coulomb/inter-hub
2
0
Fork 0
generated from coulomb/repo-seed
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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:
Bernd Worsch
2026-03-29 15:54:33 +00:00
parent 1862bb295a
commit 2605c1c977
23 changed files with 1284 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
SCOPE.md
View File

@@ -65,9 +65,9 @@ IHF treats every meaningful UI element as a **governed interaction artifact** ra
## Current State
- Status: Phase 4 complete — outcome observation and antifragility loop implemented
- Implementation: Phase 0 complete (specification); Phase 1 complete (widget registry, event capture, annotations, hub dashboard, auth); Phase 2 complete (annotation severity, annotation threads, requirement candidates, triage lifecycle, reviewer assignment, triage dashboard); Phase 3 complete (requirement promotion, decision records, policy references, implementation change references, governance dashboard); Phase 4 complete (deployment records, outcome signals, pre/post comparison, regression detection, change evaluation, recurrence tracking, antifragility dashboard)
- Stability: core artifact model and schema are stable; Phase 4 data model (DeploymentRecord, OutcomeSignal, ChangeEvaluation) is additive and stable; outcome signals and interaction events are append-only (DB triggers)
- Status: Phase 5 complete — agent-assisted distillation and suggestion implemented
- Implementation: Phase 0 complete (specification); Phase 1 complete (widget registry, event capture, annotations, hub dashboard, auth); Phase 2 complete (annotation severity, annotation threads, requirement candidates, triage lifecycle, reviewer assignment, triage dashboard); Phase 3 complete (requirement promotion, decision records, policy references, implementation change references, governance dashboard); Phase 4 complete (deployment records, outcome signals, pre/post comparison, regression detection, change evaluation, recurrence tracking, antifragility dashboard); Phase 5 complete (agent proposals, review records, confidence annotations, cluster summarization, requirement drafting, duplicate detection, policy sensitivity, implementation proposals, agent audit dashboard)
- Stability: core artifact model and schema are stable; Phase 5 data model (AgentProposal, AgentReviewRecord, ConfidenceAnnotation) is additive; all AI outputs are attributed and reviewer-controlled
- Usage: reference implementation running on IHP v1.5 + PostgreSQL; `devenv up` to start
---