{ "schema_version": "service_health_gap_matrix_v1", "generated_at": "2026-06-05T14:05:00+08:00", "program_status": { "overall_completion_percent": 100, "current_priority": "P1", "current_task_id": "P1-005", "next_task_id": "P1-006", "read_only_mode": true }, "source_refs": [ "docs/schemas/service_health_gap_matrix_v1.schema.json", "docs/reference/SERVICE-ENDPOINTS.md", "scripts/health_check_session.sh", "docs/reference/ALERT-TAXONOMY-CATALOG.md", "apps/api/src/core/config.py", "apps/api/src/api/v1/health.py", "apps/api/src/services/ai_provider_route_matrix.py", "docs/evaluations/ai_provider_route_matrix_2026-06-05.json", "docs/evaluations/observability_contract_matrix_2026-06-05.json", "docs/evaluations/gitea_workflow_runner_health_2026-06-05.json", "k8s/awoooi-prod/05-deployment-web.yaml", "apps/api/src/services/metrics_service.py", "apps/api/src/services/ai_providers/ollama.py", "apps/api/src/services/ai_providers/openclaw_nemo.py", "scripts/ops/backup-health-textfile-exporter.py", "docs/ai/AI_AGENT_AUTOMATION_WORKLIST_2026-06-04.md" ], "rollups": { "total_targets": 10, "by_kind": { "api_health": 1, "web_health": 1, "ai_provider_health": 2, "observability_health": 3, "devops_health": 1, "backup_health": 1, "security_edge_health": 1 }, "by_status": { "verified": 5, "action_required": 5 }, "by_freshness_status": { "fresh_readback": 1, "manifest_mapped": 1, "source_mismatch": 3, "committed_health_hook": 1, "stale_evidence": 1, "committed_exporter": 1, "source_heartbeat_contract": 1, "manifest_only": 1 }, "target_ids_requiring_action": [ "gitea_workflow_runner_health_contract", "kali_scanner_health_reference", "ollama_three_layer_health_contract", "openclaw_health_endpoint_contract", "prometheus_alertmanager_endpoint_reference" ], "health_gap_ids": [ "endpoint_reference_stale_hosts", "gitea_runner_attestation_health_gap", "health_check_script_not_authoritative", "openclaw_nemo_rca_health_review", "security_scanner_health_evidence_gap" ], "stale_endpoint_ids": [ "legacy_188_ollama_provider_endpoint", "openclaw_8088_comment_vs_8089_contract", "prometheus_alertmanager_110_188_split" ], "critical_target_ids": [ "ollama_three_layer_health_contract", "openclaw_health_endpoint_contract", "production_api_health_public", "gitea_workflow_runner_health_contract" ], "read_only_denials_total": 10, "service_restart_allowed_count": 0, "endpoint_change_allowed_count": 0, "active_probe_allowed_count": 0, "notification_send_allowed_count": 0, "runtime_execution_allowed_count": 0 }, "service_health_targets": [ { "target_id": "production_api_health_public", "display_name": "Production API Health", "kind": "api_health", "status": "verified", "risk_level": "critical", "freshness_status": "fresh_readback", "health_contract": "`/api/v1/health` 是正式環境健康讀回入口,回傳 PostgreSQL / Redis / Ollama / OpenClaw / SigNoz 等 component 狀態與 `mock_mode=false`。", "endpoint_contract": "正式站以 `https://awoooi.wooo.work/api/v1/health` 讀回;P1-005 只記錄現有讀回形狀,不新增 probe。", "evidence_refs": [ "apps/api/src/api/v1/health.py", "docs/LOGBOOK.md", "docs/runbooks/AWOOOP-RLS-CANARY-WAVE1.md" ], "next_action": "P1-006 只把健康證據卡顯示到 UI;不得把讀回成功解讀成可重啟或改 endpoint。" }, { "target_id": "awoooi_web_health_manifest", "display_name": "AWOOOI Web /api/health", "kind": "web_health", "status": "verified", "risk_level": "high", "freshness_status": "manifest_mapped", "health_contract": "Web deployment liveness / readiness / startup probe 皆指向 `/api/health`。", "endpoint_contract": "只讀 K8s manifest;不 patch deployment、不 rollout restart、不改 public URL。", "evidence_refs": [ "k8s/awoooi-prod/05-deployment-web.yaml" ], "next_action": "P1-006 顯示 manifest health contract;任何 probe path 變更需另開部署批准。" }, { "target_id": "ollama_three_layer_health_contract", "display_name": "Ollama 三層健康合約", "kind": "ai_provider_health", "status": "action_required", "risk_level": "critical", "freshness_status": "source_mismatch", "health_contract": "目前 AI provider route truth 是 GCP-A → GCP-B → 111;Gemini 只作 final fallback。", "endpoint_contract": "`SERVICE-ENDPOINTS.md` 仍有 188 Ollama 參考,`scripts/health_check_session.sh` 又檢查 111 / 110;需把 endpoint truth 收斂為 owner-attested source,不可直接改路由。", "evidence_refs": [ "docs/reference/SERVICE-ENDPOINTS.md", "scripts/health_check_session.sh", "docs/evaluations/ai_provider_route_matrix_2026-06-05.json", "apps/api/src/services/ai_providers/ollama.py" ], "next_action": "只開 health evidence card 與 endpoint truth review;不得改 `OLLAMA_*`、不重啟 Ollama、不做 live benchmark。" }, { "target_id": "openclaw_health_endpoint_contract", "display_name": "OpenClaw 健康端點合約", "kind": "ai_provider_health", "status": "action_required", "risk_level": "critical", "freshness_status": "source_mismatch", "health_contract": "OpenClaw 仍是生產仲裁核心;health check 使用 `OPENCLAW_URL/health`。", "endpoint_contract": "`SERVICE-ENDPOINTS.md` 已標 8089,但 `openclaw_nemo.py` 註解仍殘留 8088;需收斂註解與 runbook truth。", "evidence_refs": [ "docs/reference/SERVICE-ENDPOINTS.md", "apps/api/src/services/ai_providers/openclaw_nemo.py", "docs/evaluations/ai_provider_route_matrix_2026-06-05.json" ], "next_action": "只提出 source cleanup;不得重啟 OpenClaw、不得把 health gap 當成替換 OpenClaw 批准。" }, { "target_id": "prometheus_alertmanager_endpoint_reference", "display_name": "Prometheus / Alertmanager 端點參考", "kind": "observability_health", "status": "action_required", "risk_level": "high", "freshness_status": "source_mismatch", "health_contract": "Prometheus / Alertmanager 只允許 read-only readiness evidence;Alertmanager 仍必須走 AWOOOI API,不得指向 OpenClaw receiver。", "endpoint_contract": "`SERVICE-ENDPOINTS.md` 記錄 188:9090 / 9093,`health_check_session.sh` 檢查 110:9090 / 9093;需要 owner attestation。", "evidence_refs": [ "docs/reference/SERVICE-ENDPOINTS.md", "scripts/health_check_session.sh", "docs/evaluations/observability_contract_matrix_2026-06-05.json" ], "next_action": "P1-006 顯示 source mismatch;不得改 alert rule、receiver、route 或 silence。" }, { "target_id": "signoz_clickhouse_health_contract", "display_name": "SigNoz / ClickHouse 健康合約", "kind": "observability_health", "status": "verified", "risk_level": "high", "freshness_status": "committed_health_hook", "health_contract": "metrics service 有 ClickHouse health check;observability matrix 已把 SigNoz / ClickHouse 視為 committed evidence。", "endpoint_contract": "只讀 committed health hook 與 matrix;不改 SigNoz query、不改 ClickHouse datasource。", "evidence_refs": [ "apps/api/src/services/metrics_service.py", "docs/evaluations/observability_contract_matrix_2026-06-05.json" ], "next_action": "後續若要 live query,需另開批准;P1-005 只呈現 committed evidence。" }, { "target_id": "sentry_source_health_contract", "display_name": "Sentry Source Health", "kind": "observability_health", "status": "verified", "risk_level": "medium", "freshness_status": "source_heartbeat_contract", "health_contract": "Source provider heartbeat 與 upstream canary 已被 observability matrix 納入來源證據;P1-005 不呼叫 Sentry API。", "endpoint_contract": "只讀 source-link / heartbeat contract;不改 webhook、不讀 Sentry token。", "evidence_refs": [ "docs/evaluations/observability_contract_matrix_2026-06-05.json", "docs/reference/SERVICE-ENDPOINTS.md" ], "next_action": "P1-006 顯示 source heartbeat contract;token / webhook 變更需另行批准。" }, { "target_id": "gitea_workflow_runner_health_contract", "display_name": "Gitea Workflow / Runner Health", "kind": "devops_health", "status": "action_required", "risk_level": "critical", "freshness_status": "stale_evidence", "health_contract": "Gitea workflow runner health matrix 已完成,但 runner owner attestation gap 仍需處置。", "endpoint_contract": "只讀 Gitea workflow / runner snapshot;不重啟 runner、不停止 container、不觸發 workflow。", "evidence_refs": [ "docs/evaluations/gitea_workflow_runner_health_2026-06-05.json", "docs/LOGBOOK.md" ], "next_action": "保留 owner attestation 待補;不得用 P1-005 觸發 Gitea Actions 或 runner mutation。" }, { "target_id": "backup_health_exporter_freshness", "display_name": "Backup Health Exporter Freshness", "kind": "backup_health", "status": "verified", "risk_level": "high", "freshness_status": "committed_exporter", "health_contract": "backup health textfile exporter 已定義 backup freshness、restore drill freshness、offsite freshness 與 escrow freshness metrics。", "endpoint_contract": "只讀 exporter contract;不執行 backup / restore / offsite sync,不寫 credential marker。", "evidence_refs": [ "scripts/ops/backup-health-textfile-exporter.py", "docs/evaluations/backup_dr_readiness_matrix_2026-06-04.json", "docs/evaluations/offsite_escrow_readiness_status_2026-06-05.json" ], "next_action": "維持成功不洗版;失敗或 stale 才進 P1-007 通知合約。" }, { "target_id": "kali_scanner_health_reference", "display_name": "Kali Scanner Health Reference", "kind": "security_edge_health", "status": "action_required", "risk_level": "medium", "freshness_status": "manifest_only", "health_contract": "`SERVICE-ENDPOINTS.md` 記錄 Kali Scanner `192.168.0.112:8080`,但 P1-005 不做 live probe。", "endpoint_contract": "只讀服務端點參考;不啟動掃描、不呼叫 scanner、不改 host 服務。", "evidence_refs": [ "docs/reference/SERVICE-ENDPOINTS.md", "docs/LOGBOOK.md" ], "next_action": "P1-006 僅顯示需 owner attestation;真正掃描健康檢查需另行批准。" } ], "health_gaps": [ { "gap_id": "endpoint_reference_stale_hosts", "display_name": "端點參考存在主機 truth drift", "status": "action_required", "severity": "high", "summary": "服務端點文件、health script、AI provider route matrix 對 Ollama / Prometheus / Alertmanager / OpenClaw 的主機來源不完全一致。", "target_ids": [ "ollama_three_layer_health_contract", "openclaw_health_endpoint_contract", "prometheus_alertmanager_endpoint_reference" ], "evidence_refs": [ "docs/reference/SERVICE-ENDPOINTS.md", "scripts/health_check_session.sh", "docs/evaluations/ai_provider_route_matrix_2026-06-05.json" ], "next_action": "建立 owner attestation / source cleanup,不直接改 endpoint。" }, { "gap_id": "gitea_runner_attestation_health_gap", "display_name": "Runner 健康仍缺 owner attestation", "status": "action_required", "severity": "high", "summary": "P1-002 已列 runner attestation gap;P1-005 只把它納入 service health 缺口,不觸發 runner 操作。", "target_ids": [ "gitea_workflow_runner_health_contract" ], "evidence_refs": [ "docs/evaluations/gitea_workflow_runner_health_2026-06-05.json" ], "next_action": "由 P1-006 顯示,P1-007 才定義失敗限定通知。" }, { "gap_id": "health_check_script_not_authoritative", "display_name": "健康檢查腳本不是唯一真相來源", "status": "proposal_required", "severity": "medium", "summary": "`scripts/health_check_session.sh` 可供人工會前檢查,但它與正式 K8s / public health / provider matrix 的 truth chain 需對齊。", "target_ids": [ "production_api_health_public", "prometheus_alertmanager_endpoint_reference", "kali_scanner_health_reference" ], "evidence_refs": [ "scripts/health_check_session.sh", "docs/reference/SERVICE-ENDPOINTS.md" ], "next_action": "只產生 P1-006 顯示與後續 runbook cleanup 提案。" }, { "gap_id": "openclaw_nemo_rca_health_review", "display_name": "OpenClaw / Nemo RCA 健康仍需複核", "status": "action_required", "severity": "high", "summary": "AI provider route matrix 將 OpenClaw Nemo RCA lane 標為需處置;P1-005 不改 provider,只列健康缺口。", "target_ids": [ "openclaw_health_endpoint_contract" ], "evidence_refs": [ "docs/evaluations/ai_provider_route_matrix_2026-06-05.json", "apps/api/src/services/ai_providers/openclaw_nemo.py" ], "next_action": "用 replay / smoke 證據補強,不把 health review 當作 OpenClaw 替換批准。" }, { "gap_id": "security_scanner_health_evidence_gap", "display_name": "Kali scanner 只有 endpoint reference", "status": "proposal_required", "severity": "medium", "summary": "Security edge 目前只有服務端點參考,缺少 committed health contract 或 owner attestation。", "target_ids": [ "kali_scanner_health_reference" ], "evidence_refs": [ "docs/reference/SERVICE-ENDPOINTS.md" ], "next_action": "後續建立 read-only scanner health evidence card;不得啟動掃描。" } ], "stale_endpoints": [ { "endpoint_id": "legacy_188_ollama_provider_endpoint", "display_name": "legacy 188 Ollama endpoint reference", "status": "action_required", "severity": "high", "stale_ref": "`docs/reference/SERVICE-ENDPOINTS.md` 仍列 `192.168.0.188:11434` 為 Ollama。", "current_truth": "P1-004 provider route truth 是 GCP-A → GCP-B → 111;188 不再作為 AWOOOI Ollama provider。", "evidence_refs": [ "docs/reference/SERVICE-ENDPOINTS.md", "docs/evaluations/ai_provider_route_matrix_2026-06-05.json", "apps/api/src/services/ai_providers/ollama.py" ], "next_action": "準備 source cleanup 批准包;不得改 `OLLAMA_URL` 或重啟 Ollama。" }, { "endpoint_id": "prometheus_alertmanager_110_188_split", "display_name": "Prometheus / Alertmanager 110 與 188 參考分裂", "status": "action_required", "severity": "medium", "stale_ref": "`SERVICE-ENDPOINTS.md` 使用 188,`health_check_session.sh` 使用 110。", "current_truth": "P1-005 只判定為 source mismatch,需要 owner attestation;不判定 live service down。", "evidence_refs": [ "docs/reference/SERVICE-ENDPOINTS.md", "scripts/health_check_session.sh", "docs/evaluations/observability_contract_matrix_2026-06-05.json" ], "next_action": "只補 truth owner;不得改 Alertmanager route 或 receiver。" }, { "endpoint_id": "openclaw_8088_comment_vs_8089_contract", "display_name": "OpenClaw 8088 註解與 8089 合約不一致", "status": "action_required", "severity": "medium", "stale_ref": "`openclaw_nemo.py` 註解仍提到 `192.168.0.188:8088`。", "current_truth": "`SERVICE-ENDPOINTS.md` 與設定使用 OpenClaw 8089;P1-005 只標記註解 / runbook drift。", "evidence_refs": [ "apps/api/src/services/ai_providers/openclaw_nemo.py", "docs/reference/SERVICE-ENDPOINTS.md", "apps/api/src/core/config.py" ], "next_action": "後續 source cleanup 不得改 provider route 或降級 OpenClaw。" } ], "latest_observations": [ { "observation_id": "service_health_gap_matrix_seed", "status": "verified", "summary": "P1-005 只讀收斂 committed health / endpoint / stale evidence;不做 live probe。", "evidence_refs": [ "docs/reference/SERVICE-ENDPOINTS.md", "docs/evaluations/ai_provider_route_matrix_2026-06-05.json", "docs/evaluations/observability_contract_matrix_2026-06-05.json" ] }, { "observation_id": "active_probe_denied", "status": "preserved", "summary": "本矩陣沒有呼叫任何內網、外部 provider、Sentry、SigNoz、Gitea 或 scanner health endpoint。", "evidence_refs": [ "docs/HARD_RULES.md", "docs/ai/AI_AGENT_AUTOMATION_WORKLIST_2026-06-04.md" ] } ], "operator_contract": { "display_mode": "read_only_service_health_gap_matrix", "must_not_interpret_as": [ "服務重啟批准", "endpoint 修改批准", "active probe 批准", "live health check 已執行", "Secret payload 已讀取或可輸出", "Telegram 成功通知批准", "workflow / deploy / reload 觸發批准", "provider 切換批准", "runtime execution 授權", "OpenClaw 取代或降級批准" ], "secret_display_policy": "只顯示來源檔案與 env var 名稱,不輸出 secret payload。", "restart_policy": "P1-005 只能列缺口;任何 service / pod / host restart 都需另行批准。", "endpoint_policy": "P1-005 不修改端點、不改 ConfigMap、不改 public URL,只提出 source truth cleanup。", "notification_policy": "成功 smoke 不通知;只有失敗、stale、action-required 才進 P1-007 通知合約。" }, "operation_boundaries": { "read_only_api_allowed": true, "service_restart_allowed": false, "pod_restart_allowed": false, "host_restart_allowed": false, "rollout_restart_allowed": false, "endpoint_change_allowed": false, "configmap_patch_allowed": false, "active_probe_allowed": false, "external_health_probe_allowed": false, "live_benchmark_allowed": false, "provider_switch_allowed": false, "paid_api_call_allowed": false, "secret_read_allowed": false, "secret_plaintext_allowed": false, "notification_send_allowed": false, "workflow_trigger_allowed": false, "deploy_trigger_allowed": false, "reload_trigger_allowed": false, "runtime_execution_allowed": false }, "approval_boundaries": { "service_restart_approved": false, "endpoint_change_approved": false, "configmap_patch_approved": false, "active_probe_approved": false, "secret_read_approved": false, "notification_send_approved": false, "workflow_trigger_approved": false, "provider_switch_approved": false, "cost_change_approved": false } }