b059bc7675
Some checks failed
Docs CI / lint-and-preview (push) Has been cancelled
feat(telemetry): Record chunk latency, result count, and source count in AdvisoryAiTelemetry fix(endpoint): Include telemetry source count in advisory chunks endpoint response test(metrics): Enhance WebServiceEndpointsTests to validate new metrics for chunk latency, results, and sources refactor(tests): Update test utilities for Deno language analyzer tests chore(tests): Add performance tests for AdvisoryGuardrail with scenarios and blocked phrases docs: Archive Sprint 137 design document for scanner and surface enhancements
1.1 KiB
1.1 KiB
2025-11-07 – Concelier advisory chunks API
Subject: Paragraph-anchored advisory chunks land for Advisory AI Audience: Concelier WebService Guild, Advisory AI Guild, Observability Guild
- Shipped /advisories/{advisoryKey}/chunks with tenant enforcement, AdvisoryRead scopes, and filters for sections/formats/limits/minLength so Advisory AI can pull paragraph anchors plus source metadata deterministically.
- Registered AdvisoryChunkBuilder behind new advisoryChunks configuration (chunk/observation/min-length caps) to keep offline and air-gapped deployments tunable without code changes.
- Added regression coverage that seeds synthetic observations with embedded paragraphs to validate anchors, metadata, and source ordering before Advisory AI consumes the API; module README now points at this release note.
Follow-ups
- CONCELIER-AIAI-31-002 – surface structured workaround/fix fields plus caching for downstream retrievers.
- CONCELIER-AIAI-31-003 – wire chunk request metrics/logs and guardrail telemetry once the API stabilizes. (2025-11-10: request/latency/source histograms + structured guardrail logs shipped.)