feat(P5): IHF Phase 5 complete — agent-assisted distillation

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>

flake.nix

@@ -37,6 +37,10 @@
                         # ihp-job-dashboard  # Job dashboard UI
                         # ihp-typed-sql      # Type-safe SQL queries
                         # ihp-pglistener     # PostgreSQL LISTEN/NOTIFY
+                        # Phase 5: Anthropic API calls
+                        http-conduit
+                        aeson
+                        string-conversions
                     ];
                     devHaskellPackages = p: with p; [
                         cabal-install