Advisory AI architecture

Captures the retrieval, guardrail, and inference packaging requirements defined in the Advisory AI implementation plan and related module guides.

1) Goals

Summarise advisories/VEX evidence into operator-ready briefs with citations.
Explain conflicting statements with provenance and trust weights (using VEX Lens & Excititor data).
Suggest remediation plans aligned with Offline Kit deployment models and scheduler follow-ups.
Operate deterministically where possible; cache generated artefacts with digests for audit.

2) Pipeline overview

                       +---------------------+
   Concelier/VEX Lens  |  Evidence Retriever |
   Policy Engine ----> |  (vector + keyword) | ---> Context Pack (JSON)
   Zastava runtime     +---------------------+
                               |
                               v
                        +-------------+
                        | Prompt      |
                        | Assembler   |
                        +-------------+
                               |
                               v
                        +-------------+
                        | Guarded LLM |
                        | (local/host)|
                        +-------------+
                               |
                               v
                        +-----------------+
                        | Citation &     |
                        | Validation      |
                        +-----------------+
                               |
                               v
                        +----------------+
                        | Output cache   |
                        | (hash, bundle) |
                        +----------------+

3) Retrieval & context

Hybrid search: vector embeddings (SBERT-compatible) + keyword filters for advisory IDs, PURLs, CVEs.
Context packs include:
- Advisory raw excerpts with highlighted sections and source URLs.
- VEX statements (normalized tuples + trust metadata).
- Policy explain traces for the affected finding.
- Runtime/impact hints from Zastava (exposure, entrypoints).
- Export-ready remediation data (fixed versions, patches).

All context references include content_hash and source_id enabling verifiable citations.

4) Guardrails

Prompt templates enforce structure: summary, conflicts, remediation, references.
Response validator ensures:
- No hallucinated advisories (every fact must map to input context).
- Citations follow [n] indexing referencing actual sources.
- Remediation suggestions only cite policy-approved sources (fixed versions, vendor hotfixes).
Moderation/PII filters prevent leaking secrets; responses failing validation are rejected and logged.

5) Output persistence

Cached artefacts stored in advisory_ai_outputs with fields:
- output_hash (sha256 of JSON response).
- input_digest (hash of context pack).
- summary, conflicts, remediation, citations.
- generated_at, model_id, profile (Sovereign/FIPS etc.).
- signatures (optional DSSE if run in deterministic mode).
Offline bundle format contains summary.md, citations.json, context_manifest.json, signatures/.

6) Profiles & sovereignty

Profiles: default, fips-local (FIPS-compliant local model), gost-local, cloud-openai (optional, disabled by default). Each profile defines allowed models, key management, and telemetry endpoints.
CryptoProfile/RootPack integration: generated artefacts can be signed using configured CryptoProfile to satisfy procurement/trust requirements.

7) APIs

POST /v1/advisory-ai/summaries — generate (or retrieve cached) summary for {advisoryKey, artifactId, policyVersion}.
POST /v1/advisory-ai/conflicts — explain conflicting VEX statements with trust ranking.
POST /v1/advisory-ai/remediation — fetch remediation plan with target fix versions, prerequisites, verification steps.
GET /v1/advisory-ai/outputs/{hash} — retrieve cached artefact (used by CLI/Console/Export Center).

All endpoints accept profile parameter (default fips-local) and return output_hash, input_digest, and citations for verification.

8) Observability

Metrics: advisory_ai_requests_total{profile,type}, advisory_ai_latency_seconds, advisory_ai_validation_failures_total.
Logs: include output_hash, input_digest, profile, model_id, tenant, artifacts. Sensitive context is not logged.
Traces: spans for retrieval, prompt assembly, model inference, validation, cache write.

9) Operational controls

Feature flags per tenant (ai.summary.enabled, ai.remediation.enabled).
Rate limits (per tenant, per profile) enforced by Orchestrator to prevent runaway usage.
Offline/air-gapped deployments run local models packaged with Offline Kit; model weights validated via manifest digests.

4.9 KiB Raw Blame History