fix(api): resolve recovery preflight paths in containers

apps/api/src/services/harbor_registry_controlled_recovery_preflight.py

@@ -15,9 +15,12 @@ from collections.abc import Callable
 from pathlib import Path
 from typing import Any
 
+from src.services.snapshot_paths import resolve_repo_root
+
 _SCHEMA_VERSION = "harbor_registry_controlled_recovery_preflight_v1"
+_REPO_ROOT = resolve_repo_root(Path(__file__))
 _DEFAULT_ROUTE_SOURCE = (
-    Path(__file__).resolve().parents[4]
+    _REPO_ROOT
     / "infra"
     / "ansible"
     / "roles"
@@ -26,7 +29,7 @@ _DEFAULT_ROUTE_SOURCE = (
     / "188-internal-tools-https.conf.j2"
 )
 _DEFAULT_WATCHDOG_SOURCE = (
-    Path(__file__).resolve().parents[4]
+    _REPO_ROOT
     / "scripts"
     / "reboot-recovery"
     / "harbor-watchdog.sh"

apps/api/src/services/stockplatform_public_api_controlled_recovery_preflight.py

@@ -11,13 +11,15 @@ import re
 from pathlib import Path
 from typing import Any
 
+from src.services.snapshot_paths import resolve_repo_root
 from src.services.stockplatform_public_api_runtime_readback import (
     load_latest_stockplatform_public_api_runtime_readback,
 )
 
 _SCHEMA_VERSION = "stockplatform_public_api_controlled_recovery_preflight_v1"
+_REPO_ROOT = resolve_repo_root(Path(__file__))
 _DEFAULT_ROUTE_SOURCE = (
-    Path(__file__).resolve().parents[4]
+    _REPO_ROOT
     / "infra"
     / "ansible"
     / "roles"

docs/LOGBOOK.md

@@ -6,16 +6,18 @@
 - ArgoCD `awoooi-prod` 回 `ComparisonError`：repo-server gRPC `connection refused`；`argocd-repo-server` initContainer `copyutil` 因 `/bin/ln: Already exists` 反覆 BackOff。已 live patch repo-server init command，先移除既有 symlink 再建立，repo-server 成功 rollout Ready。
 - ArgoCD refresh 後成功同步到 `9db4f72cb`，但 API rollout 卡在 1/2；Pending pod event 顯示 `nodeSelector=mon` 搭配 `topologySpreadConstraints minDomains=2 whenUnsatisfiable=DoNotSchedule` 自相矛盾，造成 scheduler deadlock。
 - 已把 API / Web / Worker 的 topology spread 從硬性 `DoNotSchedule + minDomains=2` 調整為柔性 `ScheduleAnyway`，保留 hostname spread preference，但不再阻塞 post-reboot / GitOps rollout。
+- API 新 pod 排程後又 `CrashLoopBackOff`；previous log 顯示 `harbor_registry_controlled_recovery_preflight.py` 在 production container layout `/app/src/services/...` 使用 `Path(__file__).parents[4]` 造成 `IndexError: 4`。已改用既有 `resolve_repo_root(Path(__file__))`，並同步修掉同型的 StockPlatform controlled recovery preflight 路徑解析，避免下一個 import 再炸。
 
 **驗證**：
 - `argocd-repo-server` rollout：`deployment "argocd-repo-server" successfully rolled out`。
 - ArgoCD readback：`sync=Synced rev=9db4f72cbf98`，API deployment image / env 已更新為 `06819ea96c05...`。
 - `kubectl apply --dry-run=server` 驗證 `awoooi-api`、`awoooi-web`、`awoooi-worker` manifests：通過。
+- `py_compile` / targeted pytest 需在 path resolver fix 後重跑並推正常 CD，因為 production 必須建出新 API image 才能離開 CrashLoop。
 
 **邊界**：未讀 secret / token / `.env` / raw sessions / SQLite / auth；未使用 GitHub / `gh` / GitHub API；未重啟主機 / Docker / Nginx / K3s / DB / firewall；live patch 僅限 ArgoCD repo-server init command 與 prod Deployment topology scheduler policy。
 
 **下一步**：
-- 推 Gitea main 後等 ArgoCD 套用 source 修法，讀回 API / Web / Worker 全部 Ready、production workbench runtime/desired tag 等於 `06819ea...`，再判定 Gitea/CD 恢復完成。
+- 推 Gitea main 後等 CD 建新 API image，讀回 API / Web / Worker 全部 Ready、production workbench runtime/desired tag 等於最新 commit，再判定 Gitea/CD 恢復完成。
 
 ## 2026-07-01 — 15:25 Gitea live recovery after 110 Docker/control-plane failure