fix(ops): close Gitea backup restore verification

This commit is contained in:
ogt
2026-07-10 20:26:00 +08:00
parent 866811bbb3
commit 872a3ed5eb
22 changed files with 1460 additions and 71 deletions

View File

@@ -1,6 +1,6 @@
{
"schema_version": "agent99_enterprise_ai_automation_work_items_v1",
"generated_at": "2026-07-10T16:22:00+08:00",
"generated_at": "2026-07-10T19:40:00+08:00",
"status": "in_progress_p0_alert_routing_grouping_dedupe",
"scope_complete": false,
"north_star": "Make Windows host 192.168.0.99 the policy-controlled on-prem AI execution node for all hosts, VMs, services, products, sites, tools, packages, alerts and recovery workflows, with external monitoring when host 99 is unavailable.",
@@ -20,8 +20,8 @@
"id": "AG99-P0-002",
"title": "Alert taxonomy, routing, grouping and dedupe",
"reason": "Explicit event kind and suggested mode are not consistently authoritative, and forwarding before grouping can create wrong-domain or duplicate Agent99 work.",
"implementation_status": "in_progress_replay_corpus_and_pre_bridge_grouping",
"next_action": "Add routing precedence and a replay corpus for backup, provider, reboot, PostgreSQL, host and K3s events; move grouping and single-flight ahead of Agent99 dispatch."
"implementation_status": "local_package_and_contract_green_runtime_deploy_pending",
"next_action": "Finish the current Gitea source receipt, atomically deploy the tested Agent99 package to Windows 99 when an authenticated no-secret management channel is available, then replay backup, provider, reboot, PostgreSQL, host and K3s events against the runtime manifest."
},
"current_runtime_truth": {
"observed_at": "2026-07-10T15:04:27+08:00",
@@ -316,7 +316,10 @@
"verifier": "Replay routing corpus and assert one active incident and expected mode per fingerprint.",
"callback": "Publish normalized route decision and dedupe reason to AWOOOI and AwoooP.",
"acceptance": "Known backup, provider, reboot, PostgreSQL, host and K3s samples route to the correct lane with no duplicate same-state dispatch.",
"next_action": "Add routing precedence and pre-bridge grouping regression corpus."
"completion_percent": 80,
"implementation_progress": "Local Agent99 contract and synthetic replay are green; Windows 99 runtime deployment and runtime replay remain pending.",
"evidence_refs": ["local Agent99 PowerShell contract 19/19", "local Agent99 synthetic replay 8/8", "isolated atomic deploy test passed"],
"next_action": "Deploy the tested package atomically to Windows 99, verify the runtime manifest, and rerun the routing/dedupe corpus through the live ingress."
},
{
"id": "AG99-P0-003",
@@ -536,7 +539,10 @@
"verifier": "Each baseline domain has schedule, freshness, integrity and isolated restore evidence.",
"callback": "Report one lifecycle incident per failed backup domain and update DR scorecard.",
"acceptance": "No unknown backup target; failures name the domain, age, SLA, owner, evidence and safe next action.",
"next_action": "Reconcile failed readbacks and add missing full Gitea, DB, packages, LFS and tool/log restore receipts."
"completion_percent": 78,
"implementation_progress": "The 110/188 backup heartbeat, Gitea full-dump isolated restore, private bundle off-host copy, sample restore, Velero missed-run backfill and Prometheus alert slice are live green.",
"evidence_refs": ["110 backup 13/13", "188 backup 4/4", "Gitea dump CRC and inventory 15/15", "Gitea product bundles and remote SHA-256 12/12 on 188", "Velero backfill job succeeded", "Prometheus source/canonical/active/runtime SHA matched", "Backup/Gitea non-inactive alerts 0"],
"next_action": "Merge and deploy the source branch through Gitea, then complete the remaining DB, registry, package, tool, log and AI-artifact restore-receipt matrix."
},
{
"id": "AG99-P0-013",
@@ -580,7 +586,10 @@
"verifier": "All expected repos and refs, full dump components, registry artifacts, CD run and runtime markers read back successfully.",
"callback": "Update source-control, release and DR scorecards with one trace.",
"acceptance": "All 12 products have source and release proof and the platform can be reconstructed in isolation from verified backups.",
"next_action": "Add full Gitea state and registry restore receipts to the existing repo-bundle proof."
"completion_percent": 72,
"implementation_progress": "Gitea full dump and off-host private bundle restore-confidence are live verified; Harbor/Registry artifacts, runner/CD and complete platform reconstruction remain open.",
"evidence_refs": ["Gitea full dump 6928031514 bytes", "regular repository inventory 15/15", "product bundle manifest 12/12", "188 sample clone and fsck passed"],
"next_action": "Merge/deploy the Gitea DR source, then add Harbor/Registry artifact restore receipts and runner/CD/runtime-marker reconstruction proof."
},
{
"id": "AG99-P1-001",