1.7 KiB
1.7 KiB
Concelier Advisory Chunks API (Paragraph-Anchored)
Module
Concelier
Status
IMPLEMENTED
Description
REST API endpoint serving paragraph-anchored advisory chunks with tenant enforcement, AdvisoryRead scopes, and filters for sections/formats/limits/minLength. Designed for Advisory AI to pull deterministic paragraph anchors plus source metadata.
Implementation Details
- Modules:
src/Concelier/StellaOps.Concelier.WebService/ - Key Classes:
AdvisoryChunkBuilder(src/Concelier/StellaOps.Concelier.WebService/Services/AdvisoryChunkBuilder.cs) - builds paragraph-anchored chunks from advisory contentAdvisoryChunkCache(src/Concelier/StellaOps.Concelier.WebService/Services/AdvisoryChunkCache.cs) - in-memory cache for advisory chunksMessagingAdvisoryChunkCache(src/Concelier/StellaOps.Concelier.WebService/Services/MessagingAdvisoryChunkCache.cs) - messaging-backed cache implementationAdvisoryChunkOptions(src/Concelier/StellaOps.Concelier.WebService/Options/ConcelierOptions.cs) - configuration for chunk sizes, limits, and formats
- Interfaces:
IAdvisoryChunkCache - Source: 2025-11-07-concelier-advisory-chunks.md
E2E Test Plan
- Call the advisory chunks endpoint with a valid advisory ID and verify paragraph-anchored chunks are returned
- Verify tenant enforcement: request chunks without AdvisoryRead scope and confirm 403 response
- Verify section filter: request only specific sections and confirm only matching chunks are returned
- Verify minLength filter: set minLength and confirm short paragraphs are excluded
- Verify caching: request same advisory chunks twice and confirm second response is served from cache