From 29dad403ec608431dacf5e79f2a46161242eb2a1 Mon Sep 17 00:00:00 2001 From: Mikhail Date: Mon, 24 Aug 2026 01:03:52 +0300 Subject: [PATCH] docs: record gpu timeout after bounded retry --- docs/PROJECT_STATUS.md | 2 +- ...audit-completion-matrix-2026-08-24-v8.json | 12 ++++++++++++ ...u-qualification-runtime-2026-08-24-v2.json | 19 +++++++++++++++++++ 3 files changed, 32 insertions(+), 1 deletion(-) create mode 100644 docs/evidence/audit-completion-matrix-2026-08-24-v8.json create mode 100644 docs/evidence/gpu-qualification-runtime-2026-08-24-v2.json diff --git a/docs/PROJECT_STATUS.md b/docs/PROJECT_STATUS.md index 727368d..071d346 100644 --- a/docs/PROJECT_STATUS.md +++ b/docs/PROJECT_STATUS.md @@ -8,7 +8,7 @@ - `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`. -- `GPU_QUALIFICATION_STATUS = LIVE_UNRATED_TIMEOUT`; Domovoy qualification discovered four exact GPU model IDs and probed them in parallel; the fresh bounded probe timed out for all four at about 10 seconds, so quality remains `UNRATED`, no promotion occurred, and CPU/LIFEBOAT fallback remains authoritative. Evidence: `docs/evidence/gpu-qualification-runtime-2026-08-24-v1.json`. +- `GPU_QUALIFICATION_STATUS = LIVE_UNRATED_TIMEOUT`; after increasing the GPU adapter to a bounded configurable `60s` window, Domovoy probed all four discovered models in parallel and all four still timed out without output. Quality remains `UNRATED`, no promotion occurred, and CPU/LIFEBOAT fallback remains authoritative. Evidence: `docs/evidence/gpu-qualification-runtime-2026-08-24-v2.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. diff --git a/docs/evidence/audit-completion-matrix-2026-08-24-v8.json b/docs/evidence/audit-completion-matrix-2026-08-24-v8.json new file mode 100644 index 0000000..ffcdc5c --- /dev/null +++ b/docs/evidence/audit-completion-matrix-2026-08-24-v8.json @@ -0,0 +1,12 @@ +{ + "evidence_id": "audit-completion-matrix-2026-08-24-v8", + "captured_at": "2026-08-23T22:02:37Z", + "production_revision": "041c1ce", + "supersedes": "docs/evidence/audit-completion-matrix-2026-08-24-v7.json", + "overall_status": "NOT_COMPLETE", + "completed_areas": ["agent execution durable lease/recovery", "bounded independent local agent execution bridge", "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": ["universal generic/Codex Agent Execution capability is unavailable", "GPU upstream did not respond within a 60-second bounded window; quality qualification and promotion remain incomplete", "real mobile authenticated visual acceptance is unavailable in the current browser surface"], + "live_facts": {"healthz": "OK", "cognitive_worker": "OK", "agent_bridge": "READY", "agent_mode": "execution", "agent_capabilities": ["task-evaluation"], "diagnostics": "7/7 OK", "fleet_ready": "3/4", "selected_tier": "FAST", "fallback_tier": "LIFEBOAT", "gpu_timeout_window": "60s"}, + "responsive_guard": "CI PASS: cmd/creator-web responsive regression test", + "secrets": "No secret values included." +} diff --git a/docs/evidence/gpu-qualification-runtime-2026-08-24-v2.json b/docs/evidence/gpu-qualification-runtime-2026-08-24-v2.json new file mode 100644 index 0000000..18e04c8 --- /dev/null +++ b/docs/evidence/gpu-qualification-runtime-2026-08-24-v2.json @@ -0,0 +1,19 @@ +{ + "evidence_id": "gpu-qualification-runtime-2026-08-24-v2", + "captured_at": "2026-08-23T22:02:37Z", + "production_revision": "041c1ce", + "route": "Domovoy cognitive-worker /v1/provider-discovery/gpu/qualify", + "provider": "local-gpu-opportunistic", + "timeout_window": "60s per model, four models in parallel", + "results": [ + {"provider_model_id": "Qwen3.6-27B-UD-Q4_K_XL", "status": "RESPONDED_WITHOUT_QUALIFICATION", "finish_reason": "TIMEOUT", "latency_millis": 60030, "quality_assessed": false, "category": "UNRATED"}, + {"provider_model_id": "Qwen3.8-27B-UD-Q3_K_XL", "status": "RESPONDED_WITHOUT_QUALIFICATION", "finish_reason": "TIMEOUT", "latency_millis": 60030, "quality_assessed": false, "category": "UNRATED"}, + {"provider_model_id": "Qwen3.8-27B-UD-Q4_K_XL", "status": "RESPONDED_WITHOUT_QUALIFICATION", "finish_reason": "TIMEOUT", "latency_millis": 60029, "quality_assessed": false, "category": "UNRATED"}, + {"provider_model_id": "gemma-4-26B-A4B-it-UD-Q2_K_XL", "status": "RESPONDED_WITHOUT_QUALIFICATION", "finish_reason": "TIMEOUT", "latency_millis": 60030, "quality_assessed": false, "category": "UNRATED"} + ], + "diagnosis": "The previous 10-second client deadline was not the sole cause; the GPU upstream produced no bounded response within 60 seconds for any discovered model.", + "routing_effect": "No GPU promotion or priority; FAST remains selected and CPU/LIFEBOAT fallback remains authoritative.", + "runtime_health": {"public_health": "OK", "cognitive_worker": "OK", "agent_bridge": "OK", "agent_worker": "READY"}, + "secrets_exposed": false, + "limitations": ["GPU quality and promotion remain unproven", "upstream GPU service requires separate runtime diagnosis or recovery"] +} -- 2.54.0