fix(sre): close bounded runtime contract gaps

docs/operations/portfolio-infrastructure-asset-reconciliation.snapshot.json

@@ -122,7 +122,7 @@
         "next_action": "Resolve exact database/container/port identity, collect read-only health and backup freshness, then create bounded DB verifier work."
       },
       "members": [
-        {"canonical_id": "database:awoooi:prod", "inventory_labels": ["awoooi_prod"], "source_rows": ["L025"], "runtime_identity": "host188/postgresql/awoooi_prod", "reconciliation_state": "identity_scope_conflict", "findings": ["Inventory combines AWOOOI business database and K3s datastore into one purpose", "Canonical service registry names the container postgres, not awoooi_prod"], "source_refs": ["ops/config/service-registry.yaml", "scripts/backup/backup-awoooi.sh"], "product_id": "awoooi", "project_id": "awoooi", "backup_restore": {"mode": "critical_read_only_default", "target": "scripts/backup/backup-awoooi.sh", "freshness": "unverified"}},
+        {"canonical_id": "database:awoooi:prod", "inventory_labels": ["awoooi_prod"], "source_rows": ["L025"], "runtime_identity": "host188/postgresql/awoooi_prod", "reconciliation_state": "identity_scope_conflict", "findings": ["Inventory combines AWOOOI business database and K3s datastore into one purpose", "Canonical service registry names the container postgres, not awoooi_prod", "The fixed telegram_receipt_index_apply_v1 DB executor is source-ready but has no production same-run apply and independent verifier receipt"], "source_refs": ["ops/config/service-registry.yaml", "scripts/backup/backup-awoooi.sh", "apps/api/src/services/db_bounded_executor.py", "agent99-db-bounded-executor.ps1"], "product_id": "awoooi", "project_id": "awoooi", "owner_lane": "database_ops", "domain_router": "database", "executor": "db_bounded_executor", "verifier": "db_independent_verifier", "bounded_command": {"command_id": "telegram_receipt_index_apply_v1", "canonical_asset": "public.awooop_outbound_message", "execution_hub": "host:192.168.0.99", "transport": "host99_to_host110_to_host120_fixed_sudo_kubectl_exec", "cross_domain_fallback_allowed": false, "runtime_status": "source_ready_runtime_pending"}, "backup_restore": {"mode": "critical_read_only_default", "target": "scripts/backup/backup-awoooi.sh", "freshness": "unverified"}},
         {"canonical_id": "database:momo-pro:postgres", "inventory_labels": ["momo-db"], "source_rows": ["L026"], "runtime_identity": "host188/docker/momo-db", "reconciliation_state": "matched_source_runtime_unverified", "findings": ["Exact exposed port and database name are not proven by the inventory row"], "source_refs": ["ops/config/service-registry.yaml", "scripts/backup/backup-momo.sh"], "product_id": "momo-pro", "project_id": "momo-pro-system", "owner_lane": "momo_product_ops", "telegram_destination": "blocked:momo_configured_chat_unresolved", "backup_restore": {"mode": "critical_read_only_default", "target": "scripts/backup/backup-momo.sh", "freshness": "unverified"}},
         {"canonical_id": "database:vibework:postgres", "inventory_labels": ["vibework-production-postgres-1"], "source_rows": ["L027"], "runtime_identity": "host188/docker/vibework-production-postgres-1", "reconciliation_state": "missing_from_canonical_service_registry", "findings": ["No exact AWOOOI service registry entry or committed restore contract found"], "source_refs": ["docs/security/telegram-canonical-routing-registry.snapshot.json"], "product_id": "vibework", "project_id": "vibework", "owner_lane": "vibework_product_ops", "telegram_destination": "blocked:vibework_route_not_implemented"},
         {"canonical_id": "database:2026fifa:timescaledb", "inventory_labels": ["current-fifa2026-postgres-1", "TimescaleDB current-fifa2026-postgres-1"], "source_rows": ["L028", "L043"], "runtime_identity": "host188/docker/current-fifa2026-postgres-1", "reconciliation_state": "duplicate_inventory_row_and_registry_gap", "findings": ["Same instance is counted once as PostgreSQL and again as TimescaleDB", "No exact restore drill is registered"], "source_refs": ["docs/security/telegram-canonical-routing-registry.snapshot.json"], "product_id": "2026fifa", "project_id": "2026FIFAWorldCup", "owner_lane": "2026fifa_product_ops", "telegram_destination": "blocked:2026fifa_destination_unassigned"},
@@ -544,7 +544,7 @@
         "next_action": "Add the canonical asset to the reconciled source registry and require same-run production readback."
       },
       "members": [
-        {"canonical_id": "windows-vmware:host_99", "inventory_labels": ["Agent99 Windows/VMware control plane"], "source_rows": [], "runtime_identity": "192.168.0.99/Agent99", "findings": ["Agent99 is required for Windows/VMware and control-plane recovery but absent from the imported inventory", "Agent99 also owns the read-only host110 Alertmanager poll/reduced relay coordination role; Linux remediation still routes only to the host Ansible executor", "The atomic 15-file runtime bundle includes the poller but production deployment/readback is pending"], "source_refs": ["docs/operations/agent99-enterprise-ai-automation-work-items.snapshot.json", "k8s/awoooi-prod/04-configmap.yaml", "agent99-alertmanager-alertchain-poll.ps1", "scripts/reboot-recovery/deploy-agent99-via-windows99-ssh.sh"], "owner_lane": "Agent99", "domain_router": "windows_vmware", "executor": "Agent99", "verifier": "agent99_independent_runtime_verifier"},
+        {"canonical_id": "windows-vmware:host_99", "inventory_labels": ["Agent99 Windows/VMware control plane"], "source_rows": [], "runtime_identity": "192.168.0.99/Agent99", "findings": ["Agent99 is required for Windows/VMware and control-plane recovery but absent from the imported inventory", "Agent99 also owns the read-only host110 Alertmanager poll/reduced relay coordination role; Linux remediation still routes only to the host Ansible executor", "The atomic 16-file runtime bundle includes the poller and fixed database dispatch entrypoint but production deployment/readback is pending"], "source_refs": ["docs/operations/agent99-enterprise-ai-automation-work-items.snapshot.json", "k8s/awoooi-prod/04-configmap.yaml", "agent99-alertmanager-alertchain-poll.ps1", "agent99-db-bounded-executor.ps1", "scripts/reboot-recovery/deploy-agent99-via-windows99-ssh.sh"], "owner_lane": "Agent99", "domain_router": "windows_vmware", "executor": "Agent99", "verifier": "agent99_independent_runtime_verifier"},
         {"canonical_id": "service:ollama:host110", "inventory_labels": ["retired Host110 Ollama tombstone"], "source_rows": [], "runtime_identity": "retired-tombstone:host110/ollama/no-endpoint", "source_truth_state": "retired_tombstone_runtime_absence_verified", "reconciliation_state": "retired_tombstone_runtime_absence_verified", "findings": ["Host110 Ollama is forbidden as a provider, proxy, primary, secondary or failover target", "A tombstone is retained so stale sensors and routes create drift instead of resurrecting the endpoint", "AIA-SRE-002 run-aia-sre-002-20260716-1752 removed the exact stale Nginx 11435 proxy with a root-only rollback backup", "Independent post-verifier proved listeners 11435/11434=0, Ollama containers and systemd units=0, stale config paths=0, Nginx active/config valid and Prometheus host110 Ollama targets=0"], "source_refs": ["ops/config/service-registry.yaml", "ops/monitoring/service-registry.yaml", "docs/operations/sre-k3s-controlled-automation-work-items.snapshot.json", "scripts/ops/retire-host110-ollama-proxy.sh"], "owner_lane": "ai_team", "domain_router": "host_systemd", "executor": "host_ansible_executor", "bounded_executor_receipt": "run-aia-sre-002-20260716-1752", "runtime_closure": {"status": "verified_absent", "trace_id": "trace-aia-sre-002-20260716-1752", "run_id": "run-aia-sre-002-20260716-1752", "work_item_id": "AIA-SRE-002", "post_verifier": "host110_ollama_runtime_and_monitoring_absence_verifier"}, "verifier": "host110_ollama_runtime_and_monitoring_absence_verifier", "monitoring": {"signals": ["runtime_endpoint_absence", "prometheus_target_absence", "route_reference_absence"], "coverage": "runtime_absence_verified_20260716"}, "next_action": "Preserve the tombstone and create a drift work item on any Host110 Ollama process, proxy, listener, target, rule or provider-route recurrence."},
         {"canonical_id": "host:111", "inventory_labels": ["host111 local Ollama"], "source_rows": [], "runtime_identity": "192.168.0.111/macos-launchd/ollama", "findings": ["Approved third provider hop and Ansible host are absent from the imported inventory", "The runtime manager is a macOS LaunchAgent, not systemd", "The exact LaunchAgent playbook requires local verification plus independent origin probes from host120 and host121", "The canonical host111 Ollama sensor/rule has no fresh production series"], "source_refs": ["infra/ansible/inventory/hosts.yml", "infra/ansible/playbooks/111-ollama-fallback.yml", "ops/monitoring/service-registry.yaml", "ops/monitoring/alerts-unified.yml", "apps/api/src/services/awooop_ansible_post_verifier.py"], "owner_lane": "ai_team", "domain_router": "host_systemd", "executor": "host_ansible_executor", "verifier": "host111_launchagent_local_and_120_121_origin_verifier", "monitoring": {"signals": ["launchagent_state", "local_generation", "host120_origin_generation", "host121_origin_generation", "canonical_alert_series"], "coverage": "source_candidate_runtime_sensor_missing"}, "next_action": "Check/apply the exact LaunchAgent catalog, verify local plus host120/host121 origins, and require a fresh canonical sensor series before provider readiness."},
         {"canonical_id": "ai-provider:ollama_gcp_a", "inventory_labels": ["GCP-A Ollama"], "source_rows": [], "runtime_identity": "34.143.170.20:11434", "source_truth_state": "source_reconciled_runtime_pending", "findings": ["Approved first provider hop is absent from the imported inventory", "Observed transport is public HTTP and is candidate-only until secure mesh/TLS promotion", "Only sanitized prompts may cross this boundary; unsanitized input and every tool loop fail closed before network access", "The exact Prometheus provider target is missing in production"], "source_refs": ["ops/monitoring/service-registry.yaml", "k8s/monitoring/prometheus.yml", "docs/operations/sre-k3s-controlled-automation-work-items.snapshot.json", "apps/api/src/services/ai_provider_policy.py"], "owner_lane": "ai_team", "domain_router": "ai_provider", "executor": "deterministic_provider_router", "verifier": "provider_health_generation_and_transport_receipt_verifier", "monitoring": {"signals": ["exact_target_up", "scrape_freshness", "sanitization_receipt", "tool_loop_denial", "transport_boundary"], "coverage": "source_candidate_runtime_target_missing"}, "transport_policy": {"observed": "public_http", "execution_scope": "sanitized_candidate_only", "tool_loop": "fail_closed", "promotion_requires": "secure_mesh_or_tls_plus_runtime_readback"}, "next_action": "Deploy the exact blackbox target, verify fresh series and sanitization/tool-loop denials, then retain candidate-only status until secure transport promotion."},
@@ -556,7 +556,7 @@
         {"canonical_id": "k8s:awoooi-prod:web", "inventory_labels": ["AWOOOI production Web"], "source_rows": [], "runtime_identity": "k3s/awoooi-prod/deployment/awoooi-web", "findings": ["Production Web is in the monitoring registry but absent from the imported infrastructure inventory"], "source_refs": ["ops/monitoring/service-registry.yaml", "k8s/awoooi-prod"], "owner_lane": "frontend_team", "domain_router": "kubernetes_workload", "executor": "kubernetes_controlled_executor", "verifier": "kubernetes_rollout_verifier"},
         {"canonical_id": "k8s:awoooi-prod:worker", "inventory_labels": ["AWOOOI production Worker"], "source_rows": [], "runtime_identity": "k3s/awoooi-prod/deployment/awoooi-worker", "findings": ["Worker is in the monitoring registry but absent from the imported infrastructure inventory"], "source_refs": ["ops/monitoring/service-registry.yaml", "k8s/awoooi-prod"], "owner_lane": "backend_team", "domain_router": "kubernetes_workload", "executor": "kubernetes_controlled_executor", "verifier": "kubernetes_rollout_verifier"},
         {"canonical_id": "k8s:awoooi-prod:broker", "inventory_labels": ["AWOOOI production Broker"], "source_rows": [], "runtime_identity": "k3s/awoooi-prod/deployment/awoooi-broker", "findings": ["Broker is part of production deployment/readback but absent from the imported inventory and monitoring service registry"], "source_refs": ["k8s/awoooi-prod", "docs/operations/sre-k3s-controlled-automation-work-items.snapshot.json"], "owner_lane": "backend_team", "domain_router": "kubernetes_workload", "executor": "kubernetes_controlled_executor", "verifier": "kubernetes_rollout_verifier"},
-        {"canonical_id": "signal:alertmanager-webhook-chain", "inventory_labels": ["AlertChainBroken_Alertmanager"], "source_rows": [], "runtime_identity": "alertmanager->awoooi-api-webhook->incident->telegram plus host99 Agent99 exact-host pull fallback", "source_truth_state": "source_reconciled_runtime_pending", "findings": ["Canonical signal is locked to container:host_110:alertmanager", "Rule, concise attribution card, exact bounded recovery and independent verifier are source-ready", "Host99 Agent99 independently polls only the exact active/critical AlertChain signal from host110 without a first-hop credential or raw-payload persistence", "The reduced event is relayed over HTTPS with stable dedupe while Linux execution remains in the host Ansible lane", "Production deployment, poll freshness/dedupe, current alert resolution and same-run learning acknowledgements remain pending"], "source_refs": ["k8s/monitoring/alert-chain-monitor.yaml", "ops/alertmanager/alertmanager.yml", "agent99-alertmanager-alertchain-poll.ps1", "agent99-sre-alert-relay.ps1", "apps/api/src/api/v1/webhooks.py", "apps/api/src/services/controlled_alert_target_router.py", "infra/ansible/playbooks/110-alertmanager-delivery-recovery.yml", "scripts/reboot-recovery/deploy-agent99-via-windows99-ssh.sh"], "owner_lane": "observability_ops", "verifier": "alert_delivery_chain_plus_agent99_pull_independent_verifier", "monitoring": {"signals": ["alertmanager_delivery_counters", "primary_webhook_health", "agent99_pull_freshness", "dedupe_receipt", "telegram_delivery_receipt"], "coverage": "source_primary_and_independent_pull_ready_runtime_pending"}, "next_action": "Deploy the receiver-scoped scrape/rule/playbook and the atomic Agent99 15-file bundle; run check/apply/verify under one trace/run/work item; then require Alertmanager resolution, Telegram and KM/RAG/MCP/PlayBook acknowledgements before closure."},
+        {"canonical_id": "signal:alertmanager-webhook-chain", "inventory_labels": ["AlertChainBroken_Alertmanager"], "source_rows": [], "runtime_identity": "alertmanager->awoooi-api-webhook->incident->telegram plus host99 Agent99 exact-host pull fallback", "source_truth_state": "source_reconciled_runtime_pending", "findings": ["Canonical signal is locked to container:host_110:alertmanager", "Rule, concise attribution card, exact bounded recovery and independent verifier are source-ready", "Host99 Agent99 independently polls only the exact active/critical AlertChain signal from host110 without a first-hop credential or raw-payload persistence", "The reduced event is relayed over HTTPS with stable dedupe while Linux execution remains in the host Ansible lane", "Production deployment, poll freshness/dedupe, current alert resolution and same-run learning acknowledgements remain pending"], "source_refs": ["k8s/monitoring/alert-chain-monitor.yaml", "ops/alertmanager/alertmanager.yml", "agent99-alertmanager-alertchain-poll.ps1", "agent99-sre-alert-relay.ps1", "apps/api/src/api/v1/webhooks.py", "apps/api/src/services/controlled_alert_target_router.py", "infra/ansible/playbooks/110-alertmanager-delivery-recovery.yml", "scripts/reboot-recovery/deploy-agent99-via-windows99-ssh.sh"], "owner_lane": "observability_ops", "verifier": "alert_delivery_chain_plus_agent99_pull_independent_verifier", "monitoring": {"signals": ["alertmanager_delivery_counters", "primary_webhook_health", "agent99_pull_freshness", "dedupe_receipt", "telegram_delivery_receipt"], "coverage": "source_primary_and_independent_pull_ready_runtime_pending"}, "next_action": "Deploy the receiver-scoped scrape/rule/playbook and the atomic Agent99 16-file bundle; run check/apply/verify under one trace/run/work item; then require Alertmanager resolution, Telegram and KM/RAG/MCP/PlayBook acknowledgements before closure."},
         {"canonical_id": "control-plane:telegram-routing-registry", "inventory_labels": ["Canonical Telegram routing registry"], "source_rows": [], "runtime_identity": "docs/security/telegram-canonical-routing-registry.snapshot.json", "findings": ["Nine product routes are blocked/disabled/not implemented; scattering alerts is forbidden"], "source_refs": ["docs/security/telegram-canonical-routing-registry.snapshot.json"], "owner_lane": "NotificationGovernance", "verifier": "telegram_route_and_delivery_receipt_verifier"},
         {"canonical_id": "control-plane:km-rag", "inventory_labels": ["Knowledge Base and RAG"], "source_rows": [], "runtime_identity": "awoooi-api/knowledge-rag", "findings": ["Required learning target is implemented in source but absent from the imported inventory and runtime closure is unverified"], "source_refs": ["apps/api/src/api/v1/knowledge.py", "apps/api/src/api/v1/rag.py"], "owner_lane": "LearningPlane", "verifier": "km_rag_durable_write_ack_verifier"},
         {"canonical_id": "control-plane:mcp-gateway", "inventory_labels": ["Internal MCP Gateway"], "source_rows": [], "runtime_identity": "awoooi-api/mcp-control-plane", "findings": ["MCP catalog has broad product coverage but is absent from the imported inventory; write adapters must remain policy controlled"], "source_refs": ["docs/operations/mcp-control-plane-catalog.snapshot.json"], "owner_lane": "MCPControlPlane", "verifier": "mcp_gateway_audit_and_runtime_verifier"},

docs/operations/sre-k3s-controlled-automation-work-items.snapshot.json

@@ -513,14 +513,30 @@
         "ops/config/service-registry.yaml",
         "apps/api/src/db/base.py",
         "apps/api/src/core/unit_of_work.py",
+        "apps/api/src/services/db_bounded_executor.py",
         "apps/api/src/services/executor_trust_boundary_readback.py",
+        "agent99-db-bounded-executor.ps1",
         "scripts/ops/awoooi-workload-db-identity-bootstrap.sh"
       ],
       "executor": "db_bounded_executor",
       "verifier": "db_independent_verifier",
       "rollback": "transactional or compensating action only; destructive restore remains break-glass",
       "exit_condition": "DB incidents use DB-native preflight/postconditions and never generic host restart",
-      "next_action": "deploy then verify cap-2 global session budget, role headroom >= 8 and DB-native no-cross-domain receipts"
+      "runtime_entrypoint_contract": {
+        "status": "source_ready_runtime_not_applied",
+        "command_id": "telegram_receipt_index_apply_v1",
+        "canonical_asset": "public.awooop_outbound_message",
+        "execution_hub": "host:192.168.0.99",
+        "dispatch_role": "Agent99_dispatch_only",
+        "executor_domain": "database",
+        "runtime_transport": "host99_to_host110_to_host120_fixed_sudo_kubectl_exec",
+        "host120_installer_required": false,
+        "check_apply_pod_role": "first_ready_awoooi_api_pod",
+        "independent_verifier_role": "second_ready_awoooi_api_pod_second_process",
+        "arbitrary_sql_allowed": false,
+        "cross_domain_fallback_allowed": false
+      },
+      "next_action": "deploy the fixed Agent99 dispatch through the atomic runtime bundle, then use the already allowlisted host120 sudo kubectl path for one same-trace check/apply/second-pod verify of telegram_receipt_index_apply_v1; separately retain cap-2 global session budget and role headroom >= 8 verification"
     },
     {
       "id": "AIA-SRE-011",
@@ -713,7 +729,7 @@
         "the host99 Agent99 independent pull/reduced relay has no production deployment, freshness, dedupe or controlled-repair receipt",
         "production Alertmanager exposes integration-only notification counters; the bounded check now passes after adding a scrape-time receiver_contract label, but apply, alert resolution and same-run learning receipts remain pending"
       ],
-      "next_action": "deploy the production-schema-compatible Alertmanager runtime scrape/canonical rules and the host99 Agent99 exact-host poller through the atomic 15-file bundle; verify receiver-contract freshness, dedupe and the current firing alert resolution; then reconcile every project/product/alert class against its typed domain and canonical Telegram destination"
+      "next_action": "deploy the production-schema-compatible Alertmanager runtime scrape/canonical rules, the host99 Agent99 exact-host poller and the fixed DB dispatch entrypoint through the atomic 16-file bundle; verify receiver-contract freshness, dedupe and the current firing alert resolution; then reconcile every project/product/alert class against its typed domain and canonical Telegram destination"
     },
     {
       "id": "AIA-SRE-018",