m/Assistant
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

DEV-000281 Reconcile live generic execution evidence #259

Merged
m merged 1 commits from codex/dev-000248-self-development-runtime-status into main 2026-08-24 00:38:55 +00:00
Conversation 0 Commits 1 Files Changed 4
+52 -9
4 changed files with 52 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
dev/ACTIVE_TASK.json
+2 -2
View File
@@ -1,5 +1,5 @@
{
"task_file": "dev/tasks/DEV-000280-local-generic-agent-execution.json",
"task_id": "DEV-000280",
"task_file": "dev/tasks/DEV-000281-live-generic-agent-execution-evidence.json",
"task_id": "DEV-000281",
"task_revision": 1
}
dev/tasks/DEV-000281-live-generic-agent-execution-evidence.json
+23
View File
@@ -0,0 +1,23 @@
{
"task_id": "DEV-000281",
"task_revision": 1,
"architecture_revision": "ADR-0018",
"base_repo_revision": "080bd44",
"risk_tier": "E",
"intent": "Reconcile production evidence after the generic local Agent Execution rollout.",
"requirement_ids": ["no stale production claims", "generic bridge evidence is explicit", "remaining acceptance gaps remain visible"],
"allowed_change_scope": {"modules": [], "paths": ["dev/ACTIVE_TASK.json", "dev/tasks/DEV-000281-live-generic-agent-execution-evidence.json", "docs/PROJECT_STATUS.md", "docs/evidence/audit-completion-matrix-2026-08-24-v12.json"]},
"forbidden_change_scope": {"paths": ["architecture/**", "security/**", "database/**", "contracts/**", "modules/**", "adapters/**", "cmd/**", "deploy/**", "LLM-local/**"]},
"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 image labels", "agent bridge health", "agent worker readiness", "assistant health"], "may_change": ["audit evidence only"]},
"semantic_owner": "evidence reconciliation",
"canonical_state": ["no runtime state changed"],
"state_transitions": ["live observations -> versioned evidence"],
"side_effects_and_privileges": ["read-only production inspection"],
"persistence_and_migrations": ["documentation only"],
"failure_retry_restart": ["none"],
"assumptions": ["the deployment label is the authoritative runtime revision evidence", "generic candidate output still requires independent graph verification"],
"acceptance_scenarios": ["matrix records 080bd44 production revision", "bridge and worker advertise generic-cognitive-work", "mobile and authenticated chat gaps remain explicit"],
"required_tests": ["go test ./...", "go vet ./...", "preflight", "check-diff", "check-architecture", "independent", "git diff --check", "CI"],
"terminal_gap_states": ["BLOCKED_BY_MISSING_CAPABILITY"]
}
docs/PROJECT_STATUS.md
+7 -7
View File
@@ -7,14 +7,14 @@
- `LAST_COMPLETED = DEV-000260`; the governed self-development path, provider-neutral reachability rating, bounded authenticated operations smoke, responsive static regression guard and deep authenticated acceptance evidence are live. Mobile visual UI remains explicitly unverified because the current browser control surface cannot emulate a 390x844 viewport.
- `CURRENT_PRODUCTION_STATUS = LIVE_HEALTHY`; public `/healthz` is healthy and current project image labels match merged `e4f8d6fa70545410e84f0d7572783aeafc58d288`. Evidence: `docs/evidence/audit-runtime-status-2026-08-24-v1.json`.
- `CURRENT_PRODUCTION_STATUS = LIVE_HEALTHY`; public `/healthz` is healthy and current runtime project labels match merged `080bd440216372770b54bcf93a02bd6fb526e96c`. Evidence: `docs/evidence/audit-completion-matrix-2026-08-24-v12.json`.
- `FAST_PROVIDER_STATUS = LIVE_SMOKE_SUPPORTED`: local CPU gateway authentication is configured through a protected file reference; four bounded local-only advisory cases completed through cognitive-worker. Evidence: `docs/evidence/wp-601-fast-gateway-live-smoke-2026-08-22-v1.json`.
- `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`.
- `EXTERNAL_MODEL_STATUS = DEFERRED_BY_SCOPE`; previous bounded GPU timeout evidence remains historical diagnostic evidence, but no external model is part of the current operating route and no further external probes are planned in this phase.
- `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`.
- `AGENT_EXECUTION_STATUS = LIVE_TYPED_GENERIC_LOCAL_BRIDGE`; production worker and bridge are ready for task-evaluation and generic cognitive work. Generic output is recorded as an unverified Work Graph candidate and still requires independent synthesis before graph success. Evidence: `docs/evidence/audit-completion-matrix-2026-08-24-v12.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-completion-matrix-2026-08-24-v11.json`; current live readiness has MEDIUM and LIFEBOAT ready, FAST and HEAVY unavailable by timeout, MEDIUM selected and LIFEBOAT fallback.
- `FLEET_EXECUTION_EVIDENCE = docs/evidence/audit-completion-matrix-2026-08-24-v12.json`; current live readiness has MEDIUM and LIFEBOAT ready, FAST and HEAVY unavailable by timeout, MEDIUM selected and LIFEBOAT fallback.
- `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`.
- `TRUTH_FIRST_CHAT_STATUS = LIVE_SOURCE_ROUTING`; factual questions require strict semantic routing to optional `WEB_RESEARCH`, and production research smoke returned observed source excerpts with explicit `UNVERIFIED` claim state. Evidence: `docs/evidence/semantic-web-research-routing-2026-08-24-v2.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`.
@@ -22,15 +22,15 @@
- `GOVERNED_SELF_DEVELOPMENT_STATUS = DURABLE_GATE_VERIFIER_AND_TRANSITIONS_LIVE`; Work-owned revisioned gate storage, independent local verification, and authenticated optimistic-concurrency transitions for canary/promotion/rollback are live. Source mutation and external bridge execution remain unclaimed. Evidence: `docs/evidence/governed-development-gate-persistence-2026-08-23-v1.json` and DEV-000254 CI/live-smoke records.
- `UI_AUTHENTICATED_ACCEPTANCE = AUTHENTICATED_QUICK_SMOKE_PASS`; browser-driven smoke completed in the active production session: chat response received, admin login accepted, diagnostics 7/7 passed, operations fleet 4/4 READY, and action history loaded. Deep mutation, delegation-specific and long-running acceptance remain intentionally deferred.
- `CURRENT_UI_SESSION_STATUS = NO_CURRENT_AUTHENTICATED_SESSION`; the historical quick-smoke evidence above is retained, but the current acceptance run has no signed-in browser session, so no new authenticated visual result is claimed. Public cabinet shell and unauthenticated protection were checked separately.
- `AGENT_EXECUTION_BRIDGE_STATUS = LIVE_BOUNDED_LOCAL_BRIDGE`; the independent local bridge reports `healthz=200`, and `agent-worker` reports `mode=execution`, `executor_configured=true`, `ready=true` for `task-evaluation`; unsupported generic work remains durably waiting and is not represented as completed. Evidence: `docs/evidence/agent-execution-bridge-live-2026-08-24-v1.json`.
- `FLEET_READINESS_LIVE = MEDIUM_SELECTED_BY_AVAILABILITY`; the live cognitive worker observed FAST unavailable, MEDIUM available, HEAVY available and LIFEBOAT available; it selected MEDIUM while the configured preference remained FAST. This is routing evidence only, not a quality or promotion claim. Evidence: `docs/evidence/fleet-readiness-live-2026-08-23-v2.json`.
- `AGENT_EXECUTION_BRIDGE_STATUS = LIVE_LOCAL_TYPED_BRIDGE`; the independent local bridge reports `healthz=200` with `task-evaluation` and `generic-cognitive-work`; `agent-worker` reports `mode=execution`, `executor_configured=true`, `ready=true`. Evidence: `docs/evidence/audit-completion-matrix-2026-08-24-v12.json`.
- `FLEET_READINESS_LIVE = MEDIUM_SELECTED_BY_AVAILABILITY`; the latest live readiness endpoint observed FAST unavailable, MEDIUM available, HEAVY unavailable by timeout and LIFEBOAT available; it selected MEDIUM while the configured preference remained FAST. This is routing evidence only, not a quality or promotion claim. Evidence: `docs/evidence/audit-completion-matrix-2026-08-24-v12.json`.
- `UI_AUTHENTICATED_ACCEPTANCE = DEEP_DESKTOP_PASS_WITH_MOBILE_GAP`; deep signed-in browser evidence covers chat reply, diagnostics 7/7 after refresh, fleet/agent/action-history refresh, 3/4 fleet readiness with FAST selected, truthful local executor state and learning/reflection refresh. Static responsive regression guard passed in CI; mobile viewport acceptance is not claimed. Evidence: `docs/evidence/deep-authenticated-acceptance-2026-08-23-v1.json`.
## Current governance checkpoint
- `COMPLETION_MATRIX = docs/evidence/audit-completion-matrix-2026-08-24-v10.json`; current production provenance and authenticated desktop evidence are refreshed; generic agent execution, mobile viewport acceptance and deferred external qualification remain explicit.
- `COMPLETION_MATRIX = docs/evidence/audit-completion-matrix-2026-08-24-v12.json`; generic local bridge rollout is live; independent candidate verification, authenticated chat E2E, mobile viewport acceptance and deferred external qualification remain explicit.
- `ACTIVE_TASK = dev/tasks/DEV-000273-live-audit-status-reconciliation.json revision 1`; this evidence reconciliation does not change runtime behavior or model routing.
- `ACTIVE_TASK = dev/tasks/DEV-000281-live-generic-agent-execution-evidence.json revision 1`; this evidence reconciliation does not change runtime behavior or model routing.
- `LINEAGE_DECISION = docs/GOVERNANCE_LINEAGE_DECISION_2026-08-22.md`; historical packets remain provenance and are not current authority.
- `REGISTRY_STATUS = YAML and JSON semantic mirrors agree`
- `PRODUCTION_DOMAIN = docker.cin.su`; shared docker-test is not used for this project.
docs/evidence/audit-completion-matrix-2026-08-24-v12.json
+20
View File
@@ -0,0 +1,20 @@
{
"evidence_id": "audit-completion-matrix-2026-08-24-v12",
"captured_at": "2026-08-24T00:34:00Z",
"production_revision": "080bd440216372770b54bcf93a02bd6fb526e96c",
"supersedes": "docs/evidence/audit-completion-matrix-2026-08-24-v11.json",
"overall_status": "NOT_COMPLETE",
"completed_areas": ["durable Agent Execution lease/heartbeat/recovery", "bounded local task-evaluation bridge", "typed local generic cognitive specialist bridge", "multi-agent Work Graph fan-out/fan-in foundation", "Truth/Research runtime and source-backed routing", "Learning reflection loop", "governed self-development gate and verifier", "local-first model routing", "production rollout and live runtime health"],
"remaining_gaps": ["generic candidate still requires an independent verifier/synthesis before graph success", "authenticated chat end-to-end research response was not exercised in this session", "real mobile authenticated visual acceptance is unavailable", "external model qualification and promotion remain deferred by explicit scope"],
"live_facts": {
"assistant_healthz": "OK",
"runtime_project_revision": "080bd440216372770b54bcf93a02bd6fb526e96c",
"bridge": {"status": "ok", "capabilities": ["task-evaluation", "generic-cognitive-work"]},
"agent_worker": {"ready": true, "executor_configured": true, "mode": "execution", "capabilities": ["task-evaluation", "generic-cognitive-work"], "last_result": "idle"},
"fleet": {"ready_tiers": ["MEDIUM", "LIFEBOAT"], "selected_tier": "MEDIUM", "fallback_tier": "LIFEBOAT", "fast_ready": false, "heavy_ready": false},
"mobile_viewport_verified": false,
"authenticated_chat_e2e_verified": false,
"external_probe_required": false,
"secrets": "No secret values included."
}
}