What this documentation covers

• Troubleshooting retrieval relevance and missing sources.
• Understanding policy denials and permission boundaries.
• Handling tool errors and retries.
• Improving cost and latency via routing and context control.
• Debugging integration issues (webhooks, auth, commands).

Who this is for

• Operators and engineers diagnosing real production issues.

Operational expectations

• Examples favor deterministic behavior and explicit contracts (schemas, IDs, correlation).
• Security is treated as a default: least privilege, audit logs, and safe fallbacks.
• Changes are versioned; breaking changes should be announced via /docs/changelog.