957360f6ce
CLAUDE.md: 178→25 lines — commands + @ARCHITECTURE.md import only Rules split into .claude/rules/ (load at startup, topic-scoped): llm-inference.md — Bifrost-only, semaphore, model name format, timeouts agent-pipeline.md — tier rules, no tools in medium, memory outside loop fast-tools.md — extension guide (path-scoped: fast_tools.py + agent.py) secrets.md — .env keys, Vaultwarden, no hardcoding Path-scoped rule: fast-tools.md only loads when editing fast_tools.py or agent.py Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
1.1 KiB
1.1 KiB
paths
| paths | ||
|---|---|---|
|
Fast Tools — Extension Guide
To add a new fast tool:
-
In
fast_tools.py, subclassFastTooland implement:name(str property) — unique identifier, used in logsmatches(message: str) -> bool— regex or logic; keep it cheap, runs on every messagerun(message: str) -> str— async fetch; return a short context block or""on failure; never raise
-
In
agent.py, add an instance to the_fast_tool_runnerlist (module level, after env vars are defined). -
The router will automatically force medium tier when
matches()returns true — no router changes needed.
Constraints
run()must return in under 15s — it runs in the pre-flight gather that blocks routing.- Return
""or a[tool error: ...]string on failure — never raise exceptions. - Keep returned context under ~1000 chars — larger contexts slow down
qwen3:4bstreaming significantly. - The deepagents container has no direct external internet. Use SearXNG (
host.docker.internal:11437) or internal services.