chore(deps): bump the python group across 1 directory with 4 updates

Updates the requirements on [httpcore](https://github.com/encode/httpcore), [pydantic-settings](https://github.com/pydantic/pydantic-settings), [mcp](https://github.com/modelcontextprotocol/python-sdk) and [markitdown](https://github.com/microsoft/markitdown) to permit the latest version.

Updates `httpcore` to 1.0.9
- [Release notes](https://github.com/encode/httpcore/releases)
- [Changelog](https://github.com/encode/httpcore/blob/master/CHANGELOG.md)
- [Commits](https://github.com/encode/httpcore/compare/1.0.0...1.0.9)

Updates `pydantic-settings` to 2.14.2
- [Release notes](https://github.com/pydantic/pydantic-settings/releases)
- [Commits](https://github.com/pydantic/pydantic-settings/compare/v2.14.1...v2.14.2)

Updates `mcp` to 2.0.0
- [Release notes](https://github.com/modelcontextprotocol/python-sdk/releases)
- [Changelog](https://github.com/modelcontextprotocol/python-sdk/blob/main/RELEASE.md)
- [Commits](https://github.com/modelcontextprotocol/python-sdk/compare/v0.2.0...v2.0.0)

Updates `markitdown` from 0.1.6 to 0.1.7
- [Release notes](https://github.com/microsoft/markitdown/releases)
- [Commits](https://github.com/microsoft/markitdown/compare/v0.1.6...v0.1.7)

---
updated-dependencies:
- dependency-name: httpcore
  dependency-version: 1.0.9
  dependency-type: direct:production
  dependency-group: python
- dependency-name: pydantic-settings
  dependency-version: 2.14.2
  dependency-type: direct:production
  dependency-group: python
- dependency-name: mcp
  dependency-version: 2.0.0
  dependency-type: direct:production
  dependency-group: python
- dependency-name: markitdown
  dependency-version: 0.1.7
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: python
...

Signed-off-by: dependabot[bot] <support@github.com>

.dockerignore

@@ -9,6 +9,17 @@ __pycache__/
 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~
+.secrets.env.swp
+.secrets.env.swo
+**/#secrets.env#
+!secrets.env.example
 /data/
 /logs/
 .git/
@@ -18,6 +29,8 @@ build/
 .vscode/
 .idea/
 dev-docs/
+docs/
+*.md
 *.db
 *.sqlite
 *.sqlite3

.env.example

@@ -16,6 +16,10 @@ LLM_HOST=localhost
 # when started with OLLAMA_HOST=0.0.0.0:11434.
 # OLLAMA_BASE_URL=http://host.docker.internal:11434/v1
 
+# Optional LM Studio URL. In Docker, host LM Studio is reachable here
+# when LM Studio is set to serve on all interfaces (0.0.0.0).
+# LM_STUDIO_URL=http://host.docker.internal:1234
+
 # OpenAI API key (only needed if using OpenAI models).
 # Do not commit real keys. Keep this commented until needed.
 # OPENAI_API_KEY=your_openai_api_key_here
@@ -23,6 +27,16 @@ LLM_HOST=localhost
 # Research service LLM endpoint
 # RESEARCH_LLM_ENDPOINT=http://localhost:8000/v1/chat/completions
 
+# Extra CA bundle for LLM providers whose TLS chain isn't in the default
+# trust store. Layered ON TOP of the system / certifi bundle — verification
+# stays on for every host, the trust set just gets larger. Useful for:
+#   - GigaChat / Sber (Russian Trusted Root CA): without this the endpoint
+#     shows offline with CERTIFICATE_VERIFY_FAILED — self-signed certificate
+#     in certificate chain.
+#   - On-premise / corporate LLM gateways with an internal CA.
+# Point at a PEM file containing the missing root(s).
+# LLM_CA_BUNDLE=/etc/odysseus/ca/extra-roots.pem
+
 # ============================================================
 # Search & Web
 # ============================================================
@@ -42,6 +56,13 @@ SEARXNG_INSTANCE=http://localhost:8080
 # SQLite database path (default: sqlite:///./data/app.db)
 # DATABASE_URL=sqlite:///./data/app.db
 
+# ============================================================
+# Data directory
+# ============================================================
+# Move everything that lives under data/ - settings, sessions, database, auth,
+# cache, uploads, etc. - to another path:
+# ODYSSEUS_DATA_DIR=C:\path\to\dir
+
 # ============================================================
 # Auth & Security
 # ============================================================
@@ -49,10 +70,20 @@ SEARXNG_INSTANCE=http://localhost:8080
 # Enable authentication (default: true)
 # AUTH_ENABLED=true
 
+# Host bind address and port for the Odysseus web UI in Docker Compose.
+# Keep APP_BIND on loopback unless you intentionally want LAN/reverse-proxy access.
+# APP_BIND=127.0.0.1
+# Change this if another local service already uses 7000 (macOS AirPlay often does).
+# APP_PORT=7000
+
 # Development-only auth bypass for loopback requests.
 # Keep false for Docker, LAN, reverse proxy, and any shared deployment.
 # LOCALHOST_BYPASS=false
 
+# Mark session cookies Secure. Set true when Odysseus is served through HTTPS
+# by a trusted reverse proxy or private access gateway.
+# SECURE_COOKIES=true
+
 # Optional: pre-seed the first admin password during setup.
 # Do not commit a real password.
 # ODYSSEUS_ADMIN_PASSWORD=change_me_before_first_boot
@@ -88,6 +119,9 @@ SEARXNG_INSTANCE=http://localhost:8080
 # Default: http://{LLM_HOST}:11434/v1/embeddings (ollama)
 # EMBEDDING_URL=http://localhost:11434/v1/embeddings
 
+# Embedding API key (if there's one)
+# EMBEDDING_API_KEY=embedding_api_key_here
+
 # Embedding model name (must be available at the endpoint above)
 # EMBEDDING_MODEL=all-minilm:l6-v2
 
@@ -96,6 +130,27 @@ SEARXNG_INSTANCE=http://localhost:8080
 # FASTEMBED_MODEL=sentence-transformers/all-MiniLM-L6-v2
 # FASTEMBED_CACHE_PATH=  # defaults to ~/.cache/fastembed
 
+# ============================================================
+# Google OAuth2 (Google Workspace / .edu email accounts)
+# ============================================================
+# Required to use the "Connect with Google" OAuth flow in email account setup.
+# Create credentials at: console.cloud.google.com → APIs & Services → Credentials
+#   1. Enable the Gmail API for your project.
+#   2. Configure the OAuth consent screen (User Type: Internal for Workspace orgs).
+#      Add scopes: https://mail.google.com/ and email.
+#   3. Create an OAuth 2.0 Client ID (type: Web application).
+#      Add your redirect URI: http://localhost:7000/api/email/oauth/google/callback
+#      (replace host/port for hosted installs).
+#   4. Copy the Client ID and Client Secret below.
+#
+# GOOGLE_OAUTH_CLIENT_ID=your-client-id.apps.googleusercontent.com
+# GOOGLE_OAUTH_CLIENT_SECRET=replace-with-client-secret
+#
+# Set this explicitly for HTTPS, reverse-proxy, or hosted deployments. The
+# value must exactly match an authorized redirect URI in the Google client.
+# Local HTTP setups may use the callback URL inferred by the application.
+# GOOGLE_OAUTH_REDIRECT_URI=https://your-domain.com/api/email/oauth/google/callback
+
 # ============================================================
 # Misc
 # ============================================================
@@ -119,3 +174,68 @@ SEARXNG_INSTANCE=http://localhost:8080
 # Empty/local/localhost runs scripts on the app host. Set to an SSH host alias
 # if you intentionally want scheduled scripts to run remotely.
 # ODYSSEUS_SCRIPT_HOST=localhost
+
+# Chat / agent attachment size cap in bytes (default: 10 MB).
+# Raise this for local installs that need larger PDFs or text documents.
+# Example: 52428800 = 50 MB.
+# ODYSSEUS_CHAT_UPLOAD_MAX_BYTES=10485760
+
+# Other per-feature upload size caps in bytes. All are validated and optional;
+# defaults shown. An invalid value (non-integer or < 1) fails fast at startup.
+# ODYSSEUS_GALLERY_UPLOAD_MAX_BYTES=104857600            # gallery image upload (100 MB)
+# ODYSSEUS_GALLERY_TRANSFORM_UPLOAD_MAX_BYTES=26214400   # gallery transform input (25 MB)
+# ODYSSEUS_MEMORY_IMPORT_MAX_BYTES=10485760              # memory import file (10 MB)
+# ODYSSEUS_PERSONAL_UPLOAD_MAX_BYTES=26214400            # personal document upload (25 MB)
+# ODYSSEUS_EMAIL_COMPOSE_UPLOAD_MAX_BYTES=26214400       # email compose attachment (25 MB)
+# ODYSSEUS_STT_MAX_AUDIO_BYTES=26214400                  # speech-to-text audio (25 MB)
+# ODYSSEUS_ICS_MAX_BYTES=10485760                        # calendar .ics import (10 MB)
+# ODYSSEUS_TTS_CACHE_MAX_BYTES=524288000                 # TTS cache (500 MB)
+
+# ============================================================
+# Host Docker access (explicit opt-in)
+# ============================================================
+# Default Docker Compose does not mount /var/run/docker.sock. Existing
+# Ollama, vLLM, and other OpenAI-compatible endpoints remain usable without it.
+#
+# Enable this only for intentional Cookbook/local Docker-daemon management.
+# Raw socket access is high-trust and can grant broad control over the host
+# Docker daemon. Set DOCKER_GID to the host docker group's numeric GID.
+# Put these values in .env, or export them before running docker compose.
+# COMPOSE_FILE=docker-compose.yml:docker/host-docker.yml
+# DOCKER_GID=963
+# docker/host-docker.yml sets this inside the container. Keep it paired
+# with the socket overlay; setting it alone is not sufficient.
+# ODYSSEUS_ENABLE_HOST_DOCKER=true
+#
+# Host Docker access can be combined with one GPU overlay:
+# COMPOSE_FILE=docker-compose.yml:docker/gpu.nvidia.yml:docker/host-docker.yml
+# COMPOSE_FILE=docker-compose.yml:docker/gpu.amd.yml:docker/host-docker.yml
+
+# ============================================================
+# GPU support (Docker Compose)
+# ============================================================
+# Pass the host GPU into the odysseus container. Default (unset) = CPU.
+# COMPOSE_FILE is a native `docker compose` feature: a colon-separated
+# list of files merged left-to-right. Pick ONE GPU line below, or leave
+# all commented for CPU.
+#
+# NVIDIA (requires nvidia-container-toolkit + `nvidia-ctk runtime
+# configure --runtime=docker` on the host):
+# COMPOSE_FILE=docker-compose.yml:docker/gpu.nvidia.yml
+# COMPOSE_FILE=docker-compose.yml;docker/gpu.nvidia.yml    #(Windows)
+#
+# AMD ROCm (requires ROCm drivers on the host and the GID of the render group):
+# COMPOSE_FILE=docker-compose.yml:docker/gpu.amd.yml
+# Find the render GID with: getent group render | cut -d: -f3
+# RENDER_GID=989
+#
+# 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

.gitattributes

@@ -1,2 +1,27 @@
-*.sh text eol=lf
+# Normalize line endings so a Windows checkout (git core.autocrlf=true) can't
+# corrupt shell-script shebangs. A CRLF `#!/bin/sh\r` makes the kernel look for
+# an interpreter literally named "/bin/sh\r", producing the Docker startup error
+# "exec /usr/local/bin/entrypoint.sh: no such file or directory" (issues #150, #77).
+* text=auto
+
+# Shell scripts must stay LF on every platform (run by sh/bash, incl. in Docker).
+*.sh   text eol=lf
+*.bash text eol=lf
+entrypoint.sh text eol=lf
 docker/entrypoint.sh text eol=lf
+
+# Windows-native scripts stay CRLF.
+*.ps1 text eol=crlf
+*.cmd text eol=crlf
+*.bat text eol=crlf
+
+# Binary assets — never normalize.
+*.png  binary
+*.jpg  binary
+*.jpeg binary
+*.gif  binary
+*.webp binary
+*.pdf  binary
+*.ico  binary
+*.woff binary
+*.woff2 binary

.github/CODEOWNERS

@@ -0,0 +1,9 @@
+# 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/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,114 @@
+name: Bug Report
+description: Report a reproducible bug in Odysseus.
+labels: ["bug"]
+
+body:
+  - type: markdown
+    attributes:
+      value: |
+        **Before submitting:** search [open issues](https://github.com/odysseus-dev/odysseus/issues)
+        and [discussions](https://github.com/odysseus-dev/odysseus/discussions) first.
+        Duplicate reports slow things down.
+
+        For security vulnerabilities, **do not open a public issue** —
+        use [GitHub Security Advisories](https://github.com/odysseus-dev/odysseus/security/advisories/new)
+        and read [SECURITY.md](https://github.com/odysseus-dev/odysseus/blob/main/SECURITY.md) first.
+
+  - type: checkboxes
+    id: prerequisites
+    attributes:
+      label: Prerequisites
+      options:
+        - label: I searched [open issues](https://github.com/odysseus-dev/odysseus/issues?q=is%3Aissue+is%3Aopen) and [discussions](https://github.com/odysseus-dev/odysseus/discussions) and did not find an existing report of this bug.
+          required: true
+        - label: This is **not** a security vulnerability. (Vulnerabilities go to [GitHub Security Advisories](https://github.com/odysseus-dev/odysseus/security/advisories/new) — see [SECURITY.md](https://github.com/odysseus-dev/odysseus/blob/main/SECURITY.md).)
+          required: true
+        - label: I am running the latest code from the `dev` branch (the default branch you get on clone, where fixes land first) and the bug still reproduces there. Please `git pull` the latest `dev` before filing.
+          required: true
+
+  - type: dropdown
+    id: install-method
+    attributes:
+      label: Install Method
+      options:
+        - "-- Please Select --"
+        - Docker (docker compose up)
+        - Manual Python install (pip / venv)
+        - Windows native (launch-windows.ps1)
+        - macOS app (build-macos-app.sh / start-macos.sh)
+        - Other (describe in the reproduction steps below)
+    validations:
+      required: true
+
+  - type: dropdown
+    id: os
+    attributes:
+      label: Operating System
+      options:
+        - "-- Please Select --"
+        - Linux
+        - macOS
+        - Windows
+        - Other
+    validations:
+      required: true
+
+  - type: textarea
+    id: steps
+    attributes:
+      label: Steps to Reproduce
+      description: Exact steps that reliably trigger the bug. The more specific, the faster this gets fixed.
+      placeholder: |
+        1. Go to ...
+        2. Click / type ...
+        3. Observe ...
+    validations:
+      required: true
+
+  - type: textarea
+    id: expected
+    attributes:
+      label: Expected Behaviour
+      description: What should have happened?
+    validations:
+      required: true
+
+  - type: textarea
+    id: actual
+    attributes:
+      label: Actual Behaviour
+      description: What actually happened? Include the full error message if there is one.
+    validations:
+      required: true
+
+  - type: textarea
+    id: logs
+    attributes:
+      label: Logs / Screenshots
+      description: Paste relevant terminal output or attach screenshots. Remove API keys, passwords, and personal data before pasting.
+      render: text
+
+  - type: input
+    id: model-backend
+    attributes:
+      label: Model / Backend (if relevant)
+      description: "e.g. Ollama + llama3.2:latest, vLLM + mistral-7b, OpenAI API, Anthropic API"
+      placeholder: "Ollama + llama3.2:latest"
+
+  - type: dropdown
+    id: willing_to_fix
+    attributes:
+      label: Are you willing to submit a fix?
+      options:
+        - "-- Please Select --"
+        - "Yes — I can open a PR"
+        - "Partially — I can help but need guidance"
+        - "No — I am only filing the report"
+    validations:
+      required: true
+
+  - type: textarea
+    id: additional-info
+    attributes:
+      label: Additional Information
+      description: Anything else that might help — browser console errors, related issues, things you already tried, or environment quirks.

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,13 @@
+blank_issues_enabled: false
+contact_links:
+  - name: Question / Need Help
+    url: https://github.com/odysseus-dev/odysseus/discussions/categories/q-a
+    about: Ask how-to questions, setup help, and model configuration questions here. Issues are for confirmed bugs and concrete proposals only.
+
+  - name: Idea or Suggestion
+    url: https://github.com/odysseus-dev/odysseus/discussions/categories/ideas
+    about: Discuss ideas and gauge interest before opening a formal feature request. If there is already a discussion, link it in your feature request.
+
+  - name: Security Vulnerability
+    url: https://github.com/odysseus-dev/odysseus/security/advisories/new
+    about: Report vulnerabilities privately via GitHub Security Advisories — never as a public issue. Read SECURITY.md before reporting.

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,92 @@
+name: Feature Request
+description: Propose a new feature or a concrete improvement to Odysseus.
+labels: ["enhancement"]
+
+body:
+  - type: markdown
+    attributes:
+      value: |
+        **Before submitting:** search [open issues](https://github.com/odysseus-dev/odysseus/issues)
+        and [discussions](https://github.com/odysseus-dev/odysseus/discussions) first.
+        Feature requests that duplicate [ROADMAP.md](https://github.com/odysseus-dev/odysseus/blob/main/ROADMAP.md)
+        or an existing open issue will be closed as duplicates.
+
+        If your idea needs community input before it becomes a concrete proposal,
+        start a [discussion](https://github.com/odysseus-dev/odysseus/discussions/categories/ideas) instead.
+
+  - type: checkboxes
+    id: prerequisites
+    attributes:
+      label: Prerequisites
+      options:
+        - label: I searched [open issues](https://github.com/odysseus-dev/odysseus/issues?q=is%3Aissue+is%3Aopen) and this has not already been proposed.
+          required: true
+        - label: I searched [discussions](https://github.com/odysseus-dev/odysseus/discussions) and this is not already being debated there.
+          required: true
+        - label: This is a concrete, actionable proposal — not a vague "it would be nice if..." request.
+          required: true
+
+  - type: dropdown
+    id: area
+    attributes:
+      label: Area
+      description: Which part of the application does this affect?
+      options:
+        - "-- Please Select --"
+        - Chat / Agent
+        - Email
+        - Calendar
+        - Documents / RAG
+        - Memory
+        - Cookbook / Local Models / GPU
+        - Search
+        - Notes / Editor
+        - Auth / Security
+        - Docker / Deployment
+        - UI / Frontend
+        - API / Backend
+        - MCP
+        - Testing / CI
+        - Other
+    validations:
+      required: true
+
+  - type: textarea
+    id: problem
+    attributes:
+      label: Problem or Motivation
+      description: What problem does this solve, or what use case does it enable? Be specific — "it would be better" is not enough.
+    validations:
+      required: true
+
+  - type: textarea
+    id: solution
+    attributes:
+      label: Proposed Solution
+      description: Describe the behaviour or change you want to see. Include API shape, UI sketch, or code snippets if that helps make it concrete.
+    validations:
+      required: true
+
+  - type: textarea
+    id: alternatives
+    attributes:
+      label: Alternatives Considered
+      description: What other approaches did you consider and why did you rule them out? If there is an existing workaround, describe it.
+
+  - type: textarea
+    id: prior-art
+    attributes:
+      label: Prior Art / Related Issues
+      description: Link any related issues, discussions, or external references that informed this proposal.
+
+  - type: dropdown
+    id: willing_to_implement
+    attributes:
+      label: Are you willing to implement this?
+      options:
+        - "-- Please Select --"
+        - "Yes — I can open a PR"
+        - "Partially — I can help but need guidance"
+        - "No — I am only filing the request"
+    validations:
+      required: true

.github/dependabot.yml

@@ -0,0 +1,48 @@
+# 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

@@ -0,0 +1,123 @@
+# 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/pull_request_template.md

@@ -0,0 +1,57 @@
+## Summary
+
+<!-- One paragraph: what changed and why. "Fixed bug" and "Added feature" are not summaries. -->
+
+## Target branch
+
+- [ ] This PR targets **`dev`**, not `main`. All PRs land in `dev`; `main` is curated by the maintainer at each release. If your PR is on `main` by accident, click "Edit" on this PR and change the base.
+
+## Linked Issue
+
+<!-- Every PR should be linked to an issue.
+     Use one of:  Fixes #NNN  |  Part of #NNN  |  Closes #NNN  -->
+
+Fixes #
+
+## Type of Change
+
+- [ ] Bug fix (non-breaking — fixes a confirmed issue)
+- [ ] New feature (non-breaking — adds new behaviour)
+- [ ] Breaking change (changes or removes existing behaviour)
+- [ ] Refactor / cleanup (behaviour unchanged)
+- [ ] Documentation only
+- [ ] CI / tooling / configuration
+
+## Checklist
+
+- [ ] I searched [open issues](https://github.com/odysseus-dev/odysseus/issues) and [open PRs](https://github.com/odysseus-dev/odysseus/pulls) — this is not a duplicate.
+- [ ] This PR targets `dev`
+- [ ] My changes are limited to the scope described above — no unrelated refactors or whitespace changes mixed in.
+- [ ] I actually ran the app (`docker compose up` or `uvicorn app:app`) and verified the change works end-to-end. Type-checks and unit tests are not enough.
+
+## How to Test
+
+<!-- Step-by-step instructions a reviewer can follow to verify this works.
+     Do not leave this empty — a PR without test steps will be sent back. -->
+
+1.
+2.
+3.
+
+## Visual / UI changes — REQUIRED if you touched anything that renders
+
+**Anything that changes what the UI looks like — buttons, icons, padding, colors, fonts, spacing, layout, CSS, HTML, SVG, or any `static/js/` module that draws to the DOM — needs all of the following. PRs that change rendering without these WILL be closed.**
+
+- [ ] **Screenshot or short clip** of the change in the running app, attached below. Mobile screenshot too if the change affects mobile.
+- [ ] **Style match**: the change uses Odysseus's existing visual language. Specifically:
+  - Reuse existing CSS variables (`--red`, `--fg`, `--bg`, `--card`, `--border`, etc.) — do not introduce new color values, font sizes, or spacing units.
+  - Reuse existing button/input/card/border classes. Don't invent parallel styling.
+  - **No Unicode emoji in UI or code.** Use inline SVG (matching the monochrome icon style already in `static/index.html`) or plain text.
+  - Monospaced font (`Fira Code`) for primary UI text. Don't override.
+  - Dark theme is the default; any light-mode work must be wired through the existing theme system, not hard-coded.
+- [ ] **No new component patterns.** If a similar widget already exists in the app, extend it instead of writing a parallel one.
+- [ ] **I am not an LLM agent submitting a bulk PR.** If you are, please open an issue describing the problem first — bulk auto-generated PRs that don't match the project's visual style are closed on sight, even when the underlying fix is correct.
+
+### Screenshots / clips
+
+<!-- Drag and drop images or a screen recording here. Required for any UI/visual change. -->

.github/scripts/check-issue-description.js

@@ -0,0 +1,203 @@
+// @ts-check
+'use strict';
+
+/** @param {{ github: import('@octokit/rest').Octokit, context: import('@actions/github').context, core: import('@actions/core') }} */
+module.exports = async ({ github, context, core }) => {
+  const issue  = context.payload.issue;
+  const body   = (issue.body || '').trim();
+  const labels = issue.labels.map(l => l.name);
+  const owner  = context.repo.owner;
+  const repo   = context.repo.repo;
+
+  const isBug     = labels.includes('bug');
+  const isFeature = labels.includes('enhancement');
+
+  // Extract a Section's text, stripping HTML comments. Matches any heading
+  // depth (#, ##, ###, …) so a manually-written body isn't penalised for
+  // using a different number of hashes than the issue form generates.
+  function section(heading) {
+    const re = new RegExp(`#+\\s+${heading}\\s*([\\s\\S]*?)(?=\\n#+\\s+|$)`, 'i');
+    const m  = body.match(re);
+    return m ? m[1].replace(/<!--[\s\S]*?-->/g, '').trim() : '';
+  }
+
+  const failures = [];
+
+  // ── Common: body must exist ───────────────────────────────────────────────
+  if (body.length < 50) {
+    failures.push(
+      '**Description** — body is empty or too short. ' +
+      'Please open the issue using one of the provided templates.',
+    );
+  }
+
+  // An issue is one or the other — never both. Resolve to a single type so the
+  // validation can't run two conflicting blocks at once.
+  const type = isBug && isFeature ? 'conflict' : isBug ? 'bug' : isFeature ? 'feature' : 'untyped';
+
+  switch (type) {
+    case 'conflict':
+      failures.push('**Labels** — an issue cannot be both `bug` and `enhancement`. Remove one label.');
+      break;
+
+    case 'bug': {
+      if (!section('Install Method')) {
+        failures.push('**Install Method** — select how you installed Odysseus');
+      }
+
+      if (!section('Operating System')) {
+        failures.push('**Operating System** — select your OS');
+      }
+
+      const stepsText = section('Steps to Reproduce');
+      if (!stepsText || !/\d+\.|[-*]/.test(stepsText)) {
+        failures.push('**Steps to Reproduce** — must include at least one numbered or bulleted step');
+      }
+
+      if (section('Expected Behaviour').length < 10) {
+        failures.push('**Expected Behaviour** — section is empty or too short');
+      }
+
+      if (section('Actual Behaviour').length < 10) {
+        failures.push('**Actual Behaviour** — section is empty or too short');
+      }
+      break;
+    }
+
+    case 'feature':
+      if (!section('Area')) {
+        failures.push('**Area** — select which part of the application this affects');
+      }
+
+      if (section('Problem or Motivation').length < 20) {
+        failures.push(
+          '**Problem or Motivation** — section is empty or too short ' +
+          '(explain the concrete problem this solves)',
+        );
+      }
+
+      if (section('Proposed Solution').length < 20) {
+        failures.push(
+          '**Proposed Solution** — section is empty or too short ' +
+          '(describe the change you want to see)',
+        );
+      }
+
+      if (!section('Are you willing to implement this\\?')) {
+        failures.push('**Are you willing to implement this?** — select an option');
+      }
+      break;
+
+    // 'untyped' → only the common body-length check applies.
+  }
+
+  // ── Unfilled dropdowns ────────────────────────────────────────────────────
+  // #2068 added a "-- Please Select --" default to every template dropdown, so
+  // a contributor who never opens the dropdown submits with that literal string
+  // as the section value. The per-section checks above only verify presence, so
+  // a placeholder value passes. Scan every section and flag the ones still
+  // showing the placeholder, as a single comma-separated line item.
+  const PLACEHOLDER = '-- Please Select --';
+  const headingRe = /^#+\s+(.+?)\s*$/gm;
+  const headings = [];
+  let headingMatch;
+  while ((headingMatch = headingRe.exec(body)) !== null) {
+    headings.push({
+      name: headingMatch[1].trim(),
+      headStart: headingMatch.index,
+      contentStart: headingMatch.index + headingMatch[0].length,
+    });
+  }
+  const unfilled = [];
+  for (let i = 0; i < headings.length; i++) {
+    const end = i + 1 < headings.length ? headings[i + 1].headStart : body.length;
+    if (body.slice(headings[i].contentStart, end).includes(PLACEHOLDER)) {
+      unfilled.push(headings[i].name);
+    }
+  }
+  if (unfilled.length > 0) {
+    failures.push(
+      `**Unfilled dropdowns** — please choose a value; these sections still show ` +
+      `the \`${PLACEHOLDER}\` placeholder: ${unfilled.join(', ')}.`,
+    );
+  }
+
+  // ── Labels ────────────────────────────────────────────────────────────────
+  // These labels are expected to already exist in the repo — managing the
+  // repo's label set is the maintainer's job, not this workflow's. We check a
+  // label exists before applying it (issues.addLabels would otherwise silently
+  // create a missing label) and fail soft — warn and skip — if it's absent.
+  async function labelExists(name) {
+    try {
+      await github.rest.issues.getLabel({ owner, repo, name });
+      return true;
+    } catch (e) {
+      if (e.status === 404) return false;
+      throw e;
+    }
+  }
+
+  async function addLabel(name) {
+    if (await labelExists(name)) {
+      await github.rest.issues.addLabels({ owner, repo, issue_number: issue.number, labels: [name] });
+    } else {
+      core.warning(`Label "${name}" does not exist in the repo — skipping. Create it once to enable labelling.`);
+    }
+  }
+
+  async function dropLabel(name) {
+    try {
+      await github.rest.issues.removeLabel({ owner, repo, issue_number: issue.number, name });
+    } catch (e) {
+      if (e.status !== 404 && e.status !== 410) throw e;
+    }
+  }
+
+  const LABEL_BAD  = 'needs more info';
+  const LABEL_GOOD = 'ready for review';
+
+  // Closed issues are no longer awaiting review.
+  // This also prevents later edits to closed issues from restoring the label.
+  if (issue.state === 'closed') {
+    await dropLabel(LABEL_GOOD);
+    return;
+  }
+
+  // ── Find existing bot comment to update in-place ──────────────────────────
+  const MARKER = '<!-- issue-description-check -->';
+  const { data: comments } = await github.rest.issues.listComments({
+    owner, repo, issue_number: issue.number,
+  });
+  const existing = comments.find(c => c.user.type === 'Bot' && c.body.includes(MARKER));
+
+  if (failures.length === 0) {
+    if (existing) {
+      await github.rest.issues.deleteComment({ owner, repo, comment_id: existing.id });
+    }
+
+    await dropLabel(LABEL_BAD);
+    await addLabel(LABEL_GOOD);
+
+  } else {
+    const list = failures.map(f => `- ${f}`).join('\n');
+    const commentBody = [
+      MARKER,
+      '⚠️ **Issue description is incomplete.** Please update the following sections:',
+      '',
+      list,
+      '',
+      '_This comment is deleted automatically once all sections are complete._',
+    ].join('\n');
+
+    if (existing) {
+      await github.rest.issues.updateComment({ owner, repo, comment_id: existing.id, body: commentBody });
+    } else {
+      await github.rest.issues.createComment({ owner, repo, issue_number: issue.number, body: commentBody });
+    }
+
+    await dropLabel(LABEL_GOOD);
+    await addLabel(LABEL_BAD);
+
+    core.setFailed(`Issue description has ${failures.length} issue(s) — see bot comment for details.`);
+  }
+};

.github/scripts/check-pr-description.js

@@ -0,0 +1,130 @@
+// @ts-check
+'use strict';
+
+/** @param {{ github: import('@octokit/rest').Octokit, context: import('@actions/github').context, core: import('@actions/core') }} */
+module.exports = async ({ github, context, core }) => {
+  const body   = context.payload.pull_request.body || '';
+  const prNum  = context.payload.pull_request.number;
+  const MARKER = '<!-- pr-description-check-bot -->';
+  const owner  = context.repo.owner;
+  const repo   = context.repo.repo;
+
+  // Strip HTML comments so placeholder text does not count as content.
+  function strip(text) {
+    return (text ?? '').replace(/<!--[\s\S]*?-->/g, '').trim();
+  }
+
+  // Extract the text content of a Section. Matches any heading depth (#, ##,
+  // ###, …) so the check doesn't break if the template's heading level changes.
+  function section(heading) {
+    const m = body.match(new RegExp(`#+\\s+${heading}[\\s\\S]*?(?=\\n#+\\s+|$)`, 'i'));
+    return strip(m?.[0].replace(new RegExp(`#+\\s+${heading}`, 'i'), '') ?? '');
+  }
+
+  const problems = [];
+
+  // 1. Summary must be filled in.
+  if (section('Summary').length < 20) {
+    problems.push('**Summary** is empty or too short — describe what changed and why.');
+  }
+
+  // 2. Linked Issue must reference a real issue. Accept a bare #NNN, a closing
+  //    keyword + #NNN, or a full issue URL (e.g. .../issues/123) — the strict
+  //    keyword-prefixed form previously false-flagged correctly-linked PRs.
+  const linkedSection = section('Linked Issue');
+  const hasIssueRef = /#\d+\b/.test(linkedSection) || /\/issues\/\d+/.test(linkedSection);
+  if (!linkedSection || !hasIssueRef) {
+    problems.push('**Linked Issue** — add a reference like `Fixes #NNN`, a bare `#NNN`, or a link to the issue.');
+  }
+
+  // 3. At least one Type of Change box must be checked.
+  const typeBlock = body.match(/##\s+Type of Change[\s\S]*?(?=\n##\s|$)/i)?.[0] ?? '';
+  if (!/- \[x\]/i.test(typeBlock)) {
+    problems.push('**Type of Change** — check at least one box.');
+  }
+
+  // 4. Duplicate-search checklist item must be checked.
+  if (!/- \[x\] I searched/i.test(body)) {
+    problems.push('**Checklist** — check the duplicate-search box to confirm you searched existing issues and PRs.');
+  }
+
+  // 5. How to Test must contain enough real detail for a reviewer to act on.
+  //    Any format is fine — numbered steps, prose, the commands you ran, or a
+  //    code block — so we only require non-trivial content, not a specific shape.
+  const howTo = section('How to Test');
+  if (howTo.length < 30) {
+    problems.push('**How to Test** — explain how a reviewer can verify this change. Numbered steps, the commands you ran, or a short code block all work — give a sentence or two of real detail (not just "tested locally").');
+  }
+
+  // ── Comment ──────────────────────────────────────────────────────────────
+  const comments = await github.paginate(github.rest.issues.listComments, {
+    owner, repo, issue_number: prNum, per_page: 100,
+  });
+  const existing = comments.find(c => (c.body ?? '').includes(MARKER));
+
+  if (problems.length === 0) {
+    if (existing) {
+      await github.rest.issues.deleteComment({ owner, repo, comment_id: existing.id });
+    }
+  } else {
+    const commentBody = [
+      MARKER,
+      '⚠️ **PR description — action needed**',
+      '',
+      'The following required sections are missing or incomplete. Please update the PR description to address them:',
+      '',
+      problems.map(p => `- ${p}`).join('\n'),
+      '',
+      '---',
+      '_This comment is deleted automatically once all sections are complete._',
+    ].join('\n');
+
+    if (existing) {
+      await github.rest.issues.updateComment({ owner, repo, comment_id: existing.id, body: commentBody });
+    } else {
+      await github.rest.issues.createComment({ owner, repo, issue_number: prNum, body: commentBody });
+    }
+  }
+
+  // ── Labels ────────────────────────────────────────────────────────────────
+  // These labels are expected to already exist in the repo — managing the
+  // repo's label set is the maintainer's job, not this workflow's. We check a
+  // label exists before applying it (issues.addLabels would otherwise silently
+  // create a missing label) and fail soft — warn and skip — if it's absent.
+  async function labelExists(name) {
+    try {
+      await github.rest.issues.getLabel({ owner, repo, name });
+      return true;
+    } catch (e) {
+      if (e.status === 404) return false;
+      throw e;
+    }
+  }
+
+  async function swapLabel(num, add, remove) {
+    if (await labelExists(add)) {
+      try {
+        await github.rest.issues.addLabels({ owner, repo, issue_number: num, labels: [add] });
+      } catch (e) {
+        // Fail soft on a token that can't write labels so a label permission
+        // problem never masks the actual description verdict.
+        if (e.status !== 403) throw e;
+        core.warning(`Could not add "${add}" — token lacks label write here; skipping.`);
+      }
+    } else {
+      core.warning(`Label "${add}" does not exist in the repo — skipping. Create it once to enable labelling.`);
+    }
+    try {
+      await github.rest.issues.removeLabel({ owner, repo, issue_number: num, name: remove });
+    } catch (e) {
+      if (e.status !== 404 && e.status !== 410 && e.status !== 403) throw e;
+    }
+  }
+
+  if (problems.length === 0) {
+    await swapLabel(prNum, 'ready for review', 'needs work');
+  } else {
+    await swapLabel(prNum, 'needs work', 'ready for review');
+    core.setFailed(`PR description has ${problems.length} issue(s) — see bot comment for details.`);
+  }
+};

.github/scripts/focused_test_guidance.py

@@ -0,0 +1,124 @@
+#!/usr/bin/env python3
+"""Report focused pytest guidance for changed paths under tests/."""
+
+from __future__ import annotations
+
+import argparse
+import os
+import shlex
+import subprocess
+import sys
+from collections.abc import Iterable
+from pathlib import PurePosixPath
+
+
+def parse_paths(raw_paths: bytes) -> list[str]:
+    """Decode the NUL-delimited output of ``git diff --name-only -z``."""
+    return [os.fsdecode(path) for path in raw_paths.split(b"\0") if path]
+
+
+def changed_paths_from_merge_base(base_sha: str, head_sha: str) -> list[str]:
+    """Return changed ``tests/`` paths using GitHub PR three-dot semantics.
+
+    GitHub PR changed files are based on the merge base and the PR head, not a
+    direct endpoint diff between the current base branch tip and the PR head.
+    Using the direct endpoint diff can include files changed only on the base
+    branch when the PR branch is stale.
+    """
+    merge_base = subprocess.check_output(
+        ["git", "merge-base", base_sha, head_sha],
+        stderr=subprocess.DEVNULL,
+    ).strip()
+    raw_paths = subprocess.check_output(
+        [
+            "git",
+            "diff",
+            "--name-only",
+            "--diff-filter=ACMRT",
+            "-z",
+            os.fsdecode(merge_base),
+            head_sha,
+            "--",
+            "tests/",
+        ],
+    )
+    return parse_paths(raw_paths)
+
+
+def select_test_paths(paths: Iterable[str]) -> list[str]:
+    """Return unique, repository-relative paths contained by tests/."""
+    selected: set[str] = set()
+    for raw_path in paths:
+        path = PurePosixPath(raw_path)
+        if path.is_absolute() or ".." in path.parts:
+            continue
+        parts = tuple(part for part in path.parts if part != ".")
+        if len(parts) >= 2 and parts[0] == "tests":
+            selected.add(PurePosixPath(*parts).as_posix())
+    return sorted(selected)
+
+
+def is_pytest_file(path: str) -> bool:
+    """Return whether a changed path follows this repository's pytest naming."""
+    name = PurePosixPath(path).name
+    return name.endswith(".py") and (
+        name.startswith("test_") or name.endswith("_test.py")
+    )
+
+
+def pytest_command(paths: Iterable[str]) -> str:
+    """Build a copyable pytest command for changed runnable test files."""
+    command = ["python3", "-m", "pytest", "-q", *paths]
+    return shlex.join(command)
+
+
+def format_report(paths: Iterable[str]) -> str:
+    """Format focused guidance for CI logs and the workflow summary."""
+    changed_paths = select_test_paths(paths)
+    runnable_paths = [path for path in changed_paths if is_pytest_file(path)]
+    lines = ["## Focused test guidance (report-only)", ""]
+    if not changed_paths:
+        lines.append("No changed paths under `tests/`.")
+    else:
+        lines.extend(["Changed paths under `tests/`:", ""])
+        lines.extend(f"- `{path}`" for path in changed_paths)
+    lines.extend(["", "Suggested focused validation:", ""])
+    if runnable_paths:
+        lines.append(f"```sh\n{pytest_command(runnable_paths)}\n```")
+    else:
+        lines.append("No directly runnable pytest files changed.")
+    lines.extend(
+        [
+            "",
+            "This guidance does not infer tests from source changes. "
+            "Existing blocking CI remains the source of truth.",
+        ]
+    )
+    return "\n".join(lines)
+
+
+def _parse_args(argv: list[str]) -> argparse.Namespace:
+    parser = argparse.ArgumentParser(
+        description="Report focused pytest guidance for changed tests/ paths.",
+    )
+    parser.add_argument("--base-sha", help="Pull request base commit SHA.")
+    parser.add_argument("--head-sha", help="Pull request head commit SHA.")
+    return parser.parse_args(argv)
+
+
+def main(argv: list[str] | None = None) -> int:
+    args = _parse_args(sys.argv[1:] if argv is None else argv)
+    if bool(args.base_sha) != bool(args.head_sha):
+        raise SystemExit("--base-sha and --head-sha must be provided together")
+
+    if args.base_sha and args.head_sha:
+        paths = changed_paths_from_merge_base(args.base_sha, args.head_sha)
+    else:
+        paths = parse_paths(sys.stdin.buffer.read())
+
+    print(format_report(paths))
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

.github/workflows/ci.yml

@@ -0,0 +1,148 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+
+# Least privilege: none of the jobs write to the repo.
+permissions:
+  contents: read
+
+# Cancel superseded runs on the same ref to save Actions minutes.
+concurrency:
+  group: ci-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  focused-test-guidance:
+    name: Focused test guidance (report-only)
+    if: github.event_name == 'pull_request'
+    runs-on: ubuntu-latest
+    continue-on-error: true
+    steps:
+      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+      - name: Report changed test paths
+        env:
+          BASE_SHA: ${{ github.event.pull_request.base.sha }}
+          HEAD_SHA: ${{ github.event.pull_request.head.sha }}
+        run: |
+          report_file="$RUNNER_TEMP/focused-test-guidance.md"
+          publish_report() {
+            cat "$report_file"
+            if [ -n "${GITHUB_STEP_SUMMARY:-}" ]; then
+              cat "$report_file" >> "$GITHUB_STEP_SUMMARY" || true
+            fi
+            return 0
+          }
+
+          report_unavailable() {
+            {
+              printf '%s\n\n' '## Focused test guidance unavailable (report-only)'
+              printf '%s\n\n' "$1"
+              printf '%s\n' 'Existing blocking CI remains the source of truth.'
+            } > "$report_file"
+            publish_report
+            exit 0
+          }
+
+          if [ -z "$BASE_SHA" ] || [ -z "$HEAD_SHA" ]; then
+            report_unavailable "Pull request base/head metadata is missing."
+          fi
+
+          if ! git cat-file -e "${BASE_SHA}^{commit}" 2>/dev/null; then
+            report_unavailable "The pull request base commit is unavailable locally."
+          fi
+
+          if ! git cat-file -e "${HEAD_SHA}^{commit}" 2>/dev/null; then
+            report_unavailable "The pull request head commit is unavailable locally."
+          fi
+
+          if ! python3 .github/scripts/focused_test_guidance.py \
+            --base-sha "$BASE_SHA" \
+            --head-sha "$HEAD_SHA" > "$report_file"; then
+            report_unavailable "The focused test guidance helper could not produce a report."
+          fi
+
+          publish_report
+
+  python-syntax:
+    name: Python syntax (compileall)
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+        with:
+          persist-credentials: false
+      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6.2.0
+        with:
+          python-version: "3.11"
+      # Byte-compile sources — catches syntax errors without installing deps.
+      - run: python -m compileall -q app.py core routes src services scripts tests
+
+  node-syntax:
+    name: JS syntax (node --check)
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+        with:
+          persist-credentials: false
+      - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e  # v6.4.0
+        with:
+          node-version: "20"
+      # Syntax-check our own JS (skip vendored libs in static/lib).
+      - name: node --check
+        run: |
+          shopt -s globstar nullglob
+          for f in static/app.js static/js/**/*.js; do
+            node --check "$f"
+          done
+
+  python-tests:
+    name: Python tests (pytest)
+    runs-on: ubuntu-latest
+    # Informational for now: the suite has known flaky / environment-dependent
+    # failures (test isolation + embedding-model assertions). Tracked under the
+    # ROADMAP "fresh install smoke tests" item; make this required once green.
+    continue-on-error: true
+    steps:
+      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+
+      # Detect whether this PR only touches documentation files.
+      # If so, skip the expensive pytest run while still reporting a passing check.
+      - name: Check for docs-only changes
+        id: docs-check
+        run: |
+          if [ "${{ github.event_name }}" = "pull_request" ]; then
+            BASE="${{ github.event.pull_request.base.sha }}"
+            HEAD="${{ github.event.pull_request.head.sha }}"
+          else
+            BASE="${{ github.event.before }}"
+            HEAD="${{ github.sha }}"
+          fi
+          # List all changed files; if every file matches docs/markdown patterns, skip pytest.
+          changed=$(git diff --name-only "$BASE" "$HEAD" 2>/dev/null || git diff --name-only HEAD~1 HEAD)
+          non_docs=$(echo "$changed" | grep -Ev '^(docs/|.*\.md$|\.github/[^/]+\.md$)' || true)
+          if [ -z "$non_docs" ]; then
+            echo "docs_only=true" >> "$GITHUB_OUTPUT"
+            echo "Docs-only change detected — skipping pytest."
+          else
+            echo "docs_only=false" >> "$GITHUB_OUTPUT"
+          fi
+
+      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6.2.0
+        if: steps.docs-check.outputs.docs_only != 'true'
+        with:
+          python-version: "3.11"
+          cache: pip
+      - run: pip install -r requirements.txt
+        if: steps.docs-check.outputs.docs_only != 'true'
+      - run: mkdir -p data  # sqlite DB lives at ./data/app.db
+        if: steps.docs-check.outputs.docs_only != 'true'
+      - run: python -m pytest -q
+        if: steps.docs-check.outputs.docs_only != 'true'

.github/workflows/codeql.yml

@@ -0,0 +1,41 @@
+name: CodeQL
+
+# Advanced setup so CodeQL also runs on pull requests (including from forks),
+# surfacing findings before merge instead of only after a change lands on dev.
+on:
+  push:
+    branches: [dev, main]
+  pull_request:
+    branches: [dev]
+  schedule:
+    - cron: "17 3 * * 1"
+
+permissions:
+  contents: read
+
+jobs:
+  analyze:
+    name: Analyze (${{ matrix.language }})
+    runs-on: ubuntu-latest
+    permissions:
+      security-events: write
+      actions: read
+      contents: read
+    strategy:
+      fail-fast: false
+      matrix:
+        language: [actions, javascript-typescript, python]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+        with:
+          persist-credentials: false
+      - name: Initialize CodeQL
+        uses: github/codeql-action/init@8aad20d150bbac5944a9f9d289da16a4b0d87c1e  # v4.36.2
+        with:
+          languages: ${{ matrix.language }}
+          build-mode: none
+      - name: Perform CodeQL Analysis
+        uses: github/codeql-action/analyze@8aad20d150bbac5944a9f9d289da16a4b0d87c1e  # v4.36.2
+        with:
+          category: "/language:${{ matrix.language }}"

.github/workflows/container-scan.yml

@@ -0,0 +1,52 @@
+# 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@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+        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

@@ -0,0 +1,125 @@
+# 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@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+        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@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+        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

@@ -0,0 +1,71 @@
+# 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@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+        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@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+        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/docker-publish.yml

@@ -0,0 +1,140 @@
+name: ci / docker publish
+
+# Build the Odysseus image and publish to GHCR.
+#   push to main -> :latest, :X.Y.Z            (curated release; main is fast-forwarded at releases)
+#   push to dev  -> :dev,    :X.Y.Z-dev.<sha>  (rolling dev + an immutable, traceable pin)
+# Multi-arch (linux/amd64 + linux/arm64): each arch builds on its own native
+# runner and pushes by digest, then a merge job stitches the digests into one
+# manifest list and applies the tags (faster + cleaner than QEMU emulation).
+# Registry: ghcr.io/<owner>/<repo>.
+
+on:
+  push:
+    branches: [dev, main]
+    paths-ignore:
+      - '**.md'
+      - 'docs/**'
+      - '.github/ISSUE_TEMPLATE/**'
+
+concurrency:
+  group: docker-publish-${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  build:
+    name: build (${{ matrix.arch }})
+    runs-on: ${{ matrix.runner }}
+    permissions:
+      contents: read
+      packages: write
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - platform: linux/amd64
+            arch: amd64
+            runner: ubuntu-latest
+          - platform: linux/arm64
+            arch: arm64
+            runner: ubuntu-24.04-arm
+    steps:
+      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+        with:
+          persist-credentials: false
+      - name: Set up Buildx
+        uses: docker/setup-buildx-action@d7f5e7f509e45cec5c76c4d5afdd7de93d0b3df5  # v4.1.0
+      - name: Log in to GHCR
+        uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee  # v4.2.0
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Build and push by digest
+        id: build
+        uses: docker/build-push-action@f9f3042f7e2789586610d6e8b85c8f03e5195baf  # v7.2.0
+        with:
+          context: .
+          platforms: ${{ matrix.platform }}
+          outputs: type=image,name=${{ env.REGISTRY }}/${{ env.IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
+          cache-from: type=gha,scope=${{ matrix.arch }}
+          cache-to: type=gha,mode=max,scope=${{ matrix.arch }}
+      - name: Export digest
+        run: |
+          mkdir -p /tmp/digests
+          digest="${{ steps.build.outputs.digest }}"
+          touch "/tmp/digests/${digest#sha256:}"
+      - name: Upload digest
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a  # v7.0.1
+        with:
+          name: digest-${{ matrix.arch }}
+          path: /tmp/digests/*
+          if-no-files-found: error
+          retention-days: 1
+
+  merge:
+    name: merge manifest + tag
+    runs-on: ubuntu-latest
+    needs: build
+    permissions:
+      contents: read
+      packages: write
+    steps:
+      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+        with:
+          persist-credentials: false
+      - name: Read APP_VERSION + short sha
+        id: ver
+        run: |
+          v=$(grep -E '^APP_VERSION' src/constants.py | head -1 | sed -E 's/.*"([^"]+)".*/\1/')
+          [ -n "$v" ] || { echo "APP_VERSION not found"; exit 1; }
+          echo "version=$v" >> "$GITHUB_OUTPUT"
+          echo "short=${GITHUB_SHA::7}" >> "$GITHUB_OUTPUT"
+      - name: Download digests
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c  # v8.0.1
+        with:
+          path: /tmp/digests
+          pattern: digest-*
+          merge-multiple: true
+      - name: Set up Buildx
+        uses: docker/setup-buildx-action@d7f5e7f509e45cec5c76c4d5afdd7de93d0b3df5  # v4.1.0
+      - name: Log in to GHCR
+        uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee  # v4.2.0
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Compute tags
+        id: meta
+        uses: docker/metadata-action@80c7e94dd9b9319bd5eb7a0e0fe9291e23a2a2e9  # v6.1.0
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+          tags: |
+            type=raw,value=latest,enable=${{ github.ref == 'refs/heads/main' }}
+            type=raw,value=${{ steps.ver.outputs.version }},enable=${{ github.ref == 'refs/heads/main' }}
+            type=raw,value=dev,enable=${{ github.ref == 'refs/heads/dev' }}
+            type=raw,value=${{ steps.ver.outputs.version }}-dev.${{ steps.ver.outputs.short }},enable=${{ github.ref == 'refs/heads/dev' }}
+      - name: Create manifest list + push tags
+        working-directory: /tmp/digests
+        run: |
+          tags=$(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON")
+          digests=$(printf "${REGISTRY}/${IMAGE_NAME}@sha256:%s " *)
+          # word-splitting is intended: $tags and $digests each expand to multiple args
+          # shellcheck disable=SC2086
+          docker buildx imagetools create $tags $digests
+        env:
+          REGISTRY: ${{ env.REGISTRY }}
+          IMAGE_NAME: ${{ env.IMAGE_NAME }}
+      - name: Inspect
+        run: |
+          if [ "$GITHUB_REF" = "refs/heads/main" ]; then ref=latest; else ref=dev; fi
+          docker buildx imagetools inspect "${REGISTRY}/${IMAGE_NAME}:${ref}"
+        env:
+          REGISTRY: ${{ env.REGISTRY }}
+          IMAGE_NAME: ${{ env.IMAGE_NAME }}

.github/workflows/issue-description-check.yml

@@ -0,0 +1,24 @@
+name: ci / issue description check
+
+on:
+  issues:
+    types: [opened, edited, reopened, closed]
+
+permissions:
+  issues: write
+
+jobs:
+  check:
+    name: Check issue description
+    runs-on: ubuntu-latest
+    # Skip bots (Dependabot, release-drafter, etc.)
+    if: ${{ github.event.issue.user.type != 'Bot' }}
+    steps:
+      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+        with:
+          sparse-checkout: .github/scripts
+          persist-credentials: false
+
+      - uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3  # v9.0.0
+        with:
+          script: return require('./.github/scripts/check-issue-description.js')({github, context, core})

.github/workflows/pr-description-check.yml

@@ -0,0 +1,109 @@
+name: ci / PR checks
+
+on:
+  # pull_request_target runs in the base-repo context (has secrets) so the check
+  # works on fork PRs. Safe here: the checkout pins to the base branch (no fork
+  # code runs) and the scripts only read context.payload and call the GitHub API.
+  pull_request_target:  # zizmor: ignore[dangerous-triggers]
+    types: [opened, edited, synchronize, reopened, ready_for_review]
+
+# Default-deny at the workflow level; each job opts into only the scopes it needs.
+# Note: modifying a PR's labels/comments needs pull-requests:write even though the
+# REST path is under /issues/{n}/...; issues:write alone returns 403 on PRs.
+permissions: {}
+
+jobs:
+  check-description:
+    name: Check PR description
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
+      issues: write
+    # Skip bots: they open PRs programmatically and have their own process.
+    if: github.event.pull_request.user.type != 'Bot'
+    steps:
+      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+        with:
+          ref: ${{ github.base_ref }}
+          sparse-checkout: .github/scripts
+          persist-credentials: false
+
+      - uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3  # v9.0.0
+        with:
+          script: return require('./.github/scripts/check-pr-description.js')({github, context, core})
+
+  check-title:
+    name: Check PR title (Conventional Commits)
+    runs-on: ubuntu-latest
+    permissions: {}
+    # Skip bots: they open PRs programmatically and have their own process.
+    if: github.event.pull_request.user.type != 'Bot'
+    steps:
+      - uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3  # v9.0.0
+        with:
+          script: |
+            const title = context.payload.pull_request.title || "";
+            // Conventional Commits: type(optional-scope)(optional !): summary
+            const re = /^(feat|fix|docs|style|refactor|perf|test|build|ci|chore|revert)(\([\w .\/-]+\))?!?: .+/;
+            if (!re.test(title)) {
+              core.setFailed(
+                `PR title is not in Conventional Commits format:\n  "${title}"\n\n` +
+                `Expected: type(scope): summary\n` +
+                `Example:  fix(search): handle empty query\n` +
+                `Types: feat, fix, docs, style, refactor, perf, test, build, ci, chore, revert.`
+              );
+            } else {
+              core.info(`PR title OK: ${title}`);
+            }
+
+  check-mergeable:
+    name: Flag unmergeable PRs
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
+      issues: write
+    # Skip bots: they open PRs programmatically and have their own process.
+    if: github.event.pull_request.user.type != 'Bot'
+    steps:
+      - uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3  # v9.0.0
+        with:
+          script: |
+            const repo = { owner: context.repo.owner, repo: context.repo.repo };
+            const number = context.payload.pull_request.number;
+            const READY = "ready for review";
+            const CONFLICT = "merge conflict";
+
+            // Ensure the conflict label exists (red). Ignore if already present.
+            try {
+              await github.rest.issues.getLabel({ ...repo, name: CONFLICT });
+            } catch {
+              await github.rest.issues.createLabel({
+                ...repo, name: CONFLICT, color: "B60205",
+                description: "Conflicts with the base branch; needs a rebase before review.",
+              }).catch(() => {});
+            }
+
+            // mergeable is computed asynchronously and is often null right after
+            // an event, so poll a few times until GitHub has resolved it.
+            let pr = null;
+            for (let i = 0; i < 5; i++) {
+              const { data } = await github.rest.pulls.get({ ...repo, pull_number: number });
+              if (data.mergeable !== null) { pr = data; break; }
+              await new Promise(r => setTimeout(r, 3000));
+            }
+            if (!pr || pr.draft) return;
+            const labels = pr.labels.map(l => l.name);
+
+            if (pr.mergeable === false) {
+              if (labels.includes(READY)) {
+                await github.rest.issues.removeLabel({ ...repo, issue_number: number, name: READY }).catch(() => {});
+              }
+              if (!labels.includes(CONFLICT)) {
+                await github.rest.issues.addLabels({ ...repo, issue_number: number, labels: [CONFLICT] });
+              }
+            } else if (pr.mergeable === true) {
+              if (labels.includes(CONFLICT)) {
+                await github.rest.issues.removeLabel({ ...repo, issue_number: number, name: CONFLICT }).catch(() => {});
+              }
+            }

.github/workflows/secret-scan.yml

@@ -0,0 +1,60 @@
+# 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@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+        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

@@ -0,0 +1,80 @@
+# 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@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+        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@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+        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

@@ -12,7 +12,17 @@ venv/
 
 # Environment
 .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/
@@ -60,12 +70,20 @@ 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
 !docs/*.png
 !docs/*.gif
 !docs/*.webp
+# …and curated docs/ subfolder assets (e.g. accessibility before/after shots).
+!docs/**/*.png
+!docs/**/*.jpg
+!docs/**/*.gif
+!docs/**/*.webp
 
 # Reports and temp files
 reports/
@@ -76,8 +94,11 @@ research_data/
 
 # Internal dev/review notes — not for public repo
 dev-docs/
+# Windows-port working docs (local only, not for public repo)
+docs/windows-port/
 
 # Local config
 compound.config.json
 *.error.log
 _scratch/
+/odysseus/

ACKNOWLEDGMENTS.md

@@ -33,8 +33,8 @@ The full license texts are kept in [`licenses/`](licenses/).
 - **[Tongyi DeepResearch](https://github.com/Alibaba-NLP/DeepResearch)** by
   **Alibaba-NLP / Tongyi Lab** — the multi-step deep-research agent pipeline.
   Copyright © Alibaba-NLP / Tongyi Lab. **Apache-2.0.** Adapted for Odysseus's
-  Deep Research feature (`api/research_*.py`, `routes/research_routes.py`,
-  `services/search/`). Full text in
+  Deep Research feature (`services/research/`, `src/research_handler.py`,
+  `routes/research_routes.py`, `services/search/`). Full text in
   [`licenses/DeepResearch-Apache-2.0.txt`](licenses/DeepResearch-Apache-2.0.txt).
 
 ---
@@ -47,7 +47,7 @@ just composed.
 
 | Service | Image | Purpose | License |
 |---|---|---|---|
-| [SearXNG](https://github.com/searxng/searxng) | `searxng/searxng:latest` | Default metasearch backend | AGPL-3.0 |
+| [SearXNG](https://github.com/searxng/searxng) | `searxng/searxng:2026.5.31-7159b8aed` (pinned tag; see compose) | Default metasearch backend | AGPL-3.0 |
 | [ChromaDB](https://github.com/chroma-core/chroma) | `chromadb/chroma:latest` | Vector store for memory / RAG | Apache-2.0 |
 | [ntfy](https://github.com/binwiederhier/ntfy) | `binwiederhier/ntfy` | Push notifications (self-hosted reminders) | Apache-2.0 / GPL-2.0 |
 
@@ -86,6 +86,7 @@ Bundled in `static/fonts/`:
 | [Fira Code](https://github.com/tonsky/FiraCode) | SIL Open Font License 1.1 | Nikita Prokopov & contributors |
 | [Inter](https://github.com/rsms/inter) | SIL Open Font License 1.1 | Rasmus Andersson |
 | [GohuFont](https://font.gohu.org/) (`fonts/custom/GohuFont.ttf`) | WTFPL | Hugo Chargois |
+| [OpenDyslexic](https://opendyslexic.org/) (`fonts/OpenDyslexic-{Regular,Bold}.woff2`) | SIL Open Font License 1.1 ([`licenses/OpenDyslexic-OFL.txt`](licenses/OpenDyslexic-OFL.txt)) | Abbie Gonzalez |
 
 ## Python dependencies
 
@@ -118,6 +119,7 @@ Core (`requirements.txt`) and optional (`requirements-optional.txt`):
 | croniter | MIT |
 | pytest / pytest-asyncio | MIT / Apache-2.0 |
 | duckduckgo-search (optional) | MIT |
+| markitdown (optional — Office/EPUB text extraction) | MIT |
 | **PyMuPDF** *(optional — form-filling only)* | **AGPL-3.0** — see note below |
 
 ## Companion services (interoperated with, not bundled)
@@ -152,6 +154,9 @@ concerns from earlier are resolved:
   deployment (Artifex also sells a commercial PyMuPDF license that lifts this).
 - **`caldav`** (Python lib) is **dual-licensed GPL-3.0-or-later OR Apache-2.0**.
   Odysseus uses it under **Apache-2.0**, which is permissive and MIT-compatible.
+- **`markitdown`** (Microsoft) is **MIT** and used only as an *optional* dependency for Office/EPUB text
+  extraction (`src/markitdown_runtime.py`), lazy-imported with graceful fallback — the MIT core runs without
+  it. The cloud `az-doc-intel` extra is deliberately **not** installed, keeping extraction fully local.
 
 ---
 

CONTRIBUTING.md

@@ -2,6 +2,17 @@
 
 Thanks for helping. The project is moving quickly, so the best contributions are focused, easy to review, and easy to test.
 
+## Branch model
+
+Odysseus has two branches:
+
+- **`dev`** — where all PRs land. Things can be in flux here; the merge button gets used freely.
+- **`main`** — what users run. Curated and tested by the maintainer. Fast-forwarded to a stable `dev` commit at each release.
+
+**Open your PR against `dev`, not `main`.** The GitHub "base" dropdown defaults to `dev`. If you opened a PR against `main` by accident, click "Edit" on the PR and change the base — no rebase needed.
+
+End-users cloning the repo will land on `dev` by default. To run the curated/stable version: `git checkout main` after clone.
+
 ## Before You Start
 
 - Search existing issues and pull requests before opening a new one.
@@ -14,7 +25,7 @@ Thanks for helping. The project is moving quickly, so the best contributions are
 Docker is the recommended path for normal testing:
 
 ```bash
-git clone https://github.com/pewdiepie-archdaemon/odysseus.git
+git clone https://github.com/odysseus-dev/odysseus.git
 cd odysseus
 cp .env.example .env
 docker compose up -d --build
@@ -26,7 +37,7 @@ Manual development uses Python 3.11+:
 python3 -m venv venv
 source venv/bin/activate
 pip install -r requirements.txt
-python -m uvicorn app:app --host 0.0.0.0 --port 7000
+python -m uvicorn app:app --host 127.0.0.1 --port 7000
 ```
 
 Windows is not actively tested. Docker on Linux or a Linux/macOS manual install is the safer path for now.
@@ -57,12 +68,44 @@ Good pull requests usually include:
 
 - A short explanation of the bug or feature.
 - The files or areas changed.
-- Manual test steps or automated test results.
+- Manual test steps or automated test results from running the actual app, not just the test suite.
 - Screenshots or short recordings for UI changes.
 - Links to related issues, for example `Fixes #123`.
 
 Please keep PRs small. Large PRs that mix unrelated cleanup, formatting, refactors, and behavior changes are much harder to review.
 
+> **Auto-generated PRs.** If you are running an LLM agent (Devin, Cursor, OpenHands, Claude Code, etc.) against this repo: please open an issue describing the problem first instead of opening a PR directly. Bulk agent-generated PRs that don't match the project's visual style or contribution format will be closed without review, even when the underlying fix is correct.
+
+## Style and visual changes
+
+Odysseus has an intentional visual style. PRs that ignore it will be closed without merge, no matter how correct the underlying code is.
+
+Before submitting any change that affects what the app looks like — buttons, icons, fonts, colors, spacing, layout, CSS, HTML, SVG, or any `static/js/` module that draws to the DOM — please:
+
+1. **Run the app locally** and view the change in a browser. Type-checks and unit tests are not enough.
+2. **Attach a screenshot or short clip** of the change in the running app. Add a mobile screenshot too if the change affects mobile.
+3. **Match the existing visual language.** Specifically:
+   - Reuse existing CSS variables (`--red`, `--fg`, `--bg`, `--card`, `--border`, …). Do not introduce new color values, font sizes, or spacing units.
+   - Reuse existing button, input, card, and border classes. Don't invent parallel styling for similar widgets.
+   - **No Unicode emoji in UI or code.** Use inline SVG (matching the monochrome icon style already in `static/index.html`) or plain text.
+   - Monospaced font (`Fira Code`) for primary UI text. Don't override.
+   - Dark theme is the default; any light-mode work goes through the existing theme system, not hard-coded.
+4. **Don't add parallel components.** If a similar widget already exists in the app, extend it instead of writing a new one.
+
+If you are unsure whether a change is "visual," it is. Default to attaching a screenshot.
+
+## Code conventions
+
+Don't hardcode values that the project already exposes through a constant or a helper. Hardcoded literals drift out of sync, break on non-default deployments, and reintroduce bugs we've already fixed.
+
+- **Filesystem paths:** never build writable paths from `Path(__file__)...` into the source tree, hardcode `/app/...`, or use a relative `"data/..."` string. Every persisted file and directory has a named constant in `src/constants.py` (for example `AUTH_FILE`, `USER_PREFS_FILE`, `SETTINGS_FILE`, `TTS_CACHE_DIR`, `CHROMA_DIR`). Import and use that named constant; do not re-derive the path locally with `os.path.join(DATA_DIR, "x.json")` or `DATA_DIR / "x.json"`. `DATA_DIR` is the single place that reads `ODYSSEUS_DATA_DIR`, so use it directly only for dynamic paths that have no fixed name (for example per-owner files). If a data file or directory has no constant yet, add one to `src/constants.py`. The source tree is read-only in Docker and `/app/...` does not exist on native runs; guard directory creation so an unwritable path degrades gracefully instead of crashing at import.
+- **Internal API / loopback URLs:** don't hardcode `http://localhost:7000`. Use `internal_api_base()` from `src.constants` (it honors `ODYSSEUS_INTERNAL_BASE` / `APP_PORT`).
+- **Ports, limits, model lists, and similar:** reuse the existing constant if one exists; if it doesn't and the value is used in more than one place, add a constant rather than copying the literal.
+
+If you need a value that has no constant or helper yet, add it to `src/constants.py` (the single source of truth for paths and config; `core/constants.py` only re-exports it for backward compatibility) and import it, rather than repeating a literal across files.
+
+**Commits:** use [Conventional Commits](https://www.conventionalcommits.org), `type(scope): summary` (e.g. `fix(search): ...`, `feat(notes): ...`, `docs(contributing): ...`). Common types: `fix`, `feat`, `refactor`, `docs`, `test`, `chore`, `ci`. Keep the subject short and imperative; put the "why" in the body when it isn't obvious.
+
 ## Issue Reports
 
 For bugs, include:

Dockerfile

@@ -1,11 +1,23 @@
-FROM python:3.12-slim
+# ---- builder: patch + build wheels for Real-ESRGAN's broken-on-3.14 deps ----
+# basicsr/gfpgan/facexlib read their version via exec()+locals()['__version__'],
+# which raises KeyError on Python 3.13+ (PEP 667). Build patched wheels here so
+# the final image / Cookbook never has to compile the broken sdists. See
+# docker/build-realesrgan-wheels.sh for the full rationale.
+FROM python:3.14-slim AS realesrgan-wheels
+RUN apt-get update && apt-get install -y --no-install-recommends curl \
+    && rm -rf /var/lib/apt/lists/*
+COPY docker/build-realesrgan-wheels.sh /usr/local/bin/build-realesrgan-wheels.sh
+RUN bash /usr/local/bin/build-realesrgan-wheels.sh /wheels
+
+FROM python:3.14-slim
 
 # System deps. tmux is required by Cookbook for background downloads/serves.
 # openssh-client is required for Cookbook remote server tests, setup, probes,
 # downloads, and serves from Docker installs.
 # git/cmake are required when Cookbook builds llama.cpp on first llama.cpp
 # launch inside Docker.
-# nodejs/npm provide npx for the optional built-in Browser MCP server.
+# nodejs/npm provide npx for the built-in Browser MCP server.
+# chromium provides the actual browser binary used by that MCP server.
 # gosu lets the entrypoint drop privileges cleanly so signals still reach
 # uvicorn directly (no extra shell layer like `su`/`sudo` would add).
 RUN apt-get update && apt-get install -y --no-install-recommends \
@@ -15,22 +27,76 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     git \
     nodejs \
     npm \
+    chromium \
     tmux \
     openssh-client \
     gosu \
+    libgl1 \
+    libglib2.0-0t64 \
+    libxcb1 \
+    libmagic1 \
     && rm -rf /var/lib/apt/lists/*
 
+# libgl1/libglib2.0-0t64/libxcb1 are runtime shared libs (libGL.so.1,
+# libglib-2.0/libgthread, libxcb.so.1) that opencv-python (cv2) loads. The
+# slim base omits them, so the Cookbook "install realesrgan" path imports cv2
+# and dies with `libxcb.so.1: cannot open shared object file` despite a clean
+# pip install. Using full opencv-python (not -headless) because basicsr/gfpgan/
+# facexlib/realesrgan all depend on the `opencv-python` distribution by name.
+#
+# libmagic1 is the shared lib (libmagic.so.1) that python-magic dlopens for
+# content-based MIME sniffing in src/upload_handler.py. We install both here
+# (libmagic1 + the python-magic wrapper, below) rather than in requirements.txt
+# because python-magic resolves libmagic at import time: where the lib is
+# absent the import can block or raise, so keeping it image-only avoids
+# regressing pip/venv installs on hosts without libmagic. Debian always has the
+# lib here, so the import is instant and detection actually works.
+
+# Docker CLI (client only — daemon stays on the host via the
+# /var/run/docker.sock mount). The Debian `docker.io` package ships
+# dockerd but not the client binary on slim, so grab the static client
+# tarball from download.docker.com instead.
+ARG DOCKER_CLI_VERSION=29.6.2
+RUN ARCH="$(dpkg --print-architecture)" \
+    && case "$ARCH" in \
+         amd64) DARCH=x86_64 ;; \
+         arm64) DARCH=aarch64 ;; \
+         *) echo "unsupported arch $ARCH"; exit 1 ;; \
+       esac \
+    && curl -fsSL "https://download.docker.com/linux/static/stable/${DARCH}/docker-${DOCKER_CLI_VERSION}.tgz" \
+       -o /tmp/docker.tgz \
+    && tar -xzf /tmp/docker.tgz -C /tmp \
+    && install -m 0755 /tmp/docker/docker /usr/local/bin/docker \
+    && rm -rf /tmp/docker /tmp/docker.tgz
+
 WORKDIR /app
 
-# Install Python deps first (layer cache)
-COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+# Install Python deps first (layer cache). Optional extras (PyMuPDF AGPL, etc.)
+# are opt-in so the default image stays MIT-core; see requirements-optional.txt.
+ARG INSTALL_OPTIONAL=false
+COPY requirements.txt requirements-optional.txt ./
+RUN pip install --no-cache-dir -r requirements.txt \
+    && if [ "$INSTALL_OPTIONAL" = "true" ]; then pip install --no-cache-dir -r requirements-optional.txt; fi
+
+# python-magic powers content-based MIME sniffing in src/upload_handler.py.
+# Image-only (not in requirements.txt) because it needs the libmagic1 system
+# lib installed above; see the apt note near the top of this stage.
+RUN pip install --no-cache-dir python-magic==0.4.27
+
+# Pre-install the patched basicsr/gfpgan/facexlib wheels built in the
+# realesrgan-wheels stage (--no-deps keeps the image lean — torch & friends are
+# pulled only when realesrgan is actually installed). With these dists already
+# satisfied, the Cookbook's plain `pip install realesrgan` resolves them from
+# wheels instead of rebuilding the sdists that fail on Python 3.14.
+COPY --from=realesrgan-wheels /wheels/ /tmp/odysseus-wheels/
+RUN pip install --no-cache-dir --no-deps /tmp/odysseus-wheels/*.whl \
+    && rm -rf /tmp/odysseus-wheels
 
 # Copy app code
 COPY . .
 
 # Create data directory (mount a volume here for persistence)
-RUN mkdir -p data logs
+RUN mkdir -p data logs services/cache/search
 
 # Entrypoint that drops to PUID/PGID (default 1000:1000) and repairs
 # ownership on the bind-mounted /app/data and /app/logs. Without this,

LICENSE

@@ -1,21 +1,235 @@
-MIT License
+GNU AFFERO GENERAL PUBLIC LICENSE
+Version 3, 19 November 2007
 
-Copyright (c) 2025 Odysseus Contributors
+Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
 
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
+Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed.
 
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
+                            Preamble
 
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
+The GNU Affero General Public License is a free, copyleft license for software and other kinds of works, specifically designed to ensure cooperation with the community in the case of network server software.
+
+The licenses for most software and other practical works are designed to take away your freedom to share and change the works.  By contrast, our General Public Licenses are intended to guarantee your freedom to share and change all versions of a program--to make sure it remains free software for all its users.
+
+When we speak of free software, we are referring to freedom, not price.  Our General Public Licenses are designed to make sure that you have the freedom to distribute copies of free software (and charge for them if you wish), that you receive source code or can get it if you want it, that you can change the software or use pieces of it in new free programs, and that you know you can do these things.
+
+Developers that use our General Public Licenses protect your rights with two steps: (1) assert copyright on the software, and (2) offer you this License which gives you legal permission to copy, distribute and/or modify the software.
+
+A secondary benefit of defending all users' freedom is that improvements made in alternate versions of the program, if they receive widespread use, become available for other developers to incorporate.  Many developers of free software are heartened and encouraged by the resulting cooperation.  However, in the case of software used on network servers, this result may fail to come about. The GNU General Public License permits making a modified version and letting the public access it on a server without ever releasing its source code to the public.
+
+The GNU Affero General Public License is designed specifically to ensure that, in such cases, the modified source code becomes available to the community.  It requires the operator of a network server to provide the source code of the modified version running there to the users of that server.  Therefore, public use of a modified version, on a publicly accessible server, gives the public access to the source code of the modified version.
+
+An older license, called the Affero General Public License and published by Affero, was designed to accomplish similar goals.  This is a different license, not a version of the Affero GPL, but Affero has released a new version of the Affero GPL which permits relicensing under this license.
+
+The precise terms and conditions for copying, distribution and modification follow.
+
+                       TERMS AND CONDITIONS
+
+0. Definitions.
+
+"This License" refers to version 3 of the GNU Affero General Public License.
+
+"Copyright" also means copyright-like laws that apply to other kinds of works, such as semiconductor masks.
+
+"The Program" refers to any copyrightable work licensed under this License.  Each licensee is addressed as "you".  "Licensees" and "recipients" may be individuals or organizations.
+
+To "modify" a work means to copy from or adapt all or part of the work in a fashion requiring copyright permission, other than the making of an exact copy.  The resulting work is called a "modified version" of the earlier work or a work "based on" the earlier work.
+
+A "covered work" means either the unmodified Program or a work based on the Program.
+
+To "propagate" a work means to do anything with it that, without permission, would make you directly or secondarily liable for infringement under applicable copyright law, except executing it on a computer or modifying a private copy.  Propagation includes copying, distribution (with or without modification), making available to the public, and in some countries other activities as well.
+
+To "convey" a work means any kind of propagation that enables other parties to make or receive copies.  Mere interaction with a user through a computer network, with no transfer of a copy, is not conveying.
+
+An interactive user interface displays "Appropriate Legal Notices" to the extent that it includes a convenient and prominently visible feature that (1) displays an appropriate copyright notice, and (2) tells the user that there is no warranty for the work (except to the extent that warranties are provided), that licensees may convey the work under this License, and how to view a copy of this License.  If the interface presents a list of user commands or options, such as a menu, a prominent item in the list meets this criterion.
+
+1. Source Code.
+The "source code" for a work means the preferred form of the work for making modifications to it.  "Object code" means any non-source form of a work.
+
+A "Standard Interface" means an interface that either is an official standard defined by a recognized standards body, or, in the case of interfaces specified for a particular programming language, one that is widely used among developers working in that language.
+
+The "System Libraries" of an executable work include anything, other than the work as a whole, that (a) is included in the normal form of packaging a Major Component, but which is not part of that Major Component, and (b) serves only to enable use of the work with that Major Component, or to implement a Standard Interface for which an implementation is available to the public in source code form.  A "Major Component", in this context, means a major essential component (kernel, window system, and so on) of the specific operating system (if any) on which the executable work runs, or a compiler used to produce the work, or an object code interpreter used to run it.
+
+The "Corresponding Source" for a work in object code form means all the source code needed to generate, install, and (for an executable work) run the object code and to modify the work, including scripts to control those activities.  However, it does not include the work's System Libraries, or general-purpose tools or generally available free programs which are used unmodified in performing those activities but which are not part of the work.  For example, Corresponding Source includes interface definition files associated with source files for the work, and the source code for shared libraries and dynamically linked subprograms that the work is specifically designed to require, such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+The Corresponding Source need not include anything that users can regenerate automatically from other parts of the Corresponding Source.
+
+The Corresponding Source for a work in source code form is that same work.
+
+2. Basic Permissions.
+All rights granted under this License are granted for the term of copyright on the Program, and are irrevocable provided the stated conditions are met.  This License explicitly affirms your unlimited permission to run the unmodified Program.  The output from running a covered work is covered by this License only if the output, given its content, constitutes a covered work.  This License acknowledges your rights of fair use or other equivalent, as provided by copyright law.
+
+You may make, run and propagate covered works that you do not convey, without conditions so long as your license otherwise remains in force.  You may convey covered works to others for the sole purpose of having them make modifications exclusively for you, or provide you with facilities for running those works, provided that you comply with the terms of this License in conveying all material for which you do not control copyright.  Those thus making or running the covered works for you must do so exclusively on your behalf, under your direction and control, on terms that prohibit them from making any copies of your copyrighted material outside their relationship with you.
+
+Conveying under any other circumstances is permitted solely under the conditions stated below.  Sublicensing is not allowed; section 10 makes it unnecessary.
+
+3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+No covered work shall be deemed part of an effective technological measure under any applicable law fulfilling obligations under article 11 of the WIPO copyright treaty adopted on 20 December 1996, or similar laws prohibiting or restricting circumvention of such measures.
+
+When you convey a covered work, you waive any legal power to forbid circumvention of technological measures to the extent such circumvention is effected by exercising rights under this License with respect to the covered work, and you disclaim any intention to limit operation or modification of the work as a means of enforcing, against the work's users, your or third parties' legal rights to forbid circumvention of technological measures.
+
+4. Conveying Verbatim Copies.
+You may convey verbatim copies of the Program's source code as you receive it, in any medium, provided that you conspicuously and appropriately publish on each copy an appropriate copyright notice; keep intact all notices stating that this License and any non-permissive terms added in accord with section 7 apply to the code; keep intact all notices of the absence of any warranty; and give all recipients a copy of this License along with the Program.
+
+You may charge any price or no price for each copy that you convey, and you may offer support or warranty protection for a fee.
+
+5. Conveying Modified Source Versions.
+You may convey a work based on the Program, or the modifications to produce it from the Program, in the form of source code under the terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is released under this License and any conditions added under section 7.  This requirement modifies the requirement in section 4 to "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this License to anyone who comes into possession of a copy.  This License will therefore apply, along with any applicable section 7 additional terms, to the whole of the work, and all its parts, regardless of how they are packaged.  This License gives no permission to license the work in any other way, but it does not invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display Appropriate Legal Notices; however, if the Program has interactive interfaces that do not display Appropriate Legal Notices, your work need not make them do so.
+
+A compilation of a covered work with other separate and independent works, which are not by their nature extensions of the covered work, and which are not combined with it such as to form a larger program, in or on a volume of a storage or distribution medium, is called an "aggregate" if the compilation and its resulting copyright are not used to limit the access or legal rights of the compilation's users beyond what the individual works permit.  Inclusion of a covered work in an aggregate does not cause this License to apply to the other parts of the aggregate.
+
+6. Conveying Non-Source Forms.
+You may convey a covered work in object code form under the terms of sections 4 and 5, provided that you also convey the machine-readable Corresponding Source under the terms of this License, in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product (including a physical distribution medium), accompanied by the Corresponding Source fixed on a durable physical medium customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product (including a physical distribution medium), accompanied by a written offer, valid for at least three years and valid for as long as you offer spare parts or customer support for that product model, to give anyone who possesses the object code either (1) a copy of the Corresponding Source for all the software in the product that is covered by this License, on a durable physical medium customarily used for software interchange, for a price no more than your reasonable cost of physically performing this conveying of source, or (2) access to copy the Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the written offer to provide the Corresponding Source.  This alternative is allowed only occasionally and noncommercially, and only if you received the object code with such an offer, in accord with subsection 6b.
+
+    d) Convey the object code by offering access from a designated place (gratis or for a charge), and offer equivalent access to the Corresponding Source in the same way through the same place at no further charge.  You need not require recipients to copy the Corresponding Source along with the object code.  If the place to copy the object code is a network server, the Corresponding Source may be on a different server (operated by you or a third party) that supports equivalent copying facilities, provided you maintain clear directions next to the object code saying where to find the Corresponding Source.  Regardless of what server hosts the Corresponding Source, you remain obligated to ensure that it is available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided you inform other peers where the object code and Corresponding Source of the work are being offered to the general public at no charge under subsection 6d.
+
+A separable portion of the object code, whose source code is excluded from the Corresponding Source as a System Library, need not be included in conveying the object code work.
+
+A "User Product" is either (1) a "consumer product", which means any tangible personal property which is normally used for personal, family, or household purposes, or (2) anything designed or sold for incorporation into a dwelling.  In determining whether a product is a consumer product, doubtful cases shall be resolved in favor of coverage.  For a particular product received by a particular user, "normally used" refers to a typical or common use of that class of product, regardless of the status of the particular user or of the way in which the particular user actually uses, or expects or is expected to use, the product.  A product is a consumer product regardless of whether the product has substantial commercial, industrial or non-consumer uses, unless such uses represent the only significant mode of use of the product.
+
+"Installation Information" for a User Product means any methods, procedures, authorization keys, or other information required to install and execute modified versions of a covered work in that User Product from a modified version of its Corresponding Source.  The information must suffice to ensure that the continued functioning of the modified object code is in no case prevented or interfered with solely because modification has been made.
+
+If you convey an object code work under this section in, or with, or specifically for use in, a User Product, and the conveying occurs as part of a transaction in which the right of possession and use of the User Product is transferred to the recipient in perpetuity or for a fixed term (regardless of how the transaction is characterized), the Corresponding Source conveyed under this section must be accompanied by the Installation Information.  But this requirement does not apply if neither you nor any third party retains the ability to install modified object code on the User Product (for example, the work has been installed in ROM).
+
+The requirement to provide Installation Information does not include a requirement to continue to provide support service, warranty, or updates for a work that has been modified or installed by the recipient, or for the User Product in which it has been modified or installed.  Access to a network may be denied when the modification itself materially and adversely affects the operation of the network or violates the rules and protocols for communication across the network.
+
+Corresponding Source conveyed, and Installation Information provided, in accord with this section must be in a format that is publicly documented (and with an implementation available to the public in source code form), and must require no special password or key for unpacking, reading or copying.
+
+7. Additional Terms.
+"Additional permissions" are terms that supplement the terms of this License by making exceptions from one or more of its conditions. Additional permissions that are applicable to the entire Program shall be treated as though they were included in this License, to the extent that they are valid under applicable law.  If additional permissions apply only to part of the Program, that part may be used separately under those permissions, but the entire Program remains governed by this License without regard to the additional permissions.
+
+When you convey a copy of a covered work, you may at your option remove any additional permissions from that copy, or from any part of it.  (Additional permissions may be written to require their own removal in certain cases when you modify the work.)  You may place additional permissions on material, added by you to a covered work, for which you have or can give appropriate copyright permission.
+
+Notwithstanding any other provision of this License, for material you add to a covered work, you may (if authorized by the copyright holders of that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or author attributions in that material or in the Appropriate Legal Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or requiring that modified versions of such material be marked in reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that material by anyone who conveys the material (or modified versions of it) with contractual assumptions of liability to the recipient, for any liability that these contractual assumptions directly impose on those licensors and authors.
+
+All other non-permissive additional terms are considered "further restrictions" within the meaning of section 10.  If the Program as you received it, or any part of it, contains a notice stating that it is governed by this License along with a term that is a further restriction, you may remove that term.  If a license document contains a further restriction but permits relicensing or conveying under this License, you may add to a covered work material governed by the terms of that license document, provided that the further restriction does not survive such relicensing or conveying.
+
+If you add terms to a covered work in accord with this section, you must place, in the relevant source files, a statement of the additional terms that apply to those files, or a notice indicating where to find the applicable terms.
+
+Additional terms, permissive or non-permissive, may be stated in the form of a separately written license, or stated as exceptions; the above requirements apply either way.
+
+8. Termination.
+
+You may not propagate or modify a covered work except as expressly provided under this License.  Any attempt otherwise to propagate or modify it is void, and will automatically terminate your rights under this License (including any patent licenses granted under the third paragraph of section 11).
+
+However, if you cease all violation of this License, then your license from a particular copyright holder is reinstated (a) provisionally, unless and until the copyright holder explicitly and finally terminates your license, and (b) permanently, if the copyright holder fails to notify you of the violation by some reasonable means prior to 60 days after the cessation.
+
+Moreover, your license from a particular copyright holder is reinstated permanently if the copyright holder notifies you of the violation by some reasonable means, this is the first time you have received notice of violation of this License (for any work) from that copyright holder, and you cure the violation prior to 30 days after your receipt of the notice.
+
+Termination of your rights under this section does not terminate the licenses of parties who have received copies or rights from you under this License.  If your rights have been terminated and not permanently reinstated, you do not qualify to receive new licenses for the same material under section 10.
+
+9. Acceptance Not Required for Having Copies.
+
+You are not required to accept this License in order to receive or run a copy of the Program.  Ancillary propagation of a covered work occurring solely as a consequence of using peer-to-peer transmission to receive a copy likewise does not require acceptance.  However, nothing other than this License grants you permission to propagate or modify any covered work.  These actions infringe copyright if you do not accept this License.  Therefore, by modifying or propagating a covered work, you indicate your acceptance of this License to do so.
+
+10. Automatic Licensing of Downstream Recipients.
+
+Each time you convey a covered work, the recipient automatically receives a license from the original licensors, to run, modify and propagate that work, subject to this License.  You are not responsible for enforcing compliance by third parties with this License.
+
+An "entity transaction" is a transaction transferring control of an organization, or substantially all assets of one, or subdividing an organization, or merging organizations.  If propagation of a covered work results from an entity transaction, each party to that transaction who receives a copy of the work also receives whatever licenses to the work the party's predecessor in interest had or could give under the previous paragraph, plus a right to possession of the Corresponding Source of the work from the predecessor in interest, if the predecessor has it or can get it with reasonable efforts.
+
+You may not impose any further restrictions on the exercise of the rights granted or affirmed under this License.  For example, you may not impose a license fee, royalty, or other charge for exercise of rights granted under this License, and you may not initiate litigation (including a cross-claim or counterclaim in a lawsuit) alleging that any patent claim is infringed by making, using, selling, offering for sale, or importing the Program or any portion of it.
+
+11. Patents.
+
+A "contributor" is a copyright holder who authorizes use under this License of the Program or a work on which the Program is based.  The work thus licensed is called the contributor's "contributor version".
+
+A contributor's "essential patent claims" are all patent claims owned or controlled by the contributor, whether already acquired or hereafter acquired, that would be infringed by some manner, permitted by this License, of making, using, or selling its contributor version, but do not include claims that would be infringed only as a consequence of further modification of the contributor version.  For purposes of this definition, "control" includes the right to grant patent sublicenses in a manner consistent with the requirements of this License.
+
+Each contributor grants you a non-exclusive, worldwide, royalty-free patent license under the contributor's essential patent claims, to make, use, sell, offer for sale, import and otherwise run, modify and propagate the contents of its contributor version.
+
+In the following three paragraphs, a "patent license" is any express agreement or commitment, however denominated, not to enforce a patent (such as an express permission to practice a patent or covenant not to sue for patent infringement).  To "grant" such a patent license to a party means to make such an agreement or commitment not to enforce a patent against the party.
+
+If you convey a covered work, knowingly relying on a patent license, and the Corresponding Source of the work is not available for anyone to copy, free of charge and under the terms of this License, through a publicly available network server or other readily accessible means, then you must either (1) cause the Corresponding Source to be so available, or (2) arrange to deprive yourself of the benefit of the patent license for this particular work, or (3) arrange, in a manner consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have actual knowledge that, but for the patent license, your conveying the covered work in a country, or your recipient's use of the covered work in a country, would infringe one or more identifiable patents in that country that you have reason to believe are valid.
+
+If, pursuant to or in connection with a single transaction or arrangement, you convey, or propagate by procuring conveyance of, a covered work, and grant a patent license to some of the parties receiving the covered work authorizing them to use, propagate, modify or convey a specific copy of the covered work, then the patent license you grant is automatically extended to all recipients of the covered work and works based on it.
+
+A patent license is "discriminatory" if it does not include within the scope of its coverage, prohibits the exercise of, or is conditioned on the non-exercise of one or more of the rights that are specifically granted under this License.  You may not convey a covered work if you are a party to an arrangement with a third party that is in the business of distributing software, under which you make payment to the third party based on the extent of your activity of conveying the work, and under which the third party grants, to any of the parties who would receive the covered work from you, a discriminatory patent license (a) in connection with copies of the covered work conveyed by you (or copies made from those copies), or (b) primarily for and in connection with specific products or compilations that contain the covered work, unless you entered into that arrangement, or that patent license was granted, prior to 28 March 2007.
+
+Nothing in this License shall be construed as excluding or limiting any implied license or other defenses to infringement that may otherwise be available to you under applicable patent law.
+
+12. No Surrender of Others' Freedom.
+
+If conditions are imposed on you (whether by court order, agreement or otherwise) that contradict the conditions of this License, they do not excuse you from the conditions of this License.  If you cannot convey a covered work so as to satisfy simultaneously your obligations under this License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you to collect a royalty for further conveying from those to whom you convey the Program, the only way you could satisfy both those terms and this License would be to refrain entirely from conveying the Program.
+
+13. Remote Network Interaction; Use with the GNU General Public License.
+
+Notwithstanding any other provision of this License, if you modify the Program, your modified version must prominently offer all users interacting with it remotely through a computer network (if your version supports such interaction) an opportunity to receive the Corresponding Source of your version by providing access to the Corresponding Source from a network server at no charge, through some standard or customary means of facilitating copying of software.  This Corresponding Source shall include the Corresponding Source for any work covered by version 3 of the GNU General Public License that is incorporated pursuant to the following paragraph.
+
+Notwithstanding any other provision of this License, you have permission to link or combine any covered work with a work licensed under version 3 of the GNU General Public License into a single combined work, and to convey the resulting work.  The terms of this License will continue to apply to the part which is the covered work, but the work with which it is combined will remain governed by version 3 of the GNU General Public License.
+
+14. Revised Versions of this License.
+
+The Free Software Foundation may publish revised and/or new versions of the GNU Affero General Public License from time to time.  Such new versions will be similar in spirit to the present version, but may differ in detail to address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program specifies that a certain numbered version of the GNU Affero General Public License "or any later version" applies to it, you have the option of following the terms and conditions either of that numbered version or of any later version published by the Free Software Foundation.  If the Program does not specify a version number of the GNU Affero General Public License, you may choose any version ever published by the Free Software Foundation.
+
+If the Program specifies that a proxy can decide which future versions of the GNU Affero General Public License can be used, that proxy's public statement of acceptance of a version permanently authorizes you to choose that version for the Program.
+
+Later license versions may give you additional or different permissions.  However, no additional obligations are imposed on any author or copyright holder as a result of your choosing to follow a later version.
+
+15. Disclaimer of Warranty.
+
+THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+16. Limitation of Liability.
+
+IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
+
+17. Interpretation of Sections 15 and 16.
+
+If the disclaimer of warranty and limitation of liability provided above cannot be given local legal effect according to their terms, reviewing courts shall apply local law that most closely approximates an absolute waiver of all civil liability in connection with the Program, unless a warranty or assumption of liability accompanies a copy of the Program in return for a fee.
+
+END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+If you develop a new program, and you want it to be of the greatest possible use to the public, the best way to achieve this is to make it free software which everyone can redistribute and change under these terms.
+
+To do so, attach the following notices to the program.  It is safest to attach them to the start of each source file to most effectively state the exclusion of warranty; and each file should have at least the "copyright" line and a pointer to where the full notice is found.
+
+     <one line to give the program's name and a brief idea of what it does.>
+     Copyright (C) <year>  <name of author>
+
+     This program is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
+
+     This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Affero General Public License for more details.
+
+     You should have received a copy of the GNU Affero General Public License along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+If your software can interact with users remotely through a computer network, you should also make sure that it provides a way for users to get its source.  For example, if your program is a web application, its interface could display a "Source" link that leads users to an archive of the code.  There are many ways you could offer source, and different solutions will be better for different programs; see section 13 for the specific requirements.
+
+You should also get your employer (if you work as a programmer) or school, if any, to sign a "copyright disclaimer" for the program, if necessary. For more information on this, and how to apply and follow the GNU AGPL, see <http://www.gnu.org/licenses/>.

Odysseus.spec

@@ -0,0 +1,45 @@
+# -*- mode: python ; coding: utf-8 -*-
+
+
+a = Analysis(
+    ['launcher.py'],
+    pathex=[],
+    binaries=[],
+    datas=[('static', 'static'), ('scripts', 'scripts'), ('mcp_servers', 'mcp_servers'), ('services/hwfit/data', 'services/hwfit/data'), ('config', 'config'), ('.env.example', '.env.example')],
+    hiddenimports=[],
+    hookspath=[],
+    hooksconfig={},
+    runtime_hooks=[],
+    excludes=[],
+    noarchive=False,
+    optimize=0,
+)
+pyz = PYZ(a.pure)
+
+exe = EXE(
+    pyz,
+    a.scripts,
+    [],
+    exclude_binaries=True,
+    name='Odysseus',
+    debug=False,
+    bootloader_ignore_signals=False,
+    strip=False,
+    upx=True,
+    console=False,
+    disable_windowed_traceback=False,
+    argv_emulation=False,
+    target_arch=None,
+    codesign_identity=None,
+    entitlements_file=None,
+    icon=['static\\icon.ico'],
+)
+coll = COLLECT(
+    exe,
+    a.binaries,
+    a.datas,
+    strip=False,
+    upx=True,
+    upx_exclude=[],
+    name='Odysseus',
+)

README.md

@@ -1,246 +1,76 @@
-# Odysseus
-───────────────────────────────────────────────
- ⊹ ࣪ ˖ ૮( ˶ᵔ ᵕ ᵔ˶ )っ  Odysseus vers. 1.0
-───────────────────────────────────────────────
+<p align="center">
+  <img src="docs/odysseus-wordmark.png" alt="Odysseus" width="238">
+</p>
 
-![Odysseus](docs/odysseus.jpg)
+<p align="center">
+  A self-hosted AI workspace for chat, agents, research, documents, email, notes, calendar, and local model workflows.
+</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.
+<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>
 
-## Features
-  - **Chat** -- chat with any local model or API; adding them is super simple.<br>　<sub>vLLM · llama.cpp · Ollama · OpenRouter · OpenAI</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>
+<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>
 
-## Demo
-A full, hover-to-play tour lives on the landing page (`docs/index.html`). A few looks:
+<p align="center">
+  <img src="docs/odysseus-browser.jpg" alt="Odysseus interface">
+</p>
 
-### 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)
+---
 
 ## Quick Start
 
-Defaults work out of the box — clone, run, configure inside the app.
-Open the **Settings** panel after first login to point Odysseus at your LLM
-server, search provider, email account, etc. Only touch `.env` if you need
-to override deployment-level things like `AUTH_ENABLED`, `DATABASE_URL`,
-or pre-seed `ODYSSEUS_ADMIN_PASSWORD` (otherwise an initial password is
-generated and printed on first boot).
+> `dev` is the default branch and gets the newest changes first. Use [`main`](https://github.com/odysseus-dev/odysseus/tree/main) if you want the more curated branch.
 
-Contributing? See [CONTRIBUTING.md](CONTRIBUTING.md) for setup, testing, and
-pull request guidelines.
-
-### Option 1: Docker (recommended)
 ```bash
-git clone https://github.com/pewdiepie-archdaemon/odysseus.git
+git clone https://github.com/odysseus-dev/odysseus.git
 cd odysseus
-cp .env.example .env       # optional, but recommended for explicit defaults
+cp .env.example .env
 docker compose up -d --build
 ```
-Compose starts Odysseus, ChromaDB, SearXNG, and ntfy. First run does a full
-image build. Open `http://localhost:7000` after the containers are healthy.
 
-Cookbook remote servers use an Odysseus-owned SSH key from `./data/ssh`
-inside Docker. In **Cookbook -> Settings -> Servers**, generate/copy the
-public key and add it to the remote server's `~/.ssh/authorized_keys`.
-After generating the key, you can also install it from the host with:
-```bash
-ssh-copy-id -i data/ssh/id_ed25519.pub user@server
-```
-Cookbook local downloads are stored in `./data/huggingface`, mounted as
-`~/.cache/huggingface` inside the Odysseus container.
+Open `http://localhost:7000` when the containers are healthy. The first admin password is printed in `docker compose logs odysseus`.
 
-Useful checks:
-```bash
-docker compose ps
-docker compose logs --tail=120 odysseus
-docker compose logs odysseus | grep -E 'ChromaDB|MemoryVectorStore|DEGRADED'
-docker compose exec odysseus python -c "from services.hwfit.models import get_models; print(len(get_models()))"
-```
+Native installs, GPU notes, Windows/macOS instructions, HTTPS, and configuration live in the [setup guide](docs/setup.md).
 
-Expected vector-memory startup lines in Docker:
-```text
-ChromaDB connected: chromadb:8000
-MemoryVectorStore initialized
-```
+## Features
 
-The Cookbook model catalog check should print a non-zero count. If it prints
-`0`, rebuild the Odysseus image with `docker compose build --no-cache odysseus`.
+- **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.
 
-### Option 2: Manual install — Linux / macOS
-**Requirements:** Python 3.11+. On Linux/Termux, Cookbook also requires `tmux`
-for background model downloads and serves.
+## Demo
 
-Install system packages first:
-```bash
-# Debian/Ubuntu
-sudo apt install tmux
-
-# Arch
-sudo pacman -S tmux
-
-# Fedora
-sudo dnf install tmux
-```
-
-Then install Odysseus:
-```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            # creates data dirs and prints an initial admin password
-python -m uvicorn app:app --host 0.0.0.0 --port 7000
-```
-
-### Option 3: Manual install — Windows (PowerShell)
-Windows support is not actively tested. Use it with caution; Docker on Linux
-or a Linux/macOS manual install is the safer path for now.
-
-```powershell
-git clone https://github.com/pewdiepie-archdaemon/odysseus.git
-cd odysseus
-python -m venv venv
-venv\Scripts\Activate.ps1
-pip install -r requirements.txt
-python setup.py
-python -m uvicorn app:app --host 0.0.0.0 --port 7000
-```
-
-Open `http://localhost:7000`, log in with the generated admin password,
-and configure everything else inside **Settings**.
-
-## 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.
-- Do not expose it directly to the public internet without HTTPS and a trusted reverse proxy.
-- Keep `data/`, `.env`, logs, databases, and uploaded/generated media out of Git. 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.
-- Before publishing a fork, run `git status --short` and confirm no private files from `.env`, `data/`, `logs/`, uploads, backups, or local databases are staged.
-
-### Putting it behind HTTPS
-Odysseus serves plain HTTP on its port. That's fine for `localhost` and trusted LAN/VPN use, but browsers will warn ("Password fields present on an insecure page") and the login + API tokens travel in cleartext. For anything reachable outside your machine — including a Tailscale IP shared with other devices — put a TLS-terminating reverse proxy in front.
-
-Shortest path with [Caddy](https://caddyserver.com/) (auto-renews Let's Encrypt certs):
-
-```caddy
-odysseus.example.com {
-  reverse_proxy localhost:7000
-}
-```
-
-For a LAN-only Tailscale deployment, Caddy + [tailscale-cert](https://caddyserver.com/docs/caddyfile/options#auto-https) or the built-in MagicDNS HTTPS feature both work. nginx/Traefik configs are similar — proxy `localhost:7000`, terminate TLS at the proxy. Once that's in place, the browser warning goes away and your login is encrypted.
+A full hover-to-play tour lives on the landing page: [`docs/index.html`](docs/index.html).
 
 ## 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.
 
-## 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:
+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).
 
-| 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. |
-| `AUTH_ENABLED` | `true` | Enable/disable login |
-| `LOCALHOST_BYPASS` | `false` | Development-only auth bypass for loopback requests. Keep false for shared/network deployments. |
-| `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 |
+## Security
 
-### Bundled services
-Docker Compose includes these by default. The bundled service ports bind to `127.0.0.1` unless you opt in to a different bind address in `.env`, so they are reachable from the host machine but not from your LAN or the public internet by default:
+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).
 
-  - **ChromaDB** → vector store for semantic memory. In Docker, Odysseus connects to `chromadb:8000`; from the host it is exposed as `${CHROMADB_BIND:-127.0.0.1}:8100`.
-  - **SearXNG** → meta search for web search. In Docker, Odysseus connects to `searxng:8080`; from the host it is exposed as `127.0.0.1:8080`.
-  - **ntfy** → local notification service, exposed as `${NTFY_BIND:-127.0.0.1}:8091`.
+## Star History
 
-**Phone push notifications via ntfy:** A phone cannot subscribe to `127.0.0.1` on your server. To expose ntfy safely without opening it on every interface:
-
-  - **Tailscale (recommended)** — set `NTFY_BIND=<tailscale-host-ip>` and `NTFY_BASE_URL=http://<tailscale-host-ip>:8091` in `.env`, recreate ntfy, then point the ntfy Android/iOS app at `http://<tailscale-host-ip>:8091/<your-topic>`.
-  - **Enable ntfy auth and bind to LAN** — add `NTFY_AUTH_FILE` + `NTFY_AUTH_DEFAULT_ACCESS=deny-all` to the `ntfy` service, create a user with `docker compose exec ntfy ntfy user add ...`, then set `NTFY_BIND` to your LAN IP. See the [ntfy docs](https://docs.ntfy.sh/config/#access-control).
-
-### Optional external services
-  - **Ollama** → local LLM server -- [ollama.ai](https://ollama.ai)
-
-### Ollama with Docker
-If Odysseus is running in Docker and Ollama is running on the host, add the endpoint in Settings as:
-
-`http://host.docker.internal:11434/v1`
-
-The default Compose file already maps `host.docker.internal` on Linux. Ollama also needs to listen outside its own loopback interface:
-
-```bash
-OLLAMA_HOST=0.0.0.0:11434 ollama serve
-```
-
-For a systemd Ollama install, set that in the Ollama service override. If Odysseus can see Ollama but requests hang or fail, check that your host firewall allows Docker bridge traffic to port `11434`.
-
-First-token latency is usually Ollama/model/hardware, not Odysseus. To compare, test Ollama directly:
-
-```bash
-curl http://127.0.0.1:11434/v1/models
-```
-
-## 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`.
+<a href="https://www.star-history.com/?repos=odysseus-dev%2Fodysseus&type=date&legend=top-left">
+ <picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/chart?repos=odysseus-dev/odysseus&type=date&theme=dark&legend=top-left" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/chart?repos=odysseus-dev/odysseus&type=date&legend=top-left" />
+   <img alt="Star History Chart" src="https://api.star-history.com/chart?repos=odysseus-dev/odysseus&type=date&legend=top-left" />
+ </picture>
+</a>
 
 ## License
-MIT -- see [LICENSE](LICENSE) and [ACKNOWLEDGMENTS.md](ACKNOWLEDGMENTS.md).
 
-```
-                                  |
-                                 |||
-                                |||||
-                  |    |    |   |||||||
-                 )_)  )_)  )_)   ~|~
-                )___))___))___)\  |
-               )____)____)_____)\\|
-             _____|____|____|_____\\\__
-             \                       /
-       ~^~^~~^~^~~^~^~~^~^~~^~^~~^~^~~^~^~~^~^~
-               ~^~  all aboard!  ~^~
-       ~^~^~~^~^~~^~^~~^~^~~^~^~~^~^~~^~^~~^~^~
-```
+AGPL-3.0-or-later -- see [LICENSE](LICENSE) and [ACKNOWLEDGMENTS.md](ACKNOWLEDGMENTS.md).

ROADMAP.md

@@ -1,6 +1,6 @@
 # Roadmap / Help Wanted
 
-Odysseus is on a voyage, but not home yet. It works great for me (lol), but this is ship is moving fast and feedback/help would be appreciated! (I dont know what I'm doing hlep).
+Odysseus is on a voyage, but not home yet. It works great for me (lol), but this ship is moving fast and feedback/help would be appreciated! (I don't know what I'm doing, help).
 
 If you see weird CSS, strange layout behavior, or a suspiciously murky corner of
 the codebase, you are probably right to stay away.
@@ -8,25 +8,67 @@ the codebase, you are probably right to stay away.
 ## High Priority
 
 - SQUASH BUGS
-- Fresh Docker install smoke tests on Linux, macOS, and Windows!!
+- Fresh install smoke tests on Linux, macOS, and Windows. Docker, native Python,
+  and WSL all need coverage.
 
 - Integration audit: do integrations even work? Confirm what works, what needs setup docs, and what should be removed or hidden. 
-- Self-host troubleshooting cookbook. Document the weird 30-second fixes that otherwise become 30-minute searches: Dovecot cleartext auth for local stacks, ntfy Android Instant Delivery for non-ntfy.sh servers, clipboard limits on plain-HTTP Tailscale URLs, Radicale collection URLs, and similar traps.
 - Cookbook reliability on other computers. This is probably the area most likely to need work across different machines, GPUs, drivers, shells, and Python environments.
-- Tile/window management correctness. I had to brute force my way a bit here, I'm aware, popups, dropdowns, and fixed-position UI inside transformed modals can land in the wrong place.
-- Esc button, it's small but a lot of windows that arent still close on esc and alot of them doesnt. 
-- Skill audit, how does your model respond to skill injection, does it follow? Does its parsing miss? 
+- Cookbook SGLang support across platforms. Make sure SGLang setup/serve works
+  predictably on Linux, Windows/WSL, macOS where possible, Docker, and common
+  NVIDIA/AMD hardware paths.
+- Deep Research model presets by hardware. Recommend approved model/parameter
+  profiles for small, medium, and large local setups so people with different
+  hardware can use Deep Research without guessing. Surface this either in Deep
+  Research settings or as a Cookbook scan/dropdown suggestion.
+- Cookbook model scan/download ranking. Prioritize newer architectures and
+  better hardware-fit models instead of scoring everything almost the same.
+  Ranking should account for architecture age, quant format, VRAM/RAM fit,
+  backend support, vision/mmproj requirements, and likely serve reliability.
+- Cookbook error feedback and logging. Failed downloads, dependency installs,
+  preflights, and serve jobs should show the actual command/output/error in the
+  UI, with copyable logs and clear next steps instead of just "crashed".
+- Agent prompt/context bloat. Agent mode is too heavy for smaller local models:
+  tool schemas, skills, memory, documents, and instructions can eat the context
+  before the user request really starts. We need slimmer prompts, better tool
+  selection, smaller default tool sets, and clearer guidance for models with
+  4k/8k/16k context windows.
+- Local model speculative decoding support. For Odysseus-tuned local models,
+  plan to ship or recommend a small same-tokenizer draft model when the serving
+  backend supports it. Early vLLM testing showed a generic `Qwen3-0.6B` draft
+  beside `Qwen3-8B` can materially reduce wall time, while an unsupported
+  DSpark conversion performed poorly. Treat this as a supported draft-model lane
+  first; keep MTP-specific packaging as future work only when the architecture
+  and runtime support are real. Judge this by time-to-success, tool correctness,
+  grammar, and unchanged target output, not tokens/sec alone.
+- Skill/tool prompt-injection audit. User-editable skills, notes, documents,
+  fetched pages, and memories should be treated as untrusted data. Keep testing
+  whether models follow malicious instructions from those surfaces.
 - Better degraded-state reporting for ChromaDB, SearXNG, email, ntfy, and provider probes.
+- Email performance audit. Fetching, searching, opening, deleting, and sending
+  email can feel slow, especially over IMAP/SMTP providers with high latency.
+  Need someone who knows mail performance to profile the current flow, identify
+  whether the bottleneck is IMAP folder select/fetch, cache invalidation,
+  attachment/body loading, SMTP handshakes, or frontend refresh behavior, then
+  propose safer caching/prefetch/batching without breaking multi-account state.
 - Provider setup/probing audit for Anthropic, Gemini, Groq, xAI, OpenRouter, OpenAI, and DeepSeek.
 
 ## Refactor Targets
 - CSS cleanup. `static/style.css` basically Calypso's island atm.
 - Tour core helper. The onboarding tours have too much copy-pasted scaffolding; promote a shared `tour-core.js` helper before adding more tours.
+- Modal/window positioning cleanup. Some window controls have improved, but the
+  underlying popup/dropdown/fixed-position behavior is still too fragile.
 - Mobile media override discoverability. A lot of "CSS did not move" bugs are mobile `@media` overrides of the same selector; comments or linting around desktop/mobile paired rules would help.
 - Dead code pass for old routes, stale feature flags, and unused UI states.
 
 ## Frontend
 
+- Expand the Editor for quicker, more robust everyday use. Better file/document
+  handling, smoother window behavior, clearer save/export flows, stronger image
+  editing affordances, and fewer brittle edge cases.
+- Better AI integration for Notes and Todos. Notes should be easier for the
+  agent to read, update, summarize, and turn into actions. Todos should be
+  assignable to an agent from the UI, possibly through a button, task action,
+  or dedicated skill/tool flow.
 - Mobile gallery/editor polish. Easier to launch/download inpaint model or any missing pieces.
 - Accessibility pass: keyboard navigation, focus states, contrast, reduced motion.
 - Improve empty states and error messages on fresh installs.

SECURITY.md

@@ -8,16 +8,20 @@ Security fixes are handled on the default branch until formal releases are cut.
 
 ## Deployment Guidance
 
-- Keep `AUTH_ENABLED=true`.
+- Keep `AUTH_ENABLED=true` for any network-accessible deployment.
+- Keep `LOCALHOST_BYPASS=false` outside local development.
+- Set `SECURE_COOKIES=true` when Odysseus is served through HTTPS by a trusted reverse proxy or private access gateway.
 - Use HTTPS when exposing the app beyond localhost.
-- Put the app behind a trusted reverse proxy or private network.
-- Protect `.env`, `data/`, logs, uploaded files, generated media, and database files.
+- Put the authenticated Odysseus web/API entrypoint behind a trusted reverse proxy or private access layer such as Cloudflare Access, Tailscale, or a VPN.
+- Keep ChromaDB, SearXNG, ntfy, Ollama, vLLM, llama.cpp, databases, and raw model/provider APIs internal-only.
+- Protect `.env`, `data/`, `logs/`, uploads, generated media, backups, auth/session files, database files, API keys, and model/provider tokens.
 - Disable open signup unless you intentionally want new accounts.
 - Keep demo/test users non-admin, and remove them entirely on serious deployments.
 - Give admin accounts strong passwords and enable 2FA where possible.
 - Leave high-risk agent tools restricted to admins: shell, Python, file read/write, email send/read, MCP, app API, task/skill/memory management, settings, tokens, and model serving.
 - Rotate API keys, webhook secrets, and Odysseus API tokens if they appear in logs, screenshots, demos, or shared chats.
 - Treat shell, model-serving, MCP, email, calendar, and vault features as privileged admin functionality.
+- Common internal-only ports are Odysseus `7000`, SearXNG `8080`, ntfy `8091`, ChromaDB `8100`, Ollama `11434`, and local model/provider APIs such as `8000-8020`.
 
 ## Publishing A Fork
 
@@ -29,7 +33,7 @@ git check-ignore -v .env data/auth.json data/app.db logs/compound.log odysseus.d
 git grep -n -I -E "(sk-[A-Za-z0-9_-]{20,}|xox[baprs]-|AIza[0-9A-Za-z_-]{20,}|Bearer [A-Za-z0-9._~+/-]{20,})" -- . ':!static/lib/**' ':!package-lock.json'
 ```
 
-Only `.env.example`, docs, source, tests, and static assets should be committed. Never commit live `data/` contents, local databases, uploaded files, generated media, logs, backups, API keys, password hashes, or personal documents.
+Only `.env.example`, docs, source, tests, and static assets should be committed. Never commit live `.env` values, `data/` contents, local databases, uploaded files, generated media, logs, backups, auth/session files, API keys, model/provider tokens, password hashes, or personal documents.
 
 ## Reporting
 

THREAT_MODEL.md

@@ -0,0 +1,81 @@
+# Threat Model
+
+Odysseus is a **self-hosted AI workspace with privileged local access**. This document states the trust boundary so contributors can reason about security decisions without reading through the full auth and middleware stack.
+
+## Trust Boundary
+
+Odysseus is designed for **trusted users on a private network**, not public exposure. The README describes it as "treat it like an admin console" — that framing is accurate. A logged-in admin can execute shell commands, read and write files, send email, and control model serving. This is intentional. The threat model does not try to prevent admins from doing these things. It does try to prevent:
+
+- Unauthenticated access
+- Non-admins reaching admin-only capabilities
+- The AI agent acting on instructions injected through untrusted content (web results, emails, fetched pages, memories)
+- Internal services (ChromaDB, Ollama, SearXNG, etc.) being reachable from outside the host
+
+## Roles and Capabilities
+
+| Capability | Admin | Non-admin (default) |
+|---|---|---|
+| Chat with agent | ✓ | ✓ |
+| Browser tool | ✓ | ✓ |
+| Documents | ✓ | ✓ |
+| Research mode | ✓ | ✓ |
+| Image generation | ✓ | ✓ |
+| Memory management | ✓ | ✓ |
+| Shell / Python execution | ✓ | ✗ |
+| File read / write | ✓ | ✗ |
+| Email send / read | ✓ | ✗ |
+| MCP tools | ✓ | ✗ |
+| Calendar management | ✓ | ✗ |
+| Token / webhook management | ✓ | ✗ |
+| Model serving | ✓ | ✗ |
+| Vault | ✓ | ✗ |
+| Settings | ✓ | ✗ |
+
+Non-admin defaults are in `core/auth.py:DEFAULT_PRIVILEGES`. Tool enforcement is in `src/tool_security.py:NON_ADMIN_BLOCKED_TOOLS`. Any tool whose name starts with `mcp__` is also blocked for non-admins. Admins always get full access regardless of stored privilege values.
+
+## Authentication
+
+- **Sessions:** bcrypt passwords, 7-day session tokens stored atomically in `data/sessions.json` via `core/atomic_io.py`.
+- **2FA:** TOTP with 8 single-use backup codes. Verified after password check, before session issuance.
+- **Reserved usernames:** `internal-tool`, `api`, `demo`, `system` cannot be registered or renamed into. Defined in `core/auth.py:RESERVED_USERNAMES`.
+  - `internal-tool` is security-critical: `core/middleware.py:require_admin` treats any request where `request.state.current_user == "internal-tool"` as the in-process tool loopback and grants admin unconditionally. A real account with that name would silently pass every `require_admin` check.
+- **Orphan sessions:** `validate_token` re-checks that the user record still exists on every call. A deleted user's cookie is dropped on next request rather than continuing to authenticate.
+
+## Internal Tool Loopback
+
+Agent tool calls reach admin-gated HTTP routes over an in-process HTTP loopback. The mechanism:
+
+1. At app startup, `core/middleware.py` generates a random `INTERNAL_TOOL_TOKEN` via `secrets.token_hex(32)`. It is never persisted and never sent to clients.
+2. Loopback requests carry `X-Odysseus-Internal-Token: <token>` or have `request.state.current_user` already set to `"internal-tool"` by the auth middleware.
+3. `require_admin` recognises either signal and grants access without checking the session user.
+
+The agent may be running in a non-admin user's session, but tool dispatch first calls `src/tool_security.py:owner_is_admin_or_single_user` to verify the session owner is an admin before issuing any loopback call. Non-admin users cannot invoke admin tools even via the agent.
+
+## Prompt-Injection Hardening
+
+External content that reaches the LLM is treated as untrusted via `src/prompt_security.py`:
+
+- `untrusted_context_message(label, content)` wraps the content in a `user`-role message with a header block instructing the model not to follow instructions inside it. Content goes in as data, not as a system instruction.
+- `UNTRUSTED_CONTEXT_POLICY` is a system-prompt preamble that states the same policy at the top of every session where untrusted data may appear.
+
+**Untrusted surfaces that must go through this wrapper:** web search results, fetched URLs, emails (read), saved memories, skill text, notes, and any tool output sourced from outside the server. Injecting untrusted content directly into the system role is a security bug.
+
+## Security Headers
+
+`core/middleware.py:SecurityHeadersMiddleware` sets headers on every response:
+
+- `X-Frame-Options: DENY` + `frame-ancestors 'none'` on all routes except tool-render iframes (which are sandboxed at the HTML level).
+- `X-Content-Type-Options: nosniff` and `Referrer-Policy: no-referrer` everywhere.
+- **CSP:** nonce-based `script-src 'self' 'nonce-{nonce}' https://cdn.jsdelivr.net`. `style-src 'unsafe-inline'` is intentionally kept — `static/index.html` ships inline `<style>` blocks and JS modules set `style=""` attributes at runtime. Inline styles do not execute script so the risk is visual-only. Removing this requires templating the HTML files and auditing all JS-set style attributes.
+
+## Known Gaps
+
+These are open, acknowledged, and contributor help is welcome:
+
+1. **No shell/filesystem sandbox.** The agent `bash` and `read_file`/`write_file` tools run as the app process user with no network egress filtering or filesystem confinement. A successful prompt-injection reaching a shell-enabled admin session can make outbound requests to internal services. See #1058 for the sandbox proposal.
+
+2. **SSRF via `/api/v1/chat` `base_url` parameter.** A chat-scoped API token can supply an arbitrary `base_url`; the server forwards the LLM request to that host without validating the scheme or address. PR #1039 fixes this.
+
+3. **`src/search/` partial consolidation.** `src.search.core` and `src.search.providers` correctly alias `services.search` via `sys.modules` replacement. `analytics`, `cache`, `content`, `query`, and `ranking` are still independent copies that can drift. The SSRF regression tests in `tests/test_webhook_ssrf_resilience.py` test `src.webhook_manager` directly (separate from search), so the safety net there is intact. See #1058.
+
+4. **Token scopes are coarse.** There is no way to grant a session a subset of the owning user's privileges. Companion/mobile tokens carry either `chat` or `admin` scope with no per-capability granularity.

app.py

@@ -1,28 +1,74 @@
 # app.py — slim orchestrator
-from dotenv import load_dotenv
-load_dotenv()
+import mimetypes
 import os
-import uuid
+import sys
+import asyncio
+import time
+
+# On Windows, asyncio.create_subprocess_exec/shell require the ProactorEventLoop.
+# When started via `python -m uvicorn` from a terminal, uvicorn sets this
+# automatically. But the VS Code debugger (and other non-uvicorn entrypoints)
+# use the default SelectorEventLoop, which raises NotImplementedError on any
+# subprocess call. Force ProactorEventLoop here so the right loop is always
+# used, regardless of how the process is launched.
+if sys.platform == "win32":
+    asyncio.set_event_loop_policy(asyncio.WindowsProactorEventLoopPolicy())
+
+
+def register_static_mime_types() -> None:
+    """Force stable JS module MIME types across platforms.
+
+    Some native Windows setups inherit stale/incorrect registry mappings for
+    ``.js``/``.mjs``, which can make Starlette serve ES modules with a non-JS
+    ``Content-Type`` and cause the UI to load but fail on click. Re-register the
+    standard MIME types at startup so static assets are served consistently.
+    """
+
+    mimetypes.add_type("text/javascript", ".js")
+    mimetypes.add_type("application/javascript", ".mjs")
+
+
+register_static_mime_types()
+
+# Windows: force HuggingFace/fastembed to COPY model files instead of symlinking.
+# On a network-share/UNC data dir Windows can't follow HF's symlinks ([WinError
+# 1463]), so the ONNX embedding model fails to load. huggingface_hub reads this
+# at import time, so set it before anything pulls it in. (Mirrored in
+# src/embeddings.py for non-server entrypoints.)
+if os.name == "nt":
+    os.environ.setdefault("HF_HUB_DISABLE_SYMLINKS", "1")
+    os.environ.setdefault("HF_HUB_DISABLE_SYMLINKS_WARNING", "1")
+
+from dotenv import load_dotenv
+# encoding="utf-8-sig" tolerates a UTF-8 BOM in .env — a common Windows gotcha
+# when the file is saved from Notepad. Without this, the first key parses as
+# "AUTH_ENABLED" instead of "AUTH_ENABLED", so AUTH_ENABLED=false (etc.)
+# is silently ignored and the user is unexpectedly forced to log in (issue #142).
+# utf-8-sig reads plain UTF-8 (no BOM) identically, so this is safe everywhere.
+load_dotenv(encoding="utf-8-sig")
 
 import asyncio
 import logging
-from datetime import datetime
+import secrets
+from datetime import datetime, timezone
 from typing import Dict
 
+from contextlib import asynccontextmanager
 from fastapi import FastAPI, Request, HTTPException
-from fastapi.responses import JSONResponse, FileResponse, HTMLResponse
+from fastapi.responses import JSONResponse, FileResponse
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.staticfiles import StaticFiles
 from starlette.middleware.base import BaseHTTPMiddleware
+from starlette.middleware.gzip import GZipMiddleware
 
 # Core imports
 from core.constants import (
     BASE_DIR, STATIC_DIR, SESSIONS_FILE,
-    REQUEST_TIMEOUT, OPENAI_API_KEY,
+    REQUEST_TIMEOUT, OPENAI_API_KEY, AUTH_FILE,
 )
 from core.database import SessionLocal, ApiToken
-from core.middleware import SecurityHeadersMiddleware
-from core.auth import AuthManager
+from core.middleware import SecurityHeadersMiddleware, is_cors_preflight
+from core.auth import AuthManager, normalize_known_username
 from core.exceptions import (
     SessionNotFoundError, InvalidFileUploadError,
     LLMServiceError, WebSearchError,
@@ -30,17 +76,48 @@ from core.exceptions import (
 
 import bcrypt as _bcrypt
 
-from src.app_helpers import abs_join
+from src.app_helpers import abs_join, serve_html_with_nonce
+from src.generated_images import GENERATED_IMAGE_HEADERS, resolve_generated_image_path
 from starlette.responses import RedirectResponse
 
 # ========= LOGGING =========
-logging.basicConfig(
-    level=logging.INFO,
-    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
-)
+import logging.handlers
+from core.constants import DATA_DIR
+
+_root_logger = logging.getLogger()
+_root_logger.setLevel(logging.INFO)
+_formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+
+# Clear existing handlers to avoid duplicates
+for _h in list(_root_logger.handlers):
+    _root_logger.removeHandler(_h)
+
+_console_h = logging.StreamHandler()
+_console_h.setFormatter(_formatter)
+_root_logger.addHandler(_console_h)
+
+try:
+    _log_dir = os.path.join(DATA_DIR, "logs")
+    os.makedirs(_log_dir, exist_ok=True)
+    _log_file = os.path.join(_log_dir, "app.log")
+
+    # RotatingFileHandler is not multi-process safe (e.g. if uvicorn is run with --workers N).
+    # Odysseus is single-process by convention, so this is acceptable, but be aware that
+    # concurrent log rotation issues can arise if multiple workers are configured.
+    _file_h = logging.handlers.RotatingFileHandler(
+        _log_file, maxBytes=5 * 1024 * 1024, backupCount=3, encoding="utf-8"
+    )
+    _file_h.setFormatter(_formatter)
+    _root_logger.addHandler(_file_h)
+except Exception as e:
+    _root_logger.warning(f"Failed to initialize file logging handler (falling back to console-only): {e}")
+
 logger = logging.getLogger(__name__)
 
 # ========= APP =========
+# Lifespan is defined below (after all helpers it references are in scope)
+# and passed to FastAPI so we can use the modern context-manager lifecycle
+# instead of the deprecated @app.on_event("startup"/"shutdown") decorators.
 app = FastAPI(
     title="AI Chat Application",
     description="Comprehensive AI chat with memory, research, and multi-modal capabilities",
@@ -48,12 +125,13 @@ app = FastAPI(
 )
 
 # ========= CORS =========
+CORS_ALLOW_METHODS = ["GET", "POST", "PUT", "PATCH", "DELETE"]
 allowed_origins = os.getenv("ALLOWED_ORIGINS", "http://localhost,http://127.0.0.1").split(",")
 app.add_middleware(
     CORSMiddleware,
     allow_origins=allowed_origins,
     allow_credentials=True,
-    allow_methods=["GET", "POST", "PUT", "DELETE"],
+    allow_methods=CORS_ALLOW_METHODS,
     allow_headers=[
         "Accept",
         "Authorization",
@@ -67,6 +145,16 @@ app.add_middleware(
     ],
 )
 
+# ========= RESPONSE COMPRESSION (gzip) =========
+# The frontend's text assets (style.css, index.html, the JS bundles) shipped
+# uncompressed on every cold load. gzip cuts CSS/JS/HTML by ~75-85% on the wire
+# with no behavioural change. Starlette's GZipMiddleware excludes
+# `text/event-stream` by default, so the SSE streams (chat, shell, research,
+# model-probe — all served with media_type="text/event-stream") are never
+# compressed or buffered; only complete bodies over minimum_size are. The
+# security-header middleware composes cleanly on top.
+app.add_middleware(GZipMiddleware, minimum_size=1024, compresslevel=6)
+
 # ========= SECURITY HEADERS MIDDLEWARE =========
 app.add_middleware(SecurityHeadersMiddleware)
 
@@ -92,6 +180,7 @@ _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
 )
 
 
@@ -109,7 +198,50 @@ class _RequestTimeoutMiddleware(_BaseHTTPMiddleware):
             )
 
 
+class _InteractiveActivityMiddleware(_BaseHTTPMiddleware):
+    async def dispatch(self, request, call_next):
+        from src.interactive_gate import should_track_interactive_request, track_interactive_request
+
+        path = request.url.path or ""
+        if not should_track_interactive_request(path, request.method):
+            return await call_next(request)
+        async def _stop_background():
+            try:
+                await task_scheduler.stop_background_tasks_for_foreground(reason=f"foreground request {request.method} {path}")
+            except Exception:
+                logging.getLogger("app.foreground_gate").debug("foreground task stop failed", exc_info=True)
+        asyncio.create_task(_stop_background())
+        async with track_interactive_request(path, request.method):
+            return await call_next(request)
+
+
+class _SlowRequestLogMiddleware(_BaseHTTPMiddleware):
+    async def dispatch(self, request, call_next):
+        start = time.perf_counter()
+        status = 500
+        try:
+            response = await call_next(request)
+            status = getattr(response, "status_code", 0) or 0
+            return response
+        finally:
+            elapsed = time.perf_counter() - start
+            try:
+                threshold = float(os.getenv("ODYSSEUS_SLOW_REQUEST_LOG_SECONDS", "0.75") or "0.75")
+            except Exception:
+                threshold = 0.75
+            if elapsed >= threshold:
+                logging.getLogger("app.slow_request").warning(
+                    "slow_request method=%s path=%s status=%s elapsed=%.3fs",
+                    request.method,
+                    request.url.path,
+                    status,
+                    elapsed,
+                )
+
+
 app.add_middleware(_RequestTimeoutMiddleware)
+app.add_middleware(_InteractiveActivityMiddleware)
+app.add_middleware(_SlowRequestLogMiddleware)
 
 # ========= AUTH =========
 from routes.auth_routes import setup_auth_routes, SESSION_COOKIE
@@ -118,6 +250,8 @@ auth_manager = AuthManager()
 app.state.auth_manager = auth_manager
 AUTH_ENABLED = os.getenv("AUTH_ENABLED", "true").lower() != "false"
 LOCALHOST_BYPASS = os.getenv("LOCALHOST_BYPASS", "false").lower() == "true"
+if LOCALHOST_BYPASS:
+    logger.warning("LOCALHOST_BYPASS is enabled, loopback requests bypass authentication. Do not expose this instance to a network.")
 
 if AUTH_ENABLED:
     AUTH_EXEMPT_EXACT = {
@@ -134,9 +268,25 @@ if AUTH_ENABLED:
         "/login",
     }
     AUTH_EXEMPT_PREFIXES = ["/static"]
+    # Dynamic paths whose own handler proves identity via a path-embedded
+    # secret instead of the session/bearer auth. The route handler at
+    # routes/task_routes.py validates the per-task `webhook_token` itself
+    # and returns 404 on mismatch, so the path is the credential — the
+    # UI labels these URLs "no auth needed" precisely because external
+    # callers (Zapier, n8n, curl) can't supply a session cookie. Without
+    # this exemption AuthMiddleware rejects every POST with 401 before
+    # the token is ever checked.
+    import re as _re
+    AUTH_EXEMPT_PATTERNS = [
+        _re.compile(r"^/api/tasks/[^/]+/webhook/[^/]+/?$"),
+    ]
 
     def _is_auth_exempt(path: str) -> bool:
-        return path in AUTH_EXEMPT_EXACT or any(path.startswith(p) for p in AUTH_EXEMPT_PREFIXES)
+        if path in AUTH_EXEMPT_EXACT:
+            return True
+        if any(path.startswith(p) for p in AUTH_EXEMPT_PREFIXES):
+            return True
+        return any(p.match(path) for p in AUTH_EXEMPT_PATTERNS)
 
     # In-memory token cache: prefix → list[(token_id, token_hash, owner, scopes)]. The DB
     # query was running on every API-bearer request and scanning bcrypt
@@ -162,17 +312,59 @@ if AUTH_ENABLED:
         try:
             rows = db.query(ApiToken).filter(ApiToken.is_active == True).all()
             for r in rows:
+                owner_key = normalize_known_username(auth_manager.users, getattr(r, "owner", None))
+                if not owner_key:
+                    logger.warning(
+                        "Ignoring active API token '%s' for unknown auth user '%s'",
+                        getattr(r, "id", ""),
+                        getattr(r, "owner", None),
+                    )
+                    continue
                 scopes = [s.strip() for s in (getattr(r, "scopes", "") or "chat").split(",") if s.strip()]
-                new_map[r.token_prefix].append((r.id, r.token_hash, getattr(r, "owner", None), scopes))
+                new_map[r.token_prefix].append((r.id, r.token_hash, owner_key, scopes))
         finally:
             db.close()
         _token_cache.clear()
         _token_cache.update(new_map)
         app.state._token_cache_dirty = False
 
+    # Headers that prove a request was forwarded by a proxy/tunnel (cloudflared,
+    # nginx, Caddy, Tailscale Funnel, …). cloudflared connects to the app FROM
+    # 127.0.0.1, so without this check every tunneled request would look like
+    # loopback and could bypass auth.
+    _PROXY_FWD_HEADERS = (
+        "cf-connecting-ip", "cf-ray", "cf-visitor",
+        "x-forwarded-for", "x-forwarded-host", "x-real-ip", "forwarded",
+    )
+
+    def _is_trusted_loopback(request: Request) -> bool:
+        """True ONLY for a DIRECT loopback connection with no proxy/tunnel
+        forwarding headers. A bare ``client.host in ('127.0.0.1','::1')`` check is
+        unsafe behind a Cloudflare tunnel / reverse proxy: those connect from
+        loopback, so a remote visitor would otherwise inherit local trust and
+        slip past LOCALHOST_BYPASS or spoof the internal-tool path. Odysseus's own
+        in-process agent loopback calls carry none of these headers, so they still
+        qualify."""
+        host = request.client.host if request.client else None
+        if host not in ("127.0.0.1", "::1"):
+            return False
+        for _h in _PROXY_FWD_HEADERS:
+            if request.headers.get(_h):
+                return False
+        return True
+
     class AuthMiddleware(BaseHTTPMiddleware):
         async def dispatch(self, request: Request, call_next):
             path = request.url.path
+            # A genuine CORS preflight (OPTIONS + Access-Control-Request-Method)
+            # carries no credentials by design and must reach CORSMiddleware to be
+            # answered. AuthMiddleware is the outermost middleware, so gating the
+            # preflight on auth 401s it before CORS can respond -- which blocks
+            # every cross-origin browser/WebView client before the real request
+            # is sent. Let real preflights through (only OPTIONS w/ the ACRM
+            # header; never a credentialed request).
+            if is_cors_preflight(request.method, request.headers):
+                return await call_next(request)
             if _is_auth_exempt(path):
                 return await call_next(request)
             # In-process internal-tool token bypass. Used by the agent
@@ -180,28 +372,30 @@ if AUTH_ENABLED:
             # (no admin cookie available in that context). Restricted to
             # loopback clients + matching token to keep it locked down.
             try:
-                from core.middleware import INTERNAL_TOOL_HEADER, INTERNAL_TOOL_TOKEN as _ITT
+                from core.middleware import INTERNAL_TOOL_HEADER, INTERNAL_TOOL_TOKEN as _ITT, INTERNAL_TOOL_USER
                 _hdr = request.headers.get(INTERNAL_TOOL_HEADER)
-                _client_host = request.client.host if request.client else None
-                if _hdr and _hdr == _ITT and _client_host in ("127.0.0.1", "::1"):
+                if _hdr and secrets.compare_digest(_hdr, _ITT) and _is_trusted_loopback(request):
                     # Impersonation: when the agent's loopback call sets
-                    # X-Odysseus-Owner, attribute the request to that
-                    # user so notes/calendar/etc. land in their account
-                    # instead of being owned by "internal-tool" (which
-                    # made the agent's POSTs invisible to the user that
-                    # asked for them).
+                    # X-Odysseus-Owner, attribute the request to that user only
+                    # if they exist. Authorization checks remain separate; this
+                    # is just owner attribution for notes/calendar/etc.
                     _impersonate = (request.headers.get("X-Odysseus-Owner") or "").strip()
-                    request.state.current_user = _impersonate or "internal-tool"
+                    _auth_mgr = getattr(request.app.state, "auth_manager", None) or auth_manager
+                    if _impersonate and _impersonate in getattr(_auth_mgr, "users", {}):
+                        request.state.current_user = _impersonate
+                    else:
+                        request.state.current_user = INTERNAL_TOOL_USER
                     request.state.api_token = False
                     return await call_next(request)
-            except Exception:
-                pass
-            # Allow localhost requests (internal service calls from heartbeats etc.)
-            # Disable with LOCALHOST_BYPASS=false when exposing via reverse proxy / Tailscale Funnel
-            if LOCALHOST_BYPASS:
-                client_host = request.client.host if request.client else None
-                if client_host in ("127.0.0.1", "::1"):
-                    return await call_next(request)
+            except Exception as _e:
+                logger.warning("Internal tool auth header check failed", exc_info=_e)
+            # Allow DIRECT localhost requests (internal service calls from
+            # heartbeats etc.). Tunnel/proxy-forwarded requests are excluded by
+            # _is_trusted_loopback so LOCALHOST_BYPASS can't be abused over a
+            # Cloudflare tunnel / reverse proxy. Keep LOCALHOST_BYPASS=false for
+            # network-exposed deployments regardless.
+            if LOCALHOST_BYPASS and _is_trusted_loopback(request):
+                return await call_next(request)
             if not auth_manager.is_configured:
                 # No users yet — redirect to login for first-time setup
                 if not path.startswith("/api/"):
@@ -247,11 +441,10 @@ if AUTH_ENABLED:
                                     _db.close()
                             try:
                                 await _asyncio.to_thread(_do)
-                            except Exception:
-                                pass
+                            except Exception as _e:
+                                logger.debug("Failed to update token last_used_at", exc_info=_e)
                         _asyncio.create_task(_touch_last_used(matched_id))
                         # Keep bearer-token callers out of normal cookie/user
-                        # routes. API-aware routes can read api_token_owner.
                         request.state.current_user = "api"
                         request.state.api_token = True
                         request.state.api_token_id = matched_id
@@ -300,19 +493,13 @@ class _RevalidatingStatic(StaticFiles):
         return resp
 
 
-app.mount("/static", _RevalidatingStatic(directory="static"), name="static")
+app.mount("/static", _RevalidatingStatic(directory=STATIC_DIR), name="static")
 
 # ========= GENERATED IMAGES =========
 @app.get("/api/generated-image/{filename}")
 async def serve_generated_image(filename: str, request: Request):
     """Serve generated images from the data directory."""
-    from pathlib import Path
-    import re
-    if not re.match(r'^[a-f0-9]{8,64}\.(png|jpg|jpeg|webp|gif|mp4|mov|webm|mkv|m4v)$', filename):
-        raise HTTPException(status_code=400, detail="Invalid filename")
-    img_path = Path("data/generated_images") / filename
-    if not img_path.exists():
-        raise HTTPException(status_code=404, detail="Image not found")
+    img_path = resolve_generated_image_path(filename)
     # SECURITY: filename is the only key, so anyone who knows / guesses a
     # 12-hex content hash could pull another user's image bytes. Require
     # auth and verify ownership via the gallery row (when one exists).
@@ -332,8 +519,8 @@ async def serve_generated_image(filename: str, request: Request):
                 _db.close()
     except HTTPException:
         raise
-    except Exception:
-        pass
+    except Exception as _e:
+        logger.warning("Image ownership verification failed for %r", filename, exc_info=_e)
     ext = filename.rsplit('.', 1)[-1].lower()
     mime = {
         "png": "image/png", "jpg": "image/jpeg", "jpeg": "image/jpeg",
@@ -348,22 +535,33 @@ async def serve_generated_image(filename: str, request: Request):
     return FileResponse(
         str(img_path),
         media_type=mime,
-        headers={"Cache-Control": "public, max-age=31536000, immutable"},
+        headers=GENERATED_IMAGE_HEADERS,
     )
 
 # ========= YOUTUBE INIT =========
 from services.youtube import init_youtube
 init_youtube()
 
-# ========= RAG (vector document RAG — DISABLED) =========
-# VectorRAG (ChromaDB-backed personal-document semantic search) is unused
-# (0 directories ever indexed) and its chromadb 1.4.1 / pydantic 2.12 client
-# can't even instantiate — it threw at init and cost ~30s of startup waiting on
-# the embedding probe. Disabled. All callers already guard on rag_available /
-# `if rag_manager`, so personal-doc routes degrade cleanly.
-rag_manager = None
-rag_available = False
-logger.info("Vector document RAG disabled (unused)")
+# ========= RAG (vector document RAG) =========
+# VectorRAG (ChromaDB-backed personal-document semantic search). Initialized
+# lazily via get_rag_manager() — returns None if ChromaDB isn't reachable
+# (no server running on the configured host:port), in which case personal-doc
+# routes return a clean 503 instead of busy-retrying every request.
+#
+# Note: this was previously hardcoded off because chromadb 1.4.1 / pydantic
+# 2.12 were mutually incompatible at the time. With the current pins
+# (chromadb 1.5.x + pydantic 2.13.x) the init works and Personal Docs
+# (POST /api/personal/add_directory etc.) is functional again.
+from src.rag_singleton import get_rag_manager
+rag_manager = get_rag_manager()
+rag_available = rag_manager is not None
+if rag_available:
+    logger.info("Vector document RAG initialized")
+else:
+    logger.info(
+        "Vector document RAG not available at startup "
+        "(ChromaDB may not be reachable yet — routes will retry lazily)"
+    )
 
 # ========= IMPORT CONFIG =========
 from src.config import config
@@ -376,14 +574,21 @@ components = initialize_managers(BASE_DIR, rag_manager)
 session_manager   = components["session_manager"]
 from src.assistant_log import set_session_manager as _set_asst_sm
 _set_asst_sm(session_manager)
+# Set the global session manager singleton (used by core.models.Session.add_message)
+from core.models import set_session_manager_instance
+set_session_manager_instance(session_manager)
+app.state.session_manager = session_manager
 memory_manager    = components["memory_manager"]
 memory_vector     = components.get("memory_vector")
 upload_handler    = components["upload_handler"]
+app.state.upload_handler = upload_handler
 personal_docs_mgr = components["personal_docs_manager"]
+app.state.personal_docs_manager = personal_docs_mgr
 api_key_manager   = components["api_key_manager"]
 preset_manager    = components["preset_manager"]
 chat_processor    = components["chat_processor"]
 research_handler  = components["research_handler"]
+app.state.research_handler = research_handler
 chat_handler      = components["chat_handler"]
 model_discovery   = components["model_discovery"]
 skills_manager    = components["skills_manager"]
@@ -422,6 +627,20 @@ webhook_manager = WebhookManager(api_key_manager=api_key_manager)
 auth_router = setup_auth_routes(auth_manager)
 app.include_router(auth_router)
 
+
+@app.post("/api/activity/heartbeat")
+async def activity_heartbeat():
+    from src.interactive_gate import mark_browser_activity
+    await mark_browser_activity()
+    async def _stop_background():
+        try:
+            await task_scheduler.stop_background_tasks_for_foreground(reason="browser heartbeat")
+        except Exception:
+            logging.getLogger("app.foreground_gate").debug("heartbeat task stop failed", exc_info=True)
+    asyncio.create_task(_stop_background())
+    return {"ok": True}
+
+
 # Uploads
 from routes.upload_routes import setup_upload_routes
 upload_router, upload_cleanup_func = setup_upload_routes(upload_handler)
@@ -436,15 +655,21 @@ app.include_router(setup_emoji_routes())
 # Sessions
 from routes.session_routes import setup_session_routes
 session_config = {"REQUEST_TIMEOUT": REQUEST_TIMEOUT, "OPENAI_API_KEY": OPENAI_API_KEY, "SESSIONS_FILE": SESSIONS_FILE}
-app.include_router(setup_session_routes(session_manager, session_config, webhook_manager=webhook_manager))
+app.include_router(setup_session_routes(
+    session_manager,
+    session_config,
+    webhook_manager=webhook_manager,
+    upload_handler=upload_handler,
+))
 
 # Admin Danger Zone wipes (Settings → System → Danger Zone)
-from routes.admin_wipe_routes import setup_admin_wipe_routes
+from routes.admin_wipe.admin_wipe_routes import setup_admin_wipe_routes
 app.include_router(setup_admin_wipe_routes(session_manager))
 
 # Memory
-from routes.memory_routes import setup_memory_routes
-app.include_router(setup_memory_routes(memory_manager, session_manager, memory_vector=memory_vector))
+from routes.memory.memory_routes import setup_memory_routes
+memory_router = setup_memory_routes(memory_manager, session_manager, memory_vector=memory_vector)
+app.include_router(memory_router)
 from routes.skills_routes import setup_skills_routes
 app.include_router(setup_skills_routes(skills_manager))
 
@@ -459,15 +684,15 @@ app.include_router(setup_chat_routes(
 ))
 
 # Research (background deep-research tasks)
-from routes.research_routes import setup_research_routes
+from routes.research.research_routes import setup_research_routes
 app.include_router(setup_research_routes(research_handler, session_manager=session_manager))
 
 # History
-from routes.history_routes import setup_history_routes
-app.include_router(setup_history_routes(session_manager))
+from routes.history.history_routes import setup_history_routes
+app.include_router(setup_history_routes(session_manager, upload_handler=upload_handler))
 
 # Search
-from routes.search_routes import setup_search_routes
+from routes.search.search_routes import setup_search_routes
 app.include_router(setup_search_routes(config))
 
 # Presets
@@ -476,10 +701,10 @@ app.include_router(setup_preset_routes(preset_manager))
 
 # Diagnostics
 from routes.diagnostics_routes import setup_diagnostics_routes
-app.include_router(setup_diagnostics_routes(rag_manager, rag_available, research_handler))
+app.include_router(setup_diagnostics_routes(rag_manager, rag_available, research_handler, memory_vector))
 
 # Cleanup
-from routes.cleanup_routes import setup_cleanup_routes
+from routes.cleanup.cleanup_routes import setup_cleanup_routes
 app.include_router(setup_cleanup_routes(session_manager))
 
 # Personal docs
@@ -494,6 +719,14 @@ app.include_router(setup_embedding_routes())
 from routes.model_routes import setup_model_routes
 app.include_router(setup_model_routes(model_discovery))
 
+# GitHub Copilot device-flow login
+from routes.copilot_routes import setup_copilot_routes
+app.include_router(setup_copilot_routes())
+
+# ChatGPT Subscription device-flow login
+from routes.chatgpt_subscription_routes import setup_chatgpt_subscription_routes
+app.include_router(setup_chatgpt_subscription_routes())
+
 # TTS
 from routes.tts_routes import setup_tts_routes
 app.include_router(setup_tts_routes(tts_service))
@@ -507,14 +740,15 @@ logger.info("STT service initialized (provider managed via settings)")
 
 # Documents (artifacts/canvas)
 from routes.document_routes import setup_document_routes
-app.include_router(setup_document_routes(session_manager, upload_handler))
+document_router = setup_document_routes(session_manager, upload_handler)
+app.include_router(document_router)
 
 # Signatures (reusable image stamps)
 from routes.signature_routes import setup_signature_routes
 app.include_router(setup_signature_routes())
 
 # Gallery (image library)
-from routes.gallery_routes import setup_gallery_routes
+from routes.gallery.gallery_routes import setup_gallery_routes
 app.include_router(setup_gallery_routes())
 
 # Persisted image-editor drafts (server-backed projects)
@@ -534,7 +768,8 @@ app.include_router(setup_assistant_routes(task_scheduler))
 
 # Calendar (CalDAV)
 from routes.calendar_routes import setup_calendar_routes
-app.include_router(setup_calendar_routes())
+calendar_router = setup_calendar_routes(upload_handler=upload_handler)
+app.include_router(calendar_router)
 
 # Shell (user-facing command execution)
 from routes.shell_routes import setup_shell_routes
@@ -544,12 +779,15 @@ app.include_router(setup_shell_routes())
 from routes.cookbook_routes import setup_cookbook_routes
 app.include_router(setup_cookbook_routes())
 
+from routes.workspace_routes import setup_workspace_routes
+app.include_router(setup_workspace_routes())
+
 # Hardware model fitting (cookbook "What Fits?" tab)
 from routes.hwfit_routes import setup_hwfit_routes
 app.include_router(setup_hwfit_routes())
 
 # Model A/B Comparison
-from routes.compare_routes import setup_compare_routes
+from routes.compare.compare_routes import setup_compare_routes
 app.include_router(setup_compare_routes(session_manager))
 
 # User Preferences
@@ -592,39 +830,51 @@ app.include_router(setup_api_token_routes())
 logger.info("Webhook & API token routes initialized")
 
 # Notes (Google Keep-style notes/todos)
-from routes.note_routes import setup_note_routes
-app.include_router(setup_note_routes(task_scheduler))
+from routes.note.note_routes import setup_note_routes
+app.include_router(setup_note_routes(task_scheduler, upload_handler=upload_handler))
 
 # Email
 from routes.email_routes import setup_email_routes
-app.include_router(setup_email_routes())
+email_router = setup_email_routes()
+app.include_router(email_router)
+
+# Codex integration — HTTP surface for the Codex plugin/MCP bridge. Reuses
+# api_token scopes (todos:read|write, email:read|draft|send) so external
+# Codex sessions can only touch the data the user explicitly allowed. Mounted
+# AFTER email so the codex_routes can borrow the email router for shared
+# search/threading helpers.
+from routes.codex_routes import setup_codex_routes, setup_claude_routes
+app.include_router(setup_codex_routes(
+    email_router=email_router,
+    memory_router=memory_router,
+    calendar_router=calendar_router,
+    document_router=document_router,
+))
+app.include_router(setup_claude_routes())
 
 from routes.vault_routes import setup_vault_routes
 app.include_router(setup_vault_routes())
 
 # Contacts (CardDAV)
-from routes.contacts_routes import setup_contacts_routes
+from routes.contacts.contacts_routes import setup_contacts_routes
 app.include_router(setup_contacts_routes())
 
-# ========= ROUTES (kept in app.py) =========
+from companion import setup_companion_routes
+app.include_router(setup_companion_routes())
 
-def _serve_html_with_nonce(request: Request, file_path: str) -> HTMLResponse:
-    """Read an HTML file and inject the CSP nonce into inline <script> tags."""
-    with open(file_path, "r", encoding="utf-8") as f:
-        html = f.read()
-    nonce = getattr(request.state, "csp_nonce", "")
-    html = html.replace("{{CSP_NONCE}}", nonce)
-    return HTMLResponse(html)
+# ========= ROUTES (kept in app.py) =========
 
 @app.get("/")
 async def serve_index(request: Request):
     static_path = abs_join(BASE_DIR, "static/index.html")
     if os.path.exists(static_path):
-        return _serve_html_with_nonce(request, static_path)
-    root_path = abs_join(BASE_DIR, "index.html")
-    if os.path.exists(root_path):
-        return _serve_html_with_nonce(request, root_path)
-    raise HTTPException(404, "index.html not found")
+        return serve_html_with_nonce(request, static_path)
+    # No static bundle — fall back to a root-level index.html if one is shipped.
+    # If neither exists, serve_html_with_nonce logs it and returns a generic 500:
+    # a missing index.html is a broken deployment (server fault), not a client
+    # "not found". This keeps the app-shell route consistent with the other
+    # bundled-template routes instead of mislabelling the fault as a 404.
+    return serve_html_with_nonce(request, abs_join(BASE_DIR, "index.html"))
 
 @app.get("/notes")
 async def serve_notes(request: Request):
@@ -665,11 +915,13 @@ async def serve_library(request: Request):
 @app.get("/backgrounds")
 async def serve_backgrounds(request: Request):
     """Sandbox page for prototyping background effects. No auth required."""
-    return _serve_html_with_nonce(request, abs_join(BASE_DIR, "static/backgrounds.html"))
+    return serve_html_with_nonce(request, abs_join(BASE_DIR, "static/backgrounds.html"))
 
 @app.get("/login")
 async def serve_login(request: Request):
-    return _serve_html_with_nonce(request, abs_join(BASE_DIR, "static/login.html"))
+    if not AUTH_ENABLED:
+        return RedirectResponse(url="/", status_code=302)
+    return serve_html_with_nonce(request, abs_join(BASE_DIR, "static/login.html"))
 
 @app.get("/api/version")
 async def get_version():
@@ -678,7 +930,46 @@ async def get_version():
 
 @app.get("/api/health")
 async def health_check() -> Dict[str, str]:
-    return {"status": "healthy", "timestamp": datetime.utcnow().isoformat()}
+    return {"status": "healthy", "timestamp": datetime.now(timezone.utc).isoformat()}
+
+@app.post("/api/client-perf")
+async def client_perf(request: Request):
+    """Low-volume frontend timing reports for stalls that happen before SSE logs."""
+    try:
+        data = await request.json()
+    except Exception:
+        data = {}
+    try:
+        kind = str(data.get("type") or "client").replace("\n", " ")[:80]
+        total_ms = float(data.get("total_ms") or 0)
+        stages = data.get("stages") if isinstance(data.get("stages"), list) else []
+        stage_txt = " ".join(
+            f"{str(s.get('name') or '')[:40]}={float(s.get('delta_ms') or 0):.0f}ms"
+            for s in stages[:20]
+            if isinstance(s, dict)
+        )
+        extra = str(data.get("extra") or "").replace("\n", " ")[:200]
+        logging.getLogger("app.client_perf").warning(
+            "client_perf type=%s total=%.0fms %s%s",
+            kind,
+            total_ms,
+            stage_txt,
+            f" extra={extra}" if extra else "",
+        )
+    except Exception:
+        logging.getLogger("app.client_perf").debug("client_perf log failed", exc_info=True)
+    return {"ok": True}
+
+@app.get("/api/ready")
+async def readiness_check() -> JSONResponse:
+    """Readiness / integrity self-check — DB, data dir, local-first storage.
+
+    Unlike /api/health (liveness), this returns 503 unless every critical
+    subsystem is whole, so an orchestrator can gate traffic on real readiness.
+    """
+    from src.readiness import check_readiness
+    result = check_readiness()
+    return JSONResponse(status_code=200 if result.get("ready") else 503, content=result)
 
 @app.get("/api/runtime")
 async def runtime_info() -> Dict[str, object]:
@@ -702,8 +993,19 @@ async def runtime_info() -> Dict[str, object]:
 
 # ========= LIFECYCLE =========
 
-@app.on_event("startup")
-async def startup_event():
+@asynccontextmanager
+async def _lifespan(app):
+    """Modern lifespan context manager replacing deprecated @app.on_event."""
+    # ── STARTUP ──
+    await _startup_event()
+    yield
+    # ── SHUTDOWN ──
+    await _shutdown_event()
+
+app.router.lifespan_context = _lifespan
+
+
+async def _startup_event():
     global upload_cleanup_task
     logger.info("Application starting up...")
     webhook_manager.set_loop(asyncio.get_running_loop())
@@ -746,7 +1048,7 @@ async def startup_event():
         except BaseException as e:
             logger.warning(f"Built-in MCP registration failed (non-critical): {type(e).__name__}: {e}")
         try:
-            await asyncio.wait_for(mcp_manager.connect_all_enabled(), timeout=20)
+            await mcp_manager.connect_all_enabled()
         except asyncio.TimeoutError:
             logger.warning("User MCP startup timed out (non-critical)")
         except BaseException as e:
@@ -754,61 +1056,67 @@ async def startup_event():
 
     _startup_tasks.append(asyncio.create_task(_startup_mcp_connections()))
 
-    # Pre-warm the RAG tool index off the request path. Loading the local
-    # embedding model + opening ChromaDB + indexing the built-in tools is a
-    # one-time ~1-3s cost that otherwise lands on the user's FIRST message
-    # (showing up as a big `tool_selection` time). Doing it here makes the
-    # first turn as fast as subsequent ones (warm embed ≈ a few ms).
-    async def _warmup_tool_index():
-        try:
-            from src.tool_index import get_tool_index
-            idx = await asyncio.to_thread(get_tool_index)
-            if idx:
-                await asyncio.to_thread(idx.index_builtin_tools)
-                await asyncio.to_thread(idx.get_tools_for_query, "warmup", 8)
-                logger.info("[startup] Tool index pre-warmed")
-        except Exception as e:
-            logger.warning(f"Tool index warmup failed (non-critical): {type(e).__name__}: {e}")
+    # Startup warmups are opt-in. They make later requests a little warmer, but
+    # they also compete with the first seconds of real UI use on slow or busy
+    # machines. Default to clear/idle startup and let requests warm what they use.
+    _startup_warmups_enabled = str(os.getenv("ODYSSEUS_STARTUP_WARMUPS", "")).lower() in {"1", "true", "yes", "on"}
+    if _startup_warmups_enabled:
+        async def _warmup_tool_index():
+            try:
+                from src.tool_index import get_tool_index
+                idx = await asyncio.to_thread(get_tool_index)
+                if idx:
+                    await asyncio.to_thread(idx.get_tools_for_query, "warmup", 8)
+                    logger.info("[startup] Tool index pre-warmed")
+            except Exception as e:
+                logger.warning(f"Tool index warmup failed (non-critical): {type(e).__name__}: {e}")
 
-    _startup_tasks.append(asyncio.create_task(_warmup_tool_index()))
-    # Warmup: ping all known LLM endpoints to prime connections
-    async def _warmup_endpoints():
-        try:
-            import httpx
-            endpoints = model_discovery.get_endpoints() if model_discovery else []
-            for ep in endpoints[:5]:
-                url = ep.get("url", "").replace("/chat/completions", "/models")
-                if url:
+        _startup_tasks.append(asyncio.create_task(_warmup_tool_index()))
+
+        async def _warmup_endpoints():
+            try:
+                import httpx
+                urls = (
+                    await asyncio.to_thread(model_discovery.warmup_ping_urls)
+                    if model_discovery else []
+                )
+                for url in urls:
                     try:
                         async with httpx.AsyncClient(timeout=5.0) as client:
                             await client.get(url)
                         logger.info(f"Warmup ping OK: {url}")
                     except Exception as e:
                         logger.debug(f"Warmup ping failed for endpoint: {e}")
-        except Exception as e:
-            logger.debug(f"Warmup ping skipped: {e}")
-
-    _startup_tasks.append(asyncio.create_task(_warmup_endpoints()))
-
-    # Keep-alive: ping endpoints every 60 seconds to prevent cold starts
-    async def _keepalive_loop():
-        while True:
-            try:
-                await asyncio.sleep(60)
-                await _warmup_endpoints()
             except Exception as e:
-                logger.warning(f"Keepalive loop error: {e}")
-                await asyncio.sleep(300)  # Back off on error
+                logger.debug(f"Warmup ping skipped: {e}")
 
-    _startup_tasks.append(asyncio.create_task(_keepalive_loop()))
+        _startup_tasks.append(asyncio.create_task(_warmup_endpoints()))
+    else:
+        logger.info("Startup warmups disabled (set ODYSSEUS_STARTUP_WARMUPS=1 to enable)")
+
+    # Keep-alive is opt-in. The ping path performs model discovery, and when
+    # stale LAN endpoints are configured it can add periodic backend pressure
+    # that delays unrelated UI requests such as Notes/Documents.
+    _keepalive_enabled = str(os.getenv("ODYSSEUS_MODEL_KEEPALIVE", "")).lower() in {"1", "true", "yes", "on"}
+    if _keepalive_enabled:
+        async def _keepalive_loop():
+            while True:
+                try:
+                    await asyncio.sleep(60)
+                    await _warmup_endpoints()
+                except Exception as e:
+                    logger.warning(f"Keepalive loop error: {e}")
+                    await asyncio.sleep(300)  # Back off on error
+
+        _startup_tasks.append(asyncio.create_task(_keepalive_loop()))
 
     async def _ensure_default_tasks():
         # Create/reconcile default automation tasks + personal assistant for every user.
         owners = set()
         try:
             import json as _json
-            auth_path = "data/auth.json"
-            with open(auth_path) as f:
+            auth_path = AUTH_FILE
+            with open(auth_path, encoding="utf-8") as f:
                 users = _json.load(f).get("users", {})
             owners.update(users.keys())
         except Exception as e:
@@ -854,8 +1162,8 @@ async def startup_event():
     # does not make an existing library look empty after auth/account changes.
     try:
         import json as _json
-        auth_path = "data/auth.json"
-        with open(auth_path) as f:
+        auth_path = AUTH_FILE
+        with open(auth_path, encoding="utf-8") as f:
             users = _json.load(f).get("users", {})
         primary_owner = None
         for uname, udata in users.items():
@@ -926,69 +1234,19 @@ async def startup_event():
                 logger.warning(f"Nightly skill audit failed: {e}")
 
     _startup_tasks.append(asyncio.create_task(_skill_audit_nightly_loop()))
-    # Auto-detect Ollama — run in background to avoid blocking startup. In Docker,
-    # localhost is the container, so also try host.docker.internal.
-    async def _detect_ollama():
-        try:
-            import httpx
-            raw_candidates = [
-                os.getenv("OLLAMA_BASE_URL", ""),
-                os.getenv("OLLAMA_URL", ""),
-                "http://localhost:11434/v1",
-                "http://host.docker.internal:11434/v1",
-            ]
-            candidates = []
-            for raw in raw_candidates:
-                base = (raw or "").strip().rstrip("/")
-                if not base:
-                    continue
-                if base.endswith("/api"):
-                    base = base[:-4].rstrip("/")
-                if not base.endswith("/v1"):
-                    base = base + "/v1"
-                if base not in candidates:
-                    candidates.append(base)
 
-            found_base = ""
-            async with httpx.AsyncClient() as client:
-                for base in candidates:
-                    try:
-                        r = await client.get(base + "/models", timeout=2)
-                        if r.status_code == 200:
-                            found_base = base
-                            break
-                    except Exception:
-                        continue
-            if not found_base:
-                return
-            from core.database import SessionLocal, ModelEndpoint
-            db = SessionLocal()
-            try:
-                existing = None
-                for base in candidates:
-                    existing = db.query(ModelEndpoint).filter(ModelEndpoint.base_url == base).first()
-                    if existing:
-                        break
-                if not existing:
-                    host = found_base.replace("http://", "").replace("https://", "").split("/")[0]
-                    ep = ModelEndpoint(
-                        id=str(uuid.uuid4())[:8],
-                        name="Ollama" if host.startswith("localhost") else f"Ollama ({host})",
-                        base_url=found_base,
-                        is_enabled=True,
-                    )
-                    db.add(ep)
-                    db.commit()
-                    logger.info(f"Auto-added Ollama endpoint ({found_base})")
-            finally:
-                db.close()
-        except Exception as e:
-            logger.debug(f"Ollama auto-detect: {e}")
-    _startup_tasks.append(asyncio.create_task(_detect_ollama()))
+    # Cookbook serve lifecycle — kills scheduler-launched serves whose
+    # window-end has passed. Paired with the cookbook_serve builtin
+    # action; both are no-ops unless a scheduled task actually launches
+    # something with end_after_min set. Removing this line + the
+    # cookbook_serve entry in BUILTIN_ACTIONS + src/cookbook_serve_lifecycle.py
+    # removes the feature.
+    from src.cookbook_serve_lifecycle import cookbook_serve_lifecycle_loop
+    _startup_tasks.append(asyncio.create_task(cookbook_serve_lifecycle_loop()))
+
     logger.info("Application startup complete")
 
-@app.on_event("shutdown")
-async def shutdown_event():
+async def _shutdown_event():
     logger.info("Application shutting down...")
     if upload_cleanup_task:
         upload_cleanup_task.cancel()
@@ -1012,3 +1270,12 @@ async def shutdown_event():
     except Exception as e:
         logger.warning(f"MCP shutdown error: {e}")
     logger.info("Application shutdown complete")
+
+
+if __name__ == "__main__":
+    import uvicorn
+
+    bind_host = os.getenv("APP_BIND", "127.0.0.1")
+    bind_port = int(os.getenv("APP_PORT", "7000"))
+
+    uvicorn.run(app, host=bind_host, port=bind_port, log_level="info")

build-macos-app.sh

@@ -0,0 +1,173 @@
+#!/bin/bash
+# Build a downloadable macOS launcher app + .dmg for Odysseus.
+#
+#   ./build-macos-app.sh
+#
+# Produces:
+#   dist/Odysseus.app   — double-click: starts the local server (using this
+#                         repo's venv) and opens the UI in an app-style window.
+#   dist/Odysseus.dmg   — drag-to-Applications disk image (the downloadable).
+#
+# This is a *launcher* wrapper: it drives the venv we set up in this repo, it
+# does not bundle Python. The install path is baked into the app at build time,
+# so rebuild if you move the repo. Override the port with ODYSSEUS_PORT.
+set -e
+
+REPO_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+APP_NAME="Odysseus"
+INSTALL_DIR="$REPO_DIR"
+PORT="${ODYSSEUS_PORT:-7860}"
+DIST="$REPO_DIR/dist"
+APP="$DIST/$APP_NAME.app"
+
+echo "Building $APP_NAME.app"
+echo "  install dir: $INSTALL_DIR"
+echo "  port:        $PORT"
+
+rm -rf "$APP"
+mkdir -p "$APP/Contents/MacOS" "$APP/Contents/Resources"
+
+# ── Icon (best effort) — center-crop docs/odysseus.jpg to a square .icns ──
+if [ -f "$REPO_DIR/docs/odysseus.jpg" ] && command -v sips >/dev/null 2>&1; then
+  TMPIMG="$(mktemp -d)"
+  # Center-crop to a square, scale to 512 (sips' icns encoder caps at 512), and
+  # let sips emit the .icns directly — more robust across macOS versions than
+  # building an .iconset by hand.
+  sips -c 720 720 "$REPO_DIR/docs/odysseus.jpg" --out "$TMPIMG/sq.png" >/dev/null 2>&1 || cp "$REPO_DIR/docs/odysseus.jpg" "$TMPIMG/sq.png"
+  sips -z 512 512 "$TMPIMG/sq.png" --out "$TMPIMG/icon.png" >/dev/null 2>&1
+  if sips -s format icns "$TMPIMG/icon.png" --out "$APP/Contents/Resources/odysseus.icns" >/dev/null 2>&1; then
+    echo "  icon:        odysseus.icns"
+  else
+    echo "  icon:        (skipped — conversion failed)"
+  fi
+  rm -rf "$TMPIMG"
+else
+  echo "  icon:        (skipped — no docs/odysseus.jpg)"
+fi
+
+# ── Info.plist ──
+cat > "$APP/Contents/Info.plist" <<PLIST
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+    <key>CFBundleName</key>            <string>$APP_NAME</string>
+    <key>CFBundleDisplayName</key>     <string>$APP_NAME</string>
+    <key>CFBundleIdentifier</key>      <string>com.odysseus.launcher</string>
+    <key>CFBundleVersion</key>         <string>1.0</string>
+    <key>CFBundleShortVersionString</key><string>1.0</string>
+    <key>CFBundlePackageType</key>     <string>APPL</string>
+    <key>CFBundleExecutable</key>      <string>$APP_NAME</string>
+    <key>CFBundleIconFile</key>        <string>odysseus</string>
+    <key>LSMinimumSystemVersion</key>  <string>11.0</string>
+    <key>NSHighResolutionCapable</key> <true/>
+    <key>LSUIElement</key>             <false/>
+</dict>
+</plist>
+PLIST
+
+# ── Launcher executable (placeholders filled below) ──
+cat > "$APP/Contents/MacOS/$APP_NAME.tmpl" <<'LAUNCHER'
+#!/bin/bash
+# Odysseus.app — start the local server and open the UI in an app window.
+INSTALL_DIR="__INSTALL_DIR__"
+PORT="__PORT__"
+URL="http://127.0.0.1:${PORT}"
+export PATH="/opt/homebrew/bin:/usr/local/bin:/usr/bin:/bin:$PATH"
+
+UVICORN="$INSTALL_DIR/venv/bin/uvicorn"
+LOG="$INSTALL_DIR/logs/odysseus-app.log"
+
+notify() { /usr/bin/osascript -e "display notification \"$1\" with title \"Odysseus\"" >/dev/null 2>&1; }
+die_gui() {
+  /usr/bin/osascript -e "display dialog \"$1\" with title \"Odysseus\" buttons {\"OK\"} default button 1 with icon stop" >/dev/null 2>&1
+  exit 1
+}
+
+[ -x "$UVICORN" ] || die_gui "Odysseus isn't set up yet. Open Terminal and run:
+
+cd $INSTALL_DIR
+python3.11 -m venv venv
+./venv/bin/pip install -r requirements.txt
+./venv/bin/python setup.py"
+
+# Open the UI in a chrome-less app window (Chromium browsers), else default browser.
+open_ui() {
+  local b base exe bin
+  for b in "Google Chrome" "Microsoft Edge" "Brave Browser" "Chromium"; do
+    for base in "/Applications" "$HOME/Applications"; do
+      if [ -d "$base/$b.app" ]; then
+        exe="$(/usr/bin/defaults read "$base/$b.app/Contents/Info" CFBundleExecutable 2>/dev/null)"
+        bin="$base/$b.app/Contents/MacOS/$exe"
+        if [ -x "$bin" ]; then
+          "$bin" --app="$URL" --new-window >/dev/null 2>&1 &
+          return 0
+        fi
+      fi
+    done
+  done
+  /usr/bin/open "$URL"
+}
+
+mkdir -p "$INSTALL_DIR/logs"
+
+# Already running? Just open the UI.
+if /usr/bin/curl -s -o /dev/null --max-time 2 "$URL"; then
+  open_ui
+  exit 0
+fi
+
+notify "Starting…"
+cd "$INSTALL_DIR" || die_gui "Install folder not found: $INSTALL_DIR"
+if [ "$(uname -m)" = "arm64" ]; then
+  arch -arm64 "$UVICORN" app:app --host 127.0.0.1 --port "$PORT" >>"$LOG" 2>&1 &
+else
+  "$UVICORN" app:app --host 127.0.0.1 --port "$PORT" >>"$LOG" 2>&1 &
+fi
+SERVER_PID=$!
+
+# Quitting the app stops the server it started.
+trap 'kill $SERVER_PID 2>/dev/null; exit 0' TERM INT
+
+# Wait for readiness (first run downloads an embedding model — allow ~2 min).
+READY=0
+for i in $(seq 1 120); do
+  /usr/bin/curl -s -o /dev/null --max-time 2 "$URL" && { READY=1; break; }
+  kill -0 "$SERVER_PID" 2>/dev/null || die_gui "Odysseus failed to start. Log:
+$LOG"
+  sleep 1
+done
+
+if [ "$READY" = "1" ]; then
+  open_ui
+else
+  notify "Odysseus is taking a while — open $URL once it finishes starting."
+fi
+wait "$SERVER_PID"
+LAUNCHER
+
+sed -e "s|__INSTALL_DIR__|$INSTALL_DIR|g" -e "s|__PORT__|$PORT|g" \
+    "$APP/Contents/MacOS/$APP_NAME.tmpl" > "$APP/Contents/MacOS/$APP_NAME"
+rm -f "$APP/Contents/MacOS/$APP_NAME.tmpl"
+chmod +x "$APP/Contents/MacOS/$APP_NAME"
+
+# Refresh Finder's icon cache for the new bundle.
+touch "$APP"
+
+# ── .dmg (drag-to-Applications) ──
+echo "Packaging dist/$APP_NAME.dmg"
+STAGE="$(mktemp -d)/dmg"
+mkdir -p "$STAGE"
+cp -R "$APP" "$STAGE/"
+ln -s /Applications "$STAGE/Applications"
+rm -f "$DIST/$APP_NAME.dmg"
+hdiutil create -volname "$APP_NAME" -srcfolder "$STAGE" -ov -format UDZO "$DIST/$APP_NAME.dmg" >/dev/null
+rm -rf "$STAGE"
+
+echo ""
+echo "Done:"
+echo "  $APP"
+echo "  $DIST/$APP_NAME.dmg"
+echo ""
+echo "Run it:        open '$APP'"
+echo "Install:       open '$DIST/$APP_NAME.dmg'  (drag Odysseus to Applications)"

build-windows-portable.ps1

@@ -0,0 +1,72 @@
+#Requires -Version 5.1
+<#
+  Build a portable Windows distribution for Odysseus.
+
+  Output layout:
+    dist\Odysseus\Odysseus.exe
+    dist\Odysseus\static\...
+    dist\Odysseus\scripts\...
+    dist\Odysseus\mcp_servers\...
+    dist\Odysseus\services\hwfit\data\...
+
+  The app then keeps using its normal filesystem layout when frozen.
+
+  Usage:
+    powershell -ExecutionPolicy Bypass -File .\build-windows-portable.ps1
+#>
+
+$ErrorActionPreference = "Stop"
+Set-Location -Path $PSScriptRoot
+
+function Write-Step($msg) { Write-Host ""; Write-Host ("==> " + $msg) -ForegroundColor Cyan }
+function Fail($msg) {
+    Write-Host ""
+    Write-Host ("ERROR: " + $msg) -ForegroundColor Red
+    exit 1
+}
+
+Write-Step "Checking for Python"
+$pyExe = $null
+if (Test-Path ".\.venv\Scripts\python.exe") {
+    $pyExe = (Resolve-Path ".\.venv\Scripts\python.exe").Path
+} else {
+    foreach ($c in @("py", "python")) {
+        $cmd = Get-Command $c -ErrorAction SilentlyContinue
+        if ($cmd) { $pyExe = $cmd.Source; break }
+    }
+    if ($pyExe -like "*WindowsApps*python.exe") {
+        $pyCmd = Get-Command py -ErrorAction SilentlyContinue
+        if ($pyCmd) {
+            $pyExe = $pyCmd.Source
+        }
+    }
+}
+if (-not $pyExe) {
+    Fail "Python not found on PATH. Install Python 3.11+ first."
+}
+Write-Host ("Using Python: " + $pyExe)
+
+Write-Step "Installing build dependencies"
+& $pyExe -m pip install --upgrade pip --quiet
+& $pyExe -m pip install -r requirements.txt pyinstaller pystray Pillow
+if ($LASTEXITCODE -ne 0) { Fail "Dependency install failed." }
+
+Write-Step "Building portable exe bundle"
+Remove-Item -Recurse -Force build, dist -ErrorAction SilentlyContinue
+
+$dataArgs = @(
+    "--add-data", "static;static",
+    "--add-data", "scripts;scripts",
+    "--add-data", "mcp_servers;mcp_servers",
+    "--add-data", "services/hwfit/data;services/hwfit/data",
+    "--add-data", "config;config",
+    "--add-data", ".env.example;.env.example"
+)
+
+& $pyExe -m PyInstaller --noconfirm --clean --onedir --noconsole --icon=static/icon.ico --name Odysseus @dataArgs launcher.py
+if ($LASTEXITCODE -ne 0) { Fail "PyInstaller build failed." }
+
+Write-Host ""
+Write-Host "Build complete." -ForegroundColor Green
+Write-Host "Portable app folder: $PSScriptRoot\dist\Odysseus" -ForegroundColor Green
+Write-Host "Distribute the whole folder (or zip it) so static assets and scripts stay with the exe." -ForegroundColor Green

companion/README.md

@@ -0,0 +1,28 @@
+# Companion bridge
+
+A thin, additive layer so a LAN client (e.g. a phone) can discover what an
+Odysseus server offers and pair to it, without duplicating any LLM logic.
+
+| Method | Path | Auth | Purpose |
+|---|---|---|---|
+| GET | `/api/companion/ping` | session or token | cheap, auth-validated health check |
+| GET | `/api/companion/info` | session or token | server identity + capability flags |
+| GET | `/api/companion/models` | session or token | the **caller's own** model endpoints |
+| GET | `/api/companion/pair` | **admin cookie** | pairing page (a form; never mints) |
+| POST | `/api/companion/pair` | **admin cookie** | mint a one-time pairing token (`?format=json` for an in-app screen) |
+
+`/models` scopes to the caller's real owner plus legacy null-owner shared rows
+(same rule as `owner_filter`) and never returns API-key material.
+
+## Pairing CSRF posture
+
+Minting happens **only on POST**. The session cookie is `SameSite=Lax`
+(`routes/auth_routes.py`), so a browser will not send it on a cross-site POST —
+the same protection `POST /api/tokens` relies on. A `GET` would be unsafe (Lax
+cookies ride top-level GET navigations), so `GET /pair` only renders a form.
+Minting invalidates the auth middleware's token cache, so a freshly minted token
+works on the next request without a restart.
+
+The pairing/scoping rules live in small, tested units (`token_owner`,
+`owner_can_see`, `mint_pairing_token`, `pairing.*`) — see
+`tests/test_companion_readonly.py` and `tests/test_companion_pairing.py`.

companion/__init__.py

@@ -0,0 +1,11 @@
+"""Odysseus companion bridge — additive LAN endpoints.
+
+Read endpoints (/api/companion/ping, /info, owner-scoped /models) so a LAN
+client can discover what a server offers, plus admin-only pairing
+(/api/companion/pair) that mints a one-time chat-scoped token on POST. No new LLM
+logic; auth is enforced by the existing AuthMiddleware. See companion/README.md.
+"""
+
+from companion.routes import setup_companion_routes
+
+__all__ = ["setup_companion_routes"]

companion/pairing.py

@@ -0,0 +1,128 @@
+"""Shared pairing helpers for the companion bridge.
+
+Token minting + LAN discovery + QR rendering, kept here as small, importable
+units so the route layer stays thin and the logic is directly testable.
+"""
+
+from __future__ import annotations
+
+import json
+import os
+import secrets
+import socket
+import uuid
+
+import bcrypt
+
+from src.constants import AUTH_FILE
+
+PAIRING_VERSION = 1
+COMPANION_SCOPE = "chat"
+
+
+def default_port() -> int:
+    """Best guess at the port the server is reachable on. Callers that know the
+    real request port should pass it explicitly."""
+    try:
+        return int(os.environ.get("APP_PORT", "7000"))
+    except ValueError:
+        return 7000
+
+
+def lan_ip_candidates() -> list[str]:
+    """Likely LAN IPv4 addresses for this host, best candidate first.
+
+    The UDP-connect trick reveals the egress interface the OS would use to reach
+    the default gateway -- i.e. the address a phone on the same Wi-Fi should
+    target. No packets are actually sent. Loopback is dropped.
+    """
+    candidates: list[str] = []
+
+    def _add(ip):
+        if ip and ip not in candidates and not ip.startswith("127."):
+            candidates.append(ip)
+
+    s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
+    try:
+        s.connect(("8.8.8.8", 80))
+        _add(s.getsockname()[0])
+    except OSError:
+        pass
+    finally:
+        s.close()
+
+    try:
+        for info in socket.getaddrinfo(socket.gethostname(), None, socket.AF_INET):
+            _add(info[4][0])
+    except OSError:
+        pass
+
+    return candidates
+
+
+def find_admin_user() -> str | None:
+    """Resolve an admin username from data/auth.json (schema uses is_admin),
+    falling back to the first user."""
+    auth_path = AUTH_FILE
+    try:
+        with open(auth_path, "r", encoding="utf-8") as f:
+            data = json.load(f)
+    except (OSError, json.JSONDecodeError):
+        return None
+    if not isinstance(data, dict):
+        return None
+    users = data.get("users") or {}
+    if not isinstance(users, dict):
+        return None
+    for uname, udata in users.items():
+        if isinstance(udata, dict) and udata.get("is_admin") is True:
+            return uname
+    return next(iter(users), None)
+
+
+def mint_token(owner: str, name: str = "companion") -> tuple[str, str]:
+    """Create a chat-scoped API token row and return (token_id, raw_token).
+
+    The raw token is returned ONCE -- only its bcrypt hash + an 8-char prefix
+    are persisted. Mirrors routes/api_token_routes.py so cookie- and
+    companion-minted tokens are indistinguishable to the auth middleware.
+    """
+    from core.database import get_db_session, ApiToken
+
+    raw_token = "ody_" + secrets.token_urlsafe(32)
+    token_hash = bcrypt.hashpw(raw_token.encode(), bcrypt.gensalt()).decode()
+    token_id = str(uuid.uuid4())[:8]
+
+    with get_db_session() as db:
+        db.add(ApiToken(
+            id=token_id,
+            owner=owner,
+            name=name,
+            token_hash=token_hash,
+            token_prefix=raw_token[:8],
+            scopes=COMPANION_SCOPE,
+            is_active=True,
+        ))
+    return token_id, raw_token
+
+
+def pairing_payload(host: str, port: int, token: str) -> dict:
+    """The exact JSON a client scans / accepts. Keep keys stable."""
+    return {"v": PAIRING_VERSION, "host": host, "port": port, "token": token}
+
+
+def pairing_qr_png_data_uri(payload: dict) -> str | None:
+    """Render the pairing payload as a QR `data:` URI for an <img>. Returns None
+    if the optional qrcode dep is unavailable."""
+    try:
+        import base64
+        import io
+
+        import qrcode
+
+        img = qrcode.make(json.dumps(payload, separators=(",", ":")))
+        buf = io.BytesIO()
+        img.save(buf, format="PNG")
+        return "data:image/png;base64," + base64.b64encode(buf.getvalue()).decode()
+    except Exception:
+        return None

companion/routes.py

@@ -0,0 +1,250 @@
+"""Companion bridge — /api/companion/*.
+
+A thin, additive layer so a LAN client (e.g. a phone) can discover what a server
+offers and pair to it, without duplicating any LLM logic.
+
+Auth is enforced globally by AuthMiddleware (app.py), so reaching a handler here
+means the caller is authenticated by either a cookie session or a Bearer `ody_`
+API token. Ping/info accept either credential type, models requires a chat-
+scoped API token for bearer callers, and the pairing endpoints are admin-cookie
+only.
+
+Pairing CSRF posture: minting happens ONLY on POST. The session cookie is
+SameSite=Lax (routes/auth_routes.py), which a browser does not send on a
+cross-site POST, so an admin's cookie can't be used by a malicious page to mint
+a token -- the same protection the existing POST /api/tokens relies on. Minting
+on a GET would be unsafe (Lax cookies ride top-level GET navigations), so GET
+/pair only renders a form.
+"""
+
+import html
+
+from fastapi import APIRouter, HTTPException, Request
+from fastapi.responses import HTMLResponse
+
+from core.middleware import require_admin
+from src.auth_helpers import get_current_user
+
+from companion import pairing as _pairing
+
+
+def token_owner(request: Request) -> str | None:
+    """The real owner to attribute a request to, for read-scoping.
+
+    Cookie sessions resolve to the logged-in username via get_current_user.
+    Bearer-token callers come through as the sandboxed pseudo-user "api"; their
+    real owner is stamped on request.state.api_token_owner by the auth
+    middleware. Returns None when no owner can be resolved.
+    """
+    if getattr(request.state, "api_token", False):
+        return getattr(request.state, "api_token_owner", None)
+    return get_current_user(request)
+
+
+def owner_can_see(row_owner, owner) -> bool:
+    """Owner-scope rule for read endpoints.
+
+    A caller sees a row when it is their own, or when it is a legacy null-owner
+    ("shared") row. A caller must NEVER see another owner's row. Mirrors the
+    `owner_filter` rule used elsewhere, expressed as a pure predicate so it can
+    be tested directly and used as a defensive in-Python check alongside the
+    SQL filter.
+    """
+    return row_owner is None or row_owner == owner
+
+
+def require_models_scope(request: Request) -> None:
+    """Require the companion chat scope for bearer-token model inventory."""
+    if not getattr(request.state, "api_token", False):
+        return
+    scopes = getattr(request.state, "api_token_scopes", None) or []
+    if isinstance(scopes, str):
+        scopes = [scope.strip() for scope in scopes.split(",")]
+    scope_set = {str(scope).strip() for scope in scopes if str(scope).strip()}
+    if _pairing.COMPANION_SCOPE not in scope_set:
+        raise HTTPException(403, "API token requires chat scope")
+
+
+def mint_pairing_token(owner: str, invalidate=None) -> tuple[str, str]:
+    """Mint a pairing token AND invalidate the auth middleware's in-memory token
+    cache, so the new token is accepted on the very next request without a server
+    restart. Returns (token_id, raw_token); the raw token is shown once.
+
+    `invalidate` is the app's request.app.state.invalidate_token_cache callable
+    (passed in so this stays a pure, testable unit).
+    """
+    token_id, raw_token = _pairing.mint_token(owner)
+    if callable(invalidate):
+        invalidate()
+    return token_id, raw_token
+
+
+def setup_companion_routes() -> APIRouter:
+    router = APIRouter(prefix="/api/companion", tags=["companion"])
+
+    @router.get("/ping")
+    def ping(request: Request):
+        """Cheap, auth-validated health check. A 200 with ok=true confirms the
+        host/port and credential are valid; middleware returns 401 otherwise."""
+        from core.constants import APP_VERSION
+        return {
+            "ok": True,
+            "name": "odysseus",
+            "version": APP_VERSION,
+            "auth": "token" if getattr(request.state, "api_token", False) else "session",
+        }
+
+    @router.get("/info")
+    def info(request: Request):
+        """Server identity + coarse capability flags. `owner` is the caller's own
+        identity (the token's owner for bearer callers)."""
+        from core.constants import APP_VERSION
+        return {
+            "name": "odysseus",
+            "version": APP_VERSION,
+            "owner": token_owner(request),
+            "capabilities": {"chat": True, "streaming": True},
+        }
+
+    @router.get("/models")
+    def models(request: Request):
+        """LLM model endpoints the CALLER can use.
+
+        The stock /api/models route scopes to get_current_user, which for a
+        bearer token is the sandboxed pseudo-user "api" (owns nothing). Here we
+        scope to the token's real owner instead, plus legacy null-owner shared
+        rows -- the same rule as owner_filter. Read-only; never returns api_key
+        material.
+        """
+        require_models_scope(request)
+        import json as _json
+
+        from core.database import SessionLocal, ModelEndpoint
+        from src.endpoint_resolver import build_chat_url
+
+        owner = token_owner(request)
+        out = []
+        db = SessionLocal()
+        try:
+            q = db.query(ModelEndpoint).filter(
+                ModelEndpoint.is_enabled == True,  # noqa: E712
+                (ModelEndpoint.model_type == "llm") | (ModelEndpoint.model_type == None),  # noqa: E711
+            )
+            if owner:
+                q = q.filter((ModelEndpoint.owner == owner) | (ModelEndpoint.owner == None))  # noqa: E711
+            for ep in q.all():
+                if not owner_can_see(ep.owner, owner):
+                    continue
+                try:
+                    model_ids = _json.loads(ep.cached_models) if ep.cached_models else []
+                except (ValueError, TypeError):
+                    model_ids = []
+                try:
+                    hidden = set(_json.loads(ep.hidden_models)) if ep.hidden_models else set()
+                except (ValueError, TypeError):
+                    hidden = set()
+                model_ids = [m for m in model_ids if m not in hidden]
+                try:
+                    chat_url = build_chat_url(ep.base_url)
+                except Exception:
+                    chat_url = ep.base_url
+                out.append({
+                    "endpoint_id": ep.id,
+                    "name": ep.name,
+                    "endpoint_url": chat_url,
+                    "models": model_ids,
+                    "supports_tools": ep.supports_tools,
+                })
+        finally:
+            db.close()
+        return {"endpoints": out}
+
+    @router.get("/pair")
+    def pair_page(request: Request):
+        """Admin-only pairing page. Renders a form that POSTs to mint a code.
+
+        A GET never mints a credential: SameSite=Lax session cookies ride
+        top-level GET navigations, so minting on GET would be triggerable by a
+        link or <img> (CSRF). The actual mint is the POST handler below.
+        """
+        require_admin(request)
+        page = """<!doctype html>
+<html><head><meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
+<title>Pair a device</title>
+<style>
+  body{font-family:-apple-system,system-ui,sans-serif;max-width:520px;margin:48px auto;padding:0 20px;color:#e8e8e8;background:#16161a}
+  .card{background:#1f1f25;border:1px solid #2c2c35;border-radius:14px;padding:28px;text-align:center}
+  button{background:#7c9cff;color:#0e0e12;border:none;border-radius:10px;padding:12px 20px;font-size:15px;font-weight:600;cursor:pointer}
+</style></head>
+<body><div class="card">
+  <h2>Pair a device</h2>
+  <p>Generate a one-time pairing code (a chat-scoped API token) for a LAN client.</p>
+  <form method="POST" action="/api/companion/pair">
+    <button type="submit">Generate pairing code</button>
+  </form>
+  <p style="color:#8a8a96;font-size:12px;margin-top:18px">Admin only. Each code mints a new token, shown once. Manage or revoke under Settings &rarr; API tokens.</p>
+</div></body></html>"""
+        return HTMLResponse(page)
+
+    @router.post("/pair")
+    def pair_create(request: Request):
+        """Mint a pairing code. Admin-cookie only; CSRF-safe because the
+        SameSite=Lax session cookie is not sent on a cross-site POST (same
+        protection as POST /api/tokens). Minting invalidates the token cache so
+        the code works immediately, no restart. `?format=json` returns the
+        payload for an in-app pairing screen."""
+        require_admin(request)
+        owner = get_current_user(request)
+        invalidate = getattr(request.app.state, "invalidate_token_cache", None)
+        token_id, raw_token = mint_pairing_token(owner, invalidate)
+
+        hosts = _pairing.lan_ip_candidates()
+        host = hosts[0] if hosts else "127.0.0.1"
+        port = request.url.port or _pairing.default_port()
+        payload = _pairing.pairing_payload(host, port, raw_token)
+        qr = _pairing.pairing_qr_png_data_uri(payload)
+        qr_ok = bool(qr and qr.startswith("data:image/png;base64,"))
+
+        if (request.query_params.get("format") or "").lower() == "json":
+            return {
+                "host": host,
+                "port": port,
+                "token": raw_token,
+                "token_id": token_id,
+                "hosts": hosts,
+                "payload": payload,
+                "qr": qr if qr_ok else None,
+            }
+
+        import json as _json
+        payload_json = _json.dumps(payload, separators=(",", ":"))
+        # Only ever emit a known PNG data-URI into the src; every other value is
+        # html.escaped.
+        qr_block = (
+            f'<img src="{html.escape(qr)}" alt="Pairing QR" width="260" height="260">'
+            if qr_ok else "<p><em>QR rendering unavailable -- enter the details manually.</em></p>"
+        )
+        page = f"""<!doctype html>
+<html><head><meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
+<title>Pairing code</title>
+<style>
+  body{{font-family:-apple-system,system-ui,sans-serif;max-width:520px;margin:40px auto;padding:0 20px;color:#e8e8e8;background:#16161a}}
+  .card{{background:#1f1f25;border:1px solid #2c2c35;border-radius:14px;padding:24px;text-align:center}}
+  code{{background:#0e0e12;padding:2px 6px;border-radius:6px;word-break:break-all}}
+  .row{{text-align:left;margin:10px 0;font-size:14px;color:#bdbdc7}}
+  .warn{{color:#e0a85e;font-size:13px;margin-top:18px}}
+</style></head>
+<body><div class="card">
+  <h2>Pairing code</h2>
+  {qr_block}
+  <div class="row"><strong>Host:</strong> <code>{html.escape(host)}</code></div>
+  <div class="row"><strong>Port:</strong> <code>{html.escape(str(port))}</code></div>
+  <div class="row"><strong>Token:</strong> <code>{html.escape(raw_token)}</code></div>
+  <div class="row"><strong>Payload:</strong> <code>{html.escape(payload_json)}</code></div>
+  <p class="warn">Shown once. This grants chat access to your Odysseus; revoke it
+  in Settings &rarr; API tokens (id <code>{html.escape(token_id)}</code>). The
+  device must be on the same network, and the server must bind to your LAN.</p>
+</div></body></html>"""
+        return HTMLResponse(page)
+
+    return router

core/atomic_io.py

@@ -26,7 +26,7 @@ def atomic_write_json(path: str, data: Any, *, indent: Optional[int] = None) ->
     """
     os.makedirs(os.path.dirname(path) or ".", exist_ok=True)
     tmp = f"{path}.tmp.{os.getpid()}"
-    with open(tmp, "w") as f:
+    with open(tmp, "w", encoding="utf-8") as f:
         json.dump(data, f, indent=indent)
         f.flush()
         os.fsync(f.fileno())
@@ -34,9 +34,11 @@ def atomic_write_json(path: str, data: Any, *, indent: Optional[int] = None) ->
 
 
 def atomic_write_text(path: str, text: str) -> None:
+    if not isinstance(text, str):
+        raise TypeError("atomic_write_text expects a string")
     os.makedirs(os.path.dirname(path) or ".", exist_ok=True)
     tmp = f"{path}.tmp.{os.getpid()}"
-    with open(tmp, "w") as f:
+    with open(tmp, "w", encoding="utf-8") as f:
         f.write(text)
         f.flush()
         os.fsync(f.fileno())

core/auth.py

@@ -3,6 +3,7 @@ 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
@@ -19,6 +20,7 @@ logger = logging.getLogger(__name__)
 
 
 from core.atomic_io import atomic_write_json as _atomic_write_json  # noqa: E402
+from core.middleware import INTERNAL_TOOL_USER  # noqa: E402
 
 DEFAULT_PRIVILEGES = {
     "can_use_agent": True,
@@ -30,16 +32,50 @@ DEFAULT_PRIVILEGES = {
     "can_manage_memory": True,
     "max_messages_per_day": 0,
     "allowed_models": [],
+    "allowed_models_restricted": False,
+    # Explicit "block every model" sentinel. An empty `allowed_models` list is
+    # ambiguous — it's also what gets sent when the admin clicks "[All]" — so
+    # we need a dedicated flag to express "this user may use no models at all"
+    # distinctly from "this user has no restriction".
+    "block_all_models": False,
 }
 
 # Admins get everything
 ADMIN_PRIVILEGES = {k: (True if isinstance(v, bool) else (0 if isinstance(v, int) else [])) for k, v in DEFAULT_PRIVILEGES.items()}
+ADMIN_PRIVILEGES["allowed_models_restricted"] = False
+# Admins must never be blocked from using models — the generic dict
+# comprehension above flips every boolean default to True, which would be
+# backwards for this sentinel.
+ADMIN_PRIVILEGES["block_all_models"] = False
 
-DEFAULT_AUTH_PATH = os.path.join(
-    Path(__file__).parent.parent, "data", "auth.json"
-)
+from src.constants import AUTH_FILE, PASSWORD_MIN_LENGTH
+DEFAULT_AUTH_PATH = AUTH_FILE
 TOKEN_TTL = 60 * 60 * 24 * 7  # 7 days
 
+# Usernames the auth + middleware layer reserve as internal "synthetic owner"
+# sentinels; they must never belong to a real account. The most dangerous is
+# "internal-tool": `core.middleware.require_admin` treats any request whose
+# `current_user == "internal-tool"` as the in-process tool loopback and grants
+# admin, and because the cookie auth path sets `current_user` to the raw
+# username, an account literally named "internal-tool" would be silently
+# treated as an admin by every `require_admin`-gated route. "api" collides with
+# the bearer-token owner-attribution sentinel. "demo"/"system" round out the
+# synthetic-owner set the rest of the codebase already special-cases (see
+# `_SYNTHETIC_OWNERS` in routes/assistant_routes.py and the matching guards in
+# src/task_scheduler.py / routes/research_routes.py) — a real account with one
+# of those names would be denied an assistant and inconsistently owner-scoped.
+# Refuse to create or rename into any of them so the sentinels can't be
+# impersonated. (Keep this in sync with that synthetic-owner set.)
+RESERVED_USERNAMES = frozenset({INTERNAL_TOOL_USER, "api", "demo", "system"})
+
+
+def normalize_known_username(users: Dict[str, Any], username: str | None) -> Optional[str]:
+    """Return a normalized username only when it exists in the auth user map."""
+    key = str(username or "").strip().lower()
+    if not key or key not in users:
+        return None
+    return key
+
 
 def _hash_password(password: str) -> str:
     return bcrypt.hashpw(password.encode("utf-8"), bcrypt.gensalt()).decode("utf-8")
@@ -49,6 +85,15 @@ 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."""
 
@@ -60,16 +105,33 @@ class AuthManager:
         # Guards mutations of self._sessions and the on-disk sessions.json.
         # Validate/create/revoke run concurrently from the FastAPI threadpool.
         self._sessions_lock = threading.RLock()
+        # Guards all mutations of self._config and the on-disk auth.json so
+        # concurrent create/delete/rename/privilege operations don't interleave
+        # and corrupt the user database.
+        self._config_lock = threading.Lock()
+        # Guards the first-run setup check-and-write so concurrent requests
+        # cannot both observe is_configured==False and both create admin accounts.
+        self._setup_lock = threading.Lock()
         self._load()
         self._load_sessions()
         self._migrate_single_user()
+        self._drop_reserved_loaded_users()
         self._migrate_legacy_admin_role()
 
     def _load(self):
         try:
             if os.path.exists(self.auth_path):
-                with open(self.auth_path, "r") as f:
+                with open(self.auth_path, "r", encoding="utf-8") as f:
                     self._config = json.load(f)
+                # Normalize all stored usernames to lowercase so they match
+                # the .strip().lower() applied at login/verify time. Fixes
+                # "Invalid credentials" when auth.json was written with
+                # mixed-case keys (e.g. via manual edit or a future migration).
+                if "users" in self._config:
+                    self._config["users"] = {
+                        k.strip().lower(): v
+                        for k, v in self._config["users"].items()
+                    }
                 logger.info("Auth config loaded")
             else:
                 self._config = {}
@@ -82,7 +144,7 @@ class AuthManager:
         """Load persisted session tokens from disk, pruning expired ones."""
         try:
             if os.path.exists(self._sessions_path):
-                with open(self._sessions_path, "r") as f:
+                with open(self._sessions_path, "r", encoding="utf-8") as f:
                     data = json.load(f)
                 now = time.time()
                 self._sessions = {k: v for k, v in data.items() if v.get("expiry", 0) > now}
@@ -106,20 +168,52 @@ class AuthManager:
     def _migrate_single_user(self):
         """Migrate old single-user format to multi-user format."""
         if "password_hash" in self._config and "users" not in self._config:
-            old_user = self._config.get("username", "admin")
+            old_user = str(self._config.get("username", "admin") or "admin").strip().lower()
+            if old_user in RESERVED_USERNAMES:
+                logger.warning(
+                    "Migrating legacy single-user reserved username '%s' to 'admin'",
+                    old_user,
+                )
+                old_user = "admin"
             old_hash = self._config["password_hash"]
-            self._config = {
-                "users": {
-                    old_user: {
-                        "password_hash": old_hash,
-                        "created": time.time(),
-                        "is_admin": True,
+            with self._config_lock:
+                self._config = {
+                    "users": {
+                        old_user: {
+                            "password_hash": old_hash,
+                            "created": time.time(),
+                            "is_admin": True,
+                        }
                     }
                 }
-            }
-            self._save()
+                self._save()
             logger.info(f"Migrated single-user auth to multi-user (admin: {old_user})")
 
+    def _drop_reserved_loaded_users(self):
+        """Fail closed for legacy/manual auth rows that collide with sentinels."""
+        users = self._config.get("users")
+        if not isinstance(users, dict):
+            return
+        normalized = {}
+        removed = []
+        for username, data in users.items():
+            key = str(username or "").strip().lower()
+            if not key:
+                continue
+            if key in RESERVED_USERNAMES:
+                removed.append(key)
+                continue
+            normalized[key] = data
+        if removed or normalized != users:
+            with self._config_lock:
+                self._config["users"] = normalized
+                self._save()
+        if removed:
+            logger.warning(
+                "Removed reserved username(s) from auth config: %s",
+                ", ".join(sorted(set(removed))),
+            )
+
     def _migrate_legacy_admin_role(self):
         """Normalize setup.py's old role='admin' marker to is_admin=True."""
         changed = False
@@ -144,37 +238,54 @@ class AuthManager:
 
     @signup_enabled.setter
     def signup_enabled(self, value: bool):
-        self._config["signup_enabled"] = value
-        self._save()
+        with self._config_lock:
+            self._config["signup_enabled"] = value
+            self._save()
 
     @property
     def is_configured(self) -> bool:
         return len(self.users) > 0
 
+    def policy(self) -> dict:
+        """Return public auth policy constants for the frontend."""
+        return {
+            "password_min_length": PASSWORD_MIN_LENGTH,
+            "reserved_usernames": sorted(RESERVED_USERNAMES),
+            "signup_enabled": self.signup_enabled,
+            "session_days": TOKEN_TTL // 86400,
+        }
+
     # ------------------------------------------------------------------
     # Account management
     # ------------------------------------------------------------------
 
     def setup(self, username: str, password: str) -> bool:
         """First-run admin setup. Only works if no users exist."""
-        if self.is_configured:
-            return False
-        return self.create_user(username, password, is_admin=True)
+        with self._setup_lock:
+            if self.is_configured:
+                return False
+            return self.create_user(username, password, is_admin=True)
 
     def create_user(self, username: str, password: str, is_admin: bool = False) -> bool:
         """Create a new user account."""
         username = username.strip().lower()
-        if username in self.users:
+        if not username:
             return False
-        if "users" not in self._config:
-            self._config["users"] = {}
-        self._config["users"][username] = {
-            "password_hash": _hash_password(password),
-            "created": time.time(),
-            "is_admin": is_admin,
-            "privileges": dict(ADMIN_PRIVILEGES if is_admin else DEFAULT_PRIVILEGES),
-        }
-        self._save()
+        if username in RESERVED_USERNAMES:
+            logger.warning("Refused to create reserved username '%s'", username)
+            return False
+        with self._config_lock:
+            if username in self.users:
+                return False
+            if "users" not in self._config:
+                self._config["users"] = {}
+            self._config["users"][username] = {
+                "password_hash": _hash_password(password),
+                "created": time.time(),
+                "is_admin": is_admin,
+                "privileges": dict(ADMIN_PRIVILEGES if is_admin else DEFAULT_PRIVILEGES),
+            }
+            self._save()
         logger.info(f"Created user '{username}' (admin={is_admin})")
         return True
 
@@ -187,14 +298,31 @@ class AuthManager:
         their cookie expired naturally (default ~30 days).
         """
         username = username.strip().lower()
-        if username not in self.users:
-            return False
-        if username == requesting_user:
-            return False
-        if not self.users.get(requesting_user, {}).get("is_admin"):
-            return False
-        del self._config["users"][username]
-        self._save()
+        with self._config_lock:
+            if username not in self.users:
+                return False
+            if username == requesting_user:
+                return False
+            if not self.users.get(requesting_user, {}).get("is_admin"):
+                return False
+            # Revoke API bearer tokens before removing the auth row. The bearer
+            # path authenticates from ApiToken rows and does not require the
+            # owner to still exist, so a successful delete must not leave active
+            # rows behind. If the token store is unavailable, fail closed and
+            # keep the user/session state intact so the admin can retry.
+            try:
+                from core.database import get_db_session, ApiToken
+                with get_db_session() as db:
+                    removed_tokens = db.query(ApiToken).filter(ApiToken.owner == username).delete()
+                if removed_tokens:
+                    logger.info(
+                        f"Revoked {removed_tokens} API token(s) owned by deleted user '{username}'"
+                    )
+            except Exception:
+                logger.warning(f"Failed to revoke API tokens for deleted user '{username}'")
+                return False
+            del self._config["users"][username]
+            self._save()
         # Purge all sessions belonging to this user. validate_token doesn't
         # cross-check `self.users`, so without this step a deleted user's
         # cookie keeps authenticating.
@@ -210,6 +338,41 @@ class AuthManager:
         logger.info(f"Deleted user '{username}' (by {requesting_user}); revoked {revoked} active session(s)")
         return True
 
+    def rename_user(self, old_username: str, new_username: str, requesting_user: str) -> bool:
+        """Rename a user in auth config and active sessions. Admin only."""
+        old_username = old_username.strip().lower()
+        new_username = new_username.strip().lower()
+        requesting_user = (requesting_user or "").strip().lower()
+        if not old_username or not new_username:
+            return False
+        if new_username in RESERVED_USERNAMES:
+            logger.warning("Refused to rename '%s' into reserved username '%s'", old_username, new_username)
+            return False
+        with self._config_lock:
+            if old_username not in self.users:
+                return False
+            if new_username in self.users:
+                return False
+            if not self.users.get(requesting_user, {}).get("is_admin"):
+                return False
+            self._config.setdefault("users", {})[new_username] = self._config["users"].pop(old_username)
+            self._save()
+
+        renamed_sessions = 0
+        with self._sessions_lock:
+            for sess in self._sessions.values():
+                sess_user = str((sess or {}).get("username") or "").strip().lower()
+                if sess_user == old_username:
+                    sess["username"] = new_username
+                    renamed_sessions += 1
+        if renamed_sessions:
+            self._save_sessions()
+        logger.info(
+            "Renamed user '%s' -> '%s' (by %s); updated %d active session(s)",
+            old_username, new_username, requesting_user, renamed_sessions,
+        )
+        return True
+
     def is_admin(self, username: str) -> bool:
         return self.users.get(username, {}).get("is_admin", False)
 
@@ -231,28 +394,93 @@ class AuthManager:
     def set_privileges(self, username: str, privileges: Dict[str, Any]) -> bool:
         """Update privileges for a user. Can't modify admin privileges."""
         username = username.strip().lower()
-        if username not in self.users:
-            return False
-        if self.users[username].get("is_admin"):
-            return False  # admins always have full access
-        # Only allow known privilege keys
-        current = self.get_privileges(username)
-        for k, v in privileges.items():
-            if k in DEFAULT_PRIVILEGES:
-                current[k] = v
-        self._config["users"][username]["privileges"] = current
-        self._save()
+        with self._config_lock:
+            if username not in self.users:
+                return False
+            if self.users[username].get("is_admin"):
+                return False  # admins always have full access
+            # Only allow known privilege keys
+            current = self.get_privileges(username)
+            for k, v in privileges.items():
+                if k in DEFAULT_PRIVILEGES:
+                    current[k] = v
+            self._config["users"][username]["privileges"] = current
+            self._save()
         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:
             return False
         if not _verify_password(current_password, self.users[username]["password_hash"]):
             return False
-        self._config["users"][username]["password_hash"] = _hash_password(new_password)
-        self._save()
+        with self._config_lock:
+            self._config["users"][username]["password_hash"] = _hash_password(new_password)
+            self._save()
         return True
 
     # ------------------------------------------------------------------
@@ -270,8 +498,9 @@ class AuthManager:
         if username not in self.users:
             return None
         secret = pyotp.random_base32()
-        self._config["users"][username]["totp_secret_pending"] = secret
-        self._save()
+        with self._config_lock:
+            self._config["users"][username]["totp_secret_pending"] = secret
+            self._save()
         return secret
 
     def totp_get_provisioning_uri(self, username: str, secret: str) -> str:
@@ -290,13 +519,14 @@ class AuthManager:
         if not totp.verify(code, valid_window=1):
             return False
         # Enable 2FA
-        self._config["users"][username]["totp_secret"] = secret
-        self._config["users"][username]["totp_enabled"] = True
-        self._config["users"][username].pop("totp_secret_pending", None)
-        # Generate backup codes
-        backup = [secrets.token_hex(4) for _ in range(8)]
-        self._config["users"][username]["totp_backup_codes"] = backup
-        self._save()
+        with self._config_lock:
+            self._config["users"][username]["totp_secret"] = secret
+            self._config["users"][username]["totp_enabled"] = True
+            self._config["users"][username].pop("totp_secret_pending", None)
+            # Generate backup codes
+            backup = [secrets.token_hex(4) for _ in range(8)]
+            self._config["users"][username]["totp_backup_codes"] = backup
+            self._save()
         logger.info(f"2FA enabled for '{username}'")
         return True
 
@@ -308,13 +538,17 @@ class AuthManager:
             return True  # 2FA not enabled, always pass
         secret = user.get("totp_secret")
         if not secret:
-            return True
+            # 2FA is enabled but no secret is stored (corrupt/partially-written
+            # auth.json). Fail closed — returning True here bypassed the second
+            # factor entirely.
+            return False
         # Check backup codes first
         backup = user.get("totp_backup_codes", [])
         if code in backup:
-            backup.remove(code)
-            self._config["users"][username]["totp_backup_codes"] = backup
-            self._save()
+            with self._config_lock:
+                backup.remove(code)
+                self._config["users"][username]["totp_backup_codes"] = backup
+                self._save()
             logger.info(f"Backup code used for '{username}' ({len(backup)} remaining)")
             return True
         totp = pyotp.TOTP(secret)
@@ -325,11 +559,12 @@ class AuthManager:
         username = username.strip().lower()
         if not self.verify_password(username, password):
             return False
-        self._config["users"][username].pop("totp_secret", None)
-        self._config["users"][username].pop("totp_secret_pending", None)
-        self._config["users"][username].pop("totp_backup_codes", None)
-        self._config["users"][username]["totp_enabled"] = False
-        self._save()
+        with self._config_lock:
+            self._config["users"][username].pop("totp_secret", None)
+            self._config["users"][username].pop("totp_secret_pending", None)
+            self._config["users"][username].pop("totp_backup_codes", None)
+            self._config["users"][username]["totp_enabled"] = False
+            self._save()
         logger.info(f"2FA disabled for '{username}'")
         return True
 
@@ -348,12 +583,22 @@ class AuthManager:
         username = username.strip().lower()
         if not self.verify_password(username, password):
             return None
+        return self.create_session_trusted(username)
+
+    def create_session_trusted(self, username: str) -> Optional[str]:
+        """Issue a session token for an already-verified user.
+        Call only after verify_password (and TOTP if enabled) have passed."""
+        username = username.strip().lower()
         token = secrets.token_hex(32)
-        with self._sessions_lock:
-            self._sessions[token] = {
-                "username": username,
-                "expiry": time.time() + TOKEN_TTL,
-            }
+        with self._config_lock:
+            if username not in self.users:
+                logger.warning("Refused to issue session for missing user '%s'", username)
+                return None
+            with self._sessions_lock:
+                self._sessions[token] = {
+                    "username": username,
+                    "expiry": time.time() + TOKEN_TTL,
+                }
         self._save_sessions()
         return token
 
@@ -412,6 +657,22 @@ class AuthManager:
             self._sessions.pop(token, None)
         self._save_sessions()
 
+    def revoke_user_sessions(self, username: str, except_token: Optional[str] = None) -> int:
+        """Revoke active browser sessions for a user, optionally preserving one."""
+        username = username.strip().lower()
+        revoked = 0
+        with self._sessions_lock:
+            to_drop = [
+                token for token, session in self._sessions.items()
+                if token != except_token and (session or {}).get("username") == username
+            ]
+            for token in to_drop:
+                self._sessions.pop(token, None)
+                revoked += 1
+            if revoked:
+                self._save_sessions()
+        return revoked
+
     def status(self, token: Optional[str]) -> Dict[str, Any]:
         username = self.get_username_for_token(token)
         authenticated = username is not None

core/constants.py

@@ -1,40 +1,12 @@
-# src/constants.py
-"""Application-wide constants and configuration values."""
-import os
+# core/constants.py
+"""Backward-compatible shim — the single source of truth is src/constants.py.
 
-APP_VERSION = "0.9.1"
-
-# Base paths
-BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) + "/"
-STATIC_DIR = os.path.join(BASE_DIR, "static")
-DATA_DIR = os.path.join(BASE_DIR, "data")
-
-# Data file paths
-SESSIONS_FILE = os.path.join(DATA_DIR, "sessions.json")
-MEMORY_FILE = os.path.join(DATA_DIR, "memory.json")
-MEMORY_DOC = os.path.join(DATA_DIR, "memory_doc.md")
-PERSONAL_DIR = os.path.join(DATA_DIR, "personal_docs")
-RUNBOOK_DIR = os.path.join(PERSONAL_DIR, "runbook")
-UPLOAD_DIR = os.path.join(DATA_DIR, "uploads")
-FEATURES_FILE = os.path.join(DATA_DIR, "features.json")
-SETTINGS_FILE = os.path.join(DATA_DIR, "settings.json")
-
-# API Configuration
-MAX_CONTEXT_MESSAGES = 90
-REQUEST_TIMEOUT = 20
-OPENAI_COMPAT_PATH = "/v1/chat/completions"
-
-# Environment variables with defaults
-DEFAULT_HOST = os.getenv("LLM_HOST", "localhost")
-LLM_HOSTS = [h.strip() for h in os.getenv("LLM_HOSTS", "").split(",") if h.strip()]
-OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
-SEARXNG_INSTANCE = os.getenv('SEARXNG_INSTANCE', 'http://localhost:8080')
-
-
-# Cleanup configuration
-CLEANUP_ENABLED = os.getenv("CLEANUP_ENABLED", "True").lower() == "true"
-CLEANUP_INTERVAL_HOURS = int(os.getenv("CLEANUP_INTERVAL_HOURS", "24"))
-
-# Default parameters
-DEFAULT_TEMPERATURE = 1.0
-DEFAULT_MAX_TOKENS = 0
+Historically there were two copies of this module (this one lagged behind at
+APP_VERSION 0.9.1 and was missing the consolidated tool-output constants). To
+kill the drift, this now simply re-exports everything from src.constants so
+there is exactly one place that defines paths and reads ODYSSEUS_DATA_DIR.
+internal_api_base() also lives in src.constants now and is re-exported here so
+existing `from core.constants import internal_api_base` callers keep working.
+"""
+from src.constants import *  # noqa: F401,F403
+from src.constants import internal_api_base  # noqa: F401  (explicit: functions aren't covered by some linters' * checks)

core/exceptions.py

@@ -1,4 +1,4 @@
-# src/exceptions.py
+# core/exceptions.py
 """Custom exceptions for the application."""
 
 class SessionNotFoundError(Exception):

core/log_safety.py

@@ -0,0 +1,27 @@
+"""Helpers for keeping sensitive data out of logs.
+
+Endpoint URLs configured by admins can embed credentials in the userinfo
+(``https://user:pass@host``) or query string (``?api_key=...``). Logging them
+raw leaks those secrets, so route/diagnostic logs run URLs through
+``redact_url`` first. Reconstructing the URL without userinfo/query/fragment
+also doubles as a sanitizer barrier for CodeQL's clear-text-logging query.
+"""
+
+from urllib.parse import urlparse, urlunparse
+
+
+def redact_url(url: str) -> str:
+    """Return a URL safe for logs by removing userinfo and query/fragment.
+
+    Keeps scheme, host, port and path so logs stay useful for debugging.
+    """
+    try:
+        parsed = urlparse(url or "")
+        host = parsed.hostname or ""
+        if ":" in host:  # IPv6 literal — re-bracket so host:port stays unambiguous
+            host = f"[{host}]"
+        if parsed.port:
+            host = f"{host}:{parsed.port}"
+        return urlunparse((parsed.scheme, host, parsed.path, "", "", ""))
+    except Exception:
+        return "<endpoint>"

core/middleware.py

@@ -15,6 +15,17 @@ from starlette.responses import Response
 # same value from this module. Never persisted or exposed externally.
 INTERNAL_TOOL_TOKEN = os.environ.get("ODYSSEUS_INTERNAL_TOKEN") or secrets.token_hex(32)
 INTERNAL_TOOL_HEADER = "X-Odysseus-Internal-Token"
+# Pseudo-username on in-process tool-loopback requests; require_admin trusts it and it is reserved.
+INTERNAL_TOOL_USER = "internal-tool"
+
+
+def is_cors_preflight(method: str, headers) -> bool:
+    """True for a genuine CORS preflight: an OPTIONS request carrying the
+    Access-Control-Request-Method header. Such requests are credential-less by
+    design and must reach CORSMiddleware to be answered -- gating them on auth
+    401s the preflight and breaks every cross-origin browser/WebView client.
+    Pure so it can be unit-tested without standing up the app."""
+    return method == "OPTIONS" and "access-control-request-method" in headers
 
 
 def require_admin(request: Request):
@@ -27,9 +38,10 @@ def require_admin(request: Request):
     # (b) the auth middleware already validated the token and stamped
     #     request.state.current_user = "internal-tool".
     try:
-        if request.headers.get(INTERNAL_TOOL_HEADER) == INTERNAL_TOOL_TOKEN:
+        hdr = request.headers.get(INTERNAL_TOOL_HEADER)
+        if hdr and secrets.compare_digest(hdr, INTERNAL_TOOL_TOKEN):
             return
-        if getattr(request.state, "current_user", None) == "internal-tool":
+        if getattr(request.state, "current_user", None) == INTERNAL_TOOL_USER:
             return
     except Exception:
         pass
@@ -55,13 +67,23 @@ class SecurityHeadersMiddleware(BaseHTTPMiddleware):
         response = await call_next(request)
         path = request.url.path
 
-        # Tool render endpoints are served inside iframes — allow framing by self
+        # Tool render endpoints
         is_tool_render = path.startswith("/api/tools/") and path.endswith("/render")
+        # Document library PDF preview endpoint
+        is_document_pdf_preview = path.startswith("/api/document/") and path.endswith("/render-pdf")
         # Visual report pages are self-contained HTML — need inline scripts + external images
         is_report = path.startswith("/api/research/report/")
 
         response.headers["X-Content-Type-Options"] = "nosniff"
         response.headers["Referrer-Policy"] = "no-referrer"
+        response.headers["Permissions-Policy"] = "camera=(), microphone=(self), geolocation=()"
+
+        is_https = (
+            request.url.scheme == "https"
+            or request.headers.get("X-Forwarded-Proto") == "https"
+        )
+        if is_https:
+            response.headers["Strict-Transport-Security"] = "max-age=31536000; includeSubDomains"
 
         if is_report:
             response.headers["Content-Security-Policy"] = (
@@ -74,10 +96,14 @@ class SecurityHeadersMiddleware(BaseHTTPMiddleware):
                 "frame-ancestors 'none'"
             )
         elif is_tool_render:
-            # Tool iframe content: skip all framing headers — the iframe's
-            # sandbox="allow-scripts" attribute provides isolation.
-            # Don't overwrite the route's own restrictive CSP either.
+            # Skip framing headers for tools.
             pass
+        elif is_document_pdf_preview:
+            response.headers["X-Frame-Options"] = "SAMEORIGIN"
+            response.headers["Content-Security-Policy"] = (
+                "default-src 'none'; "
+                "frame-ancestors 'self'"
+            )
         else:
             response.headers["X-Frame-Options"] = "DENY"
             # NOTE: `style-src 'unsafe-inline'` is intentionally retained.
@@ -91,7 +117,7 @@ class SecurityHeadersMiddleware(BaseHTTPMiddleware):
                 f"script-src 'self' 'nonce-{nonce}' https://cdn.jsdelivr.net; "
                 "style-src 'self' 'unsafe-inline' https://cdn.jsdelivr.net; "
                 "font-src 'self' https://cdn.jsdelivr.net; "
-                "img-src 'self' data: blob:; "
+                "img-src 'self' data: blob: https:; "
                 "media-src 'self' blob:; "
                 "connect-src 'self'; "
                 "frame-src 'self'; "

core/models.py

@@ -11,14 +11,24 @@ from typing import Dict, List, Any, Optional, TYPE_CHECKING
 if TYPE_CHECKING:
     from .session_manager import SessionManager
 
-# Module-level session manager reference (set at app startup)
-_session_manager: Optional["SessionManager"] = None
+# Module-level session manager singleton (single source of truth)
+_SESSION_MANAGER_INSTANCE: Optional["SessionManager"] = None
 
 
-def set_session_manager(manager: "SessionManager"):
-    """Set the global session manager reference."""
-    global _session_manager
-    _session_manager = manager
+def set_session_manager_instance(manager: "SessionManager"):
+    """Set the global SessionManager singleton."""
+    global _SESSION_MANAGER_INSTANCE
+    _SESSION_MANAGER_INSTANCE = manager
+
+
+def get_session_manager_instance() -> Optional["SessionManager"]:
+    """Get the global SessionManager singleton."""
+    return _SESSION_MANAGER_INSTANCE
+
+
+# Keep legacy name for backward compatibility
+set_session_manager = set_session_manager_instance
+get_session_manager = get_session_manager_instance
 
 
 @dataclass
@@ -42,7 +52,17 @@ class ChatMessage:
 
 @dataclass
 class Session:
-    """A chat session — pure data container."""
+    """A chat session — pure data container.
+
+    ``.history`` is the authoritative mutable message list. Callers may
+    read, append, pop, or reassign it directly — these changes take
+    effect immediately. ``_history`` remains a compatibility alias that
+    always resolves to the authoritative ``history`` list.
+
+    Each session gets its own unique history list at construction time
+    (the dataclass default is never shared between instances).
+    """
+
     id: str
     name: str
     endpoint_url: str
@@ -56,29 +76,56 @@ class Session:
     message_count: int = 0
 
     def __post_init__(self):
-        if self.history is None:
-            self.history = []
         if self.headers is None:
             self.headers = {}
+        # Ensure each session gets its OWN list (not the shared dataclass default)
+        if self.history is None:
+            self.history = []
+
+    @property
+    def _history(self) -> List[ChatMessage]:
+        """Compatibility alias for callers that still reference ``_history``."""
+        return self.history
+
+    @_history.setter
+    def _history(self, messages: List[ChatMessage]):
+        self.history = messages
 
     def add_message(self, message: ChatMessage):
         """
         Add a message to this session.
 
-        Delegates to SessionManager for persistence if available,
-        otherwise just appends to history.
+        Appends to the authoritative history list and increments
+        message_count. Delegates to SessionManager for persistence
+        if available.
         """
         self.history.append(message)
         self.message_count = len(self.history)
 
         # Delegate to session manager for persistence
-        if _session_manager:
-            _session_manager._persist_message(self.id, message)
+        if _SESSION_MANAGER_INSTANCE:
+            _SESSION_MANAGER_INSTANCE._persist_message(self.id, message)
 
     def get_context_messages(self) -> List[Dict[str, Any]]:
-        """Get messages in format for LLM API."""
-        return [msg.to_dict() for msg in self.history]
+        """Get messages in format for LLM API.
+
+        Slash-command / setup replies are persisted to history so they render
+        in the transcript, but they are UI chatter (e.g. ``/setup ...`` and its
+        status lines) the user never meant as conversation. They carry
+        ``metadata.source == "slash"``; exclude them here so they never reach
+        the model. Display/history-load paths use the raw ``history`` and are
+        unaffected.
+        """
+        return [
+            msg.to_dict()
+            for msg in self.history
+            if (msg.metadata or {}).get("source") != "slash"
+        ]
 
     def get(self, key: str, default=None):
         """Dict-like access for compatibility."""
         return getattr(self, key, default)
+
+    def __getitem__(self, key: str):
+        """Allow session['field'] syntax."""
+        return getattr(self, key)

core/platform_compat.py

@@ -0,0 +1,452 @@
+"""Cross-platform OS compatibility helpers.
+
+Odysseus began as a Linux/macOS/Docker-only app. This module centralizes the
+small set of OS differences needed to run it *natively* on Windows so the rest
+of the codebase can stay platform-agnostic. Import from here instead of
+sprinkling ``os.name == "nt"`` checks (and POSIX-only calls) across modules.
+
+Design rules:
+  * Stdlib + ctypes only — no new third-party deps (no psutil/pywinpty).
+  * POSIX behaviour is unchanged; Windows gets a faithful equivalent or a
+    safe, documented no-op.
+"""
+
+from __future__ import annotations
+
+import os
+import ntpath
+import shutil
+import subprocess
+from pathlib import Path
+import sys
+from typing import List, Optional
+import platform
+
+IS_WINDOWS = os.name == "nt"
+IS_POSIX = not IS_WINDOWS
+# Allows APFEL support and ARM-native binary recommendations on Apple Silicon Macs.
+IS_APPLE_SILICON = (
+    IS_POSIX
+    and platform.system() == "Darwin"
+    and platform.machine().lower()
+    in {
+        "arm64",
+        "aarch64",
+    }
+)
+
+
+# ── File permissions ────────────────────────────────────────────────────────
+def safe_chmod(path, mode: int) -> bool:
+    """``os.chmod`` that is a harmless no-op on Windows.
+
+    On POSIX we apply the mode — used to lock secret/key files down to 0o600.
+    Windows has no POSIX permission bits; files under the user profile are
+    already ACL-restricted to that user, so we skip rather than raise. Returns
+    True when the mode was actually applied.
+    """
+    if IS_WINDOWS:
+        return False
+    try:
+        os.chmod(path, mode)
+        return True
+    except OSError:
+        return False
+
+
+# ── Process detach / liveness / teardown ────────────────────────────────────
+def detached_popen_kwargs() -> dict:
+    """Keyword args for :class:`subprocess.Popen` that fully detach a child so
+    it outlives the request/stream that launched it.
+
+    POSIX: ``start_new_session=True`` (setsid) — new session + process group.
+    Windows: ``CREATE_NEW_PROCESS_GROUP | DETACHED_PROCESS`` — the child gets
+    its own process group (so it isn't killed when the parent's console closes)
+    and is detached from any console.
+    """
+    if IS_WINDOWS:
+        flags = getattr(subprocess, "CREATE_NEW_PROCESS_GROUP", 0x00000200) | getattr(
+            subprocess, "DETACHED_PROCESS", 0x00000008
+        )
+        return {"creationflags": flags}
+    return {"start_new_session": True}
+
+
+def pid_alive(pid: Optional[int]) -> bool:
+    """True if a process with ``pid`` is currently running.
+
+    POSIX uses the classic ``os.kill(pid, 0)`` probe. That is **unsafe on
+    Windows**: CPython's ``os.kill`` calls ``TerminateProcess(handle, sig)`` for
+    any signal other than CTRL_C/CTRL_BREAK, so ``os.kill(pid, 0)`` would *kill*
+    the process it is checking. We instead open the process and read its exit
+    code via the Win32 API.
+    """
+    if not pid:
+        return False
+    if IS_WINDOWS:
+        import ctypes
+        from ctypes import wintypes
+
+        PROCESS_QUERY_LIMITED_INFORMATION = 0x1000
+        STILL_ACTIVE = 259
+        kernel32 = ctypes.windll.kernel32
+        handle = kernel32.OpenProcess(
+            PROCESS_QUERY_LIMITED_INFORMATION, False, int(pid)
+        )
+        if not handle:
+            return False
+        try:
+            code = wintypes.DWORD()
+            if kernel32.GetExitCodeProcess(handle, ctypes.byref(code)):
+                return code.value == STILL_ACTIVE
+            return False
+        finally:
+            kernel32.CloseHandle(handle)
+    try:
+        os.kill(pid, 0)
+        return True
+    except (OSError, ProcessLookupError):
+        return False
+
+
+def kill_process_tree(pid: Optional[int]) -> None:
+    """Terminate ``pid`` and all of its descendants.
+
+    POSIX: signal the whole process group (``killpg``), falling back to a plain
+    ``kill`` if the pid isn't a group leader.
+    Windows: ``taskkill /T /F`` walks and kills the child tree (there is no
+    process-group signalling).
+    """
+    if not pid:
+        return
+    if IS_WINDOWS:
+        try:
+            subprocess.run(
+                ["taskkill", "/F", "/T", "/PID", str(pid)],
+                stdout=subprocess.DEVNULL,
+                stderr=subprocess.DEVNULL,
+                creationflags=getattr(subprocess, "CREATE_NO_WINDOW", 0),
+            )
+        except Exception:
+            pass
+        return
+    import signal
+
+    try:
+        os.killpg(os.getpgid(pid), signal.SIGTERM)
+    except Exception:
+        try:
+            os.kill(pid, signal.SIGTERM)
+        except Exception:
+            pass
+
+
+# ── Shell / executable resolution ───────────────────────────────────────────
+_BASH_CACHE: Optional[str] = None
+_BASH_PROBED = False
+
+# Common Git-for-Windows install locations to probe when bash isn't on PATH.
+_WINDOWS_BASH_ROOT_ENV_VARS = (
+    "ProgramFiles",
+    "ProgramW6432",
+    "ProgramFiles(x86)",
+    "LocalAppData",
+)
+_WINDOWS_BASH_DEFAULT_ROOTS = (
+    r"C:\Program Files\Git",
+    r"C:\Program Files (x86)\Git",
+)
+_WINDOWS_BASH_RELATIVE_PATHS = (
+    ("bin", "bash.exe"),
+    ("usr", "bin", "bash.exe"),
+)
+
+# Paths to add to the remote SSH probe command to find tools like nvidia-smi that may not be on PATH.
+_SSH_PATH_MEMBERS = (
+    "/usr/bin",
+    "/usr/local/bin",
+    "/usr/local/cuda/bin",
+    "/usr/lib/wsl/lib"
+)
+# Fallback locations for nvidia-smi on WSL and other Linux distros where it may not be on PATH.
+NVIDIA_PATH_CANDIDATES = (
+    "/usr/bin/nvidia-smi",
+    "/usr/local/bin/nvidia-smi",
+    "/usr/local/cuda/bin/nvidia-smi",
+    "/usr/lib/wsl/lib/nvidia-smi",
+)
+
+
+def _ssh_path_override() -> str:
+    """Build the PATH export snippet used for remote SSH shell probes."""
+    return f"export PATH=\"$PATH:{':'.join(_SSH_PATH_MEMBERS)}\"; "
+
+
+SSH_PATH_OVERRIDE = _ssh_path_override()
+
+
+def _windows_bash_fallbacks() -> List[str]:
+    roots: List[str] = []
+    for env_name in _WINDOWS_BASH_ROOT_ENV_VARS:
+        base = os.environ.get(env_name)
+        if base:
+            roots.append(ntpath.join(base, "Git"))
+            if env_name == "LocalAppData":
+                roots.append(ntpath.join(base, "Programs", "Git"))
+    roots.extend(_WINDOWS_BASH_DEFAULT_ROOTS)
+
+    paths: List[str] = []
+    seen = set()
+    for root in roots:
+        for rel in _WINDOWS_BASH_RELATIVE_PATHS:
+            path = ntpath.join(root, *rel)
+            key = path.lower()
+            if key not in seen:
+                seen.add(key)
+                paths.append(path)
+    return paths
+
+
+def _is_windows_bash_stub(path: str) -> bool:
+    lowered = path.lower()
+    return (
+        "system32\\bash.exe" in lowered
+        or "sysnative\\bash.exe" in lowered
+        or "windowsapps\\bash.exe" in lowered
+    )
+
+
+def git_bash_path(path: str | Path) -> str:
+    """Convert a path to POSIX style suitable for Git Bash on Windows.
+
+    Transforms drive letters (e.g., 'C:\\path') to POSIX '/c/path',
+    and uses forward slashes.
+    """
+    p = Path(path)
+    p_str = p.as_posix()
+    if IS_WINDOWS and len(p_str) >= 2 and p_str[1] == ":":
+        drive = p_str[0].lower()
+        return f"/{drive}{p_str[2:]}"
+    return p_str
+
+
+
+def find_bash() -> Optional[str]:
+    """Locate a real ``bash`` interpreter, or None.
+
+    On Windows this is typically Git Bash / WSL. Many Odysseus features (the
+    agent ``bash`` tool, background jobs, Cookbook scripts) emit bash syntax, so
+    when a bash is present we use it and keep full parity with POSIX. Result is
+    cached.
+    """
+    global _BASH_CACHE, _BASH_PROBED
+    if _BASH_PROBED:
+        return _BASH_CACHE
+    _BASH_PROBED = True
+    found = which_tool("bash")
+    if found and IS_WINDOWS and _is_windows_bash_stub(found):
+        found = None
+    if not found and IS_WINDOWS:
+        for cand in _windows_bash_fallbacks():
+            if os.path.exists(cand):
+                found = cand
+                break
+    _BASH_CACHE = found
+    return found
+
+
+def has_bash() -> bool:
+    return find_bash() is not None
+
+
+def which_tool(name: str) -> Optional[str]:
+    """``shutil.which`` that also tries Windows executable suffixes.
+
+    On Windows, Node/npm shims are ``npx.cmd``/``npm.cmd`` and binaries end in
+    ``.exe``; a bare ``which("npx")`` can miss them depending on PATHEXT. We try
+    the bare name first, then the common suffixes.
+    """
+    found = shutil.which(name)
+    if found:
+        return found
+    if IS_WINDOWS:
+        for ext in (".cmd", ".exe", ".bat"):
+            found = shutil.which(name + ext)
+            if found:
+                return found
+    return None
+
+
+def run_script_argv(script_path) -> List[str]:
+    """argv to execute a shell *script file*.
+
+    Prefers bash (so existing ``.sh`` wrappers work verbatim, including on
+    Windows via Git Bash). On Windows with no bash available, falls back to
+    ``cmd.exe /c`` — simple commands still run, but bash-specific syntax won't.
+    Callers that need guaranteed bash should check :func:`has_bash` first and
+    surface a clear "install Git Bash" message.
+    """
+    bash = find_bash()
+    if bash:
+        return [bash, str(script_path)]
+    if IS_WINDOWS:
+        comspec = os.environ.get("ComSpec", "cmd.exe")
+        return [comspec, "/c", str(script_path)]
+    return ["sh", str(script_path)]
+
+
+def is_wsl() -> bool:
+    """True if running inside Windows Subsystem for Linux (WSL)."""
+    import sys
+    if sys.platform.startswith("linux") or os.name == "posix":
+        try:
+            with open("/proc/version", "r", encoding="utf-8", errors="ignore") as f:
+                if "microsoft" in f.read().lower():
+                    return True
+        except Exception:
+            pass
+    return False
+
+
+def translate_path(path_str: str) -> str:
+    """Translate a path (possibly a Windows path) to the current OS format.
+
+    Particularly handles Windows paths (e.g. C:\\foo or C:/foo) when running
+    under WSL, translating them to /mnt/c/foo.
+    Also handles standard path normalization to avoid string breakages.
+    """
+    if not path_str:
+        return path_str
+
+    if is_wsl():
+        path_str = path_str.replace("\\", "/")
+        import re
+        m = re.match(r"^([a-zA-Z]):(.*)", path_str)
+        if m:
+            drive = m.group(1).lower()
+            rest = m.group(2)
+            if not rest.startswith("/"):
+                rest = "/" + rest
+            return f"/mnt/{drive}{rest}"
+
+    try:
+        return str(Path(path_str).resolve())
+    except Exception:
+        return path_str
+
+
+def get_wsl_windows_user_profile() -> Optional[str]:
+    """Retrieve the Windows host User Profile path from inside WSL."""
+    if not is_wsl():
+        return None
+    try:
+        r = run_wsl_windows_powershell("Write-Output $env:USERPROFILE", timeout=5)
+        if r.returncode == 0 and r.stdout.strip():
+            return translate_path(r.stdout.strip())
+    except Exception:
+        pass
+
+    try:
+        users_dir = "/mnt/c/Users"
+        if os.path.isdir(users_dir):
+            for entry in os.listdir(users_dir):
+                if entry not in ("All Users", "Default", "Default User", "desktop.ini", "Public"):
+                    path = os.path.join(users_dir, entry)
+                    if os.path.isdir(path):
+                        return path
+    except Exception:
+        pass
+    return None
+
+
+def _ssh_exec_argv(
+    remote: str,
+    ssh_port: str | None,
+    *,
+    remote_cmd: str | None = None,
+    connect_timeout: int | None = None,
+    strict_host_key_checking: bool | None = None,
+) -> list[str]:
+    """Build a consistent ssh argv for remote command execution."""
+    remote_value = str(remote or "").strip()
+    remote_host = remote_value.rsplit("@", 1)[-1]
+    if not remote_value or remote_value.startswith("-") or not remote_host or remote_host.startswith("-"):
+        raise ValueError("Invalid SSH remote host")
+    argv = ["ssh"]
+    if connect_timeout is not None:
+        argv.extend(["-o", f"ConnectTimeout={int(connect_timeout)}"])
+    if strict_host_key_checking is not None:
+        argv.extend(
+            [
+                "-o",
+                "StrictHostKeyChecking=yes"
+                if strict_host_key_checking
+                else "StrictHostKeyChecking=no",
+            ]
+        )
+    if ssh_port and ssh_port != "22":
+        argv.extend(["-p", str(ssh_port)])
+    argv.append(remote)
+    if remote_cmd is not None:
+        argv.append(remote_cmd)
+    return argv
+
+
+def run_ssh_command(
+    remote: str,
+    ssh_port: str | None,
+    remote_cmd: str,
+    *,
+    timeout: float,
+    connect_timeout: int | None = None,
+    strict_host_key_checking: bool | None = None,
+    text: bool = True,
+) -> subprocess.CompletedProcess:
+    """Run an ssh command with centralized timeout and stderr/stdout capture."""
+    return subprocess.run(
+        _ssh_exec_argv(
+            remote,
+            ssh_port,
+            remote_cmd=remote_cmd,
+            connect_timeout=connect_timeout,
+            strict_host_key_checking=strict_host_key_checking,
+        ),
+        timeout=timeout,
+        capture_output=True,
+        text=text,
+    )
+
+
+def _windows_powershell_argv(
+    command: str,
+    *,
+    no_profile: bool = True,
+    non_interactive: bool = True,
+) -> List[str]:
+    argv: List[str] = ["powershell.exe"]
+    if no_profile:
+        argv.append("-NoProfile")
+    if non_interactive:
+        argv.append("-NonInteractive")
+    argv.extend(["-Command", command])
+    return argv
+
+
+def run_wsl_windows_powershell(
+    command: str,
+    *,
+    timeout: float = 5,
+) -> subprocess.CompletedProcess[str]:
+    """Run a PowerShell command on the Windows host from WSL.
+
+    Raises ``RuntimeError`` when called outside WSL.
+    """
+
+    if not is_wsl():
+        raise RuntimeError("run_wsl_windows_powershell is only supported in WSL")
+    return subprocess.run(
+        _windows_powershell_argv(command),
+        capture_output=True,
+        text=True,
+        timeout=timeout,
+    )

core/session_manager.py

@@ -14,12 +14,52 @@ import logging
 from datetime import datetime, timezone, timedelta
 from typing import Dict, Optional
 
-from .database import Session as DbSession, ChatMessage as DbChatMessage, Document as DbDocument, SessionLocal
+from .database import Session as DbSession, ChatMessage as DbChatMessage, Document as DbDocument, SessionLocal, utcnow_naive
 from .models import Session, ChatMessage
+from src.attachment_refs import persistable_message_content
+from src.upload_handler import reserve_message_upload_references
+
+# Re-export singleton accessors from models for convenience
+from .models import set_session_manager_instance, get_session_manager_instance
 
 logger = logging.getLogger(__name__)
 
 
+def _message_timestamp_iso(value: Optional[datetime]) -> Optional[str]:
+    """Return a stable ISO timestamp for chat message metadata."""
+    if not value:
+        return None
+    if value.tzinfo is None:
+        value = value.replace(tzinfo=timezone.utc)
+    return value.isoformat().replace("+00:00", "Z")
+
+
+def _parse_msg_content(raw):
+    """Parse message content from DB — deserialises JSON arrays back to lists
+    (multimodal content with image/audio attachments)."""
+    if isinstance(raw, list):
+        return raw
+    if isinstance(raw, str) and raw.startswith('[{') and '"type"' in raw:
+        try:
+            parsed = json.loads(raw)
+            # Only treat as serialized multimodal content when EVERY element is
+            # a dict whose "type" is a recognized content-block kind. Otherwise a
+            # plain text message that merely *looks* like a JSON array of objects
+            # (e.g. a user pasting an API schema/sample with a "type" field) was
+            # silently parsed back into a list, destroying the original string.
+            _BLOCK_TYPES = {
+                "text", "image", "image_url", "audio", "input_audio",
+                "input_image", "document", "file",
+            }
+            if (isinstance(parsed, list) and parsed
+                    and all(isinstance(p, dict) and p.get("type") in _BLOCK_TYPES
+                            for p in parsed)):
+                return parsed
+        except (json.JSONDecodeError, ValueError):
+            pass
+    return raw
+
+
 class SessionManager:
     """
     Manages chat sessions with database persistence.
@@ -34,6 +74,7 @@ class SessionManager:
     def __init__(self, sessions_file: str = None):
         # sessions_file kept for backward compat, not used
         self.sessions: Dict[str, Session] = {}
+        self.upload_handler = None
         self.load_sessions()
 
     # ------------------------------------------------------------------
@@ -107,9 +148,10 @@ class SessionManager:
                 meta = json.loads(db_msg.meta_data) if db_msg.meta_data else {}
                 if meta is None: meta = {}
                 meta['_db_id'] = db_msg.id
+                meta.setdefault('timestamp', _message_timestamp_iso(db_msg.timestamp))
                 history.append(ChatMessage(
                     role=db_msg.role,
-                    content=db_msg.content,
+                    content=_parse_msg_content(db_msg.content),
                     metadata=meta,
                 ))
         else:
@@ -121,9 +163,10 @@ class SessionManager:
                 meta = json.loads(db_msg.meta_data) if db_msg.meta_data else {}
                 if meta is None: meta = {}
                 meta['_db_id'] = db_msg.id
+                meta.setdefault('timestamp', _message_timestamp_iso(db_msg.timestamp))
                 history.append(ChatMessage(
                     role=db_msg.role,
-                    content=db_msg.content,
+                    content=_parse_msg_content(db_msg.content),
                     metadata=meta,
                 ))
 
@@ -162,12 +205,17 @@ class SessionManager:
         """
         Add a message to a session and persist to database.
 
+        Updates the authoritative history list and persists through this
+        manager directly so tests and temporary managers do not depend on the
+        process-wide session-manager singleton.
+
         Args:
             session_id: Session ID
             message: ChatMessage to add
         """
         session = self.get_session(session_id)
         session.history.append(message)
+        session._history = session.history
         session.message_count = len(session.history)
 
         self._persist_message(session_id, message)
@@ -176,31 +224,59 @@ class SessionManager:
         """Persist a single message to the database."""
         db = SessionLocal()
         try:
+            db_session = db.query(DbSession).filter(DbSession.id == session_id).first()
+            if db_session is None:
+                # A stream/tool callback can outlive a session delete. Do not
+                # create a chat_messages row with no parent session; also drop
+                # any stale cached session so later writes fail closed too.
+                self.sessions.pop(session_id, None)
+                logger.warning("Dropping message for deleted session %s", session_id)
+                return
+
+            missing_upload_id = reserve_message_upload_references(
+                getattr(self, "upload_handler", None),
+                getattr(db_session, "owner", None),
+                message.content,
+                message.metadata,
+            )
+            if missing_upload_id:
+                raise ValueError(
+                    f"Referenced upload is no longer available: {missing_upload_id}"
+                )
+
             msg_id = str(uuid.uuid4())
+            msg_time = datetime.utcnow()
+            if message.metadata is None:
+                message.metadata = {}
+            message.metadata.setdefault('timestamp', _message_timestamp_iso(msg_time))
+            # Multimodal content may contain provider data URLs for the live
+            # model call. Persist only readable text plus attachment references
+            # so chat_messages/FTS do not duplicate upload bytes.
+            _content = persistable_message_content(message.content, message.metadata)
             db_message = DbChatMessage(
                 id=msg_id,
                 session_id=session_id,
                 role=message.role,
-                content=message.content,
-                meta_data=json.dumps(message.metadata) if message.metadata else None
+                content=_content,
+                meta_data=json.dumps(message.metadata) if message.metadata else None,
+                timestamp=msg_time,
             )
             db.add(db_message)
 
-            db_session = db.query(DbSession).filter(DbSession.id == session_id).first()
-            if db_session:
-                db_session.message_count = len(self.sessions.get(session_id, {}).history) if session_id in self.sessions else 0
-                _now = datetime.now(timezone.utc)
-                db_session.last_accessed = _now
-                # Clean "last conversation" timestamp — only bumped here on a
-                # real message persist, so it powers an accurate "Last active"
-                # sort that ignores renames / model swaps / mere opens.
-                db_session.last_message_at = _now
+            if session_id in self.sessions:
+                db_session.message_count = len(self.sessions[session_id].history)
+            else:
+                db_session.message_count = 0
+            _now = datetime.now(timezone.utc)
+            db_session.last_accessed = _now
+            # Clean "last conversation" timestamp — only bumped here on a
+            # real message persist, so it powers an accurate "Last active"
+            # sort that ignores renames / model swaps / mere opens.
+            db_session.last_message_at = _now
 
             db.commit()
 
             # Store DB ID on the in-memory message for edit/delete by ID
-            if message.metadata is None:
-                message.metadata = {}
             message.metadata['_db_id'] = msg_id
 
             logger.debug(f"Persisted message to session {session_id}")
@@ -231,13 +307,17 @@ class SessionManager:
 
             db_session = db.query(DbSession).filter(DbSession.id == session_id).first()
             if db_session:
-                db_session.message_count = keep_count
+                # keep_count can exceed the real message total (e.g. the AI tool
+                # defaults to keep_count=10 on a short session); message_count must
+                # track the rows that actually remain, not the requested cap.
+                db_session.message_count = min(keep_count, len(db_messages))
                 db_session.updated_at = datetime.now(timezone.utc)
 
             db.commit()
 
             # Update in-memory
             session.history = session.history[:keep_count]
+            session._history = session.history
 
             logger.info(f"Truncated session {session_id} to {keep_count} messages")
             return True
@@ -254,6 +334,28 @@ class SessionManager:
         session = self.get_session(session_id)
         db = SessionLocal()
         try:
+            db_session = db.query(DbSession).filter(DbSession.id == session_id).first()
+            if db_session is None:
+                logger.warning("Cannot replace history for missing session %s", session_id)
+                return False
+
+            # Reserve every incoming attachment before removing any durable
+            # message row. reserve_upload() shares the upload lifecycle lock
+            # with cleanup, so an upload cannot be deleted between this
+            # ownership check/access touch and the replacement transaction.
+            # A failed reservation must leave the existing transcript intact.
+            for message in messages:
+                missing_upload_id = reserve_message_upload_references(
+                    getattr(self, "upload_handler", None),
+                    getattr(db_session, "owner", None),
+                    message.content,
+                    message.metadata,
+                )
+                if missing_upload_id:
+                    raise ValueError(
+                        f"Referenced upload is no longer available: {missing_upload_id}"
+                    )
+
             db.query(DbChatMessage).filter(DbChatMessage.session_id == session_id).delete()
             now = datetime.now(timezone.utc)
             for i, message in enumerate(messages):
@@ -262,7 +364,9 @@ class SessionManager:
                     id=msg_id,
                     session_id=session_id,
                     role=message.role,
-                    content=message.content,
+                    # Mirrors _persist_message: keep raw media bytes out of the
+                    # persisted transcript and search index.
+                    content=persistable_message_content(message.content, message.metadata),
                     meta_data=json.dumps(message.metadata) if message.metadata else None,
                     timestamp=now + timedelta(microseconds=i),
                 )
@@ -271,15 +375,14 @@ class SessionManager:
                     message.metadata = {}
                 message.metadata["_db_id"] = msg_id
 
-            db_session = db.query(DbSession).filter(DbSession.id == session_id).first()
-            if db_session:
-                db_session.message_count = len(messages)
-                db_session.updated_at = now
-                db_session.last_accessed = now
-                db_session.last_message_at = now
+            db_session.message_count = len(messages)
+            db_session.updated_at = now
+            db_session.last_accessed = now
+            db_session.last_message_at = now
 
             db.commit()
             session.history = list(messages)
+            session._history = session.history
             session.message_count = len(messages)
             logger.info("Replaced session %s history with %d messages", session_id, len(messages))
             return True
@@ -440,6 +543,12 @@ class SessionManager:
         """Permanently delete a session and all its messages."""
         db = SessionLocal()
         try:
+            try:
+                from src.session_image_cleanup import cleanup_session_images
+                cleanup_session_images(session_id, db=db)
+            except Exception as e:
+                logger.warning(f"Image cleanup failed while deleting session {session_id}: {e}")
+
             # Detach documents so they survive as orphans in the library
             db.query(DbDocument).filter(DbDocument.session_id == session_id).update(
                 {DbDocument.session_id: None}, synchronize_session=False
@@ -452,11 +561,17 @@ class SessionManager:
             db_session = db.query(DbSession).filter(DbSession.id == session_id).first()
             if db_session:
                 db.delete(db_session)
+
+            # Drop the in-memory copy even when there is no DB row. A "ghost"
+            # session lives only here (never persisted, or its row was removed
+            # out-of-band); without this it can never be cleared and keeps
+            # 404ing on every operation (issue #1044).
+            removed_in_memory = self.sessions.pop(session_id, None) is not None
+
+            if db_session or removed_in_memory:
+                # Commit the document-detach / message-delete above (a no-op when
+                # the ghost had no rows) together with the session delete.
                 db.commit()
-
-                if session_id in self.sessions:
-                    del self.sessions[session_id]
-
                 logger.info(f"Deleted session {session_id}")
                 return True
             return False
@@ -549,24 +664,52 @@ class SessionManager:
     def save_sessions(self):
         """No-op for DB compatibility."""
 
+    def ensure_task_session(self, session_id: str, name: str, endpoint_url: str, model: str, owner: str = None, task: object = None) -> Session:
+        """Create a task session if it doesn't exist, or return the existing one.
+
+        Unlike create_session, this checks the cache first and does NOT
+        overwrite an existing in-memory session. The task scheduler must
+        use this instead of direct dict assignment.
+        """
+        if session_id in self.sessions:
+            return self.sessions[session_id]
+
+        session = self.create_session(session_id, name, endpoint_url, model, owner=owner)
+        if task is not None:
+            task.session_id = session_id
+        return session
+
     # ------------------------------------------------------------------
     # Cleanup
     # ------------------------------------------------------------------
 
-    def cleanup_empty_sessions(self, auto_archive_days: int = 30) -> dict:
-        """Clean up empty and old sessions."""
+    def cleanup_empty_sessions(self, auto_archive_days: int = 30, min_age_hours: int = 1) -> dict:
+        """Clean up empty and old sessions.
+
+        Args:
+            auto_archive_days: Age in days before non-important sessions are archived.
+            min_age_hours: Minimum age in hours before an empty session can be deleted.
+                          Prevents deleting sessions that were just created.
+        """
         db = SessionLocal()
         stats = {'deleted_empty': 0, 'archived_old': 0, 'total_checked': 0}
 
         try:
             all_sessions = db.query(DbSession).all()
-            cutoff_date = datetime.now(timezone.utc) - timedelta(days=auto_archive_days)
+            cutoff_date = utcnow_naive() - timedelta(days=auto_archive_days)
+            min_age = utcnow_naive() - timedelta(hours=min_age_hours)
 
             for db_session in all_sessions:
                 stats['total_checked'] += 1
 
-                # Delete empty sessions
+                # Delete empty sessions only if older than min_age_hours
                 if db_session.message_count == 0:
+                    if db_session.created_at is not None:
+                        created = db_session.created_at
+                        if created.tzinfo is None:
+                            created = created.replace(tzinfo=timezone.utc)
+                        if created > min_age:
+                            continue  # Too young to delete
                     if db_session.id in self.sessions:
                         del self.sessions[db_session.id]
                     db.delete(db_session)

docker-compose.gpu-amd.yml

@@ -0,0 +1,177 @@
+# Standalone AMD ROCm GPU Compose file for stack-management UIs (Portainer,
+# Coolify, Dockhand, etc.) that accept only a single Compose file and do not
+# reliably honor COMPOSE_FILE or multiple `-f` overlays.
+#
+# This is equivalent to: docker-compose.yml + docker/gpu.amd.yml.
+# The base docker-compose.yml plus the docker/gpu.amd.yml overlay remain the
+# source of truth — CLI users should keep using the COMPOSE_FILE overlay
+# workflow. Keep this file in sync with both when either changes.
+#
+# Requires ROCm drivers on the host (kfd + DRI devices) and the host user
+# running Docker in the `video` and `render` groups. Set RENDER_GID to your
+# host's numeric render group id when needed. See docker/gpu.amd.yml for details.
+services:
+  odysseus:
+    build: .
+    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
+      # 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
+      # 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
+      # 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.
+      - ${APP_DATA_DIR:-./data}/local:/app/.local:z
+    extra_hosts:
+      # Lets the container reach local services on the Docker host, including
+      # Ollama at http://host.docker.internal:11434.
+      - "host.docker.internal:host-gateway"
+    environment:
+      - LLM_HOST=${LLM_HOST:-localhost}
+      - LLM_HOSTS=${LLM_HOSTS:-}
+      - OPENAI_API_KEY=${OPENAI_API_KEY:-}
+      - OLLAMA_BASE_URL=${OLLAMA_BASE_URL:-}
+      - RESEARCH_LLM_ENDPOINT=${RESEARCH_LLM_ENDPOINT:-}
+      - HF_TOKEN=${HF_TOKEN:-}
+      - HUGGING_FACE_HUB_TOKEN=${HUGGING_FACE_HUB_TOKEN:-}
+      - SEARXNG_INSTANCE=http://searxng:8080
+      - CHROMADB_HOST=chromadb
+      - CHROMADB_PORT=8000
+      - DATABASE_URL=${DATABASE_URL:-sqlite:///./data/app.db}
+      - AUTH_ENABLED=${AUTH_ENABLED:-true}
+      - LOCALHOST_BYPASS=${LOCALHOST_BYPASS:-false}
+      - ODYSSEUS_ADMIN_USER=${ODYSSEUS_ADMIN_USER:-admin}
+      - ODYSSEUS_ADMIN_PASSWORD=${ODYSSEUS_ADMIN_PASSWORD:-}
+      - ALLOWED_ORIGINS=${ALLOWED_ORIGINS:-http://localhost,http://127.0.0.1}
+      - SECURE_COOKIES=${SECURE_COOKIES:-false}
+      - EMBEDDING_URL=${EMBEDDING_URL:-}
+      - EMBEDDING_MODEL=${EMBEDDING_MODEL:-}
+      - EMBEDDING_API_KEY=${EMBEDDING_API_KEY:-}
+      - FASTEMBED_MODEL=${FASTEMBED_MODEL:-sentence-transformers/all-MiniLM-L6-v2}
+      - FASTEMBED_CACHE_PATH=${FASTEMBED_CACHE_PATH:-}
+      - CLEANUP_INTERVAL_HOURS=${CLEANUP_INTERVAL_HOURS:-24}
+      - ODYSSEUS_INPROCESS_POLLERS=${ODYSSEUS_INPROCESS_POLLERS:-1}
+      - ODYSSEUS_INPROCESS_TASKS=${ODYSSEUS_INPROCESS_TASKS:-1}
+      - ODYSSEUS_SCRIPT_HOST=${ODYSSEUS_SCRIPT_HOST:-localhost}
+      - ODYSSEUS_CHAT_UPLOAD_MAX_BYTES=${ODYSSEUS_CHAT_UPLOAD_MAX_BYTES:-10485760}
+      - ODYSSEUS_GALLERY_UPLOAD_MAX_BYTES=${ODYSSEUS_GALLERY_UPLOAD_MAX_BYTES:-104857600}
+      - ODYSSEUS_GALLERY_TRANSFORM_UPLOAD_MAX_BYTES=${ODYSSEUS_GALLERY_TRANSFORM_UPLOAD_MAX_BYTES:-26214400}
+      - ODYSSEUS_MEMORY_IMPORT_MAX_BYTES=${ODYSSEUS_MEMORY_IMPORT_MAX_BYTES:-10485760}
+      - ODYSSEUS_PERSONAL_UPLOAD_MAX_BYTES=${ODYSSEUS_PERSONAL_UPLOAD_MAX_BYTES:-26214400}
+      - ODYSSEUS_EMAIL_COMPOSE_UPLOAD_MAX_BYTES=${ODYSSEUS_EMAIL_COMPOSE_UPLOAD_MAX_BYTES:-26214400}
+      - ODYSSEUS_STT_MAX_AUDIO_BYTES=${ODYSSEUS_STT_MAX_AUDIO_BYTES:-26214400}
+      - ODYSSEUS_ICS_MAX_BYTES=${ODYSSEUS_ICS_MAX_BYTES:-10485760}
+      - ODYSSEUS_TTS_CACHE_MAX_BYTES=${ODYSSEUS_TTS_CACHE_MAX_BYTES}
+      - DATA_BRAVE_API_KEY=${DATA_BRAVE_API_KEY:-}
+      - GOOGLE_API_KEY=${GOOGLE_API_KEY:-}
+      - GOOGLE_PSE_CX=${GOOGLE_PSE_CX:-}
+      - GOOGLE_OAUTH_CLIENT_ID=${GOOGLE_OAUTH_CLIENT_ID:-}
+      - GOOGLE_OAUTH_CLIENT_SECRET=${GOOGLE_OAUTH_CLIENT_SECRET:-}
+      - GOOGLE_OAUTH_REDIRECT_URI=${GOOGLE_OAUTH_REDIRECT_URI:-}
+      - TAVILY_API_KEY=${TAVILY_API_KEY:-}
+      - SERPER_API_KEY=${SERPER_API_KEY:-}
+      # PUID / PGID — the user/group the container drops to before
+      # running uvicorn (entrypoint also chowns /app/data + /app/logs
+      # to match, so bind-mounted files stay editable from the host).
+      # 1000 is the default first user on most Linux installs. If your
+      # host user has a different id, override here or via .env, e.g.:
+      #   PUID=1001
+      #   PGID=1001
+      # Find yours with:  id -u  /  id -g
+      - PUID=${PUID:-1000}
+      - PGID=${PGID:-1000}
+    depends_on:
+      searxng:
+        condition: service_healthy
+      chromadb:
+        condition: service_started
+    restart: unless-stopped
+    # AMD ROCm overlay (from docker/gpu.amd.yml).
+    devices:
+      - /dev/kfd
+      - /dev/dri
+    group_add:
+      - video
+      - ${RENDER_GID:-render}
+
+  chromadb:
+    image: docker.io/chromadb/chroma:latest
+    ports:
+      - "${CHROMADB_BIND:-127.0.0.1}:8100:8000"
+    volumes:
+      - chromadb-data:/chroma/chroma
+    environment:
+      - ANONYMIZED_TELEMETRY=FALSE
+    restart: unless-stopped
+
+  searxng:
+    # Pinned, not :latest — odysseus waits on searxng's healthcheck
+    # (depends_on: condition: service_healthy), so a broken upstream `latest`
+    # tag blocks the whole app from starting. 2026.6.2 crashes on boot with
+    # `KeyError: 'default_doi_resolver'`, failing the healthcheck (issue #1414).
+    # Bump this deliberately after verifying a newer tag boots clean.
+    image: docker.io/searxng/searxng:2026.5.31-7159b8aed
+    entrypoint:
+      - /bin/sh
+      - -c
+      - |
+        set -eu
+        if [ ! -s /etc/searxng/settings.yml ] || grep -q 'odysseus-local-searxng-json-2026-05-30\|__SEARXNG_SECRET__' /etc/searxng/settings.yml; then
+          secret="$${SEARXNG_SECRET:-}"
+          if [ -z "$$secret" ]; then
+            secret="$$(python -c 'import secrets; print(secrets.token_urlsafe(48))')"
+          fi
+          sed "s|__SEARXNG_SECRET__|$$secret|g" /tmp/searxng-settings.yml.template > /etc/searxng/settings.yml
+        fi
+        exec /usr/local/searxng/entrypoint.sh
+    ports:
+      - "127.0.0.1:8080:8080"
+    volumes:
+      - searxng-data:/etc/searxng
+      - ./config/searxng/settings.yml:/tmp/searxng-settings.yml.template:ro,z
+    environment:
+      - SEARXNG_BASE_URL=http://localhost:8080/
+      - SEARXNG_SECRET=${SEARXNG_SECRET:-}
+    # The official searxng image runs as the non-root `searxng` user, but its
+    # entrypoint still needs to chown /etc/searxng on first boot, drop privs via
+    # su-exec, and (with our wrapper above) write settings.yml into the named
+    # volume. Without these capabilities the wrapper aborts at the redirection
+    # with EACCES and the container fails its healthcheck with permission
+    # errors during setup. Mirrors the cap set recommended by the upstream
+    # searxng-docker compose file. See issue #721.
+    cap_drop:
+      - ALL
+    cap_add:
+      - CHOWN
+      - SETGID
+      - SETUID
+      - DAC_OVERRIDE
+    healthcheck:
+      test: ["CMD-SHELL", "python -c \"import urllib.request; urllib.request.urlopen('http://localhost:8080/', timeout=5).read(1)\""]
+      interval: 5s
+      timeout: 6s
+      retries: 20
+      start_period: 10s
+    restart: unless-stopped
+
+  ntfy:
+    image: docker.io/binwiederhier/ntfy
+    command: serve
+    ports:
+      - "${NTFY_BIND:-127.0.0.1}:8091:80"
+    volumes:
+      - ntfy-cache:/var/cache/ntfy
+    environment:
+      - NTFY_BASE_URL=${NTFY_BASE_URL:-http://localhost:8091}
+    restart: unless-stopped
+
+volumes:
+  searxng-data:
+  chromadb-data:
+  ntfy-cache:

docker-compose.gpu-nvidia.yml

@@ -0,0 +1,180 @@
+# Standalone NVIDIA GPU Compose file for stack-management UIs (Portainer,
+# Coolify, Dockhand, etc.) that accept only a single Compose file and do not
+# reliably honor COMPOSE_FILE or multiple `-f` overlays.
+#
+# This is equivalent to: docker-compose.yml + docker/gpu.nvidia.yml.
+# The base docker-compose.yml plus the docker/gpu.nvidia.yml overlay remain
+# the source of truth — CLI users should keep using the COMPOSE_FILE overlay
+# workflow. Keep this file in sync with both when either changes.
+#
+# Requires the NVIDIA Container Toolkit on the host. See docker/gpu.nvidia.yml
+# for setup details.
+services:
+  odysseus:
+    build: .
+    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
+      # 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
+      # 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
+      # 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.
+      - ${APP_DATA_DIR:-./data}/local:/app/.local:z
+    extra_hosts:
+      # Lets the container reach local services on the Docker host, including
+      # Ollama at http://host.docker.internal:11434.
+      - "host.docker.internal:host-gateway"
+    environment:
+      - LLM_HOST=${LLM_HOST:-localhost}
+      - LLM_HOSTS=${LLM_HOSTS:-}
+      - OPENAI_API_KEY=${OPENAI_API_KEY:-}
+      - OLLAMA_BASE_URL=${OLLAMA_BASE_URL:-}
+      - RESEARCH_LLM_ENDPOINT=${RESEARCH_LLM_ENDPOINT:-}
+      - HF_TOKEN=${HF_TOKEN:-}
+      - HUGGING_FACE_HUB_TOKEN=${HUGGING_FACE_HUB_TOKEN:-}
+      - SEARXNG_INSTANCE=http://searxng:8080
+      - CHROMADB_HOST=chromadb
+      - CHROMADB_PORT=8000
+      - DATABASE_URL=${DATABASE_URL:-sqlite:///./data/app.db}
+      - AUTH_ENABLED=${AUTH_ENABLED:-true}
+      - LOCALHOST_BYPASS=${LOCALHOST_BYPASS:-false}
+      - ODYSSEUS_ADMIN_USER=${ODYSSEUS_ADMIN_USER:-admin}
+      - ODYSSEUS_ADMIN_PASSWORD=${ODYSSEUS_ADMIN_PASSWORD:-}
+      - ALLOWED_ORIGINS=${ALLOWED_ORIGINS:-http://localhost,http://127.0.0.1}
+      - SECURE_COOKIES=${SECURE_COOKIES:-false}
+      - EMBEDDING_URL=${EMBEDDING_URL:-}
+      - EMBEDDING_MODEL=${EMBEDDING_MODEL:-}
+      - EMBEDDING_API_KEY=${EMBEDDING_API_KEY:-}
+      - FASTEMBED_MODEL=${FASTEMBED_MODEL:-sentence-transformers/all-MiniLM-L6-v2}
+      - FASTEMBED_CACHE_PATH=${FASTEMBED_CACHE_PATH:-}
+      - CLEANUP_INTERVAL_HOURS=${CLEANUP_INTERVAL_HOURS:-24}
+      - ODYSSEUS_INPROCESS_POLLERS=${ODYSSEUS_INPROCESS_POLLERS:-1}
+      - ODYSSEUS_INPROCESS_TASKS=${ODYSSEUS_INPROCESS_TASKS:-1}
+      - ODYSSEUS_SCRIPT_HOST=${ODYSSEUS_SCRIPT_HOST:-localhost}
+      - ODYSSEUS_CHAT_UPLOAD_MAX_BYTES=${ODYSSEUS_CHAT_UPLOAD_MAX_BYTES:-10485760}
+      - ODYSSEUS_GALLERY_UPLOAD_MAX_BYTES=${ODYSSEUS_GALLERY_UPLOAD_MAX_BYTES:-104857600}
+      - ODYSSEUS_GALLERY_TRANSFORM_UPLOAD_MAX_BYTES=${ODYSSEUS_GALLERY_TRANSFORM_UPLOAD_MAX_BYTES:-26214400}
+      - ODYSSEUS_MEMORY_IMPORT_MAX_BYTES=${ODYSSEUS_MEMORY_IMPORT_MAX_BYTES:-10485760}
+      - ODYSSEUS_PERSONAL_UPLOAD_MAX_BYTES=${ODYSSEUS_PERSONAL_UPLOAD_MAX_BYTES:-26214400}
+      - ODYSSEUS_EMAIL_COMPOSE_UPLOAD_MAX_BYTES=${ODYSSEUS_EMAIL_COMPOSE_UPLOAD_MAX_BYTES:-26214400}
+      - ODYSSEUS_STT_MAX_AUDIO_BYTES=${ODYSSEUS_STT_MAX_AUDIO_BYTES:-26214400}
+      - ODYSSEUS_ICS_MAX_BYTES=${ODYSSEUS_ICS_MAX_BYTES:-10485760}
+      - ODYSSEUS_TTS_CACHE_MAX_BYTES=${ODYSSEUS_TTS_CACHE_MAX_BYTES}
+      - DATA_BRAVE_API_KEY=${DATA_BRAVE_API_KEY:-}
+      - GOOGLE_API_KEY=${GOOGLE_API_KEY:-}
+      - GOOGLE_PSE_CX=${GOOGLE_PSE_CX:-}
+      - GOOGLE_OAUTH_CLIENT_ID=${GOOGLE_OAUTH_CLIENT_ID:-}
+      - GOOGLE_OAUTH_CLIENT_SECRET=${GOOGLE_OAUTH_CLIENT_SECRET:-}
+      - GOOGLE_OAUTH_REDIRECT_URI=${GOOGLE_OAUTH_REDIRECT_URI:-}
+      - TAVILY_API_KEY=${TAVILY_API_KEY:-}
+      - SERPER_API_KEY=${SERPER_API_KEY:-}
+      # PUID / PGID — the user/group the container drops to before
+      # running uvicorn (entrypoint also chowns /app/data + /app/logs
+      # to match, so bind-mounted files stay editable from the host).
+      # 1000 is the default first user on most Linux installs. If your
+      # host user has a different id, override here or via .env, e.g.:
+      #   PUID=1001
+      #   PGID=1001
+      # Find yours with:  id -u  /  id -g
+      - PUID=${PUID:-1000}
+      - PGID=${PGID:-1000}
+      # NVIDIA overlay (from docker/gpu.nvidia.yml).
+      - NVIDIA_VISIBLE_DEVICES=all
+      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
+    depends_on:
+      searxng:
+        condition: service_healthy
+      chromadb:
+        condition: service_started
+    restart: unless-stopped
+    # NVIDIA overlay (from docker/gpu.nvidia.yml).
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+
+  chromadb:
+    image: docker.io/chromadb/chroma:latest
+    ports:
+      - "${CHROMADB_BIND:-127.0.0.1}:8100:8000"
+    volumes:
+      - chromadb-data:/chroma/chroma
+    environment:
+      - ANONYMIZED_TELEMETRY=FALSE
+    restart: unless-stopped
+
+  searxng:
+    # Pinned, not :latest — odysseus waits on searxng's healthcheck
+    # (depends_on: condition: service_healthy), so a broken upstream `latest`
+    # tag blocks the whole app from starting. 2026.6.2 crashes on boot with
+    # `KeyError: 'default_doi_resolver'`, failing the healthcheck (issue #1414).
+    # Bump this deliberately after verifying a newer tag boots clean.
+    image: docker.io/searxng/searxng:2026.5.31-7159b8aed
+    entrypoint:
+      - /bin/sh
+      - -c
+      - |
+        set -eu
+        if [ ! -s /etc/searxng/settings.yml ] || grep -q 'odysseus-local-searxng-json-2026-05-30\|__SEARXNG_SECRET__' /etc/searxng/settings.yml; then
+          secret="$${SEARXNG_SECRET:-}"
+          if [ -z "$$secret" ]; then
+            secret="$$(python -c 'import secrets; print(secrets.token_urlsafe(48))')"
+          fi
+          sed "s|__SEARXNG_SECRET__|$$secret|g" /tmp/searxng-settings.yml.template > /etc/searxng/settings.yml
+        fi
+        exec /usr/local/searxng/entrypoint.sh
+    ports:
+      - "127.0.0.1:8080:8080"
+    volumes:
+      - searxng-data:/etc/searxng
+      - ./config/searxng/settings.yml:/tmp/searxng-settings.yml.template:ro,z
+    environment:
+      - SEARXNG_BASE_URL=http://localhost:8080/
+      - SEARXNG_SECRET=${SEARXNG_SECRET:-}
+    # The official searxng image runs as the non-root `searxng` user, but its
+    # entrypoint still needs to chown /etc/searxng on first boot, drop privs via
+    # su-exec, and (with our wrapper above) write settings.yml into the named
+    # volume. Without these capabilities the wrapper aborts at the redirection
+    # with EACCES and the container fails its healthcheck with permission
+    # errors during setup. Mirrors the cap set recommended by the upstream
+    # searxng-docker compose file. See issue #721.
+    cap_drop:
+      - ALL
+    cap_add:
+      - CHOWN
+      - SETGID
+      - SETUID
+      - DAC_OVERRIDE
+    healthcheck:
+      test: ["CMD-SHELL", "python -c \"import urllib.request; urllib.request.urlopen('http://localhost:8080/', timeout=5).read(1)\""]
+      interval: 5s
+      timeout: 6s
+      retries: 20
+      start_period: 10s
+    restart: unless-stopped
+
+  ntfy:
+    image: docker.io/binwiederhier/ntfy
+    command: serve
+    ports:
+      - "${NTFY_BIND:-127.0.0.1}:8091:80"
+    volumes:
+      - ntfy-cache:/var/cache/ntfy
+    environment:
+      - NTFY_BASE_URL=${NTFY_BASE_URL:-http://localhost:8091}
+    restart: unless-stopped
+
+volumes:
+  searxng-data:
+  chromadb-data:
+  ntfy-cache:

docker-compose.yml

@@ -2,26 +2,68 @@ services:
   odysseus:
     build: .
     ports:
-      - "7000:7000"
+      - "${APP_BIND:-127.0.0.1}:${APP_PORT:-7000}:7000"
     volumes:
-      - ./data:/app/data
-      - ./logs:/app/logs
+      - ${APP_DATA_DIR:-./data}:/app/data:z
+      - ${APP_LOGS_DIR:-./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.
-      - ./data/ssh:/app/.ssh
+      - ${APP_DATA_DIR:-./data}/ssh:/app/.ssh:z
       # Cookbook local model cache. Inside Docker, "Local" means the Odysseus
       # container, so persist its HuggingFace cache under ./data/huggingface.
-      - ./data/huggingface:/app/.cache/huggingface
+      - ${APP_DATA_DIR:-./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.
+      - ${APP_DATA_DIR:-./data}/local:/app/.local:z
     extra_hosts:
       # Lets the container reach local services on the Docker host, including
       # Ollama at http://host.docker.internal:11434.
       - "host.docker.internal:host-gateway"
-    env_file:
-      - .env
     environment:
+      - LLM_HOST=${LLM_HOST:-localhost}
+      - LLM_HOSTS=${LLM_HOSTS:-}
+      - OPENAI_API_KEY=${OPENAI_API_KEY:-}
+      - OLLAMA_BASE_URL=${OLLAMA_BASE_URL:-}
+      - RESEARCH_LLM_ENDPOINT=${RESEARCH_LLM_ENDPOINT:-}
+      - HF_TOKEN=${HF_TOKEN:-}
+      - HUGGING_FACE_HUB_TOKEN=${HUGGING_FACE_HUB_TOKEN:-}
       - SEARXNG_INSTANCE=http://searxng:8080
       - CHROMADB_HOST=chromadb
       - CHROMADB_PORT=8000
+      - DATABASE_URL=${DATABASE_URL:-sqlite:///./data/app.db}
+      - AUTH_ENABLED=${AUTH_ENABLED:-true}
+      - LOCALHOST_BYPASS=${LOCALHOST_BYPASS:-false}
+      - ODYSSEUS_ADMIN_USER=${ODYSSEUS_ADMIN_USER:-admin}
+      - ODYSSEUS_ADMIN_PASSWORD=${ODYSSEUS_ADMIN_PASSWORD:-}
+      - ALLOWED_ORIGINS=${ALLOWED_ORIGINS:-http://localhost,http://127.0.0.1}
+      - SECURE_COOKIES=${SECURE_COOKIES:-false}
+      - EMBEDDING_URL=${EMBEDDING_URL:-}
+      - EMBEDDING_MODEL=${EMBEDDING_MODEL:-}
+      - EMBEDDING_API_KEY=${EMBEDDING_API_KEY:-}
+      - FASTEMBED_MODEL=${FASTEMBED_MODEL:-sentence-transformers/all-MiniLM-L6-v2}
+      - FASTEMBED_CACHE_PATH=${FASTEMBED_CACHE_PATH:-}
+      - CLEANUP_INTERVAL_HOURS=${CLEANUP_INTERVAL_HOURS:-24}
+      - ODYSSEUS_INPROCESS_POLLERS=${ODYSSEUS_INPROCESS_POLLERS:-1}
+      - ODYSSEUS_INPROCESS_TASKS=${ODYSSEUS_INPROCESS_TASKS:-1}
+      - ODYSSEUS_SCRIPT_HOST=${ODYSSEUS_SCRIPT_HOST:-localhost}
+      - ODYSSEUS_CHAT_UPLOAD_MAX_BYTES=${ODYSSEUS_CHAT_UPLOAD_MAX_BYTES:-10485760}
+      - ODYSSEUS_GALLERY_UPLOAD_MAX_BYTES=${ODYSSEUS_GALLERY_UPLOAD_MAX_BYTES:-104857600}
+      - ODYSSEUS_GALLERY_TRANSFORM_UPLOAD_MAX_BYTES=${ODYSSEUS_GALLERY_TRANSFORM_UPLOAD_MAX_BYTES:-26214400}
+      - ODYSSEUS_MEMORY_IMPORT_MAX_BYTES=${ODYSSEUS_MEMORY_IMPORT_MAX_BYTES:-10485760}
+      - ODYSSEUS_PERSONAL_UPLOAD_MAX_BYTES=${ODYSSEUS_PERSONAL_UPLOAD_MAX_BYTES:-26214400}
+      - ODYSSEUS_EMAIL_COMPOSE_UPLOAD_MAX_BYTES=${ODYSSEUS_EMAIL_COMPOSE_UPLOAD_MAX_BYTES:-26214400}
+      - ODYSSEUS_STT_MAX_AUDIO_BYTES=${ODYSSEUS_STT_MAX_AUDIO_BYTES:-26214400}
+      - ODYSSEUS_ICS_MAX_BYTES=${ODYSSEUS_ICS_MAX_BYTES:-10485760}
+      - ODYSSEUS_TTS_CACHE_MAX_BYTES=${ODYSSEUS_TTS_CACHE_MAX_BYTES}
+      - DATA_BRAVE_API_KEY=${DATA_BRAVE_API_KEY:-}
+      - GOOGLE_API_KEY=${GOOGLE_API_KEY:-}
+      - GOOGLE_PSE_CX=${GOOGLE_PSE_CX:-}
+      - GOOGLE_OAUTH_CLIENT_ID=${GOOGLE_OAUTH_CLIENT_ID:-}
+      - GOOGLE_OAUTH_CLIENT_SECRET=${GOOGLE_OAUTH_CLIENT_SECRET:-}
+      - GOOGLE_OAUTH_REDIRECT_URI=${GOOGLE_OAUTH_REDIRECT_URI:-}
+      - TAVILY_API_KEY=${TAVILY_API_KEY:-}
+      - SERPER_API_KEY=${SERPER_API_KEY:-}
       # PUID / PGID — the user/group the container drops to before
       # running uvicorn (entrypoint also chowns /app/data + /app/logs
       # to match, so bind-mounted files stay editable from the host).
@@ -40,7 +82,7 @@ services:
     restart: unless-stopped
 
   chromadb:
-    image: chromadb/chroma:latest
+    image: docker.io/chromadb/chroma:latest
     ports:
       - "${CHROMADB_BIND:-127.0.0.1}:8100:8000"
     volumes:
@@ -50,7 +92,12 @@ services:
     restart: unless-stopped
 
   searxng:
-    image: searxng/searxng:latest
+    # Pinned, not :latest — odysseus waits on searxng's healthcheck
+    # (depends_on: condition: service_healthy), so a broken upstream `latest`
+    # tag blocks the whole app from starting. 2026.6.2 crashes on boot with
+    # `KeyError: 'default_doi_resolver'`, failing the healthcheck (issue #1414).
+    # Bump this deliberately after verifying a newer tag boots clean.
+    image: docker.io/searxng/searxng:2026.5.31-7159b8aed
     entrypoint:
       - /bin/sh
       - -c
@@ -68,10 +115,24 @@ services:
       - "127.0.0.1:8080:8080"
     volumes:
       - searxng-data:/etc/searxng
-      - ./config/searxng/settings.yml:/tmp/searxng-settings.yml.template:ro
+      - ./config/searxng/settings.yml:/tmp/searxng-settings.yml.template:ro,z
     environment:
       - SEARXNG_BASE_URL=http://localhost:8080/
       - SEARXNG_SECRET=${SEARXNG_SECRET:-}
+    # The official searxng image runs as the non-root `searxng` user, but its
+    # entrypoint still needs to chown /etc/searxng on first boot, drop privs via
+    # su-exec, and (with our wrapper above) write settings.yml into the named
+    # volume. Without these capabilities the wrapper aborts at the redirection
+    # with EACCES and the container fails its healthcheck with permission
+    # errors during setup. Mirrors the cap set recommended by the upstream
+    # searxng-docker compose file. See issue #721.
+    cap_drop:
+      - ALL
+    cap_add:
+      - CHOWN
+      - SETGID
+      - SETUID
+      - DAC_OVERRIDE
     healthcheck:
       test: ["CMD-SHELL", "python -c \"import urllib.request; urllib.request.urlopen('http://localhost:8080/', timeout=5).read(1)\""]
       interval: 5s
@@ -81,7 +142,7 @@ services:
     restart: unless-stopped
 
   ntfy:
-    image: binwiederhier/ntfy
+    image: docker.io/binwiederhier/ntfy
     command: serve
     ports:
       - "${NTFY_BIND:-127.0.0.1}:8091:80"

docker/build-realesrgan-wheels.sh

@@ -0,0 +1,70 @@
+#!/usr/bin/env bash
+# Build patched wheels for Real-ESRGAN's unmaintained dependencies.
+#
+# basicsr / gfpgan / facexlib (xinntao, last released 2022) read their version
+# in setup.py with:
+#
+#     exec(compile(f.read(), version_file, 'exec'))
+#     return locals()['__version__']
+#
+# Python 3.13+ implements PEP 667: locals() inside a function returns an
+# independent snapshot that exec() can no longer mutate, so the read raises
+# `KeyError: '__version__'` and the sdist build fails. That is why the Cookbook
+# "install realesrgan" button dies on the python:3.14 image. The packages have
+# no fixed release, so we patch get_version() to exec into an explicit namespace
+# dict (works on every Python) and build wheels from the patched source.
+#
+# Usage: build-realesrgan-wheels.sh [OUTPUT_DIR]   (default: /wheels)
+set -euo pipefail
+
+OUT="${1:-/wheels}"
+mkdir -p "$OUT"
+
+work="$(mktemp -d)"
+trap 'rm -rf "$work"' EXIT
+cd "$work"
+
+# Pinned to the versions Real-ESRGAN 0.3.0 resolves to.
+SPECS="basicsr==1.4.2 gfpgan==1.3.8 facexlib==0.3.0"
+
+for spec in $SPECS; do
+  name="${spec%%==*}"
+  ver="${spec##*==}"
+  # pip download builds metadata (and trips the same bug), so fetch the raw
+  # sdist URL from the PyPI JSON API instead.
+  url="$(python - "$name" "$ver" <<'PY'
+import json, sys, urllib.request
+name, ver = sys.argv[1], sys.argv[2]
+data = json.load(urllib.request.urlopen(f"https://pypi.org/pypi/{name}/{ver}/json"))
+for f in data["urls"]:
+    if f["packagetype"] == "sdist":
+        print(f["url"]); break
+else:
+    sys.exit(f"no sdist found for {name}=={ver}")
+PY
+)"
+  echo ">> fetching ${name} ${ver}: ${url}"
+  curl -fsSL "$url" -o "${name}.tar.gz"
+  tar xzf "${name}.tar.gz"
+done
+
+echo ">> patching get_version()"
+python - <<'PY'
+import pathlib
+old_exec = "exec(compile(f.read(), version_file, 'exec'))"
+new_exec = "_ver_ns = {}\n        exec(compile(f.read(), version_file, 'exec'), _ver_ns)"
+old_ret = "return locals()['__version__']"
+new_ret = "return _ver_ns['__version__']"
+patched = 0
+for setup in pathlib.Path(".").glob("*/setup.py"):
+    s = setup.read_text()
+    if old_exec in s and old_ret in s:
+        setup.write_text(s.replace(old_exec, new_exec).replace(old_ret, new_ret))
+        print("   patched", setup)
+        patched += 1
+assert patched == 3, f"expected to patch 3 setup.py files, patched {patched}"
+PY
+
+echo ">> building wheels into ${OUT}"
+pip wheel --no-deps -w "$OUT" ./basicsr-* ./gfpgan-* ./facexlib-*
+ls -l "$OUT"

docker/entrypoint.sh

@@ -13,6 +13,8 @@ set -e
 
 PUID="${PUID:-1000}"
 PGID="${PGID:-1000}"
+GOSU_BIN="$(command -v gosu)"
+PYTHON_BIN="$(command -v python)"
 
 # Reuse an existing matching group/user if the host's UID/GID already
 # corresponds to one in /etc/passwd (e.g. when the image is rebuilt
@@ -24,29 +26,121 @@ if ! getent passwd "$PUID" >/dev/null 2>&1; then
     useradd -u "$PUID" -g "$PGID" -M -s /bin/sh -d /app odysseus
 fi
 
-# Repair ownership on every writable path the app touches at runtime.
-#
-# Bind-mounted dirs (/app/data, /app/logs) are the obvious ones, but
-# the app ALSO writes inside the image's own source tree at runtime:
-#   - services/cache/{search,content}/*  (search cache LRU)
-#   - services/search_analytics.json
-#   - services/search_engine_error.log
-#   - services/tts cache, etc.
-# These dirs were created as root during `docker build`, so dropping
-# to PUID:PGID would otherwise crash on the first import that tries
-# to mkdir them. Chown the whole /app tree — fast (<1s on this size)
-# and idempotent via the `-not -uid` filter so we only touch files
-# that need fixing.
-for dir in /app /app/data /app/logs; do
+ODY_USER="$(getent passwd "$PUID" | cut -d: -f1)"
+[ -z "$ODY_USER" ] && ODY_USER=odysseus
+
+# Docker-socket group plumbing for the explicit host-Docker overlay. When
+# opted in, the socket is owned by root:<host docker gid>. Add the app user
+# to that group and later call gosu by username so supplementary groups are
+# retained.
+DOCKER_SOCK="${DOCKER_SOCK:-/var/run/docker.sock}"
+if [ "${ODYSSEUS_ENABLE_HOST_DOCKER:-}" = "true" ] && [ -S "$DOCKER_SOCK" ]; then
+    SOCK_GID="$(stat -c '%g' "$DOCKER_SOCK" 2>/dev/null || echo '')"
+    if [ -n "$SOCK_GID" ] && [ "$SOCK_GID" != "0" ]; then
+        if ! getent group "$SOCK_GID" >/dev/null 2>&1; then
+            groupadd -g "$SOCK_GID" docker_host || true
+        fi
+        SOCK_GROUP="$(getent group "$SOCK_GID" | cut -d: -f1)"
+        if [ -n "$SOCK_GROUP" ]; then
+            usermod -aG "$SOCK_GROUP" "$ODY_USER" 2>/dev/null || true
+        fi
+    fi
+fi
+
+mount_root_for() {
+    awk -v target="$1" '$5 == target { print $4; exit }' /proc/self/mountinfo 2>/dev/null || true
+}
+
+is_broad_mount_root() {
+    case "$1" in
+        /|/home|/srv|/var|/usr|/opt|/tmp|/mnt|/media)
+            return 0
+            ;;
+    esac
+    return 1
+}
+
+repair_tree_ownership() {
+    dir="$1"
     if [ -d "$dir" ]; then
-        # `find ... -not -uid` keeps this O(touched-files), not
-        # O(everything), so terabyte-sized maildirs don't slow startup.
-        find "$dir" -not -uid "$PUID" -print0 2>/dev/null \
+        find "$dir" -xdev -not -uid "$PUID" -print0 2>/dev/null \
             | xargs -0 -r chown "$PUID:$PGID" 2>/dev/null || true
     fi
+}
+
+repair_app_tree_ownership() {
+    if [ -d /app ]; then
+        find /app -xdev \
+            \( -path /app/data -o -path /app/logs -o -path /app/.ssh -o -path /app/.cache -o -path /app/.local \) -prune \
+            -o -not -uid "$PUID" -print0 2>/dev/null \
+            | xargs -0 -r chown "$PUID:$PGID" 2>/dev/null || true
+    fi
+}
+
+repair_bind_mount_ownership() {
+    dir="$1"
+    if [ ! -d "$dir" ]; then
+        return
+    fi
+
+    mount_root="$(mount_root_for "$dir")"
+    if is_broad_mount_root "$mount_root"; then
+        echo "Skipping recursive ownership repair for $dir because it maps to broad host path $mount_root" >&2
+        chown "$PUID:$PGID" "$dir" 2>/dev/null || true
+        return
+    fi
+
+    repair_tree_ownership "$dir"
+}
+
+# Repair image-owned writable paths without walking into bind-mounted host
+# trees, then repair the app-owned mount roots separately.
+repair_app_tree_ownership
+for dir in /app/data /app/logs /app/.ssh /app/.cache/huggingface /app/.local; do
+    repair_bind_mount_ownership "$dir"
 done
 
+# Cookbook installs vllm/etc. via `pip install --user`, which pulls
+# nvidia-cuda-* wheels into /app/.local but does not set CUDA_HOME or
+# symlink /usr/local/cuda. vllm 0.22+ then crashes during engine init
+# when FlashInfer tries to JIT a sampler kernel ("Could not find nvcc",
+# then "CUDA compiler and toolkit headers are incompatible" on the
+# mixed cuda-nvcc 13.3 / cuda-runtime 13.0 wheel combo).
+#
+# Auto-set CUDA_HOME if a pip-installed nvcc is present, and disable the
+# FlashInfer JIT sampler — sampler only, no impact on attention path.
+# No-op when vllm isn't installed.
+#
+# Checked layouts (all are real pip-wheel install paths):
+#   nvidia/cu13        — nvidia-nvcc-cu13 (CUDA 13.x wheel style)
+#   nvidia/cu12        — nvidia-nvcc-cu12 (CUDA 12.x wheel style)
+#   nvidia/cuda_nvcc   — nvidia-cuda-nvcc-cu12 (older cu12 sub-package style)
+for cu in \
+    /app/.local/lib/python*/site-packages/nvidia/cu13 \
+    /app/.local/lib/python*/site-packages/nvidia/cu12 \
+    /app/.local/lib/python*/site-packages/nvidia/cuda_nvcc; do
+    if [ -x "$cu/bin/nvcc" ]; then
+        export CUDA_HOME="$cu"
+        break
+    fi
+done
+
+# Disable the FlashInfer JIT sampler unconditionally — it is sampler-only
+# and has no impact on the attention path, but requires nvcc + matching
+# CUDA headers at startup. Without this, vLLM crashes with "Could not find
+# nvcc" even when the GPU itself is fully visible to the container.
+export VLLM_USE_FLASHINFER_SAMPLER="${VLLM_USE_FLASHINFER_SAMPLER:-0}"
+
+# Make Cookbook-installed Python CLIs visible after `pip install --user`.
+# vLLM and helper scripts land here because /app is the non-root user's HOME.
+export PATH="/app/.local/bin:$PATH"
+
+# Run first-time setup as the app user so data/ files get the right ownership.
+# setup.py is idempotent — skips auth.json / .env if they already exist.
+# || true so a setup failure never prevents the container from starting.
+"$GOSU_BIN" "$ODY_USER" "$PYTHON_BIN" /app/setup.py || true
+
 # Drop root and run the actual app. `gosu` is preferred over `su` /
 # `sudo` because it cleans up the process tree (no extra shell layer)
 # so signals (SIGTERM from `docker stop`) reach uvicorn directly.
-exec gosu "$PUID:$PGID" "$@"
+exec "$GOSU_BIN" "$ODY_USER" "$@"

docker/gpu.amd.yml

@@ -0,0 +1,19 @@
+# AMD ROCm GPU overlay. Enable by setting COMPOSE_FILE in .env:
+#   COMPOSE_FILE=docker-compose.yml:docker/gpu.amd.yml
+#   RENDER_GID=<numeric output of: getent group render | cut -d: -f3>
+#
+# Requires ROCm drivers on the host (kfd + DRI devices). The host user
+# running Docker must be in the `video` and `render` groups.
+#
+# This overlay only passes the host GPU through to the container.
+# The slim Odysseus image does not bundle ROCm userspace or inference
+# engines — install ROCm-compatible builds of vLLM / llama-cpp-python
+# via Cookbook -> Dependencies (or pip) before serving GPU models.
+services:
+  odysseus:
+    devices:
+      - /dev/kfd
+      - /dev/dri
+    group_add:
+      - video
+      - ${RENDER_GID:-render}

docker/gpu.nvidia.yml

@@ -0,0 +1,34 @@
+# NVIDIA GPU overlay. Enable by setting COMPOSE_FILE in .env:
+#   COMPOSE_FILE=docker-compose.yml:docker/gpu.nvidia.yml
+#
+# Use scripts/check-docker-gpu.sh to diagnose GPU passthrough, optionally
+# install the NVIDIA Container Toolkit (Ubuntu/Debian), and write COMPOSE_FILE
+# to .env. The script is read-only by default — it installs nothing and never
+# edits .env unless explicitly asked.
+#
+# Requires the NVIDIA Container Toolkit on the host.
+#   Arch:    sudo pacman -S nvidia-container-toolkit
+#   Debian:  sudo apt install nvidia-container-toolkit
+#   Fedora:  sudo dnf install nvidia-container-toolkit
+# Then:
+#   sudo nvidia-ctk runtime configure --runtime=docker
+#   sudo systemctl restart docker
+# Verify with:
+#   docker info | grep -i nvidia
+#
+# This overlay only passes the host GPU through to the container.
+# The slim Odysseus image does not bundle CUDA userspace or inference
+# engines — install vLLM / llama-cpp-python / SGLang via
+# Cookbook -> Dependencies (or pip) before serving GPU models.
+services:
+  odysseus:
+    environment:
+      - NVIDIA_VISIBLE_DEVICES=all
+      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]

docker/host-docker.yml

@@ -0,0 +1,12 @@
+# High-trust host Docker access. Enable only when local Docker-daemon
+# management from Cookbook is required and you accept that raw socket access
+# grants broad control over the host Docker daemon.
+#   COMPOSE_FILE=docker-compose.yml:docker/host-docker.yml
+#   DOCKER_GID=<numeric host Docker group id>
+services:
+  odysseus:
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock
+    group_add: ["${DOCKER_GID:-963}"]
+    environment:
+      - ODYSSEUS_ENABLE_HOST_DOCKER=true

docs/agent-migration.md

@@ -0,0 +1,194 @@
+# 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/attachments.md

@@ -0,0 +1,85 @@
+# Attachment References and Upload Storage
+
+Odysseus stores uploaded bytes once under the configured upload directory and
+passes stable references through chat history, tools, and future artifact work.
+The goal is to avoid duplicating large inline media payloads in
+`chat_messages.content` or the SQLite FTS index.
+
+## Reference Shape
+
+Attachment references use this minimum shape:
+
+```json
+{
+  "type": "attachment_ref",
+  "attachment_id": "32hex-or-32hex.ext",
+  "name": "original-filename.png",
+  "mime": "image/png",
+  "size": 12345,
+  "checksum_sha256": "hex-digest",
+  "created_at": "2026-07-09T12:00:00"
+}
+```
+
+Optional fields such as `width`, `height`, `vision`, `vision_model`, and
+`gallery_id` may be present when the uploader or preprocessing path knows them.
+
+## Persistence
+
+The live model call may still receive provider-specific multimodal blocks for
+the current turn. Persistence is different:
+
+- `chat_messages.content` stores readable text plus compact attachment reference
+  lines, never raw `data:*;base64,...` upload bytes.
+- `chat_messages.metadata.attachments` stores structured attachment reference
+  metadata for UI reloads and future processing.
+- The SQLite FTS migration recreates chat-message FTS triggers so new rows do
+  not index inline media payloads, and it scrubs legacy rows that were already
+  indexed with data URLs.
+
+## Tool Access
+
+Agent/tool context receives upload entries as `attachment_ref` manifests with an
+`odysseus://attachment/<id>` URI and `read_policy: "owner_checked_upload"`.
+
+For compatibility with existing built-in tools, a local `path` may be included
+only after all of these checks pass:
+
+- the upload ID resolves through `UploadHandler.resolve_upload`;
+- the requested owner is allowed to read the upload;
+- the file remains inside the configured upload directory;
+- the file path is inside the tool-readable roots.
+
+External MCP/custom tools should treat the URI and attachment ID as the stable
+contract and request bytes through an owner-checked server path, not by assuming
+host filesystem layout.
+
+## Retention and Deletion
+
+Current retention behavior is conservative:
+
+- uploads are indexed in `uploads.json` with owner, checksum, MIME type, size,
+  and creation time;
+- admin cleanup first scans persisted chat metadata/content, document versions,
+  PDF source markers, gallery hashes, notes, and calendar records for live
+  references;
+- cleanup fails closed if that reference scan cannot complete, and the lower-level
+  cleanup API removes nothing unless it receives a complete reference snapshot;
+- expired, unreferenced uploads are removed during the completed scan, while
+  attachment-bearing writers must first take an owner-checked reservation that
+  serializes with deletion and refreshes the upload's access timestamp;
+- deliberate removal atomically drops matching `uploads.json` rows before deleting
+  the bytes and restores those rows if filesystem removal fails;
+- deleting a chat removes the chat rows but does not immediately delete shared
+  upload bytes, because the same upload may also be referenced by gallery items,
+  documents, duplicate-upload rows, or future artifact records.
+
+There is no distinct artifact table in the current schema. Artifact-like upload
+references persisted in chat or document text are covered by the canonical
+attachment-ID scan; any future artifact store must be added to reference discovery
+before cleanup is allowed to consider its uploads unreferenced.
+
+Cleanup and write reservations share the upload-index lock. This closes the
+scan/write/delete race in the documented single-worker deployment; a future
+multi-process deployment must add an inter-process lock or move lifecycle state
+into the database before enabling destructive cleanup in more than one worker.

docs/backup-restore.md

@@ -0,0 +1,129 @@
+# 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/email-outlook.md

@@ -0,0 +1,17 @@
+# Outlook / Office 365 email accounts
+
+Odysseus email accounts currently use IMAP and SMTP with username/password
+authentication. That works for providers that still allow app passwords or
+mailbox passwords for IMAP/SMTP.
+
+Microsoft disables basic authentication for Outlook and Microsoft 365 in most
+modern accounts and tenants. If you try to add an Outlook account with a normal
+password, Microsoft may return errors such as:
+
+- `IMAP: AUTHENTICATE failed`
+- `SMTP: 535 5.7.139 Authentication unsuccessful, basic authentication is disabled`
+
+This is expected. Odysseus does not support Microsoft OAuth or Graph Mail yet,
+so Outlook / Office 365 accounts cannot currently be added through the password
+form. Use another email provider with app-password support, or track the future
+Microsoft Graph OAuth integration.

docs/index.html

@@ -25,9 +25,16 @@
     --radius: 8px;
   }
   * { box-sizing: border-box; }
-  html { scroll-behavior: smooth; scroll-snap-type: y mandatory; scroll-padding-top: 60px; }
-  /* Each section is a full-viewport "page" with its content centered, so only
-     one shows at a time and the snap is obvious. */
+  html { scroll-behavior: smooth; scroll-padding-top: 60px; }
+  /* REMOVED: "scroll-snap-type: y proximity"
+     The idea was: >>Each section is a full-viewport "page" with its content centered,
+     so only one shows at a time and the snap is obvious.<<
+
+     PROBLEM: sections easily grow taller than 100vh IRL
+     This cause forced jumps mid-read. It's intrusive UX.
+     The landing-page is not a PowerPoint presentation!
+
+     Preserved: CSS snap-points to avoid destroying code meta-data*/
   .hero, section {
     scroll-snap-align: start; min-height: 100vh;
     display: flex; flex-direction: column; justify-content: center;
@@ -357,8 +364,16 @@
     display: inline-flex; align-items: center; gap: 14px; margin: 18px auto 8px;
     background: var(--bg2); border: 1px solid var(--border); border-radius: 10px;
     padding: 12px 16px; font-family: ui-monospace, monospace; font-size: 14px; color: var(--fg);
+    text-align: left;
   }
   .codeblock .prompt { color: var(--accent); }
+  .codeblock .copy-btn {
+    background: none; border: 1px solid var(--border); border-radius: 6px;
+    color: var(--muted); cursor: pointer; font-size: 12px; padding: 4px 10px;
+    font-family: inherit; transition: border-color .12s ease, color .12s ease;
+  }
+  .codeblock .copy-btn:hover { border-color: var(--accent); color: var(--fg); }
+  .codeblock .copy-btn.copied { border-color: var(--green); color: var(--green); }
   .pill-row { display: flex; gap: 8px; justify-content: center; flex-wrap: wrap; margin-top: 44px; }
   .pill { font-size: 12.5px; color: var(--muted); border: 1px solid var(--border); border-radius: 999px; padding: 5px 12px; background: var(--panel); }
 
@@ -369,6 +384,9 @@
     .grid { grid-template-columns: repeat(2, 1fr); }
     .shotrow { grid-template-columns: 1fr; }
     .nav-links a:not(.btn) { display: none; }
+    .codeblock { display: flex; flex-wrap: wrap; gap: 8px; align-items: flex-start; overflow-wrap: anywhere; }
+    .codeblock > span { flex: 1 1 auto; min-width: 0; }
+    .codeblock .copy-btn { margin-left: auto; }
   }
   @media (max-width: 520px) {
     .grid { grid-template-columns: 1fr; }
@@ -391,7 +409,7 @@
         <a href="#testimonials">Testimonials</a>
         <a href="#how">How it started</a>
         <a href="#start">Get started</a>
-        <a class="btn" href="https://github.com/pewdiepie-archdaemon/odysseus" target="_blank">
+        <a class="btn" href="https://github.com/odysseus-dev/odysseus" target="_blank">
           <svg width="16" height="16" viewBox="0 0 24 24" fill="currentColor"><path d="M12 .5C5.7.5.5 5.7.5 12c0 5.1 3.3 9.4 7.9 10.9.6.1.8-.2.8-.6v-2c-3.2.7-3.9-1.5-3.9-1.5-.5-1.3-1.3-1.7-1.3-1.7-1-.7.1-.7.1-.7 1.2.1 1.8 1.2 1.8 1.2 1 1.8 2.7 1.3 3.4 1 .1-.8.4-1.3.7-1.6-2.6-.3-5.3-1.3-5.3-5.7 0-1.3.5-2.3 1.2-3.1-.1-.3-.5-1.5.1-3.1 0 0 1-.3 3.3 1.2a11.5 11.5 0 0 1 6 0C17.3 4.7 18.3 5 18.3 5c.6 1.6.2 2.8.1 3.1.8.8 1.2 1.8 1.2 3.1 0 4.4-2.7 5.4-5.3 5.7.4.4.8 1.1.8 2.2v3.3c0 .4.2.7.8.6 4.6-1.5 7.9-5.8 7.9-10.9C23.5 5.7 18.3.5 12 .5z"/></svg>
           GitHub
         </a>
@@ -419,7 +437,7 @@
       </p>
       <div class="hero-cta">
         <a class="btn primary" href="#start">Get started</a>
-        <a class="btn" href="https://github.com/pewdiepie-archdaemon/odysseus" target="_blank">View on GitHub</a>
+        <a class="btn" href="https://github.com/odysseus-dev/odysseus" target="_blank">View on GitHub</a>
       </div>
 
     </div>
@@ -660,9 +678,9 @@
         <div class="eyebrow"><svg viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M4 17l6-5-6-5"/><path d="M12 19h8"/></svg>Get started</div>
         <h2 class="h" style="margin-bottom:6px;">Odysseus is yours.</h2>
         <p class="sub center" style="margin:0 auto;">It's open source and free. No sales team, no demo request, no Trojan horse.</p>
-        <div class="codeblock"><span class="prompt">$</span> git clone https://github.com/pewdiepie-archdaemon/odysseus.git &amp;&amp; cd odysseus</div>
+        <div class="codeblock"><span><span class="prompt">$</span> git clone https://github.com/odysseus-dev/odysseus.git &amp;&amp; cd odysseus</span><button class="copy-btn" data-copy="git clone https://github.com/odysseus-dev/odysseus.git && cd odysseus">Copy</button></div>
         <div>
-          <a class="btn primary" href="https://github.com/pewdiepie-archdaemon/odysseus" target="_blank" style="margin-top:14px;">View on GitHub</a>
+          <a class="btn primary" href="https://github.com/odysseus-dev/odysseus" target="_blank" style="margin-top:14px;">View on GitHub</a>
         </div>
         <div class="pill-row">
           <span class="pill">Self-hosted</span>
@@ -925,6 +943,18 @@
 
       show(0);
     })();
+
+    // Copy button for the codeblock command.
+    (function () {
+      var btn = document.querySelector('.codeblock .copy-btn');
+      if (!btn) return;
+      btn.addEventListener('click', function () {
+        navigator.clipboard.writeText(btn.getAttribute('data-copy')).then(function () {
+          btn.textContent = 'Copied!'; btn.classList.add('copied');
+          setTimeout(function () { btn.textContent = 'Copy'; btn.classList.remove('copied'); }, 2000);
+        });
+      });
+    })();
   </script>
 
 </body>

docs/pr-blocker-audit.md

@@ -0,0 +1,188 @@
+# PR Blocker Audit
+
+`scripts/pr_blocker_audit.py` is a small, read-only triage helper for maintainers who need to inspect open pull request overlap before reviewing or starting related work.
+
+It is a triage helper, not a replacement for maintainer judgment.
+
+## What it does
+
+- Reads open PR metadata from a local JSON file or from `gh`.
+- Reports files touched by more than one open PR.
+- Groups active work into broad code areas.
+- Ranks PRs with a deterministic heuristic score.
+- Flags possible duplicate candidates based on title keyword overlap and changed-file similarity.
+- Suggests quieter areas for conservative new work.
+- Prints Markdown by default, compact terminal output when requested, or machine-readable JSON.
+
+## What it does not do
+
+- It does not post comments.
+- It does not review, approve, label, close, merge, or otherwise mutate PRs.
+- It does not add or run GitHub Actions.
+- It does not import the Odysseus application package.
+- It does not claim that a PR is definitely blocked or duplicated.
+
+## Read-only safety guarantee
+
+Offline mode only reads a local JSON file. Live mode runs read-only GitHub CLI commands:
+
+```bash
+gh pr list --repo OWNER/REPO --state open --limit 1000 --json number,title,author,files,mergeStateStatus,reviewDecision,updatedAt,url
+```
+
+If a PR from that list has missing or empty changed-file metadata, live mode fills it with read-only per-PR REST calls:
+
+```bash
+gh api --paginate "repos/OWNER/REPO/pulls/NUMBER/files?per_page=100"
+```
+
+If that GraphQL-backed command fails, it falls back to:
+
+```bash
+gh api --paginate "repos/OWNER/REPO/pulls?state=open&per_page=100"
+```
+
+Per-PR file fetching makes live overlap results useful, but it can be slower on repositories with hundreds of open PRs.
+
+## Generate input JSON
+
+For repeatable offline audits, capture PR metadata first:
+
+```bash
+gh pr list --repo OWNER/REPO --state open --limit 1000 --json number,title,author,files,mergeStateStatus,reviewDecision,updatedAt,url > open-prs.json
+```
+
+## Run offline mode
+
+```bash
+python3 scripts/pr_blocker_audit.py --input open-prs.json
+```
+
+## Run live mode
+
+```bash
+python3 scripts/pr_blocker_audit.py --repo OWNER/REPO
+```
+
+Live mode fetches up to 1000 open PRs by default. Use `--limit` to cap how many open PRs are fetched and analyzed, and `--top` to cap how many rows are displayed in ranked sections:
+
+```bash
+python3 scripts/pr_blocker_audit.py --repo OWNER/REPO --limit 50 --top 10
+```
+
+Live mode may take time on large PR queues because it fetches changed-file metadata for each PR that did not include it in the initial list response. Progress is shown on `stderr` by default only when `stderr` is a TTY:
+
+```bash
+python3 scripts/pr_blocker_audit.py --repo OWNER/REPO --progress auto
+python3 scripts/pr_blocker_audit.py --repo OWNER/REPO --progress always
+python3 scripts/pr_blocker_audit.py --repo OWNER/REPO --progress never
+```
+
+Use `--quiet` to suppress progress and non-fatal warning output. Progress and warnings never go to `stdout`, so redirected reports and `--output` files remain clean.
+
+For a faster metadata-only scan, skip changed-file metadata entirely:
+
+```bash
+python3 scripts/pr_blocker_audit.py --repo OWNER/REPO --no-fetch-files
+```
+
+## JSON output
+
+Use `--format json` for machine-readable output suitable for scripting or downstream tooling:
+
+```bash
+python3 scripts/pr_blocker_audit.py --input open-prs.json --format json
+python3 scripts/pr_blocker_audit.py --input open-prs.json --format json --output report.json
+```
+
+JSON output is stable and deterministic for the same input. It uses `sort_keys=True` so field order does not vary between runs. It never includes ANSI escape codes, even with `--color always`. Progress text is always `stderr`-only and never appears in JSON output.
+
+The top-level object contains these keys:
+
+- `summary` — scalar overview: `total_prs_analyzed`, `unique_files_touched`, `prs_missing_changed_file_metadata`, `main_overlap_drivers`, `highest_risk_areas`, `recommended_first_review_target`
+- `locked_areas` — list of objects with `area`, `files` (top paths as a string), `prs` (list of PR numbers), `why`, `priority`
+- `hot_files` — list of objects with `file`, `pr_count`, `pr_numbers` (list of PR numbers); capped at `--top`
+- `review_priorities` — ranked list with `rank`, `number`, `score`, `title`, `url`, `merge_state`, `review_decision`, `reasons` (list); capped at `--top`
+- `duplicate_candidates` — list of objects with `pr_numbers` (list) and `titles` (list, one entry per PR in the group)
+- `safer_areas` — list of strings
+
+## Write output to a file
+
+```bash
+python3 scripts/pr_blocker_audit.py --input open-prs.json --output pr-blocker-report.md
+python3 scripts/pr_blocker_audit.py --input open-prs.json --format json --output report.json
+```
+
+Markdown and JSON output never include ANSI color codes. ANSI codes are stripped defensively when writing any output file.
+
+## Terminal output and color
+
+Use terminal output for quick interactive scans:
+
+```bash
+python3 scripts/pr_blocker_audit.py --input open-prs.json --format terminal
+```
+
+Terminal output includes locked areas, hot files, review / blocker priorities, possible duplicate candidates, and safer areas.
+
+Color is readability-only. It is never included in Markdown reports and is stripped defensively when writing output files. Color modes are:
+
+```bash
+python3 scripts/pr_blocker_audit.py --input open-prs.json --format terminal --color auto
+python3 scripts/pr_blocker_audit.py --input open-prs.json --format terminal --color always
+python3 scripts/pr_blocker_audit.py --input open-prs.json --format terminal --color never
+```
+
+`--no-color` is kept as an alias for `--color never`. With `--color auto`, color is used only for terminal output on a TTY when `NO_COLOR` is not set and output is not being written to a file.
+
+## Interpret locked areas
+
+Locked areas are broad categories with one or more open PRs. An area is higher priority when several PRs touch it, when PRs share files, or when the highest scoring PR in that area has risk signals. Treat this as a prompt to inspect the PRs together.
+
+`PRs missing changed-file metadata` counts PRs that still had no changed-file paths after live file fetching, or PRs from offline input that did not include files. Those PRs can still appear in area summaries from title matching, but file overlap analysis is weaker for them.
+
+`Docs / tooling / tests` is conservative: runtime PRs are not classified there just because they include tests or README changes. Docs-only, README-only, scripts-only, tests-only, or strongly titled docs/tooling/test work still maps there.
+
+`Other / unclassified` is kept visible for PRs that do not match the area rules. When most of it comes from missing file metadata, the report summarizes that instead of letting long PR lists dominate the locked-area section.
+
+## Interpret duplicate candidates
+
+Duplicate candidates are labeled as possible duplicate / needs human review. The script groups PRs only when their file sets are highly similar and their titles share meaningful keywords. Similar PRs can still be complementary.
+
+## Interpret heuristic scores
+
+The review priority score is deterministic for the same input. Recency is measured against the newest parseable PR update timestamp in the input, and the score uses simple weights for:
+
+- direct auth, bearer-token, API-token, privilege, or permission lifecycle signals
+- security, secret, or data exposure keywords
+- persistence, migration, database, SQLite, or Postgres keywords
+- memory, vector, RAG, embedding, or retrieval keywords
+- overlapping changed files
+- clean merge state as a small actionability signal
+- review state
+- recently updated PRs when timestamp data exists
+
+Higher scores mean "inspect earlier", not "correct" or "merge-ready". Broad PRs can score high because they overlap many files and may block other work, but they still need normal review and validation.
+
+Dirty, blocked, conflicting, and unknown merge states are shown as risk/caution reasons. They do not add importance points by themselves.
+
+## Design note: intentional single-script layout
+
+`pr_blocker_audit.py` is intentionally kept as one standalone script. The goal is to keep this maintainer/contributor workflow helper low-friction while broader repo tooling and test-suite conventions are still evolving. Splitting it into packages or modules is not ruled out, but is deferred until there is a clearer settled pattern to follow.
+
+## Limitations
+
+- Some PRs may still lack changed files if GitHub file metadata calls fail or metadata-only mode is used.
+- Area classification is intentionally small and editable.
+- Title keyword matching misses semantic duplicates.
+- Heuristic scoring cannot know project strategy, reviewer availability, or hidden dependency chains.
+- Empty or missing file metadata produces a valid report but weak overlap analysis.
+
+## Validation
+
+```bash
+python3 -m py_compile scripts/pr_blocker_audit.py tests/test_pr_blocker_audit.py
+python3 -m pytest tests/test_pr_blocker_audit.py -q
+python3 scripts/pr_blocker_audit.py --help
+git diff --check
+```

docs/security-ci.md

@@ -0,0 +1,101 @@
+# Security CI guide
+
+This project runs a set of automated security checks on pull requests and
+selected branch pushes. This page explains what each one does, whether it can
+block a merge, and the few one-time settings you should turn on to get the full
+benefit.
+
+## What runs, and why
+
+Most checks live in files under `.github/workflows/`. CodeQL uses the
+checked-in advanced configuration in `.github/workflows/codeql.yml`. 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**, keep **Default setup** disabled. CodeQL is
+   configured by `.github/workflows/codeql.yml`; enabling default setup at the
+   same time causes GitHub to reject uploads from the checked-in workflow.
+
+## 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

@@ -0,0 +1,548 @@
+# 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/odysseus-dev/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/odysseus-dev/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/odysseus-dev/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/odysseus-dev/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
+```
+
+**Host Docker access (explicit opt-in).** Default Docker Compose intentionally
+does not mount `/var/run/docker.sock`. You can still connect Odysseus to
+existing Ollama, vLLM, and other OpenAI-compatible endpoints without Docker
+socket access.
+
+Cookbook/local Docker-daemon management requires the opt-in overlay below. Raw
+Docker socket access is high-trust because it can effectively grant broad
+control over the host Docker daemon. Remote server Docker workflows over SSH
+remain preferred.
+
+Place these values in `.env`, or export them in the shell before running
+`docker compose`:
+
+```bash
+COMPOSE_FILE=docker-compose.yml:docker/host-docker.yml
+DOCKER_GID=<host docker group gid>
+```
+
+Combine host Docker access with a GPU overlay when both are intentionally
+required:
+
+```bash
+COMPOSE_FILE=docker-compose.yml:docker/gpu.nvidia.yml:docker/host-docker.yml
+# or
+COMPOSE_FILE=docker-compose.yml:docker/gpu.amd.yml:docker/host-docker.yml
+```
+
+**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
+```
+#### Arch Linux NVIDIA Docker notes
+
+On Arch Linux, verify the host NVIDIA driver and Docker GPU passthrough before enabling the Odysseus NVIDIA overlay.
+
+Install the required packages:
+
+```bash
+sudo pacman -Syu
+sudo pacman -S docker docker-compose nvidia-container-toolkit nvidia-utils
+sudo systemctl enable --now docker
+```
+
+Configure Docker to use the NVIDIA container runtime:
+
+```bash
+sudo nvidia-ctk runtime configure --runtime=docker
+sudo systemctl restart docker
+```
+
+Verify the host GPU:
+
+```bash
+nvidia-smi
+```
+
+Verify Docker GPU passthrough:
+
+```bash
+docker run --rm --gpus all nvidia/cuda:12.9.0-base-ubuntu22.04 nvidia-smi
+```
+
+Then enable the Odysseus NVIDIA compose overlay:
+
+```env
+COMPOSE_FILE=docker-compose.yml:docker/gpu.nvidia.yml
+```
+
+Rebuild and verify the GPU inside the Odysseus container:
+
+```bash
+docker compose up -d --build
+docker compose exec odysseus nvidia-smi -L
+```
+
+For first-time local model testing on 8 GB laptop GPUs, start with GGUF/Q4 models on llama.cpp before trying GPTQ/AWQ models on vLLM or SGLang. This keeps the first run simpler while confirming GPU passthrough works.
+
+**WSL2 + snap Docker.** If the NVIDIA check fails with this error, Docker may be
+installed via snap:
+
+```text
+failed to fulfil mount request: open /usr/lib/wsl/lib/libdxcore.so: no such file or directory
+```
+
+Check with `snap list docker` or:
+
+```bash
+docker info --format '{{.DockerRootDir}}'
+```
+
+A Docker root under `/var/snap/docker/` means snap confinement can prevent
+Docker from seeing WSL2's `/usr/lib/wsl/lib` GPU libraries even when the files
+exist on the host. Reinstalling or reconfiguring `nvidia-container-toolkit` will
+not fix that. Remove snap Docker, install the official apt-based Docker Engine
+([Docker docs](https://docs.docker.com/engine/install/ubuntu/)), then configure
+the NVIDIA runtime again:
+
+```bash
+sudo snap remove docker
+sudo nvidia-ctk runtime configure --runtime=docker
+sudo systemctl restart docker
+```
+
+Then re-run `scripts/check-docker-gpu.sh`.
+
+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/odysseus-dev/odysseus.git
+cd odysseus
+powershell -ExecutionPolicy Bypass -File .\launch-windows.ps1
+```
+
+Or do it by hand:
+
+```powershell
+git clone https://github.com/odysseus-dev/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.
+
+**Exposing on a LAN/Tailscale (Windows):** the launcher binds to `127.0.0.1` and
+does **not** read `APP_BIND` / `ODYSSEUS_HOST` from `.env`, so editing `.env`
+alone leaves the native Windows server on loopback. Pass the launcher's
+`-BindHost` flag instead:
+
+```powershell
+powershell -ExecutionPolicy Bypass -File .\launch-windows.ps1 -BindHost 0.0.0.0
+```
+
+The manual `uvicorn` command takes the same address as `--host 0.0.0.0`. Bind
+outside loopback only for a trusted LAN/VPN such as Tailscale: keep
+`AUTH_ENABLED=true` and do not expose the port directly to the public internet.
+
+**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).
+
+### Common self-host traps (30-second fixes)
+A grab-bag of small gotchas that otherwise turn into long debugging sessions.
+
+- **`AUTH_ENABLED=false` is ignored / you're still forced to log in (Windows).** If you edited `.env` in Notepad it may have saved a UTF-8 **BOM**, turning the first key into `AUTH_ENABLED` so it is never matched. Odysseus loads `.env` with `encoding="utf-8-sig"` to tolerate a leading BOM, but the safe fix is to re-save `.env` as **UTF-8 without BOM** (VS Code: *Save with Encoding → UTF-8*).
+- **macOS: the app isn't at `http://localhost:7000`.** macOS AirPlay Receiver usually holds port `7000`, so the macOS start script serves on **`7860`** instead — open `http://localhost:7860`. To use `7000`, free it (System Settings → General → AirDrop & Handoff → turn off *AirPlay Receiver*) and set `APP_PORT=7000`.
+- **Copy buttons do nothing over a plain-HTTP Tailscale/LAN URL.** Browsers only expose the clipboard API (`navigator.clipboard`) on **secure origins** — HTTPS, or `localhost`. Over `http://100.x.y.z:7860` it is blocked. Serve over HTTPS (see *HTTPS + LAN/Tailscale exposure* above); `localhost` is exempt, so copy still works on the host itself.
+- **Self-hosted ntfy reminders don't reach your phone.** Two things: (1) the bundled ntfy binds to loopback by default — to reach it from your phone set `NTFY_BIND` to your host/Tailscale IP and `NTFY_BASE_URL` to the same server URL in `.env`, then recreate the ntfy container (see the `NTFY_*` block in `.env.example`); (2) in the ntfy **Android** app, subscribe to the topic with **Instant delivery** enabled — non-`ntfy.sh` servers don't get instant push otherwise.
+- **Local mail (Dovecot) login fails: "Plaintext authentication disallowed on non-encrypted connections."** Your IMAP/SMTP server is refusing cleartext auth over an unencrypted link. Prefer enabling TLS on the mail server; on a trusted LAN only, you can allow cleartext (Dovecot: `disable_plaintext_auth = no`).
+- **Calendar/contacts (Radicale) won't sync.** Point Odysseus at the **full collection URL** with its trailing slash — e.g. `http://host:5232/<user>/<collection-id>/` — not just the server root. Radicale shows this address for each calendar/address book in its web UI.
+
+### 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](backup-restore.md).

integrations/claude/README.md

@@ -0,0 +1,36 @@
+# Odysseus Claude Code Integration
+
+This directory contains the Claude Code skill bundle for Odysseus.
+
+## User Flow
+
+1. Open Odysseus Settings > Integrations.
+2. Add a Claude Agent.
+3. Copy the full setup commands shown after the generated token.
+4. Toggle the tools Claude is allowed to use.
+5. Configure the terminal Claude Code session:
+
+```bash
+export ODYSSEUS_URL=http://your-odysseus-host:7000
+export ODYSSEUS_API_TOKEN=ody_generated_token
+mkdir -p ~/.claude
+curl -fsSL -H "Authorization: Bearer $ODYSSEUS_API_TOKEN" "$ODYSSEUS_URL/api/claude/plugin.zip" -o /tmp/odysseus-claude-skill.zip
+python3 -m zipfile -e /tmp/odysseus-claude-skill.zip ~/.claude/
+```
+
+Claude Code auto-loads anything under `~/.claude/skills/`, so the `odysseus` skill is
+available in any session that has `ODYSSEUS_URL` and `ODYSSEUS_API_TOKEN` in its
+environment.
+
+## What's in the bundle
+
+- `skills/odysseus/SKILL.md` — the skill definition Claude Code reads.
+- `skills/odysseus/scripts/odysseus_api.py` — small helper that calls the scoped
+  `/api/codex/*` endpoints (these are the canonical scope-gated agent API; the
+  `codex` path is historic and shared by all agent integrations).
+
+## Scope enforcement
+
+The token is scope-gated. Every tool surface is checked server-side in Odysseus,
+so even if Claude tries to call a forbidden endpoint, it gets `403` until the
+user enables the matching toggle in Settings > Integrations > Claude Agent.

integrations/claude/skills/odysseus/SKILL.md

@@ -0,0 +1,154 @@
+---
+name: odysseus
+description: Use when the user asks Claude Code to read or write Odysseus data (todos, email, calendar, memory, documents) or to launch/monitor/stop a Cookbook model-serve task through the scoped Claude Agent API. Requires ODYSSEUS_URL and ODYSSEUS_API_TOKEN.
+---
+
+# Odysseus
+
+Use this skill when a user asks to interact with Odysseus from Claude Code.
+
+## Configuration
+
+Expect these environment variables:
+
+- `ODYSSEUS_URL`: Base URL for the user's Odysseus instance, for example `http://127.0.0.1:7000`.
+- `ODYSSEUS_API_TOKEN`: Scoped API token created in Odysseus Settings > Integrations > Add Integration > Claude Agent.
+
+If either value is missing, do not guess credentials. Tell the user to create a Claude Agent token in Odysseus Settings and expose both values to the terminal session.
+
+## When to use what
+
+- **Reminder ("remind me at 5pm to do X")** → TODO with `due_date`. The due_date IS the reminder — it fires a notification automatically via the user's configured channel (browser/email/ntfy). **Do NOT create a calendar event for a reminder.** Creating a calendar event named "Reminder" does NOT trigger a notification — it's just a time block on the calendar.
+- **Calendar event ("meeting at 3pm", "dentist Tuesday 10am")** → calendar event. Use for scheduled time blocks, meetings, appointments, recurring schedules. These show up on the calendar grid; reminders for them are configured separately in Odysseus settings.
+- **Note / freeform info ("note that the wifi password is ...")** → memory or todo without a due_date (depending on whether it's a fact about the user or an action item).
+- **Persistent fact / preference about the user** → memory.
+
+If the user says "reminder" + a time, default to TODO with due_date. Only switch to calendar if the user explicitly says "calendar", "event", "meeting", "appointment", or describes a time *range*.
+
+## Safety
+
+- All Odysseus data access MUST go through the scoped HTTP API under `/api/codex/*` (the canonical scope-gated agent API, shared by all agent integrations).
+- Check `/api/codex/capabilities` before using a tool surface.
+- Treat `403` as an intentional Settings restriction. Do not work around it.
+- Do not use SSH, Docker, direct Python imports, SQLite queries, MCP internals, browser cookies, or local files to read/write Odysseus user data.
+- Do not call helpers like `do_manage_notes`, email MCP internals, or database sessions directly for user data, even if shell access exists.
+- Never send email directly unless the user explicitly asks to send and the token has a send-capable scope.
+- Keep actions scoped to the token owner.
+
+## Todos
+
+The scoped agent API supports todos/checklists:
+
+- `GET /api/codex/todos`
+- `POST /api/codex/todos`
+
+Use the bundled helper script when available:
+
+```bash
+python3 ~/.claude/skills/odysseus/scripts/odysseus_api.py capabilities
+python3 ~/.claude/skills/odysseus/scripts/odysseus_api.py todos list
+python3 ~/.claude/skills/odysseus/scripts/odysseus_api.py todos add "Follow up"
+```
+
+Supported todo actions are `list`, `add`, `update`, `delete`, and `toggle_item`.
+
+**Reminders (todos with a due date)** — the backend parses natural language. Send `due_date` in the body via the generic POST so the time becomes a structured reminder, NOT a literal substring inside the title. The `todos add TITLE` shortcut only sets the title, so use the POST form for anything with a time:
+
+```bash
+python3 ~/.claude/skills/odysseus/scripts/odysseus_api.py POST /api/codex/todos '{"action":"add","title":"Call dentist","due_date":"tomorrow at 5pm"}'
+```
+
+The backend accepts both ISO timestamps and natural language like `"tomorrow 5pm"`, `"next Monday 9am"`, `"in 2 hours"`. It anchors to the user's timezone.
+
+## Email
+
+The scoped agent API supports email reads:
+
+- `GET /api/codex/emails?folder=INBOX&limit=10&offset=0&filter=all`
+- `GET /api/codex/emails/{uid}?folder=INBOX`
+
+Use the bundled helper script when available:
+
+```bash
+python3 ~/.claude/skills/odysseus/scripts/odysseus_api.py emails list 5
+python3 ~/.claude/skills/odysseus/scripts/odysseus_api.py emails read UID
+```
+
+If `/api/codex/capabilities` does not show `email.read: true`, do not inspect email. Ask the user to enable Email read in the Claude Agent settings.
+
+## Memory
+
+- `GET /api/codex/memory` — list memories for the token owner.
+- `POST /api/codex/memory` — body `{"text": "...", "category": "fact", "source": "user", "session_id": null}`. Requires `memory:write`.
+- `DELETE /api/codex/memory/{memory_id}` — remove a memory entry. Requires `memory:write`.
+
+```bash
+python3 ~/.claude/skills/odysseus/scripts/odysseus_api.py GET /api/codex/memory
+python3 ~/.claude/skills/odysseus/scripts/odysseus_api.py POST /api/codex/memory '{"text":"User prefers SI units","category":"preference"}'
+```
+
+## Calendar
+
+- `GET /api/codex/calendar/events?start=ISO&end=ISO` — list events in window.
+- `POST /api/codex/calendar/events` — body matches `EventCreate` (`summary`, `dtstart`, `dtend`, `all_day`, `description`, `location`, `calendar_href`, `rrule`, `color`). Requires `calendar:write`.
+- `DELETE /api/codex/calendar/events/{uid}` — delete event by uid (the value returned in the POST response). Requires `calendar:write`.
+
+## Documents
+
+- `GET /api/codex/documents?search=...&limit=50` — paginated library.
+- `GET /api/codex/documents/{doc_id}` — fetch one document.
+- `POST /api/codex/documents` — body `{"session_id": "...", "title": "...", "content": "...", "language": "markdown"}`. Requires `documents:write`.
+- `DELETE /api/codex/documents/{doc_id}` — delete a document. Requires `documents:write`.
+
+## 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.
+
+## Cookbook serve (debug a failing model launch)
+
+The Cookbook surface lets you reproduce what a human would do in Odysseus → Cookbook: read which serves are running, tail their tmux output to see why they crashed, edit the launch command, relaunch, kill a stuck one. Use this when the user is debugging a model server that won't come up (compute-capability errors, OOM, missing kernels, wrong attention backend, etc.).
+
+- `GET /api/codex/cookbook/tasks` — list active serve/download/install tasks (sessionId, type, status, repo_id, remoteHost, payload._cmd). Requires `cookbook:read`.
+- `GET /api/codex/cookbook/servers` — list configured servers (name, host, port, env type + path, model dirs). Requires `cookbook:read`.
+- `GET /api/codex/cookbook/cached?host=<NAME>` — list models already cached on the named server (HF cache + Ollama + extra modelDirs). Call BEFORE `serve` to see what's already on disk. Requires `cookbook:read`.
+- `GET /api/codex/cookbook/presets` — list saved serve presets (model + host + port + cmd). The user's saved preset usually has a working cmd — try `preset NAME` before composing your own. Requires `cookbook:read`.
+- `GET /api/codex/cookbook/output/{session_id}?tail=400` — read the last N lines of the task's persistent log file (preferred) or tmux pane (fallback). The log file persists across vllm crashes, so this returns the actual Python traceback even after the bash prompt + neofetch banner overwrites the pane. Default tail=400. Requires `cookbook:read`.
+- `POST /api/codex/cookbook/serve` — launch a serve task. Body matches `ServeRequest`: `{ repo_id, cmd, remote_host?, ssh_port?, env_prefix?, gpus?, platform? }`. The `cmd` is validated: leading binary must be `vllm`/`python3`/`sglang`/`llama-server`/`ollama`/`node`/`npx`. NEVER prefix with `cd …`, `source …`, or chain with `&&`/`||`/`;`/`$(...)` — the validator rejects shell metacharacters. The venv activation (`env_prefix`) is added automatically from the host's saved settings, so pass the bare binary + args. Requires `cookbook:launch`.
+- `POST /api/codex/cookbook/preset/{name}` — launch a saved preset by name. Reuses the working cmd + host the user already saved. Requires `cookbook:launch`.
+- `POST /api/codex/cookbook/adopt` — register an externally-launched tmux session into cookbook tracking. Body: `{ tmux_session, model, host?, port? }`. Use this when serve_model rejected a cmd and you fell back to direct ssh+tmux — without adoption, the session is invisible to the UI. Requires `cookbook:launch`.
+- `POST /api/codex/cookbook/stop/{session_id}` — kill the tmux session for that task. Requires `cookbook:launch`.
+
+```bash
+# Survey what's running
+python3 ~/.claude/skills/odysseus/scripts/odysseus_api.py cookbook tasks
+
+# Tail the failing one (sessionId from `cookbook tasks`)
+python3 ~/.claude/skills/odysseus/scripts/odysseus_api.py cookbook output serve-abc12345 400
+
+# Stop the previous attempt before you try a new flag set
+python3 ~/.claude/skills/odysseus/scripts/odysseus_api.py cookbook stop serve-abc12345
+
+# Relaunch with new flags. cmd MUST begin with one of the allowlisted binaries.
+python3 ~/.claude/skills/odysseus/scripts/odysseus_api.py cookbook serve \
+  /mnt/HADES/models/Qwen3.5-397B-A17B-AWQ \
+  "vllm serve /mnt/HADES/models/Qwen3.5-397B-A17B-AWQ --host 0.0.0.0 --port 8001 --tensor-parallel-size 8 --max-model-len 262144 --gpu-memory-utilization 0.90 --dtype auto --max-num-seqs 8 --trust-remote-code --enable-expert-parallel --enable-auto-tool-choice --tool-call-parser qwen3_coder --reasoning-parser qwen3" \
+  pewds@192.168.1.12
+```
+
+**Debug loop pattern:** when a serve is failing, the productive sequence is
+
+1. `cookbook tasks` → find the failing sessionId.
+2. `cookbook output SID 600` → read the last 600 lines, find the actual root-cause line (often above the visible tail because tmux scrollback rolled — request a larger `tail` if the error references "above").
+3. `cookbook stop SID` — kill the previous attempt before relaunching; two serves on the same `--port` collide.
+4. `cookbook serve repo "new cmd"` — try the next variation. Wait ~20s, then `cookbook output` on the new sessionId.
+
+**Hard limits this surface enforces:**
+- `cookbook serve` cmd allowlist + shell-metacharacter rejection — you cannot run arbitrary shell, only model-server binaries.
+- `cookbook stop` only targets task sessionIds matching `[a-zA-Z0-9_-]+`.
+- The agent CAN spawn GPU-pinning long-lived processes — always `cookbook stop` your previous attempt before relaunching, and check `cookbook tasks` for collisions on the same `--port` before launching.
+
+## Forbidden Bypass Pattern
+
+If you are about to reach the Odysseus host/container, import app internals, query the database, or call MCP helper modules directly, stop. Those paths bypass Odysseus Settings and token scopes. Ask the user to enable the relevant Claude Agent tool toggle instead.

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

@@ -0,0 +1,218 @@
+#!/usr/bin/env python3
+"""Small Odysseus scoped API helper for Codex terminal sessions."""
+
+from __future__ import annotations
+
+import json
+import os
+import sys
+import urllib.error
+import urllib.request
+
+
+def _usage() -> int:
+    print("usage:", file=sys.stderr)
+    print("  odysseus_api.py capabilities", file=sys.stderr)
+    print("  odysseus_api.py todos list", file=sys.stderr)
+    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)
+    print("  odysseus_api.py cookbook presets", file=sys.stderr)
+    print("  odysseus_api.py cookbook output SESSION_ID [tail]", file=sys.stderr)
+    print("  odysseus_api.py cookbook serve REPO_ID 'CMD' [REMOTE_HOST]", file=sys.stderr)
+    print("  odysseus_api.py cookbook preset NAME", file=sys.stderr)
+    print("  odysseus_api.py cookbook adopt SESSION_ID MODEL [HOST] [PORT]", file=sys.stderr)
+    print("  odysseus_api.py cookbook stop SESSION_ID", file=sys.stderr)
+    print("  odysseus_api.py METHOD /api/codex/path [json-body]", file=sys.stderr)
+    return 2
+
+
+def _config() -> tuple[str, str] | None:
+    base_url = os.environ.get("ODYSSEUS_URL", "").strip().rstrip("/")
+    token = os.environ.get("ODYSSEUS_API_TOKEN", "").strip()
+    missing = []
+    if not base_url:
+        missing.append("ODYSSEUS_URL")
+    if not token:
+        missing.append("ODYSSEUS_API_TOKEN")
+    if missing:
+        print(f"missing {', '.join(missing)}; create a Codex Agent token in Odysseus Settings", file=sys.stderr)
+        return None
+    return base_url, token
+
+
+def main() -> int:
+    if len(sys.argv) < 2:
+        return _usage()
+
+    command = sys.argv[1].lower()
+    if command == "capabilities":
+        method = "GET"
+        path = "/api/codex/capabilities"
+        body = None
+    elif command == "todos":
+        if len(sys.argv) < 3:
+            return _usage()
+        action = sys.argv[2].lower()
+        path = "/api/codex/todos"
+        if action == "list":
+            method = "GET"
+            body = None
+        elif action == "add" and len(sys.argv) >= 4:
+            method = "POST"
+            body = json.dumps({"action": "add", "title": " ".join(sys.argv[3:])})
+        else:
+            return _usage()
+    elif command == "emails":
+        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 "10"
+            path = f"/api/codex/emails?folder=INBOX&limit={limit}&offset=0&filter=all"
+            body = None
+        elif action == "read" and len(sys.argv) >= 4:
+            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":
+        if len(sys.argv) < 3:
+            return _usage()
+        action = sys.argv[2].lower()
+        if action == "tasks":
+            method = "GET"
+            path = "/api/codex/cookbook/tasks"
+            body = None
+        elif action == "servers":
+            method = "GET"
+            path = "/api/codex/cookbook/servers"
+            body = None
+        elif action == "output" and len(sys.argv) >= 4:
+            method = "GET"
+            sid = sys.argv[3]
+            tail = sys.argv[4] if len(sys.argv) >= 5 else "400"
+            path = f"/api/codex/cookbook/output/{sid}?tail={tail}"
+            body = None
+        elif action == "cached":
+            method = "GET"
+            if len(sys.argv) >= 4:
+                from urllib.parse import quote
+                path = f"/api/codex/cookbook/cached?host={quote(sys.argv[3])}"
+            else:
+                path = "/api/codex/cookbook/cached"
+            body = None
+        elif action == "presets":
+            method = "GET"
+            path = "/api/codex/cookbook/presets"
+            body = None
+        elif action == "preset" and len(sys.argv) >= 4:
+            from urllib.parse import quote
+            method = "POST"
+            path = f"/api/codex/cookbook/preset/{quote(sys.argv[3])}"
+            body = None
+        elif action == "adopt" and len(sys.argv) >= 5:
+            method = "POST"
+            path = "/api/codex/cookbook/adopt"
+            payload = {"tmux_session": sys.argv[3], "model": sys.argv[4]}
+            if len(sys.argv) >= 6: payload["host"] = sys.argv[5]
+            if len(sys.argv) >= 7: payload["port"] = int(sys.argv[6])
+            body = json.dumps(payload)
+        elif action == "serve" and len(sys.argv) >= 5:
+            method = "POST"
+            path = "/api/codex/cookbook/serve"
+            payload = {"repo_id": sys.argv[3], "cmd": sys.argv[4]}
+            if len(sys.argv) >= 6:
+                payload["remote_host"] = sys.argv[5]
+            body = json.dumps(payload)
+        elif action == "stop" and len(sys.argv) >= 4:
+            method = "POST"
+            path = f"/api/codex/cookbook/stop/{sys.argv[3]}"
+            body = None
+        else:
+            return _usage()
+    else:
+        if len(sys.argv) < 3:
+            return _usage()
+        method = sys.argv[1].upper()
+        path = sys.argv[2]
+        body = sys.argv[3] if len(sys.argv) > 3 else None
+
+    if not path.startswith("/"):
+        path = "/" + path
+    if not path.startswith("/api/codex/"):
+        print("refusing non-/api/codex path; use scoped Odysseus integration endpoints only", file=sys.stderr)
+        return 2
+
+    config = _config()
+    if config is None:
+        return 2
+    base_url, token = config
+
+    data = None
+    headers = {
+        "Accept": "application/json",
+        "Authorization": f"Bearer {token}",
+    }
+    if body is not None:
+        try:
+            parsed = json.loads(body)
+        except json.JSONDecodeError as exc:
+            print(f"invalid json body: {exc}", file=sys.stderr)
+            return 2
+        data = json.dumps(parsed).encode("utf-8")
+        headers["Content-Type"] = "application/json"
+
+    req = urllib.request.Request(base_url + path, data=data, headers=headers, method=method)
+    try:
+        with urllib.request.urlopen(req, timeout=20) as resp:
+            print(resp.read().decode("utf-8"))
+            return 0
+    except urllib.error.HTTPError as exc:
+        text = exc.read().decode("utf-8", errors="replace")
+        print(text or f"HTTP {exc.code}", file=sys.stderr)
+        return 1
+    except OSError as exc:
+        print(f"request failed: {exc}", file=sys.stderr)
+        return 1
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

integrations/codex/.codex-plugin/plugin.json

@@ -0,0 +1,22 @@
+{
+  "name": "odysseus",
+  "version": "0.1.1",
+  "description": "Connect Codex to a scoped Odysseus instance.",
+  "author": {
+    "name": "Odysseus"
+  },
+  "skills": "./skills/",
+  "interface": {
+    "displayName": "Odysseus",
+    "shortDescription": "Use scoped Odysseus tools from Codex.",
+    "longDescription": "Connects Codex terminal sessions to Odysseus through user-controlled scoped API tokens. Codex must use /api/codex/* endpoints so Odysseus Settings can enforce tool access.",
+    "developerName": "Odysseus",
+    "category": "Productivity",
+    "capabilities": [
+      "todos",
+      "email",
+      "scoped-api"
+    ],
+    "defaultPrompt": "Use Odysseus only through configured scoped access. Check capabilities before reading or writing data."
+  }
+}

integrations/codex/README.md

@@ -0,0 +1,51 @@
+# Odysseus Codex Integration
+
+This directory contains the Codex plugin/skill bundle for Odysseus.
+
+## User Flow
+
+1. Open Odysseus Settings > Integrations.
+2. Add a Codex Agent.
+3. Copy the full setup commands shown after the generated token.
+4. Toggle the tools Codex is allowed to use.
+5. Configure the terminal Codex session:
+
+```bash
+export ODYSSEUS_URL=http://your-odysseus-host:7000
+export ODYSSEUS_API_TOKEN=ody_generated_token
+mkdir -p ~/plugins
+curl -fsSL -H "Authorization: Bearer $ODYSSEUS_API_TOKEN" "$ODYSSEUS_URL/api/codex/plugin.zip" -o /tmp/odysseus-codex-plugin.zip
+python3 -m zipfile -e /tmp/odysseus-codex-plugin.zip ~/plugins
+python3 - <<'PY'
+import json
+from pathlib import Path
+
+p = Path.home() / ".agents" / "plugins" / "marketplace.json"
+p.parent.mkdir(parents=True, exist_ok=True)
+if p.exists():
+    data = json.loads(p.read_text())
+else:
+    data = {"name": "personal", "interface": {"displayName": "Personal"}, "plugins": []}
+
+data.setdefault("name", "personal")
+data.setdefault("interface", {}).setdefault("displayName", "Personal")
+plugins = data.setdefault("plugins", [])
+entry = {
+    "name": "odysseus",
+    "source": {"source": "local", "path": "./plugins/odysseus"},
+    "policy": {"installation": "AVAILABLE", "authentication": "ON_INSTALL"},
+    "category": "Productivity",
+}
+data["plugins"] = [item for item in plugins if item.get("name") != "odysseus"] + [entry]
+p.write_text(json.dumps(data, indent=2) + "\n")
+PY
+codex plugin add odysseus@personal
+```
+
+6. Verify:
+
+```bash
+python3 ~/plugins/odysseus/scripts/odysseus_api.py capabilities
+```
+
+Codex must use `/api/codex/*` endpoints. SSH, Docker, direct Python imports, database queries, and MCP internals bypass Odysseus Settings and must not be used for user data access.

integrations/codex/scripts/odysseus_api.py

@@ -0,0 +1,218 @@
+#!/usr/bin/env python3
+"""Small Odysseus scoped API helper for Codex terminal sessions."""
+
+from __future__ import annotations
+
+import json
+import os
+import sys
+import urllib.error
+import urllib.request
+
+
+def _usage() -> int:
+    print("usage:", file=sys.stderr)
+    print("  odysseus_api.py capabilities", file=sys.stderr)
+    print("  odysseus_api.py todos list", file=sys.stderr)
+    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)
+    print("  odysseus_api.py cookbook presets", file=sys.stderr)
+    print("  odysseus_api.py cookbook output SESSION_ID [tail]", file=sys.stderr)
+    print("  odysseus_api.py cookbook serve REPO_ID 'CMD' [REMOTE_HOST]", file=sys.stderr)
+    print("  odysseus_api.py cookbook preset NAME", file=sys.stderr)
+    print("  odysseus_api.py cookbook adopt SESSION_ID MODEL [HOST] [PORT]", file=sys.stderr)
+    print("  odysseus_api.py cookbook stop SESSION_ID", file=sys.stderr)
+    print("  odysseus_api.py METHOD /api/codex/path [json-body]", file=sys.stderr)
+    return 2
+
+
+def _config() -> tuple[str, str] | None:
+    base_url = os.environ.get("ODYSSEUS_URL", "").strip().rstrip("/")
+    token = os.environ.get("ODYSSEUS_API_TOKEN", "").strip()
+    missing = []
+    if not base_url:
+        missing.append("ODYSSEUS_URL")
+    if not token:
+        missing.append("ODYSSEUS_API_TOKEN")
+    if missing:
+        print(f"missing {', '.join(missing)}; create a Codex Agent token in Odysseus Settings", file=sys.stderr)
+        return None
+    return base_url, token
+
+
+def main() -> int:
+    if len(sys.argv) < 2:
+        return _usage()
+
+    command = sys.argv[1].lower()
+    if command == "capabilities":
+        method = "GET"
+        path = "/api/codex/capabilities"
+        body = None
+    elif command == "todos":
+        if len(sys.argv) < 3:
+            return _usage()
+        action = sys.argv[2].lower()
+        path = "/api/codex/todos"
+        if action == "list":
+            method = "GET"
+            body = None
+        elif action == "add" and len(sys.argv) >= 4:
+            method = "POST"
+            body = json.dumps({"action": "add", "title": " ".join(sys.argv[3:])})
+        else:
+            return _usage()
+    elif command == "emails":
+        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 "10"
+            path = f"/api/codex/emails?folder=INBOX&limit={limit}&offset=0&filter=all"
+            body = None
+        elif action == "read" and len(sys.argv) >= 4:
+            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":
+        if len(sys.argv) < 3:
+            return _usage()
+        action = sys.argv[2].lower()
+        if action == "tasks":
+            method = "GET"
+            path = "/api/codex/cookbook/tasks"
+            body = None
+        elif action == "servers":
+            method = "GET"
+            path = "/api/codex/cookbook/servers"
+            body = None
+        elif action == "output" and len(sys.argv) >= 4:
+            method = "GET"
+            sid = sys.argv[3]
+            tail = sys.argv[4] if len(sys.argv) >= 5 else "400"
+            path = f"/api/codex/cookbook/output/{sid}?tail={tail}"
+            body = None
+        elif action == "cached":
+            method = "GET"
+            if len(sys.argv) >= 4:
+                from urllib.parse import quote
+                path = f"/api/codex/cookbook/cached?host={quote(sys.argv[3])}"
+            else:
+                path = "/api/codex/cookbook/cached"
+            body = None
+        elif action == "presets":
+            method = "GET"
+            path = "/api/codex/cookbook/presets"
+            body = None
+        elif action == "preset" and len(sys.argv) >= 4:
+            from urllib.parse import quote
+            method = "POST"
+            path = f"/api/codex/cookbook/preset/{quote(sys.argv[3])}"
+            body = None
+        elif action == "adopt" and len(sys.argv) >= 5:
+            method = "POST"
+            path = "/api/codex/cookbook/adopt"
+            payload = {"tmux_session": sys.argv[3], "model": sys.argv[4]}
+            if len(sys.argv) >= 6: payload["host"] = sys.argv[5]
+            if len(sys.argv) >= 7: payload["port"] = int(sys.argv[6])
+            body = json.dumps(payload)
+        elif action == "serve" and len(sys.argv) >= 5:
+            method = "POST"
+            path = "/api/codex/cookbook/serve"
+            payload = {"repo_id": sys.argv[3], "cmd": sys.argv[4]}
+            if len(sys.argv) >= 6:
+                payload["remote_host"] = sys.argv[5]
+            body = json.dumps(payload)
+        elif action == "stop" and len(sys.argv) >= 4:
+            method = "POST"
+            path = f"/api/codex/cookbook/stop/{sys.argv[3]}"
+            body = None
+        else:
+            return _usage()
+    else:
+        if len(sys.argv) < 3:
+            return _usage()
+        method = sys.argv[1].upper()
+        path = sys.argv[2]
+        body = sys.argv[3] if len(sys.argv) > 3 else None
+
+    if not path.startswith("/"):
+        path = "/" + path
+    if not path.startswith("/api/codex/"):
+        print("refusing non-/api/codex path; use scoped Odysseus integration endpoints only", file=sys.stderr)
+        return 2
+
+    config = _config()
+    if config is None:
+        return 2
+    base_url, token = config
+
+    data = None
+    headers = {
+        "Accept": "application/json",
+        "Authorization": f"Bearer {token}",
+    }
+    if body is not None:
+        try:
+            parsed = json.loads(body)
+        except json.JSONDecodeError as exc:
+            print(f"invalid json body: {exc}", file=sys.stderr)
+            return 2
+        data = json.dumps(parsed).encode("utf-8")
+        headers["Content-Type"] = "application/json"
+
+    req = urllib.request.Request(base_url + path, data=data, headers=headers, method=method)
+    try:
+        with urllib.request.urlopen(req, timeout=20) as resp:
+            print(resp.read().decode("utf-8"))
+            return 0
+    except urllib.error.HTTPError as exc:
+        text = exc.read().decode("utf-8", errors="replace")
+        print(text or f"HTTP {exc.code}", file=sys.stderr)
+        return 1
+    except OSError as exc:
+        print(f"request failed: {exc}", file=sys.stderr)
+        return 1
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

integrations/codex/skills/odysseus/SKILL.md

@@ -0,0 +1,142 @@
+---
+name: odysseus
+description: Use when the user asks Codex to read or write Odysseus data (todos, email, calendar, memory, documents) or to launch/monitor/stop a Cookbook model-serve task through the scoped Codex Agent API. Requires ODYSSEUS_URL and ODYSSEUS_API_TOKEN.
+---
+
+# Odysseus
+
+Use this skill when a user asks to interact with Odysseus from Codex.
+
+## Configuration
+
+Expect these environment variables:
+
+- `ODYSSEUS_URL`: Base URL for the user's Odysseus instance, for example `http://127.0.0.1:7000`.
+- `ODYSSEUS_API_TOKEN`: Scoped API token created in Odysseus Settings > Integrations > Add Integration > Codex Agent.
+
+If either value is missing, do not guess credentials. Tell the user to create a Codex Agent token in Odysseus Settings and expose both values to the terminal session.
+
+## When to use what
+
+- **Reminder ("remind me at 5pm to do X")** → TODO with `due_date`. The due_date IS the reminder — it fires a notification automatically via the user's configured channel (browser/email/ntfy). **Do NOT create a calendar event for a reminder.** Creating a calendar event named "Reminder" does NOT trigger a notification — it's just a time block on the calendar.
+- **Calendar event ("meeting at 3pm", "dentist Tuesday 10am")** → calendar event. Use for scheduled time blocks, meetings, appointments, recurring schedules. These show up on the calendar grid; reminders for them are configured separately in Odysseus settings.
+- **Note / freeform info ("note that the wifi password is ...")** → memory or todo without a due_date (depending on whether it's a fact about the user or an action item).
+- **Persistent fact / preference about the user** → memory.
+
+If the user says "reminder" + a time, default to TODO with due_date. Only switch to calendar if the user explicitly says "calendar", "event", "meeting", "appointment", or describes a time *range*.
+
+## Safety
+
+- All Odysseus data access MUST go through the scoped HTTP API under `/api/codex/*`.
+- Check `/api/codex/capabilities` before using a tool surface.
+- Treat `403` as an intentional Settings restriction. Do not work around it.
+- Do not use SSH, Docker, direct Python imports, SQLite queries, MCP internals, browser cookies, or local files to read/write Odysseus user data.
+- Do not call helpers like `do_manage_notes`, email MCP internals, or database sessions directly for user data, even if shell access exists.
+- Never send email directly unless the user explicitly asks to send and the token has a send-capable scope.
+- Keep actions scoped to the token owner.
+
+## Todos
+
+The Codex API supports todos/checklists:
+
+- `GET /api/codex/todos`
+- `POST /api/codex/todos`
+
+Use the bundled helper script when available:
+
+```bash
+python3 integrations/codex/scripts/odysseus_api.py capabilities
+python3 integrations/codex/scripts/odysseus_api.py todos list
+python3 integrations/codex/scripts/odysseus_api.py todos add "Follow up"
+```
+
+Supported todo actions are `list`, `add`, `update`, `delete`, and `toggle_item`.
+
+**Reminders (todos with a due date)** — the backend parses natural language. Send `due_date` in the body via the generic POST so the time becomes a structured reminder, NOT a literal substring inside the title. The `todos add TITLE` shortcut only sets the title, so use the POST form for anything with a time:
+
+```bash
+python3 integrations/codex/scripts/odysseus_api.py POST /api/codex/todos '{"action":"add","title":"Call dentist","due_date":"tomorrow at 5pm"}'
+```
+
+The backend accepts both ISO timestamps and natural language like `"tomorrow 5pm"`, `"next Monday 9am"`, `"in 2 hours"`. It anchors to the user's timezone.
+
+## Email
+
+The Codex API supports scoped email reads:
+
+- `GET /api/codex/emails?folder=INBOX&limit=10&offset=0&filter=all`
+- `GET /api/codex/emails/{uid}?folder=INBOX`
+
+Use the bundled helper script when available:
+
+```bash
+python3 integrations/codex/scripts/odysseus_api.py emails list 5
+python3 integrations/codex/scripts/odysseus_api.py emails read UID
+```
+
+If `/api/codex/capabilities` does not show `email.read: true`, do not inspect email. Ask the user to enable Email read in the Codex Agent settings.
+
+## Memory
+
+- `GET /api/codex/memory` — list memories for the token owner.
+- `POST /api/codex/memory` — body `{"text": "...", "category": "fact", "source": "user", "session_id": null}`. Requires `memory:write`.
+- `DELETE /api/codex/memory/{memory_id}` — remove a memory entry. Requires `memory:write`.
+
+```bash
+python3 integrations/codex/scripts/odysseus_api.py GET /api/codex/memory
+python3 integrations/codex/scripts/odysseus_api.py POST /api/codex/memory '{"text":"User prefers SI units","category":"preference"}'
+```
+
+## Calendar
+
+- `GET /api/codex/calendar/events?start=ISO&end=ISO` — list events in window.
+- `POST /api/codex/calendar/events` — body matches `EventCreate` (`summary`, `dtstart`, `dtend`, `all_day`, `description`, `location`, `calendar_href`, `rrule`, `color`). Requires `calendar:write`.
+- `DELETE /api/codex/calendar/events/{uid}` — delete event by uid (the value returned in the POST response). Requires `calendar:write`.
+
+## Documents
+
+- `GET /api/codex/documents?search=...&limit=50` — paginated library.
+- `GET /api/codex/documents/{doc_id}` — fetch one document.
+- `POST /api/codex/documents` — body `{"session_id": "...", "title": "...", "content": "...", "language": "markdown"}`. Requires `documents:write`.
+- `DELETE /api/codex/documents/{doc_id}` — delete a document. Requires `documents:write`.
+
+## 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.
+
+## Cookbook serve (debug a failing model launch)
+
+The Cookbook surface lets you reproduce what a human would do in Odysseus → Cookbook: read which serves are running, tail their tmux output to see why they crashed, edit the launch command, relaunch, kill a stuck one. Use this when the user is debugging a model server that won't come up (compute-capability errors, OOM, missing kernels, wrong attention backend, etc.).
+
+- `GET /api/codex/cookbook/tasks` — list active serve/download/install tasks (sessionId, type, status, repo_id, remoteHost, payload._cmd). Requires `cookbook:read`.
+- `GET /api/codex/cookbook/servers` — list configured servers (name, host, port, env type + path, model dirs). Requires `cookbook:read`.
+- `GET /api/codex/cookbook/cached?host=<NAME>` — list models already cached on the named server (HF cache + Ollama + extra modelDirs). Call BEFORE `serve` to see what's already on disk. Requires `cookbook:read`.
+- `GET /api/codex/cookbook/presets` — list saved serve presets (model + host + port + cmd). The user's saved preset usually has a working cmd — try `preset NAME` before composing your own. Requires `cookbook:read`.
+- `GET /api/codex/cookbook/output/{session_id}?tail=400` — read the last N lines of the task's persistent log file (preferred) or tmux pane (fallback). The log file persists across vllm crashes, so this returns the actual Python traceback even after the bash prompt + neofetch banner overwrites the pane. Default tail=400. Requires `cookbook:read`.
+- `POST /api/codex/cookbook/serve` — launch a serve task. Body matches `ServeRequest`: `{ repo_id, cmd, remote_host?, ssh_port?, env_prefix?, gpus?, platform? }`. The `cmd` is validated: leading binary must be `vllm`/`python3`/`sglang`/`llama-server`/`ollama`/`node`/`npx`. NEVER prefix with `cd …`, `source …`, or chain with `&&`/`||`/`;`/`$(...)` — the validator rejects shell metacharacters. The venv activation (`env_prefix`) is added automatically from the host's saved settings, so pass the bare binary + args. Requires `cookbook:launch`.
+- `POST /api/codex/cookbook/preset/{name}` — launch a saved preset by name. Reuses the working cmd + host the user already saved. Requires `cookbook:launch`.
+- `POST /api/codex/cookbook/adopt` — register an externally-launched tmux session into cookbook tracking. Body: `{ tmux_session, model, host?, port? }`. Use this when serve_model rejected a cmd and you fell back to direct ssh+tmux — without adoption, the session is invisible to the UI. Requires `cookbook:launch`.
+- `POST /api/codex/cookbook/stop/{session_id}` — kill the tmux session. Requires `cookbook:launch`.
+
+```bash
+python3 ~/plugins/odysseus/scripts/odysseus_api.py cookbook tasks
+python3 ~/plugins/odysseus/scripts/odysseus_api.py cookbook output serve-abc12345 400
+python3 ~/plugins/odysseus/scripts/odysseus_api.py cookbook stop serve-abc12345
+python3 ~/plugins/odysseus/scripts/odysseus_api.py cookbook serve \
+  /mnt/HADES/models/Qwen3.5-397B-A17B-AWQ \
+  "vllm serve /mnt/HADES/models/Qwen3.5-397B-A17B-AWQ --host 0.0.0.0 --port 8001 --tensor-parallel-size 8 --max-model-len 262144 --gpu-memory-utilization 0.90 --dtype auto --max-num-seqs 8 --trust-remote-code --enable-expert-parallel --enable-auto-tool-choice --tool-call-parser qwen3_coder --reasoning-parser qwen3" \
+  pewds@192.168.1.12
+```
+
+**Debug loop pattern:** `tasks` → `output SID 600` (find root cause; request larger `tail` if it references "above") → `stop SID` → `serve repo "new cmd"` → wait ~20s → `output` on the new sessionId.
+
+**Hard limits this surface enforces:**
+- `cookbook serve` cmd allowlist + shell-metacharacter rejection.
+- `cookbook stop` requires sessionIds matching `[a-zA-Z0-9_-]+`.
+- Agent CAN spawn GPU-pinning long-lived processes — always `cookbook stop` your previous attempt before relaunching.
+
+## Forbidden Bypass Pattern
+
+If you are about to reach the Odysseus host/container, import app internals, query the database, or call MCP helper modules directly, stop. Those paths bypass Odysseus Settings and token scopes. Ask the user to enable the relevant Codex Agent tool toggle instead.

launch-windows.ps1

@@ -0,0 +1,169 @@
+#Requires -Version 5.1
+<#
+  Odysseus - native Windows launcher (no Docker).
+
+  One command to: create a virtualenv, install dependencies, run first-time
+  setup (prints an admin password on first run), and start the server.
+  Safe to re-run - it skips whatever already exists.
+
+  Usage:
+    powershell -ExecutionPolicy Bypass -File .\launch-windows.ps1
+    powershell -ExecutionPolicy Bypass -File .\launch-windows.ps1 -Port 7000 -BindHost 127.0.0.1
+
+  Tip: bind 127.0.0.1 (default) for local-only use. Use 0.0.0.0 only when you
+  intentionally want other devices on your LAN to reach it.
+#>
+param(
+    [int]$Port = 7000,
+    [string]$BindHost = "127.0.0.1"
+)
+
+$ErrorActionPreference = "Stop"
+Set-Location -Path $PSScriptRoot
+
+function Write-Step($msg) { Write-Host ""; Write-Host ("==> " + $msg) -ForegroundColor Cyan }
+function Fail($msg) {
+    Write-Host ""
+    Write-Host ("ERROR: " + $msg) -ForegroundColor Red
+    Write-Host ""
+    Read-Host "Press Enter to exit"
+    exit 1
+}
+
+function Test-WindowsBashStub($path) {
+    if (-not $path) { return $false }
+    $lowered = $path.ToLowerInvariant()
+    foreach ($stub in @("system32\bash.exe", "sysnative\bash.exe", "windowsapps\bash.exe")) {
+        if ($lowered.Contains($stub)) { return $true }
+    }
+    return $false
+}
+
+function Find-GitBash {
+    $cmd = Get-Command bash -ErrorAction SilentlyContinue
+    if ($cmd -and -not (Test-WindowsBashStub $cmd.Source)) { return $cmd.Source }
+
+    $roots = @()
+    foreach ($name in @("ProgramFiles", "ProgramW6432", "ProgramFiles(x86)", "LocalAppData")) {
+        $base = [Environment]::GetEnvironmentVariable($name)
+        if ($base) {
+            $roots += (Join-Path $base "Git")
+            if ($name -eq "LocalAppData") { $roots += (Join-Path $base "Programs\Git") }
+        }
+    }
+    $roots += @("C:\Program Files\Git", "C:\Program Files (x86)\Git")
+
+    foreach ($root in ($roots | Select-Object -Unique)) {
+        foreach ($relative in @("bin\bash.exe", "usr\bin\bash.exe")) {
+            $candidate = Join-Path $root $relative
+            if (Test-Path $candidate) { return $candidate }
+        }
+    }
+    return $null
+}
+
+# 1. Locate a Python interpreter (3.11+ required)
+Write-Step "Checking for Python"
+function Get-PythonVersionText($launcher, $launcherArgs) {
+    try {
+        return (& $launcher @launcherArgs -c "import sys; print('.'.join(map(str, sys.version_info[:3])))" 2>$null).Trim()
+    } catch {
+        return $null
+    }
+}
+
+$pyExe = $null
+$pyArgs = @()
+$pyVersion = $null
+
+$pyLauncher = Get-Command py -ErrorAction SilentlyContinue
+if ($pyLauncher) {
+    foreach ($v in @("-3.13", "-3.12", "-3.11")) {
+        $ver = Get-PythonVersionText $pyLauncher.Source @($v)
+        if ($ver) {
+            $pyExe = $pyLauncher.Source
+            $pyArgs = @($v)
+            $pyVersion = $ver
+            break
+        }
+    }
+}
+
+if (-not $pyExe) {
+    $pythonCmd = Get-Command python -ErrorAction SilentlyContinue
+    if ($pythonCmd) {
+        $ver = Get-PythonVersionText $pythonCmd.Source @()
+        if ($ver) {
+            $versionParts = $ver.Split('.')
+            $major = [int]$versionParts[0]
+            $minor = [int]$versionParts[1]
+            if ($major -gt 3 -or ($major -eq 3 -and $minor -ge 11)) {
+                $pyExe = $pythonCmd.Source
+                $pyVersion = $ver
+            }
+        }
+    }
+}
+
+if ($pyExe -like "*WindowsApps*python.exe") {
+    $pyCmd = Get-Command py -ErrorAction SilentlyContinue
+    if ($pyCmd) {
+        $pyExe = $pyCmd.Source
+        $pyArgs = @("-3.11")
+    }
+}
+
+if (-not $pyExe) {
+    Fail "Couldn't find Python 3.11+ for Windows setup. Install Python 3.11+ (or open the Python launcher with 'py -3.11') from https://www.python.org/downloads/, then re-run this script."
+}
+$pythonLabel = ("Using Python {0}: {1} {2}" -f $pyVersion, $pyExe, ($pyArgs -join ' ')).TrimEnd()
+Write-Host $pythonLabel
+
+# 2. Create the virtualenv if missing
+$venvPy = Join-Path $PSScriptRoot "venv\Scripts\python.exe"
+if (-not (Test-Path $venvPy)) {
+    Write-Step "Creating virtual environment (venv)"
+    & $pyExe @pyArgs -m venv venv
+    if ($LASTEXITCODE -ne 0 -or -not (Test-Path $venvPy)) { Fail "Failed to create the virtual environment." }
+} else {
+    Write-Host "venv already exists - skipping creation."
+}
+
+# 3. Install / update dependencies
+Write-Step "Installing dependencies (first run can take a few minutes)"
+& $venvPy -m pip install --upgrade pip --quiet
+& $venvPy -m pip install -r requirements.txt
+if ($LASTEXITCODE -ne 0) { Fail "Dependency install failed. Scroll up for the pip error." }
+
+# 4. First-time setup (creates data dirs, DB, .env, admin user)
+Write-Step "Running first-time setup"
+& $venvPy setup.py
+if ($LASTEXITCODE -ne 0) { Fail "setup.py failed." }
+
+# 5. Friendly note about Git Bash (full Cookbook / agent-shell parity)
+if (-not (Find-GitBash)) {
+    Write-Host ""
+    Write-Host "NOTE: Git Bash (bash.exe) was not found on PATH." -ForegroundColor Yellow
+    Write-Host "      The core app works without it. For full Cookbook background" -ForegroundColor Yellow
+    Write-Host "      downloads and the agent shell tool, install Git for Windows:" -ForegroundColor Yellow
+    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)
+Write-Step ("Starting Odysseus at http://{0}:{1}" -f $BindHost, $Port)
+Write-Host "Press Ctrl+C to stop."
+Write-Host ""
+& $venvPy -m uvicorn app:app --host $BindHost --port $Port

launcher.py

@@ -0,0 +1,142 @@
+# launcher.py
+"""Dedicated entrypoint for the standalone Windows portable launcher.
+
+Handles:
+- Immediate GUI splash screen creation using tkinter.
+- Suppressing console stream crashes in windowed GUI mode via NullWriter.
+- Spawning system tray icon via pystray and Pillow (lazy-loaded).
+- Auto-opening default browser pointing to the running backend.
+- Launching the FastAPI server (importing and running app.py).
+"""
+import os
+import sys
+import threading
+import time
+import webbrowser
+
+# Define a dummy NullWriter to suppress standard stream crashes (isatty etc.) in GUI mode
+class NullWriter:
+    def write(self, text):
+        pass
+    def flush(self):
+        pass
+    def isatty(self):
+        return False
+
+if sys.stdout is None:
+    sys.stdout = NullWriter()
+if sys.stderr is None:
+    sys.stderr = NullWriter()
+
+
+splash_root = None
+
+# If running from a frozen PyInstaller bundle, launch the splash screen IMMEDIATELY
+if getattr(sys, 'frozen', False):
+    import tkinter as tk
+
+    def show_splash_instantly():
+        global splash_root
+        try:
+            splash_root = tk.Tk()
+            splash_root.title("Odysseus")
+            splash_root.overrideredirect(True)
+            splash_root.configure(bg="#1a1c23")
+
+            # Accented borders
+            splash_root.config(highlightbackground="#e06c75", highlightcolor="#e06c75", highlightthickness=1)
+
+            w, h = 360, 160
+            ws = splash_root.winfo_screenwidth()
+            hs = splash_root.winfo_screenheight()
+            x = (ws - w) // 2
+            y = (hs - h) // 2
+            splash_root.geometry(f"{w}x{h}+{x}+{y}")
+
+            tk.Label(splash_root, text="⛵ Odysseus", font=("Segoe UI", 22, "bold"), bg="#1a1c23", fg="#e06c75").pack(pady=(22, 2))
+            tk.Label(splash_root, text="Launching background services...", font=("Segoe UI", 10), bg="#1a1c23", fg="#d1d4e0").pack(pady=2)
+            tk.Label(splash_root, text="Please wait, this will take a few seconds.", font=("Segoe UI", 8, "italic"), bg="#1a1c23", fg="#5c6370").pack(pady=(12, 0))
+
+            splash_root.attributes("-topmost", True)
+            splash_root.mainloop()
+        except Exception:
+            pass
+
+    # Launch the GUI splash screen immediately on a background thread
+    threading.Thread(target=show_splash_instantly, daemon=True).start()
+
+
+def create_tray_image():
+    # Generate a beautiful 64x64 icon matching Odysseus brand red accent (#e06c75)
+    from PIL import Image, ImageDraw
+    image = Image.new('RGBA', (64, 64), (0, 0, 0, 0))
+    dc = ImageDraw.Draw(image)
+    accent_red = (224, 108, 117, 255)
+    light_red = (224, 108, 117, 150)
+
+    # Draw premium sailing boat
+    dc.polygon([(32, 10), (32, 45), (12, 45)], fill=accent_red)
+    dc.polygon([(32, 18), (32, 45), (48, 45)], fill=light_red)
+    dc.polygon([(8, 48), (56, 48), (44, 56), (20, 56)], fill=accent_red)
+    return image
+
+
+def on_open_browser(icon, item, url):
+    webbrowser.open(url)
+
+
+def on_exit(icon, item):
+    icon.stop()
+    os._exit(0)
+
+
+def setup_system_tray(url):
+    try:
+        import pystray
+        icon_img = create_tray_image()
+        menu = (
+            pystray.MenuItem('Open Odysseus', lambda icon, item: on_open_browser(icon, item, url), default=True),
+            pystray.MenuItem('Exit', on_exit)
+        )
+        tray_icon = pystray.Icon(
+            "Odysseus",
+            icon_img,
+            "Odysseus",
+            menu
+        )
+        tray_icon.run()
+    except Exception:
+        pass
+
+
+def open_browser(url):
+    # Allow uvicorn and app lifecycles to complete warmups
+    time.sleep(3.5)
+
+    # Safely close the splash screen
+    try:
+        global splash_root
+        if splash_root:
+            splash_root.after(0, splash_root.destroy)
+    except Exception:
+        pass
+
+    webbrowser.open(url)
+
+
+if __name__ == "__main__":
+    import uvicorn
+    # Import the FastAPI app from app.py
+    from app import app
+
+    bind_host = os.getenv("APP_BIND", "127.0.0.1")
+    bind_port = int(os.getenv("APP_PORT", "7000"))
+    url = f"http://{bind_host}:{bind_port}"
+
+    if getattr(sys, 'frozen', False):
+        # Start browser manager thread
+        threading.Thread(target=open_browser, args=(url,), daemon=True).start()
+        # Start system tray manager thread
+        threading.Thread(target=setup_system_tray, args=(url,), daemon=True).start()
+
+    uvicorn.run(app, host=bind_host, port=bind_port, log_level="info")

licenses/OpenDyslexic-OFL.txt

@@ -0,0 +1,94 @@
+Copyright (c) 2019-07-29, Abbie Gonzalez (https://abbiecod.es|support@abbiecod.es),
+with Reserved Font Name OpenDyslexic.
+Copyright (c) 12/2012 - 2019
+This Font Software is licensed under the SIL Open Font License, Version 1.1.
+This license is copied below, and is also available with a FAQ at:
+http://scripts.sil.org/OFL
+
+
+-----------------------------------------------------------
+SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007
+-----------------------------------------------------------
+
+PREAMBLE
+The goals of the Open Font License (OFL) are to stimulate worldwide
+development of collaborative font projects, to support the font creation
+efforts of academic and linguistic communities, and to provide a free and
+open framework in which fonts may be shared and improved in partnership
+with others.
+
+The OFL allows the licensed fonts to be used, studied, modified and
+redistributed freely as long as they are not sold by themselves. The
+fonts, including any derivative works, can be bundled, embedded,
+redistributed and/or sold with any software provided that any reserved
+names are not used by derivative works. The fonts and derivatives,
+however, cannot be released under any other type of license. The
+requirement for fonts to remain under this license does not apply
+to any document created using the fonts or their derivatives.
+
+DEFINITIONS
+"Font Software" refers to the set of files released by the Copyright
+Holder(s) under this license and clearly marked as such. This may
+include source files, build scripts and documentation.
+
+"Reserved Font Name" refers to any names specified as such after the
+copyright statement(s).
+
+"Original Version" refers to the collection of Font Software components as
+distributed by the Copyright Holder(s).
+
+"Modified Version" refers to any derivative made by adding to, deleting,
+or substituting -- in part or in whole -- any of the components of the
+Original Version, by changing formats or by porting the Font Software to a
+new environment.
+
+"Author" refers to any designer, engineer, programmer, technical
+writer or other person who contributed to the Font Software.
+
+PERMISSION & CONDITIONS
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of the Font Software, to use, study, copy, merge, embed, modify,
+redistribute, and sell modified and unmodified copies of the Font
+Software, subject to the following conditions:
+
+1) Neither the Font Software nor any of its individual components,
+in Original or Modified Versions, may be sold by itself.
+
+2) Original or Modified Versions of the Font Software may be bundled,
+redistributed and/or sold with any software, provided that each copy
+contains the above copyright notice and this license. These can be
+included either as stand-alone text files, human-readable headers or
+in the appropriate machine-readable metadata fields within text or
+binary files as long as those fields can be easily viewed by the user.
+
+3) No Modified Version of the Font Software may use the Reserved Font
+Name(s) unless explicit written permission is granted by the corresponding
+Copyright Holder. This restriction only applies to the primary font name as
+presented to the users.
+
+4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font
+Software shall not be used to promote, endorse or advertise any
+Modified Version, except to acknowledge the contribution(s) of the
+Copyright Holder(s) and the Author(s) or with their explicit written
+permission.
+
+5) The Font Software, modified or unmodified, in part or in whole,
+must be distributed entirely under this license, and must not be
+distributed under any other license. The requirement for fonts to
+remain under this license does not apply to any document created
+using the Font Software.
+
+TERMINATION
+This license becomes null and void if any of the above conditions are
+not met.
+
+DISCLAIMER
+THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT
+OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE
+COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL
+DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM
+OTHER DEALINGS IN THE FONT SOFTWARE.

mcp_servers/_common.py

@@ -1,18 +0,0 @@
-"""
-_common.py
-
-Shared constants and helpers for built-in MCP servers.
-"""
-
-MAX_OUTPUT_CHARS = 10_000
-MAX_READ_CHARS = 20_000
-SHELL_TIMEOUT = 60
-PYTHON_TIMEOUT = 30
-SEARCH_TIMEOUT = 30
-
-
-def truncate(text: str, limit: int = MAX_OUTPUT_CHARS) -> str:
-    """Truncate text to *limit* characters with a suffix note."""
-    if len(text) > limit:
-        return text[:limit] + f"\n... (truncated, {len(text)} chars total)"
-    return text

mcp_servers/image_gen_server.py

@@ -16,6 +16,8 @@ from mcp.types import Tool, TextContent
 
 sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
 
+from src.constants import GENERATED_IMAGES_DIR
+
 server = Server("image_gen")
 
 
@@ -71,7 +73,7 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
         if not model_spec:
             for candidate in ("gpt-image-1.5", "gpt-image-1", "dall-e-3"):
                 try:
-                    _resolve_model(candidate)
+                    await asyncio.to_thread(_resolve_model, candidate)
                     model_spec = candidate
                     break
                 except ValueError:
@@ -79,7 +81,13 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
             if not model_spec:
                 return [TextContent(type="text", text="Error: No image model found. Configure one in Admin.")]
 
-        url, model_id, headers = _resolve_model(model_spec)
+        try:
+            url, model_id, headers = await asyncio.to_thread(_resolve_model, model_spec, model_type="image")
+        except ValueError:
+            _lower_model_spec = model_spec.lower()
+            if not any(_name in _lower_model_spec for _name in ("gpt-image", "dall-e")):
+                raise
+            url, model_id, headers = await asyncio.to_thread(_resolve_model, model_spec)
 
         is_gpt_image = "gpt-image" in model_id.lower()
         base_url = url.replace("/chat/completions", "").replace("/v1/messages", "").rstrip("/")
@@ -115,14 +123,18 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
 
             img = images[0]
             image_url = None
+            # Prefix the instance's public base URL (existing app_public_url setting) so the
+            # link is fully-qualified and clickable when the model echoes it. Empty = relative
+            # same-origin path (unchanged default).
+            _pub_base = (get_setting("app_public_url", "") or "").rstrip("/")
 
             if img.get("b64_json"):
-                img_dir = Path("data/generated_images")
+                img_dir = Path(GENERATED_IMAGES_DIR)
                 img_dir.mkdir(parents=True, exist_ok=True)
                 filename = f"{uuid.uuid4().hex[:12]}.png"
                 img_path = img_dir / filename
                 img_path.write_bytes(base64.b64decode(img["b64_json"]))
-                image_url = f"/api/generated-image/{filename}"
+                image_url = f"{_pub_base}/api/generated-image/{filename}"
 
                 # Save to gallery
                 try:
@@ -146,7 +158,13 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
             else:
                 return [TextContent(type="text", text="Error: Unexpected image API response format")]
 
-            result = f"Generated image for: {prompt[:100]}\nimage_url: {image_url}\nmodel: {model_id}\nsize: {size}"
+            # "Direct link:" rather than an "image_url:" label — small models copied the
+            # label token ("image_url") into the link href, producing a broken link.
+            result = (
+                f"Generated image for: {prompt[:100]}\n"
+                f"Direct link: {image_url}\n"
+                f"model: {model_id}\nsize: {size}"
+            )
             return [TextContent(type="text", text=result)]
 
     except httpx.TimeoutException:

mcp_servers/memory_server.py

@@ -6,6 +6,7 @@ Imports MemoryManager and MemoryVectorStore from the Odysseus codebase.
 """
 
 import asyncio
+import os
 import sys
 import time
 from pathlib import Path
@@ -23,6 +24,55 @@ _memory_manager = None
 _memory_vector = None
 _initialized = False
 
+_OWNER_ENV_KEYS = ("ODYSSEUS_MCP_MEMORY_OWNER", "ODYSSEUS_MEMORY_OWNER")
+_OWNER_SCOPE_ERROR = (
+    "Error: Memory MCP owner is not configured for an owner-scoped memory store. "
+    "Set ODYSSEUS_MCP_MEMORY_OWNER for this server or use the owner-aware native memory tool."
+)
+
+
+def _configured_owner() -> str | None:
+    for key in _OWNER_ENV_KEYS:
+        owner = os.environ.get(key, "").strip()
+        if owner:
+            return owner
+    return None
+
+
+def _entry_owner(entry: dict) -> str | None:
+    owner = entry.get("owner")
+    if owner is None:
+        return None
+    owner_text = str(owner).strip()
+    return owner_text or None
+
+
+def _owner_scoped_store(entries: list[dict]) -> bool:
+    return any(_entry_owner(entry) for entry in entries if isinstance(entry, dict))
+
+
+def _scope_entries() -> tuple[str | None, list[dict], list[dict], str | None]:
+    """Return configured owner, all entries, visible entries, and optional error."""
+    entries = _memory_manager.load_all()
+    owner = _configured_owner()
+    if owner is None and _owner_scoped_store(entries):
+        return None, entries, [], _OWNER_SCOPE_ERROR
+    if owner is None:
+        visible = [
+            entry for entry in entries
+            if isinstance(entry, dict) and _entry_owner(entry) is None
+        ]
+    else:
+        visible = [
+            entry for entry in entries
+            if isinstance(entry, dict) and _entry_owner(entry) == owner
+        ]
+    return owner, entries, visible, None
+
+
+def _text_result(text: str) -> list[TextContent]:
+    return [TextContent(type="text", text=text)]
+
 
 def _ensure_init():
     """Lazy-init memory managers on first use."""
@@ -75,43 +125,46 @@ async def list_tools() -> list[Tool]:
 @server.call_tool()
 async def call_tool(name: str, arguments: dict) -> list[TextContent]:
     if name != "manage_memory":
-        return [TextContent(type="text", text=f"Unknown tool: {name}")]
+        return _text_result(f"Unknown tool: {name}")
 
     _ensure_init()
     if not _memory_manager:
-        return [TextContent(type="text", text="Error: Memory manager not available")]
+        return _text_result("Error: Memory manager not available")
 
     action = arguments.get("action", "")
 
     if action == "list":
         category_filter = arguments.get("category", "")
-        memories = _memory_manager.load()
+        _owner, _all_memories, memories, scope_error = _scope_entries()
+        if scope_error:
+            return _text_result(scope_error)
         if category_filter:
             memories = [m for m in memories if m.get("category", "").lower() == category_filter.lower()]
         if not memories:
             msg = "No memories found"
             if category_filter:
                 msg += f" in category '{category_filter}'"
-            return [TextContent(type="text", text=msg + ".")]
+            return _text_result(msg + ".")
+
         lines = [f"Found {len(memories)} memory entries:\n"]
-        for m in memories[:100]:
+        for m in memories:
             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))]
+        return _text_result("\n".join(lines))
 
     elif action == "add":
         text = arguments.get("text", "")
         category = arguments.get("category", "fact")
         if not text:
-            return [TextContent(type="text", text="Error: Memory text cannot be empty")]
-        entry = _memory_manager.add_entry(text, source="ai_agent", category=category)
-        memories = _memory_manager.load_all()
+            return _text_result("Error: Memory text cannot be empty")
+        owner, memories, _visible, scope_error = _scope_entries()
+        if scope_error:
+            return _text_result(scope_error)
+        entry = _memory_manager.add_entry(text, source="ai_agent", category=category, owner=owner)
         memories.append(entry)
         _memory_manager.save(memories)
         if _memory_vector and _memory_vector.healthy:
@@ -119,25 +172,28 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
                 _memory_vector.add(entry["id"], text)
             except Exception:
                 pass
-        return [TextContent(type="text", text=f"Memory added: [{category}] {text} (id: {entry['id'][:8]})")]
+        return _text_result(f"Memory added: [{category}] {text} (id: {entry['id'][:8]})")
 
     elif action == "edit":
         memory_id = arguments.get("memory_id", "")
         new_text = arguments.get("text", "")
         if not memory_id or not new_text:
-            return [TextContent(type="text", text="Error: edit needs memory_id and text")]
-        memories = _memory_manager.load_all()
-        found = False
+            return _text_result("Error: edit needs memory_id and text")
+        _owner, memories, visible, scope_error = _scope_entries()
+        if scope_error:
+            return _text_result(scope_error)
         full_id = None
-        for m in memories:
+        for m in visible:
             if m.get("id", "").startswith(memory_id):
-                m["text"] = new_text
-                m["timestamp"] = int(time.time())
-                found = True
                 full_id = m["id"]
                 break
-        if not found:
-            return [TextContent(type="text", text=f"Error: Memory '{memory_id}' not found")]
+        if not full_id:
+            return _text_result(f"Error: Memory '{memory_id}' not found")
+        for m in memories:
+            if m.get("id") == full_id:
+                m["text"] = new_text
+                m["timestamp"] = int(time.time())
+                break
         _memory_manager.save(memories)
         if _memory_vector and _memory_vector.healthy and full_id:
             try:
@@ -145,26 +201,27 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
                 _memory_vector.add(full_id, new_text)
             except Exception:
                 pass
-        return [TextContent(type="text", text=f"Memory updated: {new_text}")]
+        return _text_result(f"Memory updated: {new_text}")
 
     elif action == "delete":
         memory_id = arguments.get("memory_id", "")
         if not memory_id:
-            return [TextContent(type="text", text="Error: delete needs memory_id")]
-        memories = _memory_manager.load_all()
+            return _text_result("Error: delete needs memory_id")
+        _owner, memories, visible, scope_error = _scope_entries()
+        if scope_error:
+            return _text_result(scope_error)
         full_id = None
         deleted_text = ""
         deleted_category = ""
-        for m in memories:
+        for m in visible:
             if m.get("id", "").startswith(memory_id):
                 full_id = m["id"]
                 deleted_text = m.get("text", "")
                 deleted_category = m.get("category", "")
                 break
-        original_len = len(memories)
-        memories = [m for m in memories if not m.get("id", "").startswith(memory_id)]
-        if len(memories) == original_len:
-            return [TextContent(type="text", text=f"Error: Memory '{memory_id}' not found")]
+        if not full_id:
+            return _text_result(f"Error: Memory '{memory_id}' not found")
+        memories = [m for m in memories if m.get("id") != full_id]
         _memory_manager.save(memories)
         if _memory_vector and _memory_vector.healthy and full_id:
             try:
@@ -173,30 +230,32 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
                 pass
         cat = f"[{deleted_category}] " if deleted_category else ""
         snippet = deleted_text if len(deleted_text) <= 120 else deleted_text[:117] + "..."
-        return [TextContent(type="text", text=f"Memory deleted: {cat}{snippet} (id: {memory_id})")]
+        return _text_result(f"Memory deleted: {cat}{snippet} (id: {memory_id})")
 
     elif action == "search":
         query = arguments.get("text", "")
         if not query:
-            return [TextContent(type="text", text="Error: search needs text (query)")]
-        memories = _memory_manager.load()
+            return _text_result("Error: search needs text (query)")
+        _owner, _all_memories, memories, scope_error = _scope_entries()
+        if scope_error:
+            return _text_result(scope_error)
         if hasattr(_memory_manager, 'get_relevant_memories'):
             results = _memory_manager.get_relevant_memories(query, memories, threshold=0.05, max_items=20)
         else:
             query_lower = query.lower()
             results = [m for m in memories if query_lower in m.get("text", "").lower()][:20]
         if not results:
-            return [TextContent(type="text", text=f"No memories found matching '{query}'.")]
+            return _text_result(f"No memories found matching '{query}'.")
         lines = [f"Found {len(results)} matching memories:\n"]
         for m in results:
             cat = m.get("category", "fact")
             mid = m.get("id", "?")[:8]
             text = m.get("text", "")
             lines.append(f"- [{cat}] `{mid}` — {text}")
-        return [TextContent(type="text", text="\n".join(lines))]
+        return _text_result("\n".join(lines))
 
     else:
-        return [TextContent(type="text", text=f"Error: Unknown action '{action}'. Use: list, add, edit, delete, search")]
+        return _text_result(f"Error: Unknown action '{action}'. Use: list, add, edit, delete, search")
 
 
 async def run():

mcp_servers/rag_server.py

@@ -101,10 +101,13 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
             return [TextContent(type="text", text=f"Error: {e}")]
 
     elif action == "add_directory":
-        directory = arguments.get("directory", "").strip()
+        _dir = arguments.get("directory")
+        directory = _dir.strip() if isinstance(_dir, str) else ""
         if not directory:
             return [TextContent(type="text", text="Error: add_directory needs a directory path")]
-        directory = os.path.expanduser(directory)
+        # Store an absolute path so indexed `source` metadata is absolute and
+        # remove_directory (which abspath-normalizes) can match it later (#1660).
+        directory = os.path.abspath(os.path.expanduser(directory))
         if not os.path.isdir(directory):
             return [TextContent(type="text", text=f"Error: Directory not found: {directory}")]
         if not _rag_manager:
@@ -112,14 +115,27 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
         try:
             result = _rag_manager.index_personal_documents(directory)
             indexed = result.get("indexed_count", 0) if isinstance(result, dict) else 0
+            # Record the directory so `list` and `remove_directory` can see it.
+            # Indexing was just done above, so pass index=False to avoid a second
+            # (ownerless) pass. Without this the directory was indexed but never
+            # tracked in indexed_directories, so it was invisible/unremovable.
+            if _personal_docs_manager and hasattr(_personal_docs_manager, "add_directory"):
+                try:
+                    _personal_docs_manager.add_directory(directory, index=False)
+                except Exception:
+                    pass
             return [TextContent(type="text", text=f"Directory '{directory}' added to RAG index ({indexed} chunks indexed)")]
         except Exception as e:
             return [TextContent(type="text", text=f"Error: Failed to index directory: {e}")]
 
     elif action == "remove_directory":
-        directory = arguments.get("directory", "").strip()
+        _dir = arguments.get("directory")
+        directory = _dir.strip() if isinstance(_dir, str) else ""
         if not directory:
             return [TextContent(type="text", text="Error: remove_directory needs a directory path")]
+        # Expand ~ to match add_directory, which indexes the expanded path.
+        # Without this, removing "~/docs" never matches the stored absolute path.
+        directory = os.path.expanduser(directory)
         if not _personal_docs_manager:
             return [TextContent(type="text", text="Error: Personal docs manager not available")]
         try:

odysseus-ui.service

@@ -9,7 +9,7 @@ Type=simple
 # CHANGE THESE to match your user and install path:
 User=YOURUSER
 WorkingDirectory=/home/YOURUSER/odysseus-ui
-ExecStart=/home/YOURUSER/odysseus-ui/venv/bin/uvicorn app:app --port 8000 --host 0.0.0.0
+ExecStart=/home/YOURUSER/odysseus-ui/venv/bin/uvicorn app:app --port 7000 --host 0.0.0.0
 Restart=always
 RestartSec=3
 EnvironmentFile=-/home/YOURUSER/odysseus-ui/.env

package-lock.json

@@ -1,93 +1,22 @@
 {
-  "name": "odysseus-ui",
+  "name": "odysseus",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
-      "dependencies": {
-        "@anthropic-ai/sdk": "^0.98.0"
-      },
       "devDependencies": {
-        "@antithesishq/bombadil": "^0.3.2"
-      }
-    },
-    "node_modules/@anthropic-ai/sdk": {
-      "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",
-        "standardwebhooks": "^1.0.0"
-      },
-      "bin": {
-        "anthropic-ai-sdk": "bin/cli"
-      },
-      "peerDependencies": {
-        "zod": "^3.25.0 || ^4.0.0"
-      },
-      "peerDependenciesMeta": {
-        "zod": {
-          "optional": true
-        }
+        "@antithesishq/bombadil": "^0.6.1"
       }
     },
     "node_modules/@antithesishq/bombadil": {
-      "version": "0.3.2",
-      "resolved": "https://registry.npmjs.org/@antithesishq/bombadil/-/bombadil-0.3.2.tgz",
-      "integrity": "sha512-ATy1w9ZY5gbny1H8DFc7rxZitT7DLLLFDiGcRZe+8TQiUrV5tLO+IJGOVNNLp3RpCqjZqSsxGiKoQsx31ipV1g==",
+      "version": "0.6.1",
+      "resolved": "https://registry.npmjs.org/@antithesishq/bombadil/-/bombadil-0.6.1.tgz",
+      "integrity": "sha512-d1iufG3MI7gSMSiSmMeNdcMW+qR0yQXL2zdkVynC3n3DYgFJYlYXKUQzygmqU12m4RWlR5iOdQU1hsx5UT6+IA==",
       "dev": true,
-      "license": "MIT"
-    },
-    "node_modules/@babel/runtime": {
-      "version": "7.29.7",
-      "resolved": "https://registry.npmjs.org/@babel/runtime/-/runtime-7.29.7.tgz",
-      "integrity": "sha512-Nq8OhGWiZIZGV6hLHoyAKLLcJihP/xFeBMGJoUrxTX2psI8dCifzLhZISFb+VWS3wFMRDmCGw5R+dOySCqPLhw==",
       "license": "MIT",
-      "engines": {
-        "node": ">=6.9.0"
+      "bin": {
+        "bombadil": "bin/bombadil.js"
       }
-    },
-    "node_modules/@stablelib/base64": {
-      "version": "1.0.1",
-      "resolved": "https://registry.npmjs.org/@stablelib/base64/-/base64-1.0.1.tgz",
-      "integrity": "sha512-1bnPQqSxSuc3Ii6MhBysoWCg58j97aUjuCSZrGSmDxNqtytIi0k8utUenAwTZN4V5mXXYGsVUI9zeBqy+jBOSQ==",
-      "license": "MIT"
-    },
-    "node_modules/fast-sha256": {
-      "version": "1.3.0",
-      "resolved": "https://registry.npmjs.org/fast-sha256/-/fast-sha256-1.3.0.tgz",
-      "integrity": "sha512-n11RGP/lrWEFI/bWdygLxhI+pVeo1ZYIVwvvPkW7azl/rOy+F3HYRZ2K5zeE9mmkhQppyv9sQFx0JM9UabnpPQ==",
-      "license": "Unlicense"
-    },
-    "node_modules/json-schema-to-ts": {
-      "version": "3.1.1",
-      "resolved": "https://registry.npmjs.org/json-schema-to-ts/-/json-schema-to-ts-3.1.1.tgz",
-      "integrity": "sha512-+DWg8jCJG2TEnpy7kOm/7/AxaYoaRbjVB4LFZLySZlWn8exGs3A4OLJR966cVvU26N7X9TWxl+Jsw7dzAqKT6g==",
-      "license": "MIT",
-      "dependencies": {
-        "@babel/runtime": "^7.18.3",
-        "ts-algebra": "^2.0.0"
-      },
-      "engines": {
-        "node": ">=16"
-      }
-    },
-    "node_modules/standardwebhooks": {
-      "version": "1.0.0",
-      "resolved": "https://registry.npmjs.org/standardwebhooks/-/standardwebhooks-1.0.0.tgz",
-      "integrity": "sha512-BbHGOQK9olHPMvQNHWul6MYlrRTAOKn03rOe4A8O3CLWhNf4YHBqq2HJKKC+sfqpxiBY52pNeesD6jIiLDz8jg==",
-      "license": "MIT",
-      "dependencies": {
-        "@stablelib/base64": "^1.0.0",
-        "fast-sha256": "^1.3.0"
-      }
-    },
-    "node_modules/ts-algebra": {
-      "version": "2.0.0",
-      "resolved": "https://registry.npmjs.org/ts-algebra/-/ts-algebra-2.0.0.tgz",
-      "integrity": "sha512-FPAhNPFMrkwz76P7cdjdmiShwMynZYN6SgOujD1urY4oNm80Ou9oMdmbR45LotcKOXoy7wSmHkRFE6Mxbrhefw==",
-      "license": "MIT"
     }
   }
 }

package.json

@@ -1,8 +1,9 @@
 {
-  "devDependencies": {
-    "@antithesishq/bombadil": "^0.3.2"
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/odysseus-dev/odysseus.git"
   },
-  "dependencies": {
-    "@anthropic-ai/sdk": "^0.98.0"
+  "devDependencies": {
+    "@antithesishq/bombadil": "^0.6.1"
   }
 }

pyproject.toml

@@ -1,3 +1,22 @@
 [tool.pytest.ini_options]
 testpaths = ["tests"]
 asyncio_mode = "auto"
+# Test-taxonomy markers added at collection time by tests/conftest.py. The
+# stable area_* markers are declared here; the dynamic sub_<filename-token>
+# markers are registered before collection by pytest_configure in
+# tests/conftest.py, so unknown-mark warnings still flag genuine typos outside
+# the taxonomy. See tests/_taxonomy.py and tests/README.md.
+markers = [
+    "area_security: tests covering auth, owner-scope, SSRF, XSS, confinement, redaction",
+    "area_routes: tests covering HTTP route / API behavior",
+    "area_services: tests covering service-layer behavior (llm, cookbook, email, calendar, ...)",
+    "area_cli: tests covering CLI / script behavior",
+    "area_js: JavaScript / Node-backed tests",
+    "area_helpers: self-tests for the shared test helpers in tests/helpers/",
+    "area_unit: pure parser / utility tests that do not clearly belong elsewhere",
+    "area_uncategorized: tests not yet matched by the taxonomy (fallback)",
+    # Fast-lane marker (issue #3443). Opt-in and orthogonal to the area_*/sub_*
+    # taxonomy. The fast lane runs `not slow`; mark a test slow only with
+    # duration evidence (see tests/run_focus.py --durations and tests/README.md).
+    "slow: opt-in marker for known-slow tests; excluded by the fast lane (not slow)",
+]

requirements-optional.txt

@@ -4,10 +4,18 @@
 # Note: chromadb-client + fastembed moved to requirements.txt — RAG, semantic
 # memory, and tool selection are core paths, so they ship by default now.
 
+# Local speech-to-text (microphone -> text) via faster-whisper, for the
+# "local" STT provider. Runs on CPU out of the box (CTranslate2 backend, no
+# torch needed). Install if you want to dictate/transcribe with the mic
+# without sending audio to an external endpoint.
+# Optional extra: install `torch` too if you have a CUDA GPU and want
+# GPU-accelerated transcription — it's auto-detected, CPU is used otherwise.
+faster-whisper
+
 # DuckDuckGo as a search provider option.
 # Install if you want DDG in the search-provider dropdown.
 # Alternatives: SearXNG, Brave, Tavily, Serper, Google PSE.
-duckduckgo-search
+ddgs
 
 # PDF form-filling feature (fillable AcroForm detection, field extraction,
 # value/annotation/signature stamping, page rendering for the form overlay).
@@ -15,3 +23,14 @@ duckduckgo-search
 # network-served app — see ACKNOWLEDGMENTS.md. The MIT core (PDF *text*
 # extraction via pypdf) works without it; this only unlocks form-filling.
 PyMuPDF
+
+# Office / EPUB document text extraction (chat attachments + the personal-docs
+# RAG index). markitdown (MIT, Microsoft) converts .docx/.xlsx/.pptx/.xls/.epub
+# to Markdown — more token-efficient and model-legible than a raw dump. Optional
+# and lazy-imported via src/markitdown_runtime.py; without it those formats fall
+# back to a friendly "install to extract" banner and the core stays pure-MIT.
+# Extras pull mammoth/lxml/python-pptx/pandas/openpyxl/xlrd; the base also pulls
+# 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]==0.1.7

requirements.txt

@@ -3,8 +3,9 @@ uvicorn
 python-multipart
 python-dotenv
 httpx
-pydantic
-pydantic-settings
+httpcore>=1.0.9,<2.0
+pydantic>=2.13.4
+pydantic-settings>=2.14.2
 SQLAlchemy
 pypdf
 beautifulsoup4
@@ -21,17 +22,32 @@ youtube-transcript-api
 # Markdown rendering for research reports (src/visual_report.py).
 # Imported at module-top so it's a hard core dep, not optional.
 markdown
+# HTML sanitizer for rendered research reports (src/visual_report.py). Report
+# content is untrusted (LLM output over crawled pages) and report pages run
+# under a relaxed CSP, so the rendered HTML is allowlist-sanitized.
+nh3
 # Calendar .ics import/export (routes/calendar_routes.py).
 icalendar
+# Recurrence rule expansion for calendar events (routes/calendar_routes.py).
+# Imported directly as dateutil.rrule — make it explicit even though caldav
+# pulls it in transitively.
+python-dateutil
 # CalDAV sync (src/caldav_sync.py). Handles PROPFIND discovery + REPORT
 # fetch across Radicale, Nextcloud, Apple, Fastmail; we'd be reinventing
 # the protocol without it.
 caldav
 cryptography
 bcrypt
-mcp
+# Built-in servers use the v1 low-level Server decorator API. MCP SDK v2 is a
+# breaking rewrite, so keep fresh installs on the maintained v1 line until the
+# servers are migrated together.
+mcp<3
 pyotp
 qrcode[pil]
 croniter
 pytest
 pytest-asyncio
+# starlette.testclient prefers httpx2 since Starlette 1.2.0 and warns on every
+# TestClient import when only classic httpx is present. Runtime code keeps
+# using `httpx` above; this is test-client only.
+httpx2

routes/_validators.py

@@ -0,0 +1,31 @@
+import re
+
+from fastapi import HTTPException
+
+
+_REMOTE_HOST_RE = re.compile(
+    r"^(?:[A-Za-z0-9][A-Za-z0-9._-]*@)?[A-Za-z0-9][A-Za-z0-9._-]*$"
+)
+_SSH_PORT_RE = re.compile(r"^\d{1,5}$")
+
+
+def validate_remote_host(v: str | None) -> str | None:
+    if v is None or v == "":
+        return None
+    if not _REMOTE_HOST_RE.match(v):
+        raise HTTPException(
+            400,
+            "Invalid remote_host — must be host or user@host, no SSH option syntax",
+        )
+    return v
+
+
+def validate_ssh_port(v: str | None) -> str | None:
+    if v is None or v == "":
+        return None
+    if not _SSH_PORT_RE.fullmatch(str(v)):
+        raise HTTPException(400, "Invalid ssh_port")
+    port = int(v)
+    if port < 1 or port > 65535:
+        raise HTTPException(400, "Invalid ssh_port")
+    return str(port)

routes/admin_wipe/__init__.py

@@ -0,0 +1,5 @@
+"""Admin wipe route domain package (slice 2h, #4082/#4071).
+
+Contains admin_wipe_routes.py, migrated from the flat routes/ directory.
+Backward-compat shim at routes/admin_wipe_routes.py re-exports from here.
+"""

routes/admin_wipe/admin_wipe_routes.py

@@ -0,0 +1,176 @@
+"""Admin Danger Zone — per-category wipes.
+
+Each endpoint is admin-only and truncates exactly one domain so the
+user can selectively reset memory / skills / notes / etc. without
+nuking everything. The catch-all `chats` endpoint mirrors the
+existing /api/sessions/all so the Danger Zone speaks one URL pattern.
+
+URL shape: DELETE /api/admin/wipe/{kind}
+Kinds: chats, memory, skills, notes, tasks, documents, gallery, calendar.
+"""
+
+import json
+import logging
+import os
+import shutil
+from fastapi import APIRouter, HTTPException, Request
+
+from core.middleware import require_admin
+from core.database import (
+    SessionLocal,
+    Session as DbSession,
+    ChatMessage as DbChatMessage,
+    Memory,
+    Note,
+    ScheduledTask,
+    TaskRun,
+    Document,
+    DocumentVersion,
+    GalleryImage,
+    GalleryAlbum,
+    CalendarEvent,
+    CalendarCal,
+)
+from src.constants import DATA_DIR, SKILLS_DIR, SKILLS_FILE, GALLERY_DIR, GALLERY_UPLOADS_DIR
+
+logger = logging.getLogger(__name__)
+
+
+def _wipe_memory_files():
+    """Blank memory.json + drop the per-owner tidy-state sidecar so the
+    next audit doesn't try to diff against gone memories."""
+    for name in ("memory.json", "memory_tidy_state.json"):
+        p = os.path.join(DATA_DIR, name)
+        if not os.path.exists(p):
+            continue
+        try:
+            if name == "memory.json":
+                with open(p, "w", encoding="utf-8") as f:
+                    json.dump([], f)
+            else:
+                os.remove(p)
+        except OSError as e:
+            logger.warning(f"Could not reset {name}: {e}")
+
+
+def _rmtree_quiet(path: str):
+    """rmtree that doesn't crash if the path doesn't exist."""
+    if os.path.isdir(path):
+        try:
+            shutil.rmtree(path)
+        except OSError as e:
+            logger.warning(f"Could not remove {path}: {e}")
+
+
+def setup_admin_wipe_routes(session_manager):
+    """The session_manager is passed in so we can also clear its
+    in-memory cache when wiping chats — without it the DB is empty
+    but the next /api/sessions returns stale entries."""
+    router = APIRouter(prefix="/api/admin")
+
+    @router.delete("/wipe/{kind}")
+    def wipe(kind: str, request: Request):
+        require_admin(request)
+        kind = (kind or "").strip().lower()
+
+        db = SessionLocal()
+        try:
+            if kind == "chats":
+                count = db.query(DbSession).count()
+                db.query(DbChatMessage).delete()
+                db.query(DbSession).delete()
+                db.commit()
+                try:
+                    session_manager.sessions.clear()
+                except Exception:
+                    pass
+                return {"status": "deleted", "kind": kind, "count": count}
+
+            if kind == "memory":
+                count = db.query(Memory).count()
+                db.query(Memory).delete()
+                db.commit()
+                _wipe_memory_files()
+                # Drop the vector store too so semantic search doesn't
+                # return ghosts. Lazy import — chromadb may not be
+                # initialised in every deployment.
+                try:
+                    from src.memory_vector import get_memory_vector_store
+                    mv = get_memory_vector_store()
+                    if mv and hasattr(mv, "clear"):
+                        mv.clear()
+                except Exception as e:
+                    logger.info(f"Memory vector clear skipped: {e}")
+                return {"status": "deleted", "kind": kind, "count": count}
+
+            if kind == "skills":
+                # Skills live as SKILL.md files under data/skills/. Drop
+                # the entire directory; the SkillsManager re-creates the
+                # tree on next write.
+                skills_dir = SKILLS_DIR
+                count = 0
+                if os.path.isdir(skills_dir):
+                    # Count SKILL.md files for the response — quick walk.
+                    for _, _, files in os.walk(skills_dir):
+                        count += sum(1 for f in files if f == "SKILL.md")
+                    _rmtree_quiet(skills_dir)
+                # Legacy fallback file
+                legacy = SKILLS_FILE
+                if os.path.exists(legacy):
+                    try:
+                        os.remove(legacy)
+                    except OSError:
+                        pass
+                return {"status": "deleted", "kind": kind, "count": count}
+
+            if kind == "notes":
+                count = db.query(Note).count()
+                db.query(Note).delete()
+                db.commit()
+                return {"status": "deleted", "kind": kind, "count": count}
+
+            if kind == "tasks":
+                # TaskRun rows reference tasks via FK — clear them first.
+                db.query(TaskRun).delete()
+                count = db.query(ScheduledTask).count()
+                db.query(ScheduledTask).delete()
+                db.commit()
+                return {"status": "deleted", "kind": kind, "count": count}
+
+            if kind == "documents":
+                # DocumentVersion FKs Document — clear children first.
+                db.query(DocumentVersion).delete()
+                count = db.query(Document).count()
+                db.query(Document).delete()
+                db.commit()
+                return {"status": "deleted", "kind": kind, "count": count}
+
+            if kind == "gallery":
+                count = db.query(GalleryImage).count() + db.query(GalleryAlbum).count()
+                db.query(GalleryImage).delete()
+                db.query(GalleryAlbum).delete()
+                db.commit()
+                # Also drop the upload dir so disk doesn't keep orphans.
+                _rmtree_quiet(GALLERY_DIR)
+                _rmtree_quiet(GALLERY_UPLOADS_DIR)
+                return {"status": "deleted", "kind": kind, "count": count}
+
+            if kind == "calendar":
+                # Events FK calendars — clear children first, then both.
+                db.query(CalendarEvent).delete()
+                count = db.query(CalendarCal).count()
+                db.query(CalendarCal).delete()
+                db.commit()
+                return {"status": "deleted", "kind": kind, "count": count}
+
+            raise HTTPException(400, f"Unknown wipe kind: {kind!r}")
+        except HTTPException:
+            raise
+        except Exception as e:
+            db.rollback()
+            logger.exception(f"Wipe {kind} failed")
+            raise HTTPException(500, f"Wipe {kind} failed: {e}")
+        finally:
+            db.close()
+
+    return router

routes/admin_wipe_routes.py

@@ -1,174 +1,17 @@
-"""Admin Danger Zone — per-category wipes.
+"""Backward-compat shim — canonical location is routes/admin_wipe/admin_wipe_routes.py.
 
-Each endpoint is admin-only and truncates exactly one domain so the
-user can selectively reset memory / skills / notes / etc. without
-nuking everything. The catch-all `chats` endpoint mirrors the
-existing /api/sessions/all so the Danger Zone speaks one URL pattern.
-
-URL shape: DELETE /api/admin/wipe/{kind}
-Kinds: chats, memory, skills, notes, tasks, documents, gallery, calendar.
+This module is replaced in ``sys.modules`` by the canonical module object so
+that ``import routes.admin_wipe_routes``, ``from routes.admin_wipe_routes
+import X``, ``importlib.import_module("routes.admin_wipe_routes")``, and the
+``import ... as admin_wipe_routes`` + ``monkeypatch.setattr(admin_wipe_routes,
+"SessionLocal", ...)`` / ``"require_admin"`` pattern used by
+test_admin_wipe_gallery.py all operate on the *same* object the application
+actually uses. Keeps existing import paths working after slice 2h
+(#4082/#4071).
 """
 
-import json
-import logging
-import os
-import shutil
-from fastapi import APIRouter, HTTPException, Request
+import sys as _sys
 
-from core.middleware import require_admin
-from core.database import (
-    SessionLocal,
-    Session as DbSession,
-    ChatMessage as DbChatMessage,
-    Memory,
-    Note,
-    ScheduledTask,
-    TaskRun,
-    Document,
-    DocumentVersion,
-    GalleryImage,
-    CalendarEvent,
-    CalendarCal,
-)
-from src.constants import DATA_DIR
+from routes.admin_wipe import admin_wipe_routes as _canonical  # noqa: F401
 
-logger = logging.getLogger(__name__)
-
-
-def _wipe_memory_files():
-    """Blank memory.json + drop the per-owner tidy-state sidecar so the
-    next audit doesn't try to diff against gone memories."""
-    for name in ("memory.json", "memory_tidy_state.json"):
-        p = os.path.join(DATA_DIR, name)
-        if not os.path.exists(p):
-            continue
-        try:
-            if name == "memory.json":
-                with open(p, "w") as f:
-                    json.dump([], f)
-            else:
-                os.remove(p)
-        except OSError as e:
-            logger.warning(f"Could not reset {name}: {e}")
-
-
-def _rmtree_quiet(path: str):
-    """rmtree that doesn't crash if the path doesn't exist."""
-    if os.path.isdir(path):
-        try:
-            shutil.rmtree(path)
-        except OSError as e:
-            logger.warning(f"Could not remove {path}: {e}")
-
-
-def setup_admin_wipe_routes(session_manager):
-    """The session_manager is passed in so we can also clear its
-    in-memory cache when wiping chats — without it the DB is empty
-    but the next /api/sessions returns stale entries."""
-    router = APIRouter(prefix="/api/admin")
-
-    @router.delete("/wipe/{kind}")
-    def wipe(kind: str, request: Request):
-        require_admin(request)
-        kind = (kind or "").strip().lower()
-
-        db = SessionLocal()
-        try:
-            if kind == "chats":
-                count = db.query(DbSession).count()
-                db.query(DbChatMessage).delete()
-                db.query(DbSession).delete()
-                db.commit()
-                try:
-                    session_manager.sessions.clear()
-                except Exception:
-                    pass
-                return {"status": "deleted", "kind": kind, "count": count}
-
-            if kind == "memory":
-                count = db.query(Memory).count()
-                db.query(Memory).delete()
-                db.commit()
-                _wipe_memory_files()
-                # Drop the vector store too so semantic search doesn't
-                # return ghosts. Lazy import — chromadb may not be
-                # initialised in every deployment.
-                try:
-                    from src.memory_vector import get_memory_vector_store
-                    mv = get_memory_vector_store()
-                    if mv and hasattr(mv, "clear"):
-                        mv.clear()
-                except Exception as e:
-                    logger.info(f"Memory vector clear skipped: {e}")
-                return {"status": "deleted", "kind": kind, "count": count}
-
-            if kind == "skills":
-                # Skills live as SKILL.md files under data/skills/. Drop
-                # the entire directory; the SkillsManager re-creates the
-                # tree on next write.
-                skills_dir = os.path.join(DATA_DIR, "skills")
-                count = 0
-                if os.path.isdir(skills_dir):
-                    # Count SKILL.md files for the response — quick walk.
-                    for _, _, files in os.walk(skills_dir):
-                        count += sum(1 for f in files if f == "SKILL.md")
-                    _rmtree_quiet(skills_dir)
-                # Legacy fallback file
-                legacy = os.path.join(DATA_DIR, "skills.json")
-                if os.path.exists(legacy):
-                    try:
-                        os.remove(legacy)
-                    except OSError:
-                        pass
-                return {"status": "deleted", "kind": kind, "count": count}
-
-            if kind == "notes":
-                count = db.query(Note).count()
-                db.query(Note).delete()
-                db.commit()
-                return {"status": "deleted", "kind": kind, "count": count}
-
-            if kind == "tasks":
-                # TaskRun rows reference tasks via FK — clear them first.
-                db.query(TaskRun).delete()
-                count = db.query(ScheduledTask).count()
-                db.query(ScheduledTask).delete()
-                db.commit()
-                return {"status": "deleted", "kind": kind, "count": count}
-
-            if kind == "documents":
-                # DocumentVersion FKs Document — clear children first.
-                db.query(DocumentVersion).delete()
-                count = db.query(Document).count()
-                db.query(Document).delete()
-                db.commit()
-                return {"status": "deleted", "kind": kind, "count": count}
-
-            if kind == "gallery":
-                count = db.query(GalleryImage).count()
-                db.query(GalleryImage).delete()
-                db.commit()
-                # Also drop the upload dir so disk doesn't keep orphans.
-                _rmtree_quiet(os.path.join(DATA_DIR, "gallery"))
-                _rmtree_quiet(os.path.join(DATA_DIR, "gallery_uploads"))
-                return {"status": "deleted", "kind": kind, "count": count}
-
-            if kind == "calendar":
-                # Events FK calendars — clear children first, then both.
-                db.query(CalendarEvent).delete()
-                count = db.query(CalendarCal).count()
-                db.query(CalendarCal).delete()
-                db.commit()
-                return {"status": "deleted", "kind": kind, "count": count}
-
-            raise HTTPException(400, f"Unknown wipe kind: {kind!r}")
-        except HTTPException:
-            raise
-        except Exception as e:
-            db.rollback()
-            logger.exception(f"Wipe {kind} failed")
-            raise HTTPException(500, f"Wipe {kind} failed: {e}")
-        finally:
-            db.close()
-
-    return router
+_sys.modules[__name__] = _canonical

routes/api_token_routes.py

@@ -12,6 +12,65 @@ from src.auth_helpers import get_current_user
 
 MAX_NAME_LEN = 100
 DEFAULT_SCOPES = "chat"
+ALLOWED_SCOPES = {
+    "chat",
+    "todos:read",
+    "todos:write",
+    "documents:read",
+    "documents:write",
+    "email:read",
+    "email:draft",
+    "email:send",
+    "calendar:read",
+    "calendar:write",
+    "memory:read",
+    "memory:write",
+    "cookbook:read",
+    "cookbook:launch",
+}
+TOKEN_PROFILES = {
+    "chat": ["chat"],
+    "codex_todos": ["todos:read", "todos:write"],
+    "codex_documents": ["documents:read", "documents:write"],
+    "codex_email_drafts": ["email:read", "email:draft", "documents:read", "documents:write"],
+}
+
+
+def _normalize_scopes(scopes: str | list[str] | None = None, profile: str | None = None) -> list[str]:
+    profile = profile if isinstance(profile, str) else None
+    profile_key = (profile or "").strip()
+    if profile_key:
+        if profile_key not in TOKEN_PROFILES:
+            raise HTTPException(400, "Unknown token profile")
+        requested = list(TOKEN_PROFILES[profile_key])
+    elif isinstance(scopes, list):
+        requested = [str(s).strip() for s in scopes if str(s).strip()]
+    elif isinstance(scopes, str) and scopes:
+        requested = [s.strip() for s in scopes.replace(" ", ",").split(",") if s.strip()]
+    else:
+        requested = [DEFAULT_SCOPES]
+
+    normalized = []
+    for scope in requested:
+        if scope not in ALLOWED_SCOPES:
+            raise HTTPException(400, f"Unknown token scope: {scope}")
+        if scope not in normalized:
+            normalized.append(scope)
+
+    def ensure_before(write_scope: str, read_scope: str):
+        if write_scope not in normalized or read_scope in normalized:
+            return
+        idx = normalized.index(write_scope)
+        normalized.insert(idx, read_scope)
+
+    ensure_before("todos:write", "todos:read")
+    ensure_before("documents:write", "documents:read")
+    ensure_before("calendar:write", "calendar:read")
+    ensure_before("memory:write", "memory:read")
+    ensure_before("email:draft", "email:read")
+    ensure_before("cookbook:launch", "cookbook:read")
+
+    return normalized or [DEFAULT_SCOPES]
 
 
 def setup_api_token_routes() -> APIRouter:
@@ -45,13 +104,28 @@ def setup_api_token_routes() -> APIRouter:
         except Exception:
             pass
 
+    @router.get("/tokens/profiles")
+    def token_profiles(request: Request):
+        require_admin(request)
+        return {
+            "profiles": TOKEN_PROFILES,
+            "allowed_scopes": sorted(ALLOWED_SCOPES),
+        }
+
     @router.post("/tokens")
-    def create_token(request: Request, name: str = Form("")):
+    def create_token(
+        request: Request,
+        name: str = Form(""),
+        scopes: str = Form(None),
+        profile: str = Form(None),
+    ):
         require_admin(request)
         name = name.strip()[:MAX_NAME_LEN]
         if not name:
             raise HTTPException(400, "Token name is required")
         owner = get_current_user(request)
+        scope_list = _normalize_scopes(scopes, profile)
+        scopes_value = ",".join(scope_list)
 
         raw_token = "ody_" + secrets.token_urlsafe(32)
         token_hash = bcrypt.hashpw(raw_token.encode(), bcrypt.gensalt()).decode()
@@ -64,7 +138,7 @@ def setup_api_token_routes() -> APIRouter:
                 name=name,
                 token_hash=token_hash,
                 token_prefix=raw_token[:8],
-                scopes=DEFAULT_SCOPES,
+                scopes=scopes_value,
                 is_active=True,
             ))
         _invalidate_cache(request)
@@ -75,16 +149,60 @@ def setup_api_token_routes() -> APIRouter:
             "owner": owner,
             "token": raw_token,
             "token_prefix": raw_token[:8],
-            "scopes": DEFAULT_SCOPES.split(","),
+            "scopes": scope_list,
         }
 
+    @router.patch("/tokens/{token_id}")
+    async def update_token(request: Request, token_id: str):
+        require_admin(request)
+        current_user = get_current_user(request)
+        try:
+            payload = await request.json()
+        except Exception:
+            payload = {}
+        if not isinstance(payload, dict):
+            payload = {}
+        with get_db_session() as db:
+            token = db.query(ApiToken).filter(ApiToken.id == token_id).first()
+            if not token:
+                raise HTTPException(404, "Token not found")
+            if current_user and token.owner != current_user:
+                raise HTTPException(403, "Not your token")
+            if isinstance(payload.get("name"), str) and payload["name"].strip():
+                token.name = payload["name"].strip()[:MAX_NAME_LEN]
+            # Only touch scopes when the caller actually sent them. A partial
+            # update such as a rename ({"name": ...} with no "scopes" key) must
+            # not silently reset the token to the default scope — that dropped
+            # every previously granted scope.
+            if "scopes" in payload:
+                token.scopes = ",".join(_normalize_scopes(payload.get("scopes")))
+            db.add(token)
+            current_scopes = [
+                s.strip()
+                for s in (getattr(token, "scopes", "") or DEFAULT_SCOPES).split(",")
+                if s.strip()
+            ]
+            response = {
+                "id": token_id,
+                "name": getattr(token, "name", ""),
+                "owner": getattr(token, "owner", None),
+                "token_prefix": getattr(token, "token_prefix", ""),
+                "scopes": current_scopes,
+            }
+        _invalidate_cache(request)
+        return response
+
     @router.delete("/tokens/{token_id}")
     def delete_token(request: Request, token_id: str):
         require_admin(request)
+        current_user = get_current_user(request)
         with get_db_session() as db:
-            deleted = db.query(ApiToken).filter(ApiToken.id == token_id).delete()
-            if not deleted:
+            token = db.query(ApiToken).filter(ApiToken.id == token_id).first()
+            if not token:
                 raise HTTPException(404, "Token not found")
+            if current_user and token.owner != current_user:
+                raise HTTPException(403, "Not your token")
+            db.delete(token)
         _invalidate_cache(request)
         return {"status": "deleted"}