9112861d8e
Three converging fixes so the chat agent + external Codex/Claude skills can actually debug a crashed serve instead of staring at a post-crash neofetch banner:
* Serves now `tee` to /tmp/odysseus-tmux/SESSION.log on the host running them. Runner saves fds 3/4 before the tee and restores them right before `exec ${SHELL}`, so the post-crash interactive zsh banner does NOT pollute the log file.
* `tail_serve_output` (chat agent) and `/api/codex/cookbook/output/{sid}` (Codex+Claude skills) both prefer the persistent log file over the tmux pane. Pane is fallback for sessions predating the tee runner. Default tail bumped 150 -> 400.
* `list_served_models` "recent log" snippet seeks to the Traceback line instead of showing the last 6 lines (which was always the bash prompt).
Cookbook auto-adoption sweep on `/api/cookbook/tasks/status`: every 20s (rate-limited) the cookbook SSHes each configured server, finds `serve-*` / `cookbook-*` tmux sessions running an actual model process (vllm/python/llama-server/etc., filtered via `pane_current_command`), and writes them into state.tasks. So when the agent falls back to raw ssh+tmux, the session appears in the Cookbook UI on the next poll.
`serve_model` error path now reads `data["detail"]` in addition to `data["error"]` so the FastAPI HTTPException message ("Invalid characters in cmd") actually reaches the agent instead of being swallowed as a generic "Serve failed". Tool description updated to warn against `cd …`/`source …`/`&&` prefixes.
Intent-without-action supervisor in agent_loop: when the model writes "Let me tail the output" / "I'll check the logs" / "Let me investigate" and ends the turn without emitting a tool call, the loop injects a sharp system nudge ("You said you would X — DO IT NOW") and continues. Capped at 2 nudges per chat so a model that genuinely cannot use the tool does not pin the loop.
Codex/Claude skill parity: adds `/cookbook/cached`, `/cookbook/presets`, `/cookbook/preset/{name}`, `/cookbook/adopt` so external agents have the same surface as the chat agent. SKILL.md docs + odysseus_api.py wrapper updated for both bundles.
`adopt_served_model` promoted to the always-on tool set so the agent has a documented fallback when serve_model rejects a cmd.
Also various cookbook UI tweaks accumulated alongside the above (cookbook.js, cookbookRunning.js, cookbookServe.js, cookbook-diagnosis.js, settings.js, style.css).
Odysseus Claude Code Integration
This directory contains the Claude Code skill bundle for Odysseus.
User Flow
- Open Odysseus Settings > Integrations.
- Add a Claude Agent.
- Copy the full setup commands shown after the generated token.
- Toggle the tools Claude is allowed to use.
- Configure the terminal Claude Code session:
export ODYSSEUS_URL=http://your-odysseus-host:7000
export ODYSSEUS_API_TOKEN=ody_generated_token
mkdir -p ~/.claude
curl -fsSL -H "Authorization: Bearer $ODYSSEUS_API_TOKEN" "$ODYSSEUS_URL/api/claude/plugin.zip" -o /tmp/odysseus-claude-skill.zip
python3 -m zipfile -e /tmp/odysseus-claude-skill.zip ~/.claude/
Claude Code auto-loads anything under ~/.claude/skills/, so the odysseus skill is
available in any session that has ODYSSEUS_URL and ODYSSEUS_API_TOKEN in its
environment.
What's in the bundle
skills/odysseus/SKILL.md— the skill definition Claude Code reads.skills/odysseus/scripts/odysseus_api.py— small helper that calls the scoped/api/codex/*endpoints (these are the canonical scope-gated agent API; thecodexpath is historic and shared by all agent integrations).
Scope enforcement
The token is scope-gated. Every tool surface is checked server-side in Odysseus,
so even if Claude tries to call a forbidden endpoint, it gets 403 until the
user enables the matching toggle in Settings > Integrations > Claude Agent.