Adds bounded AI support to the IHF governance loop. All AI outputs are
attributed (model_ref), reviewable (AgentReviewRecord), and reversible.
No autonomous decisions; no silent requirement promotion.
- T01: Schema — agent_proposals, agent_review_records,
confidence_annotations (migration 1743379200)
- T02: AgentProposalsController (index/show/accept/reject, idempotent
review guard), global nav "Agent" link
- T03: SummarizeClusterAction — Claude API cluster summary on widget show
- T04: DraftRequirementAction — AI requirement draft; acceptance creates
RequirementCandidate (human-gated)
- T05: DetectDuplicatesAction — duplicate_flag proposal on candidate show
- T06: DetectPolicySensitivityAction — policy_flag with
ConfidenceAnnotations per concern scope
- T07: ProposeImplementationAction — impl_proposal from decision show
- T08: AgentAuditDashboardAction — autoRefresh; KPI row, unreviewed queue,
recent proposals, attribution log matrix
- T09: integration tests, SCOPE.md updated, phase5-summary.md, flake.nix
adds http-conduit/aeson/string-conversions
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- docs/phase1-summary.md: what was built, known limitations, Phase 2 readiness
- SCOPE.md: current state updated to Phase 1 complete
- All 12 workplan tasks marked done; workplan status set to done
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>