diff --git a/.dockerignore b/.dockerignore index 80d80a1..25aeefe 100644 --- a/.dockerignore +++ b/.dockerignore @@ -10,6 +10,16 @@ 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/ diff --git a/.env.example b/.env.example index f282880..e96dd15 100644 --- a/.env.example +++ b/.env.example @@ -56,6 +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 # ============================================================ @@ -112,6 +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 @@ -144,6 +154,41 @@ SEARXNG_INSTANCE=http://localhost:8080 # 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) + +# ============================================================ +# 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) # ============================================================ @@ -165,3 +210,10 @@ SEARXNG_INSTANCE=http://localhost:8080 # These overlays only expose the GPU devices. The slim Odysseus image # still needs CUDA/ROCm userspace via Cookbook -> Dependencies (vLLM, # llama-cpp-python, etc.) before models can actually serve on GPU. + +# ============================================================ +# Storage Paths (Docker Compose) +# ============================================================ + +# APP_DATA_DIR=./data +# APP_LOGS_DIR=./logs diff --git a/.github/CODEOWNERS b/.github/CODEOWNERS new file mode 100644 index 0000000..fc7545a --- /dev/null +++ b/.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. diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.yml index 67d84b1..64f2d7d 100644 --- a/.github/ISSUE_TEMPLATE/bug_report.yml +++ b/.github/ISSUE_TEMPLATE/bug_report.yml @@ -23,7 +23,7 @@ body: required: true - label: This is **not** a security vulnerability. (Vulnerabilities go to [GitHub Security Advisories](https://github.com/pewdiepie-archdaemon/odysseus/security/advisories/new) — see [SECURITY.md](https://github.com/pewdiepie-archdaemon/odysseus/blob/main/SECURITY.md).) required: true - - label: I am running the latest code from `main`. + - 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 diff --git a/.github/dependabot.yml b/.github/dependabot.yml new file mode 100644 index 0000000..e1e0bf1 --- /dev/null +++ b/.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 diff --git a/.github/pull_request_review_template.md b/.github/pull_request_review_template.md new file mode 100644 index 0000000..7251385 --- /dev/null +++ b/.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 + +**![P2 Badge](https://img.shields.io/badge/P2-yellow?style=flat) 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. diff --git a/.github/scripts/check-pr-description.js b/.github/scripts/check-pr-description.js index 2a06c2b..f5dabea 100644 --- a/.github/scripts/check-pr-description.js +++ b/.github/scripts/check-pr-description.js @@ -103,14 +103,21 @@ module.exports = async ({ github, context, core }) => { async function swapLabel(num, add, remove) { if (await labelExists(add)) { - await github.rest.issues.addLabels({ owner, repo, issue_number: num, labels: [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) throw e; + if (e.status !== 404 && e.status !== 410 && e.status !== 403) throw e; } } diff --git a/.github/scripts/focused_test_guidance.py b/.github/scripts/focused_test_guidance.py new file mode 100644 index 0000000..1426d35 --- /dev/null +++ b/.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()) diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 3978ef5..f7d3659 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -15,12 +15,68 @@ concurrency: 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" > "$report_file"; then + report_unavailable "The focused test guidance helper could not produce a report." + fi + + publish_report + python-syntax: name: Python syntax (compileall) runs-on: ubuntu-latest steps: - - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4 - - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5 + - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 + with: + persist-credentials: false + - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 with: python-version: "3.11" # Byte-compile sources — catches syntax errors without installing deps. @@ -30,8 +86,10 @@ jobs: name: JS syntax (node --check) runs-on: ubuntu-latest steps: - - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4 - - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4 + - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 + with: + persist-credentials: false + - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0 with: node-version: "20" # Syntax-check our own JS (skip vendored libs in static/lib). @@ -50,11 +108,41 @@ jobs: # ROADMAP "fresh install smoke tests" item; make this required once green. continue-on-error: true steps: - - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4 - - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5 + - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 + with: + fetch-depth: 0 + persist-credentials: false + + # Detect whether this PR only touches documentation files. + # If so, skip the expensive pytest run while still reporting a passing check. + - name: Check for docs-only changes + id: docs-check + run: | + if [ "${{ 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' diff --git a/.github/workflows/container-scan.yml b/.github/workflows/container-scan.yml new file mode 100644 index 0000000..f1c4b5b --- /dev/null +++ b/.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 diff --git a/.github/workflows/container-trivy.yml b/.github/workflows/container-trivy.yml new file mode 100644 index 0000000..2a482f0 --- /dev/null +++ b/.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 diff --git a/.github/workflows/dependency-review.yml b/.github/workflows/dependency-review.yml new file mode 100644 index 0000000..0a587de --- /dev/null +++ b/.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 diff --git a/.github/workflows/docker-publish.yml b/.github/workflows/docker-publish.yml new file mode 100644 index 0000000..d52c0c4 --- /dev/null +++ b/.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. (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//. + +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 }} diff --git a/.github/workflows/issue-description-check.yml b/.github/workflows/issue-description-check.yml index 5dc3fdf..52e9ddd 100644 --- a/.github/workflows/issue-description-check.yml +++ b/.github/workflows/issue-description-check.yml @@ -14,10 +14,11 @@ jobs: # Skip bots (Dependabot, release-drafter, etc.) if: ${{ github.event.issue.user.type != 'Bot' }} steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 with: sparse-checkout: .github/scripts + persist-credentials: false - - uses: actions/github-script@v7 + - uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 with: script: return require('./.github/scripts/check-issue-description.js')({github, context, core}) diff --git a/.github/workflows/pr-description-check.yml b/.github/workflows/pr-description-check.yml index 9ac05b3..53f0b5f 100644 --- a/.github/workflows/pr-description-check.yml +++ b/.github/workflows/pr-description-check.yml @@ -1,28 +1,109 @@ -name: ci / PR description check +name: ci / PR checks on: - pull_request_target: - types: [opened, edited, synchronize, reopened] + # 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] -# pull_request_target runs in the base-repo context (has secrets). -# The checkout below pins to the base branch so no fork code is executed. -# The script only reads context.payload and calls the GitHub API. -permissions: - issues: write - pull-requests: write +# 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 - # Skip bots — they open PRs programmatically and have their own process. + 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@v4 + - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 with: ref: ${{ github.base_ref }} sparse-checkout: .github/scripts + persist-credentials: false - - uses: actions/github-script@v7 + - 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(() => {}); + } + } diff --git a/.github/workflows/secret-scan.yml b/.github/workflows/secret-scan.yml new file mode 100644 index 0000000..0251220 --- /dev/null +++ b/.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 }}-${{ github.ref }} + cancel-in-progress: true + +jobs: + gitleaks: + name: gitleaks + runs-on: ubuntu-latest + permissions: + contents: read + steps: + - name: Checkout repository + uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 + with: + # Full history so a secret committed in an earlier commit (and later + # deleted) is still caught -- deletion does not remove it from Git. + fetch-depth: 0 + persist-credentials: false + + # Pinned version + checksum so a tampered release binary cannot run here. + # Bump VERSION/SHA256 together; the checksum comes from the matching + # gitleaks__checksums.txt on the GitHub release. + - name: Run gitleaks (pinned, checksum-verified) + env: + GITLEAKS_VERSION: 8.30.1 + GITLEAKS_SHA256: 551f6fc83ea457d62a0d98237cbad105af8d557003051f41f3e7ca7b3f2470eb + run: | + set -euo pipefail + TARBALL="gitleaks_${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 . diff --git a/.github/workflows/workflow-security.yml b/.github/workflows/workflow-security.yml new file mode 100644 index 0000000..ee34533 --- /dev/null +++ b/.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/ diff --git a/.gitignore b/.gitignore index c48f6cd..77c364b 100644 --- a/.gitignore +++ b/.gitignore @@ -14,6 +14,15 @@ venv/ .env .env.bak.* !.env.example +# Local uv lockfile (optional, per-platform — see "Faster installs with uv" in README) +requirements.lock + +# SOPS workflow — encrypted `secrets.env` is intentionally committable, +# but every variant (plaintext, manual decrypt copy, editor backup) +# must stay out of git. Mirrored in .dockerignore so the same artifacts +# also cannot enter image build layers. +secrets.env.* +!secrets.env.example # Data — all user data stays local data/ @@ -61,6 +70,9 @@ 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 @@ -89,3 +101,4 @@ docs/windows-port/ compound.config.json *.error.log _scratch/ +/odysseus/ diff --git a/ACKNOWLEDGMENTS.md b/ACKNOWLEDGMENTS.md index fdf55c4..94092c6 100644 --- a/ACKNOWLEDGMENTS.md +++ b/ACKNOWLEDGMENTS.md @@ -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 diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 2302c41..efb38ed 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -37,7 +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. @@ -94,6 +94,18 @@ Before submitting any change that affects what the app looks like — buttons, i 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: diff --git a/Dockerfile b/Dockerfile index ad273ce..9b30556 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,4 +1,15 @@ -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, @@ -18,8 +29,44 @@ RUN apt-get update && apt-get install -y --no-install-recommends \ 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=27.5.1 +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-${DOCKER_CLI_VERSION}.tgz" \ + -o /tmp/docker.tgz \ + && tar -xzf /tmp/docker.tgz -C /tmp \ + && install -m 0755 /tmp/docker/docker /usr/local/bin/docker \ + && rm -rf /tmp/docker /tmp/docker.tgz + WORKDIR /app # Install Python deps first (layer cache). Optional extras (PyMuPDF AGPL, etc.) @@ -29,6 +76,20 @@ COPY requirements.txt requirements-optional.txt ./ RUN pip install --no-cache-dir -r requirements.txt \ && if [ "$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 . . diff --git a/LICENSE b/LICENSE index 7087e2d..0c97efd 100644 --- a/LICENSE +++ b/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. -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. + + + Copyright (C) + + 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 . + +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 . diff --git a/Odysseus.spec b/Odysseus.spec new file mode 100644 index 0000000..547460c --- /dev/null +++ b/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', +) diff --git a/README.md b/README.md index d58d617..e69ded8 100644 --- a/README.md +++ b/README.md @@ -1,75 +1,40 @@ -# Odysseus +

+ Odysseus +

-``` -─────────────────────────────────────────────── - ⊹ ࣪ ˖ ૮( ˶ᵔ ᵕ ᵔ˶ )っ Odysseus vers. 1.0 -─────────────────────────────────────────────── -``` +

+ A self-hosted AI workspace for chat, agents, research, documents, email, notes, calendar, and local model workflows. +

-![Odysseus](docs/odysseus.jpg) +

+ Quick Start · + Setup Guide · + Contributing · + Roadmap +

-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. +

+ Packaging status +

-## Features - - **Chat** -- chat with any local model or API; adding them is super simple.
　vLLM · llama.cpp · Ollama · OpenRouter · OpenAI · GitHub Copilot - - **Agent** -- hand it tools and let it run the whole task itself.
　built on [opencode](https://github.com/anomalyco/opencode) · MCP · web · files · shell · skills · memory - - **Cookbook** -- Scans your hardware, recommends models, click to download and serve.. easy!
　built on [llmfit](https://github.com/AlexsJones/llmfit) · VRAM-aware · GGUF / FP8 / AWQ · fit scoring · vLLM / llama.cpp serving - - **Deep Research** -- multi-step runs that gather, read, and synthesize sources into a nice visual report.
　adapted from [Tongyi DeepResearch](https://github.com/Alibaba-NLP/DeepResearch) - - **Compare** -- a fun tool to compare models side by side. Test completely blind, no bias!
　multi-model · blind test · synthesis - - **Documents** -- YOU write the text, AI is there to assist, not the opposite.
　multi-tab editor · markdown · HTML · CSV · syntax highlighting · AI edits · suggestions - - **Memory / Skills** -- Persistent memory and skills, your agent evolves over time as it better understands you and your tasks!
　ChromaDB · fastembed (ONNX) · vector + keyword retrieval · import/export - - **Email** -- IMAP/SMTP inbox with AI triage built in: urgency reminders, auto-tag, auto-summary, auto-reply drafts, auto-spam.
　IMAP · SMTP · per-account routing · CalDAV-aware - - **Notes & Tasks** -- Quick notes with reminders, a todo list, and scheduled tasks the agent can act on.
　note pings · checklist · cron-style tasks · ntfy / browser / email channels - - **Calendar** -- Local-first calendar with CalDAV sync to Radicale / Nextcloud / Apple / Fastmail.
　CalDAV pull · .ics import/export · per-calendar colors · agent-aware - - **Works on mobile** -- looks and runs great on your phone, not just desktop.
　responsive · installable (PWA) · touch gestures - - **Extras** -- more to explore, happy if you give it a go!
　image editor · theme editor · file uploads (vision + PDF) · web search · presets · sessions · 2FA +

+ Odysseus interface +

-## Demo -A full, hover-to-play tour lives on the landing page (`docs/index.html`). - -
-Screenshots / clips - -### 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, 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. +> `dev` is the default branch and gets the newest changes first. Use [`main`](https://github.com/pewdiepie-archdaemon/odysseus/tree/main) if you want the more curated branch. -On first setup, Odysseus creates an admin account (`admin` unless -`ODYSSEUS_ADMIN_USER` is set) and prints a temporary password in the terminal. -For Docker installs, the same line is in `docker compose logs odysseus`. -Use that for the first login, then change it in **Settings**. - -Contributing? See [CONTRIBUTING.md](CONTRIBUTING.md) for setup, testing, and -pull request guidelines. - -### Docker (recommended) ```bash git clone https://github.com/pewdiepie-archdaemon/odysseus.git cd odysseus -cp .env.example .env # optional, but recommended for explicit defaults +cp .env.example .env 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. +Open `http://localhost:7000` when the containers are healthy. The first admin password is printed in `docker compose logs odysseus`. ### Dockge / Gitea Registry Image Use this when you want Dockge to pull the prebuilt image from the Gitea @@ -214,356 +179,30 @@ PUID=1000 PGID=1000 ``` -### Native Linux / macOS -```bash -git clone https://github.com/pewdiepie-archdaemon/odysseus.git -cd odysseus -python3 -m venv venv -source venv/bin/activate -pip install -r requirements.txt -python setup.py -python -m uvicorn app:app --host 127.0.0.1 --port 7000 -``` -Requirements: Python 3.11+. Cookbook also needs `tmux` for background model -downloads and serves. The app itself is lightweight; local model serving is the -heavy part and depends on the model, runtime, GPU, and VRAM, so small hosts can -connect to API or remote model servers instead. Use `--host 0.0.0.0` only when you intentionally want LAN/reverse-proxy access. +Native installs, GPU notes, Windows/macOS instructions, HTTPS, and configuration live in the [setup guide](docs/setup.md). -### Apple Silicon -Docker on macOS cannot use the Metal GPU. For GPU-accelerated Cookbook on an -M-series Mac, run Odysseus natively: +## Features -```bash -git clone https://github.com/pewdiepie-archdaemon/odysseus.git -cd odysseus -./start-macos.sh -``` +- **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. -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: +## Demo -```bash -ODYSSEUS_HOST=0.0.0.0 ./start-macos.sh -# then open http://: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 -``` - -
-Cookbook, GPU, Ollama, and troubleshooting notes - -**Docker bundled services.** Compose starts Odysseus, ChromaDB, SearXNG, and -ntfy. Odysseus and the bundled service ports bind to `127.0.0.1` by default, so -they are reachable from the host but not exposed to your LAN/public internet -unless you opt in. - -**Cookbook storage in Docker.** Downloads live in `./data/huggingface` -(`~/.cache/huggingface` in the container). Cookbook-installed Python CLIs and -serve engines live in `./data/local` (`~/.local` in the container), so they -survive container recreation. - -**Remote servers.** In **Cookbook -> Settings -> Servers**, generate the -Odysseus SSH key and add the public key to the remote server's -`~/.ssh/authorized_keys`. From the host you can also run: - -```bash -ssh-copy-id -i data/ssh/id_ed25519.pub user@server -``` - -**Docker GPU overlays.** CPU-only users can skip this section. Cookbook can -only detect GPUs that Docker exposes to the container — if the host runtime or -device passthrough is not configured, Cookbook sees the iGPU, another card, or -CPU instead of your intended GPU. - -For NVIDIA, `scripts/check-docker-gpu.sh` diagnoses GPU passthrough and can -optionally install the host runtime or update `.env`. - -```bash -# Read-only diagnostic (default — installs nothing, never edits .env): -scripts/check-docker-gpu.sh - -# Print OS-specific install commands without running them: -scripts/check-docker-gpu.sh --print-install-commands - -# Install NVIDIA Container Toolkit on Ubuntu/Debian (requires sudo): -scripts/check-docker-gpu.sh --install-nvidia-toolkit - -# Write COMPOSE_FILE to .env (only when GPU passthrough is confirmed working): -scripts/check-docker-gpu.sh --enable-nvidia-overlay - -# Full assisted setup — install toolkit, then enable overlay if passthrough works: -scripts/check-docker-gpu.sh --install-nvidia-toolkit --enable-nvidia-overlay -``` - -Safety notes: -- The app never installs host GPU runtime automatically. -- The app never edits `.env` automatically. -- `.env` is only modified when `--enable-nvidia-overlay` is explicitly passed, - and only after GPU passthrough succeeds. `--yes` skips prompts but does not - bypass the passthrough gate. -- `.env.bak.*` backups created by `--enable-nvidia-overlay` are ignored by - Git and the Docker build context. - -To enable manually without the script, add this to `.env`: - -```bash -COMPOSE_FILE=docker-compose.yml:docker/gpu.nvidia.yml -``` - -**AMD / ROCm.** AMD setup is read-only diagnostic plus manual `.env` edit. Run: - -```bash -scripts/check-docker-amd-gpu.sh -``` - -Then add the reported values to `.env`, replacing `RENDER_GID` with your host's -numeric render group id: - -```bash -COMPOSE_FILE=docker-compose.yml:docker/gpu.amd.yml -RENDER_GID=989 -``` - -For NVIDIA/AMD GPU support, also read the comments in the selected overlay file: docker/gpu.nvidia.yml or docker/gpu.amd.yml. - -**Stack-management UIs (Portainer, Coolify, Dockhand, etc.).** These tools -often accept only a single Compose file and do not reliably honor `COMPOSE_FILE` -or multiple `-f` overlays. CLI users should keep using the `COMPOSE_FILE` -overlay workflow above. For stack UIs, point the stack at one of the standalone -files instead, which bundle the base stack plus the GPU settings: - -- `docker-compose.gpu-nvidia.yml` — still requires the NVIDIA Container Toolkit - on the host. -- `docker-compose.gpu-amd.yml` — still requires host ROCm/kfd/DRI setup, the - `video`/`render` group membership, and `RENDER_GID` when needed. - -The base `docker-compose.yml` plus the `docker/gpu.*.yml` overlays remain the -source of truth; the standalone files mirror them for single-file deployments. - -Verify after enabling either overlay: - -```bash -docker compose exec odysseus nvidia-smi -L # NVIDIA -docker compose exec odysseus sh -lc 'test -e /dev/kfd && test -d /dev/dri && ls -l /dev/kfd /dev/dri/renderD*' # AMD -``` - -> **GPU passthrough ≠ llama.cpp CUDA.** `nvidia-smi` passing inside the -> container confirms Docker GPU access, but llama.cpp also needs `cudart` and -> the CUDA Toolkit at runtime. If Cookbook logs show `Unable to find cudart -> library`, `Could NOT find CUDAToolkit`, `CUDA Toolkit not found`, or -> tensors/layers assigned to CPU, that is a Cookbook/llama.cpp build issue — -> not a Docker passthrough failure. Re-install the serve engine via -> **Cookbook → Dependencies** to get a CUDA-enabled build. -> -> The same split applies to AMD/ROCm: seeing `/dev/kfd` and `/dev/dri` inside -> the container confirms device passthrough, not ROCm userspace or a -> ROCm-enabled vLLM/llama.cpp build. `rocm-smi` and `rocminfo` are not expected -> inside the slim Odysseus image. - -**Ollama with Docker.** If Ollama runs on the host, add this endpoint in -Settings: - -```text -http://host.docker.internal:11434/v1 -``` - -Ollama must listen outside its own loopback interface: - -```bash -OLLAMA_HOST=0.0.0.0:11434 ollama serve -``` - -This connects Odysseus in Docker to an Ollama server that is already running on -your host machine; it does not start Ollama inside the container. -`host.docker.internal` is Docker's hostname for the host machine from inside the -container. Cookbook **Serve** is a separate workflow for serving downloaded -models through Odysseus/llama.cpp, so Windows users with an existing Ollama -install usually only need to add the endpoint in Settings. - -**Useful checks.** - -```bash -docker compose ps -docker compose logs --tail=120 odysseus -docker compose logs odysseus | grep -E 'ChromaDB|MemoryVectorStore|DEGRADED' -``` - -**macOS details.** `start-macos.sh` installs Homebrew deps, creates the venv, -runs setup, and starts uvicorn on port `7860` because AirPlay often holds -`7000`. It uses llama.cpp/Ollama for Metal. vLLM/SGLang are CUDA/ROCm-only and -do not run on macOS. MLX-only models are not served by Odysseus. - -
- -### Native Windows - -**One-command launcher** (creates the venv, installs deps, runs setup, starts the -server; safe to re-run): - -```powershell -git clone https://github.com/pewdiepie-archdaemon/odysseus.git -cd odysseus -powershell -ExecutionPolicy Bypass -File .\launch-windows.ps1 -``` - -Or do it by hand: - -```powershell -git clone https://github.com/pewdiepie-archdaemon/odysseus.git -cd odysseus -py -3.11 -m venv venv -venv\Scripts\Activate.ps1 -pip install -r requirements.txt -python setup.py -python -m uvicorn app:app --host 127.0.0.1 --port 7000 -``` - -If `python` points at an older interpreter, use `py -3.12` (or another installed -3.11+ version) for the venv step. - -**Requirements:** Python 3.11+. The core app (chat, agent, memory, documents, -email, calendar, deep research) runs fully native. For full **Cookbook** background -model downloads and the agent shell tool, also install -[Git for Windows](https://git-scm.com/download/win) (provides `bash.exe`). -Local GPU *serving* of vLLM/SGLang needs Linux/WSL2; for a local model on Windows, -[Ollama](https://ollama.com/download) is the easiest path — point Odysseus at -`http://localhost:11434/v1` in Settings. - -Open `http://localhost:7000`, log in with the generated admin password, -and configure everything else inside **Settings**. - -## Troubleshooting & Advanced Setup - -### `chromadb-client` conflicts with embedded ChromaDB -If `chromadb-client` (the lightweight HTTP-only package) is installed alongside the full `chromadb` package, Odysseus starts but ChromaDB silently falls back to HTTP-only mode and fails. - -**Fix:** uninstall `chromadb-client` and force-reinstall the full package: -```bash -./venv/bin/pip uninstall chromadb-client -y -./venv/bin/pip install --force-reinstall chromadb -``` - -### HTTPS + LAN/Tailscale exposure -To expose Odysseus on a local network or Tailscale with HTTPS: -1. Change the bind address to `0.0.0.0` in `.env` (`APP_BIND=0.0.0.0` or `ODYSSEUS_HOST=0.0.0.0`). -2. Generate a locally-trusted cert for your LAN/Tailscale IPs using [mkcert](https://github.com/FiloSottile/mkcert): - ```bash - mkcert -install - mkcert -cert-file cert.pem -key-file key.pem 192.168.1.100 tailscale-ip - ``` -3. Run `uvicorn` with the generated certs: - ```bash - python -m uvicorn app:app --host 0.0.0.0 --port 7000 --ssl-certfile=cert.pem --ssl-keyfile=key.pem - ``` -4. Install the `mkcert` CA on any other device you want to access Odysseus from (e.g., for iOS, email the `rootCA.pem` to yourself, install the profile, and trust it in Certificate Trust Settings). - -### Optional Dependencies -`requirements-optional.txt` contains packages that unlock extra features. It is not installed by default. - -| Package | Feature unlocked | -|---------|-----------------| -| `faster-whisper` | Local speech-to-text (microphone -> text) via the "local" STT provider. | -| `duckduckgo-search` | DuckDuckGo as a search provider option. | -| `PyMuPDF` | PDF page rendering in the side viewer panel and form-filling. (Note: AGPL-3.0) | -| `markitdown` | Office/EPUB document text extraction (converts .docx/.xlsx/.pptx/.xls/.epub to Markdown). | - -## Security Notes -Odysseus is a self-hosted workspace with powerful local tools: shell access, file uploads, model downloads, web research, email/calendar integrations, and API tokens. Treat it like an admin console. - -- Keep `AUTH_ENABLED=true` for any network-accessible deployment. -- Keep `LOCALHOST_BYPASS=false` outside local development. -- Use `SECURE_COOKIES=true` when Odysseus is served through HTTPS by a trusted reverse proxy or private access gateway. -- Do not expose it directly to the public internet without HTTPS and a trusted reverse proxy or private access layer. -- Keep `.env`, `data/`, `logs/`, databases, uploads, generated media, backups, auth/session files, API keys, and model/provider tokens out of Git and private shares. They are ignored by default. -- Review `data/auth.json` after first boot: disable open signup unless you intentionally want it, make only your own account admin, and keep demo/test accounts non-admin. -- Non-admin users do not get shell/Python/file read/write by default, and admin-only routes/tools such as MCP management, API tokens, webhooks, model/cookbook serving, backup/vault, and app settings are admin-gated. Other features are controlled by per-user privileges, so review each user's privileges before exposing a deployment. -- Rotate any API keys or tokens that were ever pasted into a shared chat, demo, screenshot, or log. -- If you enable API tokens or webhooks, create separate tokens per integration and delete unused ones. -- Prefer binding manual development runs to `127.0.0.1`; bind to `0.0.0.0` only when you intentionally want LAN/reverse-proxy access. -- Keep ChromaDB, SearXNG, ntfy, Ollama, vLLM, llama.cpp, databases, and raw model/provider APIs internal-only. Expose only the authenticated Odysseus web/API entrypoint through your trusted proxy or private access layer. -- Before publishing a fork, run `git status --short` and confirm no private files from `.env`, `data/`, `logs/`, uploads, backups, or local databases are staged. - -### Private or proxied deployments -Odysseus serves plain HTTP on its app port. Docker Compose binds Odysseus and the bundled services to `127.0.0.1` by default, so a typical production/private setup is: - -1. Keep Odysseus on localhost, for example `127.0.0.1:7000`. -2. Terminate HTTPS at a trusted reverse proxy or private access gateway. -3. Put the authenticated Odysseus web/API entrypoint behind that layer. -4. Keep raw service and model ports internal-only. - -Cloudflare Access, Tailscale, Caddy, nginx, and Traefik can all fit this pattern; none are required by Odysseus. If your access layer reaches Odysseus on the same host, proxy to `http://127.0.0.1:7000` and keep `AUTH_ENABLED=true`, `LOCALHOST_BYPASS=false`, and `SECURE_COOKIES=true`. - -Common internal-only ports from the default docs/compose setup: - -| Port | Service | -|---|---| -| `7000` | Odysseus raw app port | -| `8080` | SearXNG | -| `8091` | ntfy | -| `8100` | ChromaDB host port for manual/compose access | -| `11434` | Ollama | -| `8000-8020` | Common local model/provider APIs | +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. | -| `APP_BIND` | `127.0.0.1` | Docker Compose host bind address for the web UI. Use `0.0.0.0` only for intentional LAN/reverse-proxy access. | -| `APP_PORT` | `7000` | Docker Compose host port for the web UI. | -| `AUTH_ENABLED` | `true` | Enable/disable login | -| `LOCALHOST_BYPASS` | `false` | Development-only auth bypass for loopback requests. Keep false for shared/network deployments. | -| `SECURE_COOKIES` | `false` | Set true when serving Odysseus through HTTPS at a trusted proxy or private access gateway. | -| `DATABASE_URL` | `sqlite:///./data/app.db` | Database connection string | -| `CHROMADB_HOST` | `localhost` | ChromaDB host for vector memory. Docker overrides this to `chromadb`. | -| `CHROMADB_PORT` | `8100` | ChromaDB port for manual host runs. Docker overrides this to `8000`. | -| `EMBEDDING_URL` | -- | OpenAI-compatible embeddings endpoint | +## Security -### 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`. +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). ## Star History @@ -576,19 +215,5 @@ All user data lives in `data/` (gitignored): `app.db` (sessions, messages, docum ## 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). diff --git a/app.py b/app.py index 87ef1ae..a89f801 100644 --- a/app.py +++ b/app.py @@ -1,6 +1,18 @@ # app.py — slim orchestrator import mimetypes import os +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: @@ -38,24 +50,25 @@ load_dotenv(encoding="utf-8-sig") import asyncio import logging import secrets -from datetime import datetime +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, @@ -63,15 +76,42 @@ 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 ========= @@ -85,12 +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", @@ -104,6 +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) @@ -129,6 +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 ) @@ -146,7 +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 @@ -217,8 +312,16 @@ 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() @@ -253,6 +356,15 @@ if AUTH_ENABLED: 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 @@ -260,7 +372,7 @@ 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) if _hdr and secrets.compare_digest(_hdr, _ITT) and _is_trusted_loopback(request): # Impersonation: when the agent's loopback call sets @@ -272,11 +384,11 @@ if AUTH_ENABLED: if _impersonate and _impersonate in getattr(_auth_mgr, "users", {}): request.state.current_user = _impersonate else: - request.state.current_user = "internal-tool" + request.state.current_user = INTERNAL_TOOL_USER request.state.api_token = False return await call_next(request) - except Exception: - pass + 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 @@ -329,11 +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 @@ -382,7 +493,7 @@ 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}") @@ -408,8 +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", @@ -463,14 +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"] @@ -509,6 +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) @@ -520,9 +652,6 @@ upload_cleanup_task = None from routes.emoji_routes import setup_emoji_routes app.include_router(setup_emoji_routes()) -from routes.workspace_routes import setup_workspace_routes -app.include_router(setup_workspace_routes()) - # Sessions from routes.session_routes import setup_session_routes session_config = {"REQUEST_TIMEOUT": REQUEST_TIMEOUT, "OPENAI_API_KEY": OPENAI_API_KEY, "SESSIONS_FILE": SESSIONS_FILE} @@ -533,7 +662,7 @@ from routes.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 +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 @@ -550,11 +679,11 @@ 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 +from routes.history.history_routes import setup_history_routes app.include_router(setup_history_routes(session_manager)) # Search @@ -567,7 +696,7 @@ app.include_router(setup_preset_routes(preset_manager)) # Diagnostics from routes.diagnostics_routes import setup_diagnostics_routes -app.include_router(setup_diagnostics_routes(rag_manager, rag_available, research_handler)) +app.include_router(setup_diagnostics_routes(rag_manager, rag_available, research_handler, memory_vector)) # Cleanup from routes.cleanup_routes import setup_cleanup_routes @@ -589,6 +718,10 @@ app.include_router(setup_model_routes(model_discovery)) 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)) @@ -610,7 +743,7 @@ 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) @@ -641,6 +774,9 @@ 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()) @@ -715,7 +851,7 @@ 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()) from companion import setup_companion_routes @@ -723,23 +859,17 @@ app.include_router(setup_companion_routes()) # ========= ROUTES (kept in app.py) ========= -def _serve_html_with_nonce(request: Request, file_path: str) -> HTMLResponse: - """Read an HTML file and inject the CSP nonce into inline - - + + @@ -258,21 +264,29 @@
-

Memories

+

Memories

+

Long-term facts the AI remembers across chats — recall, edit, or curate.

- - - +
+ + + +
+ +
@@ -293,7 +307,7 @@
-

Add Skill

+

Add Skill

-

Create a skill by hand — title, what it solves, and an approach.

+

Import a skill from GitHub or skills.sh (folder with SKILL.md and optional templates).

+
+
+ + Import URL — e.g. GitHub tree link to a skill folder +
+ +
+

Or create a skill by hand — title, what it solves, and an approach.

Title — short name, e.g. “build-vllm-wheel” @@ -331,7 +354,7 @@ Tags — comma-separated, e.g. python, build, vllm
- +
@@ -339,8 +362,9 @@ @@ -386,34 +410,23 @@ @@ -563,6 +587,7 @@ +
@@ -573,6 +598,13 @@
+
+ + +
- +
@@ -1865,7 +1929,7 @@ +
+

Model Defaults

+
+
+
Share defaults with users
+
When on, users without a personal default inherit the global default model (only if those models are allowed for them).
+
+ +
+

Users

Loading...
@@ -2003,8 +2078,8 @@

Add User

- - + +
Admin
@@ -2016,73 +2091,103 @@
-
-

Add Models (Endpoints)

-
Connect local models first, or add a cloud API.
- -