generated from coulomb/repo-seed
Mirror sibling-repo Claude setup (CLAUDE.md + .claude/rules/*), align AGENTS.md with fleet credential-routing template, and close housekeeping gaps (WP-0002-T05 done, WP-0005 status note). Draft CYA-WP-0006 for Profile 1 production hardening as the proposed next slice.
1.1 KiB
1.1 KiB
Architecture
Request pipeline (src/cya/orchestrator.py):
- Collect local context (
context/collector.py) - Recall memory via phase-memory ports (
memory/__init__.py) - Classify risk (
safety/risk.py) — rule-based; memory signals add caution only - Call LLM via
LLMAdapterProtocol (llm/adapter.py) — FakeLLMAdapter today - Render explainable response (Rich)
Memory (Profile 0 + Profile 1 spike):
- User-controlled local JSON behind explicit ports (
remember,recall,forget,export) - Kinds:
preference,retrospection,interaction_goal,reflection - Directory/project-bound activation via
activation_context cya retrospectfeeds higher-order memory; optional verbal lesson capture (Profile 1)
Boundaries: See repo-boundary.md. No production path bypasses the adapter or memory ports.
Quick Reference
- Memory contract:
MemoryVision.md - Activation/retrospection concept:
docs/cya-memory-activation-and-retrospection-concept.md - phase-memory feedback:
docs/phase-memory-optimization-suggestions.md ~/state-hub/mcp_server/TOOLS.md— MCP tool reference