docs(fleet): record CPU to lifeboat failover #217

Merged
m merged 1 commits from codex/dev-000240-cpu-lifeboat-failover-evidence into main 2026-08-23 16:07:32 +00:00
3 changed files with 40 additions and 2 deletions
+2 -2
View File
@@ -1,5 +1,5 @@
{
"task_file": "dev/tasks/DEV-000239-stable-provider-resolution.json",
"task_id": "DEV-000239",
"task_file": "dev/tasks/DEV-000240-cpu-lifeboat-failover-evidence.json",
"task_id": "DEV-000240",
"task_revision": 1
}
@@ -0,0 +1,23 @@
{
"task_id": "DEV-000240",
"task_revision": 1,
"architecture_revision": "ADR-0018",
"base_repo_revision": "383d4c6e4fd53bb0c34ed358e0d1be6a416da6cc",
"risk_tier": "E",
"intent": "Record live durable evidence of CPU model failure followed by successful local Lifeboat failover after stable provider resolution was deployed.",
"requirement_ids": ["model fleet/failover", "durable usage evidence", "false completion prevention"],
"allowed_change_scope": {"modules": ["evidence"], "paths": ["docs/evidence/cpu-lifeboat-failover-2026-08-23-v1.json", "dev/ACTIVE_TASK.json", "dev/tasks/DEV-000240-cpu-lifeboat-failover-evidence.json"]},
"forbidden_change_scope": {"paths": ["architecture/**", "security/**", "database/**", "deploy/**", "LLM-local/**", "modules/work/secrets/**", "contracts/**"]},
"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": ["cognitive advisory gateway", "cognitive usage observations"], "may_change": []},
"semantic_owner": "Evidence only",
"canonical_state": ["no runtime state mutation; evidence captures existing durable observations"],
"state_transitions": ["CPU MODEL_UNAVAILABLE -> builtin local Lifeboat COMPLETED"],
"side_effects_and_privileges": ["bounded LOCAL_ONLY advisory request; no external egress"],
"persistence_and_migrations": ["existing usage observation persistence only"],
"failure_retry_restart": ["the fallback is selected within the bounded gateway request"],
"assumptions": ["provider_instance_id and result_class in capability usage observations are authoritative route attribution"],
"acceptance_scenarios": ["primary failure is durably observed", "fallback completion is durably observed", "HTTP gateway returns COMPLETED", "public health remains OK"],
"required_tests": ["go test ./cmd/cognitive-worker/...", "go vet ./cmd/cognitive-worker/...", "go run ./cmd/devctl preflight -active dev/ACTIVE_TASK.json", "go run ./cmd/devctl check-diff -active dev/ACTIVE_TASK.json", "go run ./cmd/devctl check-architecture", "git diff --check", "independent", "CI", "production health smoke"],
"terminal_gap_states": ["BLOCKED_BY_MISSING_CAPABILITY", "BLOCKED_BY_SPEC_GAP"]
}
@@ -0,0 +1,15 @@
{
"evidence_id": "cpu-lifeboat-failover-2026-08-23-v1",
"observed_at": "2026-08-23",
"production_revision": "383d4c6e4fd53bb0c34ed358e0d1be6a416da6cc",
"request": {"surface": "internal cognitive-worker advisory gateway", "data_policy": "LOCAL_ONLY", "max_output_bytes": 128, "prompt_class": "bounded readiness response"},
"http_result": {"status": 200, "finish_reason": "COMPLETED", "output_observed": true},
"durable_route_observations": [
{"provider_instance_id": "local-cpu-primary", "result_class": "MODEL_UNAVAILABLE", "failure_type": "MODEL_UNAVAILABLE", "latency_millis": 580},
{"provider_instance_id": "builtin-local-lifeboat-v1", "result_class": "COMPLETED", "failure_type": null, "latency_millis": 455}
],
"public_health": {"url": "https://assistant.cin.su/healthz", "status": 200, "runtime": "creator-web"},
"status": "CPU_TO_LIFEBOAT_FAILOVER_LIVE_PASS",
"secrets_exposed": false,
"remaining": ["medium/GPU validated multi-model failover", "quality-based promotion", "long-running failover and restart chaos"]
}