feat(P5): IHF Phase 5 complete — agent-assisted distillation
Some checks failed
Test / test (push) Has been cancelled

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>
This commit is contained in:
2026-03-29 15:54:33 +00:00
parent 1862bb295a
commit 2605c1c977
23 changed files with 1284 additions and 21 deletions

View File

@@ -41,6 +41,10 @@ instance View ShowView where
class="text-sm border border-green-300 text-green-700 px-3 py-1.5 rounded hover:bg-green-50">
Antifragility
</a>
<a href={AgentAuditDashboardAction { hubId = hub.id }}
class="text-sm border border-purple-300 text-purple-700 px-3 py-1.5 rounded hover:bg-purple-50">
Agent Audit
</a>
<a href={EditHubAction { hubId = hub.id }}
class="text-sm border border-gray-300 px-3 py-1.5 rounded hover:bg-gray-50">
Edit