File system intelligence tool — agentic directory analysis via Claude API
The system prompt already instructs the agent to set confidence/ confidence_reason on every write_cache call, but the tool's data schema description listed only the legacy fields. Add the confidence fields and a one-line calibration pointer so the model sees them when binding the tool, not just in the system prompt. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| luminos_lib | ||
| tests | ||
| .gitignore | ||
| CLAUDE.md | ||
| luminos.py | ||
| PLAN.md | ||
| setup_env.sh | ||