Merge remote-tracking branch 'gitea-ssh/main' into codex/p0-product-manifest-standard-20260629

# Conflicts:
#	docs/LOGBOOK.md
This commit is contained in:
Your Name
2026-06-29 15:12:47 +08:00
10 changed files with 219 additions and 62 deletions

View File

@@ -1,18 +1,19 @@
{
"schema_version": "awoooi_priority_work_order_readback_v1",
"generated_at": "2026-06-29T14:49:52+08:00",
"status": "p0_006a_reboot_auto_recovery_slo_live_probe_installed_blocked_service_health",
"generated_at": "2026-06-29T15:05:00+08:00",
"status": "p0_006a_reboot_auto_recovery_slo_timer_live_services_green_waiting_reboot_window",
"source_refs": {
"global_scorecard": "~/.codex/product-runtime-governance-completion-scorecard.snapshot.json",
"workstation_dashboard": "~/.codex/codex-workstation-sync-dashboard.snapshot.json",
"post_reboot_summary": "/tmp/awoooi-post-reboot-readiness-20260629-115730/summary.txt",
"post_reboot_summary": "/home/wooo/reboot-recovery/reboot-auto-recovery-slo-20260629-150501/summary.txt",
"full_stack_cold_start_check": "scripts/reboot-recovery/full-stack-cold-start-check.sh --monitor-read-only --no-color",
"delivery_closure_workbench": "https://awoooi.wooo.work/api/v1/agents/delivery-closure-workbench",
"public_gitea_queue_readback": "ops/runner/read-public-gitea-actions-queue.py --json",
"credential_escrow_scorecard": "/tmp/awoooi-credential-escrow-intake-scorecard-20260629-1200-priority.json",
"dr_escrow_evidence_checklist_generator": "scripts/reboot-recovery/dr-escrow-evidence-checklist.py",
"gitea_private_inventory_p0_scorecard": "docs/operations/awoooi-gitea-private-inventory-p0-scorecard.snapshot.json",
"reboot_auto_recovery_slo_scorecard": "docs/operations/awoooi-reboot-auto-recovery-slo-scorecard.snapshot.json"
"reboot_auto_recovery_slo_scorecard": "docs/operations/awoooi-reboot-auto-recovery-slo-scorecard.snapshot.json",
"reboot_auto_recovery_slo_metric": "/home/wooo/node_exporter_textfiles/reboot_auto_recovery_slo.prom"
},
"current_head": {
"gitea_main_sha": "7ff959b6a8bbdf152da1969687f188ceda4b0561",
@@ -186,8 +187,8 @@
{
"workplan_id": "P0-006",
"title": "主機重啟自動偵測、自動觸發與 10 分鐘恢復 SLO",
"status": "blocked_reboot_auto_recovery_slo_not_ready",
"reason": "Boot-triggered SLO timer is live on host 110 and all required host boot probes are now observed; the 10-minute recovery claim remains fail-closed because this was not a fresh reboot window and service/backup/post-start blockers remain.",
"status": "blocked_waiting_fresh_all_host_reboot_window",
"reason": "Boot-triggered SLO timer is enabled and active on host 110; live metric and scorecard observed all required hosts. Service/data/backup/188 readback is green. The 10-minute claim remains fail-closed only because the current boot observation is older than the 600-second target window, so the next proof requires an actual fresh all-host reboot event or an approved reboot drill.",
"evidence": {
"target_minutes": 10,
"can_claim_all_services_recovered_within_target": false,
@@ -195,10 +196,10 @@
"host_boot_probe_source_present": true,
"slo_systemd_timer_source_present": true,
"slo_exporter_source_present": true,
"post_start_blocked": 6,
"service_green": false,
"post_start_blocked": 0,
"service_green": true,
"product_data_green": true,
"backup_core_green": false,
"backup_core_green": true,
"wazuh_dashboard_degraded": false,
"all_host_reboot_detection_missing": false,
"host_boot_probe_missing_hosts": false,
@@ -222,32 +223,31 @@
"121",
"188"
],
"max_observed_uptime_seconds": 518414,
"max_observed_uptime_seconds": 519376,
"active_blockers": [
"backup_core_green_not_1",
"host_boot_observation_older_than_target_window",
"post_start_blocked_not_zero",
"service_green_not_1"
]
"host_boot_observation_older_than_target_window"
],
"host_188_service_green": true,
"safe_next_step_from_scorecard": "timer_deployed_and_services_readback_green_wait_for_next_all_host_reboot_event_or_approved_reboot_drill_to_prove_10_minute_slo"
},
"professional_fix": {
"owner": "reboot auto-recovery lane",
"action": "Keep the live boot-triggered SLO timer enabled, fix backup_core/post-start/service blockers, then use the next fresh reboot window to prove max_observed_uptime_seconds<=600.",
"action": "Keep the live boot-triggered SLO timer enabled. Do not reboot from this lane. Use the next actual all-host reboot event, or a separately approved reboot drill, to prove max_observed_uptime_seconds<=600 with service/data/backup readback still green.",
"exit_criteria": [
"can_claim_all_services_recovered_within_target=true",
"observed_hosts=110,120,121,188",
"missing_hosts=[]",
"unreachable_hosts=[]",
"max_observed_uptime_seconds<=600 during a fresh reboot window",
"max_observed_uptime_seconds<=600 during a fresh all-host reboot window",
"POST_START_BLOCKED=0",
"SERVICE_GREEN=1",
"PRODUCT_DATA_GREEN=1",
"BACKUP_CORE_GREEN=1",
"WAZUH_DASHBOARD_DEGRADED=0",
"HOST_188_SERVICE_GREEN=1",
"live_slo_metric_present=true"
]
},
"safe_next_step": "fix_backup_core_post_start_and_service_green_blockers_then_rerun_live_slo_scorecard_after_next_reboot_window"
"safe_next_step": "wait_for_next_all_host_reboot_event_or_separately_approved_reboot_drill_to_prove_10_minute_slo"
}
],
"noise_integrated_risk_register": [
@@ -319,8 +319,8 @@
"database_write_or_restore_performed": false
},
"next_execution_order": [
"P0-006: keep the live reboot SLO timer active; next proof is the next fresh all-host reboot event or separately approved reboot drill, not another source deploy.",
"P0-005: fill the single DR escrow evidence checklist with five non-secret refs and rerun one preflight.",
"P0-003: convert private/internal inventory to Gitea-only readback and remove retired GitHub from active P0 blocker math.",
"P0-006: deploy boot-triggered reboot auto-recovery SLO verifier, collect all-host boot probe, and prove or block the 10-minute recovery claim."
"P0-003: complete Gitea authenticated/admin inventory export and owner coverage attestation; GitHub remains stopped/retired/do_not_use."
]
}

View File

@@ -1,29 +1,26 @@
{
"active_blockers": [
"backup_core_green_not_1",
"host_boot_observation_older_than_target_window",
"post_start_blocked_not_zero",
"service_green_not_1"
"host_boot_observation_older_than_target_window"
],
"can_claim_all_services_recovered_within_target": false,
"capacity": {
"checked": true,
"free_gib": 145.514,
"free_gib": 145.646,
"min_free_gib": 2.0
},
"generated_at": "2026-06-29T14:49:52+08:00",
"generated_at": "2026-06-29T15:06:25+08:00",
"host_boot_detection": {
"host_rows": [
{
"alias": "110",
"boot_id": "a3dfae32-3762-4394-86fa-a342aea07df5",
"reachable": true,
"startup_active": "inactive_unknown",
"startup_active": "inactive",
"startup_enabled": "enabled",
"startup_unit": "awoooi-startup-110.service",
"systemd_state": "degraded",
"target": "wooo@192.168.0.110",
"uptime_seconds": 518406
"uptime_seconds": 519367
},
{
"alias": "120",
@@ -34,7 +31,7 @@
"startup_unit": "k3s.service",
"systemd_state": "running",
"target": "wooo@192.168.0.120",
"uptime_seconds": 518397
"uptime_seconds": 519359
},
{
"alias": "121",
@@ -45,7 +42,7 @@
"startup_unit": "k3s.service",
"systemd_state": "running",
"target": "wooo@192.168.0.121",
"uptime_seconds": 518355
"uptime_seconds": 519317
},
{
"alias": "188",
@@ -56,10 +53,10 @@
"startup_unit": "awoooi-startup.service",
"systemd_state": "running",
"target": "ollama@192.168.0.188",
"uptime_seconds": 518414
"uptime_seconds": 519376
}
],
"max_observed_uptime_seconds": 518414,
"max_observed_uptime_seconds": 519376,
"missing_hosts": [],
"observed_hosts": [
"110",
@@ -83,18 +80,18 @@
"unreachable_hosts": []
},
"post_reboot_readiness": {
"backup_core_green": false,
"backup_core_green": true,
"host_188_service_green": true,
"next_required_gates": "none",
"overall_declaration": "SERVICE_BLOCKED",
"post_start_blocked": 6,
"post_start_result": "BLOCKED",
"next_required_gates": "credential_escrow_evidence",
"overall_declaration": "FULL_STACK_GREEN_DR_ESCROW_BLOCKED",
"post_start_blocked": 0,
"post_start_result": "FULL_STACK_GREEN_DR_ESCROW_BLOCKED",
"product_data_green": true,
"service_green": false,
"service_green": true,
"summary_present": true,
"wazuh_dashboard_degraded": false
},
"safe_next_step": "deploy_boot_triggered_slo_timer_and_collect_all_host_boot_probe_then_rerun_scorecard_until_status_slo_ready",
"safe_next_step": "timer_deployed_and_services_readback_green_wait_for_next_all_host_reboot_event_or_approved_reboot_drill_to_prove_10_minute_slo",
"schema_version": "awoooi_reboot_auto_recovery_slo_scorecard_v1",
"source_controls": {
"cold_start_textfile_exporter_source_present": true,