- Jev (TypeSafe, direct) triages mode and task type with confidence
- Its call stands at >= 70% on both and no split; otherwise the LLM
Sentry decides (unsure, split needs subtasks, or Jev down)
- Jev flights obey the same budget, flock cap, timeout and log
- Tests for every path; flight log is nil-safe
- start.command reads TYPESAFE_API_KEY and threshold from .env
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UQnSw4RRWp8uqpj3nsnnXF
- ChatBrain speaks OpenAI-style chat completions (OpenRouter now)
- CROWS_PROVIDER picks anthropic or openrouter; default model
openrouter/free; CROWS_MODEL overrides
- Flight log records the model that actually answered
- Token budgets fall back to a length estimate if usage is missing
- start.command reads either key from .env
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UQnSw4RRWp8uqpj3nsnnXF
Go command-line tool. Sentry classifies each todo item as solo, split,
or murder; text-only crows fly under budget, timeout, and flock caps;
trust is earned per crow and per task type; abusive requesters get a
mild, fading cooldown. Runs offline with a mock brain.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UQnSw4RRWp8uqpj3nsnnXF
