debug: fix YAML, use base64 script transfer

Co-authored-by: xiaoxia <dev@xiaoxiajianji.com>
Co-committed-by: xiaoxia <dev@xiaoxiajianji.com>

.gitea/workflows/debug-web-v2.yml

@@ -0,0 +1,30 @@
+name: "Debug: Web container v2 (mount conflict)"
+on:
+  push:
+    branches: [debug/web-crash-v2]
+  workflow_dispatch:
+jobs:
+  web-diag:
+    runs-on: runtime-builder
+    timeout-minutes: 10
+    steps:
+      - name: Setup SSH
+        shell: bash
+        env:
+          STAGING_SSH_KEY: ${{ secrets.PREVIEW_SSH_KEY }}
+        run: |
+          set -eux
+          which ssh || (apt-get update -qq && apt-get install -y -qq openssh-client)
+          mkdir -p ~/.ssh && chmod 700 ~/.ssh
+          printf "%s" "$STAGING_SSH_KEY" > ~/.ssh/id_rsa
+          chmod 600 ~/.ssh/id_rsa
+          H=47.98.113.167; P=22222
+          ssh-keyscan -p $P -H $H >> ~/.ssh/known_hosts 2>/dev/null
+      - name: Run diag via base64
+        shell: bash
+        run: |
+          set -x
+          echo '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' | base64 -d > /tmp/diag.sh
+          chmod +x /tmp/diag.sh
+          cat /tmp/diag.sh
+          ssh -p 22222 -i ~/.ssh/id_rsa -o StrictHostKeyChecking=no root@47.98.113.167 'bash -s' < /tmp/diag.sh

apps/api/app/services/lipsync_service.py

@@ -211,12 +211,18 @@ class LipsyncService:
                         normalize_emotion(emotion),
                     )
                 )
-            except Exception:
-                logger.warning(
-                    "Celery 任务提交失败，TTS 任务已创建但未触发执行: %s",
+            except Exception as exc:
+                # 投递失败时立即把 job 标成 failed 并写入 error_message，
+                # 前端轮询时能直接看到失败原因，不会无限卡在 tts_processing。
+                logger.exception(
+                    "Celery 任务提交失败，TTS 任务已创建但未触发执行: job_id=%s err=%s",
                     job_id,
-                    exc_info=True,
+                    exc,
                 )
+                job.status = "failed"
+                job.error_message = f"Celery 任务投递失败: {exc}"
+                job.error_code = "AsyncDispatchFailed"
+                job.updated_at = datetime.now(timezone.utc)
         else:
             # 2b. 直接音频模式：同步签名并提交 MediaKit
             video_url = self._sign_media_url(video_url)

apps/api/app/tasks/lipsync_tts.py

@@ -76,11 +76,21 @@ def tts_synthesize_and_submit(
     from app.services.mediakit_client import MediaKitError, get_mediakit_client
     from sqlalchemy.orm import Session as DBSession
 
-    from packages.adapters.sqlalchemy_impl.database import SessionLocal
     from packages.adapters.sqlalchemy_impl.models import LipsyncJobModel
     from packages.application.cosyvoice_service import CosyVoiceError, CosyVoiceService
     from packages.shared.url_security import safe_download_bytes
 
+    # SessionLocal 获取：
+    # - API 容器：app.db.SessionLocal（环境变量完整，导入即建引擎）
+    # - Worker 容器：worker_app.db.SessionLocal（Worker 自己的 settings 初始化引擎）
+    # API 侧没有 worker_app 模块 → ImportError 直接回退；
+    # Worker 侧 app.db 会因缺少 API 专有环境变量抛 pydantic ValidationError，
+    # 此时也要回退到 worker_app.db。
+    try:
+        from worker_app.db import SessionLocal  # type: ignore
+    except Exception:  # noqa: BLE001
+        from app.db import SessionLocal  # type: ignore
+
     db: DBSession = SessionLocal()
     try:
         job = (

infra/docker/nginx-entrypoint.sh

@@ -2,16 +2,21 @@
 # Select nginx config based on APP_ENV (staging/production).
 # Both configs are baked into the image at well-known paths.
 # nginx reads config only at startup, so symlink before exec.
+# 注意：基础镜像 /etc/nginx/conf.d/default.conf 是普通文件（非 symlink/目录），
+# alpine busybox ln -sf 在 target 已存在且为普通文件时行为不稳定（会尝试在
+# target 目录下建子链接），必须先 rm 再 ln 才能正确替换。
 set -e
 
 NGINX_CONF_DIR="/etc/nginx/conf.d"
 
 case "${APP_ENV:-production}" in
   staging)
-    ln -sf /etc/nginx/nginx-staging.conf "$NGINX_CONF_DIR/default.conf"
+    rm -f "$NGINX_CONF_DIR/default.conf"
+    ln -s /etc/nginx/nginx-staging.conf "$NGINX_CONF_DIR/default.conf"
     ;;
   *)
-    ln -sf /etc/nginx/nginx-production.conf "$NGINX_CONF_DIR/default.conf"
+    rm -f "$NGINX_CONF_DIR/default.conf"
+    ln -s /etc/nginx/nginx-production.conf "$NGINX_CONF_DIR/default.conf"
     ;;
 esac
 

packages/__init__.py

@@ -0,0 +1 @@
+# xiaoxia-saas shared packages namespace

packages/adapters/__init__.py

@@ -0,0 +1 @@
+# adapter implementations namespace

tests/unit/test_lipsync_speed_optimization.py

@@ -143,8 +143,8 @@ class TestCreateJobAsyncTTS:
         assert args[2] == "v-1"  # voice_id
         assert args[3] == "测试文本"  # script_text
 
-    def test_tts_mode_celery_dispatch_failure_still_creates_job(self):
-        """Celery dispatch 失败时，job 记录已创建，状态保持 tts_processing."""
+    def test_tts_mode_celery_dispatch_failure_marks_job_failed(self):
+        """Celery dispatch 失败时，job 标为 failed 并写入 error_message，前端轮询能直接看到错误."""
         svc, client, cosy = _make_service_with_mocks()
 
         with patch("app.services.lipsync_service.tts_synthesize_and_submit") as mock_task:
@@ -157,9 +157,11 @@ class TestCreateJobAsyncTTS:
                 script_text="测试文本",
             )
 
-        # job 已创建
+        # job 已创建且状态标为 failed
         assert job is not None
-        assert job.status == "tts_processing"
+        assert job.status == "failed"
+        assert "Celery 任务投递失败" in job.error_message
+        assert job.error_code == "AsyncDispatchFailed"
         # MediaKit 未被调用
         client.submit_lipsync.assert_not_called()
 

tests/unit/test_lipsync_tts.py

@@ -73,12 +73,16 @@ def _apply_all_patches(
     lipsync_tts.run() 在函数体内部懒 import 多个模块，通过 sys.modules 注入
     伪造包路径避免真实导入；对存在的模块用 patch() 替换返回值/side_effect。
     """
-    fake_db_mod = ModuleType("packages.adapters.sqlalchemy_impl.database")
+    # SessionLocal 通过懒探测获取（Worker 用 worker_app.db，API 用 app.db），
+    # 测试环境里两个模块都能被真实导入，必须同时 mock 保证用的是 fake session。
+    fake_app_db = ModuleType("app.db")
+    fake_worker_db = ModuleType("worker_app.db")
     session, factory = _build_session(job)
-    fake_db_mod.SessionLocal = factory
+    fake_app_db.SessionLocal = factory
+    fake_worker_db.SessionLocal = factory
 
     patches = [
-        patch.dict(sys.modules, {"packages.adapters.sqlalchemy_impl.database": fake_db_mod}),
+        patch.dict(sys.modules, {"app.db": fake_app_db, "worker_app.db": fake_worker_db}),
         patch(
             "app.tasks.lipsync_tts._sign_media_url",
             side_effect=lambda url: url + "?signed" if url else url,
@@ -289,9 +293,11 @@ class TestTtsSynthesizeAndSubmit:
         from app.tasks.lipsync_tts import tts_synthesize_and_submit
 
         job = _make_fake_job()
-        fake_db_mod = ModuleType("packages.adapters.sqlalchemy_impl.database")
+        fake_app_db = ModuleType("app.db")
+        fake_worker_db = ModuleType("worker_app.db")
         session, factory = _build_session(job)
-        fake_db_mod.SessionLocal = factory
+        fake_app_db.SessionLocal = factory
+        fake_worker_db.SessionLocal = factory
 
         # CosyVoiceService 在 __init__ 抛 RuntimeError（非 CosyVoiceError/ValueError）
         fake_cosy_mod = ModuleType("packages.application.cosyvoice_service")
@@ -309,7 +315,8 @@ class TestTtsSynthesizeAndSubmit:
         with patch.dict(
             sys.modules,
             {
-                "packages.adapters.sqlalchemy_impl.database": fake_db_mod,
+                "app.db": fake_app_db,
+                "worker_app.db": fake_worker_db,
                 "packages.application.cosyvoice_service": fake_cosy_mod,
             },
         ):