Commit Graph

4 Commits

Author SHA1 Message Date
133dae3d23 feat(WP-0012): IHF Phase 11 — Advanced AI Federation
Some checks failed
Test / test (push) Has been cancelled
- Schema: AgentRegistration, ModelRoutingPolicy, AgentDelegation,
  CollectiveProposal, CollectiveProposalContribution, AiGovernancePolicy,
  AgentPerformanceRecord + ALTER TABLE agent_proposals
  (migration 1744156800; CHECK constraints on trust_level, status,
  consensus_status — GAAF compliant)

- Bridge: scripts/llm_bridge.py (llm-connect subprocess seam) +
  Application/Helper/AgentBridge.hs (callBridge, callAgent,
  checkGovernancePolicy, jsonArrayTexts)

- Routing: Application/Helper/ModelRouter.hs (resolveAgent,
  resolveAllAgents) + ModelRoutingPolicies CRUD

- Registry: AgentRegistrations CRUD (Index/Show/New/Edit/Performance),
  DeactivateAgentAction, ComputeAgentPerformanceAction

- Delegation: AgentDelegations controller + views, DelegateSubtaskAction
  with token budget enforcement at bridge call time

- Collective: CollectiveProposals controller + views,
  CreateCollectiveProposalAction (fan-out → synthesis → consensus detection)

- Governance: AiGovernancePolicies CRUD + ToggleAiGovernancePolicyAction;
  checkGovernancePolicy enforced at all 4 Phase 5 invocation points

- Phase 5 wiring: replaced callClaudeApi in Widgets, DecisionRecords,
  RequirementCandidates with resolveAgent + callAgent + token tracking

- llm-connect feature requests: ~/llm-connect/FEATURE_REQUESTS.md
  (FR-1 HTTP serve, FR-2 RoutingPolicy, FR-3 async, FR-4 BudgetTracker)

- GAAF scorecard: 3.61 (up from 3.56); Functional 3.4→3.6, Extensions 3.8→3.9

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-01 20:57:17 +00:00
2605c1c977 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>
2026-03-29 15:54:33 +00:00
878d2577ae feat(P4): IHF Phase 4 complete — Outcome Observation and Antifragility Loop
Some checks failed
Test / test (push) Has been cancelled
Closes the IHF improvement loop. Full antifragility chain now traversable:
Widget → Annotation → Candidate → Requirement → Decision → Deployment → OutcomeSignal

New artifacts:
- DeploymentRecord (immutable, links DecisionRecord to a deployed version)
- OutcomeSignal (append-only; DB trigger prevents UPDATE/DELETE)
- ChangeEvaluation (one-per-deployment; UNIQUE constraint; 1–5 score)

New capabilities:
- DeploymentRecordsController (index, show, new, create)
- RecordOutcomeSignalAction — capture improved/regressed/neutral/inconclusive signals
- Pre/post comparison panel on deployment show (±30-day event/annotation counts)
- Regression detection — improved signal followed by high/critical annotation
- ChangeEvaluation — idempotent score+rationale per deployment
- Recurrence tracking — cycle count per widget, leaderboard
- AntifragilityDashboardAction (autoRefresh, 5 panels) per hub
- Phase 4 integration tests (T01–T08 logic coverage)
- docs/phase4-summary.md; SCOPE.md updated to Phase 4 complete

State Hub: workstream 07e9c860 → completed

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-29 12:27:30 +00:00
7f9a8dd441 feat(P3): IHF Phase 3 complete — Governance and Decision Linkage
Implements the full governance layer:
- Schema: requirements, decision_records, policy_references,
  implementation_change_references; requirement_candidates gets
  requirement_id back-reference
- RequirementsController (index/show; promotion-only create)
- DecisionRecordsController (CRUD + policy/impl ref management)
- GovernanceDashboardAction on HubsController (AutoRefresh)
- PromoteToRequirementAction + LinkToDecisionAction on candidates
- Outcome immutability enforced at controller level (fill excludes outcome)
- Full six-outcome vocabulary with Tailwind color roles
- Integration tests for all Phase 3 paths
- FrontController: registers Phase 2 missing controllers + all Phase 3
- SCOPE.md + docs/phase3-summary.md updated

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-29 10:42:56 +00:00