Implement CYA-WP-0008 llm-connect adapter integration.

Wire LLMConnectAdapter behind the existing LLMAdapter seam with config-driven
selection, graceful degradation, --offline mode, and bounded session context.
Add unit tests, integration docs, and update README/SCOPE/AGENTS.
This commit is contained in:
2026-06-22 10:36:10 +02:00
parent cd5db14fbf
commit 019f6e7dc7
17 changed files with 800 additions and 19 deletions

View File

@@ -185,6 +185,7 @@ make check-dist
# Run the assistant
cya "your natural language request here"
cya --offline "..." # deterministic fake adapter (CI / no API keys)
cya --help
cya --explain-context "show me what context would be collected"
@@ -213,7 +214,7 @@ Relevant workplans:
- `workplans/CYA-WP-0005-agentic-memory-profiles-and-phase-memory-feedback.md`
- `workplans/CYA-WP-0006-profile-1-production-hardening.md` (finished)
- `workplans/CYA-WP-0007-interactive-shell-session.md` (ready — interactive REPL + history + hub)
- `workplans/CYA-WP-0008-llm-connect-adapter-integration.md` (ready — real LLM behind adapter seam)
- `workplans/CYA-WP-0008-llm-connect-adapter-integration.md` (finished — real LLM behind adapter seam)
---