func.trim(Document.current_content) != ""),
|
||||
Document, user)
|
||||
r[0] for r in db.query(Document.session_id)
|
||||
.filter(Document.is_active == True,
|
||||
Document.current_content != None,
|
||||
func.trim(Document.current_content) != "",
|
||||
Document.owner == user)
|
||||
.distinct().all()
|
||||
)
|
||||
img_session_ids = set(
|
||||
r[0] for r in owner_filter(
|
||||
db.query(GalleryImage.session_id)
|
||||
.filter(GalleryImage.session_id != None),
|
||||
GalleryImage, user)
|
||||
r[0] for r in db.query(GalleryImage.session_id)
|
||||
.filter(GalleryImage.session_id != None,
|
||||
GalleryImage.owner == user)
|
||||
.distinct().all()
|
||||
)
|
||||
finally:
|
||||
@@ -328,7 +323,7 @@ def setup_session_routes(session_manager: SessionManager, config: dict, webhook_
|
||||
endpoint_id: str = Form(""),
|
||||
):
|
||||
skip_val = str(skip_validation).lower() == "true"
|
||||
user = effective_user(request)
|
||||
user = get_current_user(request)
|
||||
endpoint_api_key = ""
|
||||
endpoint_base_url = ""
|
||||
_reject_raw_endpoint_url_for_non_admin(request, user, endpoint_id, endpoint_url)
|
||||
@@ -477,7 +472,7 @@ def setup_session_routes(session_manager: SessionManager, config: dict, webhook_
|
||||
db.close()
|
||||
# Switch model/endpoint mid-session
|
||||
if model is not None and endpoint_url is not None:
|
||||
user = effective_user(request)
|
||||
user = get_current_user(request)
|
||||
_reject_raw_endpoint_url_for_non_admin(request, user, endpoint_id, endpoint_url)
|
||||
endpoint_api_key = ""
|
||||
endpoint_base_url = ""
|
||||
@@ -1033,7 +1028,6 @@ def setup_session_routes(session_manager: SessionManager, config: dict, webhook_
|
||||
db.query(DbMsg.session_id, _sa_func.count(DbMsg.id))
|
||||
.filter(DbMsg.role == "assistant").group_by(DbMsg.session_id).all()
|
||||
)
|
||||
cleanup_now = utcnow_naive()
|
||||
for row in rows:
|
||||
# Never delete important sessions
|
||||
if getattr(row, 'is_important', False):
|
||||
@@ -1046,8 +1040,6 @@ def setup_session_routes(session_manager: SessionManager, config: dict, webhook_
|
||||
if hasattr(session_manager, 'delete_session'):
|
||||
session_manager.delete_session(row.id)
|
||||
continue
|
||||
if is_session_recently_active(row, now=cleanup_now):
|
||||
continue
|
||||
msg_count = _counts.get(row.id, 0)
|
||||
should_delete = False
|
||||
if msg_count == 0:
|
||||
|
||||
+2
-16
@@ -1,7 +1,6 @@
|
||||
"""Shell routes — user-facing command execution endpoint."""
|
||||
|
||||
import asyncio
|
||||
import importlib
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
@@ -15,7 +14,6 @@ from collections import namedtuple
|
||||
from pathlib import Path
|
||||
from typing import Dict, Any
|
||||
from core.platform_compat import IS_APPLE_SILICON, which_tool
|
||||
from src.optional_deps import prepare_optional_dependency_import
|
||||
|
||||
# POSIX-only: `pty`/`fcntl` transitively import `termios`, which does NOT exist
|
||||
# on Windows, so importing them unconditionally crashed app startup there
|
||||
@@ -151,11 +149,6 @@ def _pip_dist_name(pkg: dict) -> str:
|
||||
return (pkg.get("name") or "").replace("_", "-")
|
||||
|
||||
|
||||
def _import_optional_dependency_for_status(name: str):
|
||||
prepare_optional_dependency_import(name)
|
||||
return importlib.import_module(name)
|
||||
|
||||
|
||||
def _package_installed_from_probe(name: str, probe: dict) -> bool:
|
||||
"""Return whether an optional dependency is usable by Cookbook.
|
||||
|
||||
@@ -977,6 +970,7 @@ def setup_shell_routes() -> APIRouter:
|
||||
"""
|
||||
_require_admin(request)
|
||||
_reject_cross_site(request)
|
||||
import importlib
|
||||
import importlib.metadata as importlib_metadata
|
||||
import shlex
|
||||
import json as _json
|
||||
@@ -1063,13 +1057,6 @@ def setup_shell_routes() -> APIRouter:
|
||||
"category": "Image",
|
||||
"target": "remote",
|
||||
},
|
||||
{
|
||||
"name": "transformers",
|
||||
"pip": "transformers",
|
||||
"desc": "Hugging Face model components used by SD/Flux pipelines and image tools",
|
||||
"category": "Image",
|
||||
"target": "remote",
|
||||
},
|
||||
{
|
||||
"name": "rembg",
|
||||
"pip": "rembg[gpu]",
|
||||
@@ -1215,7 +1202,7 @@ def setup_shell_routes() -> APIRouter:
|
||||
pkg["status_note"] = _package_status_note("vllm", probe)
|
||||
else:
|
||||
try:
|
||||
_import_optional_dependency_for_status(pkg["name"])
|
||||
importlib.import_module(pkg["name"])
|
||||
importlib_metadata.version(_pip_dist_name(pkg))
|
||||
pkg["installed"] = True
|
||||
except ImportError:
|
||||
@@ -1264,7 +1251,6 @@ def setup_shell_routes() -> APIRouter:
|
||||
"sglang[all]",
|
||||
"diffusers",
|
||||
"diffusers[torch]",
|
||||
"transformers",
|
||||
"TTS",
|
||||
"bark",
|
||||
"faster-whisper",
|
||||
|
||||
@@ -691,12 +691,8 @@ async def _run_skill_test_once(md: str, task: str, url, model, headers, owner) -
|
||||
{"role": "user", "content": task},
|
||||
]
|
||||
try:
|
||||
# max_tokens explicitly set: passing 0 lets some upstreams (Ollama,
|
||||
# OpenAI-compat) generate an empty completion, which manifested as
|
||||
# the skill test returning nothing while chat (which carries its
|
||||
# preset's max_tokens) worked. 4096 matches the chat default.
|
||||
async for chunk in stream_agent_loop(url, model, messages, headers=headers,
|
||||
temperature=0.3, max_tokens=4096, max_rounds=8, owner=owner):
|
||||
temperature=0.3, max_tokens=0, max_rounds=8, owner=owner):
|
||||
if not chunk.startswith("data: ") or chunk.strip() == "data: [DONE]":
|
||||
continue
|
||||
try:
|
||||
|
||||
@@ -151,7 +151,6 @@ class TaskCreate(BaseModel):
|
||||
endpoint_url: Optional[str] = None
|
||||
then_task_id: Optional[str] = None # chain: run this task after success
|
||||
notifications_enabled: Optional[bool] = None # None lets action-specific defaults apply
|
||||
character_id: Optional[str] = None # built-in persona id (PERSONAS) — biases output voice
|
||||
|
||||
|
||||
class TaskUpdate(BaseModel):
|
||||
@@ -172,7 +171,6 @@ class TaskUpdate(BaseModel):
|
||||
endpoint_url: Optional[str] = None
|
||||
then_task_id: Optional[str] = None
|
||||
notifications_enabled: Optional[bool] = None
|
||||
character_id: Optional[str] = None
|
||||
|
||||
|
||||
def _display_task_name(t: ScheduledTask) -> str:
|
||||
@@ -205,7 +203,6 @@ def _task_to_dict(t: ScheduledTask, include_last_run_result: bool = False) -> di
|
||||
"output_target": t.output_target,
|
||||
"session_id": t.session_id,
|
||||
"crew_member_id": getattr(t, "crew_member_id", None),
|
||||
"character_id": getattr(t, "character_id", None),
|
||||
"model": t.model,
|
||||
"endpoint_url": t.endpoint_url,
|
||||
"run_count": t.run_count or 0,
|
||||
@@ -522,15 +519,6 @@ def setup_task_routes(task_scheduler) -> APIRouter:
|
||||
else bool(req.notifications_enabled) if req.notifications_enabled is not None
|
||||
else True
|
||||
)
|
||||
# Validate chained task belongs to same owner
|
||||
if req.then_task_id:
|
||||
chain_target = db.query(ScheduledTask).filter(
|
||||
ScheduledTask.id == req.then_task_id
|
||||
).first()
|
||||
if not chain_target:
|
||||
raise HTTPException(400, "Chained task not found")
|
||||
if chain_target.owner != user:
|
||||
raise HTTPException(403, "Cannot chain to another user's task")
|
||||
task = ScheduledTask(
|
||||
id=task_id,
|
||||
owner=user,
|
||||
@@ -555,7 +543,6 @@ def setup_task_routes(task_scheduler) -> APIRouter:
|
||||
then_task_id=then_task_id,
|
||||
webhook_token=webhook_token,
|
||||
notifications_enabled=notifications_enabled,
|
||||
character_id=(req.character_id or None),
|
||||
)
|
||||
db.add(task)
|
||||
db.commit()
|
||||
@@ -709,9 +696,6 @@ def setup_task_routes(task_scheduler) -> APIRouter:
|
||||
task.then_task_id = _validate_then_task_id(db, req.then_task_id, user, current_task_id=task.id)
|
||||
if req.notifications_enabled is not None:
|
||||
task.notifications_enabled = bool(req.notifications_enabled)
|
||||
if req.character_id is not None:
|
||||
# Empty string clears the persona; non-empty stores the id.
|
||||
task.character_id = req.character_id or None
|
||||
if req.cron_expression is not None:
|
||||
if req.cron_expression:
|
||||
try:
|
||||
|
||||
@@ -7,7 +7,7 @@ from fastapi import APIRouter, Request, File, UploadFile, HTTPException
|
||||
from typing import List
|
||||
import logging
|
||||
from core.middleware import require_admin
|
||||
from src.auth_helpers import effective_user
|
||||
from src.auth_helpers import get_current_user
|
||||
from src.upload_handler import count_recent_uploads
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -78,7 +78,7 @@ def setup_upload_routes(upload_handler):
|
||||
|
||||
for u in files:
|
||||
try:
|
||||
meta = upload_handler.save_upload(u, client_ip, owner=effective_user(request))
|
||||
meta = upload_handler.save_upload(u, client_ip, owner=get_current_user(request))
|
||||
out.append({
|
||||
"id": meta["id"],
|
||||
"name": meta["name"],
|
||||
@@ -138,7 +138,7 @@ def setup_upload_routes(upload_handler):
|
||||
original_name = info.get("name", file_id)
|
||||
auth_mgr = getattr(request.app.state, "auth_manager", None)
|
||||
auth_configured = bool(auth_mgr and auth_mgr.is_configured)
|
||||
current_user = effective_user(request)
|
||||
current_user = get_current_user(request)
|
||||
file_owner = info.get("owner") if info else None
|
||||
if auth_configured:
|
||||
if not current_user:
|
||||
@@ -204,7 +204,7 @@ def setup_upload_routes(upload_handler):
|
||||
info = _load_upload_info(file_id)
|
||||
auth_mgr = getattr(request.app.state, "auth_manager", None)
|
||||
auth_configured = bool(auth_mgr and auth_mgr.is_configured)
|
||||
current_user = effective_user(request)
|
||||
current_user = get_current_user(request)
|
||||
file_owner = info.get("owner") if info else None
|
||||
if auth_configured:
|
||||
if not current_user:
|
||||
@@ -247,7 +247,7 @@ def setup_upload_routes(upload_handler):
|
||||
raise HTTPException(404, "File not found")
|
||||
auth_mgr = getattr(request.app.state, "auth_manager", None)
|
||||
auth_configured = bool(auth_mgr and auth_mgr.is_configured)
|
||||
current_user = effective_user(request)
|
||||
current_user = get_current_user(request)
|
||||
file_owner = info.get("owner")
|
||||
if auth_configured:
|
||||
if not current_user:
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
"""Webhook, API Token, and sync chat routes."""
|
||||
|
||||
import asyncio
|
||||
import uuid
|
||||
import logging
|
||||
from typing import Optional
|
||||
@@ -197,8 +198,6 @@ def setup_webhook_routes(
|
||||
"opencode-go": "https://opencode.ai/zen/go/v1",
|
||||
"fireworks": "https://api.fireworks.ai/inference/v1",
|
||||
"venice": "https://api.venice.ai/api/v1",
|
||||
"kimi-code": "https://api.kimi.com/coding/v1",
|
||||
"kimicode": "https://api.kimi.com/coding/v1",
|
||||
}
|
||||
|
||||
# Model prefix → provider mapping for auto-detection
|
||||
@@ -211,8 +210,6 @@ def setup_webhook_routes(
|
||||
"mistral": "mistral",
|
||||
"llama": "groq",
|
||||
"mixtral": "groq",
|
||||
"kimi-for-coding": "kimi-code",
|
||||
"kimi": "kimi-code",
|
||||
}
|
||||
|
||||
def _resolve_base_url(model: Optional[str], provider: Optional[str]) -> Optional[str]:
|
||||
@@ -384,10 +381,10 @@ def setup_webhook_routes(
|
||||
sess.add_message(ChatMessage("assistant", reply))
|
||||
session_manager.save_sessions()
|
||||
|
||||
webhook_manager.fire_and_forget("chat.completed", {
|
||||
asyncio.create_task(webhook_manager.fire("chat.completed", {
|
||||
"session_id": session_id, "model": sess.model,
|
||||
"user_message": message[:2000], "response": reply[:2000],
|
||||
})
|
||||
}))
|
||||
|
||||
return {"response": reply, "session_id": session_id, "model": sess.model}
|
||||
|
||||
|
||||
@@ -1,15 +1,10 @@
|
||||
"""Workspace API - browse server directories to pick a tool workspace folder."""
|
||||
"""Workspace API — browse server directories to pick a tool workspace folder."""
|
||||
import os
|
||||
from fastapi import APIRouter, Request, HTTPException, Query
|
||||
|
||||
from src.auth_helpers import get_current_user
|
||||
from src.tool_security import owner_is_admin_or_single_user
|
||||
|
||||
# Cap entries returned per directory (mirrors filesystem_tools._CODENAV_MAX_HITS).
|
||||
# A huge directory shouldn't dump thousands of rows into the picker; the user can
|
||||
# type/paste a path to jump straight in instead.
|
||||
_MAX_BROWSE_DIRS = 500
|
||||
|
||||
|
||||
def setup_workspace_routes():
|
||||
router = APIRouter(prefix="/api/workspace", tags=["workspace"])
|
||||
@@ -39,7 +34,7 @@ def setup_workspace_routes():
|
||||
with os.scandir(target) as it:
|
||||
for entry in it:
|
||||
try:
|
||||
# Don't follow symlinks when classifying - a symlinked
|
||||
# Don't follow symlinks when classifying — a symlinked
|
||||
# dir is skipped rather than letting the browser wander
|
||||
# off via a link. Hidden entries are omitted.
|
||||
if entry.is_dir(follow_symlinks=False) and not entry.name.startswith("."):
|
||||
@@ -51,35 +46,11 @@ def setup_workspace_routes():
|
||||
except (PermissionError, OSError):
|
||||
dirs = []
|
||||
|
||||
dirs_sorted = sorted(dirs, key=lambda d: d["name"].lower())
|
||||
truncated = len(dirs_sorted) > _MAX_BROWSE_DIRS
|
||||
parent = os.path.dirname(target)
|
||||
from src.tool_execution import vet_workspace
|
||||
return {
|
||||
"path": target,
|
||||
"parent": parent if parent and parent != target else None,
|
||||
"dirs": dirs_sorted[:_MAX_BROWSE_DIRS],
|
||||
"truncated": truncated,
|
||||
# Whether this directory may be bound as a workspace (filesystem
|
||||
# roots and sensitive dirs may be browsed through but not chosen).
|
||||
"selectable": vet_workspace(target) is not None,
|
||||
"dirs": sorted(dirs, key=lambda d: d["name"].lower()),
|
||||
}
|
||||
|
||||
@router.get("/vet")
|
||||
def vet(request: Request, path: str = Query(default="")):
|
||||
"""Validate a workspace path without binding it.
|
||||
|
||||
The UI calls this before persisting a manually typed path (/workspace
|
||||
set) so a typo, file path, deleted folder, sensitive dir, or filesystem
|
||||
root is rejected up front with the canonical path returned on success,
|
||||
instead of being stored client-side and silently dropped at chat time.
|
||||
Admin-gated like /browse: it confirms path existence on the host.
|
||||
"""
|
||||
owner = get_current_user(request)
|
||||
if not owner_is_admin_or_single_user(owner):
|
||||
raise HTTPException(status_code=403, detail="Workspace selection is admin-only")
|
||||
from src.tool_execution import vet_workspace
|
||||
resolved = vet_workspace(path)
|
||||
return {"ok": resolved is not None, "path": resolved}
|
||||
|
||||
return router
|
||||
|
||||
@@ -1,635 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Build a neutral agent migration manifest.
|
||||
|
||||
This helper is intentionally read-only. It does not import the Odysseus
|
||||
application package, write to data/, call an LLM, or apply anything. It turns
|
||||
common agent export shapes into a portable JSON manifest that Odysseus can
|
||||
preview or import later.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import hashlib
|
||||
import json
|
||||
import mimetypes
|
||||
import sys
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any, Iterable
|
||||
|
||||
|
||||
SCHEMA_VERSION = "agent-migration.v1"
|
||||
TEXT_EXTENSIONS = {
|
||||
".cfg",
|
||||
".conf",
|
||||
".csv",
|
||||
".json",
|
||||
".log",
|
||||
".md",
|
||||
".markdown",
|
||||
".py",
|
||||
".rst",
|
||||
".toml",
|
||||
".txt",
|
||||
".yaml",
|
||||
".yml",
|
||||
}
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class InputWarning:
|
||||
path: str
|
||||
message: str
|
||||
|
||||
|
||||
def utc_now_iso() -> str:
|
||||
return datetime.now(timezone.utc).replace(microsecond=0).isoformat().replace("+00:00", "Z")
|
||||
|
||||
|
||||
def sha256_text(text: str) -> str:
|
||||
return hashlib.sha256(text.encode("utf-8")).hexdigest()
|
||||
|
||||
|
||||
def sha256_bytes(data: bytes) -> str:
|
||||
return hashlib.sha256(data).hexdigest()
|
||||
|
||||
|
||||
def sha256_path(path: Path) -> str:
|
||||
h = hashlib.sha256()
|
||||
with path.open("rb") as f:
|
||||
for chunk in iter(lambda: f.read(65536), b""):
|
||||
h.update(chunk)
|
||||
return h.hexdigest()
|
||||
|
||||
|
||||
def stable_id(kind: str, source_name: str, *parts: Any) -> str:
|
||||
raw = "\x1f".join([kind, source_name, *[str(part) for part in parts]])
|
||||
return f"{kind}:{hashlib.sha256(raw.encode('utf-8')).hexdigest()[:16]}"
|
||||
|
||||
|
||||
def read_json(path: Path) -> Any:
|
||||
with path.open("r", encoding="utf-8") as handle:
|
||||
return json.load(handle)
|
||||
|
||||
|
||||
def normalize_category(value: Any) -> str:
|
||||
category = str(value or "fact").strip().lower()
|
||||
return category or "fact"
|
||||
|
||||
|
||||
def normalize_memory_text(item: Any) -> str:
|
||||
if isinstance(item, str):
|
||||
return item.strip()
|
||||
if isinstance(item, dict):
|
||||
for key in ("text", "content", "memory", "value"):
|
||||
value = item.get(key)
|
||||
if isinstance(value, str) and value.strip():
|
||||
return value.strip()
|
||||
return ""
|
||||
|
||||
|
||||
def memory_metadata(item: Any, source_path: Path, index: int) -> dict[str, Any]:
|
||||
metadata: dict[str, Any] = {
|
||||
"source_path": str(source_path),
|
||||
"source_index": index,
|
||||
}
|
||||
if isinstance(item, dict):
|
||||
for key in ("id", "timestamp", "created_at", "updated_at", "source", "tags", "pinned"):
|
||||
if key in item:
|
||||
metadata[f"source_{key}"] = item.get(key)
|
||||
return metadata
|
||||
|
||||
|
||||
def payload_items(payload: Any, keys: tuple[str, ...]) -> Any:
|
||||
if isinstance(payload, dict):
|
||||
for key in keys:
|
||||
if isinstance(payload.get(key), list):
|
||||
return payload[key]
|
||||
return payload
|
||||
|
||||
|
||||
def collect_memory_json(path: Path, source_name: str) -> tuple[list[dict[str, Any]], list[InputWarning]]:
|
||||
warnings: list[InputWarning] = []
|
||||
try:
|
||||
payload = read_json(path)
|
||||
except Exception as exc:
|
||||
return [], [InputWarning(str(path), f"could not read JSON: {exc}")]
|
||||
|
||||
payload = payload_items(payload, ("memories", "memory", "items", "data"))
|
||||
|
||||
if not isinstance(payload, list):
|
||||
return [], [InputWarning(str(path), "expected a JSON list or an object containing a memory list")]
|
||||
|
||||
items: list[dict[str, Any]] = []
|
||||
seen: set[str] = set()
|
||||
for index, item in enumerate(payload):
|
||||
text = normalize_memory_text(item)
|
||||
if not text:
|
||||
warnings.append(InputWarning(str(path), f"skipped memory at index {index}: missing text"))
|
||||
continue
|
||||
digest = sha256_text(text.strip().lower())
|
||||
if digest in seen:
|
||||
warnings.append(InputWarning(str(path), f"skipped duplicate memory at index {index}"))
|
||||
continue
|
||||
seen.add(digest)
|
||||
category = normalize_category(item.get("category") if isinstance(item, dict) else "fact")
|
||||
source = str(item.get("source") or source_name) if isinstance(item, dict) else source_name
|
||||
items.append(
|
||||
{
|
||||
"id": stable_id("memory", source_name, path, index, digest),
|
||||
"kind": "memory",
|
||||
"text": text,
|
||||
"category": category,
|
||||
"source": source,
|
||||
"metadata": memory_metadata(item, path, index),
|
||||
}
|
||||
)
|
||||
return items, warnings
|
||||
|
||||
|
||||
def normalize_timestamp(value: Any) -> str | None:
|
||||
if value is None or value == "":
|
||||
return None
|
||||
if isinstance(value, (int, float)):
|
||||
try:
|
||||
return (
|
||||
datetime.fromtimestamp(float(value), timezone.utc)
|
||||
.replace(microsecond=0)
|
||||
.isoformat()
|
||||
.replace("+00:00", "Z")
|
||||
)
|
||||
except (OverflowError, OSError, ValueError):
|
||||
return str(value)
|
||||
return str(value)
|
||||
|
||||
|
||||
def normalize_role(value: Any) -> str:
|
||||
role = str(value or "unknown").strip().lower()
|
||||
if role in {"human", "user"}:
|
||||
return "user"
|
||||
if role in {"assistant", "ai", "bot", "model"}:
|
||||
return "assistant"
|
||||
if role in {"system", "tool"}:
|
||||
return role
|
||||
return role or "unknown"
|
||||
|
||||
|
||||
def content_part_text(part: Any) -> str:
|
||||
if isinstance(part, str):
|
||||
return part
|
||||
if isinstance(part, dict):
|
||||
for key in ("text", "content", "value"):
|
||||
value = part.get(key)
|
||||
if isinstance(value, str):
|
||||
return value
|
||||
if part.get("type") == "text" and isinstance(part.get("text"), str):
|
||||
return part["text"]
|
||||
return ""
|
||||
|
||||
|
||||
def normalize_message_text(message: dict[str, Any]) -> str:
|
||||
content = message.get("content")
|
||||
if isinstance(content, str):
|
||||
return content
|
||||
if isinstance(content, list):
|
||||
return "\n".join(text for text in (content_part_text(part).strip() for part in content) if text)
|
||||
if isinstance(content, dict):
|
||||
parts = content.get("parts")
|
||||
if isinstance(parts, list):
|
||||
return "\n".join(text for text in (content_part_text(part).strip() for part in parts) if text)
|
||||
for key in ("text", "content", "value"):
|
||||
value = content.get(key)
|
||||
if isinstance(value, str):
|
||||
return value
|
||||
for key in ("text", "body", "message"):
|
||||
value = message.get(key)
|
||||
if isinstance(value, str):
|
||||
return value
|
||||
return ""
|
||||
|
||||
|
||||
def normalize_message(message: dict[str, Any]) -> dict[str, Any] | None:
|
||||
author = message.get("author") if isinstance(message.get("author"), dict) else {}
|
||||
role = (
|
||||
message.get("role")
|
||||
or message.get("sender")
|
||||
or message.get("speaker")
|
||||
or author.get("role")
|
||||
or author.get("name")
|
||||
)
|
||||
text = normalize_message_text(message).strip()
|
||||
if not text:
|
||||
return None
|
||||
normalized: dict[str, Any] = {
|
||||
"role": normalize_role(role),
|
||||
"text": text,
|
||||
}
|
||||
timestamp = normalize_timestamp(message.get("created_at") or message.get("create_time") or message.get("timestamp"))
|
||||
if timestamp:
|
||||
normalized["created_at"] = timestamp
|
||||
message_id = message.get("id")
|
||||
if message_id is not None:
|
||||
normalized["source_id"] = str(message_id)
|
||||
return normalized
|
||||
|
||||
|
||||
def chatgpt_mapping_messages(conversation: dict[str, Any]) -> list[dict[str, Any]]:
|
||||
mapping = conversation.get("mapping")
|
||||
if not isinstance(mapping, dict):
|
||||
return []
|
||||
rows: list[tuple[float, int, dict[str, Any]]] = []
|
||||
for index, node in enumerate(mapping.values()):
|
||||
if not isinstance(node, dict) or not isinstance(node.get("message"), dict):
|
||||
continue
|
||||
message = node["message"]
|
||||
sort_value = message.get("create_time")
|
||||
try:
|
||||
sort_key = float(sort_value)
|
||||
except (TypeError, ValueError):
|
||||
sort_key = float(index)
|
||||
normalized = normalize_message(message)
|
||||
if normalized:
|
||||
rows.append((sort_key, index, normalized))
|
||||
return [row[2] for row in sorted(rows, key=lambda row: (row[0], row[1]))]
|
||||
|
||||
|
||||
def conversation_messages(conversation: dict[str, Any]) -> tuple[list[dict[str, Any]], str]:
|
||||
mapped = chatgpt_mapping_messages(conversation)
|
||||
if mapped:
|
||||
return mapped, "chatgpt_mapping"
|
||||
for key in ("messages", "chat_messages", "turns"):
|
||||
raw_messages = conversation.get(key)
|
||||
if isinstance(raw_messages, list):
|
||||
messages = [
|
||||
normalized
|
||||
for raw in raw_messages
|
||||
if isinstance(raw, dict)
|
||||
for normalized in [normalize_message(raw)]
|
||||
if normalized
|
||||
]
|
||||
return messages, key
|
||||
return [], "unknown"
|
||||
|
||||
|
||||
def conversation_title(conversation: dict[str, Any], index: int) -> str:
|
||||
for key in ("title", "name", "summary"):
|
||||
value = conversation.get(key)
|
||||
if isinstance(value, str) and value.strip():
|
||||
return value.strip()
|
||||
return f"Conversation {index + 1}"
|
||||
|
||||
|
||||
def collect_conversation_json(
|
||||
path: Path,
|
||||
source_name: str,
|
||||
*,
|
||||
include_content: bool = False,
|
||||
max_messages: int = 2000,
|
||||
) -> tuple[list[dict[str, Any]], list[InputWarning]]:
|
||||
warnings: list[InputWarning] = []
|
||||
try:
|
||||
payload = read_json(path)
|
||||
except Exception as exc:
|
||||
return [], [InputWarning(str(path), f"could not read JSON: {exc}")]
|
||||
|
||||
payload = payload_items(payload, ("conversations", "conversation", "items", "data"))
|
||||
if isinstance(payload, dict):
|
||||
payload = [payload]
|
||||
if not isinstance(payload, list):
|
||||
return [], [InputWarning(str(path), "expected a JSON list or an object containing a conversation list")]
|
||||
|
||||
items: list[dict[str, Any]] = []
|
||||
for index, conversation in enumerate(payload):
|
||||
if not isinstance(conversation, dict):
|
||||
warnings.append(InputWarning(str(path), f"skipped conversation at index {index}: expected object"))
|
||||
continue
|
||||
messages, format_hint = conversation_messages(conversation)
|
||||
if not messages:
|
||||
warnings.append(InputWarning(str(path), f"skipped conversation at index {index}: no text messages found"))
|
||||
continue
|
||||
title = conversation_title(conversation, index)
|
||||
source_id = conversation.get("id") or conversation.get("uuid") or conversation.get("conversation_id")
|
||||
text_digest = sha256_text("\n".join(f"{msg['role']}:{msg['text']}" for msg in messages))
|
||||
metadata: dict[str, Any] = {
|
||||
"source_path": str(path),
|
||||
"source_index": index,
|
||||
"source_format": format_hint,
|
||||
"message_count": len(messages),
|
||||
"text_sha256": text_digest,
|
||||
"content_included": False,
|
||||
}
|
||||
if source_id is not None:
|
||||
metadata["source_id"] = str(source_id)
|
||||
for key in ("create_time", "created_at", "update_time", "updated_at"):
|
||||
timestamp = normalize_timestamp(conversation.get(key))
|
||||
if timestamp:
|
||||
metadata[f"source_{key}"] = timestamp
|
||||
item: dict[str, Any] = {
|
||||
"id": stable_id("conversation", source_name, path, source_id or index, text_digest),
|
||||
"kind": "conversation_thread",
|
||||
"title": title,
|
||||
"source": source_name,
|
||||
"metadata": metadata,
|
||||
}
|
||||
if include_content:
|
||||
if len(messages) > max_messages:
|
||||
warnings.append(
|
||||
InputWarning(
|
||||
str(path),
|
||||
f"skipped conversation content at index {index}: over {max_messages} messages",
|
||||
)
|
||||
)
|
||||
else:
|
||||
item["messages"] = messages
|
||||
item["metadata"]["content_included"] = True
|
||||
items.append(item)
|
||||
return items, warnings
|
||||
|
||||
|
||||
def parse_skill_frontmatter(text: str) -> dict[str, Any]:
|
||||
if not text.startswith("---"):
|
||||
return {}
|
||||
end = text.find("\n---", 3)
|
||||
if end < 0:
|
||||
return {}
|
||||
frontmatter: dict[str, Any] = {}
|
||||
for line in text[3:end].strip().splitlines():
|
||||
if not line.strip() or line.lstrip().startswith("#") or ":" not in line:
|
||||
continue
|
||||
key, value = line.split(":", 1)
|
||||
key = key.strip()
|
||||
value = value.strip().strip('"').strip("'")
|
||||
if key:
|
||||
frontmatter[key] = value
|
||||
return frontmatter
|
||||
|
||||
|
||||
def collect_skill_dir(path: Path, source_name: str) -> tuple[list[dict[str, Any]], list[InputWarning]]:
|
||||
warnings: list[InputWarning] = []
|
||||
if path.is_symlink():
|
||||
return [], [InputWarning(str(path), "skills path is a symlink; skipped")]
|
||||
if not path.exists():
|
||||
return [], [InputWarning(str(path), "skills directory does not exist")]
|
||||
if not path.is_dir():
|
||||
return [], [InputWarning(str(path), "skills path is not a directory")]
|
||||
|
||||
items: list[dict[str, Any]] = []
|
||||
for skill_path in sorted(path.rglob("SKILL.md")):
|
||||
if skill_path.is_symlink():
|
||||
warnings.append(InputWarning(str(skill_path), "skipped symlinked skill file"))
|
||||
continue
|
||||
try:
|
||||
text = skill_path.read_text(encoding="utf-8")
|
||||
except Exception as exc:
|
||||
warnings.append(InputWarning(str(skill_path), f"could not read skill: {exc}"))
|
||||
continue
|
||||
frontmatter = parse_skill_frontmatter(text)
|
||||
name = str(frontmatter.get("name") or skill_path.parent.name).strip() or skill_path.parent.name
|
||||
items.append(
|
||||
{
|
||||
"id": stable_id("skill", source_name, skill_path, sha256_text(text)),
|
||||
"kind": "skill",
|
||||
"name": name,
|
||||
"category": str(frontmatter.get("category") or "general"),
|
||||
"source": source_name,
|
||||
"format": "SKILL.md",
|
||||
"content": text,
|
||||
"metadata": {
|
||||
"source_path": str(skill_path),
|
||||
"sha256": sha256_text(text),
|
||||
"frontmatter": frontmatter,
|
||||
},
|
||||
}
|
||||
)
|
||||
return items, warnings
|
||||
|
||||
|
||||
def looks_textual(path: Path) -> bool:
|
||||
if path.suffix.lower() in TEXT_EXTENSIONS:
|
||||
return True
|
||||
guessed, _ = mimetypes.guess_type(str(path))
|
||||
return bool(guessed and (guessed.startswith("text/") or guessed in {"application/json"}))
|
||||
|
||||
|
||||
def iter_archive_dir(path: Path) -> Iterable[Path | InputWarning]:
|
||||
try:
|
||||
children = sorted(path.iterdir())
|
||||
except Exception as exc:
|
||||
yield InputWarning(str(path), f"could not scan archive directory: {exc}")
|
||||
return
|
||||
for child in children:
|
||||
if child.is_symlink():
|
||||
yield InputWarning(str(child), "skipped symlinked archive path")
|
||||
continue
|
||||
if child.is_file():
|
||||
yield child
|
||||
elif child.is_dir():
|
||||
yield from iter_archive_dir(child)
|
||||
|
||||
|
||||
def iter_archive_files(paths: Iterable[Path]) -> Iterable[Path | InputWarning]:
|
||||
for path in paths:
|
||||
if path.is_symlink():
|
||||
yield InputWarning(str(path), "skipped symlinked archive path")
|
||||
continue
|
||||
if path.is_file():
|
||||
yield path
|
||||
elif path.is_dir():
|
||||
yield from iter_archive_dir(path)
|
||||
|
||||
|
||||
def collect_archive_paths(
|
||||
paths: list[Path],
|
||||
source_name: str,
|
||||
*,
|
||||
include_content: bool = False,
|
||||
max_bytes: int = 256_000,
|
||||
) -> tuple[list[dict[str, Any]], list[InputWarning]]:
|
||||
warnings: list[InputWarning] = []
|
||||
items: list[dict[str, Any]] = []
|
||||
existing_paths: list[Path] = []
|
||||
for path in paths:
|
||||
if path.is_symlink():
|
||||
warnings.append(InputWarning(str(path), "archive path is a symlink; skipped"))
|
||||
continue
|
||||
if not path.exists():
|
||||
warnings.append(InputWarning(str(path), "archive path does not exist"))
|
||||
continue
|
||||
if not path.is_file() and not path.is_dir():
|
||||
warnings.append(InputWarning(str(path), "archive path is not a file or directory"))
|
||||
continue
|
||||
existing_paths.append(path)
|
||||
|
||||
for entry in iter_archive_files(existing_paths):
|
||||
if isinstance(entry, InputWarning):
|
||||
warnings.append(entry)
|
||||
continue
|
||||
path = entry
|
||||
if not looks_textual(path):
|
||||
warnings.append(InputWarning(str(path), "skipped non-text archive file"))
|
||||
continue
|
||||
try:
|
||||
st = path.stat()
|
||||
except Exception as exc:
|
||||
warnings.append(InputWarning(str(path), f"could not stat archive file: {exc}"))
|
||||
continue
|
||||
size = st.st_size
|
||||
try:
|
||||
file_hash = sha256_path(path)
|
||||
except Exception as exc:
|
||||
warnings.append(InputWarning(str(path), f"could not hash archive file: {exc}"))
|
||||
continue
|
||||
if include_content and size > max_bytes:
|
||||
warnings.append(InputWarning(str(path), f"skipped archive content over {max_bytes} bytes"))
|
||||
archive_item: dict[str, Any] = {
|
||||
"id": stable_id("archive", source_name, path, file_hash),
|
||||
"kind": "archive_document",
|
||||
"title": path.name,
|
||||
"source": source_name,
|
||||
"metadata": {
|
||||
"source_path": str(path),
|
||||
"size_bytes": size,
|
||||
"sha256": file_hash,
|
||||
},
|
||||
}
|
||||
if include_content and size <= max_bytes:
|
||||
try:
|
||||
archive_item["content"] = path.read_text(encoding="utf-8")
|
||||
except UnicodeDecodeError:
|
||||
archive_item["content"] = path.read_text(encoding="utf-8", errors="replace")
|
||||
archive_item["metadata"]["decoded_with_replacement"] = True
|
||||
items.append(archive_item)
|
||||
return items, warnings
|
||||
|
||||
|
||||
def build_manifest(args) -> dict[str, Any]:
|
||||
warnings: list[InputWarning] = []
|
||||
items: list[dict[str, Any]] = []
|
||||
|
||||
for path in args.memory_json:
|
||||
collected, got_warnings = collect_memory_json(path, args.source_name)
|
||||
items.extend(collected)
|
||||
warnings.extend(got_warnings)
|
||||
|
||||
for path in args.skills_dir:
|
||||
collected, got_warnings = collect_skill_dir(path, args.source_name)
|
||||
items.extend(collected)
|
||||
warnings.extend(got_warnings)
|
||||
|
||||
for path in args.conversation_json:
|
||||
collected, got_warnings = collect_conversation_json(
|
||||
path,
|
||||
args.source_name,
|
||||
include_content=args.include_conversation_content,
|
||||
max_messages=args.max_conversation_messages,
|
||||
)
|
||||
items.extend(collected)
|
||||
warnings.extend(got_warnings)
|
||||
|
||||
if args.archive:
|
||||
collected, got_warnings = collect_archive_paths(
|
||||
args.archive,
|
||||
args.source_name,
|
||||
include_content=args.include_archive_content,
|
||||
max_bytes=args.max_archive_bytes,
|
||||
)
|
||||
items.extend(collected)
|
||||
warnings.extend(got_warnings)
|
||||
|
||||
counts: dict[str, int] = {}
|
||||
for item in items:
|
||||
counts[item["kind"]] = counts.get(item["kind"], 0) + 1
|
||||
|
||||
return {
|
||||
"schema_version": SCHEMA_VERSION,
|
||||
"generated_at": utc_now_iso(),
|
||||
"source": {
|
||||
"name": args.source_name,
|
||||
"kind": args.source_kind,
|
||||
},
|
||||
"summary": {
|
||||
"item_count": len(items),
|
||||
"counts_by_kind": counts,
|
||||
"warning_count": len(warnings),
|
||||
},
|
||||
"items": items,
|
||||
"warnings": [{"path": warning.path, "message": warning.message} for warning in warnings],
|
||||
}
|
||||
|
||||
|
||||
def parse_args(argv: list[str] | None = None):
|
||||
parser = argparse.ArgumentParser(description="Build a neutral Odysseus agent migration manifest.")
|
||||
parser.add_argument("--source-name", default="agent-export", help="Human-readable source name.")
|
||||
parser.add_argument("--source-kind", default="generic", help="Source adapter kind, e.g. generic, openclaw, hermes.")
|
||||
parser.add_argument(
|
||||
"--memory-json",
|
||||
action="append",
|
||||
type=Path,
|
||||
default=[],
|
||||
help="JSON memory export. May be a list, or an object containing memories/items/data.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--skills-dir",
|
||||
action="append",
|
||||
type=Path,
|
||||
default=[],
|
||||
help="Directory containing SKILL.md files. Scanned recursively.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--archive",
|
||||
action="append",
|
||||
type=Path,
|
||||
default=[],
|
||||
help="Text/Markdown/JSON file or directory to preserve as archive documents.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--conversation-json",
|
||||
action="append",
|
||||
type=Path,
|
||||
default=[],
|
||||
help="Conversation export JSON. Supports generic message lists and ChatGPT-style conversations.json.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--include-archive-content",
|
||||
action="store_true",
|
||||
help="Embed archive document content in the manifest. By default only metadata is included.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--max-archive-bytes",
|
||||
type=int,
|
||||
default=256_000,
|
||||
help="Maximum bytes to embed per archive file when --include-archive-content is used.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--include-conversation-content",
|
||||
action="store_true",
|
||||
help="Embed normalized conversation messages. By default only thread metadata is included.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--max-conversation-messages",
|
||||
type=int,
|
||||
default=2000,
|
||||
help="Maximum messages to embed per conversation when --include-conversation-content is used.",
|
||||
)
|
||||
parser.add_argument("--output", type=Path, help="Write manifest JSON to this path instead of stdout.")
|
||||
parser.add_argument("--compact", action="store_true", help="Write compact JSON without indentation.")
|
||||
return parser.parse_args(argv)
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
args = parse_args(argv)
|
||||
manifest = build_manifest(args)
|
||||
text = json.dumps(manifest, ensure_ascii=False, sort_keys=True, separators=(",", ":")) if args.compact else (
|
||||
json.dumps(manifest, ensure_ascii=False, indent=2, sort_keys=True) + "\n"
|
||||
)
|
||||
if args.output:
|
||||
args.output.parent.mkdir(parents=True, exist_ok=True)
|
||||
args.output.write_text(text, encoding="utf-8")
|
||||
else:
|
||||
sys.stdout.write(text)
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -1,133 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Backfill release_date on entries in services/hwfit/data/hf_models.json.
|
||||
|
||||
Why: the `newest` sort in the cookbook ranks rows by release_date. Anything
|
||||
missing a date sorts to the bottom. This script pulls `created_at` from the
|
||||
HuggingFace API for each catalog entry without one (or all entries when
|
||||
--refresh is passed) and writes the catalog back.
|
||||
|
||||
Usage:
|
||||
python scripts/backfill_model_release_dates.py # missing only
|
||||
python scripts/backfill_model_release_dates.py --refresh # all entries
|
||||
python scripts/backfill_model_release_dates.py --limit 50 # cap requests
|
||||
python scripts/backfill_model_release_dates.py --dry-run # show, don't write
|
||||
|
||||
Auth: set HF_TOKEN env var (or huggingface-cli login) to access gated repos.
|
||||
"""
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
import time
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
|
||||
try:
|
||||
from huggingface_hub import HfApi
|
||||
from huggingface_hub.utils import HfHubHTTPError
|
||||
except ImportError:
|
||||
print("Install huggingface_hub: pip install huggingface_hub", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
CATALOG_PATH = Path(__file__).resolve().parent.parent / "services" / "hwfit" / "data" / "hf_models.json"
|
||||
|
||||
|
||||
def fetch_release_date(api: HfApi, repo_id: str) -> str | None:
|
||||
"""Return YYYY-MM-DD release date, or None on miss / error."""
|
||||
try:
|
||||
info = api.model_info(repo_id, files_metadata=False)
|
||||
except HfHubHTTPError as e:
|
||||
# 401 = gated/private, 404 = renamed/deleted. Either way, no date.
|
||||
status = getattr(getattr(e, "response", None), "status_code", None)
|
||||
print(f" {repo_id}: HTTP {status or '?'}", file=sys.stderr)
|
||||
return None
|
||||
except Exception as e:
|
||||
print(f" {repo_id}: {type(e).__name__}: {e}", file=sys.stderr)
|
||||
return None
|
||||
created = getattr(info, "created_at", None)
|
||||
if not created:
|
||||
return None
|
||||
return created.strftime("%Y-%m-%d")
|
||||
|
||||
|
||||
def main():
|
||||
p = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
|
||||
p.add_argument("--refresh", action="store_true", help="Overwrite existing release_date too (default: only fill missing).")
|
||||
p.add_argument("--limit", type=int, default=0, help="Stop after N API calls (0 = no limit).")
|
||||
p.add_argument("--dry-run", action="store_true", help="Don't write back; just report.")
|
||||
p.add_argument("--sleep", type=float, default=0.05, help="Seconds to sleep between requests (default 0.05).")
|
||||
args = p.parse_args()
|
||||
|
||||
if not CATALOG_PATH.exists():
|
||||
print(f"Catalog not found: {CATALOG_PATH}", file=sys.stderr)
|
||||
sys.exit(2)
|
||||
|
||||
with CATALOG_PATH.open(encoding="utf-8") as f:
|
||||
catalog = json.load(f)
|
||||
|
||||
candidates = []
|
||||
for i, m in enumerate(catalog):
|
||||
name = m.get("name")
|
||||
if not name:
|
||||
continue
|
||||
existing = (m.get("release_date") or "").strip()
|
||||
if existing and not args.refresh:
|
||||
continue
|
||||
candidates.append(i)
|
||||
|
||||
if args.limit:
|
||||
candidates = candidates[: args.limit]
|
||||
|
||||
print(f"Catalog: {CATALOG_PATH}")
|
||||
print(f"Total entries: {len(catalog)}")
|
||||
print(f"Targets ({'refresh all' if args.refresh else 'missing only'}{'' if not args.limit else f', capped at {args.limit}'}): {len(candidates)}")
|
||||
if not candidates:
|
||||
print("Nothing to do.")
|
||||
return
|
||||
|
||||
api = HfApi(token=os.environ.get("HF_TOKEN") or None)
|
||||
updated = 0
|
||||
skipped = 0
|
||||
started = time.time()
|
||||
for n, idx in enumerate(candidates, start=1):
|
||||
entry = catalog[idx]
|
||||
name = entry["name"]
|
||||
old = (entry.get("release_date") or "").strip()
|
||||
new = fetch_release_date(api, name)
|
||||
if new is None:
|
||||
skipped += 1
|
||||
tag = "skip"
|
||||
elif new == old:
|
||||
tag = "unchanged"
|
||||
else:
|
||||
entry["release_date"] = new
|
||||
updated += 1
|
||||
tag = f"set {new}" + (f" (was {old})" if old else "")
|
||||
print(f"[{n}/{len(candidates)}] {name} — {tag}")
|
||||
if args.sleep:
|
||||
time.sleep(args.sleep)
|
||||
|
||||
elapsed = time.time() - started
|
||||
print()
|
||||
print(f"Done in {elapsed:.1f}s — {updated} updated, {skipped} skipped (HF unavailable / gated / missing date).")
|
||||
|
||||
if args.dry_run:
|
||||
print("Dry run — no write.")
|
||||
return
|
||||
|
||||
if updated:
|
||||
# Atomic write: tmp file in the same dir, then rename. Keeps the
|
||||
# catalog usable even if the process dies mid-write.
|
||||
tmp = CATALOG_PATH.with_suffix(".json.tmp")
|
||||
with tmp.open("w", encoding="utf-8") as f:
|
||||
json.dump(catalog, f, indent=1, ensure_ascii=False)
|
||||
f.write("\n")
|
||||
tmp.replace(CATALOG_PATH)
|
||||
print(f"Wrote {CATALOG_PATH}")
|
||||
else:
|
||||
print("No changes to write.")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,341 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Import models from the upstream vllm-project/recipes catalog into our
|
||||
local hf_models.json. Two modes:
|
||||
|
||||
--update-existing Stamp min_vllm_version + vllm_recipe=True on rows we
|
||||
already carry. Cheap, no HF API calls.
|
||||
--add-missing Create new catalog rows for every recipe model we
|
||||
don't carry. Hits the HF API for created_at + downloads
|
||||
(~1 req per missing model, paced).
|
||||
|
||||
Both modes write atomically (tmp + rename) so a crashed run leaves the
|
||||
catalog intact. Default with no mode flags runs both, prefer to pass them
|
||||
explicitly.
|
||||
|
||||
Usage:
|
||||
python scripts/import_from_vllm_recipes.py --update-existing
|
||||
python scripts/import_from_vllm_recipes.py --add-missing
|
||||
python scripts/import_from_vllm_recipes.py --dry-run
|
||||
python scripts/import_from_vllm_recipes.py --limit 10
|
||||
|
||||
Auth: set HF_TOKEN to access gated repos when --add-missing.
|
||||
"""
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
import time
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
|
||||
try:
|
||||
import httpx
|
||||
import yaml
|
||||
except ImportError:
|
||||
print("pip install httpx PyYAML", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
try:
|
||||
from huggingface_hub import HfApi
|
||||
from huggingface_hub.utils import HfHubHTTPError
|
||||
except ImportError:
|
||||
HfApi = None
|
||||
HfHubHTTPError = Exception
|
||||
|
||||
|
||||
CATALOG_PATH = Path(__file__).resolve().parent.parent / "services" / "hwfit" / "data" / "hf_models.json"
|
||||
RECIPES_TREE_URL = (
|
||||
"https://api.github.com/repos/vllm-project/recipes/git/trees/main?recursive=1"
|
||||
)
|
||||
RECIPE_RAW_URL = (
|
||||
"https://raw.githubusercontent.com/vllm-project/recipes/main/models/{repo}.yaml"
|
||||
)
|
||||
|
||||
|
||||
# Map recipe `precision` to the closest catalog `quantization` label that
|
||||
# fit.py / models.py already understand.
|
||||
_PRECISION_TO_QUANT = {
|
||||
"fp8": "FP8",
|
||||
"nvfp4": "NVFP4",
|
||||
"mxfp4": "MXFP4",
|
||||
"bf16": "BF16",
|
||||
"fp16": "F16",
|
||||
"f16": "F16",
|
||||
"fp4": "FP4",
|
||||
"int8": "INT8",
|
||||
"int4": "INT4",
|
||||
"awq-4bit": "AWQ-4bit",
|
||||
"awq-8bit": "AWQ-8bit",
|
||||
}
|
||||
|
||||
# Architecture name → use_case fallback. fit.py weights use_case for filtering;
|
||||
# missing field defaults to a generic bucket.
|
||||
_ARCH_USE_CASE = {
|
||||
"moe": "General-purpose reasoning, long-context",
|
||||
"llama": "General-purpose chat",
|
||||
"qwen2": "General-purpose chat",
|
||||
"qwen3": "General-purpose reasoning",
|
||||
"deepseek_v3_moe": "General-purpose reasoning, long-context",
|
||||
"deepseek_v4_moe": "General-purpose reasoning, long-context",
|
||||
}
|
||||
|
||||
|
||||
def _parse_param_count(s) -> int:
|
||||
"""'230B' / '8.6B' / '4.2T' → integer parameter count."""
|
||||
if s is None:
|
||||
return 0
|
||||
s = str(s).strip().replace(",", "")
|
||||
m = re.match(r"^([\d.]+)\s*([KMBT]?)$", s, re.I)
|
||||
if not m:
|
||||
return 0
|
||||
num = float(m.group(1))
|
||||
unit = (m.group(2) or "").upper()
|
||||
mult = {"K": 1e3, "M": 1e6, "B": 1e9, "T": 1e12, "": 1.0}[unit]
|
||||
return int(num * mult)
|
||||
|
||||
|
||||
def _capabilities_for(arch: str, hardware: dict, ctx_len: int, has_reasoning: bool) -> list[str]:
|
||||
caps = []
|
||||
if "moe" in (arch or "").lower():
|
||||
caps.append("moe")
|
||||
if has_reasoning:
|
||||
caps.append("reasoning")
|
||||
if ctx_len and ctx_len >= 100_000:
|
||||
caps.append("long_context")
|
||||
if any(hw in (hardware or {}) for hw in ("mi300x", "mi325x", "mi350x", "mi355x")):
|
||||
caps.append("amd_supported")
|
||||
return caps
|
||||
|
||||
|
||||
def _fetch_manifest(client: httpx.Client) -> set[str]:
|
||||
r = client.get(RECIPES_TREE_URL, headers={"Accept": "application/vnd.github+json"}, timeout=15)
|
||||
r.raise_for_status()
|
||||
tree = (r.json() or {}).get("tree") or []
|
||||
out: set[str] = set()
|
||||
for e in tree:
|
||||
path = (e or {}).get("path") or ""
|
||||
if path.startswith("models/") and path.endswith(".yaml"):
|
||||
body = path[len("models/"):-len(".yaml")]
|
||||
if "/" in body:
|
||||
out.add(body)
|
||||
return out
|
||||
|
||||
|
||||
def _fetch_recipe(client: httpx.Client, repo: str) -> dict | None:
|
||||
url = RECIPE_RAW_URL.format(repo=repo)
|
||||
try:
|
||||
r = client.get(url, timeout=10)
|
||||
if r.status_code != 200:
|
||||
return None
|
||||
return yaml.safe_load(r.text) or {}
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
|
||||
def _stamp_from_recipe(entry: dict, recipe: dict) -> bool:
|
||||
"""Mutate entry with recipe-derived fields. Returns True if anything changed."""
|
||||
model = recipe.get("model") or {}
|
||||
meta = recipe.get("meta") or {}
|
||||
features = recipe.get("features") or {}
|
||||
|
||||
changed = False
|
||||
new_min = (model.get("min_vllm_version") or "").strip()
|
||||
if new_min and entry.get("min_vllm_version") != new_min:
|
||||
entry["min_vllm_version"] = new_min
|
||||
changed = True
|
||||
if not entry.get("vllm_recipe"):
|
||||
entry["vllm_recipe"] = True
|
||||
changed = True
|
||||
# Hardware support map — useful for filtering "which models run on my AMD box".
|
||||
hw = meta.get("hardware") or {}
|
||||
if hw and entry.get("recipe_hardware") != hw:
|
||||
entry["recipe_hardware"] = {k: str(v) for k, v in hw.items()}
|
||||
changed = True
|
||||
# Tool/reasoning parser hints — purely informational at catalog level;
|
||||
# the live launch command builder still reads them from the recipe API.
|
||||
if features.get("reasoning") and not entry.get("has_reasoning_parser"):
|
||||
entry["has_reasoning_parser"] = True
|
||||
changed = True
|
||||
if features.get("tool_calling") and not entry.get("has_tool_call_parser"):
|
||||
entry["has_tool_call_parser"] = True
|
||||
changed = True
|
||||
return changed
|
||||
|
||||
|
||||
def _build_new_entry(repo: str, recipe: dict, hf_info=None) -> dict | None:
|
||||
"""Build a fresh catalog entry from a recipe + (optional) HF model info."""
|
||||
model = recipe.get("model") or {}
|
||||
meta = recipe.get("meta") or {}
|
||||
features = recipe.get("features") or {}
|
||||
variants = recipe.get("variants") or {}
|
||||
|
||||
org, name = repo.split("/", 1)
|
||||
raw_params = _parse_param_count(model.get("parameter_count"))
|
||||
active_raw = _parse_param_count(model.get("active_parameters"))
|
||||
ctx = model.get("context_length") or 0
|
||||
|
||||
# Pick the smallest-VRAM variant as the catalog quant — that's what most
|
||||
# users land on first. NVFP4/MXFP4 typically win this on Blackwell;
|
||||
# FP8 elsewhere; BF16 baseline only.
|
||||
pick_quant = None
|
||||
pick_vram = None
|
||||
for vk, vv in variants.items():
|
||||
if not isinstance(vv, dict):
|
||||
continue
|
||||
prec = (vv.get("precision") or "").lower()
|
||||
vram = vv.get("vram_minimum_gb") or 0
|
||||
quant = _PRECISION_TO_QUANT.get(prec)
|
||||
if quant and (pick_vram is None or (vram and vram < pick_vram)):
|
||||
pick_quant = quant
|
||||
pick_vram = vram or pick_vram
|
||||
if not pick_quant:
|
||||
pick_quant = "BF16"
|
||||
|
||||
arch = (model.get("architecture") or "").lower()
|
||||
use_case = _ARCH_USE_CASE.get(arch, "General-purpose chat")
|
||||
caps = _capabilities_for(arch, meta.get("hardware") or {}, ctx, bool(features.get("reasoning")))
|
||||
|
||||
rel_date = ""
|
||||
downloads = 0
|
||||
likes = 0
|
||||
if hf_info is not None:
|
||||
created = getattr(hf_info, "created_at", None)
|
||||
if created:
|
||||
rel_date = created.strftime("%Y-%m-%d")
|
||||
downloads = int(getattr(hf_info, "downloads", 0) or 0)
|
||||
likes = int(getattr(hf_info, "likes", 0) or 0)
|
||||
if not rel_date:
|
||||
rel_date = str(meta.get("date_updated") or datetime.utcnow().strftime("%Y-%m-%d"))
|
||||
|
||||
entry: dict = {
|
||||
"name": repo,
|
||||
"provider": org,
|
||||
"parameter_count": str(model.get("parameter_count") or "?"),
|
||||
"parameters_raw": raw_params,
|
||||
"is_moe": "moe" in arch,
|
||||
"quantization": pick_quant,
|
||||
"context_length": int(ctx or 0),
|
||||
"use_case": use_case,
|
||||
"capabilities": caps,
|
||||
"pipeline_tag": "text-generation",
|
||||
"architecture": arch or "unknown",
|
||||
"hf_downloads": downloads,
|
||||
"hf_likes": likes,
|
||||
"release_date": rel_date,
|
||||
# Recipe-derived bits.
|
||||
"vllm_recipe": True,
|
||||
"min_vllm_version": (model.get("min_vllm_version") or "").strip() or None,
|
||||
"recipe_hardware": {k: str(v) for k, v in (meta.get("hardware") or {}).items()},
|
||||
"has_reasoning_parser": bool(features.get("reasoning")),
|
||||
"has_tool_call_parser": bool(features.get("tool_calling")),
|
||||
}
|
||||
if active_raw:
|
||||
entry["active_parameters"] = active_raw
|
||||
if pick_vram:
|
||||
# min_vram_gb is what hwfit uses for "does this fit". Recipe states a
|
||||
# minimum for the chosen variant; round up slightly for KV-cache room.
|
||||
entry["min_vram_gb"] = float(pick_vram)
|
||||
entry["min_ram_gb"] = float(round(pick_vram * 0.6, 1))
|
||||
entry["recommended_ram_gb"] = float(round(pick_vram * 1.2, 1))
|
||||
# Drop empty / None fields to keep the JSON tidy.
|
||||
return {k: v for k, v in entry.items() if v not in (None, "", [], {})}
|
||||
|
||||
|
||||
def main():
|
||||
p = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
|
||||
p.add_argument("--update-existing", action="store_true", help="Stamp min_vllm_version + vllm_recipe on existing rows.")
|
||||
p.add_argument("--add-missing", action="store_true", help="Add new rows for recipe models not in the catalog.")
|
||||
p.add_argument("--limit", type=int, default=0, help="Stop after N recipe fetches.")
|
||||
p.add_argument("--dry-run", action="store_true", help="Don't write back; just report.")
|
||||
p.add_argument("--sleep", type=float, default=0.05, help="Seconds between HTTP requests.")
|
||||
args = p.parse_args()
|
||||
if not args.update_existing and not args.add_missing:
|
||||
args.update_existing = args.add_missing = True
|
||||
|
||||
with CATALOG_PATH.open(encoding="utf-8") as f:
|
||||
catalog = json.load(f)
|
||||
by_name = {m.get("name"): m for m in catalog if m.get("name")}
|
||||
|
||||
client = httpx.Client(follow_redirects=True)
|
||||
print(f"Catalog: {CATALOG_PATH} ({len(catalog)} entries)")
|
||||
print("Fetching upstream manifest…")
|
||||
try:
|
||||
manifest = _fetch_manifest(client)
|
||||
except Exception as e:
|
||||
print(f"FATAL: manifest fetch failed: {e}", file=sys.stderr)
|
||||
sys.exit(2)
|
||||
print(f"Manifest: {len(manifest)} recipes")
|
||||
|
||||
existing = sorted(by_name.keys() & manifest)
|
||||
missing = sorted(manifest - by_name.keys())
|
||||
print(f"Match catalog ↔ manifest: existing={len(existing)} missing={len(missing)}")
|
||||
|
||||
targets: list[tuple[str, str]] = [] # (repo, action)
|
||||
if args.update_existing:
|
||||
targets.extend((r, "update") for r in existing)
|
||||
if args.add_missing:
|
||||
targets.extend((r, "add") for r in missing)
|
||||
if args.limit:
|
||||
targets = targets[: args.limit]
|
||||
print(f"Targets: {len(targets)}")
|
||||
|
||||
hf_api = HfApi(token=os.environ.get("HF_TOKEN") or None) if HfApi else None
|
||||
updated = added = skipped = 0
|
||||
started = time.time()
|
||||
|
||||
for n, (repo, action) in enumerate(targets, 1):
|
||||
recipe = _fetch_recipe(client, repo)
|
||||
if not recipe:
|
||||
print(f"[{n}/{len(targets)}] {repo:55} skip (no recipe fetched)")
|
||||
skipped += 1
|
||||
time.sleep(args.sleep)
|
||||
continue
|
||||
if action == "update":
|
||||
entry = by_name[repo]
|
||||
if _stamp_from_recipe(entry, recipe):
|
||||
updated += 1
|
||||
print(f"[{n}/{len(targets)}] {repo:55} updated")
|
||||
else:
|
||||
print(f"[{n}/{len(targets)}] {repo:55} unchanged")
|
||||
else: # add
|
||||
hf_info = None
|
||||
if hf_api:
|
||||
try:
|
||||
hf_info = hf_api.model_info(repo, files_metadata=False)
|
||||
except HfHubHTTPError as e:
|
||||
code = getattr(getattr(e, "response", None), "status_code", "?")
|
||||
print(f" HF {code} for {repo} — building from recipe only", file=sys.stderr)
|
||||
except Exception as e:
|
||||
print(f" HF error for {repo}: {e}", file=sys.stderr)
|
||||
new_entry = _build_new_entry(repo, recipe, hf_info)
|
||||
if new_entry:
|
||||
catalog.append(new_entry)
|
||||
by_name[repo] = new_entry
|
||||
added += 1
|
||||
print(f"[{n}/{len(targets)}] {repo:55} added ({new_entry.get('parameter_count','?')}, {new_entry.get('quantization','?')})")
|
||||
else:
|
||||
skipped += 1
|
||||
print(f"[{n}/{len(targets)}] {repo:55} skip (couldn't build entry)")
|
||||
time.sleep(args.sleep)
|
||||
|
||||
elapsed = time.time() - started
|
||||
print()
|
||||
print(f"Done in {elapsed:.1f}s — added={added}, updated={updated}, skipped={skipped}")
|
||||
|
||||
if args.dry_run:
|
||||
print("Dry run — no write.")
|
||||
return
|
||||
if added or updated:
|
||||
tmp = CATALOG_PATH.with_suffix(".json.tmp")
|
||||
with tmp.open("w", encoding="utf-8") as f:
|
||||
json.dump(catalog, f, indent=1, ensure_ascii=False)
|
||||
f.write("\n")
|
||||
tmp.replace(CATALOG_PATH)
|
||||
print(f"Wrote {CATALOG_PATH} ({len(catalog)} entries)")
|
||||
else:
|
||||
print("No changes — catalog untouched.")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -14036,29 +14036,6 @@
|
||||
"vision"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "google/gemma-4-12B",
|
||||
"provider": "Google",
|
||||
"parameter_count": "12.0B",
|
||||
"parameters_raw": 12000000000,
|
||||
"min_ram_gb": 24.0,
|
||||
"recommended_ram_gb": 32.0,
|
||||
"min_vram_gb": 24.0,
|
||||
"quantization": "BF16",
|
||||
"context_length": 131072,
|
||||
"use_case": "General purpose, multimodal",
|
||||
"is_moe": false,
|
||||
"num_experts": null,
|
||||
"active_experts": null,
|
||||
"active_parameters": null,
|
||||
"architecture": "gemma4",
|
||||
"pipeline_tag": "image-text-to-text",
|
||||
"release_date": "2026-04-01",
|
||||
"gguf_sources": [],
|
||||
"capabilities": [
|
||||
"vision"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "google/gemma-4-31B-it",
|
||||
"provider": "Google",
|
||||
@@ -19144,4 +19121,4 @@
|
||||
],
|
||||
"_discovered": true
|
||||
}
|
||||
]
|
||||
]
|
||||
+13
-73
@@ -19,36 +19,22 @@ GPU_BANDWIDTH = {
|
||||
"6950 xt": 576, "6900 xt": 512, "6800 xt": 512, "6800": 512, "6700 xt": 384, "6600 xt": 256, "6600": 224,
|
||||
"mi300x": 5300, "mi300": 5300, "mi250x": 3277, "mi250": 3277, "mi210": 1638, "mi100": 1229,
|
||||
"9070 xt": 624, "9070": 488, "9060 xt": 322, "9060": 322,
|
||||
# NVIDIA GB10 Grace-Blackwell superchip (DGX Spark). Unified LPDDR5X memory,
|
||||
# not Apple Silicon, so it lives in the generic GPU table — the Apple-only
|
||||
# lookup never matches it (its name carries no "apple").
|
||||
"gb10": 273,
|
||||
# Apple Silicon unified-memory bandwidth (GB/s). Keyed off the chip name
|
||||
# reported by sysctl machdep.cpu.brand_string (e.g. "Apple M4 Max"). Listed
|
||||
# before the bare "m_" keys matters less than length-sorting (done below),
|
||||
# which guarantees "m4 max" is tried before "m4".
|
||||
"m1 ultra": 800, "m1 max": 400, "m1 pro": 200, "m1": 68,
|
||||
"m2 ultra": 800, "m2 max": 400, "m2 pro": 200, "m2": 100,
|
||||
"m3 ultra": 800, "m3 max": 300, "m3 pro": 150, "m3": 100,
|
||||
"m4 max": 546, "m4 pro": 273, "m4": 120,
|
||||
"m5 max": 546, "m5 pro": 273, "m5": 150,
|
||||
}
|
||||
|
||||
# Pre-sort keys by length descending for correct substring matching
|
||||
_BW_KEYS_SORTED = sorted(GPU_BANDWIDTH.keys(), key=len, reverse=True)
|
||||
|
||||
# Apple Silicon unified-memory bandwidth (GB/s). For chip families with both
|
||||
# binned and full variants under the same "Apple Mx Max" brand string, prefer
|
||||
# GPU core count when hardware detection provides it; otherwise fall back to the
|
||||
# conservative tier so speed estimates do not over-promise.
|
||||
APPLE_BANDWIDTH_FIXED = {
|
||||
"m1 ultra": 800, "m1 max": 400, "m1 pro": 200, "m1": 68,
|
||||
"m2 ultra": 800, "m2 max": 400, "m2 pro": 200, "m2": 100,
|
||||
"m3 ultra": 800, "m3 pro": 150, "m3": 100,
|
||||
"m4 pro": 273, "m4": 120,
|
||||
"m5 pro": 307, "m5": 153,
|
||||
}
|
||||
APPLE_BANDWIDTH_BY_CORES = {
|
||||
"m3 max": {30: 300, 40: 400},
|
||||
"m4 max": {32: 410, 40: 546},
|
||||
"m5 max": {32: 460, 40: 614},
|
||||
}
|
||||
_APPLE_FIXED_KEYS_SORTED = sorted(APPLE_BANDWIDTH_FIXED.keys(), key=len, reverse=True)
|
||||
_APPLE_VARIANT_KEYS_SORTED = sorted(APPLE_BANDWIDTH_BY_CORES.keys(), key=len, reverse=True)
|
||||
|
||||
# metal: backstop for Apple Silicon chips not in the explicit tables above
|
||||
# (e.g. a future M6) — use a conservative generic estimate when unknown.
|
||||
# metal: backstop for Apple Silicon chips not in GPU_BANDWIDTH (e.g. a future
|
||||
# M5) — the named chips above take the accurate bandwidth path instead.
|
||||
FALLBACK_K = {"cuda": 220, "rocm": 180, "metal": 150, "cpu_x86": 70, "cpu_arm": 90}
|
||||
|
||||
USE_CASE_WEIGHTS = {
|
||||
@@ -74,56 +60,10 @@ CONTEXT_TARGET = {
|
||||
}
|
||||
|
||||
|
||||
def _lookup_apple_bandwidth(system):
|
||||
gpu_name = system.get("gpu_name")
|
||||
def _lookup_bandwidth(gpu_name):
|
||||
if not isinstance(gpu_name, str) or not gpu_name:
|
||||
return None
|
||||
gn = gpu_name.lower()
|
||||
|
||||
# Guard against false matches on non-Apple GPUs whose names contain
|
||||
# "m3"/"m4"/"m5" (e.g. NVIDIA Quadro M4 000).
|
||||
if "apple" not in gn:
|
||||
return None
|
||||
|
||||
raw_cores = system.get("gpu_cores")
|
||||
try:
|
||||
gpu_cores = int(raw_cores) if raw_cores is not None else None
|
||||
except (TypeError, ValueError):
|
||||
gpu_cores = None
|
||||
|
||||
for key in _APPLE_VARIANT_KEYS_SORTED:
|
||||
if key not in gn:
|
||||
continue
|
||||
if gpu_cores in APPLE_BANDWIDTH_BY_CORES[key]:
|
||||
return APPLE_BANDWIDTH_BY_CORES[key][gpu_cores]
|
||||
return min(APPLE_BANDWIDTH_BY_CORES[key].values())
|
||||
|
||||
for key in _APPLE_FIXED_KEYS_SORTED:
|
||||
if key in gn:
|
||||
return APPLE_BANDWIDTH_FIXED[key]
|
||||
return None
|
||||
|
||||
|
||||
def _lookup_bandwidth(system):
|
||||
if isinstance(system, dict):
|
||||
gpu_name = system.get("gpu_name")
|
||||
else:
|
||||
gpu_name = system
|
||||
|
||||
if not isinstance(gpu_name, str) or not gpu_name:
|
||||
return None
|
||||
|
||||
# Apple tiers live only in the Apple-specific table now (#2564), so route
|
||||
# BOTH dict and bare-string callers through it. A bare string carries no
|
||||
# gpu_cores, so the helper falls back to the conservative (lowest) tier for
|
||||
# that model -- before #2564 the generic table answered string lookups, and
|
||||
# dropping that made _lookup_bandwidth("Apple M3 Max") return None.
|
||||
apple_input = system if isinstance(system, dict) else {"gpu_name": gpu_name}
|
||||
bw = _lookup_apple_bandwidth(apple_input)
|
||||
if bw is not None:
|
||||
return bw
|
||||
|
||||
gn = gpu_name.lower()
|
||||
for key in _BW_KEYS_SORTED:
|
||||
if key in gn:
|
||||
return GPU_BANDWIDTH[key]
|
||||
@@ -144,7 +84,7 @@ def _estimate_speed(model, quant, run_mode, system, offload_frac=0.0):
|
||||
"""
|
||||
pb = _active_params_b(model)
|
||||
is_moe = model.get("is_moe", False)
|
||||
bw = _lookup_bandwidth(system)
|
||||
bw = _lookup_bandwidth(system.get("gpu_name"))
|
||||
backend = system.get("backend", "cpu_x86")
|
||||
|
||||
if bw and run_mode in ("gpu", "cpu_offload"):
|
||||
|
||||
+1
-127
@@ -1,4 +1,3 @@
|
||||
import json
|
||||
import os
|
||||
import platform
|
||||
import re
|
||||
@@ -336,37 +335,6 @@ def _detect_apple_silicon():
|
||||
if total_gb <= 0:
|
||||
return None
|
||||
|
||||
def _parse_apple_gpu_cores(text):
|
||||
if not text:
|
||||
return None
|
||||
try:
|
||||
data = json.loads(text)
|
||||
except (TypeError, ValueError, json.JSONDecodeError):
|
||||
data = None
|
||||
if isinstance(data, dict):
|
||||
for gpu in data.get("SPDisplaysDataType") or []:
|
||||
if not isinstance(gpu, dict):
|
||||
continue
|
||||
model = str(gpu.get("sppci_model") or gpu.get("_name") or "")
|
||||
if "apple" not in model.lower():
|
||||
continue
|
||||
cores = gpu.get("sppci_cores")
|
||||
try:
|
||||
return int(str(cores).strip())
|
||||
except (TypeError, ValueError):
|
||||
continue
|
||||
m = re.search(r"Total Number of Cores:\s*(\d+)", text)
|
||||
if m:
|
||||
try:
|
||||
return int(m.group(1))
|
||||
except ValueError:
|
||||
return None
|
||||
return None
|
||||
|
||||
gpu_cores = _parse_apple_gpu_cores(_run(["system_profiler", "SPDisplaysDataType", "-json"]))
|
||||
if gpu_cores is None:
|
||||
gpu_cores = _parse_apple_gpu_cores(_run(["system_profiler", "SPDisplaysDataType"]))
|
||||
|
||||
# Usable GPU budget. macOS lets Metal use most of unified memory, but the
|
||||
# default working-set limit scales with RAM: small machines have to keep
|
||||
# more back for the OS + app. These fractions track Apple's
|
||||
@@ -389,7 +357,7 @@ def _detect_apple_silicon():
|
||||
pass
|
||||
|
||||
gpu = {"index": 0, "name": brand, "vram_gb": vram_gb}
|
||||
info = {
|
||||
return {
|
||||
"gpu_name": brand,
|
||||
"gpu_vram_gb": vram_gb,
|
||||
"gpu_count": 1,
|
||||
@@ -401,9 +369,6 @@ def _detect_apple_silicon():
|
||||
# separate pool — downstream fit logic uses this to avoid double-budgeting.
|
||||
"unified_memory": True,
|
||||
}
|
||||
if gpu_cores is not None:
|
||||
info["gpu_cores"] = gpu_cores
|
||||
return info
|
||||
|
||||
|
||||
def _read_file(path):
|
||||
@@ -646,93 +611,6 @@ def _cache_key(host: str, ssh_port: str, platform_name: str):
|
||||
)
|
||||
|
||||
|
||||
def _is_containerized():
|
||||
"""Best-effort check for whether the local Odysseus process is running in a container."""
|
||||
if _remote_host:
|
||||
return False
|
||||
|
||||
if os.path.exists("/.dockerenv"):
|
||||
return True
|
||||
|
||||
try:
|
||||
with open("/proc/1/cgroup", encoding="utf-8", errors="replace") as f:
|
||||
text = f.read().lower()
|
||||
return any(marker in text for marker in ("docker", "containerd", "kubepods"))
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
|
||||
def _hardware_visibility_warning(result):
|
||||
"""Return a non-blocking UX warning when detected hardware may only be container-visible."""
|
||||
if not isinstance(result, dict):
|
||||
return None
|
||||
|
||||
if result.get("manual_hardware"):
|
||||
return None
|
||||
|
||||
if not result.get("containerized"):
|
||||
return None
|
||||
|
||||
if result.get("gpu_error"):
|
||||
return None
|
||||
|
||||
if not result.get("has_gpu"):
|
||||
return {
|
||||
"code": "container_no_gpu_visible",
|
||||
"severity": "warning",
|
||||
"title": "No GPU visible inside Docker",
|
||||
"message": (
|
||||
"Cookbook is scanning hardware from inside the Odysseus container. "
|
||||
"If your host has a GPU, Docker may not be exposing it to the container, "
|
||||
"so model recommendations may be CPU-only or too conservative."
|
||||
),
|
||||
"actions": [
|
||||
"manual_hardware",
|
||||
"rescan",
|
||||
"copy_diagnostics",
|
||||
],
|
||||
}
|
||||
|
||||
total_ram = result.get("total_ram_gb") or 0
|
||||
if total_ram and total_ram <= 8:
|
||||
return {
|
||||
"code": "container_low_ram_visible",
|
||||
"severity": "info",
|
||||
"title": "Container-visible RAM may be lower than host RAM",
|
||||
"message": (
|
||||
"Cookbook is seeing the RAM available inside the container. "
|
||||
"If your host has more memory, validate host RAM separately or use Manual Hardware."
|
||||
),
|
||||
"actions": [
|
||||
"manual_hardware",
|
||||
"rescan",
|
||||
"copy_diagnostics",
|
||||
],
|
||||
}
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def _attach_probe_context(result, host=""):
|
||||
"""Attach probe-scope metadata and optional hardware visibility warning."""
|
||||
if not isinstance(result, dict) or result.get("error"):
|
||||
return result
|
||||
|
||||
is_remote = bool(host)
|
||||
containerized = False if is_remote else _is_containerized()
|
||||
|
||||
result["probe_scope"] = "remote" if is_remote else ("container" if containerized else "native")
|
||||
result["containerized"] = containerized
|
||||
|
||||
warning = _hardware_visibility_warning(result)
|
||||
if warning:
|
||||
result["hardware_visibility_warning"] = warning
|
||||
else:
|
||||
result.pop("hardware_visibility_warning", None)
|
||||
|
||||
return result
|
||||
|
||||
|
||||
def detect_system(host="", ssh_port="", platform="", fresh=False):
|
||||
"""Detect system hardware: RAM, CPU, GPU. Cached per host (hardware rarely
|
||||
changes, and probing a remote host over SSH is slow). Pass fresh=True to
|
||||
@@ -757,7 +635,6 @@ def detect_system(host="", ssh_port="", platform="", fresh=False):
|
||||
if _remote_platform == "windows" and _remote_host:
|
||||
result = _detect_windows()
|
||||
if result:
|
||||
result = _attach_probe_context(result, host=host)
|
||||
_remote_host = None
|
||||
_remote_platform = None
|
||||
_cache_by_host[cache_key] = (now, result)
|
||||
@@ -776,7 +653,6 @@ def detect_system(host="", ssh_port="", platform="", fresh=False):
|
||||
if not _remote_host and os.name == "nt":
|
||||
result = _detect_windows()
|
||||
if result:
|
||||
result = _attach_probe_context(result, host=host)
|
||||
_cache_by_host[cache_key] = (now, result)
|
||||
return result
|
||||
# PowerShell probe failed entirely — fall through to the generic path
|
||||
@@ -807,7 +683,6 @@ def detect_system(host="", ssh_port="", platform="", fresh=False):
|
||||
"gpu_name": gpu_info["gpu_name"],
|
||||
"gpu_vram_gb": gpu_info["gpu_vram_gb"],
|
||||
"gpu_count": gpu_info["gpu_count"],
|
||||
"gpu_cores": gpu_info.get("gpu_cores"),
|
||||
"gpus": gpu_info.get("gpus", []),
|
||||
"gpu_groups": gpu_info.get("gpu_groups", []),
|
||||
"homogeneous": gpu_info.get("homogeneous", True),
|
||||
@@ -839,7 +714,6 @@ def detect_system(host="", ssh_port="", platform="", fresh=False):
|
||||
"gpu_error": _last_gpu_error,
|
||||
}
|
||||
|
||||
result = _attach_probe_context(result, host=host)
|
||||
_remote_host = None
|
||||
_remote_platform = None
|
||||
_cache_by_host[cache_key] = (now, result)
|
||||
|
||||
@@ -188,18 +188,12 @@ def compute_serve_profiles(system, model, serve_weights_gb=None, serve_quant=Non
|
||||
# Shrink context if even the chosen KV won't fit alongside weights.
|
||||
# Start from the smaller of the profile's target and the model's limit.
|
||||
cur_ctx = min(ctx, model_ctx_max)
|
||||
# Floor the context-shrink loop at 8192, but never above the model's own
|
||||
# trained limit. A model with a sub-8192 context (e.g. a 2048-token
|
||||
# SmolLM) starts below 8192, so a hard-coded 8192 guard skipped the loop
|
||||
# entirely and produced NO profile — the serve UI then fell back to
|
||||
# manual flags even though the model fits the GPU trivially.
|
||||
ctx_floor = min(8192, model_ctx_max)
|
||||
while cur_ctx >= ctx_floor:
|
||||
while cur_ctx >= 8192:
|
||||
kv = _kv_gb(model, cur_ctx, kv_type)
|
||||
n_cpu_moe, fits = _cpu_moe_for_budget(model, quant, kv, budget, fixed_gb=serve_weights_gb)
|
||||
est = _weights_gb(model, quant, serve_weights_gb) + kv + 0.6
|
||||
# If a non-MoE model can't fit even fully offloaded, try less context.
|
||||
if model.get("is_moe") or fits or cur_ctx <= ctx_floor:
|
||||
if model.get("is_moe") or fits or cur_ctx <= 8192:
|
||||
profiles.append({
|
||||
"key": key,
|
||||
"label": label,
|
||||
|
||||
@@ -66,57 +66,41 @@ def _has_duplicate_title(skills, title: str) -> bool:
|
||||
def _extract_json_object(text: str) -> Optional[dict]:
|
||||
"""Best-effort extraction of a JSON object from an LLM response.
|
||||
|
||||
The response may be wrapped in code fences or surrounded by prose. Uses
|
||||
json.JSONDecoder().raw_decode() to locate the boundaries of complete JSON
|
||||
objects starting at each '{' position. Nested objects are filtered out to
|
||||
keep only top-level candidates. If multiple non-overlapping valid JSON
|
||||
objects are found, it is treated as ambiguous and returns None. Otherwise,
|
||||
returns the single valid candidate dictionary.
|
||||
The response may be wrapped in code fences or surrounded by prose, and some
|
||||
models emit a stray brace in the prose before the real object
|
||||
(e.g. "uses {placeholder} then {...}"). Slicing first-'{' .. last-'}' then
|
||||
grabs an unparseable span and the skill is silently lost. Try the whole
|
||||
string first, then each '{' start position in turn, returning the first
|
||||
candidate that parses to a JSON object (dict). Returns None if none do.
|
||||
"""
|
||||
if not text:
|
||||
return None
|
||||
s = text.strip()
|
||||
if s.startswith("```"):
|
||||
s = s.split("\n", 1)[-1].rsplit("```", 1)[0].strip()
|
||||
end = s.rfind("}")
|
||||
if end == -1:
|
||||
return None
|
||||
|
||||
decoder = json.JSONDecoder()
|
||||
candidates = []
|
||||
|
||||
start = s.find("{")
|
||||
while start != -1:
|
||||
def _as_dict(candidate):
|
||||
try:
|
||||
obj, idx = decoder.raw_decode(s[start:])
|
||||
end_pos = start + idx
|
||||
if isinstance(obj, dict):
|
||||
candidates.append((start, end_pos, obj))
|
||||
obj = json.loads(candidate)
|
||||
except (json.JSONDecodeError, ValueError):
|
||||
pass
|
||||
return None
|
||||
return obj if isinstance(obj, dict) else None
|
||||
|
||||
# The clean, common case: the whole (de-fenced) string is the object.
|
||||
obj = _as_dict(s)
|
||||
if obj is not None:
|
||||
return obj
|
||||
# Otherwise scan each '{' candidate up to the last '}'.
|
||||
start = s.find("{")
|
||||
while 0 <= start < end:
|
||||
obj = _as_dict(s[start : end + 1])
|
||||
if obj is not None:
|
||||
return obj
|
||||
start = s.find("{", start + 1)
|
||||
|
||||
# Filter out nested candidates to identify top-level dictionaries
|
||||
top_level = []
|
||||
for c in candidates:
|
||||
is_nested = False
|
||||
for other in candidates:
|
||||
if other == c:
|
||||
continue
|
||||
if other[0] <= c[0] and c[1] <= other[1]:
|
||||
is_nested = True
|
||||
break
|
||||
if not is_nested:
|
||||
top_level.append(c)
|
||||
|
||||
if not top_level:
|
||||
return None
|
||||
|
||||
if len(top_level) > 1:
|
||||
logger.debug(
|
||||
"[skill-extract] Found multiple non-overlapping JSON objects: %s",
|
||||
[item[2].get("title") for item in top_level]
|
||||
)
|
||||
return None
|
||||
|
||||
return top_level[0][2]
|
||||
return None
|
||||
|
||||
|
||||
async def maybe_extract_skill(
|
||||
@@ -259,20 +243,6 @@ async def maybe_extract_skill(
|
||||
logger.debug("[skill-extract] '%s' already exists — dropped as duplicate", title)
|
||||
return None
|
||||
|
||||
# Auto-publish gate: if the user has `auto_approve_skills` on, the
|
||||
# newly-extracted skill is created `published` immediately rather
|
||||
# than waiting for the next audit batch. The audit still runs later
|
||||
# and can demote it back to `draft` (or delete) on failure. Default
|
||||
# ON matches the UI label "Auto-approve skills".
|
||||
_initial_status = "draft"
|
||||
try:
|
||||
from routes.prefs_routes import _load_for_user as _load_prefs
|
||||
_prefs = _load_prefs(owner) or {}
|
||||
if _prefs.get("auto_approve_skills", True):
|
||||
_initial_status = "published"
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
entry = skills_manager.add_skill(
|
||||
title=title,
|
||||
problem=data.get("problem", ""),
|
||||
@@ -283,7 +253,6 @@ async def maybe_extract_skill(
|
||||
confidence=data.get("confidence", 0.7),
|
||||
session_id=getattr(session, "session_id", None),
|
||||
owner=owner,
|
||||
status=_initial_status,
|
||||
)
|
||||
try:
|
||||
from src.event_bus import fire_event
|
||||
|
||||
@@ -603,6 +603,7 @@ class SkillsManager:
|
||||
escalation) — those are work-in-progress and pollute the
|
||||
prompt with half-finished procedures.
|
||||
"""
|
||||
active_toolsets = active_toolsets or []
|
||||
out = []
|
||||
for s in self.load(owner=owner):
|
||||
status = s.get("status")
|
||||
@@ -616,16 +617,13 @@ class SkillsManager:
|
||||
# Platform gating
|
||||
if platform and s.get("platforms") and platform not in s["platforms"]:
|
||||
continue
|
||||
# requires_toolsets: hide unless every required toolset is active.
|
||||
# active_toolsets=None means the caller doesn't know the active
|
||||
# set (API listings, chat preface) — don't gate in that case;
|
||||
# only an explicit list filters.
|
||||
# requires_toolsets: hide unless every required toolset is active
|
||||
req = s.get("requires_toolsets") or []
|
||||
if req and active_toolsets is not None and not all(t in active_toolsets for t in req):
|
||||
if req and not all(t in active_toolsets for t in req):
|
||||
continue
|
||||
# fallback_for_toolsets: hide when any of those toolsets is active
|
||||
fb = s.get("fallback_for_toolsets") or []
|
||||
if fb and active_toolsets and any(t in active_toolsets for t in fb):
|
||||
if fb and any(t in active_toolsets for t in fb):
|
||||
continue
|
||||
out.append({
|
||||
"name": s["name"],
|
||||
|
||||
@@ -285,7 +285,6 @@ class ResearchHandler:
|
||||
query, report, stats, elapsed,
|
||||
findings=researcher.findings,
|
||||
evolving_report=researcher.evolving_report,
|
||||
analyzed_urls=getattr(researcher, "analyzed_urls", None),
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
@@ -332,8 +331,7 @@ class ResearchHandler:
|
||||
|
||||
def _format_research_report(
|
||||
self, query: str, full_report: str, stats: dict, elapsed: float,
|
||||
findings: Optional[list] = None, evolving_report: Optional[str] = None,
|
||||
analyzed_urls: Optional[list] = None,
|
||||
findings: list = None, evolving_report: str = None,
|
||||
) -> str:
|
||||
"""Format research report with sources list and expandable raw findings."""
|
||||
summary_lines = [
|
||||
@@ -344,34 +342,20 @@ class ResearchHandler:
|
||||
]
|
||||
summary_text = " | ".join(summary_lines)
|
||||
|
||||
# Build sources list with clickable links. Keep the curated Sources
|
||||
# section filtered for citation quality, but also list every unique URL
|
||||
# the research run inspected so the "URLs Analyzed" count is auditable.
|
||||
# Build sources list with clickable links
|
||||
sources_section = ""
|
||||
analyzed_urls_section = ""
|
||||
url_items = analyzed_urls if analyzed_urls is not None else findings
|
||||
if findings or url_items:
|
||||
if findings:
|
||||
seen_urls = set()
|
||||
source_lines = []
|
||||
analyzed_seen = set()
|
||||
analyzed_lines = []
|
||||
for f in findings or []:
|
||||
for f in findings:
|
||||
url = f.get("url", "")
|
||||
title = f.get("title", "") or url
|
||||
summary = f.get("summary", "") or f.get("evidence", "")
|
||||
if url and url not in seen_urls and not is_low_quality(summary):
|
||||
seen_urls.add(url)
|
||||
source_lines.append(f"- [{title}]({url})")
|
||||
for item in url_items or []:
|
||||
url = item.get("url", "")
|
||||
title = item.get("title", "") or url
|
||||
if url and url not in analyzed_seen:
|
||||
analyzed_seen.add(url)
|
||||
analyzed_lines.append(f"{len(analyzed_lines) + 1}. [{title}]({url})")
|
||||
if source_lines:
|
||||
sources_section = "\n### Sources\n\n" + "\n".join(source_lines) + "\n"
|
||||
if analyzed_lines:
|
||||
analyzed_urls_section = "\n### Analyzed URLs\n\n" + "\n".join(analyzed_lines) + "\n"
|
||||
|
||||
# Build raw findings section (individual extractions per source)
|
||||
raw_findings_section = ""
|
||||
@@ -407,7 +391,6 @@ class ResearchHandler:
|
||||
{full_report}
|
||||
|
||||
{sources_section}
|
||||
{analyzed_urls_section}
|
||||
{collected_section}
|
||||
---
|
||||
|
||||
|
||||
+14
-197
@@ -15,8 +15,6 @@ from urllib.parse import urljoin, urlparse
|
||||
import httpx
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
from src.constants import WEB_FETCH_SOFT_MAX_BYTES, WEB_FETCH_HARD_MAX_BYTES, WEB_FETCH_USER_AGENT
|
||||
|
||||
from .analytics import RateLimitError, error_logger
|
||||
from .cache import (
|
||||
CONTENT_CACHE_DIR,
|
||||
@@ -91,128 +89,18 @@ def _public_http_url(url: str) -> bool:
|
||||
return False
|
||||
|
||||
|
||||
class BodyTooLargeError(Exception):
|
||||
"""The server declared a body larger than the hard fetch ceiling."""
|
||||
|
||||
def __init__(self, url: str, declared_bytes: int):
|
||||
self.url = url
|
||||
self.declared_bytes = declared_bytes
|
||||
super().__init__(
|
||||
f"response body is {declared_bytes:,} bytes, over the "
|
||||
f"{WEB_FETCH_HARD_MAX_BYTES:,}-byte hard cap"
|
||||
)
|
||||
|
||||
|
||||
class _CappedFetch:
|
||||
"""Result of a size-capped streaming GET.
|
||||
|
||||
Carries just what fetch_webpage_content needs from an httpx.Response,
|
||||
plus the cap bookkeeping: the (possibly truncated) body, whether the
|
||||
cap cut it short, and the size the server declared via Content-Length
|
||||
(wire bytes; None when absent).
|
||||
"""
|
||||
|
||||
__slots__ = ("status_code", "headers", "content", "truncated",
|
||||
"declared_bytes", "encoding", "url")
|
||||
|
||||
def __init__(self, status_code, headers, content, truncated,
|
||||
declared_bytes, encoding, url):
|
||||
self.status_code = status_code
|
||||
self.headers = headers
|
||||
self.content = content
|
||||
self.truncated = truncated
|
||||
self.declared_bytes = declared_bytes
|
||||
self.encoding = encoding
|
||||
self.url = url
|
||||
|
||||
@property
|
||||
def text(self) -> str:
|
||||
return self.content.decode(self.encoding or "utf-8", errors="replace")
|
||||
|
||||
def raise_for_status(self):
|
||||
if self.status_code >= 400:
|
||||
request = httpx.Request("GET", self.url)
|
||||
raise httpx.HTTPStatusError(
|
||||
f"HTTP {self.status_code} for {self.url}",
|
||||
request=request,
|
||||
response=httpx.Response(self.status_code, request=request),
|
||||
)
|
||||
|
||||
|
||||
def _get_public_url(url: str, headers: dict, timeout: int, max_redirects: int = 5,
|
||||
max_bytes: int = None) -> "_CappedFetch":
|
||||
"""Capped streaming GET with SSRF-guarded manual redirects.
|
||||
|
||||
The body is streamed and buffering stops at ``max_bytes`` (default: the
|
||||
soft cap), so an oversized resource cannot be pulled into memory or the
|
||||
content cache in full. When Content-Length already declares a body over
|
||||
the hard ceiling, the fetch is refused before any body bytes are read.
|
||||
"""
|
||||
cap = min(max_bytes or WEB_FETCH_SOFT_MAX_BYTES, WEB_FETCH_HARD_MAX_BYTES)
|
||||
def _get_public_url(url: str, headers: dict, timeout: int, max_redirects: int = 5) -> httpx.Response:
|
||||
current = url
|
||||
for _ in range(max_redirects + 1):
|
||||
if not _public_http_url(current):
|
||||
raise httpx.RequestError("Blocked private/internal URL", request=httpx.Request("GET", current))
|
||||
# Force identity transfer-encoding. With gzip/deflate the wire bytes
|
||||
# (and Content-Length) can be a small fraction of the decoded body, so
|
||||
# a tiny compressed response could pass the hard-cap preflight and then
|
||||
# expand past the ceiling in a single decoded chunk before the streamed
|
||||
# cap below can slice it. Identity makes Content-Length the true body
|
||||
# size and keeps each streamed chunk bounded by the network read.
|
||||
req_headers = dict(headers or {})
|
||||
req_headers["Accept-Encoding"] = "identity"
|
||||
with httpx.stream("GET", current, headers=req_headers, timeout=timeout,
|
||||
follow_redirects=False) as response:
|
||||
if response.status_code in (301, 302, 303, 307, 308):
|
||||
location = response.headers.get("location")
|
||||
if not location:
|
||||
return _CappedFetch(response.status_code, response.headers, b"",
|
||||
False, None, response.encoding, str(response.url))
|
||||
current = urljoin(str(response.url), location)
|
||||
continue
|
||||
|
||||
# A server can ignore the identity request and still return a
|
||||
# compressed body; httpx.iter_bytes would then decode it, and a tiny
|
||||
# gzip can balloon into one decoded chunk far past the cap before we
|
||||
# slice. Refuse a compressed Content-Encoding so the streamed cap
|
||||
# stays a real memory bound (Content-Length is the compressed wire
|
||||
# length here, so the preflight and size metadata are unreliable too).
|
||||
enc = (response.headers.get("content-encoding") or "").strip().lower()
|
||||
if enc and enc != "identity":
|
||||
raise httpx.RequestError(
|
||||
f"Refusing compressed response (Content-Encoding: {enc}) after "
|
||||
"requesting identity: cannot bound decoded body size",
|
||||
request=httpx.Request("GET", current),
|
||||
)
|
||||
|
||||
declared = None
|
||||
raw_len = response.headers.get("content-length")
|
||||
if raw_len and raw_len.isdigit():
|
||||
declared = int(raw_len)
|
||||
# Refuse before buffering anything when the server already tells
|
||||
# us the body exceeds the absolute ceiling (Content-Length is wire
|
||||
# bytes; the decompressed body can only be larger).
|
||||
if declared is not None and declared > WEB_FETCH_HARD_MAX_BYTES:
|
||||
raise BodyTooLargeError(current, declared)
|
||||
|
||||
chunks = []
|
||||
read = 0
|
||||
truncated = False
|
||||
# We requested identity above, so iter_bytes yields the raw body in
|
||||
# network-read-sized chunks (no decompression expansion); the cap
|
||||
# therefore bounds what we actually buffer.
|
||||
for chunk in response.iter_bytes():
|
||||
read += len(chunk)
|
||||
if read > cap:
|
||||
keep = cap - (read - len(chunk))
|
||||
if keep > 0:
|
||||
chunks.append(chunk[:keep])
|
||||
truncated = True
|
||||
break
|
||||
chunks.append(chunk)
|
||||
return _CappedFetch(response.status_code, response.headers,
|
||||
b"".join(chunks), truncated, declared,
|
||||
response.encoding, str(response.url))
|
||||
response = httpx.get(current, headers=headers, timeout=timeout, follow_redirects=False)
|
||||
if response.status_code not in (301, 302, 303, 307, 308):
|
||||
return response
|
||||
location = response.headers.get("location")
|
||||
if not location:
|
||||
return response
|
||||
current = urljoin(str(response.url), location)
|
||||
raise httpx.RequestError("Too many redirects", request=httpx.Request("GET", current))
|
||||
|
||||
# PDF extraction (optional dependency)
|
||||
@@ -334,19 +222,9 @@ def _empty_result(url: str, error: str = "") -> dict:
|
||||
# ----------------------------------------------------------------------
|
||||
# Main content fetcher
|
||||
# ----------------------------------------------------------------------
|
||||
def fetch_webpage_content(url: str, timeout: int = 5, retry_attempt: int = 0,
|
||||
max_bytes: int = None) -> dict:
|
||||
"""Fetch and extract meaningful content from a webpage with caching.
|
||||
|
||||
``max_bytes`` raises the download budget per call (clamped to the hard
|
||||
cap); the default is the soft cap. When the body is cut short the result
|
||||
carries ``truncated``/``fetched_bytes``/``total_bytes`` so callers can
|
||||
tell the model the content is partial (#3812).
|
||||
"""
|
||||
effective_cap = min(max_bytes or WEB_FETCH_SOFT_MAX_BYTES, WEB_FETCH_HARD_MAX_BYTES)
|
||||
# The cap is part of the cache identity: a truncated soft-cap fetch must
|
||||
# not be served to a later full-budget request for the same URL.
|
||||
cache_key = generate_cache_key(f"{url}#cap={effective_cap}")
|
||||
def fetch_webpage_content(url: str, timeout: int = 5, retry_attempt: int = 0) -> dict:
|
||||
"""Fetch and extract meaningful content from a webpage with caching."""
|
||||
cache_key = generate_cache_key(url)
|
||||
cache_file = CONTENT_CACHE_DIR / f"{cache_key}.cache"
|
||||
|
||||
# Check cache
|
||||
@@ -369,24 +247,18 @@ def fetch_webpage_content(url: str, timeout: int = 5, retry_attempt: int = 0,
|
||||
# Fetch
|
||||
try:
|
||||
headers = {
|
||||
"User-Agent": WEB_FETCH_USER_AGENT,
|
||||
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
|
||||
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
|
||||
"Accept-Language": "en-US,en;q=0.5",
|
||||
# identity so the streamed size cap in _get_public_url stays honest
|
||||
# (a compressed body can decode to far more than Content-Length).
|
||||
"Accept-Encoding": "identity",
|
||||
"Accept-Encoding": "gzip, deflate",
|
||||
"Connection": "keep-alive",
|
||||
}
|
||||
response = _get_public_url(url, headers=headers, timeout=timeout,
|
||||
max_bytes=effective_cap)
|
||||
response = _get_public_url(url, headers=headers, timeout=timeout)
|
||||
|
||||
if response.status_code == 429:
|
||||
raise RateLimitError(f"Rate limit hit for {url} (attempt {retry_attempt})")
|
||||
|
||||
response.raise_for_status()
|
||||
except BodyTooLargeError as e:
|
||||
error_logger.warning(f"Refused oversized body for {url}: {e}")
|
||||
return _empty_result(url, f"TooLarge: {e}")
|
||||
except httpx.HTTPStatusError as e:
|
||||
error_logger.warning(f"HTTP {e.response.status_code} fetching {url}: {e}")
|
||||
return _empty_result(url, f"HTTP {e.response.status_code}: {e}")
|
||||
@@ -397,27 +269,9 @@ def fetch_webpage_content(url: str, timeout: int = 5, retry_attempt: int = 0,
|
||||
error_logger.error(str(e))
|
||||
return _empty_result(url, str(e))
|
||||
|
||||
# Size bookkeeping shared by every content branch below. getattr keeps
|
||||
# plain httpx.Response stand-ins (tests) working without the cap fields.
|
||||
_size_fields = {
|
||||
"truncated": getattr(response, "truncated", False),
|
||||
"fetched_bytes": len(response.content),
|
||||
"total_bytes": getattr(response, "declared_bytes", None),
|
||||
}
|
||||
|
||||
# PDF handling
|
||||
content_type = response.headers.get("Content-Type", "").lower()
|
||||
if "application/pdf" in content_type or url.lower().endswith(".pdf"):
|
||||
if _size_fields["truncated"]:
|
||||
# A PDF cut mid-stream is not parseable; unlike text there is no
|
||||
# useful partial result, so report the budget problem instead.
|
||||
_declared = _size_fields["total_bytes"]
|
||||
return _empty_result(
|
||||
url,
|
||||
f"TooLarge: PDF exceeds the {effective_cap:,}-byte fetch budget"
|
||||
+ (f" (size {_declared:,} bytes)" if _declared else "")
|
||||
+ "; retry with a larger budget if it fits under the hard cap",
|
||||
)
|
||||
if pdf_extract_text is None:
|
||||
logger.error("pdfminer.six is not installed; cannot extract PDF text.")
|
||||
pdf_text = ""
|
||||
@@ -441,42 +295,6 @@ def fetch_webpage_content(url: str, timeout: int = 5, retry_attempt: int = 0,
|
||||
"js_message": "",
|
||||
"success": bool(pdf_text),
|
||||
"error": "" if pdf_text else "Failed to extract PDF text",
|
||||
**_size_fields,
|
||||
}
|
||||
_cache_result(cache_file, cache_key, result, url)
|
||||
return result
|
||||
|
||||
# Plain-text / Markdown / JSON handling. Sources like
|
||||
# raw.githubusercontent.com serve Markdown as `text/plain`, JSON APIs and
|
||||
# raw config files serve `application/json`, and a lot of code and tool
|
||||
# docs live in `.md` / `.txt`. These have no HTML structure, so the HTML
|
||||
# branch below would extract nothing and report "no readable text content".
|
||||
# Return the body verbatim instead. The `is_html` guard keeps real HTML
|
||||
# (including `application/xhtml+xml`) on the parsing path; the `json` check
|
||||
# covers `application/json` and `+json` suffixes; the URL-suffix fallback
|
||||
# catches servers that mislabel text files as `application/octet-stream`.
|
||||
is_html = "html" in content_type
|
||||
is_json = "json" in content_type
|
||||
url_path = url.lower().split("?", 1)[0].split("#", 1)[0]
|
||||
looks_like_text_file = url_path.endswith(
|
||||
(".md", ".markdown", ".txt", ".text", ".json", ".jsonl")
|
||||
)
|
||||
if not is_html and (content_type.startswith("text/") or is_json or looks_like_text_file):
|
||||
text_body = (response.text or "").strip()
|
||||
result = {
|
||||
"url": url,
|
||||
"title": os.path.basename(url_path) or url,
|
||||
"content": text_body,
|
||||
"lists": [],
|
||||
"tables": [],
|
||||
"code_blocks": [],
|
||||
"meta_description": "",
|
||||
"meta_keywords": "",
|
||||
"js_rendered": False,
|
||||
"js_message": "",
|
||||
"success": bool(text_body),
|
||||
"error": "" if text_body else "Empty response body",
|
||||
**_size_fields,
|
||||
}
|
||||
_cache_result(cache_file, cache_key, result, url)
|
||||
return result
|
||||
@@ -539,7 +357,6 @@ def fetch_webpage_content(url: str, timeout: int = 5, retry_attempt: int = 0,
|
||||
"js_message": js_message,
|
||||
"success": True,
|
||||
"error": "",
|
||||
**_size_fields,
|
||||
}
|
||||
_cache_result(cache_file, cache_key, result, url)
|
||||
return result
|
||||
|
||||
@@ -9,12 +9,14 @@ from urllib.parse import urljoin, urlparse, parse_qs
|
||||
import httpx
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
from src.constants import SEARXNG_INSTANCE, REQUEST_TIMEOUT, WEB_FETCH_USER_AGENT
|
||||
from src.constants import SEARXNG_INSTANCE
|
||||
from .analytics import RateLimitError, error_logger
|
||||
from .query import build_enhanced_query
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
REQUEST_TIMEOUT = 20
|
||||
|
||||
# Provider registry — maps setting value to (label, needs_key, needs_url)
|
||||
PROVIDER_INFO = {
|
||||
"searxng": ("SearXNG", False, True),
|
||||
@@ -132,13 +134,12 @@ _NEWS_HINTS = ("news", "nyheter", "headlines", "breaking", "latest", "today", "i
|
||||
_GENERAL_ENGINES = os.environ.get("SEARXNG_GENERAL_ENGINES", "bing,mojeek,presearch")
|
||||
|
||||
|
||||
def searxng_search_api(query: str, count: Optional[int] = None, categories: str = "general",
|
||||
def searxng_search_api(query: str, count: int = 10, categories: str = "general",
|
||||
time_filter: Optional[str] = None) -> List[dict]:
|
||||
"""Search using SearXNG JSON API. Returns list of {title, url, snippet}."""
|
||||
count = count if count is not None else _get_result_count()
|
||||
instance = _get_search_instance()
|
||||
api_key = ""
|
||||
headers = {"User-Agent": WEB_FETCH_USER_AGENT}
|
||||
headers = {"User-Agent": "Mozilla/5.0"}
|
||||
if api_key:
|
||||
headers["Authorization"] = f"Bearer {api_key}"
|
||||
# News/fresh queries do badly in the 'general' category — it favours
|
||||
@@ -250,7 +251,7 @@ def searxng_search(query, max_results=10):
|
||||
"""Search using SearXNG instance - parsing HTML."""
|
||||
instance = _get_search_instance()
|
||||
api_key = ""
|
||||
req_headers = {"User-Agent": WEB_FETCH_USER_AGENT}
|
||||
req_headers = {"User-Agent": "Mozilla/5.0"}
|
||||
if api_key:
|
||||
req_headers["Authorization"] = f"Bearer {api_key}"
|
||||
try:
|
||||
@@ -281,9 +282,8 @@ def searxng_search(query, max_results=10):
|
||||
|
||||
# ── Brave ──
|
||||
|
||||
def brave_search(query: str, count: Optional[int] = None, time_filter: Optional[str] = None) -> List[dict]:
|
||||
def brave_search(query: str, count: int = 10, time_filter: Optional[str] = None) -> List[dict]:
|
||||
"""Search using Brave API with key from admin settings or env var."""
|
||||
count = count if count is not None else _get_result_count()
|
||||
api_key = _get_provider_key("brave") or os.environ.get("DATA_BRAVE_API_KEY") or ""
|
||||
return _brave_search_impl(query, count, time_filter, search_config={"brave_api_key": api_key})
|
||||
|
||||
@@ -381,15 +381,15 @@ def _resolve_ddg_redirect(raw: str) -> str:
|
||||
return resolved
|
||||
|
||||
|
||||
def duckduckgo_search(query: str, count: Optional[int] = None, time_filter: Optional[str] = None) -> List[dict]:
|
||||
def duckduckgo_search(query: str, count: int = 10, time_filter: Optional[str] = None) -> List[dict]:
|
||||
"""Search using DuckDuckGo via the duckduckgo-search library. No API key needed."""
|
||||
count = count if count is not None else _get_result_count()
|
||||
|
||||
def _html_fallback() -> List[dict]:
|
||||
try:
|
||||
response = httpx.get(
|
||||
"https://html.duckduckgo.com/html/",
|
||||
params={"q": query, "kp": _safesearch_for("duckduckgo_html")},
|
||||
headers={"User-Agent": WEB_FETCH_USER_AGENT},
|
||||
headers={"User-Agent": "Mozilla/5.0"},
|
||||
timeout=REQUEST_TIMEOUT,
|
||||
)
|
||||
response.raise_for_status()
|
||||
@@ -415,7 +415,7 @@ def duckduckgo_search(query: str, count: Optional[int] = None, time_filter: Opti
|
||||
return []
|
||||
|
||||
try:
|
||||
from ddgs import DDGS
|
||||
from duckduckgo_search import DDGS
|
||||
except ImportError:
|
||||
logger.warning("duckduckgo-search package not installed; using HTML fallback")
|
||||
return _html_fallback()
|
||||
@@ -452,7 +452,7 @@ def duckduckgo_search(query: str, count: Optional[int] = None, time_filter: Opti
|
||||
|
||||
# ── Google Programmable Search Engine ──
|
||||
|
||||
def google_pse_search(query: str, count: Optional[int] = None, time_filter: Optional[str] = None) -> List[dict]:
|
||||
def google_pse_search(query: str, count: int = 10, time_filter: Optional[str] = None) -> List[dict]:
|
||||
"""Search using Google PSE (Custom Search JSON API).
|
||||
|
||||
Requires two keys in settings:
|
||||
@@ -460,7 +460,6 @@ def google_pse_search(query: str, count: Optional[int] = None, time_filter: Opti
|
||||
- google_pse_cx: Programmable Search Engine ID (cx)
|
||||
Or env vars GOOGLE_API_KEY and GOOGLE_PSE_CX.
|
||||
"""
|
||||
count = count if count is not None else _get_result_count()
|
||||
settings = _get_search_settings()
|
||||
api_key = _get_provider_key("google_pse") or os.environ.get("GOOGLE_API_KEY", "")
|
||||
cx = (settings.get("google_pse_cx") or "").strip() or os.environ.get("GOOGLE_PSE_CX", "")
|
||||
@@ -523,9 +522,8 @@ def google_pse_search(query: str, count: Optional[int] = None, time_filter: Opti
|
||||
|
||||
# ── Tavily ──
|
||||
|
||||
def tavily_search(query: str, count: Optional[int] = None, time_filter: Optional[str] = None) -> List[dict]:
|
||||
def tavily_search(query: str, count: int = 10, time_filter: Optional[str] = None) -> List[dict]:
|
||||
"""Search using Tavily API. Requires search_api_key or TAVILY_API_KEY env var."""
|
||||
count = count if count is not None else _get_result_count()
|
||||
api_key = _get_provider_key("tavily") or os.environ.get("TAVILY_API_KEY", "")
|
||||
if not api_key:
|
||||
logger.warning("Tavily: no API key configured")
|
||||
@@ -582,9 +580,8 @@ def tavily_search(query: str, count: Optional[int] = None, time_filter: Optional
|
||||
|
||||
# ── Serper.dev ──
|
||||
|
||||
def serper_search(query: str, count: Optional[int] = None, time_filter: Optional[str] = None) -> List[dict]:
|
||||
def serper_search(query: str, count: int = 10, time_filter: Optional[str] = None) -> List[dict]:
|
||||
"""Search using Serper.dev API. Requires search_api_key or SERPER_API_KEY env var."""
|
||||
count = count if count is not None else _get_result_count()
|
||||
api_key = _get_provider_key("serper") or os.environ.get("SERPER_API_KEY", "")
|
||||
if not api_key:
|
||||
logger.warning("Serper: no API key configured")
|
||||
|
||||
@@ -64,40 +64,20 @@ def is_youtube_url(url: str) -> bool:
|
||||
return "youtube.com" in url or "youtu.be" in url
|
||||
|
||||
|
||||
# youtube.com-shaped hosts. music.youtube.com serves the same /watch and
|
||||
# /shorts paths, so links shared from YouTube Music must resolve too.
|
||||
_YT_HOSTS = ("www.youtube.com", "youtube.com", "m.youtube.com", "music.youtube.com")
|
||||
# Path prefixes whose first following segment is the video id. Covers the
|
||||
# /embed/ player, Shorts (/shorts/), live streams (/live/), and the legacy
|
||||
# /v/ embed — all of which `is_youtube_url` already treats as YouTube, so
|
||||
# they must be extractable or the link is silently dropped (neither web-fetched
|
||||
# nor transcript-fetched) by the chat pipeline.
|
||||
_YT_PATH_PREFIXES = ("/embed/", "/shorts/", "/live/", "/v/")
|
||||
|
||||
|
||||
def extract_youtube_id(url: str) -> Optional[str]:
|
||||
"""Extract a YouTube video ID from the common URL shapes:
|
||||
watch?v=, youtu.be/<id>, /embed/<id>, /shorts/<id>, /live/<id>, /v/<id>,
|
||||
across youtube.com / m.youtube.com / music.youtube.com / youtu.be."""
|
||||
"""Extract YouTube video ID from various URL formats."""
|
||||
if not isinstance(url, str):
|
||||
return None
|
||||
parsed = urllib.parse.urlparse(url)
|
||||
host = (parsed.hostname or "").lower()
|
||||
if host in _YT_HOSTS:
|
||||
if parsed.hostname in ("www.youtube.com", "youtube.com", "m.youtube.com"):
|
||||
if parsed.path == "/watch":
|
||||
params = urllib.parse.parse_qs(parsed.query)
|
||||
if params.get("v"):
|
||||
if "v" in params:
|
||||
return params["v"][0]
|
||||
else:
|
||||
for prefix in _YT_PATH_PREFIXES:
|
||||
if parsed.path.startswith(prefix):
|
||||
vid = parsed.path[len(prefix):].split("/")[0]
|
||||
if vid:
|
||||
return vid
|
||||
elif host == "youtu.be":
|
||||
vid = parsed.path.lstrip("/").split("/")[0]
|
||||
if vid:
|
||||
return vid
|
||||
elif parsed.path.startswith("/embed/"):
|
||||
return parsed.path.split("/")[-1]
|
||||
elif parsed.hostname == "youtu.be":
|
||||
return parsed.path[1:]
|
||||
return None
|
||||
|
||||
|
||||
@@ -190,8 +170,6 @@ def format_transcript_for_context(
|
||||
if segments:
|
||||
ctx += "Timestamped Transcript:\n"
|
||||
for seg in segments:
|
||||
if not isinstance(seg, dict):
|
||||
continue
|
||||
ctx += f"[{seg['timestamp']}] {seg['text']}\n"
|
||||
# Check length — fall back to plain text if too long
|
||||
if len(ctx) > 12000:
|
||||
@@ -224,24 +202,15 @@ async def fetch_youtube_comments(
|
||||
f"https://www.youtube.com/watch?v={video_id}",
|
||||
]
|
||||
|
||||
proc = await asyncio.create_subprocess_exec(
|
||||
*cmd,
|
||||
stdout=asyncio.subprocess.PIPE,
|
||||
stderr=asyncio.subprocess.PIPE,
|
||||
proc = await asyncio.wait_for(
|
||||
asyncio.create_subprocess_exec(
|
||||
*cmd,
|
||||
stdout=asyncio.subprocess.PIPE,
|
||||
stderr=asyncio.subprocess.PIPE,
|
||||
),
|
||||
timeout=timeout,
|
||||
)
|
||||
# Bound the wait on the process actually finishing, not on spawning it.
|
||||
# create_subprocess_exec returns as soon as the child starts, so wrapping
|
||||
# it in wait_for never enforces the timeout — proc.communicate() is the
|
||||
# blocking step. Kill and reap the child if it overruns so it does not
|
||||
# linger after we return.
|
||||
try:
|
||||
stdout, stderr = await asyncio.wait_for(
|
||||
proc.communicate(), timeout=timeout
|
||||
)
|
||||
except asyncio.TimeoutError:
|
||||
proc.kill()
|
||||
await proc.wait()
|
||||
raise
|
||||
stdout, stderr = await proc.communicate()
|
||||
|
||||
if proc.returncode != 0:
|
||||
return {"success": False, "error": f"yt-dlp failed: {stderr.decode()[:200]}", "comments": []}
|
||||
|
||||
@@ -91,9 +91,6 @@ _ROUTING_PATTERNS: tuple[tuple[str, str, Pattern[str]], ...] = tuple(
|
||||
("ui", "tool or feature toggle request", r"\b(?:disable|enable|turn\s+(?:on|off))\s+(?:the\s+)?(?:shell|search|web|browser|documents?|memory|skills|images?|calendar|email|mail|research|incognito)\b"),
|
||||
|
||||
# Deep research jobs, not quick conceptual mentions of research.
|
||||
("web", "explicit web search request", rf"{_PLEASE}(?:do|run|use|perform|make)\s+(?:a\s+)?(?:web\s+search|search\s+the\s+web)\b.+"),
|
||||
("web", "web lookup imperative request", rf"{_PLEASE}(?:web\s+search|search\s+the\s+web|search\s+online|look\s+up|google)\b.+"),
|
||||
("web", "assistant web lookup request", rf"{_ACTION_QUESTION}(?:web\s+search|search\s+the\s+web|search\s+online|look\s+up|google)\b.+"),
|
||||
("research", "deep research imperative request", rf"{_PLEASE}(?:research|deep\s+dive|look\s+into|investigate)\s+.+"),
|
||||
("research", "assistant deep research request", rf"{_ACTION_QUESTION}(?:research|do\s+research|deep\s+dive|look\s+into|investigate)\s+.+"),
|
||||
|
||||
|
||||
+69
-548
@@ -21,7 +21,7 @@ from src.settings import get_setting
|
||||
from src.prompt_security import untrusted_context_message
|
||||
from src.tool_security import blocked_tools_for_owner, plan_mode_disabled_tools
|
||||
from src.tool_policy import GUIDE_ONLY_DIRECTIVE, ToolPolicy
|
||||
from src.tool_utils import _truncate, get_mcp_manager
|
||||
from src.tool_utils import get_mcp_manager
|
||||
from src.agent_tools import (
|
||||
parse_tool_blocks,
|
||||
strip_tool_blocks,
|
||||
@@ -172,126 +172,6 @@ _API_AGENT_RULES = """\
|
||||
- After `create_session` returns id `89effa28`: "Created [New Chat](#session-89effa28) — click to switch."
|
||||
- Listing sessions: "1. [Big Chat](#session-abc123) — 2h ago, 2. [Code Review](#session-def456) — 5h ago\""""
|
||||
|
||||
_AGENT_PREAMBLE = """\
|
||||
You are an AI assistant with tool access. Only the tools listed below are available for this turn.
|
||||
To use a tool, write a fenced code block with the tool name as the language tag. The block executes automatically and you see the output."""
|
||||
|
||||
_AGENT_RULES = """\
|
||||
## Base rules
|
||||
- Only use tools when needed. For casual messages like "test", "yo", "thanks", answer normally.
|
||||
- If a needed tool/domain is missing from this turn, say what is missing briefly instead of pretending.
|
||||
- After a tool succeeds, do not second-guess it; reply with one short confirmation unless more work remains.
|
||||
- After a tool fails, retry with a concrete fix or state what is blocking you.
|
||||
- Finish only when the user's concrete request is actually done, or clearly state that you are blocked.
|
||||
- User identity facts/preferences ("my name is X", "call me X", "I live in X") use `manage_memory`, not contacts.
|
||||
"""
|
||||
|
||||
_API_AGENT_RULES = """\
|
||||
## Base rules
|
||||
- Prefer native tool/function calling when tools are needed.
|
||||
- Only call tools when they materially help answer the request. For casual messages like "test", "yo", "thanks", answer normally.
|
||||
- You MUST use tools to take action; do not claim you did something without a tool result.
|
||||
- If a needed tool/domain is missing from this turn, say what is missing briefly instead of pretending.
|
||||
- Keep answers concise unless the user asks for depth.
|
||||
- After a tool succeeds, do not second-guess it; reply with one short confirmation unless more work remains.
|
||||
- After a tool fails, retry with a concrete fix or state what is blocking you.
|
||||
- Finish only when the user's concrete request is actually done, or clearly state that you are blocked.
|
||||
- User identity facts/preferences ("my name is X", "call me X", "I live in X") use `manage_memory`, not contacts.
|
||||
"""
|
||||
|
||||
_LINK_RULES = """\
|
||||
## Link conventions
|
||||
When referencing app entities by id, use clickable markdown anchors:
|
||||
- Sessions: `[Name](#session-<id>)`
|
||||
- Documents: `[Title](#document-<id>)`
|
||||
- Notes: `[Title](#note-<id>)`
|
||||
- Emails: `[Subject](#email-<uid>)`
|
||||
- Calendar events: `[Summary](#event-<uid>)`
|
||||
- Tasks: `[Task name](#task-<id>)`
|
||||
- Skills: `[skill-name](#skill-<name>)`
|
||||
- Research jobs: `[Topic](#research-<session_id>)`
|
||||
"""
|
||||
|
||||
_DOMAIN_RULES = {
|
||||
"web": """\
|
||||
## Web rules
|
||||
- For web lookup/search/latest/current requests, use `web_search` or `web_fetch`.
|
||||
- Do not use shell, Python, curl, requests, or scraping code for web lookup unless web tools are unavailable or already failed.
|
||||
- "Research X" means `trigger_research`, not a one-off `web_search`, unless the user explicitly asks for a quick lookup.""",
|
||||
"documents": """\
|
||||
## Document rules
|
||||
- For long code/content (>15 lines), use `create_document` instead of pasting into chat.
|
||||
- If an active document is open, "fix this", "add X", "change Y", etc. usually refers to that document.
|
||||
- Use `edit_document` for targeted changes. Use `update_document` only for genuine full rewrites.
|
||||
- For feedback/review/suggestions on an open document, use `suggest_document`.""",
|
||||
"email": """\
|
||||
## Email rules
|
||||
- Email UIDs are the values after `UID:` in tool output, never list row numbers.
|
||||
- For latest/newest email, list with `max_results: 1`, `unread_only: false`, then read the returned UID if needed.
|
||||
- For named mailboxes/accounts, call `list_email_accounts` if needed and pass the exact `account` value.
|
||||
- Bulk email actions use `bulk_email` once with explicit UIDs; do not loop one message at a time.
|
||||
- "Open/start a reply" means open a draft via `ui_control open_email_reply`; only `reply_to_email` when the user clearly wants to send now.""",
|
||||
"cookbook": """\
|
||||
## Cookbook/model-serving rules
|
||||
- Cookbook is the LLM-serving subsystem.
|
||||
- "What's running/serving" starts with `list_served_models`. "What's downloading" uses `list_downloads`.
|
||||
- Launch known models by checking `list_serve_presets` before raw `serve_model`.
|
||||
- Downloads/serves run on a Cookbook server; pass the named `host` when the user names one.
|
||||
- Do not launch model servers manually with bash/ssh/tmux. Use `serve_model`/`serve_preset` so the UI can track and stop them.
|
||||
- After a successful serve, verify with `list_served_models`; if an external server is running but invisible, use `adopt_served_model`.""",
|
||||
"notes_calendar_tasks": """\
|
||||
## Notes/calendar/tasks rules
|
||||
- Notes/todos/reminders use `manage_notes`, not memory.
|
||||
- Calendar create/update/delete should call `manage_calendar` with `action=list_calendars` first.
|
||||
- Recurring/automatic/scheduled requests create a `manage_tasks` task; do not just perform the action once.""",
|
||||
"ui": """\
|
||||
## UI rules
|
||||
- "Open/show <panel>" uses `ui_control open_panel <name>`.
|
||||
- Tool toggles like "turn off shell/search/research" use `ui_control toggle <name> <on|off>`, not memory.""",
|
||||
"sessions": """\
|
||||
## Chat/session rules
|
||||
- Odysseus chats are sessions. Use `list_sessions`/`manage_session`; do not shell out looking for chat files.
|
||||
- Preserve clickable session links from tool output in your final answer.""",
|
||||
"files": """\
|
||||
## File rules
|
||||
- Use file tools for real disk files. Use document tools only for editor documents.
|
||||
- Prefer `grep`, `glob`, and `ls` over shell equivalents when available.
|
||||
- Use `edit_file`/`write_file` for writes; avoid shell redirection/heredocs for editing files.""",
|
||||
"settings": """\
|
||||
## Settings/API rules
|
||||
- Use `manage_settings` for preferences and tool enable/disable.
|
||||
- Use named tools over `app_api` when a named wrapper exists.
|
||||
- `app_api` is only for safe UI/API actions without a named tool; do not use it for shell, package installs, engine rebuilds, or sensitive auth/admin paths.""",
|
||||
"contacts": """\
|
||||
## Contacts rules
|
||||
- Use `resolve_contact` to look up a contact's email or phone number by name. Searches the CardDAV address book and sent email history.
|
||||
- Use `manage_contact` to list, add, update, or delete contacts in the address book.
|
||||
- Do NOT use `manage_memory` for contact lookups — contact details live in the address book, not memory.""",
|
||||
}
|
||||
|
||||
_DOMAIN_TOOL_MAP = {
|
||||
"web": {"web_search", "web_fetch", "trigger_research", "manage_research"},
|
||||
"documents": {"create_document", "edit_document", "update_document", "suggest_document", "manage_documents"},
|
||||
"email": {"list_email_accounts", "list_emails", "read_email", "send_email", "reply_to_email", "bulk_email", "archive_email", "delete_email", "mark_email_read", "resolve_contact", "manage_contact"},
|
||||
"cookbook": {"download_model", "serve_model", "serve_preset", "list_serve_presets", "list_served_models", "stop_served_model", "tail_serve_output", "list_downloads", "cancel_download", "search_hf_models", "list_cached_models", "list_cookbook_servers", "adopt_served_model"},
|
||||
"notes_calendar_tasks": {"manage_notes", "manage_calendar", "manage_tasks"},
|
||||
"ui": {"ui_control"},
|
||||
"sessions": {"create_session", "list_sessions", "manage_session", "send_to_session", "search_chats"},
|
||||
"files": {"bash", "python", "read_file", "write_file", "edit_file", "grep", "glob", "ls", "get_workspace"},
|
||||
"settings": {"manage_settings", "manage_endpoints", "manage_mcp", "manage_webhooks", "manage_tokens", "app_api"},
|
||||
"contacts": {"resolve_contact", "manage_contact"},
|
||||
}
|
||||
|
||||
def _domain_rules_for_tools(tool_names: set) -> list[str]:
|
||||
names = set(tool_names or set())
|
||||
rules = []
|
||||
for domain, domain_tools in _DOMAIN_TOOL_MAP.items():
|
||||
if names & domain_tools:
|
||||
rules.append(_DOMAIN_RULES[domain])
|
||||
if names & {"create_session", "list_sessions", "manage_session", "manage_documents", "manage_notes", "manage_calendar", "manage_tasks", "manage_skills", "manage_research"}:
|
||||
rules.append(_LINK_RULES)
|
||||
return rules
|
||||
|
||||
# Each tool section is keyed by tool name(s) it covers.
|
||||
# Sections with multiple tools use a tuple key.
|
||||
TOOL_SECTIONS = {
|
||||
@@ -315,7 +195,6 @@ NEVER pipe multi-line Python through `python -c "..."` — shell quoting eats re
|
||||
<python code>
|
||||
```
|
||||
Execute Python code. Use for computation, data processing, scripting. NOT for writing code for the user (use create_document for that). Same sandbox limits as bash — no TTY, no GUI, no `input()`; for anything the user should interact with, generate a single HTML file with inline JS instead.
|
||||
Prefer a dedicated tool whenever one fits the job (reading, searching, or writing files); use python only for computation/processing no dedicated tool covers - not for reading or writing files.
|
||||
Do NOT use Python/requests for web lookup/search/latest/current requests when `web_search` or `web_fetch` is available.""",
|
||||
|
||||
"web_search": """\
|
||||
@@ -354,11 +233,6 @@ Write content to a file. First line is the path, rest is the content.""",
|
||||
```
|
||||
Edit an EXISTING file by exact string replacement. PREFER this over bash (sed/echo/redirects) for changing files — it shows a before/after diff. `old_string` must match the file exactly and be unique unless `replace_all` is true. Use write_file to create a new file.""",
|
||||
|
||||
"get_workspace": """\
|
||||
```get_workspace
|
||||
```
|
||||
Return the absolute path of the active workspace folder. File tools are CONFINED to it (paths can be RELATIVE to it); the shell starts there (cwd) but is NOT sandboxed. Call this first when the user says "the project"/"the code"/"this folder" without a path, instead of asking them. No arguments.""",
|
||||
|
||||
"create_document": """\
|
||||
```create_document
|
||||
<title>
|
||||
@@ -408,7 +282,7 @@ Generate an image. Line 1 = description, line 2 = model name, line 3 = WxH (e.g.
|
||||
"ask_teacher": "- ```ask_teacher``` — Escalate a hard question to a more capable model. Line 1 = model name or 'auto', rest = the question. Use when stuck or need expert knowledge.",
|
||||
"list_models": "- ```list_models``` — Show all available AI models across all endpoints. Use when user asks what models are available.",
|
||||
"manage_session": "- ```manage_session``` — Rename, archive, delete, fork, switch, or `list` chats (the UI calls them 'chats'; 'session' is internal). Line 1 = action (list/switch/rename/archive/unarchive/delete/important/unimportant/truncate/fork), Line 2 = exact chat id from `list_sessions` (or `current` where supported). For delete/archive/truncate, always list first and reuse the exact id; never invent placeholder ids. `switch`/`open` returns a clickable anchor link the user can tap to open the chat — use for \"open my X chat\".",
|
||||
"manage_memory": "- ```manage_memory``` — Manage the user's persistent memory (facts about the USER themselves, their preferences, context that persists across chats). Line 1 = action (list/add/edit/delete/search), rest = content. Use when user says 'remember this' about themselves, states identity facts like 'my name is <name>' / 'call me <name>' / 'I live in <place>', or asks about stored memories. DO NOT use for info about another person (their address, phone, email, birthday) — that goes in `manage_contact`. If the user pastes an address/phone with a name and says 'save this for <person>', use `manage_contact add` with the address arg, NOT manage_memory.",
|
||||
"manage_memory": "- ```manage_memory``` — Manage the user's persistent memory (facts, identity, preferences, context that persists across chats). Line 1 = action (list/add/edit/delete/search), rest = content. Use when user says 'remember this', states identity facts like 'my name is <name>' / 'call me <name>' / 'I live in <place>', or asks about stored memories.",
|
||||
"manage_skills": "- ```manage_skills``` — Skill registry (SKILL.md format). Args (JSON): {\"action\": \"list|view|view_ref|search|add|edit|patch|publish|delete\", ...}. `list` returns the index of available skills (published + teacher-escalation drafts); `view name=foo` fetches the full SKILL.md; `view_ref name=foo path=...` loads a reference file under the skill directory. For `add`, provide an explicit kebab-case `name` and only report the exact returned name, because storage may normalize or dedupe it. Use this BEFORE doing domain work — there may already be a procedure (published or draft) that prescribes the correct steps. Drafts written by the teacher loop are authoritative guidance even though they're not yet published.",
|
||||
"manage_tasks": "- ```manage_tasks``` — Create and manage scheduled background tasks (recurring AI jobs). Args (JSON): {\"action\": \"list|create|edit|delete|pause|resume|run\", ...}",
|
||||
"manage_endpoints": "- ```manage_endpoints``` — Add, remove, or configure AI model API endpoints. Args (JSON): {\"action\": \"list|add|delete|enable|disable\", ...}. Use when user wants to add a new AI provider.",
|
||||
@@ -428,9 +302,7 @@ Notes, checklists, AND user reminders. Use this for "create/add/write a note", t
|
||||
```send_email
|
||||
{"to": "recipient@example.com", "subject": "Re: Your question", "body": "Hi, ...", "account": "gmail"}
|
||||
```
|
||||
Send a new email via SMTP. Use `resolve_contact` first if you only have a name. If multiple email accounts exist, call `list_email_accounts` first and pass the chosen `account`.
|
||||
|
||||
CRITICAL — signatures: DO NOT invent a sign-off name. End the body with just `Thanks,` or similar — never type a person's name unless the user explicitly told you what to sign as. When `agent_email_confirm` is on (default), the tool returns `{pending: true, pending_id: ...}` and stages the email for the user to approve in the chat UI instead of SMTPing immediately.""",
|
||||
Send a new email via SMTP. Use `resolve_contact` first if you only have a name. If multiple email accounts exist, call `list_email_accounts` first and pass the chosen `account`.""",
|
||||
"list_emails": """\
|
||||
```list_emails
|
||||
{"folder": "INBOX", "max_results": 20, "unread_only": false, "account": "gmail"}
|
||||
@@ -441,9 +313,7 @@ List recent emails from a folder, newest first, including read messages by defau
|
||||
```reply_to_email
|
||||
{"uid": "1234", "body": "Sounds good — talk Friday.", "account": "gmail"}
|
||||
```
|
||||
SEND a reply email immediately by UID. Do not use this for "open a reply" or "start a reply" — those should use `ui_control` with `open_email_reply <uid> <folder> reply` to open the email draft document. For follow-up requests like "reply ..." after reading/listing email where the user clearly wants to send now, use the exact UID and account from the latest `read_email`/`list_emails` result. Never invent UID `1`. Threads automatically (In-Reply-To/References handled).
|
||||
|
||||
CRITICAL — signatures: DO NOT invent a sign-off name. End the body with just `Thanks,` or similar — never type a person's name unless the user explicitly told you what to sign as. When `agent_email_confirm` is on (default), the tool returns `{pending: true, pending_id: ...}` and stages the email for the user to approve in the chat UI instead of SMTPing immediately.""",
|
||||
SEND a reply email immediately by UID. Do not use this for "open a reply" or "start a reply" — those should use `ui_control` with `open_email_reply <uid> <folder> reply` to open the email draft document. For follow-up requests like "reply ..." after reading/listing email where the user clearly wants to send now, use the exact UID and account from the latest `read_email`/`list_emails` result. Never invent UID `1`. Threads automatically (In-Reply-To/References handled).""",
|
||||
"bulk_email": """\
|
||||
```bulk_email
|
||||
{"action": "delete", "uids": ["10997", "10998"], "folder": "INBOX", "account": "Gmail"}
|
||||
@@ -453,7 +323,7 @@ Bulk delete/archive/mark emails. Use this for "delete all those" after listing e
|
||||
"archive_email": "- ```archive_email``` — Archive one email by UID. Args (JSON): {\"uid\":\"...\", \"folder\":\"INBOX\", \"account\":\"Gmail\"}. For multiple messages use bulk_email.",
|
||||
"mark_email_read": "- ```mark_email_read``` — Mark one email read/unread. Args (JSON): {\"uid\":\"...\", \"read\":true, \"folder\":\"INBOX\", \"account\":\"Gmail\"}. For multiple messages use bulk_email.",
|
||||
"resolve_contact": "- ```resolve_contact``` — Look up a contact's email by name. Searches CardDAV address book + sent email history. Args (JSON): {\"name\": \"...\"}. Use BEFORE send_email when the user gives only a name.",
|
||||
"manage_contact": "- ```manage_contact``` — Create/update/delete/list CardDAV contacts. Args (JSON): {\"action\": \"list|add|update|delete\", \"name\": \"...\", \"email\": \"...\", \"phones\": [...], \"address\": \"...\", \"uid\": \"...\"}. Use for info about another person: email, phone, postal address. For 'save this for <person>' / address paste / phone next to a name, use this — NOT manage_memory. Do NOT use for user identity facts ('my name is X'); those are manage_memory. For update/delete, call action=list first for the uid.",
|
||||
"manage_contact": "- ```manage_contact``` — Create/update/delete/list CardDAV contacts. Args (JSON): {\"action\": \"list|add|update|delete\", \"name\": \"...\", \"email\": \"...\", \"uid\": \"...\"}. Use only for explicit address-book/contact requests with contact details. Do NOT use for user identity facts like 'my name is <name>'; save those with manage_memory. For update/delete, call action=list first to get the uid.",
|
||||
"manage_calendar": """\
|
||||
```manage_calendar
|
||||
{"action": "create_event", "summary": "<event title>", "dtstart": "<natural language or ISO datetime>"}
|
||||
@@ -471,7 +341,7 @@ If the user asks for a reminder/alarm before the event, pass `reminder_minutes`
|
||||
"send_to_session": "- ```send_to_session``` — Send a message to another session. Line 1 = session_id, rest = message. Use for orchestrating work across sessions.",
|
||||
"search_chats": "- ```search_chats``` — Search past session transcripts for direct conversation evidence. Use when user asks 'did we discuss X?', 'find the conversation about Y', or when prior chat context is more appropriate than persistent memory.",
|
||||
"pipeline": "- ```pipeline``` — Run a multi-step AI pipeline. Args (JSON) with ordered steps, each specifying a model and prompt. Use for complex workflows.",
|
||||
"ui_control": "- ```ui_control``` — Control the UI: toggle tools on/off, OPEN PANELS, open email reply drafts, switch models, change themes. Commands: `toggle <name> on/off` (names: bash/shell, web/search, research, incognito, document_editor/documents), `open_panel <name>` (panels: documents, gallery, email, sessions, notes, memories/brain, skills, settings, cookbook), `open_email_reply <uid> <folder> <reply|reply-all|ai-reply>` (opens an email compose document, does NOT send), `set_mode agent/chat`, `switch_model <name>`, `set_theme <preset>`, `create_theme <name> <bg> <fg> <panel> <border> <accent>` (optional key=val for advanced colors AND background effects: bgPattern=<none|dots|synapse|rain|constellations|perlin-flow|petals|sparkles|embers>, bgEffectColor=#RRGGBB, bgEffectIntensity=<num>, bgEffectSize=<num>, frosted=true|false). \"open documents\" / \"open library\" / \"show gallery\" / \"open inbox\" / \"open notes\" / \"open cookbook\" all map to `open_panel <name>`. Built-in theme presets: dark, light, midnight, paper, cyberpunk, retrowave, forest, ocean, ume, copper, terminal, organs, lavender, gpt, claude, cute. For any other vibe/name, use create_theme.",
|
||||
"ui_control": "- ```ui_control``` — Control the UI: toggle tools on/off, OPEN PANELS, open email reply drafts, switch models, change themes. Commands: `toggle <name> on/off` (names: bash/shell, web/search, research, incognito, document_editor/documents), `open_panel <name>` (panels: documents, gallery, email, sessions, notes, memories/brain, skills, settings, cookbook), `open_email_reply <uid> <folder> <reply|reply-all|ai-reply>` (opens an email compose document, does NOT send), `set_mode agent/chat`, `switch_model <name>`, `set_theme <preset>`, `create_theme <name> <bg> <fg> <panel> <border> <accent>` (optional key=val for advanced colors AND background effects: bgPattern=<none|dots|synapse|rain|constellations|perlin-flow|petals|sparkles|embers>, bgEffectColor=#RRGGBB, bgEffectIntensity=<num>, bgEffectSize=<num>, frosted=true|false). \"open documents\" / \"open library\" / \"show gallery\" / \"open inbox\" / \"open notes\" / \"open cookbook\" all map to `open_panel <name>`. Theme presets: dark, light, midnight, paper, cyberpunk, retrowave, forest, ocean, ume, copper, terminal, organs, lavender, gpt, claude, cute.",
|
||||
"ask_user": "- ```ask_user``` — Ask the user a multiple-choice question when the task is genuinely ambiguous and the answer changes what you do next (pick an approach, confirm an assumption, choose a target). Args (JSON): {\"question\": \"...\", \"options\": [{\"label\": \"...\", \"description\": \"...\"?}, ...], \"multi\": false?}. 2-6 options. The user gets clickable buttons; calling this ENDS your turn and their choice comes back as your next message. Prefer sensible defaults — only ask when you truly can't proceed well without their input.",
|
||||
"update_plan": "- ```update_plan``` — While executing an approved plan, write the plan back: tick steps done or revise them. Args (JSON): {\"plan\": \"- [x] done step\\n- [ ] next step\"}. Always pass the COMPLETE checklist, not a diff. Call it after finishing each step (mark it `- [x]`) and whenever the user asks to change the plan. The user's docked plan window updates live. Does nothing if there's no active plan.",
|
||||
"list_served_models": "- ```list_served_models``` — Show what the Cookbook (LLM-serving subsystem) is currently running. NO args. Use this for ANY 'what's running' / 'what's serving' / 'show my cookbook' / 'is anything up' query. DO NOT shell out (`ps aux`, `docker ps`, etc.) — this tool is the source of truth. Failed serve tasks include recent logs plus diagnosis/retry suggestions; use those suggestions to call `serve_model` again with an adjusted command when appropriate.",
|
||||
@@ -524,7 +394,7 @@ def get_builtin_overrides() -> dict:
|
||||
ov = get_setting("builtin_tool_overrides", {})
|
||||
return ov if isinstance(ov, dict) else {}
|
||||
except Exception as e:
|
||||
logger.warning("Failed to load builtin tool overrides, using defaults", exc_info=e)
|
||||
logger.warning('Failed to load builtin tool overrides: %s', e)
|
||||
return {}
|
||||
|
||||
|
||||
@@ -548,7 +418,6 @@ def _assemble_prompt(tool_names: set, disabled_tools: set = None, compact: bool
|
||||
f"Available tools: {tool_list}.",
|
||||
_API_AGENT_RULES,
|
||||
]
|
||||
parts.extend(_domain_rules_for_tools(included))
|
||||
return "\n\n".join(parts)
|
||||
|
||||
parts = [_AGENT_PREAMBLE]
|
||||
@@ -585,7 +454,6 @@ def _assemble_prompt(tool_names: set, disabled_tools: set = None, compact: bool
|
||||
parts.append(f"(Other tools available when needed: {hint})")
|
||||
|
||||
parts.append(_AGENT_RULES)
|
||||
parts.extend(_domain_rules_for_tools(included))
|
||||
return "\n\n".join(parts)
|
||||
|
||||
|
||||
@@ -610,7 +478,7 @@ _API_HOSTS = frozenset([
|
||||
"api.deepseek.com", "deepseek.com",
|
||||
"api.together.xyz", "api.fireworks.ai",
|
||||
"api.perplexity.ai", "api.x.ai",
|
||||
"ollama.com", "api.venice.ai", "api.kimi.com",
|
||||
"ollama.com", "api.venice.ai",
|
||||
"api.githubcopilot.com",
|
||||
# Local OpenAI-compatible endpoints (llama.cpp, vLLM, LM Studio, etc.).
|
||||
# Without these, `_is_api_model` falls back to keyword sniffing on the
|
||||
@@ -706,125 +574,6 @@ def _extract_last_user_message(messages: List[Dict]) -> str:
|
||||
return ""
|
||||
|
||||
|
||||
_LOW_SIGNAL_RE = re.compile(r"^[\W_]*$", re.UNICODE)
|
||||
_EXPLICIT_CONTINUATION_RE = re.compile(
|
||||
r"^\s*(?:"
|
||||
r"yes|y|yeah|yep|ok|okay|sure|do it|go ahead|continue|carry on|"
|
||||
r"run it|launch it|start it|use that|that one|same|the same|"
|
||||
r"first|second|third|the first one|the second one|the third one|"
|
||||
r"[123]|[abc]"
|
||||
r")\s*[.!?]*\s*$",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
|
||||
def _is_explicit_continuation(text: str) -> bool:
|
||||
"""Only these terse replies may inherit older user turns for tool retrieval."""
|
||||
return bool(_EXPLICIT_CONTINUATION_RE.match(str(text or "").strip()))
|
||||
|
||||
|
||||
def _assistant_requested_followup(messages: List[Dict]) -> bool:
|
||||
"""True when the previous assistant turn asked for missing task details.
|
||||
|
||||
This allows natural replies like "buy milk" after "What would you like on
|
||||
your to-do list?" to inherit the prior domain, without letting random
|
||||
greetings inherit stale Cookbook/email/document context.
|
||||
"""
|
||||
seen_latest_user = False
|
||||
for msg in reversed(messages):
|
||||
role = msg.get("role")
|
||||
if role == "user" and not seen_latest_user:
|
||||
seen_latest_user = True
|
||||
continue
|
||||
if not seen_latest_user:
|
||||
continue
|
||||
if role != "assistant":
|
||||
continue
|
||||
content = msg.get("content", "")
|
||||
if isinstance(content, list):
|
||||
content = " ".join(b.get("text", "") for b in content if isinstance(b, dict))
|
||||
text = str(content or "").lower()
|
||||
if "?" not in text:
|
||||
return False
|
||||
return bool(re.search(
|
||||
r"\b(what would you like|what should|what do you want|which one|which model|"
|
||||
r"what.+(?:todo|to-do|list|document|email|model|server|item)|"
|
||||
r"any specific|give me|tell me)\b",
|
||||
text,
|
||||
))
|
||||
return False
|
||||
|
||||
|
||||
def _classify_agent_request(messages: List[Dict], last_user: str) -> Dict[str, object]:
|
||||
"""Classify only whether this turn deserves domain tool retrieval.
|
||||
|
||||
Normal chat should not inherit old Cookbook/email/document context. Recent
|
||||
context is used only for explicit continuations ("yes", "do it", "1").
|
||||
This function does not inject tools directly; selected tools later decide
|
||||
which domain rule packs get appended to the system prompt.
|
||||
"""
|
||||
text = str(last_user or "").strip()
|
||||
continuation = _is_explicit_continuation(text) or _assistant_requested_followup(messages)
|
||||
retrieval_query = _recent_context_for_retrieval(messages) if continuation else text
|
||||
q = retrieval_query.lower()
|
||||
|
||||
if not text or bool(_LOW_SIGNAL_RE.match(text)):
|
||||
return {
|
||||
"low_signal": True,
|
||||
"continuation": False,
|
||||
"domains": set(),
|
||||
"retrieval_query": text,
|
||||
}
|
||||
|
||||
domains: Set[str] = set()
|
||||
|
||||
def has(*patterns: str) -> bool:
|
||||
return any(re.search(p, q) for p in patterns)
|
||||
|
||||
if has(r"\b(cookbook|serve|serving|served|launch|start|preset|vllm|sglang|llama\.?cpp|ollama|download|downloading|pull|cached models?|running models?|model servers?|models? (?:are )?running|what models?|model picker|gpu box|kierkegaard|odysseus|ajax|qwen|gemma|llama|mistral|minimax)\b"):
|
||||
domains.add("cookbook")
|
||||
if has(r"\b(emails?|mails?|gmail|inbox|reply|forward|cc|bcc|send email|compose email|draft email|message chris|message him|message her)\b"):
|
||||
domains.add("email")
|
||||
if has(r"\b(note|todo|to-do|checklist|task list|remind me|reminder|buy|pickup|pick up)\b"):
|
||||
domains.add("notes_calendar_tasks")
|
||||
if has(r"\b(every day|every morning|every evening|recurring|automatically|cron|scheduled task|background task)\b"):
|
||||
domains.add("notes_calendar_tasks")
|
||||
if has(r"\b(calendar|event|meeting|appointment|schedule)\b"):
|
||||
domains.add("notes_calendar_tasks")
|
||||
if has(r"\b(documents?|docs?|draft|compose|poem|story|essay|outline|letter|edit|rewrite|proofread|suggest|feedback|review this|make a file)\b"):
|
||||
domains.add("documents")
|
||||
if "notes_calendar_tasks" not in domains and has(r"\bwrite\b"):
|
||||
domains.add("documents")
|
||||
if has(r"\b(search|web|google|look up|latest|news|current|weather|forecast|stock price|price of|website|url|https?://|www\.)\b"):
|
||||
domains.add("web")
|
||||
if has(
|
||||
r"\b(wyszukaj|wyszukać|wyszukac)\b.*\b(internet|internecie|online|web)\b",
|
||||
r"\b(sprawd[zź]|znajd[zź])\b.*\b(internet|internecie|online|web)\b",
|
||||
r"\b(aktualn\w*|bieżąc\w*|biezac\w*|dzisiaj|teraz)\b.*\b(pogod\w*|temperatur\w*)\b",
|
||||
):
|
||||
domains.add("web")
|
||||
if has(r"\b(research|deep dive|investigate|look into)\b"):
|
||||
domains.add("web")
|
||||
if has(r"\b(open|show|toggle|turn on|turn off|disable|enable|switch model|change model|settings|theme|panel)\b"):
|
||||
domains.add("ui")
|
||||
if has(r"\b(session|chat history|rename chat|delete chat|archive chat|fork chat|list chats)\b"):
|
||||
domains.add("sessions")
|
||||
if has(r"\b(file|folder|directory|repo|git|grep|find in files|read file|edit file|shell|terminal|bash|python)\b"):
|
||||
domains.add("files")
|
||||
if has(r"\b(endpoint|api token|mcp|webhook|preference|configure|config|setting)\b"):
|
||||
domains.add("settings")
|
||||
if has(r"\b(contact|contacts|phone|phone number|address book|vcard)\b"):
|
||||
domains.add("contacts")
|
||||
|
||||
low_signal = not continuation and not domains
|
||||
return {
|
||||
"low_signal": low_signal,
|
||||
"continuation": continuation,
|
||||
"domains": domains,
|
||||
"retrieval_query": retrieval_query,
|
||||
}
|
||||
|
||||
|
||||
def _recent_context_for_retrieval(messages: List[Dict], max_user: int = 3, max_chars: int = 600) -> str:
|
||||
"""Build the tool-retrieval query from the last few USER turns, not just
|
||||
the latest one.
|
||||
@@ -863,7 +612,6 @@ def _build_system_prompt(
|
||||
compact: bool = False,
|
||||
owner: Optional[str] = None,
|
||||
suppress_local_context: bool = False,
|
||||
active_email: Optional[Dict[str, str]] = None,
|
||||
) -> List[Dict]:
|
||||
"""Build agent system prompt, inject MCP/document context, merge consecutive system msgs."""
|
||||
global _cached_base_prompt, _cached_base_prompt_key
|
||||
@@ -880,7 +628,7 @@ def _build_system_prompt(
|
||||
_ov_sig = _hl.sha256(_json.dumps(get_builtin_overrides() or {}, sort_keys=True).encode()).hexdigest()
|
||||
except Exception:
|
||||
_ov_sig = ""
|
||||
cache_key = (frozenset(disabled_tools or []), bool(mcp_mgr), needs_admin, _rt_key, compact, _ov_sig, owner, suppress_local_context)
|
||||
cache_key = (frozenset(disabled_tools or []), bool(mcp_mgr), needs_admin, _rt_key, compact, _ov_sig, suppress_local_context)
|
||||
if _cached_base_prompt and _cached_base_prompt_key == cache_key and not active_document:
|
||||
agent_prompt = _cached_base_prompt
|
||||
# Skill index is user-editable (name + description), so it must never
|
||||
@@ -888,7 +636,7 @@ def _build_system_prompt(
|
||||
# when the cache hits.
|
||||
_, _skill_index_block = _build_base_prompt(
|
||||
disabled_tools, mcp_mgr, needs_admin, relevant_tools,
|
||||
mcp_disabled_map=mcp_disabled_map, compact=compact, owner=owner,
|
||||
mcp_disabled_map=mcp_disabled_map, compact=compact,
|
||||
suppress_local_context=suppress_local_context,
|
||||
)
|
||||
else:
|
||||
@@ -899,7 +647,6 @@ def _build_system_prompt(
|
||||
relevant_tools,
|
||||
mcp_disabled_map=mcp_disabled_map,
|
||||
compact=compact,
|
||||
owner=owner,
|
||||
suppress_local_context=suppress_local_context,
|
||||
)
|
||||
if not active_document:
|
||||
@@ -915,22 +662,11 @@ def _build_system_prompt(
|
||||
|
||||
# Current date/time for every agent request. This is user-local when the
|
||||
# browser provided timezone headers, with a server-local fallback.
|
||||
#
|
||||
# IMPORTANT: this is intentionally NOT prepended into agent_prompt (the
|
||||
# system message) anymore. Its text changes every minute, and local
|
||||
# OpenAI-compatible backends (llama.cpp / LM Studio) key their KV-cache
|
||||
# prefix off the system message byte-for-byte — mixing ever-changing
|
||||
# timestamp text into the (already large, tool-laden) agent system prompt
|
||||
# would invalidate the cached prefix on every single request, forcing a
|
||||
# full prompt re-evaluation each turn (issue #2927). It's built here as a
|
||||
# standalone *user*-role message and inserted near the end of the array,
|
||||
# right alongside _doc_message / _skills_message, below.
|
||||
_datetime_message = None
|
||||
try:
|
||||
from src.user_time import current_datetime_context_message
|
||||
_datetime_message = current_datetime_context_message()
|
||||
except Exception as e:
|
||||
logger.warning("Failed to build datetime context message", exc_info=e)
|
||||
from src.user_time import current_datetime_prompt
|
||||
agent_prompt = current_datetime_prompt() + agent_prompt
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Document context is kept as a SEPARATE message (not merged into the tool
|
||||
# prompt) so the context trimmer doesn't destroy it when truncating the
|
||||
@@ -973,8 +709,8 @@ def _build_system_prompt(
|
||||
try:
|
||||
from src.pdf_form_doc import find_source_upload_id
|
||||
_is_form_backed = bool(find_source_upload_id(active_document.current_content or ""))
|
||||
except Exception as e:
|
||||
logger.warning("Failed to detect if document is form-backed, assuming plain", exc_info=e)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
if _is_form_backed:
|
||||
doc_ctx = (
|
||||
@@ -1056,66 +792,6 @@ def _build_system_prompt(
|
||||
else:
|
||||
set_active_document(None)
|
||||
|
||||
# Active email reader — frontend told us the user has an email open.
|
||||
# Inject a context block so "reply", "summarize this", "what does it say"
|
||||
# resolve to the real UID instead of the agent inventing a fresh .md
|
||||
# draft with fake headers. This is the email equivalent of _doc_message.
|
||||
_email_message = None
|
||||
if active_email and active_email.get("uid"):
|
||||
_em_uid = active_email.get("uid", "")
|
||||
_em_folder = active_email.get("folder", "INBOX")
|
||||
_em_account = active_email.get("account", "")
|
||||
_em_subject = active_email.get("subject", "") or "(no subject)"
|
||||
_em_from = active_email.get("from", "") or "(unknown sender)"
|
||||
_em_preview = (active_email.get("body_preview", "") or "").strip()
|
||||
_preview_block = f"\nBody preview:\n```\n{_em_preview[:1800]}\n```" if _em_preview else ""
|
||||
_acct_arg = f" {_em_account}" if _em_account else ""
|
||||
email_ctx = (
|
||||
f"ACTIVE EMAIL OPEN (the user has this email open in a reader window right now)\n"
|
||||
f"UID: {_em_uid}\n"
|
||||
f"Folder: {_em_folder}\n"
|
||||
f"Account: {_em_account or '(default)'}\n"
|
||||
f"From: {_em_from}\n"
|
||||
f"Subject: {_em_subject}{_preview_block}\n\n"
|
||||
f"CRITICAL DEFAULT — every request about email this turn refers to "
|
||||
f"THIS email unless the user names a DIFFERENT specific recipient "
|
||||
f"(a name, an email address, or another thread). Examples that "
|
||||
f"ALL mean reply-to-the-open-email:\n"
|
||||
f" • 'reply' / 'reply to this' / 'respond'\n"
|
||||
f" • 'write email saying X' / 'send email saying X' / 'draft something'\n"
|
||||
f" • 'tell them X' / 'say hi' / 'thanks' / 'ack' / 'lmk'\n"
|
||||
f" • 'summarize it' / 'what does it say' / 'tldr'\n"
|
||||
f" • 'forward this' / 'forward to <addr>'\n"
|
||||
f"DO NOT ASK THE USER 'who do you want to send this to?' — the "
|
||||
f"answer is ALWAYS the sender of the open email (above) unless they "
|
||||
f"named someone else. Asking that is the wrong move every time.\n\n"
|
||||
f"RULES for the open email:\n"
|
||||
f"1. DRAFT a reply (default for any 'write/send/reply/tell them' "
|
||||
f"request without a different recipient): call `ui_control` with "
|
||||
f"`action=\"open_email_reply\"` and `extra=\"{_em_uid} {_em_folder} "
|
||||
f"reply\"`. This opens the proper reply doc with To/Subject/"
|
||||
f"In-Reply-To pre-filled by the backend. The user will see and edit "
|
||||
f"it before sending. DO NOT `create_document` a markdown file with "
|
||||
f"hand-written `To:` / `Subject:` / `In-Reply-To:` headers — that "
|
||||
f"is wrong every time.\n"
|
||||
f"2. SEND a reply immediately (skip the draft): call "
|
||||
f"`reply_to_email` with the UID above. Only do this when the user "
|
||||
f"explicitly says 'send' / 'send the reply' / 'reply and send'.\n"
|
||||
f"3. READ the full body (the preview above may be truncated): "
|
||||
f"call `read_email` with the UID/folder/account above.\n"
|
||||
f"4. SUMMARIZE / answer questions about it: read it first, then "
|
||||
f"answer in chat. Don't create a document for a summary unless "
|
||||
f"the user explicitly asks for one.\n"
|
||||
f"5. Never ask the user to paste the email or 'share it with you' "
|
||||
f"— you already have its identity above and can read the full body.\n"
|
||||
f"6. The ONLY time you ask 'who to send to?' is when the user "
|
||||
f"explicitly says 'send a NEW email to someone else' or names a "
|
||||
f"recipient you can't identify. A bare 'send email saying X' = the "
|
||||
f"open email's sender.\n"
|
||||
)
|
||||
_email_message = untrusted_context_message("active email reader", email_ctx)
|
||||
_email_message["_protected"] = True
|
||||
|
||||
# Inject writing style for any email writing path. This is deliberately
|
||||
# broader than read/list: models may compose via send_email, reply_to_email,
|
||||
# or ui_control open_email_reply after the first tool round.
|
||||
@@ -1323,14 +999,8 @@ def _build_system_prompt(
|
||||
if _doc_message:
|
||||
merged.insert(last_user_idx, _doc_message)
|
||||
last_user_idx += 1 # the document message is now at last_user_idx
|
||||
if _email_message:
|
||||
merged.insert(last_user_idx, _email_message)
|
||||
last_user_idx += 1
|
||||
if _skills_message:
|
||||
merged.insert(last_user_idx, _skills_message)
|
||||
last_user_idx += 1
|
||||
if _datetime_message:
|
||||
merged.insert(last_user_idx, _datetime_message)
|
||||
|
||||
return merged, mcp_schemas
|
||||
|
||||
@@ -1349,7 +1019,6 @@ def _build_base_prompt(
|
||||
relevant_tools=None,
|
||||
mcp_disabled_map=None,
|
||||
compact: bool = False,
|
||||
owner: Optional[str] = None,
|
||||
suppress_local_context: bool = False,
|
||||
):
|
||||
"""Build the agent prompt with only relevant tools included.
|
||||
@@ -1360,18 +1029,12 @@ def _build_base_prompt(
|
||||
from src.tool_index import ALWAYS_AVAILABLE
|
||||
|
||||
disabled = set(disabled_tools or [])
|
||||
if not get_setting("image_gen_enabled", False):
|
||||
if not get_setting("image_gen_enabled", True):
|
||||
disabled.add("generate_image")
|
||||
|
||||
if relevant_tools is not None:
|
||||
# RAG mode: trust the relevant_tools set as already-composed.
|
||||
# get_tools_for_query starts from ALWAYS_AVAILABLE and may
|
||||
# *discard* tools that conflict with the query's intent (e.g.
|
||||
# drop manage_memory for clear contact-save patterns). Unioning
|
||||
# ALWAYS_AVAILABLE back in here used to silently undo those
|
||||
# drops. Only force-include the irreducible loop primitives
|
||||
# (ask_user, update_plan) as belt-and-suspenders.
|
||||
tool_names = set(relevant_tools) | {"ask_user", "update_plan"}
|
||||
# RAG mode: include always-available + retrieved + admin (if needed)
|
||||
tool_names = set(ALWAYS_AVAILABLE) | set(relevant_tools)
|
||||
if needs_admin:
|
||||
tool_names |= _ADMIN_TOOLS
|
||||
agent_prompt = _assemble_prompt(tool_names, disabled, compact=compact)
|
||||
@@ -1409,7 +1072,7 @@ def _build_base_prompt(
|
||||
from src.constants import DATA_DIR
|
||||
_sm = SkillsManager(DATA_DIR)
|
||||
active_tools = list(set(TOOL_SECTIONS.keys()) - set(disabled or []))
|
||||
skill_idx = _sm.index_for(owner=owner, active_toolsets=active_tools)
|
||||
skill_idx = _sm.index_for(owner=None, active_toolsets=active_tools)
|
||||
if skill_idx:
|
||||
lines = ["## Available skills",
|
||||
"Procedures the assistant should consult before doing domain work. "
|
||||
@@ -1812,16 +1475,15 @@ async def stream_agent_loop(
|
||||
max_tool_calls: int = 0,
|
||||
context_length: int = 0,
|
||||
active_document=None,
|
||||
active_email: Optional[Dict[str, str]] = None,
|
||||
session_id: Optional[str] = None,
|
||||
disabled_tools: Optional[Set[str]] = None,
|
||||
owner: Optional[str] = None,
|
||||
relevant_tools: Optional[Set[str]] = None,
|
||||
fallbacks: Optional[List[tuple]] = None,
|
||||
workspace: Optional[str] = None,
|
||||
plan_mode: bool = False,
|
||||
approved_plan: Optional[str] = None,
|
||||
tool_policy: Optional[ToolPolicy] = None,
|
||||
workspace: Optional[str] = None,
|
||||
_is_teacher_run: bool = False,
|
||||
) -> AsyncGenerator[str, None]:
|
||||
"""Streaming agent loop generator.
|
||||
@@ -1860,18 +1522,9 @@ async def stream_agent_loop(
|
||||
_t0 = time.time()
|
||||
_needs_admin = _detect_admin_intent(messages)
|
||||
_last_user = _extract_last_user_message(messages)
|
||||
_intent = _classify_agent_request(messages, _last_user)
|
||||
# Tool retrieval uses the latest message by default. It may inherit recent
|
||||
# user turns only for explicit continuations ("yes", "do it", "1").
|
||||
_retrieval_query = str(_intent.get("retrieval_query") or _last_user)
|
||||
logger.info(
|
||||
"[agent-intent] latest=%r continuation=%s low_signal=%s domains=%s retrieval_query=%r",
|
||||
_last_user[:120],
|
||||
bool(_intent.get("continuation")),
|
||||
bool(_intent.get("low_signal")),
|
||||
sorted(_intent.get("domains") or []),
|
||||
_retrieval_query[:200],
|
||||
)
|
||||
# Tool retrieval keys on recent conversation context (last few user turns),
|
||||
# not just the latest message, so short follow-ups don't drop just-used tools.
|
||||
_retrieval_query = _recent_context_for_retrieval(messages) or _last_user
|
||||
_mcp_disabled_map = _load_mcp_disabled_map() if mcp_mgr else {}
|
||||
if plan_mode and mcp_mgr:
|
||||
# Allow read-only MCP tools to investigate, block write/unknown ones:
|
||||
@@ -1888,23 +1541,6 @@ async def stream_agent_loop(
|
||||
_t1 = time.time()
|
||||
if _relevant_tools:
|
||||
logger.info(f"[tool-rag] Using caller-provided relevant_tools ({len(_relevant_tools)} tools)")
|
||||
if not guide_only and not _relevant_tools and bool(_intent.get("low_signal")):
|
||||
from src.tool_index import ALWAYS_AVAILABLE
|
||||
if workspace:
|
||||
# An active workspace IS the file-work signal: a vague "look at the
|
||||
# project" means explore this folder. Surface only the READ-ONLY file
|
||||
# tools (intersection with the plan-mode read-only allowlist) so the
|
||||
# agent can investigate; write/shell tools stay out until the request
|
||||
# actually calls for them (RAG retrieval adds those on a real ask).
|
||||
_relevant_tools = set(ALWAYS_AVAILABLE)
|
||||
from src.tool_security import PLAN_MODE_READONLY_TOOLS
|
||||
_relevant_tools |= (_DOMAIN_TOOL_MAP["files"] & PLAN_MODE_READONLY_TOOLS)
|
||||
logger.info("[tool-rag] Low-signal but workspace active; including read-only file tools")
|
||||
else:
|
||||
# Don't short-circuit: fall through to RAG retrieval below.
|
||||
# Non-English queries are flagged low_signal by the English-only
|
||||
# intent classifier, but fastembed retrieval works across languages.
|
||||
logger.info("[tool-rag] Low-signal query; will run RAG retrieval")
|
||||
if not guide_only and not _relevant_tools:
|
||||
try:
|
||||
from src.tool_index import get_tool_index, ALWAYS_AVAILABLE
|
||||
@@ -1947,79 +1583,16 @@ async def stream_agent_loop(
|
||||
for keywords, tools in ToolIndex._KEYWORD_HINTS.items():
|
||||
if any(kw in ql for kw in keywords):
|
||||
_relevant_tools.update(tools)
|
||||
# Always include core document/memory tools
|
||||
_relevant_tools.update({"create_document", "manage_memory", "manage_notes"})
|
||||
logger.info(f"[tool-rag] Keyword fallback selected: {sorted(_relevant_tools - ALWAYS_AVAILABLE)}")
|
||||
|
||||
# If deterministic domain detection fired, seed the corresponding domain
|
||||
# tools into the selected tool set. This is not direct prompt-pack
|
||||
# injection: `_assemble_prompt()` still derives domain rules from the final
|
||||
# tool names. It prevents obvious requests like "last 5 emails" from
|
||||
# collapsing to only ask_user/manage_memory when vector retrieval misses or
|
||||
# times out.
|
||||
if not guide_only and _relevant_tools is not None:
|
||||
for _domain in (_intent.get("domains") or set()):
|
||||
_relevant_tools.update(_DOMAIN_TOOL_MAP.get(str(_domain), set()))
|
||||
if "cookbook" in (_intent.get("domains") or set()):
|
||||
_relevant_tools.update({
|
||||
"list_served_models",
|
||||
"list_downloads",
|
||||
"list_cached_models",
|
||||
"list_cookbook_servers",
|
||||
"list_serve_presets",
|
||||
})
|
||||
if "email" in (_intent.get("domains") or set()):
|
||||
_relevant_tools.add("ui_control")
|
||||
if "web" in (_intent.get("domains") or set()):
|
||||
_relevant_tools.update({"web_search", "web_fetch"})
|
||||
if "ui" in (_intent.get("domains") or set()):
|
||||
_relevant_tools.add("ui_control")
|
||||
|
||||
# If a document is open the model needs the editing tools available
|
||||
# regardless of which selection path (RAG, keyword, caller-provided) ran
|
||||
# or what keywords were in the latest user message.
|
||||
if _relevant_tools is not None and active_document is not None:
|
||||
_relevant_tools.update({"edit_document", "update_document", "suggest_document"})
|
||||
|
||||
# The skill index injected by _build_system_prompt tells the model to
|
||||
# call `manage_skills action=view`, and Jaccard-matched skills are pasted
|
||||
# into the prompt as procedures to follow — but neither path goes through
|
||||
# tool selection, so the model can be handed a procedure naming tools
|
||||
# (grep, read_file, ...) that aren't in its schema list. Keep the schemas
|
||||
# in lockstep: manage_skills is callable whenever any skill is indexed,
|
||||
# and a matched skill's declared requires_toolsets ride along with it.
|
||||
if not guide_only and _relevant_tools is not None:
|
||||
try:
|
||||
from services.memory.skills import SkillsManager
|
||||
from src.constants import DATA_DIR
|
||||
_skills_on = True
|
||||
try:
|
||||
from routes.prefs_routes import _load_for_user as _load_prefs
|
||||
_skills_on = (_load_prefs(owner) or {}).get("skills_enabled", True)
|
||||
except Exception:
|
||||
pass
|
||||
_sm = SkillsManager(DATA_DIR)
|
||||
_owner_skills = _sm.load(owner=owner) if _skills_on else []
|
||||
if _owner_skills:
|
||||
_relevant_tools.add("manage_skills")
|
||||
if _retrieval_query:
|
||||
# Validate against every known executable tool, not just
|
||||
# TOOL_SECTIONS — code-nav tools (grep/glob/ls) ship as
|
||||
# schemas without a prompt-prose section.
|
||||
from src.tool_policy import known_tool_names
|
||||
_known = known_tool_names()
|
||||
for _sk in _sm.get_relevant_skills(
|
||||
_retrieval_query, skills=_owner_skills,
|
||||
threshold=0.25, max_items=3,
|
||||
):
|
||||
_relevant_tools.update(
|
||||
t for t in (_sk.get("requires_toolsets") or [])
|
||||
if t in _known
|
||||
)
|
||||
except Exception as _e:
|
||||
logger.debug(f"[tool-rag] skill-aware tool include skipped: {_e}")
|
||||
|
||||
if _relevant_tools is not None:
|
||||
logger.info("[agent-intent] selected_tools=%s", sorted(_relevant_tools)[:50])
|
||||
|
||||
prep_timings["tool_selection"] = time.time() - _t1
|
||||
|
||||
_t2 = time.time()
|
||||
@@ -2067,10 +1640,6 @@ async def stream_agent_loop(
|
||||
# and can override this list for users who know their setup.
|
||||
_model_no_tools = any(kw in _model_lc for kw in (
|
||||
"deepseek-r1",
|
||||
# Open-weight GPT-OSS models are commonly served through llama.cpp /
|
||||
# llama-cpp-python. Their names contain "gpt-o", but they do not use
|
||||
# OpenAI's native tool-call channel unless the endpoint opts in.
|
||||
"gpt-oss",
|
||||
))
|
||||
# Native Ollama endpoints (/api/chat) handle tool schemas differently from
|
||||
# the OpenAI-compat path. Models like gemma4, qwen3.5, ministral respond to
|
||||
@@ -2100,8 +1669,28 @@ async def stream_agent_loop(
|
||||
compact=_is_api_model,
|
||||
owner=owner,
|
||||
suppress_local_context=guide_only,
|
||||
active_email=active_email,
|
||||
)
|
||||
if workspace and not guide_only:
|
||||
# PREPEND (not append) so it dominates the large base prompt — appended
|
||||
# at the end, small models ignored it and asked the user for code. The
|
||||
# folder IS the project; the agent must explore it, not ask.
|
||||
_ws_note = (
|
||||
f"## ACTIVE WORKSPACE — READ FIRST\n"
|
||||
f"The user is working in this folder: {workspace}\n"
|
||||
f"It IS the project. bash/python run with cwd set here and "
|
||||
f"read_file/write_file are confined to it (paths outside are rejected).\n"
|
||||
f"When the user says \"the code\" / \"this project\" / \"the workspace\" "
|
||||
f"or asks to review/find/edit something WITHOUT a path, they mean THIS "
|
||||
f"folder. Do NOT ask the user for code or a path, and do NOT read a file "
|
||||
f"literally named \"workspace\". ALWAYS start by exploring it yourself: "
|
||||
f"run `bash` → `git ls-files` (or `ls -R`) to see the files, then "
|
||||
f"read_file the relevant ones by path RELATIVE to the workspace."
|
||||
)
|
||||
if messages and messages[0].get("role") == "system":
|
||||
messages[0]["content"] = _ws_note + "\n\n" + (messages[0].get("content") or "")
|
||||
else:
|
||||
messages.insert(0, {"role": "system", "content": _ws_note})
|
||||
logger.info("[workspace] active for this turn: %s", workspace)
|
||||
if plan_mode and not guide_only:
|
||||
# Steer the model to investigate-then-propose. Hard tool gating handles
|
||||
# every write path except shell; this directive is what keeps the
|
||||
@@ -2133,34 +1722,30 @@ async def stream_agent_loop(
|
||||
_t3 = time.time()
|
||||
try:
|
||||
from src.context_compactor import trim_for_context
|
||||
from src.context_budget import compute_input_token_budget, DEFAULT_HARD_MAX, DEFAULT_BUDGET, budget_is_explicit as _budget_is_explicit
|
||||
from src.model_context import budget_context_for_model
|
||||
from src.context_budget import compute_input_token_budget, DEFAULT_HARD_MAX
|
||||
from src.settings import is_setting_overridden
|
||||
|
||||
soft_budget = int(get_setting("agent_input_token_budget", DEFAULT_BUDGET) or 0)
|
||||
soft_budget = int(get_setting("agent_input_token_budget", 6000) or 0)
|
||||
if soft_budget > 0:
|
||||
before_trim_tokens = estimate_tokens(messages)
|
||||
reserve_tokens = min(max(max_tokens or 1024, 512), 2048)
|
||||
# Ceiling for the auto-derived budget (no effect on an explicit budget;
|
||||
# see #1230). Falls back to DEFAULT_HARD_MAX on missing/malformed values
|
||||
# so misconfig can't zero the budget.
|
||||
# Honour the configurable ceiling for the auto-derived budget path.
|
||||
# No-op when the user has an explicit `agent_input_token_budget`
|
||||
# (that branch ignores hard_max). Falls back to DEFAULT_HARD_MAX
|
||||
# on missing/malformed values so misconfig can't zero the budget.
|
||||
try:
|
||||
hard_max = int(get_setting("agent_input_token_hard_max", DEFAULT_HARD_MAX) or DEFAULT_HARD_MAX)
|
||||
except (TypeError, ValueError):
|
||||
hard_max = DEFAULT_HARD_MAX
|
||||
if hard_max <= 0:
|
||||
hard_max = DEFAULT_HARD_MAX
|
||||
# Default value = auto sentinel (scale to the window); any other value =
|
||||
# explicit cap. Value-based, not presence-based, because the save path
|
||||
# materializes defaults so a persisted default must still read as auto (#4121).
|
||||
budget_is_explicit = _budget_is_explicit(soft_budget)
|
||||
# Scale only off a window we actually discovered, bound to the value it
|
||||
# proves (else 0) — not the passed-in context_length, which can be stale
|
||||
# or unset for some callers (#4122 review).
|
||||
ctx_for_budget = budget_context_for_model(endpoint_url, model, fallback=context_length)
|
||||
# Scale the default budget to the model's context window so long-context
|
||||
# models aren't silently capped at 6000; an explicit user setting is
|
||||
# still honoured (clamped to the window). (#1170)
|
||||
effective_budget = compute_input_token_budget(
|
||||
soft_budget,
|
||||
ctx_for_budget,
|
||||
budget_is_explicit,
|
||||
context_length,
|
||||
is_setting_overridden("agent_input_token_budget"),
|
||||
hard_max=hard_max,
|
||||
)
|
||||
trimmed_messages = trim_for_context(
|
||||
@@ -2235,12 +1820,11 @@ async def stream_agent_loop(
|
||||
# tool, so we don't nudge on harmless transitional text like "let me
|
||||
# know what you think".
|
||||
_INTENT_RE = re.compile(
|
||||
r"(?:^|\n)\s*(?:let me|i'?ll|i will|i need to|we need to|need to|"
|
||||
r"i should|we should|i must|we must|going to|let's)\s+"
|
||||
r"(?:^|\n)\s*(?:let me|i'?ll|i will|going to|let's)\s+"
|
||||
r"(?:tail|check|investigate|look at|see|tail|read|fetch|inspect|"
|
||||
r"verify|diagnose|examine|debug|capture|grab|pull|view|run|call|"
|
||||
r"trigger|launch|start|kick off|stop|kill|restart|adopt|serve|"
|
||||
r"register|adopt|list|search|find|query|hit|ping|test|use|perform|do)"
|
||||
r"register|adopt|list|search|find|query|hit|ping|test)"
|
||||
r"\b[^.\n]{0,140}",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
@@ -2281,17 +1865,9 @@ async def stream_agent_loop(
|
||||
elif _is_api_model:
|
||||
# Filter schemas by RAG-selected tools (if available)
|
||||
if _relevant_tools:
|
||||
# _build_base_prompt unions _ADMIN_TOOLS into the prompt
|
||||
# sections when admin intent fires — the schema list must
|
||||
# offer the same names, or the model reads prose describing
|
||||
# tools it cannot call and substitutes the nearest schema
|
||||
# it does have (e.g. manage_memory for manage_skills).
|
||||
_schema_names = set(_relevant_tools)
|
||||
if _needs_admin:
|
||||
_schema_names |= _ADMIN_TOOLS
|
||||
base_schemas = [
|
||||
s for s in FUNCTION_TOOL_SCHEMAS
|
||||
if s.get("function", {}).get("name") in _schema_names
|
||||
if s.get("function", {}).get("name") in _relevant_tools
|
||||
]
|
||||
_mcp_filtered = [
|
||||
s for s in mcp_schemas
|
||||
@@ -2337,7 +1913,6 @@ async def stream_agent_loop(
|
||||
prompt_type=prompt_type if round_num == 1 else None,
|
||||
tools=all_tool_schemas if all_tool_schemas else None,
|
||||
timeout=agent_stream_timeout,
|
||||
session_id=session_id,
|
||||
):
|
||||
if time.time() > _round_deadline:
|
||||
logger.warning(f"[agent] round {round_num} stream exceeded wall-clock deadline; cutting off")
|
||||
@@ -2827,46 +2402,6 @@ async def stream_agent_loop(
|
||||
)
|
||||
desc, result = await _tool_task
|
||||
|
||||
# A skill the model just loaded can prescribe tools that weren't
|
||||
# RAG-selected this turn (declared via requires_toolsets in its
|
||||
# frontmatter). Union them into the selection so the NEXT round's
|
||||
# schema list includes them — otherwise the model reads "use
|
||||
# grep" from the skill it fetched but has no grep schema to call.
|
||||
if (
|
||||
block.tool_type == "manage_skills"
|
||||
and _relevant_tools is not None
|
||||
and not result.get("error")
|
||||
):
|
||||
_ms_args = {}
|
||||
_ms_raw = (block.content or "").strip()
|
||||
if _ms_raw.startswith("{"):
|
||||
try:
|
||||
_ms_args = json.loads(_ms_raw)
|
||||
except json.JSONDecodeError:
|
||||
_ms_args = {}
|
||||
_ms_name = str(_ms_args.get("name", "") or "").strip()
|
||||
if _ms_name and _ms_args.get("action") in ("view", "view_ref"):
|
||||
try:
|
||||
from services.memory.skills import SkillsManager as _SkM
|
||||
from src.constants import DATA_DIR as _DD
|
||||
from src.tool_policy import known_tool_names as _ktn
|
||||
_known = _ktn()
|
||||
for _sk in _SkM(_DD).load(owner=owner):
|
||||
if _sk.get("name") == _ms_name:
|
||||
_new = {
|
||||
t for t in (_sk.get("requires_toolsets") or [])
|
||||
if t in _known and t not in _relevant_tools
|
||||
}
|
||||
if _new:
|
||||
_relevant_tools.update(_new)
|
||||
logger.info(
|
||||
"[tool-rag] skill '%s' unlocked tools for next round: %s",
|
||||
_ms_name, sorted(_new),
|
||||
)
|
||||
break
|
||||
except Exception as _e:
|
||||
logger.debug(f"skill requires_toolsets unlock skipped: {_e}")
|
||||
|
||||
# Extract structured web sources from web_search tool output.
|
||||
# web_search returns {"output": ..., "exit_code": 0}; check "output"
|
||||
# first so the <!-- SOURCES:…--> marker is found and stripped even
|
||||
@@ -2957,20 +2492,18 @@ async def stream_agent_loop(
|
||||
# On a bash/python timeout the result carries error + (often
|
||||
# empty) stdout/stderr; fall back to the error so the "timed
|
||||
# out" reason reaches the UI instead of a blank result.
|
||||
raw = result["stdout"] or result["stderr"] or result.get("error", "")
|
||||
output_text = _truncate(raw)
|
||||
output_text = (result["stdout"] or result["stderr"] or result.get("error", ""))[:2000]
|
||||
elif "output" in result:
|
||||
# bash / python canonical result: {"output": ..., "exit_code": ...}
|
||||
raw = result["output"] or ""
|
||||
output_text = _truncate(raw)
|
||||
output_text = (result["output"] or "")[:2000]
|
||||
elif "response" in result:
|
||||
# AI interaction tools (chat_with_model, send_to_session)
|
||||
label = result.get("model", result.get("session_name", "AI"))
|
||||
output_text = _truncate(f"{label}: {result['response']}")
|
||||
output_text = f"{label}: {result['response']}"[:4000]
|
||||
elif "content" in result:
|
||||
output_text = _truncate(result["content"])
|
||||
output_text = result["content"][:2000]
|
||||
elif "results" in result:
|
||||
output_text = _truncate(result["results"])
|
||||
output_text = result["results"][:4000]
|
||||
elif "session_id" in result and "name" in result:
|
||||
output_text = f"Session created: {result['name']} (id: {result['session_id']})"
|
||||
elif "success" in result:
|
||||
@@ -2980,25 +2513,13 @@ async def stream_agent_loop(
|
||||
else f"Error: {result.get('error', '')}"
|
||||
)
|
||||
elif "error" in result:
|
||||
output_text = _truncate(result["error"])
|
||||
output_text = result["error"][:2000]
|
||||
|
||||
# Emit tool_output (include ui_event data if present)
|
||||
tool_output_data = {"type": "tool_output", "tool": block.tool_type, "command": cmd_display, "output": output_text, "exit_code": result.get("exit_code")}
|
||||
if "ui_event" in result:
|
||||
tool_output_data["ui_event"] = result["ui_event"]
|
||||
for k in (
|
||||
"toggle_name", "state", "mode", "model", "endpoint_url",
|
||||
"theme_name", "colors",
|
||||
# ui_control open_email_reply payload — without these the
|
||||
# frontend openReplyDraft bails on undefined uid and the
|
||||
# reply window silently never opens.
|
||||
"uid", "folder", "account_id",
|
||||
# Optional pre-filled body for open_email_reply so the
|
||||
# agent can compose-and-open in one tool call.
|
||||
"body",
|
||||
# ui_control open_panel payload
|
||||
"panel",
|
||||
):
|
||||
for k in ("toggle_name", "state", "mode", "model", "endpoint_url", "theme_name", "colors"):
|
||||
if k in result:
|
||||
tool_output_data[k] = result[k]
|
||||
# Forward image data from generate_image tool
|
||||
|
||||
@@ -18,30 +18,6 @@ from src.tool_utils import _truncate, get_mcp_manager, set_mcp_manager
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
from .subprocess_tools import BashTool, PythonTool
|
||||
from .web_tools import WebSearchTool, WebFetchTool
|
||||
from .filesystem_tools import ReadFileTool, WriteFileTool, EditFileTool, LsTool, GlobTool, GrepTool, GetWorkspaceTool
|
||||
from .document_tools import CreateDocumentTool, UpdateDocumentTool, EditDocumentTool, SuggestDocumentTool, ManageDocumentTool
|
||||
|
||||
TOOL_HANDLERS = {
|
||||
"bash": BashTool().execute,
|
||||
"python": PythonTool().execute,
|
||||
"web_search": WebSearchTool().execute,
|
||||
"web_fetch": WebFetchTool().execute,
|
||||
"read_file": ReadFileTool().execute,
|
||||
"write_file": WriteFileTool().execute,
|
||||
"edit_file": EditFileTool().execute,
|
||||
"ls": LsTool().execute,
|
||||
"glob": GlobTool().execute,
|
||||
"grep": GrepTool().execute,
|
||||
"create_document": CreateDocumentTool().execute,
|
||||
"update_document": UpdateDocumentTool().execute,
|
||||
"edit_document": EditDocumentTool().execute,
|
||||
"suggest_document": SuggestDocumentTool().execute,
|
||||
"manage_documents": ManageDocumentTool().execute,
|
||||
"get_workspace": GetWorkspaceTool().execute,
|
||||
}
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Constants (re-exported for backward compatibility — single source of truth
|
||||
# is src.constants; always prefer importing from there for new code)
|
||||
@@ -52,7 +28,7 @@ PYTHON_TIMEOUT = 30
|
||||
|
||||
# Tool types that trigger execution
|
||||
TOOL_TAGS = {"bash", "python", "web_search", "web_fetch", "read_file", "write_file", "edit_file",
|
||||
"grep", "glob", "ls", "get_workspace",
|
||||
"grep", "glob", "ls",
|
||||
"create_document", "update_document", "edit_document",
|
||||
"search_chats",
|
||||
"chat_with_model", "create_session", "list_sessions",
|
||||
@@ -116,14 +92,15 @@ from src.tool_execution import ( # noqa: E402, F401
|
||||
format_tool_result,
|
||||
)
|
||||
|
||||
# Document functions
|
||||
from .document_tools import (
|
||||
set_active_document,
|
||||
set_active_model
|
||||
)
|
||||
|
||||
# Implementations
|
||||
from src.tool_implementations import ( # noqa: E402, F401
|
||||
set_active_document,
|
||||
set_active_model,
|
||||
get_active_document,
|
||||
do_create_document,
|
||||
do_update_document,
|
||||
do_edit_document,
|
||||
do_suggest_document,
|
||||
do_search_chats,
|
||||
do_manage_skills,
|
||||
do_manage_tasks,
|
||||
@@ -131,6 +108,7 @@ from src.tool_implementations import ( # noqa: E402, F401
|
||||
do_manage_mcp,
|
||||
do_manage_webhooks,
|
||||
do_manage_tokens,
|
||||
do_manage_documents,
|
||||
do_manage_settings,
|
||||
do_api_call,
|
||||
)
|
||||
@@ -1,644 +0,0 @@
|
||||
from typing import Any, Dict, List, Optional
|
||||
import logging
|
||||
import re
|
||||
import json
|
||||
from src.constants import MAX_READ_CHARS
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Active document state
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
_active_document_id: Optional[str] = None
|
||||
_active_model: Optional[str] = None
|
||||
|
||||
|
||||
def set_active_document(doc_id: Optional[str]):
|
||||
"""Set the active document ID for document tool execution."""
|
||||
global _active_document_id
|
||||
_active_document_id = doc_id
|
||||
|
||||
|
||||
def set_active_model(model: Optional[str]):
|
||||
"""Set the current model name for version summaries."""
|
||||
global _active_model
|
||||
_active_model = model
|
||||
|
||||
|
||||
def get_active_document():
|
||||
return _active_document_id
|
||||
|
||||
|
||||
def clear_active_document(doc_id: Optional[str] = None) -> bool:
|
||||
"""Clear the in-memory active-document pointer.
|
||||
|
||||
With ``doc_id`` given, only clears when it matches the current pointer, so a
|
||||
different active document is left untouched. Returns True if it was cleared.
|
||||
|
||||
Called when a document is detached from its session or deleted (its tab is
|
||||
closed): without this, the stale pointer makes the last-resort doc-injection
|
||||
path re-surface a closed document in a later, unrelated chat — even one whose
|
||||
session no longer matches — because an unlinked doc has session_id NULL (#1160).
|
||||
"""
|
||||
global _active_document_id
|
||||
if doc_id is None or _active_document_id == doc_id:
|
||||
_active_document_id = None
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def _owned_document_query(query, Document, owner: Optional[str]):
|
||||
if owner is None:
|
||||
# A bare Python `False` is not a valid SQL expression — SQLAlchemy 1.4
|
||||
# deprecates it and 2.0 raises ArgumentError. Use the SQL `false()`
|
||||
# literal to return zero rows for an unscoped (owner-less) query.
|
||||
from sqlalchemy import false
|
||||
return query.filter(false())
|
||||
return query.filter(Document.owner == owner)
|
||||
|
||||
|
||||
def _get_owned_document(db, Document, doc_id: str, owner: Optional[str], active_only: bool = False):
|
||||
q = db.query(Document).filter(Document.id == doc_id)
|
||||
if active_only:
|
||||
q = q.filter(Document.is_active == True)
|
||||
q = _owned_document_query(q, Document, owner)
|
||||
return q.first()
|
||||
|
||||
|
||||
def _most_recent_owned_document(db, Document, owner: Optional[str], active_only: bool = False):
|
||||
q = db.query(Document)
|
||||
if active_only:
|
||||
q = q.filter(Document.is_active == True)
|
||||
q = _owned_document_query(q, Document, owner)
|
||||
return q.order_by(Document.updated_at.desc()).first()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Document tools — create/update/edit/suggest living documents
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def _sniff_doc_language(text: str) -> str:
|
||||
"""Best-effort detect a document's language from its content when the model
|
||||
didn't specify one. Defaults to 'markdown' (prose). Recognizes the common
|
||||
markup/code types the editor supports so e.g. an SVG isn't saved as markdown."""
|
||||
import json as _json, re as _re2
|
||||
s = (text or "").strip()
|
||||
if not s:
|
||||
return "markdown"
|
||||
head = s[:600]
|
||||
hl = head.lower()
|
||||
if _looks_like_email_document(s):
|
||||
return "email"
|
||||
# Markup (unambiguous)
|
||||
if "<svg" in hl:
|
||||
return "svg"
|
||||
if hl.startswith("<?xml"):
|
||||
return "xml"
|
||||
if (hl.startswith("<!doctype html") or hl.startswith("<html")
|
||||
or _re2.search(r"<(div|body|head|p|span|table|button|h[1-6]|ul|ol|li|img)\b", hl)):
|
||||
return "html"
|
||||
# JSON
|
||||
if s[0] in "{[":
|
||||
try:
|
||||
_json.loads(s)
|
||||
return "json"
|
||||
except Exception:
|
||||
pass
|
||||
# Shebang
|
||||
first = s.split("\n", 1)[0].strip().lower()
|
||||
if first.startswith("#!"):
|
||||
return "python" if "python" in first else "bash"
|
||||
# Code by strong leading signals (line-anchored so prose with stray words won't match)
|
||||
if _re2.search(r"(?m)^\s*(def \w|class \w|import \w|from \w[\w.]* import )", s):
|
||||
return "python"
|
||||
if _re2.search(r"(?m)^\s*(function \w|const \w|let \w|export |import .* from )", s):
|
||||
return "javascript"
|
||||
if _re2.search(r"(?mi)^\s*(select .* from |create table |insert into |update \w)", s):
|
||||
return "sql"
|
||||
if _re2.search(r"(?m)^[.#]?[\w-]+\s*\{[^{}]*:[^{}]*;", s):
|
||||
return "css"
|
||||
return "markdown"
|
||||
|
||||
def _looks_like_email_document(text: str = "", title: str = "") -> bool:
|
||||
import re as _re
|
||||
title_l = (title or "").strip().lower()
|
||||
if title_l in {"new email", "new mail", "new message"}:
|
||||
return True
|
||||
s = (text or "").lstrip()
|
||||
if "\n---\n" in s and _re.search(r"(?im)^To:\s*", s) and _re.search(r"(?im)^Subject:\s*", s):
|
||||
return True
|
||||
return bool(_re.search(r"(?im)^To:\s*", s) and _re.search(r"(?im)^Subject:\s*", s))
|
||||
|
||||
def _coerce_email_document_content(existing: str, incoming: str) -> str:
|
||||
"""Keep email docs in the To/Subject/---/body shape even if a model writes
|
||||
only the body or dumps header labels without the separator."""
|
||||
import re as _re
|
||||
old = existing or ""
|
||||
new = (incoming or "").strip()
|
||||
if "\n---\n" in new:
|
||||
return new
|
||||
header = old.split("\n---\n", 1)[0] if "\n---\n" in old else "To: \nSubject: "
|
||||
if _looks_like_email_document(new):
|
||||
lines = new.splitlines()
|
||||
last_header_idx = -1
|
||||
header_re = _re.compile(r"^(To|Cc|Bcc|Subject|In-Reply-To|References|X-Source-UID|X-Source-Folder|X-Attachments):", _re.I)
|
||||
for i, line in enumerate(lines):
|
||||
if header_re.match(line.strip()):
|
||||
last_header_idx = i
|
||||
body_lines = lines[last_header_idx + 1:] if last_header_idx >= 0 else lines
|
||||
while body_lines and not body_lines[0].strip():
|
||||
body_lines.pop(0)
|
||||
body = "\n".join(body_lines).strip()
|
||||
else:
|
||||
body = new
|
||||
return header.rstrip() + "\n---\n" + body
|
||||
|
||||
def _parse_tool_args(content):
|
||||
"""Parse a tool-call argument blob.
|
||||
|
||||
Accepts either a JSON string or an already-decoded dict. Unwraps the
|
||||
common `{"body": {...}}` envelope that smaller models emit when they
|
||||
read tool descriptions like "Body is JSON: {...}" literally — they
|
||||
pass `body` as a field name rather than treating it as a noun.
|
||||
|
||||
Returns a dict on success, raises ValueError on bad JSON.
|
||||
"""
|
||||
if isinstance(content, str):
|
||||
try:
|
||||
args = json.loads(content) if content.strip() else {}
|
||||
except (json.JSONDecodeError, TypeError) as e:
|
||||
raise ValueError(str(e))
|
||||
elif isinstance(content, dict):
|
||||
args = content
|
||||
else:
|
||||
args = {}
|
||||
# Unwrap {"body": {...}} envelope — but only if `body` is the sole key
|
||||
# and points at a dict. We don't want to clobber a legitimate `body`
|
||||
# field on tools where it's a real arg (e.g. send_email body text).
|
||||
if (
|
||||
isinstance(args, dict)
|
||||
and len(args) == 1
|
||||
and "body" in args
|
||||
and isinstance(args["body"], dict)
|
||||
and "action" in args["body"] # extra safety: only unwrap if the inner dict looks like a tool call
|
||||
):
|
||||
args = args["body"]
|
||||
return args
|
||||
|
||||
def parse_edit_blocks(content: str) -> list:
|
||||
"""Parse <<<FIND>>>...<<<REPLACE>>>...<<<END>>> blocks."""
|
||||
edits = []
|
||||
pattern = r'<<<FIND>>>\n(.*?)\n<<<REPLACE>>>\n(.*?)\n<<<END>>>'
|
||||
for m in re.finditer(pattern, content, re.DOTALL):
|
||||
edits.append({"find": m.group(1), "replace": m.group(2)})
|
||||
return edits
|
||||
|
||||
def parse_suggest_blocks(content: str) -> list:
|
||||
"""Parse <<<FIND>>>...<<<SUGGEST>>>...<<<REASON>>>...<<<END>>> blocks."""
|
||||
suggestions = []
|
||||
_skip_phrases = ["no change", "clear", "fine as", "looks good", "no improvement", "keep as"]
|
||||
pattern = r'<<<FIND>>>\n(.*?)\n<<<SUGGEST>>>\n(.*?)\n<<<REASON>>>\n(.*?)\n<<<END>>>'
|
||||
for m in re.finditer(pattern, content, re.DOTALL):
|
||||
find_text = m.group(1)
|
||||
replace_text = m.group(2)
|
||||
reason = m.group(3).strip()
|
||||
# Skip no-op suggestions where find == replace or reason says no change
|
||||
if find_text.strip() == replace_text.strip():
|
||||
continue
|
||||
if any(phrase in reason.lower() for phrase in _skip_phrases):
|
||||
continue
|
||||
suggestions.append({
|
||||
"id": f"sugg-{len(suggestions)+1}",
|
||||
"find": find_text,
|
||||
"replace": replace_text,
|
||||
"reason": reason,
|
||||
})
|
||||
return suggestions
|
||||
|
||||
|
||||
class CreateDocumentTool:
|
||||
async def execute(self, content: str, ctx: dict) -> dict:
|
||||
"""Create a new document. Supports two formats:
|
||||
1) Line-based: line 1 = title, line 2 (optional) = language, rest = content
|
||||
2) XML-like tags: <title>...</title><language>...</language><content>...</content>
|
||||
Some models mix them — strip any XML-style tags and fall back to line parsing."""
|
||||
import uuid, re as _re
|
||||
from src.database import SessionLocal, Document, DocumentVersion, Session as DbSession
|
||||
|
||||
raw = content or ""
|
||||
session_id = ctx.get("session_id")
|
||||
owner = ctx.get("owner")
|
||||
|
||||
# Known languages the editor understands (match the <select> in HTML)
|
||||
_KNOWN_LANGS = {
|
||||
"python", "javascript", "typescript", "html", "css", "markdown", "json",
|
||||
"yaml", "bash", "sql", "rust", "go", "java", "c", "cpp", "xml", "toml",
|
||||
"ini", "ruby", "php", "csv", "email", "text", "plain", "svg",
|
||||
}
|
||||
|
||||
# Try XML tag extraction first
|
||||
title = None
|
||||
language = None
|
||||
content = None
|
||||
mt = _re.search(r"<title>\s*(.*?)\s*</title>", raw, _re.DOTALL | _re.IGNORECASE)
|
||||
ml = _re.search(r"<language>\s*(.*?)\s*</language>", raw, _re.DOTALL | _re.IGNORECASE)
|
||||
mc = _re.search(r"<content>\s*(.*?)\s*</content>", raw, _re.DOTALL | _re.IGNORECASE)
|
||||
if mt or mc:
|
||||
title = mt.group(1).strip() if mt else None
|
||||
language = ml.group(1).strip().lower() if ml else None
|
||||
content = mc.group(1) if mc else None
|
||||
|
||||
# Fall back to line-based parsing. First strip any stray XML-ish tags.
|
||||
if title is None or content is None:
|
||||
cleaned = _re.sub(r"</?(?:title|language|content)>", "", raw)
|
||||
lines = cleaned.strip().split("\n")
|
||||
if title is None:
|
||||
title = lines[0].strip() if lines else "Untitled"
|
||||
lines = lines[1:]
|
||||
# Only consume second line as language if it looks like a valid short lang token
|
||||
if language is None and lines:
|
||||
candidate = lines[0].strip().lower()
|
||||
if candidate and len(candidate) < 20 and " " not in candidate and candidate in _KNOWN_LANGS:
|
||||
language = candidate
|
||||
lines = lines[1:]
|
||||
if content is None:
|
||||
content = "\n".join(lines)
|
||||
|
||||
# Validate language: must be in known set, else default based on content
|
||||
if language and language not in _KNOWN_LANGS:
|
||||
language = None
|
||||
if not language:
|
||||
# No explicit language — sniff it from the content so an SVG / HTML / JSON
|
||||
# / code document isn't silently saved as markdown. Prose → markdown.
|
||||
language = _sniff_doc_language(content)
|
||||
if _looks_like_email_document(content, title):
|
||||
language = "email"
|
||||
|
||||
if not title:
|
||||
title = "Untitled"
|
||||
|
||||
if not session_id:
|
||||
return {"error": "No session context for document creation"}
|
||||
|
||||
db = SessionLocal()
|
||||
try:
|
||||
doc_id = str(uuid.uuid4())
|
||||
ver_id = str(uuid.uuid4())
|
||||
|
||||
# Inherit ownership from the chat session so the doc survives that
|
||||
# session later being deleted (session_id → NULL).
|
||||
_sess = db.query(DbSession).filter(DbSession.id == session_id).first()
|
||||
if owner is not None and (not _sess or _sess.owner != owner):
|
||||
return {"error": "Cannot create document in another user's session"}
|
||||
_owner = _sess.owner if _sess else None
|
||||
|
||||
doc = Document(
|
||||
id=doc_id,
|
||||
session_id=session_id,
|
||||
title=title,
|
||||
language=language,
|
||||
current_content=content,
|
||||
version_count=1,
|
||||
is_active=True,
|
||||
owner=_owner,
|
||||
)
|
||||
ver = DocumentVersion(
|
||||
id=ver_id,
|
||||
document_id=doc_id,
|
||||
version_number=1,
|
||||
content=content,
|
||||
summary=f"Created by {_active_model or 'AI'}",
|
||||
source="ai",
|
||||
)
|
||||
db.add(doc)
|
||||
db.add(ver)
|
||||
db.commit()
|
||||
|
||||
set_active_document(doc_id)
|
||||
try:
|
||||
from src.event_bus import fire_event
|
||||
fire_event("document_created", _owner)
|
||||
except Exception:
|
||||
logger.debug("document_created event dispatch failed", exc_info=True)
|
||||
|
||||
return {
|
||||
"action": "create",
|
||||
"doc_id": doc_id,
|
||||
"title": title,
|
||||
"language": language,
|
||||
"content": content,
|
||||
"version": 1,
|
||||
}
|
||||
except Exception as e:
|
||||
db.rollback()
|
||||
return {"error": f"Failed to create document: {e}"}
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
class UpdateDocumentTool:
|
||||
async def execute(self, content: str, ctx: dict) -> Dict:
|
||||
"""Update an existing document. Content = full new document text."""
|
||||
import uuid
|
||||
from src.database import SessionLocal, Document, DocumentVersion
|
||||
|
||||
target_id = ctx.get("doc_id", None) or _active_document_id
|
||||
owner = ctx.get("owner")
|
||||
|
||||
db = SessionLocal()
|
||||
try:
|
||||
doc = None
|
||||
if target_id:
|
||||
doc = _get_owned_document(db, Document, target_id, owner)
|
||||
if not doc:
|
||||
doc = _most_recent_owned_document(db, Document, owner)
|
||||
if doc:
|
||||
target_id = doc.id
|
||||
set_active_document(target_id)
|
||||
logger.info(f"update_document: fell back to most recent doc id={target_id}")
|
||||
if not doc:
|
||||
return {"error": "No documents exist to update"}
|
||||
|
||||
is_email_doc = doc.language == "email" or _looks_like_email_document(doc.current_content or "", doc.title or "")
|
||||
new_content = _coerce_email_document_content(doc.current_content or "", content) if is_email_doc else content.strip()
|
||||
if is_email_doc:
|
||||
doc.language = "email"
|
||||
|
||||
new_ver = doc.version_count + 1
|
||||
ver = DocumentVersion(
|
||||
id=str(uuid.uuid4()),
|
||||
document_id=target_id,
|
||||
version_number=new_ver,
|
||||
content=new_content,
|
||||
summary=f"Updated by {_active_model or 'AI'}",
|
||||
source="ai",
|
||||
)
|
||||
doc.current_content = new_content
|
||||
doc.version_count = new_ver
|
||||
db.add(ver)
|
||||
db.commit()
|
||||
|
||||
return {
|
||||
"action": "update",
|
||||
"doc_id": target_id,
|
||||
"title": doc.title,
|
||||
"language": doc.language,
|
||||
"content": new_content,
|
||||
"version": new_ver,
|
||||
}
|
||||
except Exception as e:
|
||||
db.rollback()
|
||||
return {"error": f"Failed to update document: {e}"}
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
class EditDocumentTool:
|
||||
async def execute(self, content: str, ctx: dict) -> Dict:
|
||||
"""Apply targeted FIND/REPLACE edits to an existing document."""
|
||||
import uuid
|
||||
from src.database import SessionLocal, Document, DocumentVersion
|
||||
|
||||
target_id = ctx.get("doc_id", None) or _active_document_id
|
||||
owner = ctx.get("owner")
|
||||
|
||||
edits = parse_edit_blocks(content)
|
||||
if not edits:
|
||||
return {"error": "No valid <<<FIND>>>...<<<REPLACE>>>...<<<END>>> blocks found"}
|
||||
|
||||
db = SessionLocal()
|
||||
try:
|
||||
doc = None
|
||||
if target_id:
|
||||
doc = _get_owned_document(db, Document, target_id, owner)
|
||||
if not doc:
|
||||
# Fallback: most recently updated document. Avoids "no active doc" errors
|
||||
# after server restart or when the agent loses track of which doc to edit.
|
||||
doc = _most_recent_owned_document(db, Document, owner)
|
||||
if doc:
|
||||
target_id = doc.id
|
||||
set_active_document(target_id)
|
||||
logger.info(f"edit_document: fell back to most recent doc id={target_id} title={doc.title!r}")
|
||||
if not doc:
|
||||
return {"error": "No documents exist to edit"}
|
||||
|
||||
updated_content = doc.current_content
|
||||
applied = 0
|
||||
skipped = 0
|
||||
for edit in edits:
|
||||
_find = edit["find"]
|
||||
if _find in updated_content:
|
||||
updated_content = updated_content.replace(_find, edit["replace"], 1)
|
||||
applied += 1
|
||||
else:
|
||||
# Defensive: the active-doc context shows a "N\t" line-number
|
||||
# gutter for reference. Weaker models sometimes copy that prefix
|
||||
# into FIND. If the exact match failed, retry with a leading
|
||||
# "<digits><tab>" stripped from each FIND line — but only use it
|
||||
# when that stripped form actually matches, so we never corrupt a
|
||||
# legitimately tab-prefixed document.
|
||||
_stripped = "\n".join(re.sub(r"^\d+\t", "", _l) for _l in _find.split("\n"))
|
||||
if _stripped != _find and _stripped in updated_content:
|
||||
updated_content = updated_content.replace(_stripped, edit["replace"], 1)
|
||||
applied += 1
|
||||
logger.info("edit_document: matched after stripping line-number gutter from FIND")
|
||||
else:
|
||||
logger.warning(f"edit_document: FIND text not found, skipping: {_find[:80]!r}")
|
||||
skipped += 1
|
||||
|
||||
if applied == 0:
|
||||
return {"error": f"No edits applied — none of the FIND blocks matched the document content (skipped {skipped})"}
|
||||
|
||||
new_ver = doc.version_count + 1
|
||||
ver = DocumentVersion(
|
||||
id=str(uuid.uuid4()),
|
||||
document_id=target_id,
|
||||
version_number=new_ver,
|
||||
content=updated_content,
|
||||
summary=f"Edited by {_active_model or 'AI'} ({applied} edit(s))",
|
||||
source="ai",
|
||||
)
|
||||
doc.current_content = updated_content
|
||||
doc.version_count = new_ver
|
||||
db.add(ver)
|
||||
db.commit()
|
||||
|
||||
return {
|
||||
"action": "edit",
|
||||
"doc_id": target_id,
|
||||
"title": doc.title,
|
||||
"language": doc.language,
|
||||
"content": updated_content,
|
||||
"version": new_ver,
|
||||
"applied": applied,
|
||||
"skipped": skipped,
|
||||
}
|
||||
except Exception as e:
|
||||
db.rollback()
|
||||
return {"error": f"Failed to edit document: {e}"}
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
class SuggestDocumentTool:
|
||||
async def execute(self, content: str, ctx: dict) -> Dict:
|
||||
"""Create inline suggestions for the active document WITHOUT modifying it."""
|
||||
from src.database import SessionLocal, Document
|
||||
|
||||
target_id = ctx.get("doc_id", None) or _active_document_id
|
||||
owner = ctx.get("owner")
|
||||
|
||||
if not target_id:
|
||||
return {"error": "No active document to suggest on"}
|
||||
|
||||
suggestions = parse_suggest_blocks(content)
|
||||
if not suggestions:
|
||||
return {"error": "No valid <<<FIND>>>...<<<SUGGEST>>>...<<<REASON>>>...<<<END>>> blocks found"}
|
||||
|
||||
db = SessionLocal()
|
||||
try:
|
||||
doc = _get_owned_document(db, Document, target_id, owner)
|
||||
if not doc:
|
||||
return {"error": f"Document {target_id} not found"}
|
||||
|
||||
# Validate that FIND text exists in document
|
||||
valid = []
|
||||
for s in suggestions:
|
||||
if s["find"] in doc.current_content:
|
||||
valid.append(s)
|
||||
else:
|
||||
logger.warning(f"suggest_document: FIND text not found, skipping: {s['find'][:80]!r}")
|
||||
|
||||
if not valid:
|
||||
return {"error": "No suggestions matched the document content"}
|
||||
|
||||
return {
|
||||
"action": "suggest",
|
||||
"doc_id": target_id,
|
||||
"suggestions": valid,
|
||||
"count": len(valid),
|
||||
}
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Document management tool (delete, list, organize)
|
||||
# ---------------------------------------------------------------------------
|
||||
class ManageDocumentTool:
|
||||
async def execute(self, content: str, ctx: dict) -> Dict:
|
||||
"""Manage documents: list, read/view/open, delete, tidy.
|
||||
|
||||
Output format mirrors `manage_session`: list rows include a
|
||||
clickable `[Title](#document-<id>)` anchor + relative timestamps
|
||||
so the user can click straight from chat to open the editor.
|
||||
"""
|
||||
from core.database import SessionLocal, Document
|
||||
from datetime import datetime, timezone
|
||||
|
||||
owner = ctx.get("owner")
|
||||
|
||||
try:
|
||||
args = _parse_tool_args(content)
|
||||
except ValueError:
|
||||
return {"error": "Invalid JSON arguments", "exit_code": 1}
|
||||
|
||||
action = args.get("action", "list")
|
||||
db = SessionLocal()
|
||||
|
||||
def _rel(ts):
|
||||
if not ts:
|
||||
return 'never'
|
||||
try:
|
||||
now = datetime.now(timezone.utc) if ts.tzinfo is not None else datetime.utcnow()
|
||||
diff = (now - ts).total_seconds()
|
||||
except Exception:
|
||||
return 'unknown'
|
||||
if diff < 60: return 'just now'
|
||||
if diff < 3600: return f'{int(diff / 60)}m ago'
|
||||
if diff < 86400: return f'{int(diff / 3600)}h ago'
|
||||
if diff < 86400 * 7: return f'{int(diff / 86400)}d ago'
|
||||
return ts.strftime('%Y-%m-%d')
|
||||
|
||||
try:
|
||||
if action == "list":
|
||||
q = db.query(Document).filter(Document.is_active == True)
|
||||
q = _owned_document_query(q, Document, owner)
|
||||
if args.get("search"):
|
||||
q = q.filter(Document.title.ilike(f"%{args['search']}%"))
|
||||
if args.get("language"):
|
||||
q = q.filter(Document.language == args["language"])
|
||||
docs = q.order_by(Document.updated_at.desc()).limit(args.get("limit", 50)).all()
|
||||
if not docs:
|
||||
msg = "No documents found" + (f" matching '{args['search']}'" if args.get("search") else "") + "."
|
||||
return {"response": msg, "documents": [], "exit_code": 0}
|
||||
lines = []
|
||||
items = []
|
||||
for i, d in enumerate(docs):
|
||||
size = len(d.current_content or "")
|
||||
lang = d.language or "text"
|
||||
ts = getattr(d, 'updated_at', None) or getattr(d, 'created_at', None)
|
||||
marker = " ← most recent" if i == 0 else ""
|
||||
lines.append(
|
||||
f"- [{d.title}](#document-{d.id}) — {lang}, {size} chars, updated {_rel(ts)}{marker}"
|
||||
)
|
||||
items.append({"id": d.id, "title": d.title, "language": lang, "size": size})
|
||||
header = f"Found {len(docs)} document(s), sorted most-recent first. Click a title to open:"
|
||||
return {
|
||||
"response": header + "\n" + "\n".join(lines),
|
||||
"documents": items,
|
||||
"exit_code": 0,
|
||||
}
|
||||
|
||||
elif action in ("read", "view", "open", "get"):
|
||||
doc_id = args.get("document_id") or args.get("id") or args.get("uid")
|
||||
if not doc_id:
|
||||
return {"error": "Need document_id (use action=list to find one)", "exit_code": 1}
|
||||
doc = _get_owned_document(db, Document, doc_id, owner, active_only=True)
|
||||
if not doc:
|
||||
return {"error": f"Document '{doc_id}' not found", "exit_code": 1}
|
||||
body = doc.current_content or ""
|
||||
preview_limit = int(args.get("limit", MAX_READ_CHARS))
|
||||
truncated = len(body) > preview_limit
|
||||
preview = body[:preview_limit] + (f"\n... (truncated, {len(body)} chars total)" if truncated else "")
|
||||
anchor = f"[{doc.title}](#document-{doc.id})"
|
||||
return {
|
||||
"response": f"{anchor} — click to open in editor.\n\n```{doc.language or ''}\n{preview}\n```",
|
||||
"document": {
|
||||
"id": doc.id,
|
||||
"title": doc.title,
|
||||
"language": doc.language,
|
||||
"size": len(body),
|
||||
"content": preview,
|
||||
"truncated": truncated,
|
||||
},
|
||||
"exit_code": 0,
|
||||
}
|
||||
|
||||
elif action == "delete":
|
||||
doc_id = args.get("document_id") or args.get("id") or args.get("uid") or _active_document_id
|
||||
doc = None
|
||||
if doc_id:
|
||||
doc = _get_owned_document(db, Document, doc_id, owner)
|
||||
if not doc:
|
||||
# Fallback: most recently updated doc (likely what the user means)
|
||||
doc = _most_recent_owned_document(db, Document, owner, active_only=True)
|
||||
if not doc:
|
||||
return {"error": "No document to delete", "exit_code": 1}
|
||||
title = doc.title
|
||||
doc.is_active = False
|
||||
db.commit()
|
||||
if _active_document_id == doc.id:
|
||||
set_active_document(None)
|
||||
return {"response": f"Deleted document '{title}'", "exit_code": 0}
|
||||
|
||||
elif action == "tidy":
|
||||
from src.document_actions import run_document_tidy
|
||||
result = await run_document_tidy(owner or "")
|
||||
return {"response": result, "exit_code": 0}
|
||||
|
||||
else:
|
||||
return {"error": f"Unknown action: {action}", "exit_code": 1}
|
||||
except Exception as e:
|
||||
logger.error(f"manage_documents error: {e}")
|
||||
return {"error": str(e), "exit_code": 1}
|
||||
finally:
|
||||
db.close()
|
||||
@@ -1,398 +0,0 @@
|
||||
import asyncio
|
||||
import json
|
||||
import os
|
||||
import difflib
|
||||
import fnmatch
|
||||
import shutil
|
||||
from typing import Optional, Dict, Any, Tuple
|
||||
|
||||
from src.constants import MAX_READ_CHARS, MAX_DIFF_LINES, MAX_OUTPUT_CHARS
|
||||
|
||||
_CODENAV_SKIP_DIRS = frozenset({
|
||||
".git", ".hg", ".svn", "node_modules", "venv", ".venv", "__pycache__",
|
||||
".mypy_cache", ".pytest_cache", ".ruff_cache", "dist", "build",
|
||||
".next", ".cache", "site-packages", ".idea", ".tox",
|
||||
})
|
||||
_CODENAV_MAX_HITS = 200
|
||||
_CODENAV_MAX_LINE = 400
|
||||
|
||||
def _unified_diff(old: str, new: str, path: str) -> Optional[Dict[str, Any]]:
|
||||
if old == new:
|
||||
return None
|
||||
old_lines = old.splitlines()
|
||||
new_lines = new.splitlines()
|
||||
label = path or "file"
|
||||
diff_lines = list(difflib.unified_diff(
|
||||
old_lines, new_lines,
|
||||
fromfile=f"a/{label}", tofile=f"b/{label}",
|
||||
lineterm="",
|
||||
))
|
||||
added = sum(1 for line in diff_lines if line.startswith("+") and not line.startswith("+++"))
|
||||
removed = sum(1 for line in diff_lines if line.startswith("-") and not line.startswith("---"))
|
||||
truncated = False
|
||||
if len(diff_lines) > MAX_DIFF_LINES:
|
||||
diff_lines = diff_lines[:MAX_DIFF_LINES]
|
||||
truncated = True
|
||||
text = "\n".join(diff_lines)
|
||||
if truncated:
|
||||
text += f"\n… diff truncated at {MAX_DIFF_LINES} lines"
|
||||
return {
|
||||
"text": text,
|
||||
"added": added,
|
||||
"removed": removed,
|
||||
"new_file": old == "",
|
||||
"file": os.path.basename(path) or (path or "file"),
|
||||
}
|
||||
|
||||
class EditFileTool:
|
||||
async def execute(self, content: str, ctx: dict) -> dict:
|
||||
from src.tool_execution import _resolve_tool_path, _resolve_search_root, _truncate
|
||||
try:
|
||||
args = json.loads(content) if content.strip().startswith("{") else {}
|
||||
except (json.JSONDecodeError, TypeError):
|
||||
args = {}
|
||||
raw_path = (args.get("path") or "").strip()
|
||||
old = args.get("old_string", "")
|
||||
new = args.get("new_string", "")
|
||||
replace_all = bool(args.get("replace_all", False))
|
||||
if not raw_path:
|
||||
return {"error": "edit_file: path required", "exit_code": 1}
|
||||
try:
|
||||
path = _resolve_tool_path(raw_path)
|
||||
except ValueError as e:
|
||||
return {"error": f"edit_file: {e}", "exit_code": 1}
|
||||
if old == "":
|
||||
return {"error": "edit_file: old_string required (use write_file to create a file)", "exit_code": 1}
|
||||
if old == new:
|
||||
return {"error": "edit_file: old_string and new_string are identical", "exit_code": 1}
|
||||
|
||||
def _apply():
|
||||
"""Helper function that performs the actual string replacement and file writing logic."""
|
||||
with open(path, "r", encoding="utf-8") as f:
|
||||
original = f.read()
|
||||
count = original.count(old)
|
||||
if count == 0:
|
||||
return original, None, "not_found"
|
||||
if count > 1 and not replace_all:
|
||||
return original, None, f"not_unique:{count}"
|
||||
updated = original.replace(old, new) if replace_all else original.replace(old, new, 1)
|
||||
with open(path, "w", encoding="utf-8") as f:
|
||||
f.write(updated)
|
||||
return original, updated, "ok"
|
||||
|
||||
try:
|
||||
original, updated, status = await asyncio.to_thread(_apply)
|
||||
except FileNotFoundError:
|
||||
return {"error": f"edit_file: {path}: not found (use write_file to create it)", "exit_code": 1}
|
||||
except (IsADirectoryError, UnicodeDecodeError):
|
||||
return {"error": f"edit_file: {path}: not an editable text file", "exit_code": 1}
|
||||
except PermissionError:
|
||||
return {"error": f"edit_file: {path}: permission denied", "exit_code": 1}
|
||||
except OSError as e:
|
||||
return {"error": f"edit_file: {path}: {e}", "exit_code": 1}
|
||||
|
||||
if status == "not_found":
|
||||
return {"error": f"edit_file: old_string not found in {path}. Read the file and match it exactly.", "exit_code": 1}
|
||||
if status.startswith("not_unique"):
|
||||
n = status.split(":", 1)[1]
|
||||
return {"error": f"edit_file: old_string is not unique in {path} ({n} matches). Add surrounding context or set replace_all=true.", "exit_code": 1}
|
||||
|
||||
n = original.count(old)
|
||||
result = {"output": f"Edited {path} ({n} replacement{'s' if n != 1 else ''})", "exit_code": 0}
|
||||
diff = _unified_diff(original, updated, path)
|
||||
if diff:
|
||||
result["diff"] = diff
|
||||
return result
|
||||
|
||||
class ReadFileTool:
|
||||
async def execute(self, content: str, ctx: dict) -> dict:
|
||||
from src.tool_execution import _resolve_tool_path, _resolve_search_root, _truncate
|
||||
raw_path, offset, limit = content.split("\n", 1)[0].strip(), 0, 0
|
||||
_stripped = content.strip()
|
||||
if _stripped.startswith("{"):
|
||||
try:
|
||||
_a = json.loads(_stripped)
|
||||
raw_path = str(_a.get("path", "")).strip()
|
||||
offset = int(_a.get("offset") or 0)
|
||||
limit = int(_a.get("limit") or 0)
|
||||
except (json.JSONDecodeError, TypeError, ValueError):
|
||||
pass
|
||||
try:
|
||||
path = _resolve_tool_path(raw_path)
|
||||
except ValueError as e:
|
||||
return {"error": f"read_file: {e}", "exit_code": 1}
|
||||
try:
|
||||
def _read():
|
||||
if offset > 0 or limit > 0:
|
||||
start = max(offset, 1)
|
||||
out, n, budget = [], 0, MAX_READ_CHARS
|
||||
with open(path, "r", encoding="utf-8", errors="replace") as f:
|
||||
for i, line in enumerate(f, 1):
|
||||
if i < start:
|
||||
continue
|
||||
if limit > 0 and n >= limit:
|
||||
break
|
||||
out.append(line)
|
||||
n += 1
|
||||
budget -= len(line)
|
||||
if budget <= 0:
|
||||
out.append(f"\n... [truncated at {MAX_READ_CHARS} chars]")
|
||||
break
|
||||
return "".join(out)
|
||||
with open(path, "r", encoding="utf-8", errors="replace") as f:
|
||||
return f.read(MAX_READ_CHARS + 1)
|
||||
data = await asyncio.to_thread(_read)
|
||||
except FileNotFoundError:
|
||||
return {"error": f"read_file: {path}: not found", "exit_code": 1}
|
||||
except PermissionError:
|
||||
return {"error": f"read_file: {path}: permission denied", "exit_code": 1}
|
||||
except IsADirectoryError:
|
||||
return {"error": f"read_file: {path}: is a directory (use ls)", "exit_code": 1}
|
||||
except OSError as e:
|
||||
return {"error": f"read_file: {path}: {e}", "exit_code": 1}
|
||||
if not (offset > 0 or limit > 0) and len(data) > MAX_READ_CHARS:
|
||||
data = data[:MAX_READ_CHARS] + f"\n... [truncated at {MAX_READ_CHARS} chars]"
|
||||
return {"output": data, "exit_code": 0}
|
||||
|
||||
class WriteFileTool:
|
||||
async def execute(self, content: str, ctx: dict) -> dict:
|
||||
from src.tool_execution import _resolve_tool_path, _resolve_search_root, _truncate
|
||||
lines = content.split("\n", 1)
|
||||
raw_path = lines[0].strip()
|
||||
body = lines[1] if len(lines) > 1 else ""
|
||||
try:
|
||||
path = _resolve_tool_path(raw_path)
|
||||
except ValueError as e:
|
||||
return {"error": f"write_file: {e}", "exit_code": 1}
|
||||
try:
|
||||
def _write():
|
||||
old = ""
|
||||
try:
|
||||
with open(path, "r", encoding="utf-8") as f:
|
||||
old = f.read()
|
||||
except (FileNotFoundError, IsADirectoryError, UnicodeDecodeError, OSError):
|
||||
old = ""
|
||||
d = os.path.dirname(path)
|
||||
if d:
|
||||
os.makedirs(d, exist_ok=True)
|
||||
with open(path, "w", encoding="utf-8") as f:
|
||||
f.write(body)
|
||||
return old, len(body)
|
||||
old_content, size = await asyncio.to_thread(_write)
|
||||
except PermissionError:
|
||||
return {"error": f"write_file: {path}: permission denied", "exit_code": 1}
|
||||
except OSError as e:
|
||||
return {"error": f"write_file: {path}: {e}", "exit_code": 1}
|
||||
diff = _unified_diff(old_content, body, path)
|
||||
result = {"output": f"Wrote {size} bytes to {path}", "exit_code": 0}
|
||||
if diff:
|
||||
result["diff"] = diff
|
||||
return result
|
||||
|
||||
class LsTool:
|
||||
async def execute(self, content: str, ctx: dict) -> dict:
|
||||
from src.tool_execution import _resolve_tool_path, _resolve_search_root, _truncate
|
||||
raw_path = ""
|
||||
_s = (content or "").strip()
|
||||
if _s.startswith("{"):
|
||||
try:
|
||||
raw_path = str(json.loads(_s).get("path", "")).strip()
|
||||
except json.JSONDecodeError:
|
||||
raw_path = ""
|
||||
else:
|
||||
raw_path = _s.split("\n", 1)[0].strip()
|
||||
try:
|
||||
root = _resolve_search_root(raw_path)
|
||||
except ValueError as e:
|
||||
return {"error": f"ls: {e}", "exit_code": 1}
|
||||
|
||||
def _ls():
|
||||
if not os.path.isdir(root):
|
||||
return None, f"ls: {root}: not a directory"
|
||||
rows = []
|
||||
try:
|
||||
with os.scandir(root) as it:
|
||||
for entry in it:
|
||||
if entry.name.startswith("."):
|
||||
continue
|
||||
try:
|
||||
is_dir = entry.is_dir(follow_symlinks=False)
|
||||
size = entry.stat(follow_symlinks=False).st_size if not is_dir else 0
|
||||
except OSError:
|
||||
continue
|
||||
rows.append((is_dir, entry.name, size))
|
||||
except (PermissionError, OSError) as _e:
|
||||
return None, f"ls: {_e}"
|
||||
rows.sort(key=lambda r: (not r[0], r[1].lower()))
|
||||
lines = [f"{root}:"]
|
||||
for is_dir, name, size in rows[:_CODENAV_MAX_HITS]:
|
||||
lines.append(f" {name}/" if is_dir else f" {name} ({size} B)")
|
||||
if len(rows) > _CODENAV_MAX_HITS:
|
||||
lines.append(f" ... [{len(rows) - _CODENAV_MAX_HITS} more]")
|
||||
if not rows:
|
||||
lines.append(" (empty)")
|
||||
return "\n".join(lines), None
|
||||
|
||||
out, err = await asyncio.to_thread(_ls)
|
||||
if err:
|
||||
return {"error": err, "exit_code": 1}
|
||||
return {"output": _truncate(out), "exit_code": 0}
|
||||
|
||||
class GlobTool:
|
||||
async def execute(self, content: str, ctx: dict) -> dict:
|
||||
from src.tool_execution import _resolve_tool_path, _resolve_search_root, _truncate
|
||||
args = {}
|
||||
_s = (content or "").strip()
|
||||
if _s.startswith("{"):
|
||||
try:
|
||||
args = json.loads(_s)
|
||||
except json.JSONDecodeError:
|
||||
args = {}
|
||||
else:
|
||||
args = {"pattern": _s}
|
||||
pattern = str(args.get("pattern", "")).strip()
|
||||
if not pattern:
|
||||
return {"error": "glob: pattern is required", "exit_code": 1}
|
||||
try:
|
||||
root = _resolve_search_root(str(args.get("path", "")))
|
||||
except ValueError as e:
|
||||
return {"error": f"glob: {e}", "exit_code": 1}
|
||||
|
||||
def _glob():
|
||||
from pathlib import Path
|
||||
base = Path(root)
|
||||
if not base.is_dir():
|
||||
return None, f"glob: {root}: not a directory"
|
||||
matched = []
|
||||
try:
|
||||
for p in base.rglob(pattern):
|
||||
if set(p.relative_to(base).parts) & _CODENAV_SKIP_DIRS:
|
||||
continue
|
||||
try:
|
||||
mtime = p.stat().st_mtime
|
||||
except OSError:
|
||||
mtime = 0
|
||||
matched.append((mtime, str(p)))
|
||||
if len(matched) > _CODENAV_MAX_HITS * 5:
|
||||
break
|
||||
except (OSError, ValueError) as _e:
|
||||
return None, f"glob: {_e}"
|
||||
matched.sort(key=lambda t: t[0], reverse=True)
|
||||
return [pth for _, pth in matched[:_CODENAV_MAX_HITS]], None
|
||||
|
||||
paths, err = await asyncio.to_thread(_glob)
|
||||
if err:
|
||||
return {"error": err, "exit_code": 1}
|
||||
if not paths:
|
||||
return {"output": f"No files matching {pattern!r} under {root}", "exit_code": 0}
|
||||
out = "\n".join(paths)
|
||||
if len(paths) >= _CODENAV_MAX_HITS:
|
||||
out += f"\n... [capped at {_CODENAV_MAX_HITS} files]"
|
||||
return {"output": _truncate(out), "exit_code": 0}
|
||||
|
||||
class GrepTool:
|
||||
async def execute(self, content: str, ctx: dict) -> dict:
|
||||
from src.tool_execution import _resolve_tool_path, _resolve_search_root, _truncate
|
||||
args: Dict[str, Any] = {}
|
||||
_s = (content or "").strip()
|
||||
if _s.startswith("{"):
|
||||
try:
|
||||
args = json.loads(_s)
|
||||
except json.JSONDecodeError:
|
||||
args = {}
|
||||
else:
|
||||
args = {"pattern": _s}
|
||||
pattern = str(args.get("pattern", "")).strip()
|
||||
if not pattern:
|
||||
return {"error": "grep: pattern is required", "exit_code": 1}
|
||||
ignore_case = bool(args.get("ignore_case"))
|
||||
glob_pat = str(args.get("glob", "") or "").strip()
|
||||
try:
|
||||
max_hits = int(args.get("max_results") or _CODENAV_MAX_HITS)
|
||||
except (TypeError, ValueError):
|
||||
max_hits = _CODENAV_MAX_HITS
|
||||
max_hits = max(1, min(max_hits, _CODENAV_MAX_HITS))
|
||||
try:
|
||||
root = _resolve_search_root(str(args.get("path", "")))
|
||||
except ValueError as e:
|
||||
return {"error": f"grep: {e}", "exit_code": 1}
|
||||
|
||||
def _grep():
|
||||
import re as _re
|
||||
import shutil
|
||||
rg = shutil.which("rg")
|
||||
if rg:
|
||||
cmd = [rg, "--line-number", "--no-heading", "--color=never",
|
||||
"--max-count", str(max_hits)]
|
||||
if ignore_case:
|
||||
cmd.append("--ignore-case")
|
||||
if glob_pat:
|
||||
cmd += ["--glob", glob_pat]
|
||||
for _d in _CODENAV_SKIP_DIRS:
|
||||
cmd += ["--glob", f"!**/{_d}/**"]
|
||||
cmd += ["--regexp", pattern, root]
|
||||
try:
|
||||
import subprocess
|
||||
p = subprocess.run(cmd, capture_output=True, text=True, timeout=20)
|
||||
lines = [ln for ln in (p.stdout or "").splitlines() if ln][:max_hits]
|
||||
return lines, None
|
||||
except subprocess.TimeoutExpired:
|
||||
return None, "grep: timed out"
|
||||
except Exception as _e:
|
||||
return None, f"grep: {_e}"
|
||||
try:
|
||||
rx = _re.compile(pattern, _re.IGNORECASE if ignore_case else 0)
|
||||
except _re.error as _e:
|
||||
return None, f"grep: bad pattern: {_e}"
|
||||
hits = []
|
||||
if os.path.isfile(root):
|
||||
file_iter = [root]
|
||||
else:
|
||||
file_iter = []
|
||||
for dp, dns, fns in os.walk(root):
|
||||
dns[:] = [d for d in dns if d not in _CODENAV_SKIP_DIRS]
|
||||
for fn in fns:
|
||||
if glob_pat and not fnmatch.fnmatch(fn, glob_pat):
|
||||
continue
|
||||
file_iter.append(os.path.join(dp, fn))
|
||||
for fp in file_iter:
|
||||
if len(hits) >= max_hits:
|
||||
break
|
||||
try:
|
||||
with open(fp, "r", encoding="utf-8", errors="strict") as f:
|
||||
for i, line in enumerate(f, 1):
|
||||
if rx.search(line):
|
||||
hits.append(f"{fp}:{i}:{line.rstrip()[:_CODENAV_MAX_LINE]}")
|
||||
if len(hits) >= max_hits:
|
||||
break
|
||||
except (UnicodeDecodeError, OSError):
|
||||
continue
|
||||
return hits, None
|
||||
|
||||
lines, err = await asyncio.to_thread(_grep)
|
||||
if err:
|
||||
return {"error": err, "exit_code": 1}
|
||||
if not lines:
|
||||
return {"output": f"No matches for {pattern!r} under {root}", "exit_code": 0}
|
||||
out = "\n".join(ln[:_CODENAV_MAX_LINE] for ln in lines)
|
||||
if len(lines) >= max_hits:
|
||||
out += f"\n... [capped at {max_hits} matches]"
|
||||
return {"output": _truncate(out), "exit_code": 0}
|
||||
|
||||
class GetWorkspaceTool:
|
||||
"""Report the active workspace folder (no args). File tools are confined to
|
||||
it; the shell starts there (cwd) but is NOT sandboxed."""
|
||||
async def execute(self, content: str, ctx: dict) -> dict:
|
||||
from src.tool_execution import get_active_workspace
|
||||
ws = get_active_workspace()
|
||||
if ws:
|
||||
return {
|
||||
"output": f"{ws}\n(File tools are confined to this folder; the shell starts "
|
||||
f"here but is not sandboxed and can reach outside it.)",
|
||||
"exit_code": 0,
|
||||
}
|
||||
return {
|
||||
"output": "No workspace is set. File tools use the default allowed roots; "
|
||||
"resolve paths from the user or use absolute paths.",
|
||||
"exit_code": 0,
|
||||
}
|
||||
@@ -1,153 +0,0 @@
|
||||
import asyncio
|
||||
import sys
|
||||
import time
|
||||
import collections
|
||||
from typing import Optional, Callable, Awaitable, Tuple, Dict
|
||||
from src.constants import MAX_OUTPUT_CHARS
|
||||
|
||||
DEFAULT_BASH_TIMEOUT = 60 * 60 # 1 hour
|
||||
DEFAULT_PYTHON_TIMEOUT = 60 * 60
|
||||
|
||||
PROGRESS_INTERVAL_S = 2.0
|
||||
PROGRESS_TAIL_LINES = 12
|
||||
|
||||
async def _run_subprocess_streaming(
|
||||
proc: asyncio.subprocess.Process,
|
||||
*,
|
||||
timeout: float,
|
||||
progress_cb: Optional[Callable[[Dict], Awaitable[None]]] = None,
|
||||
) -> Tuple[str, str, Optional[int], bool]:
|
||||
started = time.time()
|
||||
stdout_full: list[str] = []
|
||||
stderr_full: list[str] = []
|
||||
tail = collections.deque(maxlen=PROGRESS_TAIL_LINES)
|
||||
|
||||
async def _reader(stream, full_buf, label: str):
|
||||
if stream is None:
|
||||
return
|
||||
while True:
|
||||
line = await stream.readline()
|
||||
if not line:
|
||||
break
|
||||
decoded = line.decode("utf-8", errors="replace").rstrip("\n")
|
||||
full_buf.append(decoded)
|
||||
if label == "err":
|
||||
tail.append(f"! {decoded}")
|
||||
else:
|
||||
tail.append(decoded)
|
||||
|
||||
async def _progress_emitter():
|
||||
await asyncio.sleep(PROGRESS_INTERVAL_S)
|
||||
while True:
|
||||
if progress_cb:
|
||||
try:
|
||||
await progress_cb({
|
||||
"elapsed_s": round(time.time() - started, 1),
|
||||
"tail": "\n".join(list(tail)),
|
||||
})
|
||||
except Exception:
|
||||
pass
|
||||
await asyncio.sleep(PROGRESS_INTERVAL_S)
|
||||
|
||||
rd_out = asyncio.create_task(_reader(proc.stdout, stdout_full, "out"))
|
||||
rd_err = asyncio.create_task(_reader(proc.stderr, stderr_full, "err"))
|
||||
prog_task = asyncio.create_task(_progress_emitter()) if progress_cb else None
|
||||
|
||||
timed_out = False
|
||||
try:
|
||||
await asyncio.wait_for(proc.wait(), timeout=timeout)
|
||||
except asyncio.TimeoutError:
|
||||
timed_out = True
|
||||
try:
|
||||
proc.kill()
|
||||
except Exception:
|
||||
pass
|
||||
try:
|
||||
await asyncio.wait_for(proc.wait(), timeout=2)
|
||||
except Exception:
|
||||
pass
|
||||
except asyncio.CancelledError:
|
||||
try:
|
||||
proc.kill()
|
||||
except Exception:
|
||||
pass
|
||||
try:
|
||||
await asyncio.wait_for(proc.wait(), timeout=2)
|
||||
except Exception:
|
||||
pass
|
||||
for t in (rd_out, rd_err):
|
||||
t.cancel()
|
||||
if prog_task is not None:
|
||||
prog_task.cancel()
|
||||
raise
|
||||
finally:
|
||||
if prog_task is not None and not prog_task.done():
|
||||
prog_task.cancel()
|
||||
try:
|
||||
await prog_task
|
||||
except (asyncio.CancelledError, Exception):
|
||||
pass
|
||||
for t in (rd_out, rd_err):
|
||||
try:
|
||||
await asyncio.wait_for(t, timeout=1)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
return (
|
||||
"\n".join(stdout_full),
|
||||
"\n".join(stderr_full),
|
||||
proc.returncode,
|
||||
timed_out,
|
||||
)
|
||||
|
||||
class BashTool:
|
||||
async def execute(self, content: str, ctx: dict) -> dict:
|
||||
from src.tool_execution import agent_cwd, _truncate
|
||||
progress_cb = ctx.get("progress_cb")
|
||||
_subproc_env = ctx.get("subproc_env")
|
||||
proc = await asyncio.create_subprocess_shell(
|
||||
content,
|
||||
stdout=asyncio.subprocess.PIPE,
|
||||
stderr=asyncio.subprocess.PIPE,
|
||||
env=_subproc_env,
|
||||
cwd=agent_cwd(),
|
||||
)
|
||||
stdout, stderr, rc, timed_out = await _run_subprocess_streaming(
|
||||
proc,
|
||||
timeout=DEFAULT_BASH_TIMEOUT,
|
||||
progress_cb=progress_cb,
|
||||
)
|
||||
if timed_out:
|
||||
return {"error": f"bash: timed out after {DEFAULT_BASH_TIMEOUT}s — process killed", "exit_code": 124, "stdout": _truncate(stdout, MAX_OUTPUT_CHARS), "stderr": _truncate(stderr, MAX_OUTPUT_CHARS)}
|
||||
output = stdout.rstrip()
|
||||
err = stderr.rstrip()
|
||||
if err:
|
||||
output = (output + "\nSTDERR: " + err).strip() if output else "STDERR: " + err
|
||||
output = _truncate(output, MAX_OUTPUT_CHARS)
|
||||
return {"output": output or "(no output)", "exit_code": rc or 0}
|
||||
|
||||
class PythonTool:
|
||||
async def execute(self, content: str, ctx: dict) -> dict:
|
||||
from src.tool_execution import agent_cwd, _truncate
|
||||
progress_cb = ctx.get("progress_cb")
|
||||
_subproc_env = ctx.get("subproc_env")
|
||||
proc = await asyncio.create_subprocess_exec(
|
||||
(sys.executable or "python"), "-I", "-c", content,
|
||||
stdout=asyncio.subprocess.PIPE,
|
||||
stderr=asyncio.subprocess.PIPE,
|
||||
env=_subproc_env,
|
||||
cwd=agent_cwd(),
|
||||
)
|
||||
stdout, stderr, rc, timed_out = await _run_subprocess_streaming(
|
||||
proc,
|
||||
timeout=DEFAULT_PYTHON_TIMEOUT,
|
||||
progress_cb=progress_cb,
|
||||
)
|
||||
if timed_out:
|
||||
return {"error": f"python: timed out after {DEFAULT_PYTHON_TIMEOUT}s — process killed", "exit_code": 124, "stdout": _truncate(stdout, MAX_OUTPUT_CHARS), "stderr": _truncate(stderr, MAX_OUTPUT_CHARS)}
|
||||
output = stdout.rstrip()
|
||||
err = stderr.rstrip()
|
||||
if err:
|
||||
output = (output + "\nSTDERR: " + err).strip() if output else "STDERR: " + err
|
||||
output = _truncate(output, MAX_OUTPUT_CHARS)
|
||||
return {"output": output or "(no output)", "exit_code": rc or 0}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user