fix(ops): harden momo scheduler cold start gate

docs/LOGBOOK.md

@@ -3282,7 +3282,7 @@ DATABASE_URL=postgresql+asyncpg://u:p@localhost:5432/test REDIS_URL=redis://loca
 |----------|--------|
 | `docs/runbooks/FULL-STACK-COLD-START-SOP.md` | 升級為 v1.1，補齊 Golden Startup Order、Mermaid 依賴圖、phase gate 邏輯、script-to-SOP 覆蓋表、next-reboot operator contract |
 | `ops/reboot-recovery/full-stack-cold-start-baseline.yml` | 新增機器可讀 baseline，固定 hosts、roles、啟動順序、endpoint code、schedule freshness、stateful-service 禁區、AI auto-remediation gate |
-| `scripts/reboot-recovery/full-stack-cold-start-check.sh` | 新增 `--watch` / `--interval` / `--max-attempts`，可在重開機後反覆檢查直到 `GREEN` |
+| `scripts/reboot-recovery/full-stack-cold-start-check.sh` | 新增 `--watch` / `--interval` / `--max-attempts`，可在重開機後反覆檢查直到 `GREEN`；momo-scheduler 改用 container health + 6h registration evidence，避免 `tail 200` 假陰性 |
 
 ### 標準下次重開機放行指令
 
@@ -3304,7 +3304,7 @@ ruby -e 'require "yaml"; YAML.load_file("ops/reboot-recovery/full-stack-cold-sta
 # YAML OK
 
 bash scripts/reboot-recovery/full-stack-cold-start-check.sh --watch --interval 1 --max-attempts 1 --send-alert-test
-# PASS=50 WARN=0 BLOCKED=0
+# PASS=51 WARN=0 BLOCKED=0
 # Result: GREEN. Full stack is ready for controlled runner/CD release.
 ```
 

docs/runbooks/FULL-STACK-COLD-START-SOP.md

@@ -369,7 +369,7 @@ Do not mark the reboot complete until scheduled work is proven runnable. A conta
 |--------------|----------------|------------------|
 | 188 cron | `systemctl is-active cron` and `crontab -l` | cron active; backup, restart exporter, stats exporter entries present |
 | 188 backup-from-110 | `backup_110_last_success_timestamp` in textfile/Prometheus | last success age `< 25h` |
-| 188 momo-scheduler | `docker logs momo-scheduler` | `全部排程任務已註冊`; Google Drive auth works; dashboard URLs use container-reachable hostnames |
+| 188 momo-scheduler | `docker inspect momo-scheduler` and `docker logs --since 6h momo-scheduler` | container `running healthy`; `全部排程任務已註冊`; Google Drive auth works; dashboard URLs use container-reachable hostnames |
 | 188 momo import | manual `run_auto_import_task()` after parser changes | selected sheet is `即時業績明細`; imported date range has matching rows in `daily_sales_snapshot` and `realtime_sales_monthly` |
 | 110 cron | `systemctl is-active cron` | cron active; Docker/systemd textfile exporters fresh |
 | 110 startup units | `systemctl --failed` | zero failed units; stale `momo-startup-complete` and `wooo-staggered-startup` disabled |

ops/reboot-recovery/full-stack-cold-start-baseline.yml

@@ -193,6 +193,7 @@ phases:
       - "110/120/121/188 cron services active"
       - "188 backup-from-110 success age below 25h"
       - "188 docker restart/stats textfiles fresh"
+      - "188 momo-scheduler container healthy and registration evidence present within 6h"
       - "110 docker/systemd textfiles fresh"
       - "120 awoooi-prod CronJobs present and unsuspended"
       - "120 awoooi-prod has no failed Jobs"

scripts/reboot-recovery/full-stack-cold-start-check.sh

@@ -340,7 +340,8 @@ done
 if [ -f /home/ollama/node_exporter_textfiles/backup.prom ]; then
   awk -v now="$now" "/^backup_110_last_success_timestamp / {printf \"BACKUP_110_AGE %d\\n\", now - int(\$2)}" /home/ollama/node_exporter_textfiles/backup.prom
 fi
-echo "SCHEDULER_REGISTERED $(docker logs --tail 200 momo-scheduler 2>&1 | grep -c "全部排程任務已註冊" || true)"
+echo "SCHEDULER_STATE $(docker inspect -f "{{.State.Status}} {{if .State.Health}}{{.State.Health.Status}}{{end}}" momo-scheduler 2>/dev/null || true)"
+echo "SCHEDULER_REGISTERED $(docker logs --since 6h momo-scheduler 2>&1 | grep -c "全部排程任務已註冊" || true)"
 ' 2>&1); then
     echo "$out"
     grep -q "CRON_188 active" <<<"$out" && ok "188 cron active" || warn "188 cron not confirmed"
@@ -348,7 +349,8 @@ echo "SCHEDULER_REGISTERED $(docker logs --tail 200 momo-scheduler 2>&1 | grep -
     awk '/TEXTFILE_188 docker_restart_count.prom age=/ {split($3,a,"="); exit !(a[2] < 300)}' <<<"$out" && ok "188 docker restart exporter fresh" || warn "188 docker restart exporter stale"
     awk '/TEXTFILE_188 docker_stats.prom age=/ {split($3,a,"="); exit !(a[2] < 300)}' <<<"$out" && ok "188 docker stats exporter fresh" || warn "188 docker stats exporter stale"
     awk '/BACKUP_110_AGE / {exit !($2 < 90000)}' <<<"$out" && ok "188 backup-from-110 success within 25h" || warn "188 backup-from-110 success not confirmed"
-    awk '/SCHEDULER_REGISTERED / {exit !($2 > 0)}' <<<"$out" && ok "188 momo scheduler registered jobs" || warn "188 momo scheduler registration not confirmed"
+    grep -q "SCHEDULER_STATE running healthy" <<<"$out" && ok "188 momo scheduler container healthy" || warn "188 momo scheduler health not confirmed"
+    awk '/SCHEDULER_REGISTERED / {exit !($2 > 0)}' <<<"$out" && ok "188 momo scheduler registered jobs within 6h" || warn "188 momo scheduler registration not confirmed within 6h"
   else
     warn "188 schedule check unavailable"
     echo "$out"