docs: add scheduler integration and memory system plan

Documentation updates:
- AGENTS.md: Added wakeup.sh usage and local testing instructions
- LIBRARIAN_INTEGRATION.md: Complete maintenance scheduler docs
  - Scheduled task configuration for reconcile-index
  - Endpoint specifications and response formats
- docs/MEMORY_SYSTEM_PLAN.md: Three-tier memory architecture
  - Volatile (Redis TTL) for ephemeral context
  - Documents (TBD) for git mirrors, PDFs, images
  - Knowledge (Wiki + Neo4j) for permanent research

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

AGENTS.md

@@ -51,6 +51,21 @@ When changes are ready for deployment:
 
 ---
 
+### 🧪 Local Development Setup
+* **Always test locally first** before committing and deploying. The build-deploy loop is slow.
+* **Start the local server** with `./wakeup.sh` - logs are written to `logs/server.log` for easy tailing
+* **Auto-reload**: The wakeup script runs uvicorn in reload mode - code changes are picked up automatically without restart (except for requirements.txt changes)
+* **Test REST endpoints** against `http://localhost:8778` using curl or similar tools
+* **Only deploy** when a phase or feature is complete and tested locally
+* **Environment**: Copy `.env.example` to `.env` and configure for your local setup (Ollama, Redis, Neo4j, Qdrant, Wiki.js hosts)
+* **Running tests**: Always use the venv explicitly to avoid environment mismatches:
+  ```bash
+  .venv/bin/python -m pytest tests/           # All tests
+  .venv/bin/python -m pytest tests/ -v        # Verbose output
+  ```
+
+---
+
 ## 2. FastAPI Architecture & Best Practices
 *Reference: [FastAPI Best Practices](https://github.com/zhanymkanov/fastapi-best-practices)*