dev/ACTIVE_TASK.json

@@ -1,5 +1,5 @@
 {
-  "task_file": "dev/tasks/DEV-000261-durable-additional-task-evaluation-scheduling.json",
-  "task_id": "DEV-000261",
+  "task_file": "dev/tasks/DEV-000262-additional-evaluation-live-evidence.json",
+  "task_id": "DEV-000262",
   "task_revision": 1
 }

dev/tasks/DEV-000262-additional-evaluation-live-evidence.json

@@ -0,0 +1,23 @@
+{
+  "task_id": "DEV-000262",
+  "task_revision": 1,
+  "architecture_revision": "ADR-0018",
+  "base_repo_revision": "b789878",
+  "risk_tier": "E",
+  "intent": "Record production evidence for the deployed adaptive additional task-evaluation scheduling hand-off.",
+  "requirement_ids": ["auditable model qualification lifecycle", "production runtime evidence"],
+  "allowed_change_scope": {"modules": ["governance-documentation"], "paths": ["docs/evidence/additional-evaluation-runtime-live-2026-08-23-v1.json", "docs/PROJECT_STATUS.md", "docs/evidence/audit-completion-matrix-2026-08-23-v5.json", "dev/ACTIVE_TASK.json", "dev/tasks/DEV-000262-additional-evaluation-live-evidence.json"]},
+  "forbidden_change_scope": {"paths": ["architecture/**", "security/**", "database/**", "deploy/**", "contracts/**", "LLM-local/**", "cmd/**", "modules/**", "adapters/**"]},
+  "allowed_architecture_delta": {"new_cross_module_dependencies": 0, "new_canonical_owners": 0, "new_privileges": 0, "new_third_party_dependencies": 0, "new_database_owner_roles": 0},
+  "contracts": {"consume": ["production work-graph health/readiness and route response"], "may_change": ["status projection only"]},
+  "semantic_owner": "Governance evidence projection",
+  "canonical_state": ["none"],
+  "state_transitions": ["none"],
+  "side_effects_and_privileges": ["documentation-only; live probe used rejected empty request"],
+  "persistence_and_migrations": ["none"],
+  "failure_retry_restart": ["historical evidence remains immutable; status projection can be refreshed"],
+  "assumptions": ["route validation is not proof of a successful graph mutation"],
+  "acceptance_scenarios": ["production work-graph health is OK", "readiness reports PostgreSQL available", "additional scheduling route rejects incomplete payload with 422", "no secret value appears"],
+  "required_tests": ["go test ./cmd/creator-web", "go vet ./cmd/creator-web", "go run ./cmd/devctl preflight -active dev/ACTIVE_TASK.json", "go run ./cmd/devctl check-diff -active dev/ACTIVE_TASK.json", "independent evidence review", "git diff --check", "CI", "production health smoke"],
+  "terminal_gap_states": ["BLOCKED_BY_MISSING_CAPABILITY", "BLOCKED_BY_SPEC_GAP"]
+}

docs/PROJECT_STATUS.md

@@ -9,6 +9,7 @@
 - `MEDIUM_PROVIDER_STATUS = LIVE_BOUNDED_SMOKE_SUPPORTED_UNPROMOTED`; four bounded local-provider cases passed with template thinking disabled. This is availability/response-shape evidence only; lifecycle qualification, activation and promotion remain unclaimed. Evidence: `docs/evidence/medium-live-bounded-smoke-2026-08-23-v1.json`.
 - `HEAVY_PROVIDER_STATUS = LIVE_BOUNDED_INVOCATION_SUPPORTED_UNPROMOTED`; the exact Domovoy adapter payload produced one bounded Qwen completion in 0.583s. Quality is not assessed, lifecycle promotion is not performed, and GPU availability is not treated as intelligence or routing priority. Evidence: `docs/evidence/gpu-discovery-2026-08-23-v1.json`, `docs/evidence/gpu-invocation-qualification-2026-08-23-v1.json`.
 - `AGENT_EXECUTION_STATUS = DURABLE_DRY_RUN_CANARY_VERIFIED`; the explicit production canary persisted a dispatch intent, an ACTIVE lease and callback head sequence 2. No independently operated bridge endpoint is configured, so bridge-backed execution remains unavailable. Evidence: `docs/evidence/agent-execution-dry-run-canary-2026-08-23-v1.json`.
+- `ADDITIONAL_EVALUATION_STATUS = LIVE_TYPED_HANDOFF`; Capability-owned unresolved evaluation decisions can now be handed to Work through a typed production endpoint. Work preserves parent evidence lineage and schedules the bounded additional profile through the existing durable graph/dispatch path; model/provider selection remains outside Work. Evidence: `docs/evidence/additional-evaluation-runtime-live-2026-08-23-v1.json` and DEV-000261.
 - `FLEET_EXECUTION_EVIDENCE = docs/evidence/audit-runtime-status-2026-08-23-v1.json`; FAST, MEDIUM and LIFEBOAT are ready, HEAVY is explicitly degraded by provider timeout, FAST remains preferred/selected, and LIFEBOAT is the fallback tier.
 - `TRUTH_RESEARCH_STATUS = LIVE_CANARY_PERSISTED`; the web research canary preserved an OBSERVED/COMPLETE/NO-CONFLICT source chain while leaving the claim UNVERIFIED and belief PROVISIONAL. Evidence: `docs/evidence/truth-runtime-canary-2026-08-23-v1.json`.
 - `LEARNING_REFLECTION_STATUS = LIVE_RECONCILED`; reflection worker returned no pending candidate and the durable state contains 31 RESOLVED candidates with no OPEN backlog. Evidence: `docs/evidence/reflection-runtime-reconciliation-2026-08-23-v1.json`.

docs/evidence/additional-evaluation-runtime-live-2026-08-23-v1.json

@@ -0,0 +1,13 @@
+{
+  "evidence_id": "additional-evaluation-runtime-live-2026-08-23-v1",
+  "captured_at": "2026-08-23T20:00:00Z",
+  "production_main_revision": "b789878",
+  "runtime": "work-graph-runtime",
+  "health": {"healthz": "OK", "readyz": "READY", "work_postgres": "AVAILABLE"},
+  "route": {"path": "/v1/work-graphs/task-evaluations/additional/schedule", "empty_payload_status": 422, "typed_validation": "PASS"},
+  "behavior": "Capability-owned additional profile/cases are handed to Work, which preserves parent evidence lineage and uses existing durable graph admission and dispatch queue paths.",
+  "provider_selection": "not performed by Work; Capability remains the decision owner",
+  "mutations_performed": false,
+  "secrets_exposed": false,
+  "limitations": ["No live additional graph mutation was created; production route was validated with a rejected empty payload", "independent external Agent Execution bridge, GPU quality promotion and mobile visual acceptance remain open gaps"]
+}

docs/evidence/audit-completion-matrix-2026-08-23-v5.json

@@ -4,7 +4,7 @@
   "production_revision": "d4b541612647acd826477c8cbea2bc9976049f03",
   "supersedes": "docs/evidence/audit-completion-matrix-2026-08-23-v4.json",
   "overall_status": "NOT_COMPLETE",
-  "completed_areas": ["agent execution local recovery", "multi-agent work graph", "truth/research runtime", "learning reflection loop", "model availability/failover and reachability rating", "governed gate verification/transitions", "authenticated desktop operations fast smoke", "responsive static regression guard"],
+  "completed_areas": ["agent execution local recovery", "multi-agent work graph", "truth/research runtime", "learning reflection loop", "model availability/failover and reachability rating", "adaptive additional task evaluation scheduling", "governed gate verification/transitions", "authenticated desktop operations fast smoke", "responsive static regression guard"],
   "remaining_gaps": ["independently operated Agent Execution bridge is unavailable", "GPU quality qualification and promotion remain incomplete", "real mobile authenticated visual acceptance is unavailable in the current browser surface"],
   "live_facts": {"healthz": "OK", "diagnostics": "7/7 OK", "fleet_ready": "3/4", "selected_tier": "FAST", "fallback_tier": "LIFEBOAT", "agent_mode": "local-fallback"},
   "responsive_guard": "CI PASS: cmd/creator-web responsive regression test",