stella-ops.org/git.stella-ops.org
1
0
Fork 0
Code Issues Pull Requests Actions 16 Releases Wiki Activity
Files
8d78dd219b5e44c835e511491a4750f4a3ee3640
git.stella-ops.org/docs/modules/advisory-ai/README.md
StellaOps Bot 8d78dd219b
Some checks failed
Docs CI / lint-and-preview (push) Has been cancelled
Details
feat(advisory-ai): Add deployment guide, Dockerfile, and Helm chart for on-prem packaging 
- Introduced a comprehensive deployment guide for AdvisoryAI, detailing local builds, remote inference toggles, and scaling guidance.
- Created a multi-role Dockerfile for building WebService and Worker images.
- Added a docker-compose file for local and offline deployment.
- Implemented a Helm chart for Kubernetes deployment with persistence and remote inference options.
- Established a new API endpoint `/advisories/summary` for deterministic summaries of observations and linksets.
- Introduced a JSON schema for risk profiles and a validator to ensure compliance with the schema.
- Added unit tests for the risk profile validator to ensure functionality and error handling.
2025-11-23 00:35:33 +02:00

3.5 KiB
Raw Blame History

StellaOps Advisory AI

Advisory AI is the retrieval-augmented assistant that synthesizes advisory and VEX evidence into operator-ready summaries, conflict explanations, and remediation plans with strict provenance.

Responsibilities

  • Generate policy-aware advisory summaries with citations back to Conseiller and Excititor evidence.
  • Explain conflicting advisories/VEX statements using weights from VEX Lens and Policy Engine.
  • Propose remediation hints aligned with Offline Kit staging and export bundles.
  • Expose API/UI surfaces with guardrails on model prompts, outputs, and retention.

Key components

  • RAG pipeline drawing from Conseiller, Excititor, VEX Lens, Policy Engine, and SBOM Service data.
  • Prompt templates and guard models enforcing provenance and redaction policies.
  • Vercel/offline inference workers with deterministic caching of generated artefacts.

Integrations & dependencies

  • Authority for tenant-aware access control.
  • Policy Engine for context-specific decisions and explain traces.
  • Console/CLI for interaction surfaces.
  • Export Center/Vuln Explorer for embedding generated briefs.

Operational notes

  • Model cache management and offline bundle packaging per Epic 8 requirements.
  • Usage/latency dashboards for prompt/response monitoring with advisory_ai_latency_seconds, guardrail block/validation counters, and citation coverage histograms wired into the default “Advisory AI” Grafana dashboard.
  • Alert policies fire when advisory_ai_guardrail_blocks_total or advisory_ai_validation_failures_total breach burn-rate thresholds (5 blocks/min or validation failures > 1% of traffic) and when latency p95 exceeds 30s.
  • Redaction policies validated against security/LLM guardrail tests.
  • Guardrail behaviour, blocked phrases, and operational alerts are detailed in /docs/security/assistant-guardrails.md.

Deployment & configuration

  • Containers: advisory-ai-web fronts the API/cache while advisory-ai-worker drains the queue and executes prompts. Both containers mount a shared RWX volume providing /app/data/{queue,plans,outputs} (defaults; configurable via ADVISORYAI__STORAGE__*).
  • Remote inference toggle: Set ADVISORYAI__INFERENCE__MODE=Remote to send sanitized prompts to an external inference tier. Provide ADVISORYAI__INFERENCE__REMOTE__BASEADDRESS (and optional ...__APIKEY, ...__TIMEOUT) to complete the circuit; failures fall back to the sanitized prompt and surface inference.fallback_* metadata.
  • Helm/Compose: Packaged manifests live under ops/advisory-ai/ and wire SBOM base address, queue/plan/output directories, and inference options. Helm defaults to emptyDir with optional PVC; Compose creates named volumes so worker and web instances share deterministic state. See docs/modules/advisory-ai/deployment.md for commands.

CLI usage

  • stella advise run <summary|conflict|remediation> --advisory-key <id> [--artifact-id id] [--artifact-purl purl] [--policy-version v] [--profile profile] [--section name] [--force-refresh] [--timeout seconds]
    • Requests an advisory plan from the web service, enqueues execution, then polls for the generated output (default wait 120 s, single check if --timeout 0).
    • Renders plan metadata (cache key, prompt template, token budget), guardrail state, provenance hashes, signatures, and citations in a deterministic table view.
    • Honors STELLAOPS_ADVISORYAI_URL when set; otherwise the CLI reuses the backend URL and scopes requests via X-StellaOps-Scopes.

Epic alignment

  • Epic 8: Advisory AI Assistant.
  • DOCS-AI stories to be tracked in ../../TASKS.md.