stella-ops.org/git.stella-ops.org
1
0
Fork 0
Code Issues Pull Requests Actions 16 Releases Wiki Activity

work
Some checks failed
AOC Guard CI / aoc-guard (push) Has been cancelled
Details
AOC Guard CI / aoc-verify (push) Has been cancelled
Details
Concelier Attestation Tests / attestation-tests (push) Has been cancelled
Details
Docs CI / lint-and-preview (push) Has been cancelled
Details

Browse Source
This commit is contained in:
StellaOps Bot
2025-11-25 08:01:23 +02:00
parent d92973d6fd
commit 6bee1fdcf5
207 changed files with 12816 additions and 2295 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
docs/advisory-ai/guardrails-and-evidence.md
View File

@@ -1,15 +1,16 @@
# Advisory AI Guardrails & Evidence Intake
_Updated: 2025-11-22 · Owner: Advisory AI Docs Guild · Status: Draft (Sprint 0111)_
_Updated: 2025-11-24 · Owner: Advisory AI Docs Guild · Status: Published (Sprint 0111)_
This note captures the guardrail behaviors and evidence intake boundaries required by Sprint 0111 tasks (`AIAI-DOCS-31-001`, `AIAI-RAG-31-003`). It binds Advisory AI guardrails to upstream evidence sources and clarifies how Link-Not-Merge (LNM) documents flow into Retrieval-Augmented Generation (RAG) payloads.
## 1) Evidence sources and contracts
**Upstream readiness gates**
**Upstream readiness gates (now satisfied)**
- CLI + Policy artefacts (`CLI-VULN-29-001`, `CLI-VEX-30-001`, `policyVersion` digests) must be present before enabling non-default profiles. Until then, Advisory AI accepts requests but responds with `409 advisory.contextUnavailable` when those references are missing.
- LNM linksets stay the single source of truth; Advisory AI refuses ad-hoc advisory payloads even if CLI/Policy artefacts are delayed.
- CLI guardrail artefacts landed on 2025-11-19: `out/console/guardrails/cli-vuln-29-001/` (`sample-vuln-output.ndjson`, `sample-sbom-context.json`) and `out/console/guardrails/cli-vex-30-001/` (`sample-vex-output.ndjson`). Hashes are recorded in `docs/modules/cli/artefacts/guardrails-artefacts-2025-11-19.md` and must be copied into Offline Kits.
- Policy hash must be pinned (`policyVersion`, see `docs/policy/assistant-parameters.md`) before enabling non-default profiles.
- LNM linksets stay the single source of truth; Advisory AI refuses ad-hoc advisory payloads even if upstream artefacts drift.
- **Advisory observations (LNM)** — Consume immutable `advisory_observations` and `advisory_linksets` produced per `docs/modules/concelier/link-not-merge-schema.md` (frozen v1, 2025-11-17).
- **VEX statements** — Excititor + VEX Lens linksets with trust weights; treated as structured chunks with `source_id` and `confidence`.
@@ -63,5 +64,6 @@ See `docs/advisory-ai/evidence-payloads.md` for full JSON examples and alignment
- [ ] LNM feed enabled and Concelier schemas at v1 (2025-11-17).
- [ ] SBOM retriever configured or `NullSbomContextClient` left as safe default.
- [ ] Policy hash pinned via `policyVersion` when reproducibility is required.
- [ ] CLI guardrail artefact hashes verified against `docs/modules/cli/artefacts/guardrails-artefacts-2025-11-19.md` and mirrored into Offline Kits.
- [ ] Remote profiles only after Authority consent and profile allowlist are set.
- [ ] Cache directories shared between web + worker hosts for DSSE sealing.