Files
git.stella-ops.org/docs/modules/advisory-ai/unified-search-release-readiness.md

38 lines
1.7 KiB
Markdown

# Unified Search Release Readiness
## Release Checklist
- [x] Schema migration path validated (clean + existing DB paths exercised in integration and migration checks).
- [x] Ingestion adapters validated across domains (findings, vex, policy, graph, timeline, scanner, opsmemory, platform).
- [x] Ranking quality gates satisfied by benchmark suite.
- [x] Performance envelope validated (50 concurrent load profile and regression guard).
- [x] Tenant isolation validated.
- [x] Accessibility checks retained in existing Web UI search suites.
- [x] Legacy endpoint compatibility and deprecation headers validated.
- [x] Analytics collection and retention loop validated.
- [x] Runbooks and architecture docs updated.
## Rollback Plan (Tested)
1. Disable per-tenant unified search:
- `AdvisoryAI:UnifiedSearch:TenantFeatureFlags:<tenant>:Enabled=false`
2. Optionally disable high-cost features first:
- `FederationEnabled=false`
- `SynthesisEnabled=false`
3. Keep index tables intact (no data loss).
4. Keep legacy platform endpoint active during rollback window.
5. Re-enable tenant gradually after quality/perf re-check.
## Known Issues
- ONNX model artifact in repository is a packaging placeholder path. Deployments must supply the licensed production model artifact for true semantic inference.
- Environment-level UI E2E reliability depends on full backend stack availability.
## Feature Flags
Path: `AdvisoryAI:UnifiedSearch:TenantFeatureFlags`
- `Enabled`
- `FederationEnabled`
- `SynthesisEnabled`
These flags are evaluated per tenant at request time in `UnifiedSearchService`.
## Archive Criteria
Search sprint files are eligible for archive only when all delivery tracker tasks are marked `DONE` and acceptance criteria are checked.