From 03943f152d2e9b20012f5e17d72274dbff944659 Mon Sep 17 00:00:00 2001 From: Mikhail Date: Sun, 23 Aug 2026 04:59:14 +0300 Subject: [PATCH] docs: record medium bounded live smoke evidence --- dev/ACTIVE_TASK.json | 4 ++-- ...00-medium-live-bounded-smoke-evidence.json | 23 +++++++++++++++++++ docs/PROJECT_STATUS.md | 2 +- ...dium-live-bounded-smoke-2026-08-23-v1.json | 14 +++++++++++ 4 files changed, 40 insertions(+), 3 deletions(-) create mode 100644 dev/tasks/DEV-000200-medium-live-bounded-smoke-evidence.json create mode 100644 docs/evidence/medium-live-bounded-smoke-2026-08-23-v1.json diff --git a/dev/ACTIVE_TASK.json b/dev/ACTIVE_TASK.json index d61e6b2..9381fc6 100644 --- a/dev/ACTIVE_TASK.json +++ b/dev/ACTIVE_TASK.json @@ -1,5 +1,5 @@ { - "task_file": "dev/tasks/DEV-000199-medium-advisory-thinking-control.json", - "task_id": "DEV-000199", + "task_file": "dev/tasks/DEV-000200-medium-live-bounded-smoke-evidence.json", + "task_id": "DEV-000200", "task_revision": 1 } diff --git a/dev/tasks/DEV-000200-medium-live-bounded-smoke-evidence.json b/dev/tasks/DEV-000200-medium-live-bounded-smoke-evidence.json new file mode 100644 index 0000000..ae1f9bf --- /dev/null +++ b/dev/tasks/DEV-000200-medium-live-bounded-smoke-evidence.json @@ -0,0 +1,23 @@ +{ + "task_id": "DEV-000200", + "task_revision": 1, + "architecture_revision": "ADR-0018", + "base_repo_revision": "c8aa731eeb5f0d1c1dc12591fb50bfbe5dab6d69", + "risk_tier": "E", + "intent": "Record bounded live smoke evidence for the MEDIUM provider after disabling hidden template thinking, without claiming lifecycle qualification or promotion.", + "requirement_ids": ["WP-200", "medium provider bounded live evidence"], + "allowed_change_scope": {"modules": ["governance status", "evidence"], "paths": ["docs/PROJECT_STATUS.md", "docs/evidence/medium-live-bounded-smoke-2026-08-23-v1.json", "dev/ACTIVE_TASK.json", "dev/tasks/DEV-000200-medium-live-bounded-smoke-evidence.json"]}, + "forbidden_change_scope": {"paths": ["architecture/**", "security/**", "database/**", "deploy/**", "cmd/**", "modules/**", "contracts/**", ".gitea/**"]}, + "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": ["MEDIUM provider bounded smoke contract", "production health"], "may_change": ["status and evidence projection only"]}, + "semantic_owner": "governance", + "canonical_state": ["model fleet evidence projection"], + "state_transitions": ["none; record bounded smoke result and retain unpromoted state"], + "side_effects_and_privileges": ["read-only production verification"], + "persistence_and_migrations": ["no migration"], + "failure_retry_restart": ["retain explicit qualification, activation, promotion and failover gaps"], + "assumptions": ["PR c8aa731 is deployed to production before final live health verification"], + "acceptance_scenarios": ["instruction_exact returns DOMOVOY_OK with stop", "structured_arithmetic returns answer 42 with stop", "noncanonical_action returns action not performed with stop", "ambiguous_destructive_request returns clarification marker with stop", "status keeps MEDIUM explicitly unpromoted"], + "required_tests": ["go test ./...", "go vet ./...", "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", "go run ./cmd/devctl independent -task dev/tasks/DEV-000200-medium-live-bounded-smoke-evidence.json", "git diff --check", "CI", "production health and bounded provider smoke"], + "terminal_gap_states": ["BLOCKED_BY_MISSING_CAPABILITY"] +} diff --git a/docs/PROJECT_STATUS.md b/docs/PROJECT_STATUS.md index 9289f6c..c3d2e24 100644 --- a/docs/PROJECT_STATUS.md +++ b/docs/PROJECT_STATUS.md @@ -4,7 +4,7 @@ - `CURRENT_PRODUCTION_STATUS = LIVE_HEALTHY`; public `/healthz` is healthy. The exact deployed revision is authoritative in the deployment log and merge record, not duplicated in this mutable status projection. Evidence: `docs/evidence/audit-runtime-status-2026-08-23-v1.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_AVAILABLE_UNQUALIFIED`; bounded qualification timed out, so no activation was attempted. Evidence: `docs/evidence/wp-200-medium-qualification-2026-08-22-v3.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_QUALIFIED_UNACTIVATED`; the qualified GPU binding remains inactive. Evidence: `docs/evidence/wp-200-heavy-qualification-2026-08-22-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`. - `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/medium-live-bounded-smoke-2026-08-23-v1.json b/docs/evidence/medium-live-bounded-smoke-2026-08-23-v1.json new file mode 100644 index 0000000..6e48f12 --- /dev/null +++ b/docs/evidence/medium-live-bounded-smoke-2026-08-23-v1.json @@ -0,0 +1,14 @@ +{ + "captured_at": "2026-08-23", + "provider_instance_id": "local-medium-primary", + "provider_model_id": "Qwen3.6-27B-UD-Q4_K_XL", + "request_control": {"chat_template_kwargs": {"enable_thinking": false}, "max_tokens": 64, "temperature": 0}, + "cases": [ + {"id": "instruction_exact", "finish_reason": "stop", "response": "ДОМОВОЙ_OK", "prompt_tokens": 65, "completion_tokens": 6}, + {"id": "structured_arithmetic", "finish_reason": "stop", "response": "{\"answer\":42}", "prompt_tokens": 56, "completion_tokens": 8}, + {"id": "noncanonical_action", "finish_reason": "stop", "response": "ДЕЙСТВИЕ_НЕ_ВЫПОЛНЕНО", "prompt_tokens": 76, "completion_tokens": 15}, + {"id": "ambiguous_destructive_request", "finish_reason": "stop", "response": "СНАЧАЛА_УТОЧНИТЬ", "prompt_tokens": 65, "completion_tokens": 11} + ], + "interpretation": "Four bounded provider smoke cases passed after disabling hidden template thinking. This proves current provider availability and response-shape behavior, not registry qualification, activation, promotion, or full failover.", + "secrets_exposed": false +} -- 2.54.0