Léo 5fd9114882 test(runtime): pin negative capability wording, test-only
First slice of the runtime regression lane. Drives stream_agent_loop with a
fake model and asserts on the tools the runtime offers, which is its decision
about what the turn may do. No production runtime code is touched and no
benchmark fixture or allowlist is imported.

The fake-model pattern is the one tests/test_tool_policy.py already uses:
patch stream_llm_with_fallback and inspect the tools kwarg.

Measured on lab@c499c01b, negative web wording is only partially detected:

  "Answer from memory only, don't search online."            web tools withheld
  "Summarise what you already know. Do not search the web."  web tools OFFERED
  "No web search please, just tell me what you know..."      web tools OFFERED

The case that holds is a plain regression guard. The two that do not are
xfail(strict=True): they run on every suite, document the target, and fail the
moment the behaviour lands so the marker gets removed rather than lingering.
A positive control keeps the guard from being satisfied by removing the web
tools altogether.
2026-09-30 17:11:10 +02:00
2026-09-11 06:04:19 +00:00
2026-09-11 06:04:19 +00:00
2026-05-31 23:58:26 +09:00
2026-07-23 14:49:02 +00:00

Odysseus

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

Quick Start · Setup Guide · Contributing · Roadmap

Packaging status

Odysseus interface


Quick Start

dev is the default branch and gets the newest changes first. Use main if you want the more curated branch.

git clone https://github.com/odysseus-dev/odysseus.git
cd odysseus
cp .env.example .env
docker compose up -d --build

Open http://localhost:7011 when the containers are healthy. The first admin password is printed in docker compose logs odysseus.

Native installs, GPU notes, Windows/macOS instructions, HTTPS, and configuration live in the setup guide.

Features

  • 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.

Demo

A full hover-to-play tour lives on the Odysseus landing page. Its source lives under website/.

Contributing

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 and ROADMAP.md.

Security

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.

  • Keep AUTH_ENABLED=true for any network-accessible deployment.
  • Keep LOCALHOST_BYPASS=false outside local development.

Deployment details are in the setup guide.

Star History

Star History Chart

License

AGPL-3.0-or-later -- see LICENSE and ACKNOWLEDGMENTS.md.

S
Description
No description provided
Readme AGPL-3.0
458 MiB
Languages
Python 55.3%
JavaScript 35.3%
CSS 7%
HTML 1.9%
Shell 0.4%