docs(evidence): record gpu qualification timeout
This commit is contained in:
@@ -8,6 +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; all four timed out at the bounded 10-second limit, so quality remains `UNRATED`, no promotion occurred, and CPU/LIFEBOAT fallback remains authoritative. Evidence: `docs/evidence/gpu-qualification-runtime-2026-08-23-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.
|
||||
|
||||
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"evidence_id": "gpu-qualification-runtime-2026-08-23-v2",
|
||||
"captured_at": "2026-08-23T21:01:53Z",
|
||||
"production_revision": "1f20685",
|
||||
"source": "Domovoy cognitive-worker bounded qualification route",
|
||||
"provider": "local-gpu-opportunistic",
|
||||
"models_discovered": ["Qwen3.6-27B-UD-Q4_K_XL", "Qwen3.8-27B-UD-Q3_K_XL", "Qwen3.8-27B-UD-Q4_K_XL", "gemma-4-26B-A4B-it-UD-Q2_K_XL"],
|
||||
"results": {"model_count": 4, "statuses": ["RESPONDED_WITHOUT_QUALIFICATION", "RESPONDED_WITHOUT_QUALIFICATION", "RESPONDED_WITHOUT_QUALIFICATION", "RESPONDED_WITHOUT_QUALIFICATION"], "finish_reasons": ["TIMEOUT", "TIMEOUT", "TIMEOUT", "TIMEOUT"], "latency_millis": [10010, 10010, 10010, 10010], "quality_assessed": false, "categories": ["UNRATED", "UNRATED", "UNRATED", "UNRATED"]},
|
||||
"routing_effect": "GPU receives no promotion or priority; FAST remains selected and CPU/LIFEBOAT fallback remains authoritative.",
|
||||
"secrets_exposed": false,
|
||||
"limitations": ["GPU provider did not complete bounded inference, so quality and promotion remain unproven"]
|
||||
}
|
||||
Reference in New Issue
Block a user