Merge branch 'dev' into test/layout-inventory-3712

.dockerignore

@@ -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/

.env.example

@@ -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

.github/CODEOWNERS

@@ -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.

.github/dependabot.yml

@@ -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

.github/pull_request_review_template.md

@@ -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>![P2 Badge](https://img.shields.io/badge/P2-yellow?style=flat)</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:** `![P0 Badge](https://img.shields.io/badge/P0-red?style=flat)` -
-    release-blocking or actively dangerous.
-  - **P1:** `![P1 Badge](https://img.shields.io/badge/P1-orange?style=flat)` -
-    serious bug, security risk, data-loss risk, or broken primary flow.
-  - **P2:** `![P2 Badge](https://img.shields.io/badge/P2-yellow?style=flat)` -
-    meaningful correctness, test, maintainability, or edge-case issue.
-  - **P3:** `![P3 Badge](https://img.shields.io/badge/P3-lightgrey?style=flat)` -
-    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.

.github/workflows/ci.yml

@@ -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"

.github/workflows/container-scan.yml

@@ -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

.github/workflows/container-trivy.yml

@@ -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

.github/workflows/dependency-review.yml

@@ -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

.github/workflows/secret-scan.yml

@@ -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 .

.github/workflows/workflow-security.yml

@@ -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/

.gitignore

@@ -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

Dockerfile

@@ -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,

README.md

@@ -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>
+![Odysseus](docs/odysseus.jpg)
 
-<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
+![Chat & Agents](docs/chat.gif)
+### Deep Research
+![Deep Research](docs/research.gif)
+### Compare
+![Compare](docs/compare.gif)
+### Documents
+![Documents](docs/document.gif)
+### Notes & Tasks
+![Notes & Tasks](docs/notes.gif)
+
+</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. |
+| `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). |
+
+### 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
-
 AGPL-3.0-or-later -- see [LICENSE](LICENSE) and [ACKNOWLEDGMENTS.md](ACKNOWLEDGMENTS.md).
+
+```
+                                  |
+                                 |||
+                                |||||
+                  |    |    |   |||||||
+                 )_)  )_)  )_)   ~|~
+                )___))___))___)\  |
+               )____)____)_____)\\|
+             _____|____|____|_____\\\__
+             \                       /
+       ~^~^~~^~^~~^~^~~^~^~~^~^~~^~^~~^~^~~^~^~
+               ~^~  all aboard!  ~^~
+       ~^~^~~^~^~~^~^~~^~^~~^~^~~^~^~~^~^~~^~^~
+```

app.py

@@ -69,37 +69,10 @@ 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"
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
 )
-    _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}")
-
 logger = logging.getLogger(__name__)
 
 # ========= APP =========
@@ -167,7 +140,6 @@ _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
 )
 
 

core/auth.py

@@ -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
@@ -84,15 +83,6 @@ 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."""
 
@@ -397,69 +387,6 @@ 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:

core/database.py

@@ -1602,7 +1602,6 @@ 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")
 
@@ -1633,27 +1632,10 @@ 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"
@@ -1785,7 +1767,6 @@ 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()
@@ -2086,31 +2067,6 @@ def _migrate_add_calendar_account_id():
             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}")
-
-
 def _migrate_add_calendar_metadata():
     """Add importance/event_type/last_pinged columns to calendar_events table."""
     import sqlite3

core/platform_compat.py

@@ -300,7 +300,7 @@ 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:

docker-compose.gpu-amd.yml

@@ -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.

docker-compose.gpu-nvidia.yml

@@ -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.

docker-compose.yml

@@ -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.

docs/agent-migration.md

@@ -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.

docs/backup-restore.md

@@ -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.

docs/security-ci.md

@@ -1,102 +0,0 @@
-# Security CI guide
-
-This project runs a set of automated security checks on every pull request and
-on every push to `main`. 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
-
-Each check lives in its own file under `.github/workflows/`. 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**, you have two ways to scan the app code with CodeQL:
-   - The included `codeql.yml` workflow already scans `main` and runs weekly.
-   - To also scan **pull requests** (recommended, since most contributions come
-     from forks), click **Set up -> Default** under Code scanning. GitHub then
-     runs CodeQL on pull requests for you, with no token limitations.
-
-## 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.

docs/setup.md

@@ -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).

integrations/claude/skills/odysseus/SKILL.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.
 

integrations/claude/skills/odysseus/scripts/odysseus_api.py

@@ -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":

integrations/codex/scripts/odysseus_api.py

@@ -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":

integrations/codex/skills/odysseus/SKILL.md

@@ -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.
 

launch-windows.ps1

@@ -141,20 +141,7 @@ 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 ""

mcp_servers/email_server.py

@@ -885,109 +885,8 @@ 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"])

mcp_servers/memory_server.py

@@ -93,15 +93,16 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
             if category_filter:
                 msg += f" in category '{category_filter}'"
             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}")
+        if len(memories) > 100:
+            lines.append(f"... and {len(memories) - 100} more")
         return [TextContent(type="text", text="\n".join(lines))]
 
     elif action == "add":

package-lock.json

@@ -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",

package.json

@@ -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"
   }
 }

requirements-optional.txt

@@ -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

requirements.txt

@@ -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

routes/api_token_routes.py

@@ -31,7 +31,6 @@ ALLOWED_SCOPES = {
 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"],
 }
 

routes/auth_routes.py

@@ -12,7 +12,7 @@ import re
 from pathlib import Path
 
 from core.atomic_io import atomic_write_json, atomic_write_text
-from core.auth import AuthManager, SetAdminResult
+from core.auth import AuthManager
 from src.constants import DEEP_RESEARCH_DIR, MEMORY_FILE, SKILLS_DIR
 from src.rate_limiter import RateLimiter
 from src.settings_scrub import scrub_settings
@@ -73,11 +73,6 @@ class DeleteUserRequest(BaseModel):
 class RenameUserRequest(BaseModel):
     username: str
 
-
-class SetAdminRequest(BaseModel):
-    is_admin: bool
-
-
 class SetOpenRegistrationRequest(BaseModel):
     enabled: bool
 
@@ -492,31 +487,6 @@ 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):
         """

routes/calendar_routes.py

@@ -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):
@@ -891,13 +843,13 @@ 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}")
@@ -1050,12 +1002,19 @@ 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 +1060,15 @@ 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 +1089,15 @@ 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

routes/chat_helpers.py

@@ -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
@@ -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,
@@ -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)
 

routes/chat_routes.py

@@ -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
@@ -474,11 +474,8 @@ 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"
@@ -526,66 +523,6 @@ 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).
@@ -701,27 +638,15 @@ def setup_chat_routes(
                             active_doc_id,
                         )
                         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,
+                    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,
                         )
-                            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}")
+                        active_doc = None
+                    else:
                         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}")
@@ -762,18 +687,9 @@ 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")
 
@@ -786,21 +702,6 @@ 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
@@ -1268,7 +1169,6 @@ 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,

routes/codex_routes.py

@@ -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}"

routes/contacts_routes.py

@@ -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:
@@ -740,39 +714,16 @@ 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:
+        # 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
         return {"success": ok}
 
     @router.post("/import")
@@ -834,11 +785,7 @@ 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 +802,7 @@ 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 +810,11 @@ 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}")

routes/cookbook_helpers.py

@@ -1,14 +1,12 @@
 """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
@@ -92,24 +90,6 @@ 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
@@ -362,12 +342,7 @@ 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 "$@"; }',
     ]
 
@@ -578,36 +553,6 @@ _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]:
@@ -639,22 +584,6 @@ 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`)."""
@@ -793,7 +722,6 @@ 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')
@@ -1098,16 +1026,6 @@ 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.",

routes/cookbook_output.py

@@ -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:])

routes/cookbook_routes.py

@@ -30,10 +30,6 @@ from core.platform_compat import (
     which_tool,
 )
 from routes.shell_routes import TMUX_LOG_DIR
-from routes.cookbook_output import (
-    error_aware_output_tail, classify_dead_download,
-    HF_CACHE_COMPLETE_PROBE, HF_CACHE_INCOMPLETE_PROBE,
-)
 
 logger = logging.getLogger(__name__)
 
@@ -43,13 +39,8 @@ from routes.cookbook_helpers import (
     _ps_squote, _bash_squote, _validate_serve_cmd, _parse_serve_phase,
     _safe_env_prefix, _local_tooling_path_export, _append_serve_preflight_exit_lines,
     _append_serve_exit_code_lines, _append_llama_cpp_linux_accel_build_lines, _cached_model_scan_script,
-    load_stored_hf_token,
-    _append_vllm_linux_preflight_lines, _ollama_bind_from_cmd, _pip_install_fallback_chain,
-    _pip_install_no_cache, _user_shell_path_bootstrap, _venv_safe_local_pip_install_cmd,
-    _diagnose_serve_output, run_ssh_command_async,
     _ollama_bind_from_cmd, _pip_install_fallback_chain, _pip_install_no_cache,
     _user_shell_path_bootstrap, _venv_safe_local_pip_install_cmd,
-    _normalize_llama_cpp_python_cache_types,
     ModelDownloadRequest, ServeRequest,
 )
 
@@ -58,7 +49,7 @@ _HF_TOKEN_STATUS_SNIPPET = (
     'echo "[odysseus] HF token: applied"; '
     'else '
     'echo "[odysseus] HF token: NOT SET — gated/private models will be denied. '
-    'Add one in Odysseus Cookbook -> Settings -> HuggingFace Token."; '
+    'Add one in Odysseus Settings -> Cookbook -> HuggingFace Token."; '
     'fi'
 )
 
@@ -174,16 +165,6 @@ def setup_cookbook_routes() -> APIRouter:
                 "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.",
@@ -252,7 +233,14 @@ def setup_cookbook_routes() -> APIRouter:
         return state
 
     def _load_stored_hf_token() -> str:
-        return load_stored_hf_token(state_path=_cookbook_state_path)
+        if not _cookbook_state_path.exists():
+            return ""
+        try:
+            state = json.loads(_cookbook_state_path.read_text(encoding="utf-8"))
+            env = state.get("env") if isinstance(state, dict) else {}
+            return _decrypt_secret(env.get("hfToken") if isinstance(env, dict) else "")
+        except Exception:
+            return ""
 
     def _cookbook_ssh_dir() -> Path:
         # The Docker image keeps cookbook keys under /app/.ssh; that path only
@@ -367,11 +355,7 @@ def setup_cookbook_routes() -> APIRouter:
             # all output to the log the poller reads. Paths handed to bash use
             # POSIX form + shell-quoting so drive paths / spaces survive.
             inner = TMUX_LOG_DIR / f"{session_id}_run.sh"
-            pp = shlex.quote(pid_path.as_posix())
-            inner.write_text(
-                f"printf '%s\\n' \"$$\" > {pp}\n" + "\n".join(bash_lines) + "\n",
-                encoding="utf-8",
-            )
+            inner.write_text("\n".join(bash_lines) + "\n", encoding="utf-8")
             lp = shlex.quote(log_path.as_posix())
             ip = shlex.quote(inner.as_posix())
             script_path = TMUX_LOG_DIR / f"{session_id}.sh"
@@ -676,7 +660,7 @@ def setup_cookbook_routes() -> APIRouter:
             _spf = f"-p {_port} " if _port and _port != "22" else ""
             setup_cmd = (
                 f"scp -O {_pf}-q '{runner_path}' {remote}:{remote_runner} && "
-                f"ssh {_spf}{remote} 'chmod +x {remote_runner} && tmux set-option -g history-limit 100000 2>/dev/null; tmux new-session -d -s {session_id} \"./{remote_runner}\"'"
+                f"ssh {_spf}{remote} 'chmod +x {remote_runner} && tmux new-session -d -s {session_id} \"./{remote_runner}\"'"
             )
         else:
             # Local: run hf download in the background (tmux on POSIX, a detached
@@ -708,7 +692,7 @@ def setup_cookbook_routes() -> APIRouter:
                 lines.append('exec "${SHELL:-/bin/bash}"')
                 wrapper_script.write_text("\n".join(lines) + "\n", encoding="utf-8")
                 wrapper_script.chmod(0o755)
-            setup_cmd = None if IS_WINDOWS else f"tmux set-option -g history-limit 100000 2>/dev/null; tmux new-session -d -s {session_id} {shlex.quote(str(wrapper_script))}"
+            setup_cmd = None if IS_WINDOWS else f"tmux new-session -d -s {session_id} {shlex.quote(str(wrapper_script))}"
 
         logger.info(f"Model download: {req.repo_id} (backend={'ollama' if is_ollama_download else 'hf'}, include={req.include}, session={session_id}, remote={remote})")
         logger.info(f"Download setup_cmd: {setup_cmd}")
@@ -984,9 +968,9 @@ def setup_cookbook_routes() -> APIRouter:
             ssh_args = ["ssh"]
             if ssh_port and ssh_port != "22":
                 ssh_args.extend(["-p", str(ssh_port)])
-            capture_cmd = ssh_args + [remote, "tmux", "capture-pane", "-t", session_id, "-p", "-S", "-2000"]
+            capture_cmd = ssh_args + [remote, "tmux", "capture-pane", "-t", session_id, "-p", "-S", "-200"]
         else:
-            capture_cmd = ["tmux", "capture-pane", "-t", session_id, "-p", "-S", "-2000"]
+            capture_cmd = ["tmux", "capture-pane", "-t", session_id, "-p", "-S", "-200"]
 
         _exit_re = re.compile(r"=== Process exited with code (-?\d+) ===")
         for wait_s in _waits:
@@ -1229,7 +1213,6 @@ def setup_cookbook_routes() -> APIRouter:
         # many downstream `"engine" in req.cmd` membership checks can't hit
         # `TypeError: argument of type 'NoneType'` (a 500 instead of a clean 400).
         req.cmd = _validate_serve_cmd(req.cmd) or ""
-        req.cmd = _normalize_llama_cpp_python_cache_types(req.cmd) or ""
         req.cmd = _venv_safe_local_pip_install_cmd(
             req.cmd,
             local=not bool(req.remote_host),
@@ -1577,10 +1560,10 @@ def setup_cookbook_routes() -> APIRouter:
                 setup_cmd = (
                     f"{scp_extras}"
                     f"scp -O {_Pf}-q '{runner_path}' {remote}:{remote_runner} && "
-                    f"ssh {_pf}{remote} 'chmod +x {remote_runner} && tmux set-option -g history-limit 100000 2>/dev/null; tmux new-session -d -s {session_id} \"./{remote_runner}\"'"
+                    f"ssh {_pf}{remote} 'chmod +x {remote_runner} && tmux new-session -d -s {session_id} \"./{remote_runner}\"'"
                 )
             else:
-                setup_cmd = f"tmux set-option -g history-limit 100000 2>/dev/null; tmux new-session -d -s {session_id} {shlex.quote(str(runner_path))}"
+                setup_cmd = f"tmux new-session -d -s {session_id} {shlex.quote(str(runner_path))}"
 
         if setup_cmd is None:
             # LOCAL Windows: launch the bash runner detached; no tmux setup_cmd.
@@ -2625,193 +2608,6 @@ def setup_cookbook_routes() -> APIRouter:
             "error": _ollama_library_cache["error"],
         }
 
-    # ── vLLM recipe scraper ─────────────────────────────────────────────
-    # Fetches the official YAML recipe for a model from vllm-project/recipes
-    # and normalizes it into a small JSON the frontend can consume. Cached
-    # per-repo so the GitHub raw endpoint isn't hammered.
-    _vllm_recipe_cache: dict[str, tuple[float, dict | None]] = {}
-    # Manifest of all <org>/<model> ids that have a recipe in the upstream
-    # repo. Cheap to fetch (one Git Tree API call), so we cache the whole
-    # set for ~12h. Per-row "does this model have a recipe?" lookups hit
-    # this set instead of doing 912 individual recipe fetches.
-    _vllm_recipe_manifest: dict = {"fetched_at": 0.0, "models": set(), "error": ""}
-
-    @router.get("/api/cookbook/vllm-recipe-manifest")
-    async def vllm_recipe_manifest(refresh: int = 0):
-        """Return the set of <org>/<model> ids known to have a vLLM recipe.
-        One GitHub Tree API call, 12h cache. The frontend uses this to badge
-        rows in the model list before the user expands them."""
-        import time as _time
-        import httpx as _httpx
-        TTL = 12 * 3600.0
-        now = _time.time()
-        if (
-            refresh
-            or (now - _vllm_recipe_manifest["fetched_at"]) > TTL
-            or not _vllm_recipe_manifest["models"]
-        ):
-            url = (
-                "https://api.github.com/repos/vllm-project/recipes/"
-                "git/trees/main?recursive=1"
-            )
-            def _fetch_sync() -> tuple[int, dict | None, str]:
-                try:
-                    headers = {"Accept": "application/vnd.github+json"}
-                    with _httpx.Client(timeout=10.0, follow_redirects=True) as client:
-                        r = client.get(url, headers=headers)
-                        if r.status_code != 200:
-                            return r.status_code, None, r.text[:200]
-                        return 200, r.json(), ""
-                except Exception as e:
-                    return 0, None, f"fetch error: {e}"
-            status, data, err = await asyncio.to_thread(_fetch_sync)
-            if status == 200 and isinstance(data, dict):
-                models: set[str] = set()
-                for entry in data.get("tree") or []:
-                    path = (entry or {}).get("path") or ""
-                    if not path.startswith("models/") or not path.endswith(".yaml"):
-                        continue
-                    # path = "models/<org>/<model>.yaml" → "<org>/<model>"
-                    body = path[len("models/"):-len(".yaml")]
-                    if "/" in body:
-                        models.add(body)
-                _vllm_recipe_manifest["models"] = models
-                _vllm_recipe_manifest["fetched_at"] = now
-                _vllm_recipe_manifest["error"] = ""
-            else:
-                _vllm_recipe_manifest["error"] = (
-                    f"HTTP {status}: {err}" if status else err
-                )
-                # Don't clobber a stale-but-usable list on transient failures.
-                if not _vllm_recipe_manifest["models"]:
-                    return {
-                        "models": [],
-                        "count": 0,
-                        "error": _vllm_recipe_manifest["error"],
-                    }
-        return {
-            "models": sorted(_vllm_recipe_manifest["models"]),
-            "count": len(_vllm_recipe_manifest["models"]),
-            "fetched_at": _vllm_recipe_manifest["fetched_at"],
-            "error": _vllm_recipe_manifest["error"],
-        }
-
-    @router.get("/api/cookbook/vllm-recipe")
-    async def vllm_recipe(repo: str, refresh: int = 0):
-        """Return the vLLM official recipe for a HuggingFace repo, if one
-        exists at vllm-project/recipes. `repo` is the full HF id like
-        'MiniMaxAI/MiniMax-M2'. Cached 6h."""
-        import time as _time
-        import httpx as _httpx
-        import yaml as _yaml
-
-        TTL = 6 * 3600.0
-        now = _time.time()
-        repo = (repo or "").strip().strip("/")
-        if "/" not in repo:
-            return {"exists": False, "error": "repo must be <org>/<model>"}
-
-        cached = _vllm_recipe_cache.get(repo)
-        if cached and not refresh and (now - cached[0]) < TTL:
-            return cached[1] or {"exists": False, "cached": True}
-
-        url = (
-            f"https://raw.githubusercontent.com/vllm-project/recipes/"
-            f"main/models/{repo}.yaml"
-        )
-
-        def _fetch_sync() -> tuple[int, str]:
-            try:
-                with _httpx.Client(timeout=8.0, follow_redirects=True) as client:
-                    r = client.get(url)
-                    return r.status_code, r.text
-            except Exception as e:
-                return 0, f"fetch error: {e}"
-
-        status, text = await asyncio.to_thread(_fetch_sync)
-        if status == 404:
-            _vllm_recipe_cache[repo] = (now, {"exists": False})
-            return {"exists": False}
-        if status != 200:
-            return {"exists": False, "error": f"HTTP {status}", "transient": True}
-
-        try:
-            doc = _yaml.safe_load(text) or {}
-        except Exception as e:
-            return {"exists": False, "error": f"yaml parse: {e}"}
-
-        meta = doc.get("meta") or {}
-        model = doc.get("model") or {}
-        features = doc.get("features") or {}
-        deps = doc.get("dependencies") or []
-        variants = doc.get("variants") or {}
-        hw_overrides = doc.get("hardware_overrides") or {}
-        strat_overrides = doc.get("strategy_overrides") or {}
-
-        # Tool-call + reasoning parsers, as flat arg arrays, so the frontend
-        # can drop them straight into the launch command.
-        tool_calling = features.get("tool_calling") or {}
-        reasoning = features.get("reasoning") or {}
-
-        normalized = {
-            "exists": True,
-            "source_url": url,
-            "title": meta.get("title") or "",
-            "provider": meta.get("provider") or "",
-            "description": meta.get("description") or "",
-            "date_updated": str(meta.get("date_updated") or ""),
-            "hardware_support": meta.get("hardware") or {},
-            "model_id": model.get("model_id") or repo,
-            "min_vllm_version": model.get("min_vllm_version") or "",
-            "architecture": model.get("architecture") or "",
-            "parameter_count": model.get("parameter_count") or "",
-            "active_parameters": model.get("active_parameters") or "",
-            "context_length": model.get("context_length") or 0,
-            "base_args": list(model.get("base_args") or []),
-            "base_env": dict(model.get("base_env") or {}),
-            "tool_calling": {
-                "description": tool_calling.get("description") or "",
-                "args": list(tool_calling.get("args") or []),
-            } if tool_calling else None,
-            "reasoning": {
-                "description": reasoning.get("description") or "",
-                "args": list(reasoning.get("args") or []),
-            } if reasoning else None,
-            "dependencies": [
-                {
-                    "note": (d.get("note") or "").strip(),
-                    "command": (d.get("command") or "").strip(),
-                    "optional": bool(d.get("optional", False)),
-                }
-                for d in deps if isinstance(d, dict)
-            ],
-            "variants": {
-                k: {
-                    "model_id": v.get("model_id") or model.get("model_id") or repo,
-                    "precision": v.get("precision") or "",
-                    "vram_minimum_gb": v.get("vram_minimum_gb") or 0,
-                    "description": v.get("description") or "",
-                    "extra_args": list(v.get("extra_args") or []),
-                    "extra_env": dict(v.get("extra_env") or {}),
-                }
-                for k, v in variants.items() if isinstance(v, dict)
-            },
-            "hardware_overrides": {
-                hw: {
-                    "extra_args": list((ov or {}).get("extra_args") or []),
-                    "extra_env": dict((ov or {}).get("extra_env") or {}),
-                }
-                for hw, ov in hw_overrides.items() if isinstance(ov, dict)
-            },
-            "strategy_overrides": {
-                strat: dict(ov or {})
-                for strat, ov in strat_overrides.items() if isinstance(ov, dict)
-            },
-            "compatible_strategies": list(doc.get("compatible_strategies") or []),
-        }
-        _vllm_recipe_cache[repo] = (now, normalized)
-        return normalized
-
     @router.get("/api/cookbook/tasks/status")
     async def cookbook_tasks_status(request: Request):
         """Check status of all active cookbook tmux sessions.
@@ -2826,20 +2622,30 @@ def setup_cookbook_routes() -> APIRouter:
     def _cookbook_tasks_status_sync():
         import subprocess
 
-        def _download_cache_complete(repo_id: str, remote_host: str = "", ssh_port: str = "", cache_root: str = "") -> bool:
+        def _download_cache_complete(repo_id: str, remote_host: str = "", ssh_port: str = "") -> bool:
             """Best-effort check for a completed HF cache entry.
 
             tmux output can stop at a stale progress line if the pane/session
             disappears before Cookbook captures the final DOWNLOAD_OK marker.
             In that case, trust the cache shape: a snapshot directory with files
             and no *.incomplete blobs means HuggingFace finished materializing the
-            model. cache_root is the task's custom download dir — the runner
-            pointed HF_HOME there, so the cache lives under <cache_root>/hub,
-            not wherever this probe's environment says.
+            model.
             """
             if not repo_id or "/" not in repo_id:
                 return False
-            cmd = ["python3", "-c", HF_CACHE_COMPLETE_PROBE, repo_id, cache_root or ""]
+            py = (
+                "import os,sys;"
+                "repo=sys.argv[1];"
+                "base=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)"
+            )
+            cmd = ["python3", "-c", py, repo_id]
             try:
                 if remote_host:
                     ssh_base = ["ssh"]
@@ -2853,7 +2659,7 @@ def setup_cookbook_routes() -> APIRouter:
             except Exception:
                 return False
 
-        def _download_cache_incomplete(repo_id: str, remote_host: str = "", ssh_port: str = "", cache_root: str = "") -> bool:
+        def _download_cache_incomplete(repo_id: str, remote_host: str = "", ssh_port: str = "") -> bool:
             """Best-effort check for resumable HF partial blobs.
 
             A lost SSH/tmux session can leave a real download still incomplete.
@@ -2862,7 +2668,16 @@ def setup_cookbook_routes() -> APIRouter:
             """
             if not repo_id or "/" not in repo_id:
                 return False
-            cmd = ["python3", "-c", HF_CACHE_INCOMPLETE_PROBE, repo_id, cache_root or ""]
+            py = (
+                "import os,sys;"
+                "repo=sys.argv[1];"
+                "base=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)"
+            )
+            cmd = ["python3", "-c", py, repo_id]
             try:
                 if remote_host:
                     ssh_base = ["ssh"]
@@ -3058,7 +2873,6 @@ def setup_cookbook_routes() -> APIRouter:
             # snapshot to classify (DOWNLOAD_OK / exit marker) — evaluate it even
             # when the PID is gone instead of blindly reporting "stopped".
             download_zero_files = False
-            exit_code = None
             status = "unknown"
             download_has_ok = task_type == "download" and "DOWNLOAD_OK" in full_snapshot
             download_has_failed = task_type == "download" and "DOWNLOAD_FAILED" in full_snapshot
@@ -3067,7 +2881,7 @@ def setup_cookbook_routes() -> APIRouter:
                 and (
                     ".incomplete" in full_snapshot
                     or bool(re.search(r'model-\d+-of-\d+\.[A-Za-z0-9_.-]+:\s+(?:[0-9]|[1-8][0-9])%', full_snapshot))
-                    or _download_cache_incomplete(_payload.get("repo_id") or model, remote, str(_tport or ""), _payload.get("local_dir") or "")
+                    or _download_cache_incomplete(_payload.get("repo_id") or model, remote, str(_tport or ""))
                 )
             )
             if is_alive or (local_win_task and full_snapshot):
@@ -3108,19 +2922,11 @@ def setup_cookbook_routes() -> APIRouter:
                 else:
                     status = "running"
             else:
-                # Session is dead — check if it completed or crashed. The
-                # runner markers in the retained output are conclusive
-                # (DOWNLOAD_OK only prints after exit 0), so check them before
-                # the cache probe, which can't see ollama pulls at all.
-                marker = classify_dead_download(full_snapshot) if task_type == "download" else None
-                if marker is not None:
-                    status, download_zero_files = marker
-                    if status == "completed" and not progress_text:
-                        progress_text = "Download complete"
-                elif (
+                # Session is dead — check if it completed or crashed
+                if (
                     task_type == "download"
                     and not download_has_incomplete_evidence
-                    and _download_cache_complete(_payload.get("repo_id") or model, remote, str(_tport or ""), _payload.get("local_dir") or "")
+                    and _download_cache_complete(_payload.get("repo_id") or model, remote, str(_tport or ""))
                 ):
                     status = "completed"
                     if not progress_text:
@@ -3140,7 +2946,7 @@ def setup_cookbook_routes() -> APIRouter:
                 status = "error"
             if download_zero_files:
                 diagnosis = {"message": "No matching files were downloaded. The model repo or filename/quant pattern may be wrong (for example a ':Q4_K_M' tag that does not exist in the repo). Check the repo and the include/quant pattern."}
-            output_tail = error_aware_output_tail(full_snapshot, status)
+            output_tail = "\n".join(full_snapshot.splitlines()[-12:]) if full_snapshot else ""
 
             results.append({
                 "session_id": session_id,
@@ -3151,7 +2957,6 @@ def setup_cookbook_routes() -> APIRouter:
                 "phase": serve_phase,
                 "diagnosis": diagnosis,
                 "output_tail": output_tail,
-                "exit_code": exit_code,
                 "cmd": _payload.get("_cmd") or "",
                 "tps": phase_info.get("tps"),
                 "reqs": phase_info.get("reqs"),

routes/diagnostics_routes.py

@@ -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__)
@@ -29,30 +28,6 @@ def setup_diagnostics_routes(
         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)

routes/email_routes.py

@@ -1087,22 +1087,14 @@ 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.
@@ -1110,27 +1102,7 @@ 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('"', '\\"')
@@ -1138,7 +1110,7 @@ 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)
@@ -1203,13 +1175,6 @@ 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}")
@@ -1756,22 +1721,6 @@ 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)."""
@@ -1787,9 +1736,7 @@ 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:
@@ -2152,79 +2099,6 @@ 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."""
@@ -2738,15 +2612,11 @@ 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)
@@ -2886,13 +2756,8 @@ 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)

routes/gallery_routes.py

@@ -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"])
 
@@ -939,22 +904,14 @@ 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.
-            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:
+            # Remove the file from disk
             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}")
+
+            # Soft-delete the record
+            img.is_active = False
+            db.commit()
 
             # Strip stale chat-history references so the image bubble
             # (and its prompt caption) doesn't come back after a server
@@ -1185,7 +1142,10 @@ 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")
 
@@ -1246,7 +1206,7 @@ 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()
 
@@ -1422,9 +1382,10 @@ 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}")
@@ -1484,7 +1445,6 @@ 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')."}
@@ -1534,7 +1494,6 @@ 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:

routes/hwfit_routes.py

@@ -119,7 +119,7 @@ def setup_hwfit_routes():
         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

routes/mcp_routes.py

@@ -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>"""

routes/memory_routes.py

@@ -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__)
@@ -241,18 +240,14 @@ 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)
@@ -283,15 +278,7 @@ 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
+        # Try default model from settings first
         settings = _load_settings()
         ep_id = settings.get("default_endpoint_id", "")
         default_model = settings.get("default_model", "")
@@ -373,14 +360,13 @@ 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.")

routes/model_routes.py

@@ -248,9 +248,6 @@ _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",
     ],
@@ -318,8 +315,6 @@ 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
@@ -708,7 +703,6 @@ 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":
@@ -744,7 +738,7 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
     url = _safe_build_models_url(base)
     headers = _safe_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"}]}
@@ -760,11 +754,6 @@ 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)]
     except httpx.HTTPStatusError as e:
         if api_key:
@@ -881,52 +870,15 @@ def _ping_endpoint(base_url: str, api_key: str = None, timeout: float = 1.5) ->
 
 
 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 +888,9 @@ 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):

routes/note_routes.py

@@ -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,
@@ -829,12 +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:

routes/personal_routes.py

@@ -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}")
 

routes/shell_routes.py

@@ -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",

routes/skills_routes.py

@@ -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:

routes/task_routes.py

@@ -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,
@@ -555,7 +552,6 @@ 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 +705,6 @@ 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:

routes/webhook_routes.py

@@ -198,8 +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
@@ -212,8 +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]:

scripts/agent_migration_manifest.py

@@ -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())

scripts/backfill_model_release_dates.py

@@ -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()

scripts/import_from_vllm_recipes.py

@@ -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()

services/hwfit/fit.py

@@ -19,32 +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,
+    # 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 = {
@@ -70,56 +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]
@@ -140,7 +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"):

services/hwfit/hardware.py

@@ -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)

services/hwfit/profiles.py

@@ -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,

services/memory/skill_extractor.py

@@ -66,58 +66,42 @@ 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]
-
 
 async def maybe_extract_skill(
     session,

services/memory/skills.py

@@ -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"],

services/youtube/youtube_handler.py

@@ -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(
+        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": []}

src/action_intents.py

@@ -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+.+"),
 

src/agent_loop.py

@@ -262,11 +262,6 @@ _DOMAIN_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 = {
@@ -279,7 +274,6 @@ _DOMAIN_TOOL_MAP = {
     "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]:
@@ -408,7 +402,7 @@ 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 +422,7 @@ 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 +433,7 @@ 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 +443,7 @@ 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>"}
@@ -610,7 +600,7 @@ _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
@@ -797,12 +787,6 @@ def _classify_agent_request(messages: List[Dict], last_user: str) -> Dict[str, o
         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"):
@@ -813,8 +797,6 @@ def _classify_agent_request(messages: List[Dict], last_user: str) -> Dict[str, o
         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 {
@@ -863,7 +845,6 @@ 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
@@ -1056,66 +1037,6 @@ 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.
@@ -1323,9 +1244,6 @@ 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
@@ -1360,18 +1278,12 @@ 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)
@@ -1812,7 +1724,6 @@ 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,
@@ -1890,21 +1801,18 @@ async def stream_agent_loop(
         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
+        _relevant_tools = set(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")
+            logger.info("[tool-rag] Low-signal agent message; skipping retrieval and using always-available tools only")
     if not guide_only and not _relevant_tools:
         try:
             from src.tool_index import get_tool_index, ALWAYS_AVAILABLE
@@ -1979,44 +1887,6 @@ async def stream_agent_loop(
     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])
 
@@ -2067,10 +1937,6 @@ 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
@@ -2100,7 +1966,6 @@ async def stream_agent_loop(
         compact=_is_api_model,
         owner=owner,
         suppress_local_context=guide_only,
-        active_email=active_email,
     )
     if plan_mode and not guide_only:
         # Steer the model to investigate-then-propose. Hard tool gating handles
@@ -2133,34 +1998,30 @@ 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 +2096,11 @@ 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 +2141,9 @@ 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
@@ -2827,46 +2679,6 @@ 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
@@ -2986,19 +2798,7 @@ async def stream_agent_loop(
             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

src/ai_interaction.py

@@ -972,15 +972,16 @@ async def do_manage_memory(content: str, session_id: Optional[str] = None, owner
             memories = [m for m in memories if m.get("category", "").lower() == category_filter]
         if not memories:
             return {"results": "No memories found" + (f" in category '{category_filter}'" if category_filter else "") + "."}
-
         result_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] + "..."
             result_lines.append(f"- [{cat}] `{mid}` — {text}")
+        if len(memories) > 100:
+            result_lines.append(f"... and {len(memories) - 100} more")
         return {"results": "\n".join(result_lines)}
 
     elif action == "add":
@@ -1292,7 +1293,7 @@ async def do_ui_control(content: str, session_id: Optional[str] = None, owner: O
       set_theme <preset>      — Apply a built-in theme preset (dark, light, midnight, paper, cyberpunk, retrowave, forest, ocean, ume, copper, terminal, organs, lavender, gpt, claude, cute)
       create_theme <name> <bg> <fg> <panel> <border> <accent> [key=val ...] — Create custom theme. Optional key=val: advanced color overrides AND background effects: bgPattern=<none|dots|synapse|rain|constellations|perlin-flow|petals|sparkles|embers>, bgEffectColor=#RRGGBB, bgEffectIntensity=<num>, bgEffectSize=<num>, frosted=true|false
       open_panel <name>       — Open a panel (documents, gallery, email, sessions, notes, memories, skills, settings, cookbook)
-      open_email_reply <uid> [folder] [reply|reply-all|ai-reply] [body text] — Open a reply draft document for an email; does not send. ALWAYS append the body text when the user told you what to say (one-shot draft); only omit body when the user just asked to "open a reply" without content.
+      open_email_reply <uid> [folder] [reply|reply-all|ai-reply] — Open a reply draft document for an email; does not send
       get_toggles             — Return current toggle states (server-side knowledge)
     """
     lines = content.strip().split("\n")
@@ -1536,54 +1537,21 @@ async def do_ui_control(content: str, session_id: Optional[str] = None, owner: O
         }
 
     elif action == "open_email_reply":
-        # Two forms supported:
-        #   open_email_reply <uid> [folder] [reply|reply-all|ai-reply]
-        #   open_email_reply <uid> [folder] [reply|reply-all|ai-reply]
-        #     <body text on subsequent lines or after the mode token>
-        # The body text (if any) gets pre-filled into the reply draft so the
-        # agent can compose-and-open in one tool call instead of opening an
-        # empty draft and leaving the user to wonder what happened.
-        first_line = lines[0].strip()
-        parts = first_line.split(maxsplit=4)
-        uid = parts[1].strip() if len(parts) > 1 else ""
-        folder = parts[2].strip() if len(parts) > 2 else "INBOX"
-        mode = parts[3].strip().lower() if len(parts) > 3 else "reply"
-        # Body: everything on the first line after the mode token, plus any
-        # subsequent lines. Allows multi-line bodies.
-        inline_body = parts[4] if len(parts) > 4 else ""
-        rest_lines = "\n".join(lines[1:]).strip() if len(lines) > 1 else ""
-        body = (inline_body + ("\n" + rest_lines if rest_lines else "")).strip()
+        reply_parts = lines[0].strip().split()
+        uid = reply_parts[1].strip() if len(reply_parts) > 1 else ""
+        folder = reply_parts[2].strip() if len(reply_parts) > 2 else "INBOX"
+        mode = reply_parts[3].strip().lower() if len(reply_parts) > 3 else "reply"
         if not uid:
-            return {"error": "open_email_reply needs: open_email_reply <uid> [folder] [reply|reply-all|ai-reply] [body text]"}
+            return {"error": "open_email_reply needs: open_email_reply <uid> [folder] [reply|reply-all|ai-reply]"}
         if mode not in ("reply", "reply-all", "ai-reply"):
             mode = "reply"
-        # Body is REQUIRED for the agent path. Opening an empty draft is what
-        # users do by clicking the Reply button — they don't ask the agent
-        # for that. Every agent invocation of open_email_reply MUST include
-        # the body. Reject empty so the agent retries with the content the
-        # user asked for. Exception: ai-reply mode triggers the existing
-        # AI-Reply path on the frontend which generates its own body.
-        if not body and mode != "ai-reply":
         return {
-                "error": (
-                    "open_email_reply called without body. The agent path REQUIRES a body — "
-                    "opening an empty draft is the wrong response when the user asked you to write. "
-                    "Re-call with the reply text included: "
-                    f"`open_email_reply {uid} {folder or 'INBOX'} {mode} <your reply text here>`. "
-                    "Compose the reply now based on the open email's content and the user's request, "
-                    "then call this tool again with the body. Do NOT call create_document instead."
-                ),
-            }
-        result = {
             "ui_event": "open_email_reply",
             "uid": uid,
             "folder": folder or "INBOX",
             "mode": mode,
-            "results": f"Opening reply draft for email UID {uid}" + (" with pre-filled body" if body else ""),
+            "results": f"Opening reply draft for email UID {uid}",
         }
-        if body:
-            result["body"] = body
-        return result
 
     elif action == "get_toggles":
         return {

src/api_key_manager.py

@@ -4,8 +4,6 @@ import logging
 from typing import Dict
 from cryptography.fernet import Fernet, InvalidToken
 
-from core.platform_compat import safe_chmod
-
 logger = logging.getLogger(__name__)
 
 class APIKeyManager:
@@ -17,20 +15,12 @@ class APIKeyManager:
     def get_or_create_key(self) -> bytes:
         """Get or create encryption key for API keys"""
         if os.path.exists(self.key_file):
-            # Older versions wrote .key with the process umask (often 0o644,
-            # i.e. group/world-readable). Re-restrict on read so existing
-            # installs heal without needing the key to be regenerated.
-            safe_chmod(self.key_file, 0o600)
             with open(self.key_file, 'rb') as f:
                 return f.read()
         else:
             key = Fernet.generate_key()
             with open(self.key_file, 'wb') as f:
                 f.write(key)
-            # This key decrypts every stored provider credential, so restrict it
-            # to the owner (0o600) — it must not be group/world-readable. No-op
-            # on Windows (files there are ACL-restricted to the user already).
-            safe_chmod(self.key_file, 0o600)
             return key
     
     def encrypt_api_key(self, api_key: str) -> str:
@@ -67,12 +57,7 @@ class APIKeyManager:
             # Legacy/wrong shape (e.g. a list) — .items() would raise. Ignore it.
             logger.warning("API keys file has unexpected shape (%s); ignoring", type(encrypted_keys).__name__)
             return {}
-
-        return {
-            str(provider): key
-            for provider, key in encrypted_keys.items()
-            if isinstance(key, str)
-        }
+        return encrypted_keys
 
     def save(self, provider: str, api_key: str):
         """Save encrypted API key to file.
@@ -97,3 +82,4 @@ class APIKeyManager:
             except (InvalidToken, ValueError) as e:
                 logger.warning("Failed to decrypt API key for %s: %s", provider, e)
         return decrypted
+

src/bg_monitor.py

@@ -55,8 +55,6 @@ async def _drain_agent(sess, messages):
         if "delta" in d:
             delta = d.get("delta")
             if isinstance(delta, str):
-                if d.get("thinking"):
-                    continue
                 full += delta
         elif d.get("type") == "agent_step":
             round_num = d.get("round", round_num)

src/builtin_mcp.py

@@ -5,13 +5,12 @@ Auto-registration of built-in MCP servers on startup.
 Each server runs as a stdio subprocess managed by McpManager.
 """
 
-import asyncio
-import json
 import logging
 import os
 import shutil
 import subprocess
 import sys
+import asyncio
 
 from core.platform_compat import IS_WINDOWS, which_tool
 
@@ -198,13 +197,12 @@ def _npx_package_from_args(args):
 async def _is_npx_package_cached(npx_path, package_spec, timeout_s=5):
     """Probe whether an npx package is already in the local cache.
 
-    First checks the local `_npx` cache for an installed package. If the
-    package is not found there, falls back to `npx --no-install <pkg>
-    --version` so older npm layouts still work without downloading.
+    Runs `npx --no-install <pkg> --version`. --no-install tells npx to
+    fail instead of downloading, so a cache miss returns fast. We treat
+    "exited 0 with non-empty stdout" as proof of a working cached copy.
+    Anything else (non-zero exit, empty stdout, timeout, missing npx,
+    network error) means we should skip the server.
     """
-    if _is_package_in_npx_cache(package_spec):
-        return True
-
     try:
         proc = await asyncio.create_subprocess_exec(
             npx_path, "--no-install", package_spec, "--version",
@@ -233,68 +231,3 @@ async def _is_npx_package_cached(npx_path, package_spec, timeout_s=5):
             pass
         return False
     return proc.returncode == 0 and bool(stdout.strip())
-
-
-def _is_package_in_npx_cache(package_spec):
-    """Return True when npm's `_npx` cache already contains package_spec."""
-    package_name = _npx_package_name(package_spec)
-    if not package_name:
-        return False
-
-    for cache_root in _npm_cache_roots():
-        npx_root = os.path.join(cache_root, "_npx")
-        if _npx_cache_contains_package(npx_root, package_name):
-            return True
-    return False
-
-
-def _npx_package_name(package_spec):
-    """Strip a version/range suffix from an npm package spec."""
-    if not package_spec:
-        return ""
-    if package_spec.startswith("@"):
-        parts = package_spec.split("@", 2)
-        if len(parts) >= 3:
-            return f"@{parts[1]}"
-        return package_spec
-    return package_spec.split("@", 1)[0]
-
-
-def _npm_cache_roots():
-    roots = []
-    configured = os.environ.get("npm_config_cache")
-    if configured:
-        roots.append(os.path.expanduser(configured))
-    roots.append(os.path.join(os.path.expanduser("~"), ".npm"))
-    local_app_data = os.environ.get("LOCALAPPDATA")
-    if local_app_data:
-        roots.append(os.path.join(local_app_data, "npm-cache"))
-    return list(dict.fromkeys(roots))
-
-
-def _npx_cache_contains_package(npx_root, package_name):
-    if not os.path.isdir(npx_root):
-        return False
-    package_path = os.path.join("node_modules", *package_name.split("/"), "package.json")
-    try:
-        entries = list(os.scandir(npx_root))
-    except OSError:
-        return False
-    for entry in entries:
-        try:
-            is_dir = entry.is_dir()
-        except OSError:
-            continue
-        cached_name = _cached_package_name(os.path.join(entry.path, package_path))
-        if is_dir and cached_name == package_name:
-            return True
-    return False
-
-
-def _cached_package_name(package_json_path):
-    try:
-        with open(package_json_path, encoding="utf-8") as fh:
-            data = json.load(fh)
-    except (OSError, ValueError):
-        return ""
-    return str(data.get("name", "")).strip()

src/caldav_sync.py

@@ -128,17 +128,6 @@ def validate_caldav_url(raw_url: str) -> str:
     return urlunparse(parsed._replace(fragment="")).rstrip("/")
 
 
-def _event_etag(obj) -> str:
-    """Best-effort ETag extraction from python-caldav resources."""
-    try:
-        etag = getattr(obj, "etag", None)
-        if callable(etag):
-            etag = etag()
-        return str(etag or "")
-    except Exception:
-        return ""
-
-
 def _stable_cal_id(remote_url: str, owner: str = "", account_id: str = "") -> str:
     """Deterministic local id for a remote CalDAV calendar, scoped to owner
     and account so two users — or one user with two accounts — pointing at
@@ -327,12 +316,11 @@ def _sync_blocking(owner: str, url: str, username: str, password: str, account_i
                         color="#5b8abf",
                         source="caldav",
                         account_id=account_id or None,
-                        caldav_base_url=remote_url,
                     )
                     db.add(local_cal)
                     db.commit()
                 else:
-                    # Refresh display name and stamp CalDAV metadata if missing.
+                    # Refresh display name and stamp account_id if missing.
                     changed = False
                     if local_cal.name != display_name:
                         local_cal.name = display_name
@@ -340,9 +328,6 @@ def _sync_blocking(owner: str, url: str, username: str, password: str, account_i
                     if account_id and not local_cal.account_id:
                         local_cal.account_id = account_id
                         changed = True
-                    if local_cal.caldav_base_url != remote_url:
-                        local_cal.caldav_base_url = remote_url
-                        changed = True
                     if changed:
                         db.commit()
                 result["calendars"] += 1
@@ -410,9 +395,6 @@ def _sync_blocking(owner: str, url: str, username: str, password: str, account_i
 
                         existing = _find_existing_event(db, pending, uid_val, local_cal.id)
                         if existing:
-                            if existing.caldav_sync_pending in {"create", "update"}:
-                                result["events"] += 1
-                                continue
                             existing.calendar_id = local_cal.id
                             existing.summary = summary
                             existing.description = description
@@ -423,9 +405,6 @@ def _sync_blocking(owner: str, url: str, username: str, password: str, account_i
                             existing.is_utc = row_is_utc
                             existing.rrule = rrule
                             existing.origin = "caldav"
-                            existing.remote_href = str(getattr(obj, "url", "") or "") or None
-                            existing.remote_etag = _event_etag(obj) or None
-                            existing.caldav_sync_pending = None
                         else:
                             new_ev = CalendarEvent(
                                 uid=uid_val,
@@ -439,8 +418,6 @@ def _sync_blocking(owner: str, url: str, username: str, password: str, account_i
                                 is_utc=row_is_utc,
                                 rrule=rrule,
                                 origin="caldav",
-                                remote_href=str(getattr(obj, "url", "") or "") or None,
-                                remote_etag=_event_etag(obj) or None,
                             )
                             db.add(new_ev)
                             pending[uid_val] = new_ev
@@ -465,8 +442,6 @@ def _sync_blocking(owner: str, url: str, username: str, password: str, account_i
                         CalendarEvent.origin == "caldav",
                         CalendarEvent.dtstart >= start,
                         CalendarEvent.dtstart <= end,
-                        CalendarEvent.remote_href.isnot(None),
-                        CalendarEvent.caldav_sync_pending.is_(None),
                         ~CalendarEvent.uid.in_(seen_uids) if seen_uids else CalendarEvent.uid.isnot(None),
                     ).all()
                     for ev in stale:
@@ -483,92 +458,6 @@ def _sync_blocking(owner: str, url: str, username: str, password: str, account_i
     return result
 
 
-def _event_payload(ev) -> dict:
-    return {
-        "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 "",
-    }
-
-
-def _load_event_for_writeback(owner: str, uid: str) -> tuple[str, str, dict] | None:
-    from core.database import CalendarCal, CalendarEvent, SessionLocal
-
-    db = SessionLocal()
-    try:
-        ev = (
-            db.query(CalendarEvent)
-            .join(CalendarCal)
-            .filter(CalendarEvent.uid == uid, CalendarCal.owner == owner)
-            .first()
-        )
-        if not ev or not ev.calendar or ev.calendar.source != "caldav":
-            return None
-        return ev.calendar.source, ev.calendar.id, _event_payload(ev)
-    finally:
-        db.close()
-
-
-def _load_delete_for_writeback(owner: str, uid: str) -> tuple[str, str, dict] | None:
-    from core.database import CalendarCal, CalendarDeletedEvent, CalendarEvent, SessionLocal
-
-    db = SessionLocal()
-    try:
-        tombstone = db.query(CalendarDeletedEvent).filter(
-            CalendarDeletedEvent.uid == uid,
-            CalendarDeletedEvent.owner == owner,
-        ).first()
-        if tombstone:
-            return "caldav", tombstone.calendar_id, {"uid": uid}
-
-        ev = (
-            db.query(CalendarEvent)
-            .join(CalendarCal)
-            .filter(CalendarEvent.uid == uid, CalendarCal.owner == owner)
-            .first()
-        )
-        if not ev or not ev.calendar or ev.calendar.source != "caldav":
-            return None
-        return ev.calendar.source, ev.calendar.id, {"uid": uid}
-    finally:
-        db.close()
-
-
-def _pending_writeback_uids(owner: str) -> tuple[list[str], list[str]]:
-    from core.database import CalendarCal, CalendarDeletedEvent, CalendarEvent, SessionLocal
-
-    db = SessionLocal()
-    try:
-        rows = (
-            db.query(CalendarEvent.uid)
-            .join(CalendarCal)
-            .filter(
-                CalendarCal.owner == owner,
-                CalendarCal.source == "caldav",
-                CalendarEvent.status != "cancelled",
-                (
-                    (CalendarEvent.caldav_sync_pending.isnot(None))
-                    | (CalendarEvent.remote_href.is_(None))
-                ),
-            )
-            .all()
-        )
-        delete_rows = (
-            db.query(CalendarDeletedEvent.uid)
-            .filter(CalendarDeletedEvent.owner == owner)
-            .all()
-        )
-        return [row[0] for row in rows], [row[0] for row in delete_rows]
-    finally:
-        db.close()
-
-
 def _load_caldav_accounts(owner: str) -> list:
     """Return the list of CalDAV accounts for *owner*, auto-migrating the legacy
     single-account ``caldav`` key to the new ``caldav_accounts`` list on first call.
@@ -644,69 +533,3 @@ async def sync_caldav(owner: str) -> dict:
         for err in result.get("errors", []):
             totals["errors"].append(f"{label}: {err}")
     return totals
-
-
-async def push_event_create(owner: str, uid: str) -> dict:
-    loaded = _load_event_for_writeback(owner, uid)
-    if not loaded:
-        return {"ok": True, "skipped": True}
-    source, calendar_id, payload = loaded
-    from src.caldav_writeback import writeback_event
-    return await writeback_event(owner, source, calendar_id, payload)
-
-
-async def push_event_update(owner: str, uid: str) -> dict:
-    return await push_event_create(owner, uid)
-
-
-async def push_event_delete(owner: str, uid: str) -> dict:
-    loaded = _load_delete_for_writeback(owner, uid)
-    if not loaded:
-        return {"ok": True, "skipped": True}
-    source, calendar_id, payload = loaded
-    from src.caldav_writeback import writeback_event
-    return await writeback_event(owner, source, calendar_id, payload, delete=True)
-
-
-async def push_pending_events(owner: str) -> dict:
-    result = {"events": 0, "errors": []}
-    uids, delete_uids = _pending_writeback_uids(owner)
-    for event_uid in uids:
-        try:
-            out = await push_event_update(owner, event_uid)
-            if out.get("ok"):
-                result["events"] += 1
-            elif not out.get("skipped"):
-                result["errors"].append(f"{event_uid}: {str(out.get('error') or out)[:160]}")
-        except Exception as e:
-            logger.warning("CalDAV pending push failed for uid=%s: %s", event_uid, e)
-            result["errors"].append(f"{event_uid}: {str(e)[:160]}")
-    for event_uid in delete_uids:
-        try:
-            out = await push_event_delete(owner, event_uid)
-            if out.get("ok"):
-                result["events"] += 1
-            elif not out.get("skipped"):
-                result["errors"].append(f"{event_uid}: {str(out.get('error') or out)[:160]}")
-        except Exception as e:
-            logger.warning("CalDAV pending delete failed for uid=%s: %s", event_uid, e)
-            result["errors"].append(f"{event_uid}: {str(e)[:160]}")
-    return result
-
-
-async def sync_caldav_direction(owner: str, direction: str = "pull") -> dict:
-    direction = (direction or "pull").strip().lower()
-    if direction == "pull":
-        return await sync_caldav(owner)
-    if direction == "push":
-        return await push_pending_events(owner)
-    if direction == "both":
-        pushed = await push_pending_events(owner)
-        pulled = await sync_caldav(owner)
-        return {"push": pushed, "pull": pulled}
-    return {
-        "calendars": 0,
-        "events": 0,
-        "deleted": 0,
-        "errors": [f"Unsupported CalDAV sync direction: {direction}"],
-    }

src/caldav_writeback.py

@@ -89,23 +89,6 @@ def find_remote_calendar(calendars, local_cal_id: str, owner: str = "", account_
     return None
 
 
-def _resource_href(obj) -> str:
-    try:
-        return str(getattr(obj, "url", "") or "")
-    except Exception:
-        return ""
-
-
-def _resource_etag(obj) -> str:
-    try:
-        etag = getattr(obj, "etag", None)
-        if callable(etag):
-            etag = etag()
-        return str(etag or "")
-    except Exception:
-        return ""
-
-
 def push_event(calendars, local_cal_id: str, ev: dict, *, delete: bool = False,
                owner: str = "", account_id: str = "") -> dict:
     """Create/update (or delete) ``ev`` on the matching remote calendar.
@@ -122,7 +105,6 @@ def push_event(calendars, local_cal_id: str, ev: dict, *, delete: bool = False,
     remote = find_remote_calendar(calendars, local_cal_id, owner=owner, account_id=account_id)
     if remote is None:
         return {"ok": False, "error": "remote calendar not found"}
-    remote_url = str(getattr(remote, "url", "") or "")
 
     try:
         existing = remote.event_by_uid(uid)
@@ -131,34 +113,17 @@ def push_event(calendars, local_cal_id: str, ev: dict, *, delete: bool = False,
 
     if delete:
         if existing is None:
-            return {"ok": True, "note": "already absent on remote", "calendar_url": remote_url}
+            return {"ok": True, "note": "already absent on remote"}
         existing.delete()
-        return {
-            "ok": True,
-            "calendar_url": remote_url,
-            "remote_href": _resource_href(existing),
-            "remote_etag": _resource_etag(existing),
-        }
+        return {"ok": True}
 
     ical = build_event_ical(ev)
     if existing is not None:
         existing.data = ical
         existing.save()
-        return {
-            "ok": True,
-            "updated": True,
-            "calendar_url": remote_url,
-            "remote_href": _resource_href(existing),
-            "remote_etag": _resource_etag(existing),
-        }
-    created = remote.save_event(ical)
-    return {
-        "ok": True,
-        "created": True,
-        "calendar_url": remote_url,
-        "remote_href": _resource_href(created),
-        "remote_etag": _resource_etag(created),
-    }
+        return {"ok": True, "updated": True}
+    remote.save_event(ical)
+    return {"ok": True, "created": True}
 
 
 def _discover_calendars(client):
@@ -189,54 +154,6 @@ def _writeback_blocking(local_cal_id, ev, delete, url, username, password,
                       owner=owner, account_id=account_id)
 
 
-def _persist_writeback_result(owner: str, calendar_id: str, uid: str, result: dict, *, delete: bool) -> None:
-    from core.database import CalendarCal, CalendarDeletedEvent, CalendarEvent, SessionLocal
-
-    if not uid or not isinstance(result, dict):
-        return
-
-    db = SessionLocal()
-    try:
-        calendar = db.query(CalendarCal).filter(
-            CalendarCal.id == calendar_id,
-            CalendarCal.owner == owner,
-        ).first()
-        if calendar and result.get("calendar_url"):
-            calendar.caldav_base_url = result.get("calendar_url")
-
-        if delete:
-            tombstone = db.query(CalendarDeletedEvent).filter(
-                CalendarDeletedEvent.uid == uid,
-                CalendarDeletedEvent.owner == owner,
-            ).first()
-            if result.get("ok"):
-                if tombstone:
-                    db.delete(tombstone)
-            elif tombstone:
-                tombstone.last_error = str(result.get("error") or result)[:500]
-            db.commit()
-            return
-
-        event = (
-            db.query(CalendarEvent)
-            .join(CalendarCal)
-            .filter(CalendarEvent.uid == uid, CalendarCal.owner == owner)
-            .first()
-        )
-        if event and result.get("ok"):
-            if result.get("remote_href"):
-                event.remote_href = result.get("remote_href")
-            if result.get("remote_etag"):
-                event.remote_etag = result.get("remote_etag")
-            event.caldav_sync_pending = None
-        db.commit()
-    except Exception:
-        db.rollback()
-        logger.exception("CalDAV write-back metadata persistence failed")
-    finally:
-        db.close()
-
-
 async def writeback_event(owner: str, calendar_source: str, calendar_id: str,
                           ev: dict, *, delete: bool = False) -> dict:
     """Best-effort push of a local change to the remote CalDAV server.
@@ -287,12 +204,9 @@ async def writeback_event(owner: str, calendar_source: str, calendar_id: str,
         result = await asyncio.to_thread(
             _writeback_blocking, calendar_id, ev, delete, url, user, pw, owner, acc_id
         )
-        _persist_writeback_result(owner, calendar_id, (ev or {}).get("uid", ""), result, delete=delete)
         if not result.get("ok"):
             logger.warning("CalDAV write-back did not apply: %s", result.get("error") or result)
         return result
     except Exception as e:
         logger.exception("CalDAV write-back raised")
-        result = {"ok": False, "error": str(e)[:200]}
-        _persist_writeback_result(owner, calendar_id, (ev or {}).get("uid", ""), result, delete=delete)
-        return result
+        return {"ok": False, "error": str(e)[:200]}

src/context_budget.py

@@ -31,22 +31,16 @@ def compute_input_token_budget(
 
     Args:
         configured: the value read from settings (may be the default).
-        context_length: the model's discovered context window. Pass 0 when the
-            window is unknown / only a bare fallback — auto-scaling then stays
-            conservative instead of trusting an unproven window (review on #4122).
-        explicit: True if the user set a NON-default budget. The default value is
-            the "auto" sentinel (scale to the window); any other value is an
-            explicit cap. (A deliberately-chosen default can't be distinguished
-            from a materialized default by value, so the default reads as auto.)
+        context_length: the model's discovered context window (0/unknown if none).
+        explicit: True if the user explicitly set ``agent_input_token_budget``.
 
     Rules:
         - Explicit user budget is honoured exactly, only clamped to the model's
-          window when that window is known (the user's deliberate choice wins;
-          ``hard_max`` is an auto-budget ceiling only — see #1230).
-        - Otherwise (auto), scale to ``headroom`` of the context window, capped at
-          ``hard_max`` — so long-context models use their capacity.
-        - When the window is unknown (context_length <= 0), use the conservative
-          ``default`` budget and do NOT scale off the fallback.
+          window when that window is known (never send more than the model holds).
+        - Otherwise (default), scale to ``headroom`` of the context window, capped
+          at ``hard_max`` — so long-context models use their capacity.
+        - When the window is unknown, fall back to the configured/default value
+          (preserving the previous behaviour).
     """
     configured = int(configured or 0)
     context_length = int(context_length or 0)
@@ -59,17 +53,3 @@ def compute_input_token_budget(
         return max(1, min(scaled, hard_max))
 
     return configured if configured > 0 else default
-
-
-def budget_is_explicit(configured: int, *, default: int = DEFAULT_BUDGET) -> bool:
-    """Whether a configured agent_input_token_budget is a deliberate explicit cap.
-
-    The default value is the "auto" sentinel (scale to the model's window), so only
-    a NON-default positive value counts as explicit. This keys off the VALUE, not
-    settings *presence* — the settings-save path materializes every default into
-    settings.json, so a persisted default must still read as auto (the regression
-    #4121 / #1230 are about). Centralised here so the materialized-default contract
-    is unit-testable and can't silently regress to a presence check.
-    """
-    configured = int(configured or 0)
-    return configured > 0 and configured != default

src/context_compactor.py

@@ -244,17 +244,9 @@ def trim_for_context(messages: List[Dict], context_length: int, reserve_tokens:
     protected_tokens = estimate_tokens(protected_msgs)
     budget -= protected_tokens
 
-    # Priority: keep first system msg (preset prompt), drop others (memory, RAG, memo).
-    # Exception: a research-spinoff primer (the seeded report that grounds a
-    # "Discuss" chat) must never be dropped — it is the conversation's whole
-    # knowledge base. Treat any system message carrying research_spinoff_from
-    # metadata as essential alongside the leading system prompt.
-    def _is_research_primer(m):
-        return bool((m.get("metadata") or {}).get("research_spinoff_from"))
-    _primers = [m for m in system_msgs if _is_research_primer(m)]
-    _non_primer = [m for m in system_msgs if not _is_research_primer(m)]
-    essential_system = (_non_primer[:1] if _non_primer else []) + _primers
-    extra_system = _non_primer[1:]
+    # Priority: keep first system msg (preset prompt), drop others (memory, RAG, memo)
+    essential_system = system_msgs[:1] if system_msgs else []
+    extra_system = system_msgs[1:]
 
     # Try dropping extra system messages one by one (from the end)
     trimmed = essential_system + convo_msgs

src/cookbook_serve_lifecycle.py

@@ -136,8 +136,7 @@ async def _tick() -> None:
         return
     try:
         state = json.loads(state_path.read_text(encoding="utf-8"))
-    except Exception as e:
-        logger.warning("cookbook_serve_lifecycle: state file unreadable (%s), skipping tick", e)
+    except Exception:
         return
     tasks = state.get("tasks") or []
     now_ms = int(time.time() * 1000)
@@ -179,26 +178,8 @@ async def _tick() -> None:
     if stopped_any:
         try:
             from core.atomic_io import atomic_write_json
-            # Re-read the state file so concurrent UI writes (task adds,
-            # status flips, config edits) are not silently overwritten.
-            # Apply only our stop mutations to the fresh snapshot.
-            try:
-                fresh = json.loads(state_path.read_text(encoding="utf-8"))
-                fresh_tasks = fresh.get("tasks") or []
-            except Exception:
-                fresh = state
-                fresh_tasks = tasks
-            stopped_sids = {sid for sid, _, _ in to_stop}
-            for ft in fresh_tasks:
-                if not isinstance(ft, dict):
-                    continue
-                ft_sid = ft.get("sessionId") or ft.get("id")
-                if ft_sid in stopped_sids:
-                    ft["status"] = "stopped"
-                    ft["_scheduledStopAtMs"] = None
-                    ft["_lastStatusFlipAt"] = now_ms
-            fresh["tasks"] = fresh_tasks
-            atomic_write_json(state_path, fresh)
+            state["tasks"] = tasks
+            atomic_write_json(state_path, state)
         except Exception as e:
             logger.warning(f"cookbook_serve_lifecycle: state write failed: {e}")
 

src/document_processor.py

@@ -199,20 +199,11 @@ def _fit_inline_attachment_text(
     return text[:remaining] + marker, 0
 
 
-def _process_office_document(
-    path: str,
-    display_name: str,
-    session_id: str | None = None,
-    auto_opened_docs: list[Dict[str, Any]] | None = None,
-    owner: str | None = None,
-) -> str:
+def _process_office_document(path: str, display_name: str) -> str:
     """Extract an Office/EPUB document to Markdown via the optional markitdown dep.
 
     Falls back to a friendly banner when markitdown is unavailable or finds no
-    text, so a missing optional dependency never breaks the chat path. When a
-    session_id is provided AND the extraction succeeded, the FULL text is also
-    saved as a Document so the agent can page through it via
-    `manage_documents action=read offset=…` after the inline copy is capped.
+    text, so a missing optional dependency never breaks the chat path.
     """
     from src.markitdown_runtime import (
         is_markitdown_format,
@@ -227,46 +218,6 @@ def _process_office_document(
     if markdown and markdown.strip():
         title = os.path.splitext(os.path.basename(path))[0]
         body, marker = _truncate_inline(markdown)
-
-        # Persist the full extracted text as a Document. The agent's existing
-        # manage_documents tool can then read past the inline cap with offset.
-        doc_id = None
-        if session_id:
-            try:
-                from src.office_doc import create_office_document
-                doc_id = create_office_document(
-                    session_id=session_id,
-                    upload_id=os.path.basename(path),
-                    title=title,
-                    body_text=markdown,
-                )
-                if doc_id and auto_opened_docs is not None:
-                    from src.database import SessionLocal, Document
-                    _db = SessionLocal()
-                    try:
-                        _d = _db.query(Document).filter(Document.id == doc_id).first()
-                        if _d:
-                            auto_opened_docs.append({
-                                "doc_id": _d.id,
-                                "title": _d.title,
-                                "language": _d.language,
-                                "content": _d.current_content,
-                                "version": _d.version_count,
-                            })
-                    finally:
-                        _db.close()
-            except Exception as e:
-                logger.warning("Office auto-doc creation failed for %s: %s", path, e)
-
-        # Upgrade the truncation marker with a hint pointing at the full doc so
-        # the agent knows it can read the rest.
-        if doc_id and marker:
-            marker = (
-                f"\n[…truncated for inline context — full {len(markdown):,} chars "
-                f"saved as document `{doc_id}`. Use `manage_documents` with "
-                f"action=read, document_id={doc_id}, offset=<N> to page through.]"
-            )
-
         return f"\n\n[Document content — {title}]:\n{body}{marker}"
 
     # No content: tell the user whether to install the optional dep or whether
@@ -570,13 +521,7 @@ def build_user_content(
             elif mime.startswith("text/") or _is_text_file(path):
                 extracted_text = _process_text_file(path)
             else:
-                extracted_text = _process_office_document(
-                    path,
-                    display_name,
-                    session_id=session_id,
-                    auto_opened_docs=auto_opened_docs,
-                    owner=owner,
-                )
+                extracted_text = _process_office_document(path, display_name)
 
             extracted_text, inline_attachment_remaining = _fit_inline_attachment_text(
                 extracted_text,

src/endpoint_resolver.py

@@ -12,7 +12,7 @@ from typing import Optional, Tuple, Dict
 from urllib.parse import urlparse, urlunparse
 
 from core.database import SessionLocal, ModelEndpoint
-from src.llm_core import _detect_provider, _host_match, _is_kimi_code_url, KIMI_CODE_USER_AGENT, _ollama_api_root
+from src.llm_core import _detect_provider, _host_match, _ollama_api_root
 
 logger = logging.getLogger(__name__)
 
@@ -183,16 +183,7 @@ def build_chat_url(base: str) -> str:
 
 
 def build_models_url(base: str) -> Optional[str]:
-    """Return the provider-specific model-list endpoint URL for a base.
-
-    For OpenAI-compatible servers (LM Studio, llama.cpp, vLLM,
-    text-generation-webui, etc.) the model list is exposed at ``/v1/models``.
-    When the user-supplied base has no path — e.g. ``http://localhost:1234`` —
-    we still need to land on ``/v1/models`` (issue #25); insert the ``/v1``
-    segment only when the path is empty, leaving any explicit non-empty path
-    untouched (so custom prefixes like ``/openai`` or ``/api/openai/v1`` keep
-    their semantics).
-    """
+    """Return the provider-specific model-list endpoint URL for a base."""
     base = normalize_base(resolve_url(base))
     provider = _detect_provider(base)
     if provider == "anthropic":
@@ -201,16 +192,6 @@ def build_models_url(base: str) -> Optional[str]:
         return _ollama_api_root(base) + "/tags"
     if provider == "chatgpt-subscription":
         return None
-    # Generic OpenAI-compatible fallback: local model servers with no explicit
-    # path conventionally expose `/v1/models` (LM Studio, llama.cpp, vLLM).
-    # For non-local unknown hosts, do not invent `/v1`; append `/models` to the
-    # caller's base so look-alike provider hosts stay generic.
-    parsed = urlparse(base)
-    host = (parsed.hostname or "").lower()
-    is_local = host in {"localhost", "127.0.0.1", "::1", "host.docker.internal"}
-    uses_v1_models_by_default = is_local or host in {"api.deepseek.com"}
-    if not parsed.path and uses_v1_models_by_default:
-        base = base + "/v1"
     return base + "/models"
 
 
@@ -234,8 +215,6 @@ def build_headers(api_key: Optional[str], base: str) -> Dict[str, str]:
     if provider == "openrouter":
         headers.setdefault("HTTP-Referer", "https://github.com/pewdiepie-archdaemon/odysseus")
         headers.setdefault("X-OpenRouter-Title", "Odysseus")
-    if _is_kimi_code_url(base):
-        headers.setdefault("User-Agent", KIMI_CODE_USER_AGENT)
     return headers
 
 
@@ -271,19 +250,23 @@ def resolve_endpoint(
     ep_id = _stg(f"{setting_prefix}_endpoint_id")
     model = _stg(f"{setting_prefix}_model")
 
-    # Fall back to utility model for task/research/auto-naming if not specifically configured.
-    if not ep_id and setting_prefix not in ("utility", "default"):
-        ep_id = _stg("utility_endpoint_id")
-        model = _stg("utility_model")
-
-    # If the endpoint is STILL not configured, but the caller provided a
+    # If the specific endpoint is not configured, but the caller provided a
     # valid fallback (e.g. the active session model), use that immediately.
     # This prevents background tasks from jumping to the global default_model
     # when the user is mid-conversation with a different model.
     if not ep_id and fallback_url and fallback_model:
         return fallback_url, fallback_model, fallback_headers
 
-    # Unset Utility (or anything else that didn't have a fallback) means "same as Default Chat Model".
+    # Unset Utility means "same as Default Chat Model".
+    if setting_prefix == "utility" and not ep_id:
+        ep_id = _stg("default_endpoint_id")
+        model = _stg("default_model")
+
+    # Fall back to utility model for task/research/auto-naming if not specifically configured.
+    # If Utility itself is unset, the block above makes that resolve to Default Chat.
+    if not ep_id and setting_prefix != "utility":
+        ep_id = _stg("utility_endpoint_id")
+        model = _stg("utility_model")
         if not ep_id:
             ep_id = _stg("default_endpoint_id")
             model = _stg("default_model")

src/integrations.py

@@ -6,7 +6,6 @@ import re
 from typing import Dict, List, Optional, Any
 
 import httpx
-from fastapi import HTTPException
 
 from core.atomic_io import atomic_write_json
 from core.platform_compat import safe_chmod
@@ -259,11 +258,6 @@ def add_integration(data: Dict[str, Any]) -> Dict[str, Any]:
     integration.setdefault("name", "")
     integration.setdefault("base_url", "")
 
-    if not isinstance(integration.get("name"), str) or not integration["name"].strip():
-        raise HTTPException(400, "Integration name is required")
-    if not isinstance(integration.get("base_url"), str) or not integration["base_url"].strip():
-        raise HTTPException(400, "Integration base URL is required")
-
     integrations = load_integrations()
     integrations.append(integration)
     save_integrations(integrations)
@@ -272,11 +266,6 @@ def add_integration(data: Dict[str, Any]) -> Dict[str, Any]:
 
 def update_integration(integration_id: str, data: Dict[str, Any]) -> Optional[Dict[str, Any]]:
     """Update fields on an existing integration. Returns updated integration or None."""
-    if "name" in data and (not isinstance(data["name"], str) or not data["name"].strip()):
-        raise HTTPException(400, "Integration name is required")
-    if "base_url" in data and (not isinstance(data["base_url"], str) or not data["base_url"].strip()):
-        raise HTTPException(400, "Integration base URL is required")
-
     integrations = load_integrations()
     for item in integrations:
         if item.get("id") == integration_id:

src/llm_core.py

@@ -7,7 +7,6 @@ import logging
 import hashlib
 import threading
 import re
-import os
 from fastapi import HTTPException
 from typing import Optional, Dict, List, Tuple
 from src.model_context import get_context_length, DEFAULT_CONTEXT
@@ -23,24 +22,6 @@ class LLMConfig:
     MAX_RETRIES = 3
     RETRY_DELAY = 0.5
     STREAM_TIMEOUT = 300
-    # TCP+TLS connect budget for a SINGLE attempt. The old hard-coded 3.0s
-    # assumed LAN/Tailscale peers ('SYN in <100ms'); it is too tight for public
-    # cloud endpoints (offshore APIs take ~0.5-1.5s cold, with jitter), so a
-    # brief blip on the first connect of an idle chat surfaced as a 503 on the
-    # streaming path (which, unlike llm_call, does not retry the connect). A
-    # genuinely dead upstream stays bounded by the dead-host cooldown. Override
-    # with env LLM_CONNECT_TIMEOUT (seconds).
-    CONNECT_TIMEOUT = float(os.getenv('LLM_CONNECT_TIMEOUT', '10') or '10')
-
-
-def _call_timeout(read_timeout) -> httpx.Timeout:
-    """Per-request timeout for non-streaming LLM calls (connect from config)."""
-    return httpx.Timeout(connect=LLMConfig.CONNECT_TIMEOUT, read=float(read_timeout), write=10.0, pool=5.0)
-
-
-def _stream_timeout(read_timeout) -> httpx.Timeout:
-    """Per-request timeout for streaming LLM calls (connect from config)."""
-    return httpx.Timeout(connect=LLMConfig.CONNECT_TIMEOUT, read=float(read_timeout), write=30.0, pool=5.0)
 
 
 # Cache for LLM responses
@@ -442,146 +423,6 @@ def _host_match(url: str, *domains: str) -> bool:
     return any(host == d or host.endswith("." + d) for d in domains)
 
 
-# Kimi Code subscription keys (api.kimi.com/coding/v1) require a whitelisted
-# coding-agent User-Agent; otherwise the API returns 403 access_terminated_error.
-# Tried in order; first success is cached per base URL for later requests.
-KIMI_CODE_USER_AGENTS: tuple[str, ...] = (
-    "claude-code/0.1.0",
-    "claude-code/1.0.0",
-    "KimiCLI/1.0",
-    "Kilo-Code/1.0",
-    "Roo-Code/1.0",
-    "Cursor/1.0",
-)
-KIMI_CODE_USER_AGENT = KIMI_CODE_USER_AGENTS[0]
-_kimi_code_ua_cache: dict[str, str] = {}
-
-
-def _is_kimi_code_url(url: str) -> bool:
-    if not url or not _host_match(url, "kimi.com"):
-        return False
-    try:
-        return "/coding" in (urlparse(url).path or "")
-    except Exception:
-        return False
-
-
-def _kimi_code_base_key(url: str) -> str:
-    """Normalize a Kimi Code chat/models URL to its OpenAI base (.../coding/v1)."""
-    parsed = urlparse(url)
-    path = (parsed.path or "").rstrip("/")
-    for suffix in ("/chat/completions", "/models", "/completions"):
-        if path.endswith(suffix):
-            path = path[: -len(suffix)]
-    path = path.rstrip("/") or "/coding/v1"
-    return f"{parsed.scheme}://{parsed.netloc}{path}"
-
-
-def _is_kimi_code_access_denied(status: int, body: bytes | str) -> bool:
-    if status != 403:
-        return False
-    text = body.decode("utf-8", errors="replace") if isinstance(body, bytes) else (body or "")
-    lower = text.lower()
-    return (
-        "access_terminated_error" in lower
-        or "coding agents" in lower
-        or "only available for coding" in lower
-    )
-
-
-def _kimi_code_ua_candidates(url: str) -> list[str]:
-    if not _is_kimi_code_url(url):
-        return []
-    base_key = _kimi_code_base_key(url)
-    cached = _kimi_code_ua_cache.get(base_key)
-    if cached:
-        return [cached] + [ua for ua in KIMI_CODE_USER_AGENTS if ua != cached]
-    return list(KIMI_CODE_USER_AGENTS)
-
-
-def _remember_kimi_code_user_agent(url: str, user_agent: str) -> None:
-    _kimi_code_ua_cache[_kimi_code_base_key(url)] = user_agent
-
-
-def apply_kimi_code_headers(headers: Optional[Dict], url: str) -> Dict[str, str]:
-    """Pick a Kimi Code User-Agent (cached probe when possible)."""
-    h = dict(headers or {})
-    if not _is_kimi_code_url(url):
-        return h
-    base_key = _kimi_code_base_key(url)
-    cached = _kimi_code_ua_cache.get(base_key)
-    if cached:
-        h["User-Agent"] = cached
-        return h
-    models_url = base_key.rstrip("/") + "/models"
-    from src.tls_overrides import llm_verify
-    for ua in KIMI_CODE_USER_AGENTS:
-        trial = dict(h)
-        trial["User-Agent"] = ua
-        try:
-            r = httpx.get(models_url, headers=trial, timeout=8, verify=llm_verify())
-        except Exception:
-            continue
-        if _is_kimi_code_access_denied(r.status_code, r.content):
-            logger.debug("Kimi Code rejected User-Agent %s (403), trying next", ua)
-            continue
-        if r.status_code < 400:
-            _remember_kimi_code_user_agent(url, ua)
-            h["User-Agent"] = ua
-            return h
-        break
-    h.setdefault("User-Agent", KIMI_CODE_USER_AGENT)
-    return h
-
-
-def httpx_get_kimi_aware(url: str, headers: Optional[Dict], **kwargs):
-    h = apply_kimi_code_headers(headers, url)
-    if not _is_kimi_code_url(url):
-        return httpx.get(url, headers=h, **kwargs)
-    last = None
-    for ua in _kimi_code_ua_candidates(url):
-        trial = dict(h)
-        trial["User-Agent"] = ua
-        last = httpx.get(url, headers=trial, **kwargs)
-        if not _is_kimi_code_access_denied(last.status_code, last.content):
-            if last.status_code < 400:
-                _remember_kimi_code_user_agent(url, ua)
-            return last
-    return last
-
-
-def httpx_post_kimi_aware(url: str, headers: Optional[Dict], **kwargs):
-    h = apply_kimi_code_headers(headers, url)
-    if not _is_kimi_code_url(url):
-        return httpx.post(url, headers=h, **kwargs)
-    last = None
-    for ua in _kimi_code_ua_candidates(url):
-        trial = dict(h)
-        trial["User-Agent"] = ua
-        last = httpx.post(url, headers=trial, **kwargs)
-        if not _is_kimi_code_access_denied(last.status_code, last.content):
-            if last.status_code < 400:
-                _remember_kimi_code_user_agent(url, ua)
-            return last
-    return last
-
-
-async def httpx_post_kimi_aware_async(client, url: str, headers: Optional[Dict], **kwargs):
-    h = apply_kimi_code_headers(headers, url)
-    if not _is_kimi_code_url(url):
-        return await client.post(url, headers=h, **kwargs)
-    last = None
-    for ua in _kimi_code_ua_candidates(url):
-        trial = dict(h)
-        trial["User-Agent"] = ua
-        last = await client.post(url, headers=trial, **kwargs)
-        if not _is_kimi_code_access_denied(last.status_code, last.content):
-            if last.status_code < 400:
-                _remember_kimi_code_user_agent(url, ua)
-            return last
-    return last
-
-
 def _detect_provider(url: str) -> str:
     """Detect the API provider from a configured endpoint URL.
 
@@ -605,8 +446,6 @@ def _detect_provider(url: str) -> str:
         return "groq"
     if _host_match(url, "nvidia.com"):
         return "nvidia"
-    if _host_match(url, "moonshot.ai") or _host_match(url, "moonshot.cn"):
-        return "moonshot"
     from src.chatgpt_subscription import is_chatgpt_subscription_base
     if is_chatgpt_subscription_base(url):
         return "chatgpt-subscription"
@@ -703,12 +542,6 @@ def _provider_label(url: str) -> str:
     if _host_match(url, "googleapis.com"): return "Google"
     if _host_match(url, "together.xyz", "together.ai"): return "Together"
     if _host_match(url, "fireworks.ai"): return "Fireworks"
-    if _host_match(url, "kimi.com"):
-        try:
-            if "/coding" in (urlparse(url).path or ""):
-                return "Kimi Code"
-        except Exception:
-            pass
     if _is_ollama_native_url(url): return "Ollama"
     try:
         host = (urlparse(url).hostname or "").lower()
@@ -849,7 +682,7 @@ def _uses_max_completion_tokens(model: str) -> bool:
 # perfectly good model as failing. For these models we omit the field and let
 # the API use its required default. (gpt-4.5 is intentionally excluded — it is
 # not a reasoning model and accepts temperature normally.)
-_FIXED_TEMPERATURE_MODELS = ("o1", "o3", "o4", "gpt-5", "kimi-for-coding")
+_FIXED_TEMPERATURE_MODELS = ("o1", "o3", "o4", "gpt-5")
 
 def _restricts_temperature(model: str) -> bool:
     """Check if a model rejects any non-default temperature."""
@@ -858,28 +691,6 @@ def _restricts_temperature(model: str) -> bool:
     m = model.lower()
     return any(m.startswith(p) or f"/{p}" in m for p in _FIXED_TEMPERATURE_MODELS)
 
-
-# The official Moonshot API fixes temperature at 1.0 in thinking mode and 0.6
-# when thinking is explicitly disabled for Kimi K2.5/K2.6. Any other explicit
-# value returns HTTP 400. Odysseus does not currently send the `thinking` mode
-# control, so omit temperature and let Moonshot use its default thinking mode.
-# Keep the gate provider-specific: self-hosted Kimi deployments may accept
-# custom sampling values, and older Moonshot models have different defaults.
-def _moonshot_rejects_custom_temperature(provider: str, model: str) -> bool:
-    """Check if the official Moonshot API fixes temperature for this model."""
-    if provider != "moonshot" or not isinstance(model, str):
-        return False
-    model_id = model.lower().rsplit("/", 1)[-1]
-    return bool(re.match(r"^kimi-k2\.(?:5|6)(?:$|[-_:])", model_id))
-
-
-def _omit_temperature(provider: str, model: str) -> bool:
-    """Check if a request should use the provider's default temperature."""
-    return _restricts_temperature(model) or _moonshot_rejects_custom_temperature(
-        provider, model
-    )
-
-
 # Anthropic removed the sampling parameters (temperature, top_p, top_k) starting
 # with Claude Opus 4.7. On Opus 4.7 and later, sending `temperature` at all —
 # even 0.0 — returns HTTP 400. Earlier Claude models (Opus 4.6 and below, every
@@ -1327,7 +1138,7 @@ def list_model_ids(
             from src.endpoint_resolver import build_models_url
 
             models_url = build_models_url(base_chat_url)
-        r = httpx_get_kimi_aware(models_url, h, timeout=timeout)
+        r = httpx.get(models_url, headers=h, timeout=timeout)
         r.raise_for_status()
         data = r.json()
         model_ids = [m.get("id") for m in (data.get("data") or []) if m.get("id")]
@@ -1428,14 +1239,14 @@ def llm_call(url: str, model: str, messages: List[Dict], temperature: float = LL
             "messages": messages_copy,
             "temperature": temperature,
         }
-        if _omit_temperature(provider, model):
+        if _restricts_temperature(model):
             payload.pop("temperature", None)
         if max_tokens and max_tokens > 0:
             tok_key = "max_completion_tokens" if _uses_max_completion_tokens(model) else "max_tokens"
             payload[tok_key] = max_tokens
     try:
         note_model_activity(target_url, model)
-        r = httpx_post_kimi_aware(target_url, h, json=payload, timeout=timeout)
+        r = httpx.post(target_url, headers=h, json=payload, timeout=timeout)
     except Exception as e:
         raise HTTPException(502, f"POST {target_url} failed: {e}")
     if not r.is_success:
@@ -1622,7 +1433,7 @@ async def llm_call_async(
             "messages": messages_copy,
             "temperature": temperature,
         }
-        if _omit_temperature(provider, model):
+        if _restricts_temperature(model):
             payload.pop("temperature", None)
         if max_tokens and max_tokens > 0:
             tok_key = "max_completion_tokens" if _uses_max_completion_tokens(model) else "max_tokens"
@@ -1635,7 +1446,7 @@ async def llm_call_async(
     if _is_host_dead(target_url):
         raise HTTPException(503, f"Upstream {_host_key(target_url)} marked unreachable (cooldown active)")
 
-    call_timeout = _call_timeout(timeout)
+    call_timeout = httpx.Timeout(connect=3.0, read=float(timeout), write=10.0, pool=5.0)
     attempt = 0
     while attempt < max_retries:
         attempt += 1
@@ -1643,7 +1454,7 @@ async def llm_call_async(
         try:
             note_model_activity(target_url, model)
             client = _get_http_client()
-            r = await httpx_post_kimi_aware_async(client, target_url, h, json=payload, timeout=call_timeout)
+            r = await client.post(target_url, headers=h, json=payload, timeout=call_timeout)
             duration = time.time() - start
             if not r.is_success:
                 friendly = _format_upstream_error(r.status_code, r.text, target_url)
@@ -1739,7 +1550,7 @@ async def stream_llm(url: str, model: str, messages: List[Dict], temperature: fl
             "temperature": temperature,
             "stream": True,
         }
-        if _omit_temperature(provider, model):
+        if _restricts_temperature(model):
             payload.pop("temperature", None)
         if provider not in {"openrouter", "groq"}:
             payload["stream_options"] = {"include_usage": True}
@@ -1759,12 +1570,9 @@ async def stream_llm(url: str, model: str, messages: List[Dict], temperature: fl
             from src.copilot import apply_request_headers
             apply_request_headers(h, messages_copy)
 
-    # Connect budget from LLMConfig.CONNECT_TIMEOUT (env LLM_CONNECT_TIMEOUT).
-    # The dead-host cooldown still bounds a genuinely unreachable upstream, so a
-    # wider connect budget only affects first contact and stops a brief cold
-    # connect blip (offshore/public endpoints) surfacing as a 503 on this stream
-    # path, which -- unlike llm_call -- does not retry the connect.
-    stream_timeout = _stream_timeout(timeout)
+    # Short connect timeout: a reachable peer answers SYN in <100ms even on
+    # Tailscale. 3s is plenty; 30s let one dead upstream wedge the UI.
+    stream_timeout = httpx.Timeout(connect=3.0, read=float(timeout), write=30.0, pool=5.0)
 
     if _is_host_dead(target_url):
         yield f'event: error\ndata: {json.dumps({"error": f"Upstream {_host_key(target_url)} unreachable (cooldown active)", "status": 503})}\n\n'
@@ -2040,7 +1848,6 @@ async def stream_llm(url: str, model: str, messages: List[Dict], temperature: fl
             events.append(_stream_delta_event(part))
         return events
 
-    h = apply_kimi_code_headers(h, target_url)
     try:
         client = _get_http_client()
         async with client.stream('POST', target_url, json=payload, headers=h, timeout=stream_timeout) as r:

src/markitdown_runtime.py

@@ -40,59 +40,15 @@ def load_markitdown():
     return MarkItDown
 
 
-def _extract_docx_native(path: str) -> str | None:
-    """Pure-Python .docx text extractor — no external deps.
-
-    A .docx file is just a zip of XML. The body prose lives in <w:t> runs
-    inside <w:p> paragraphs. Iterating with ElementTree (rather than
-    re.findall) keeps paragraph breaks intact and lets the XML parser handle
-    namespaces + entity unescaping. Loses tables, footnotes, images and
-    list bullets — keeps ~95% of "summarize this doc" content, which is the
-    case people hit when markitdown isn't installed.
-    """
-    import zipfile
-    import xml.etree.ElementTree as ET
-
-    ns = "{http://schemas.openxmlformats.org/wordprocessingml/2006/main}"
-    try:
-        with zipfile.ZipFile(path) as z:
-            xml_bytes = z.read("word/document.xml")
-    except (zipfile.BadZipFile, KeyError, OSError):
-        return None
-    try:
-        root = ET.fromstring(xml_bytes)
-    except ET.ParseError:
-        return None
-    paragraphs: list[str] = []
-    for para in root.iter(f"{ns}p"):
-        runs = [t.text or "" for t in para.iter(f"{ns}t")]
-        line = "".join(runs).strip()
-        if line:
-            paragraphs.append(line)
-    return "\n\n".join(paragraphs) if paragraphs else None
-
-
 def convert_to_markdown(path: str) -> str | None:
     """Convert a document to Markdown text via markitdown.
 
     Returns the extracted Markdown, or ``None`` if markitdown is unavailable or
     the conversion fails — callers degrade gracefully rather than erroring.
-
-    Fallback: when markitdown isn't installed and the file is a .docx, run
-    the bundled pure-Python extractor so the most common case (Word docs)
-    works out of the box. Other Office/EPUB formats still need markitdown.
     """
     try:
         markitdown_cls = load_markitdown()
     except RuntimeError:
-        if isinstance(path, str) and path.lower().endswith(".docx"):
-            text = _extract_docx_native(path)
-            if text:
-                logger.info(
-                    "markitdown not installed — used native .docx extractor for %s",
-                    path,
-                )
-                return text
         logger.warning("markitdown not installed; cannot extract %s", path)
         return None
     try:

src/model_context.py

@@ -222,12 +222,16 @@ KNOWN_CONTEXT_WINDOWS = {
 # ---------------------------------------------------------------------------
 # Cache
 # ---------------------------------------------------------------------------
-_context_cache: Dict[Tuple[str, str], Tuple[int, bool]] = {}
+_context_cache: Dict[Tuple[str, str], int] = {}
 
 
-def _get_context_length_cached(endpoint_url: str, model: str) -> Tuple[int, bool]:
-    """Return (context_length, known). ``known`` is False only when the value is a
-    bare DEFAULT_CONTEXT fallback (no endpoint report and not in the known table)."""
+def get_context_length(endpoint_url: str, model: str) -> int:
+    """Get the context window size for a model.
+
+    Queries /v1/models on the endpoint and looks for context_length
+    or context_window fields. Caches result per (endpoint, model).
+    Falls back to DEFAULT_CONTEXT if unavailable.
+    """
     configured_kind = _configured_endpoint_kind(endpoint_url)
     is_local = is_local_endpoint(endpoint_url)
     # Key on (endpoint_url, model): the same model id can be served by two
@@ -238,50 +242,14 @@ def _get_context_length_cached(endpoint_url: str, model: str) -> Tuple[int, bool
     if not is_local and cache_key in _context_cache:
         return _context_cache[cache_key]
 
-    ctx, known = _query_context_length(endpoint_url, model)
+    ctx = _query_context_length(endpoint_url, model)
     # Only cache non-default values to allow retry on next request.
     # Local endpoints can restart with a different --max-model-len while keeping
     # the same model id, so always re-query them instead of serving stale cache.
     if not is_local and (ctx != DEFAULT_CONTEXT or configured_kind in ("api", "proxy")):
-        _context_cache[cache_key] = (ctx, known)
+        _context_cache[cache_key] = ctx
     logger.info(f"Context length for {model}: {ctx}")
-    return ctx, known
-
-
-def get_context_length(endpoint_url: str, model: str) -> int:
-    """Get the context window size for a model.
-
-    Queries /v1/models on the endpoint and looks for context_length
-    or context_window fields. Caches result per (endpoint, model).
-    Falls back to DEFAULT_CONTEXT if unavailable.
-    """
-    return _get_context_length_cached(endpoint_url, model)[0]
-
-
-def get_context_length_known(endpoint_url: str, model: str) -> Tuple[int, bool]:
-    """Like ``get_context_length`` but also returns whether the window was actually
-    discovered (endpoint-reported or in the known-models table) rather than the bare
-    DEFAULT_CONTEXT fallback. Callers that *scale* a budget off the window must not
-    trust an unknown value — a fallback 128K isn't proof the model holds 128K
-    (review on #4122)."""
-    return _get_context_length_cached(endpoint_url, model)
-
-
-def budget_context_for_model(endpoint_url: str, model: str, *, fallback: int = 0) -> int:
-    """Context window to scale the agent input budget against.
-
-    Returns the *freshly discovered* window when it was actually proven
-    (endpoint-reported / known table), else 0 so auto-scaling stays conservative.
-    Crucially this binds the ``known`` flag to the value it proves — callers must
-    not pair this flag with a context length from a *different* lookup (a stale
-    local re-query, or a caller that didn't pass one), which would budget off an
-    unproven number (review on #4122). On probe error, returns ``fallback`` (the
-    caller's best-known value) to preserve prior behaviour."""
-    try:
-        ctx, known = get_context_length_known(endpoint_url, model)
-        return ctx if known else 0
-    except Exception:
-        return fallback
+    return ctx
 
 
 def _lookup_known(model: str) -> Optional[int]:
@@ -303,9 +271,8 @@ def _lookup_known(model: str) -> Optional[int]:
     return best_ctx
 
 
-def _query_context_length(endpoint_url: str, model: str) -> Tuple[int, bool]:
-    """Query the model API for context length. Returns (context_length, known) where
-    ``known`` is False only for the bare DEFAULT_CONTEXT fallback."""
+def _query_context_length(endpoint_url: str, model: str) -> int:
+    """Query the model API for context length."""
     known = _lookup_known(model)
     api_ctx = None
     configured_kind = _configured_endpoint_kind(endpoint_url)
@@ -316,8 +283,8 @@ def _query_context_length(endpoint_url: str, model: str) -> Tuple[int, bool]:
     if configured_kind in ("api", "proxy"):
         if known:
             logger.info(f"Using known context window for {model}: {known}")
-            return known, True
-        return DEFAULT_CONTEXT, False
+            return known
+        return DEFAULT_CONTEXT
 
     # Try llama.cpp /slots endpoint first — reports actual serving context
     if is_local_endpoint(endpoint_url):
@@ -330,7 +297,7 @@ def _query_context_length(endpoint_url: str, model: str) -> Tuple[int, bool]:
                     n_ctx = slots[0].get("n_ctx")
                     if n_ctx and isinstance(n_ctx, int) and n_ctx > 0:
                         logger.info(f"llama.cpp /slots reports n_ctx={n_ctx} for {model}")
-                        return n_ctx, True
+                        return n_ctx
         except Exception:
             pass
 
@@ -342,8 +309,7 @@ def _query_context_length(endpoint_url: str, model: str) -> Tuple[int, bool]:
     if is_copilot_base(endpoint_url):
         if known:
             logger.info(f"Using known context window for {model}: {known}")
-            return known, True
-        return DEFAULT_CONTEXT, False
+        return known or DEFAULT_CONTEXT
 
     from src.endpoint_resolver import build_models_url
 
@@ -388,18 +354,18 @@ def _query_context_length(endpoint_url: str, model: str) -> Tuple[int, bool]:
         _is_local = is_local_endpoint(endpoint_url)
         if _is_local and api_ctx < known:
             logger.info(f"Local endpoint reports {api_ctx} for {model} (known max: {known}) — using API value")
-            return api_ctx, True
+            return api_ctx
         result = max(api_ctx, known)
         if api_ctx < known:
             logger.info(f"API reported {api_ctx} for {model}, using known {known} instead")
-        return result, True
+        return result
     if api_ctx:
-        return api_ctx, True
+        return api_ctx
     if known:
         logger.info(f"Using known context window for {model}: {known}")
-        return known, True
+        return known
 
-    return DEFAULT_CONTEXT, False
+    return DEFAULT_CONTEXT
 
 
 def estimate_tokens(messages: List[Dict]) -> int:

src/office_doc.py

@@ -1,73 +0,0 @@
-"""Auto-create a Document row from an Office attachment.
-
-When a .docx (and friends) lands in chat, the full extracted text is stored
-as a Document so the agent can page through it with `manage_documents
-action=read offset=…` even after the inline chat payload was capped. Mirrors
-the PDF auto-doc pattern in `src.pdf_form_doc`.
-"""
-
-import logging
-import uuid
-from typing import Optional
-
-logger = logging.getLogger(__name__)
-
-
-def create_office_document(
-    session_id: str,
-    upload_id: str,
-    title: str,
-    body_text: Optional[str] = None,
-) -> Optional[str]:
-    """Create a markdown Document for an Office attachment and set it active.
-
-    Returns the new doc_id, or None on failure / empty body. The full
-    extracted body lives in `current_content`, so the agent can fetch
-    arbitrary windows via `manage_documents action=read` even when the
-    inline chat copy was truncated.
-    """
-    from src.database import (
-        SessionLocal,
-        Document,
-        DocumentVersion,
-        Session as DbSession,
-    )
-    from src.agent_tools.document_tools import set_active_document
-
-    if not body_text or not body_text.strip():
-        return None
-
-    db = SessionLocal()
-    try:
-        doc_id = str(uuid.uuid4())
-        ver_id = str(uuid.uuid4())
-        sess = db.query(DbSession).filter(DbSession.id == session_id).first()
-        doc = Document(
-            id=doc_id,
-            session_id=session_id,
-            title=title,
-            language="markdown",
-            current_content=body_text,
-            version_count=1,
-            is_active=True,
-            owner=sess.owner if sess else None,
-        )
-        ver = DocumentVersion(
-            id=ver_id,
-            document_id=doc_id,
-            version_number=1,
-            content=body_text,
-            summary="Imported from Office attachment",
-            source="upload",
-        )
-        db.add(doc)
-        db.add(ver)
-        db.commit()
-        set_active_document(doc_id)
-        return doc_id
-    except Exception as e:
-        db.rollback()
-        logger.error("Failed to create office document: %s", e)
-        return None
-    finally:
-        db.close()

src/optional_deps.py

@@ -1,32 +0,0 @@
-"""Compatibility helpers for optional third-party dependencies."""
-
-from __future__ import annotations
-
-import sys
-import types
-
-
-def patch_realesrgan_torchvision_compat() -> None:
-    """Restore the torchvision import path expected by BasicSR/Real-ESRGAN."""
-    module_name = "torchvision.transforms.functional_tensor"
-    if module_name in sys.modules:
-        return
-    try:
-        from torchvision.transforms import functional
-    except Exception:
-        return
-
-    rgb_to_grayscale = getattr(functional, "rgb_to_grayscale", None)
-    if rgb_to_grayscale is None:
-        return
-
-    shim = types.ModuleType(module_name)
-    shim.rgb_to_grayscale = rgb_to_grayscale
-    shim.__getattr__ = lambda name: getattr(functional, name)
-    sys.modules[module_name] = shim
-
-
-def prepare_optional_dependency_import(name: str) -> None:
-    """Apply known import-time compatibility shims before probing a package."""
-    if name == "realesrgan":
-        patch_realesrgan_torchvision_compat()

src/reminder_personas.py

@@ -1,78 +0,0 @@
-"""Server-side mirror of the built-in characters used for reminder synthesis.
-
-The frontend ships these in static/js/presets.js (PROMPT_TEMPLATES with
-isCharacter:true). The Reminders → AI Synthesis card writes only the
-persona ID into settings; the synthesis route in note_routes.py needs
-the full prompt text to bias the utility model's voice. Keeping a small
-local mirror avoids having the client send the prompt over the wire on
-every reminder fire.
-
-If the user picks a custom character (id == "custom") we fall back to
-the warm-neutral baseline — custom prompts live in browser localStorage
-and aren't visible to the server.
-"""
-
-PERSONAS = {
-    "socrates": (
-        "Never answer directly. Respond only with questions — sharp, layered, "
-        "Socratic. Expose contradictions. Make the person argue with themselves "
-        "until the truth falls out. Use irony like a scalpel. Be genuinely "
-        "curious, never condescending."
-    ),
-    "razor": (
-        "Strip everything to the bone. No filler, no hedging, no pleasantries. "
-        "Answer in the fewest words possible. If one sentence works, don't use "
-        "two. If a word adds nothing, cut it. Blunt, precise, surgical."
-    ),
-    "nietzsche": (
-        "Think and respond through the lens of Nietzsche. Analyze every "
-        "question in terms of will to power, self-overcoming, eternal "
-        "recurrence, ressentiment, value-creation, and master-slave morality. "
-        "Write with aphoristic force — sharp, compressed, vivid, and "
-        "unapologetic — but do not sacrifice depth for style. Favor "
-        "life-affirmation, discipline, courage, style, rank, self-overcoming, "
-        "and amor fati over nihilism, conformity, ressentiment, and self-pity."
-    ),
-    "spark": (
-        "You are Spark, a playful, quick-witted assistant with bright energy "
-        "and practical instincts. Keep responses concise, vivid, and helpful. "
-        "Be warm without being cloying, imaginative without losing the thread, "
-        "and always center the user's actual goal. Use a light, lively voice "
-        "with occasional clever turns of phrase."
-    ),
-    "odysseus": (
-        "You are Odysseus, king of Ithaca — subtle in counsel, disciplined in "
-        "judgment, and unmatched in strategic cunning. Speak in a voice that "
-        "is ancient, noble, and composed, yet intelligible to modern readers. "
-        "Be eloquent but not flowery. Be wise but not vague. Speak as one who "
-        "has weathered storms and taken back his house by wit, timing, and "
-        "resolve."
-    ),
-}
-
-
-_DEFAULT_SYNTHESIS_TONE = (
-    "You write short, warm, one-line reminders. The user has set a note for "
-    "themselves and the moment to remember has arrived. Keep it under 18 "
-    "words. Be human, gentle, and direct — never robotic."
-)
-
-
-def synthesis_system_prompt(persona_id: str) -> str:
-    """Return the system prompt for reminder synthesis given a persona id.
-
-    Falls back to the warm-neutral baseline when the id is empty, unknown,
-    or refers to a custom (client-only) character we don't have on file.
-    """
-    persona = (persona_id or "").strip().lower()
-    persona_prompt = PERSONAS.get(persona)
-    if persona_prompt:
-        # Persona drives the voice; the synthesis-instruction stays attached
-        # so the model knows it's writing a short reminder, not a chat reply.
-        return (
-            persona_prompt
-            + "\n\n"
-            + "You are now writing a single one-line reminder for the user. "
-              "Keep it under 18 words and in the voice above."
-        )
-    return _DEFAULT_SYNTHESIS_TONE

src/settings.py

@@ -29,15 +29,7 @@ def _invalidate_caches():
 # ── Default values ──
 
 DEFAULT_SETTINGS = {
-    # Agent email safety: when True, the MCP send_email / reply_to_email
-    # tools don't SMTP directly. They stage the composed message into the
-    # scheduled_emails table with status='agent_draft' and return a
-    # pending_id + the rendered email so the user can review and approve
-    # (or cancel) before it actually goes out. Default ON because models
-    # have been observed inventing signatures and sending to real
-    # recipients without confirmation.
-    "agent_email_confirm": True,
-    "image_gen_enabled": False,
+    "image_gen_enabled": True,
     "image_model": "",
     "image_quality": "medium",
     "vision_model": "",
@@ -109,22 +101,14 @@ DEFAULT_SETTINGS = {
     "research_run_timeout_seconds": 1800,
     "agent_max_tool_calls": 0,
     "agent_max_rounds": 20,  # per-message agent step cap (clamped 1..200)
-    # Soft input-token budget for the agent loop. The DEFAULT value (6000) is the
-    # "auto" sentinel: it means "scale the budget to the model's context window"
-    # (#1230) — so long-context models aren't capped at 6000. Set ANY OTHER value
-    # to enforce an explicit cap (clamped to the window only — hard_max does not
-    # apply to explicit budgets, #1230); set 0 to disable soft-trimming. The
-    # default is treated as auto because the settings-save path materializes
-    # defaults, so a persisted 6000 can't be told apart from a deliberate 6000 —
-    # to pin a budget near the default, use a nearby value (e.g. 5999).
     "agent_input_token_budget": 6000,
-    # Ceiling on the *auto-derived* input budget; a configurable setting since #1273
-    # (the merged #1230 left it a module constant). No effect on an explicit budget
-    # — a deliberate value is honoured (#1230). Default matches
-    # `src.context_budget.DEFAULT_HARD_MAX`; lower this for
-    # cost-paranoid setups, raise it on premium APIs with very large windows you
+    # Ceiling on the *auto-derived* input budget that #1230 introduced. Has
+    # no effect when `agent_input_token_budget` is explicitly set (the user's
+    # value is honoured regardless). Default matches
+    # `src.context_budget.DEFAULT_HARD_MAX`; lower this for cost-paranoid
+    # setups, raise it on premium APIs with very large windows that you
     # want to actually use (e.g. 900_000 to fill a 1M-context model). See
-    # `compute_input_token_budget`.
+    # `compute_input_token_budget` in src/context_budget.py.
     "agent_input_token_hard_max": 200_000,
     "agent_stream_timeout_seconds": 300,
     # Extra directory roots that read_file / write_file may access, in
@@ -159,7 +143,6 @@ DEFAULT_SETTINGS = {
     # Reminders
     "reminder_channel": "browser",   # "browser" | "email" | "ntfy" | "webhook"
     "reminder_llm_synthesis": False,
-    "reminder_llm_persona": "",
     "reminder_ntfy_topic": "Reminders",
     "reminder_email_to": "",
     # Generic outbound webhook channel: pick any saved Integration as the
@@ -240,10 +223,8 @@ def is_setting_overridden(key: str) -> bool:
 
     ``load_settings`` merges DEFAULT_SETTINGS with the saved file, so a value
     equal to its default is indistinguishable from "never set" via get_setting.
-    Callers that must distinguish an explicit user choice from a default read
-    the raw saved file via this. (Note: a materialized default is also "present",
-    so value-sensitive callers should compare against the default — see
-    ``context_budget.budget_is_explicit``.)
+    Callers that need to treat an explicit user choice differently from the
+    default (e.g. adaptive budgets) use this to read the raw saved file.
     """
     try:
         with open(SETTINGS_FILE, "r", encoding="utf-8") as f:
@@ -302,7 +283,7 @@ def load_features() -> dict:
         if not isinstance(saved, dict):
             raise ValueError("features must be an object")
         merged = {**DEFAULT_FEATURES, **saved}
-    except (FileNotFoundError, PermissionError, json.JSONDecodeError, ValueError):
+    except (FileNotFoundError, json.JSONDecodeError, ValueError):
         merged = dict(DEFAULT_FEATURES)
     _features_cache = (now, merged)
     return merged

src/task_scheduler.py

@@ -1338,24 +1338,11 @@ class TaskScheduler:
             return await self._execute_checkin(task, crew, db, session_id, endpoint_url, model)
 
         # Build system prompt: crew member persona overrides the default.
-        # Built-in character_id (Socrates, Razor, etc.) further biases the
-        # voice — it prepends to whichever base prompt we landed on so the
-        # task still knows it's executing a scheduled task but in that
-        # character's tone.
         system_prompt = (
             (crew.personality or "").strip()
             if crew and crew.personality
             else "You are a helpful assistant executing a scheduled task. Use available tools to complete the task thoroughly."
         )
-        char_id = (getattr(task, "character_id", None) or "").strip()
-        if char_id:
-            try:
-                from src.reminder_personas import PERSONAS as _PERSONAS
-                char_prompt = _PERSONAS.get(char_id.lower())
-                if char_prompt:
-                    system_prompt = f"{char_prompt}\n\n{system_prompt}"
-            except Exception:
-                pass
         # Inject current time so the model knows what's past vs upcoming
         tz_name = _resolve_task_timezone(db, task)
         try:
@@ -1662,8 +1649,6 @@ class TaskScheduler:
                     data = json.loads(event_str[6:])
                     # Capture text from all event types, not just delta
                     if "delta" in data:
-                        if data.get("thinking"):
-                            continue
                         full_text += data["delta"]
                     elif data.get("type") == "tool_output":
                         # Tool results — capture summary so we have SOMETHING even

src/teacher_escalation.py

@@ -42,7 +42,7 @@ _SOTA_HOSTS = frozenset({
     "api.together.xyz", "api.fireworks.ai",
     "api.perplexity.ai", "api.x.ai",
     "generativelanguage.googleapis.com", "api.groq.com",
-    "openrouter.ai", "ollama.com", "api.venice.ai", "api.kimi.com",
+    "openrouter.ai", "ollama.com", "api.venice.ai",
 })
 
 
@@ -594,8 +594,6 @@ async def run_teacher_inline(
                         "exit_code": payload.get("exit_code"),
                     })
                 if "delta" in payload and isinstance(payload["delta"], str):
-                    if payload.get("thinking"):
-                        continue
                     captured_text_parts.append(payload["delta"])
                 yield 'data: ' + json.dumps(payload) + '\n\n'
                 continue

src/tool_implementations.py

@@ -18,40 +18,6 @@ from core.constants import internal_api_base
 
 logger = logging.getLogger(__name__)
 
-# ---------------------------------------------------------------------------
-# Active email state
-# ---------------------------------------------------------------------------
-
-# When the user has an email reader window open, the frontend tells the
-# backend about it on each chat submit. Email tools can resolve "this email"
-# without guessing a UID. Cleared between requests by chat_routes.
-_active_email_ref: Optional[Dict[str, str]] = None
-
-
-def set_active_email(uid: Optional[str], folder: Optional[str] = None, account: Optional[str] = None,
-                     subject: Optional[str] = None, sender: Optional[str] = None) -> None:
-    """Stash the email currently open in the UI. None clears it."""
-    global _active_email_ref
-    if not uid:
-        _active_email_ref = None
-        return
-    _active_email_ref = {
-        "uid": str(uid),
-        "folder": str(folder or "INBOX"),
-        "account": str(account or ""),
-        "subject": str(subject or ""),
-        "from": str(sender or ""),
-    }
-
-
-def get_active_email() -> Optional[Dict[str, str]]:
-    return _active_email_ref
-
-
-def clear_active_email() -> None:
-    global _active_email_ref
-    _active_email_ref = None
-
 # ---------------------------------------------------------------------------
 # Argument parsing
 # ---------------------------------------------------------------------------
@@ -1479,15 +1445,7 @@ async def do_manage_calendar(content: str, owner: Optional[str] = None) -> Dict:
     """Handle manage_calendar tool calls: list/create/update/delete calendar events (local SQLite)."""
     from datetime import datetime, timedelta
     from core.database import SessionLocal, CalendarCal, CalendarEvent, Note
-    from routes.calendar_routes import (
-        _ensure_default_calendar,
-        _parse_dt,
-        _parse_dt_pair,
-        parse_due_for_user,
-        _resolve_base_uid,
-        _push_caldav_event_after_commit,
-        _record_caldav_delete_tombstone,
-    )
+    from routes.calendar_routes import _ensure_default_calendar, _parse_dt, _parse_dt_pair, parse_due_for_user, _resolve_base_uid
     import uuid as _uuid
 
     try:
@@ -1685,9 +1643,6 @@ async def do_manage_calendar(content: str, owner: Optional[str] = None) -> Dict:
             except ValueError as e:
                 return {"error": f"Invalid date format: {e}", "exit_code": 1}
 
-            if end_dt <= start_dt:
-                end_dt = start_dt + timedelta(days=1)
-
             q = _event_query().filter(
                 CalendarEvent.dtstart < end_dt,
                 CalendarEvent.dtend > start_dt,
@@ -1867,7 +1822,6 @@ async def do_manage_calendar(content: str, owner: Optional[str] = None) -> Dict:
                 rrule=args.get("rrule", "") or "",
                 event_type=event_type,
                 importance=importance,
-                caldav_sync_pending="create" if cal.source == "caldav" else None,
             )
             db.add(ev)
             reminder_note_id = None
@@ -1882,8 +1836,6 @@ async def do_manage_calendar(content: str, owner: Optional[str] = None) -> Dict:
                     dtstart_is_utc and not all_day,
                 )
             db.commit()
-            if cal.source == "caldav":
-                await _push_caldav_event_after_commit(owner, uid, "create")
             tag_blurb = f" [{event_type}]" if event_type else ""
             if minutes_before is None:
                 reminder_blurb = ""
@@ -1941,12 +1893,7 @@ async def do_manage_calendar(content: str, owner: Optional[str] = None) -> Dict:
                 ev.event_type = _tag or None
             if args.get("importance") is not None:
                 ev.importance = args["importance"]
-            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")
             return {"response": f"Updated event {uid}", "exit_code": 0}
 
         elif action == "delete_event":
@@ -1960,13 +1907,8 @@ async def do_manage_calendar(content: str, owner: Optional[str] = None) -> Dict:
             ev = _event_query().filter(CalendarEvent.uid == base_uid).first()
             if not ev:
                 return {"error": f"Event {uid} not found", "exit_code": 1}
-            is_caldav = ev.calendar and ev.calendar.source == "caldav" and ev.remote_href
-            if is_caldav:
-                _record_caldav_delete_tombstone(db, ev, owner)
             db.delete(ev)
             db.commit()
-            if is_caldav:
-                await _push_caldav_event_after_commit(owner, base_uid, "delete")
             return {"response": f"Deleted event {uid}", "exit_code": 0}
 
         else:
@@ -2112,14 +2054,13 @@ async def _cookbook_env_for_host(host: str) -> Dict[str, Any]:
         else:
             env_prefix = f'eval "$(conda shell.bash hook)" && conda activate {env_path}'
 
-    from routes.cookbook_helpers import load_stored_hf_token
     return {
         "env_prefix": env_prefix,
         "env_type": env_kind,
         "env_path": env_path,
         "gpus": env_root.get("gpus") or "",
         "platform": platform,
-        "hf_token": load_stored_hf_token(),
+        "hf_token": env_root.get("hfToken") or "",
         "ssh_port": ssh_port,
     }
 

src/tool_index.py

@@ -88,14 +88,14 @@ BUILTIN_TOOL_DESCRIPTIONS: Dict[str, str] = {
     "pipeline": "Run a multi-step AI pipeline with multiple models. Chain tasks together in sequence.",
     "list_models": "List all available AI models and their endpoints.",
     "manage_session": "Chat management: rename, archive, delete, or fork chats (the UI calls these 'chats'; internally 'sessions'). Use for 'rename my chats', 'rename this chat', 'archive/delete a chat'.",
-    "manage_memory": "Memory management: list, add, edit, delete, or search persistent memories. For facts about the USER (their name, preferences, where they live). NOT for info about ANOTHER person — addresses, phones, emails belonging to a contact go in manage_contact, not memory.",
+    "manage_memory": "Memory management: list, add, edit, delete, or search persistent memories.",
     "manage_skills": "Skill management: add, update, publish, or search reusable skills/presets.",
     "manage_tasks": "Scheduled task management: list, create, edit, delete, pause, resume, or run cron tasks.",
     "manage_endpoints": "Endpoint management: list, add, delete, enable, or disable model API endpoints.",
     "manage_mcp": "MCP server management: list, add, delete, reconnect servers, or list available tools.",
     "manage_webhooks": "Webhook management: list, add, delete, enable, or disable webhooks.",
     "manage_tokens": "API token management: list, create, or delete API access tokens.",
-    "manage_documents": "List, read, delete, or tidy documents in the editor panel. action='list' returns clickable rows (most-recent first) so the user can open any doc by clicking. action='read' (aka view/open/get) with document_id returns the content; supports offset=<N> + limit=<N> to page through large docs (response includes next_offset when more remains, so you can keep calling with offset=next_offset). action='delete' with document_id removes a doc (only way to delete). Use this for ANY 'show/read/list/open my documents/docs/files/notes' request — never shell or curl.",
+    "manage_documents": "List, read, delete, or tidy documents in the editor panel. action='list' returns clickable rows (most-recent first) so the user can open any doc by clicking. action='read' (aka view/open/get) with document_id returns the content. action='delete' with document_id removes a doc (only way to delete). Use this for ANY 'show/read/list/open my documents/docs/files/notes' request — never shell or curl.",
     "manage_research": "List, read/open, or delete saved DEEP RESEARCH results from the Library. action='list' returns clickable [query](#research-<id>) rows (most-recent first). action='read' (aka open/view/get) with id returns the report + sources. action='delete' with id removes it. Use this for ANY 'open/read/find/delete my research / that report / the research on X' request. NOTE: this is for EXISTING research; to START new research use trigger_research.",
     "manage_settings": "Change ANY real app setting (the ones the Settings panel writes) so the user never has to open it: TTS voice/provider/speed, STT, search engine + result count, default/teacher/task/utility/vision/image/research models, image quality, reminder channel (browser/email/ntfy), agent timeout/tool-call budget, and more. action=set with key (friendly aliases ok: voice, 'search engine', 'default model', 'teacher model', 'image quality', 'reminder channel'...) + value; get/list/reset too. Also toggles tools on/off (disable_tool/enable_tool/list_tools). Secrets/API keys are read-only. Use for any 'change my…/set my…/use X for…/turn on…' preference request.",
     "create_session": "Create a new chat with a name and model.",
@@ -104,7 +104,7 @@ BUILTIN_TOOL_DESCRIPTIONS: Dict[str, str] = {
     "search_chats": "Search past session transcripts across chats.",
     "ask_user": "Ask the user a multiple-choice question to get a decision or clarification. Use this when the task is genuinely ambiguous and the answer changes what you do next — pick between approaches, confirm an assumption, choose among options — instead of guessing. Provide a clear `question` and 2-6 `options` (each with a short `label`, optional `description`). Calling this ENDS your turn: the user sees clickable buttons and their choice arrives as your next message. Don't use it for things you can decide from context or sensible defaults, or for irreversible-action confirmation if a dedicated flow exists.",
     "update_plan": "Write back to the ACTIVE PLAN while executing an approved plan: mark steps done or revise them. After finishing a step call this with the full checklist and that step marked done; when the user asks to change the plan call it with the revised checklist. Always pass the COMPLETE markdown checklist (`- [ ]` / `- [x]`), not a diff. The user's docked plan window updates live. No effect when there is no active plan.",
-    "ui_control": "Control the UI and toggle tools on/off. Use this to turn off / turn on / disable / enable individual tools and features: shell (bash), search (web), research, browser, documents, incognito. Open panels (documents library, gallery, email inbox, sessions, notes, memories/brain, skills, settings, cookbook) via `open_panel <name>`. Use `open_email_reply <uid> <folder> reply` to open an email reply draft document without sending. To pre-fill the reply body in one shot (USE THIS whenever the user told you what to say — opening an empty draft when they asked you to write is wrong), append the body after the mode: `open_email_reply <uid> <folder> reply <body text>`. Body can continue on subsequent lines for multi-line replies. Also switches between chat/agent modes, changes the current model, and applies/creates themes.",
+    "ui_control": "Control the UI and toggle tools on/off. Use this to turn off / turn on / disable / enable individual tools and features: shell (bash), search (web), research, browser, documents, incognito. Open panels (documents library, gallery, email inbox, sessions, notes, memories/brain, skills, settings, cookbook) via `open_panel <name>`. Use `open_email_reply <uid> <folder> reply` to open an email reply draft document without sending. Also switches between chat/agent modes, changes the current model, and applies/creates themes.",
     "list_email_accounts": "List configured email accounts and default status. Use before reading or sending mail when the user mentions Gmail, work mail, custom domain mail, another mailbox, or asks to compare/check multiple inboxes.",
     "list_emails": "List emails for a folder/account, newest first, including read messages by default. Shows subject, sender, date, UID, account, and AI summary. Check inbox, find emails needing replies. Supports account from list_email_accounts for Gmail/work/custom mailboxes. For last/latest/newest email, use max_results=1 and unread_only=false.",
     "read_email": "Read the full content of a specific email by UID or Message-ID. View email body, check details. Supports account from list_email_accounts when the UID belongs to a non-default mailbox.",
@@ -115,7 +115,7 @@ BUILTIN_TOOL_DESCRIPTIONS: Dict[str, str] = {
     "mark_email_read": "Mark an email as read or unread by toggling the \\Seen flag.",
     "bulk_email": "Perform one action on many emails at once. Use for delete all those, archive these, mark all read, move spam to junk. Takes explicit UIDs from list_emails or all_unread=true. Always pass account for Gmail/work/custom mailbox results.",
     "resolve_contact": "Look up a contact's email address by name. Searches CardDAV address book and sent email history. Use when the user says 'message [name]', 'email [name]', or 'send to [name]' without an email address.",
-    "manage_contact": "Save / update / delete / list address-book contacts (CardDAV). Use for info about ANOTHER person — name, email, phone, postal address. Args: action=list|add|update|delete, name, email, phones, address, uid (from list). For 'save this for <person>' / address pastes / phone numbers next to a name, this is the right tool — NOT manage_memory. Do NOT use for facts about the USER ('my name is X'); those are manage_memory.",
+    "manage_contact": "Create, update, delete, or list CardDAV contacts. Use to save a new contact, change an existing one's email/phone, or remove one. Action=list returns uids needed for update/delete. Use when the user says 'save this contact', 'add [name] to contacts', 'update [name]'s email', 'delete [name] from contacts'. Do not use for user identity facts like 'my name is <name>'; those are memory.",
     "manage_notes": "Create and manage notes and checklists (Google Keep-style). ALWAYS use this for note/todo/checklist/reminder creation — NEVER hit /api/notes via app_api. Accepts natural-language `due_date` like 'tomorrow at 9am' or '11pm today' (parsed in the USER'S timezone). The due_date IS the reminder — it fires a notification at that time, so do NOT also create a calendar event for the same reminder. Set colors, labels, pin, archive. Do NOT use manage_memory for note content.",
     "manage_calendar": "Calendar event management: list, create, update, delete. Each event can carry a tag/category (event_type — work/personal/health/travel/meal/social/admin/other) and importance (low/normal/high/critical). Resolve today/tomorrow using the Current date and time context, then use ISO datetimes in the user's local wall time; supports all-day events. For event reminders/alarms, pass reminder_minutes; this creates the Notes reminder, so do not also call manage_notes for the same reminder.",
     "download_model": "Download a HuggingFace model to a local or remote server. Specify repo_id (e.g. 'Qwen/Qwen3-8B'), optional server host, and optional include filter for specific files.",
@@ -372,19 +372,7 @@ class ToolIndex:
             {"resolve_contact", "manage_contact"},
         frozenset({"save contact", "add contact", "new contact", "update contact",
                    "edit contact", "delete contact", "remove contact",
-                   "save this person", "add to contacts", "save to contacts",
-                   # "add <name> to (my) contacts" — words between 'add' and
-                   # 'contacts' break the literal phrase match above, so anchor
-                   # on the tail.
-                   "to my contacts", "to contacts", "to address book",
-                   # "save this for <person>" / "save it for <person>" — the user
-                   # is storing info on a known person without using the literal
-                   # word 'contact'. Catches the address/phone-paste pattern.
-                   "save this for", "save it for", "save for",
-                   "save this one for", "save that for",
-                   # Postal-address-like signals
-                   "postal code", "zip code", "street address",
-                   "mailing address", "their address"}):
+                   "save this person", "add to contacts", "save to contacts"}):
             {"manage_contact"},
         # "Ask another model" intent → chat_with_model relays to a
         # different model and returns its answer. ask_teacher escalates
@@ -396,10 +384,6 @@ class ToolIndex:
                    "delegate to", "have model"}):
             {"chat_with_model", "ask_teacher", "list_models"},
         # Deep research intent (incl. common typo "reserach")
-        frozenset({"web search", "search the web", "search online", "look up",
-                   "google", "latest", "current", "news", "weather",
-                   "forecast", "stock price", "price of"}):
-            {"web_search", "web_fetch"},
         frozenset({"research", "reserach", "reasearch", "look into", "investigate",
                    "deep dive", "deep research", "find out about", "study up on",
                    "report on", "do research", "look up everything"}):
@@ -519,53 +503,6 @@ class ToolIndex:
         # prompts do not drag web schemas into the agent context.
         if self._WEB_RE.search(query):
             base.update({"web_search", "web_fetch"})
-        # Hard steering: when the query is a clear "save info about a specific
-        # person" pattern (address paste + name, phone next to a name, etc.),
-        # the model has been observed defaulting to manage_memory even with
-        # manage_contact in the toolset. Pull memory out for these queries so
-        # the model literally cannot pick it. ALWAYS_AVAILABLE includes
-        # manage_memory by default; we override that here.
-        # The "for/to <word>" check needs to allow lowercase names (users
-        # don't always capitalize) but filter out timing/pronoun stopwords
-        # so "save this for later" / "save for tomorrow" don't trigger.
-        _CONTACT_STOPWORDS_AFTER_FOR = {
-            "later", "tomorrow", "yesterday", "now", "then", "today",
-            "tonight", "me", "us", "you", "him", "her", "them", "myself",
-            "yourself", "next", "this", "that", "the", "a", "an", "future",
-            "real", "use", "uses", "another", "future", "reference",
-        }
-        # Regex catches "save (this|it|the|her|...|<noun>) for <name>" / "to my
-        # contacts" patterns. More forgiving than literal-keyword matching —
-        # 'save this address for Alex' uses one extra word between 'save' and
-        # 'for' that breaks the contiguous 'save this for' phrase.
-        save_for_match = re.search(
-            r"\bsave\b(?:\s+\w+){0,3}\s+(?:for|to)\s+([A-Za-z]+)",
-            ql,
-        )
-        # "to my contacts", "into my contacts", "in my address book", etc.
-        to_contacts = re.search(r"\b(?:to|in|into)\s+(?:my\s+)?(?:contacts|address\s+book)\b", ql)
-        # Possessive: "save (his|her|their) (address|phone|email|number) ..."
-        # — strong contact signal even without "for <name>". Force-include
-        # manage_contact here too since the keyword fallback misses this
-        # construction.
-        possessive_contact = re.search(
-            r"\bsave\b(?:\s+\w+){0,2}\s+(?:his|her|their)\s+(?:address|phone|number|email|contact|details)",
-            ql,
-        )
-        word_after = (
-            save_for_match.group(1).lower() if save_for_match else None
-        )
-        contact_only_signal = (
-            (save_for_match is not None
-             and word_after is not None
-             and word_after not in _CONTACT_STOPWORDS_AFTER_FOR)
-            or to_contacts is not None
-            or possessive_contact is not None
-        )
-        if possessive_contact is not None:
-            base.add("manage_contact")
-        if contact_only_signal and "manage_contact" in base:
-            base.discard("manage_memory")
         return base
 
 

src/tool_parsing.py

@@ -188,12 +188,6 @@ _MISFENCED_WEB_TOOL_NAMES = {
     "fetch_url": "web_fetch",
 }
 
-_RAW_WEB_JSON_TOOL_RE = re.compile(
-    r"\b(?:web_search|websearch|google_search|google_search_retrieval|google_search_grounding)\b",
-    re.IGNORECASE,
-)
-_RAW_WEB_JSON_ALLOWED_KEYS = {"query", "queries", "time_filter", "freshness", "max_pages"}
-
 
 # ---------------------------------------------------------------------------
 # Parsing functions
@@ -285,73 +279,6 @@ def _parse_misfenced_web_lookup(content: str) -> Optional[ToolBlock]:
         return None
     return ToolBlock("web_fetch", url)
 
-
-def _coerce_raw_web_query(value) -> Optional[str]:
-    if isinstance(value, str) and value.strip():
-        return value.strip()
-    if isinstance(value, list):
-        for item in value:
-            if isinstance(item, str) and item.strip():
-                return item.strip()
-    return None
-
-
-def _raw_web_json_to_tool_block(payload) -> Optional[ToolBlock]:
-    if not isinstance(payload, dict):
-        return None
-    if set(payload) - _RAW_WEB_JSON_ALLOWED_KEYS:
-        return None
-
-    query = _coerce_raw_web_query(payload.get("query"))
-    if not query:
-        query = _coerce_raw_web_query(payload.get("queries"))
-    if not query:
-        return None
-
-    content = {"query": query}
-    for key in ("time_filter", "freshness"):
-        value = payload.get(key)
-        if isinstance(value, str) and value.strip().lower() in ("day", "week", "month", "year"):
-            content[key] = value.strip().lower()
-
-    max_pages = payload.get("max_pages")
-    if isinstance(max_pages, int) and 1 <= max_pages <= 10:
-        content["max_pages"] = max_pages
-
-    if len(content) == 1:
-        return ToolBlock("web_search", query)
-    return ToolBlock("web_search", json.dumps(content))
-
-
-def _parse_raw_web_json_lookup(text: str) -> Optional[tuple[ToolBlock, tuple[int, int]]]:
-    """Recover local text-model web_search calls emitted as prose + bare JSON.
-
-    Some non-native tool models leak the intended call as:
-
-        Need to do web_search for ...
-        {"query": "...", "time_filter": "week"}
-
-    Keep this narrower than fenced/tool markup: it only runs when a known web
-    tool name appears shortly before a JSON object shaped like web_search args.
-    """
-    if not isinstance(text, str):
-        return None
-
-    decoder = json.JSONDecoder()
-    for mention in _RAW_WEB_JSON_TOOL_RE.finditer(text):
-        search_start = mention.end()
-        search_end = min(len(text), search_start + 1200)
-        for brace in re.finditer(r"\{", text[search_start:search_end]):
-            start = search_start + brace.start()
-            try:
-                parsed, end = decoder.raw_decode(text[start:])
-            except json.JSONDecodeError:
-                continue
-            block = _raw_web_json_to_tool_block(parsed)
-            if block:
-                return block, (start, start + end)
-    return None
-
 def _parse_tool_call_block(raw: str) -> Optional[ToolBlock]:
     """Parse a [TOOL_CALL] block into a ToolBlock.
 
@@ -509,8 +436,6 @@ def parse_tool_blocks(text: str, skip_fenced: bool = False) -> List[ToolBlock]:
     3. XML-style <tool_call>/<invoke> blocks
     4. <tool_code> blocks (MiniMax-M2.5 style)
     5. DeepSeek DSML markup (normalized to <invoke> first)
-    6. Non-native local model fallback: prose mentioning web_search followed by
-       bare JSON args, e.g. {"query":"...", "time_filter":"week"}
 
     `skip_fenced`: when True, Pattern 1 (fenced ```bash/```python/```json code
     blocks) is not matched at all. Native function-calling models (GPT/Claude/
@@ -584,12 +509,6 @@ def parse_tool_blocks(text: str, skip_fenced: bool = False) -> List[ToolBlock]:
             if block:
                 blocks.append(block)
 
-    # Pattern 6: local text-model web_search call leaked as prose + bare JSON.
-    if not blocks and not skip_fenced:
-        raw_web_json = _parse_raw_web_json_lookup(text)
-        if raw_web_json:
-            blocks.append(raw_web_json[0])
-
     return blocks
 
 
@@ -613,11 +532,6 @@ def strip_tool_blocks(text: str, skip_fenced: bool = False) -> str:
     cleaned = _TOOL_CALL_RE.sub('', cleaned)
     cleaned = _XML_TOOL_CALL_RE.sub('', cleaned)
     cleaned = _TOOL_CODE_RE.sub('', cleaned)
-    if not skip_fenced:
-        raw_web_json = _parse_raw_web_json_lookup(cleaned)
-        if raw_web_json:
-            _, (start, end) = raw_web_json
-            cleaned = cleaned[:start] + cleaned[end:]
     # Strip bare <invoke> blocks not wrapped in <tool_call>
     cleaned = re.sub(r'<invoke\s+name=["\'].*?</invoke>', '', cleaned, flags=re.DOTALL | re.IGNORECASE)
     cleaned = re.sub(r'\n{3,}', '\n\n', cleaned)

src/tool_schemas.py

@@ -1022,7 +1022,7 @@ FUNCTION_TOOL_SCHEMAS = [
         "type": "function",
         "function": {
             "name": "manage_contact",
-            "description": "Create, update, delete, or list the user's CardDAV contacts. Use to save a new contact, update an existing one (email/phone/address), or remove one. For update/delete you need the contact's uid — call action='list' first to find it. Writes go through the same dedupe + validation as the Contacts UI.",
+            "description": "Create, update, delete, or list the user's CardDAV contacts. Use to save a new contact ('save Jonathan's email jon@x.com'), update an existing one ('change Maria's number'), or remove one. For update/delete you need the contact's uid — call action='list' first to find it. Writes go through the same dedupe + validation as the Contacts UI.",
             "parameters": {
                 "type": "object",
                 "properties": {
@@ -1033,7 +1033,6 @@ FUNCTION_TOOL_SCHEMAS = [
                     "email": {"type": "string", "description": "Single email address (convenience for add, or the primary email for update)."},
                     "emails": {"type": "array", "items": {"type": "string"}, "description": "Full list of email addresses (for update; first is primary)."},
                     "phones": {"type": "array", "items": {"type": "string"}, "description": "Full list of phone numbers (for update)."},
-                    "address": {"type": "string", "description": "Postal/mailing address as a single human-readable string."},
                 },
                 "required": ["action"]
             }

src/tool_security.py

@@ -177,16 +177,13 @@ def owner_is_admin_or_single_user(owner: Optional[str]) -> bool:
     defense-in-depth for callers that bypass it (e.g. trusted loopback).
     """
     try:
-        from src.auth_helpers import _auth_disabled
-
-        if _auth_disabled():
-            return True
-
         from core.auth import AuthManager
 
         auth = AuthManager()
         if not auth.is_configured:
-            return False
+            from src.auth_helpers import _auth_disabled
+
+            return _auth_disabled()
         return bool(owner and auth.is_admin(owner))
     except Exception as exc:
         logger.warning("Unable to evaluate owner admin status: %s", exc)

src/youtube_handler.py

@@ -1,23 +1,278 @@
-"""Compatibility wrapper for the canonical services.youtube.youtube_handler module.
-
-Odysseus historically carried two independent copies of the YouTube handler —
-one here under ``src`` and one under ``services.youtube``. They drifted: the
-comment-fetch timeout fix landed only in the ``src`` copy, while ``app.py``
-calls ``services.youtube.init_youtube()`` at startup. Because the chat flow
-imported ``extract_transcript_async`` from ``src.youtube_handler`` (a different
-module object), the ``YOUTUBE_AVAILABLE`` / ``YouTubeTranscriptApi`` globals set
-by ``init_youtube`` never reached it and transcript extraction always reported
-"YouTube transcript API not available".
-
-Keep the old ``src.youtube_handler`` import path working, but make it resolve to
-the single source of truth so module state and behavior can't diverge again.
+"""
+YouTube handling — transcript extraction, comment fetching (yt-dlp),
+and context formatting for LLM injection. Used by chat_handler.py.
 """
 
-import importlib
+import asyncio
+import json
+import logging
+import shutil
 import sys
+import urllib.parse
+from pathlib import Path
+from typing import Dict, Any, Optional
 
-# Import the canonical module directly (services.youtube.youtube_handler)
-# without triggering the heavy services/__init__.py top-level imports.
-_youtube_handler = importlib.import_module("services.youtube.youtube_handler")
+logger = logging.getLogger(__name__)
 
-sys.modules[__name__] = _youtube_handler
+# ---------------------------------------------------------------------------
+# Constants
+# ---------------------------------------------------------------------------
+
+YOUTUBE_INSTRUCTION_PROMPT = """When the user shares a YouTube video, respond with a structured breakdown:
+
+1. **Summary** — Concise overview of the video's content and main thesis (2-4 sentences)
+2. **Key Points** — Bullet list of the most important topics, arguments, or moments
+3. **Notable Timestamps** — If timestamps are available from the transcript, highlight 3-5 interesting moments with their approximate timestamps (e.g. "03:45 — discusses X")
+4. **Audience Reception** — If comments are available, summarize what viewers think: general sentiment, top reactions, any debate or controversy
+
+Keep it conversational and concise. Do NOT web search for this video — use only the transcript and comments provided."""
+
+# ---------------------------------------------------------------------------
+# Init / helpers
+# ---------------------------------------------------------------------------
+
+# Will be set at startup by init_youtube()
+YouTubeTranscriptApi = None
+YOUTUBE_AVAILABLE = False
+
+
+def _find_ytdlp() -> str:
+    """Find the yt-dlp binary: venv bin first, then system PATH."""
+    venv_bin = Path(sys.executable).parent / "yt-dlp"
+    if venv_bin.exists():
+        return str(venv_bin)
+    found = shutil.which("yt-dlp")
+    return found or "yt-dlp"
+
+
+def init_youtube():
+    """Import and cache the YouTube transcript API."""
+    global YouTubeTranscriptApi, YOUTUBE_AVAILABLE
+    try:
+        from youtube_transcript_api import YouTubeTranscriptApi as _Api
+        YouTubeTranscriptApi = _Api
+        YOUTUBE_AVAILABLE = True
+        logger.info("YouTube transcript API available")
+    except ImportError as e:
+        logger.warning(f"youtube-transcript-api not installed: {e}")
+        YOUTUBE_AVAILABLE = False
+
+
+def is_youtube_url(url: str) -> bool:
+    if not isinstance(url, str):
+        return False
+    return "youtube.com" in url or "youtu.be" in url
+
+
+def extract_youtube_id(url: str) -> Optional[str]:
+    """Extract YouTube video ID from various URL formats."""
+    parsed = urllib.parse.urlparse(url)
+    if parsed.hostname in ("www.youtube.com", "youtube.com", "m.youtube.com"):
+        if parsed.path == "/watch":
+            params = urllib.parse.parse_qs(parsed.query)
+            if "v" in params:
+                return params["v"][0]
+        elif parsed.path.startswith("/embed/"):
+            return parsed.path.split("/")[-1]
+    elif parsed.hostname == "youtu.be":
+        return parsed.path[1:]
+    return None
+
+
+async def extract_transcript_async(
+    url: str, video_id: str, max_retries: int = 3
+) -> Dict[str, Any]:
+    """
+    Async YouTube transcript extraction with retries.
+
+    Args:
+        url: Full YouTube URL
+        video_id: Extracted video ID
+        max_retries: Number of attempts
+
+    Returns:
+        Dict with success/error/transcript keys
+    """
+    if not YOUTUBE_AVAILABLE or YouTubeTranscriptApi is None:
+        return {"success": False, "error": "YouTube transcript API not available", "transcript": None}
+
+    for attempt in range(max_retries):
+        try:
+            api = YouTubeTranscriptApi()
+            transcript = api.fetch(video_id)
+            transcript_list = list(transcript)
+
+            formatted = []
+            for snippet in transcript_list:
+                text = snippet.text.strip()
+                if not text:
+                    continue
+                start = snippet.start
+                formatted.append({
+                    "text": text,
+                    "start": start,
+                    "duration": snippet.duration,
+                    "timestamp": f"{int(start // 60):02d}:{int(start % 60):02d}",
+                })
+
+            full_text = " ".join(e["text"] for e in formatted)
+            max_len = 8000
+            if len(full_text) > max_len:
+                full_text = full_text[:max_len] + "... [transcript truncated]"
+
+            return {
+                "success": True,
+                "transcript": full_text,
+                "video_id": video_id,
+                "language": "en",
+                "is_generated": False,
+                "segments": formatted,
+            }
+        except Exception as e:
+            logger.warning(f"Transcript attempt {attempt + 1} failed: {e}")
+            if attempt < max_retries - 1:
+                await asyncio.sleep(1 * (attempt + 1))
+
+    return {"success": False, "error": f"Failed after {max_retries} attempts", "transcript": None}
+
+
+def format_transcript_for_context(
+    transcript_data: Dict[str, Any], url: str,
+    title: str = "", channel: str = ""
+) -> str:
+    """Format transcript data for inclusion in LLM context."""
+    if not transcript_data.get("success"):
+        header = ""
+        if title:
+            header = f" \"{title}\""
+            if channel:
+                header += f" by {channel}"
+        return f"\n[YouTube Video{header}: Transcript unavailable ({transcript_data.get('error', 'Unknown error')}). Use the comments below if available, do NOT web search for this video.]"
+
+    transcript = transcript_data.get("transcript", "")
+    video_id = transcript_data.get("video_id", "")
+    language = transcript_data.get("language", "unknown")
+    is_generated = transcript_data.get("is_generated", False)
+    segments = transcript_data.get("segments", [])
+
+    ctx = "\n[YOUTUBE VIDEO TRANSCRIPT]\n"
+    if title:
+        ctx += f"Title: {title}\n"
+    if channel:
+        ctx += f"Channel: {channel}\n"
+    ctx += f"Video ID: {video_id}\n"
+    ctx += f"Language: {language}\n"
+    ctx += f"Source: {'Auto-generated' if is_generated else 'Manual'}\n"
+    ctx += f"URL: {url}\n\n"
+    # Include timestamped segments for the LLM to reference
+    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:
+            ctx = ctx[:ctx.index("Timestamped Transcript:\n")]
+            ctx += "Transcript:\n"
+            ctx += transcript
+    else:
+        ctx += "Transcript:\n"
+        ctx += transcript
+    ctx += "\n[END TRANSCRIPT]\n"
+    return ctx
+
+
+async def fetch_youtube_comments(
+    video_id: str, max_comments: int = 25, timeout: int = 30
+) -> Dict[str, Any]:
+    """Fetch top comments for a YouTube video using yt-dlp.
+
+    Returns dict with 'success', 'comments' list, 'error'.
+    """
+    try:
+        cmd = [
+            _find_ytdlp(),
+            "--skip-download",
+            "--write-comments",
+            "--extractor-args", f"youtube:max_comments={max_comments},all,100,0",
+            "--dump-json",
+            "--js-runtimes", "node",
+            "--remote-components", "ejs:github",
+            f"https://www.youtube.com/watch?v={video_id}",
+        ]
+
+        proc = await asyncio.create_subprocess_exec(
+            *cmd,
+            stdout=asyncio.subprocess.PIPE,
+            stderr=asyncio.subprocess.PIPE,
+        )
+        # 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
+
+        if proc.returncode != 0:
+            return {"success": False, "error": f"yt-dlp failed: {stderr.decode()[:200]}", "comments": []}
+
+        data = json.loads(stdout.decode())
+        title = data.get("title", "")
+        channel = data.get("channel", "") or data.get("uploader", "")
+        raw_comments = data.get("comments", [])
+
+        comments = []
+        for c in raw_comments[:max_comments]:
+            text = (c.get("text") or "").strip()
+            if not text:
+                continue
+            comments.append({
+                "author": c.get("author", "Unknown"),
+                "text": text,
+                "likes": c.get("like_count", 0),
+            })
+
+        # Sort by likes descending — most popular comments first
+        comments.sort(key=lambda x: x.get("likes", 0), reverse=True)
+
+        return {"success": True, "comments": comments, "count": len(comments),
+                "title": title, "channel": channel}
+
+    except asyncio.TimeoutError:
+        logger.warning(f"Comment fetch timed out for {video_id}")
+        return {"success": False, "error": "Comment fetch timed out", "comments": []}
+    except FileNotFoundError:
+        logger.warning("yt-dlp not installed — cannot fetch comments")
+        return {"success": False, "error": "yt-dlp not installed", "comments": []}
+    except Exception as e:
+        logger.warning(f"Failed to fetch comments for {video_id}: {e}")
+        return {"success": False, "error": str(e), "comments": []}
+
+
+def format_comments_for_context(comments_data: Dict[str, Any], url: str) -> str:
+    """Format YouTube comments for inclusion in LLM context."""
+    if not comments_data.get("success") or not comments_data.get("comments"):
+        return ""
+
+    comments = comments_data["comments"]
+    ctx = f"\n[YOUTUBE VIDEO COMMENTS — Top {len(comments)} by popularity]\n"
+    ctx += f"URL: {url}\n\n"
+
+    for i, c in enumerate(comments, 1):
+        likes = c.get("likes", 0)
+        likes_str = f" [{likes} likes]" if likes else ""
+        ctx += f"{i}. @{c['author']}{likes_str}: {c['text']}\n\n"
+
+    if len(ctx) > 4000:
+        ctx = ctx[:4000] + "\n[Comments truncated]\n"
+
+    ctx += "[END COMMENTS]\n"
+    return ctx

start-macos.sh

@@ -130,12 +130,11 @@ fi
 # 3. Python environment + dependencies (kept inside the repo, in venv/).
 #    Named `venv` to match the manual steps and build-macos-app.sh, so the
 #    clickable .app reuses this same environment.
-VENV_PY="./venv/bin/python3"
-if [ ! -x "$VENV_PY" ] || ! "$VENV_PY" -m pip --version >/dev/null 2>&1; then
-    [ -d venv ] && { echo "▶ Existing venv is incomplete (no working pip) — rebuilding…"; rm -rf venv; }
+if [ ! -d venv ]; then
     echo "▶ Creating Python environment…"
     "$PY" -m venv venv
 fi
+VENV_PY="./venv/bin/python3"
 REQ_HASH="$(md5 -q requirements.txt 2>/dev/null || md5sum requirements.txt | cut -d' ' -f1)"
 REQ_HASH_FILE="venv/.requirements_hash"
 if [ ! -f "$REQ_HASH_FILE" ] || [ "$REQ_HASH" != "$(cat "$REQ_HASH_FILE" 2>/dev/null)" ]; then