debug: AI数字人克隆音色试听加 Network/Console 调试日志

- 请求前打印 voice_id/voice_name/voice_clone_profile_id
- 响应后打印 audio_url 前80字符 + duration
- catch 打印 HTTP status + response data + message
- 帮助定位 /tts/preview 400/422/500/502 具体原因

.gitea/workflows/ci-pipeline.yml

@@ -20,7 +20,6 @@ on:
         default: "手动触发 - CI漏触发补跑"
 permissions:
   contents: read
-  pull-requests: read
 concurrency:
   group: ci-pipeline-${{ gitea.ref }}
   cancel-in-progress: true
@@ -89,22 +88,9 @@ jobs:
         GITHUB_TOKEN: ${{ github.token }}
       run: |
         set -eu
-        # 优先用 git diff 判断 PR 改动范围（比 API 稳定）
         PR_NUMBER=$(echo "$GITHUB_REF" | sed 's|refs/pull/||; s|/.*||')
-        if command -v git >/dev/null 2>&1 && [ -d .git ]; then
-          FILES=$(git diff --name-only origin/develop...HEAD 2>/dev/null || true)
-        fi
-        if [ -z "${FILES:-}" ]; then
-          # fallback 到 API
-          API_URL="${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/pulls/${PR_NUMBER}/files?limit=300"
-          FILES=$(curl -sf -H "Authorization: token ${GITHUB_TOKEN}" "$API_URL" | python3 -c "import sys,json; [print(f['filename']) for f in json.load(sys.stdin)]" 2>/dev/null || true)
-        fi
-        if [ -z "${FILES:-}" ]; then
-          echo "⚠️ 无法获取变更文件列表，保守运行完整 CI"
-          echo "skip_backend=false" >> $GITHUB_OUTPUT
-          echo "skip_frontend=false" >> $GITHUB_OUTPUT
-          exit 0
-        fi
+        API_URL="${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/pulls/${PR_NUMBER}/files?limit=300"
+        FILES=$(curl -s -H "Authorization: token ${GITHUB_TOKEN}" "$API_URL" | python3 -c "import sys,json; [print(f['filename']) for f in json.load(sys.stdin)]")
         FRONTEND_COUNT=$(echo "$FILES" | grep -c '^apps/web/' || true)
         BACKEND_COUNT=$(echo "$FILES" | grep -cv '^apps/web/' || true)
         TOTAL=$(echo "$FILES" | grep -cv '^$' || true)
@@ -196,7 +182,7 @@ jobs:
     - name: Run style checks
       shell: bash
       run: bash scripts/ci/validate_style.sh
-    - name: Auto-fix formatting (black + isort + ruff)
+    - name: Auto-fix formatting (black + isort)
       if: failure()
       shell: sh
       env:

alembic/versions/073_add_lipsync_tts_fields.py

@@ -1,45 +0,0 @@
-"""lipsync_jobs 增加 TTS 直生字段（voice_id/script_text/speed/emotion）
-
-Revision ID: 073_add_lipsync_tts_fields
-Revises: 072_add_ai_avatar_render
-Create Date: 2026-09-09
-"""
-
-import sqlalchemy as sa
-
-from alembic import op
-
-revision = "073_add_lipsync_tts_fields"
-down_revision = "072_add_ai_avatar_render"
-branch_labels = None
-depends_on = None
-
-
-def upgrade() -> None:
-    # 对口型支持「传音色 + 文案直接生成」：后端内部先 TTS 合成音频再提交对口型
-    op.add_column(
-        "lipsync_jobs",
-        sa.Column("voice_id", sa.String(200), nullable=False, server_default=""),
-    )
-    op.add_column(
-        "lipsync_jobs",
-        sa.Column("script_text", sa.Text(), nullable=False, server_default=""),
-    )
-    op.add_column(
-        "lipsync_jobs",
-        sa.Column("speed", sa.Float(), nullable=False, server_default=sa.text("1.0")),
-    )
-    op.add_column(
-        "lipsync_jobs",
-        sa.Column("emotion", sa.String(20), nullable=False, server_default=""),
-    )
-    # audio_url 改为可空：直生模式下音频由后端 TTS 合成后回填
-    op.alter_column("lipsync_jobs", "audio_url", existing_type=sa.Text(), nullable=True)
-
-
-def downgrade() -> None:
-    op.alter_column("lipsync_jobs", "audio_url", existing_type=sa.Text(), nullable=False)
-    op.drop_column("lipsync_jobs", "emotion")
-    op.drop_column("lipsync_jobs", "speed")
-    op.drop_column("lipsync_jobs", "script_text")
-    op.drop_column("lipsync_jobs", "voice_id")

alembic/versions/074_ai_avatar_render_script_id_optional.py

@@ -1,36 +0,0 @@
-"""ai_avatar_render_jobs.script_id 放宽为可空串（手动文案直生场景不关联文案库）
-
-Revision ID: 074_render_script_id_optional
-Revises: 073_add_lipsync_tts_fields
-Create Date: 2026-09-09
-"""
-
-import sqlalchemy as sa
-
-from alembic import op
-
-revision = "074_render_script_id_optional"
-down_revision = "073_add_lipsync_tts_fields"
-branch_labels = None
-depends_on = None
-
-
-def upgrade() -> None:
-    # 列保持 NOT NULL（空串占位），仅应用层允许不传；这里显式补 server_default 防止历史约束歧义
-    with op.batch_alter_table("ai_avatar_render_jobs") as batch:
-        batch.alter_column(
-            "script_id",
-            existing_type=sa.String(length=36),
-            nullable=False,
-            server_default="",
-        )
-
-
-def downgrade() -> None:
-    with op.batch_alter_table("ai_avatar_render_jobs") as batch:
-        batch.alter_column(
-            "script_id",
-            existing_type=sa.String(length=36),
-            nullable=False,
-            server_default=None,
-        )

apps/api/app/api/routes/ai_avatar_render.py

@@ -17,10 +17,7 @@ from app.dependencies import get_db_session
 from app.schemas.ai_avatar_render import (
     AiAvatarRenderJobResponse,
     CreateAiAvatarRenderRequest,
-    SmartCoverRequest,
-    SmartCoverResponse,
 )
-from app.services.ai_avatar_cover_service import generate_smart_cover
 from app.services.ai_avatar_render_service import (
     AiAvatarRenderError,
     AiAvatarRenderService,
@@ -52,7 +49,7 @@ def create_render_job(
     """
     try:
         job = svc.create_render_job(
-            user_id=current_user.user.id,
+            user_id=current_user.id,
             lipsync_job_id=body.lipsync_job_id,
             script_id=body.script_id,
             b_roll_segments=[s.model_dump() for s in body.b_roll_segments],
@@ -97,7 +94,7 @@ def list_render_jobs(
 ):
     """获取 AI 数字人渲染任务列表."""
     items, total = svc.list_render_jobs(
-        user_id=current_user.user.id,
+        user_id=current_user.id,
         project_id=project_id,
         status=status,
         offset=offset,
@@ -121,7 +118,7 @@ def get_render_job(
     svc: AiAvatarRenderService = Depends(_get_service),
 ):
     """获取渲染任务详情."""
-    job = svc.get_render_job(job_id, current_user.user.id)
+    job = svc.get_render_job(job_id, current_user.id)
     if job is None:
         raise HTTPException(status_code=404, detail="渲染任务不存在")
     return job
@@ -137,7 +134,7 @@ def cancel_render_job(
     svc: AiAvatarRenderService = Depends(_get_service),
 ):
     """取消渲染任务（仅 pending 状态可取消）."""
-    job = svc.cancel_render_job(job_id, current_user.user.id)
+    job = svc.cancel_render_job(job_id, current_user.id)
     if job is None:
         raise HTTPException(status_code=404, detail="渲染任务不存在")
     if job.status != "cancelled":
@@ -158,7 +155,7 @@ def retry_render_job(
     svc: AiAvatarRenderService = Depends(_get_service),
 ):
     """重试失败的渲染任务."""
-    job = svc.retry_render_job(job_id, current_user.user.id)
+    job = svc.retry_render_job(job_id, current_user.id)
     if job is None:
         raise HTTPException(status_code=404, detail="渲染任务不存在")
     if job.status != "pending":
@@ -176,43 +173,3 @@ def retry_render_job(
         logger.warning("Celery 任务提交失败，重试任务已重置但未触发执行: %s", job.id)
 
     return job
-
-
-
-# ── POST /smart-cover — 智能获取封面（MediaKit 抽帧 + 评分选帧）────────
-
-
-@router.post("/smart-cover", response_model=SmartCoverResponse)
-def generate_avatar_smart_cover(
-    body: SmartCoverRequest,
-    current_user: AuthenticatedUser = Depends(get_current_user),
-) -> SmartCoverResponse:
-    """智能获取数字人视频封面.
-
-    复用智能剪辑的 MediaKit 抽帧 + 质量评分选最佳帧逻辑（非 FFmpeg 简单截帧），
-    并将选中帧转存到自家 OSS，返回非临时的封面公网 URL。
-
-    前端「智能获取封面」按钮可直接调用本接口；不依赖渲染任务完成。
-    """
-    video_url = (body.video_url or "").strip()
-    if not video_url.startswith(("http://", "https://")):
-        raise HTTPException(status_code=400, detail="video_url 必须是合法的 HTTP/HTTPS URL")
-
-    try:
-        cover_url = generate_smart_cover(video_url, max_frames=body.max_frames)
-    except Exception as exc:
-        logger.error(
-            "智能封面生成异常: user=%s video_url=%s err=%s",
-            current_user.user.id, video_url[:80], exc,
-            exc_info=True,
-        )
-        cover_url = ""
-
-    if not cover_url:
-        return SmartCoverResponse(
-            cover_url="",
-            status="fallback_failed",
-            message="智能抽帧失败（MediaKit 不可用或抽帧异常），请稍后重试",
-        )
-    logger.info("智能封面生成成功: user=%s cover_url=%s", current_user.user.id, cover_url[:120])
-    return SmartCoverResponse(cover_url=cover_url, status="completed")

apps/api/app/api/routes/chunked_upload.py

@@ -177,8 +177,8 @@ def _cleanup_expired_uploads() -> int:
                 meta_file.unlink()
                 cleaned += 1
                 logger.info(f"Cleaned up expired upload: {upload_id}")
-        except Exception:
-            logger.exception("Failed to cleanup upload metadata: %s", meta_file)
+        except Exception as e:
+            logger.warning(f"Failed to cleanup upload metadata {meta_file}: {e}")
 
     return cleaned
 

apps/api/app/api/routes/generation_variant_plans.py

@@ -108,7 +108,7 @@ def create_variant_plans(
             if _latest:
                 source_plan_id = _latest.id
         except Exception:
-            logger.exception("[variant-plans] 源 plan 解析失败")
+            logger.warning("[variant-plans] 源 plan 解析失败", exc_info=True)
 
     if not source_plan_id:
         raise HTTPException(
@@ -122,7 +122,7 @@ def create_variant_plans(
 
         voice_durations = _query_voice_durations(db, voices)
     except Exception:
-        logger.exception("[variant-plans] 配音时长查询失败（按占位段长选片）")
+        logger.warning("[variant-plans] 配音时长查询失败（按占位段长选片）", exc_info=True)
         voice_durations = [0.0] * request.count
 
     from app.services.edit_plan_service import EditPlanService
@@ -143,7 +143,7 @@ def create_variant_plans(
     except HTTPException:
         raise
     except Exception as e:
-        logger.exception("[variant-plans] 选片异常")
+        logger.error("[variant-plans] 选片异常: %s", e, exc_info=True)
         raise HTTPException(status_code=500, detail="选片失败，请稍后重试") from e
 
     # 组装 clips 响应

apps/api/app/api/routes/lipsync.py

@@ -13,16 +13,15 @@ from __future__ import annotations
 import logging
 
 from app.auth import AuthenticatedUser, get_current_user
-from app.dependencies import (
-    get_db_session,
-    get_voice_clone_profile_repository,
-)
+from app.dependencies import get_cosyvoice_service, get_db_session, get_voice_clone_profile_repository
 from app.schemas.lipsync import CreateLipsyncJobRequest, LipsyncJobResponse
 from app.services.lipsync_service import LipsyncService
 from app.services.mediakit_client import MediaKitError
-from fastapi import APIRouter, BackgroundTasks, Depends, HTTPException, Query
+from fastapi import APIRouter, Depends, HTTPException, Query
 from sqlalchemy.orm import Session
 
+from packages.application.cosyvoice_service import CosyVoiceError, CosyVoiceService
+
 logger = logging.getLogger(__name__)
 
 router = APIRouter()
@@ -30,14 +29,35 @@ router = APIRouter()
 
 def _get_service(
     db: Session = Depends(get_db_session),
-    voice_clone_repo=Depends(get_voice_clone_profile_repository),
+    cosyvoice_service: CosyVoiceService = Depends(get_cosyvoice_service),
 ) -> LipsyncService:
-    # voice_clone_repo 用于克隆音色 profile 解析
-    # TTS 合成已移至 Celery 异步任务，无需同步注入 cosyvoice_service
-    return LipsyncService(
-        db,
-        voice_clone_repo=voice_clone_repo,
-    )
+    return LipsyncService(db, cosyvoice_service=cosyvoice_service)
+
+
+def _resolve_voice_id(
+    raw_voice_id: str,
+    user_id: str,
+    voice_clone_repo,
+) -> str:
+    """解析 voice_id：支持预设音色 ID 或克隆音色 profile UUID.
+
+    与 TTS 路由保持一致：命中 profile → 校验归属 → 取 CosyVoice voice_id。
+    """
+    try:
+        profile = voice_clone_repo.get(raw_voice_id)
+    except Exception as exc:
+        logger.error("查询克隆音色失败: voice_id=%s, error=%s", raw_voice_id, exc)
+        raise HTTPException(
+            status_code=400,
+            detail=f"voice_id 无效: {raw_voice_id}",
+        ) from exc
+    if profile is not None:
+        if profile.user_id != user_id:
+            raise HTTPException(status_code=403, detail="无权访问该音色")
+        if not profile.voice_id:
+            raise HTTPException(status_code=400, detail="音色克隆尚未完成，请稍后再试")
+        return profile.voice_id
+    return raw_voice_id
 
 
 # ── POST /jobs — 提交对口型任务 ───────────────────────────────────────────
@@ -48,41 +68,41 @@ def create_lipsync_job(
     body: CreateLipsyncJobRequest,
     current_user: AuthenticatedUser = Depends(get_current_user),
     svc: LipsyncService = Depends(_get_service),
+    voice_clone_repo=Depends(get_voice_clone_profile_repository),
 ):
     """提交对口型任务.
 
-    #1809/#1822: 前端传 {video_url, voice_id, script_text, speed?, emotion?}，
-    后端创建任务记录（状态 tts_processing），dispatch Celery 异步任务执行 TTS 合成 + MediaKit 提交；
-    也支持直接传 {video_url, audio_url}（同步提交 MediaKit）。
+    #1809: 前端传 {voice_id, script_text, video_url}，
+    后端内部调 TTS 合成音频，再提交 MediaKit。
     """
+    # 解析 voice_id（支持克隆音色 profile UUID）
+    actual_voice_id = _resolve_voice_id(body.voice_id, current_user.id, voice_clone_repo)
+
     try:
         job = svc.create_job(
-            user_id=current_user.user.id,
+            user_id=current_user.id,
             video_url=body.video_url,
-            audio_url=body.audio_url,
-            voice_id=body.voice_id,
+            voice_id=actual_voice_id,
             script_text=body.script_text,
-            speed=body.speed,
-            emotion=body.emotion,
             enable_video_loop=body.enable_video_loop,
             project_id=body.project_id,
         )
     except ValueError as exc:
         # 参数无效（如 voice_id 格式不对、文本过长等）
         raise HTTPException(status_code=400, detail=str(exc)) from exc
-    except MediaKitError as exc:
-        # 音色无权访问 → 403；参数无效 → 400；MediaKit 提交失败 → 502
-        status_code = 502
-        if exc.code in ("VoiceForbidden",):
-            status_code = 403
-        elif exc.code in ("InvalidInput", "TTSInvalidParam", "VoiceNotReady"):
-            status_code = 400
+    except CosyVoiceError as exc:
+        # TTS 合成基础设施失败（API/网络/认证）
         raise HTTPException(
-            status_code=status_code,
+            status_code=502,
+            detail={"code": "TTSSynthesisFailed", "message": str(exc)},
+        ) from exc
+    except MediaKitError as exc:
+        raise HTTPException(
+            status_code=502,
             detail={
                 "code": exc.code,
                 "message": str(exc),
-                "request_id": getattr(exc, "request_id", ""),
+                "request_id": exc.request_id,
             },
         ) from exc
     except Exception as exc:
@@ -110,7 +130,7 @@ def list_lipsync_jobs(
 ):
     """获取对口型任务列表."""
     items, total = svc.list_jobs(
-        user_id=current_user.user.id,
+        user_id=current_user.id,
         project_id=project_id,
         status=status,
         offset=offset,
@@ -130,22 +150,13 @@ def list_lipsync_jobs(
 @router.get("/jobs/{job_id}", response_model=LipsyncJobResponse)
 def get_lipsync_job(
     job_id: str,
-    background: BackgroundTasks,
     current_user: AuthenticatedUser = Depends(get_current_user),
     svc: LipsyncService = Depends(_get_service),
 ):
-    """获取对口型任务详情.
-
-    非终态任务：先返回 DB 缓存，挂后台刷新（下次轮询拿到新状态），
-    避免 MediaKit 慢响应阻塞前端轮询。
-    """
-    job = svc.get_job(job_id, current_user.user.id)
+    """获取对口型任务详情."""
+    job = svc.get_job(job_id, current_user.id)
     if job is None:
         raise HTTPException(status_code=404, detail="任务不存在")
-
-    if job.status not in ("completed", "failed"):
-        background.add_task(svc.refresh_job_status, job_id, current_user.user.id)
-
     return job
 
 
@@ -159,7 +170,7 @@ def refresh_lipsync_job(
     svc: LipsyncService = Depends(_get_service),
 ):
     """从 MediaKit 拉取最新状态并更新."""
-    job = svc.refresh_job_status(job_id, current_user.user.id)
+    job = svc.refresh_job_status(job_id, current_user.id)
     if job is None:
         raise HTTPException(status_code=404, detail="任务不存在")
     return job
@@ -174,13 +185,13 @@ def cancel_lipsync_job(
     current_user: AuthenticatedUser = Depends(get_current_user),
     svc: LipsyncService = Depends(_get_service),
 ):
-    """取消对口型任务（仅 pending/tts_processing/submitted 状态可取消）."""
-    job = svc.cancel_job(job_id, current_user.user.id)
+    """取消对口型任务（仅 pending/submitted 状态可取消）."""
+    job = svc.cancel_job(job_id, current_user.id)
     if job is None:
         raise HTTPException(status_code=404, detail="任务不存在")
     if job.status != "cancelled":
         raise HTTPException(
             status_code=400,
-            detail=f"任务状态 {job.status} 不可取消，仅 pending/tts_processing/submitted 可取消",
+            detail=f"任务状态 {job.status} 不可取消，仅 pending/submitted 可取消",
         )
     return job

apps/api/app/api/routes/templates_editor/ai_features.py

@@ -65,8 +65,8 @@ def _build_asset_analyses(
                 if url:
                     video_urls.append(url)
                     valid_asset_ids.append(aid)
-            except Exception:
-                logger.exception("获取素材URL失败: asset_id=%s", aid)
+            except Exception as e:
+                logger.warning("获取素材URL失败: asset_id=%s error=%s", aid, str(e))
 
         if not video_urls:
             logger.info("无可用视频素材，跳过视频理解分析")
@@ -108,7 +108,7 @@ def _build_asset_analyses(
         return analyses
 
     except Exception as e:
-        logger.exception("MediaKit 视频理解异常，将降级到无分析模式: %s", e)
+        logger.warning("MediaKit 视频理解异常，将降级到无分析模式: %s", str(e))
         return {}
 
 
@@ -177,7 +177,7 @@ def editor_ai_recommend(
         try:
             db.rollback()
         except Exception:
-            logger.exception("db rollback failed in ai_recommend")
+            pass
         raise HTTPException(
             status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
             detail="AI推荐结果保存失败，请稍后重试",

apps/api/app/api/routes/templates_editor/clips.py

@@ -132,8 +132,8 @@ def _build_asset_url_map(
     result: dict[str, str | None] = {}
     try:
         storage = get_storage_service()
-    except Exception as e:
-        logger.exception("获取存储服务失败，跳过asset_url生成: %s", e)
+    except Exception:
+        logger.warning("获取存储服务失败，跳过asset_url生成")
         return {aid: None for aid in asset_ids}
 
     # 批量查询所有 Asset（单次 SQL IN 查询，避免 N+1）
@@ -141,7 +141,7 @@ def _build_asset_url_map(
         assets = asset_repo.find_by_ids(unique_ids)
         asset_map = {a.id: a for a in assets}
     except Exception:
-        logger.exception("批量查询素材失败: asset_ids=%s", asset_ids)
+        logger.warning("批量查询素材失败: asset_ids=%s", asset_ids, exc_info=True)
         return {aid: None for aid in asset_ids if aid}
 
     for aid in unique_ids:
@@ -156,7 +156,7 @@ def _build_asset_url_map(
                 continue
             result[aid] = storage.get_download_url(storage_key, expires_seconds=3600)
         except Exception:
-            logger.exception("生成素材签名URL失败: asset_id=%s", aid)
+            logger.warning("生成素材签名URL失败: asset_id=%s", aid, exc_info=True)
             result[aid] = None
 
     return result
@@ -486,8 +486,8 @@ def _get_mediakit_recommendations(
                 if url:
                     video_urls.append(url)
                     valid_asset_ids.append(asset_id)
-            except Exception:
-                logger.exception("获取素材URL失败: asset_id=%s", asset_id)
+            except Exception as e:
+                logger.warning("获取素材URL失败: asset_id=%s error=%s", asset_id, e)
 
         if not video_urls:
             return {}
@@ -563,7 +563,7 @@ def _get_mediakit_recommendations(
         return recommendations
 
     except Exception as e:
-        logger.exception("MediaKit 智能选片异常，降级为随机选择: %s", e)
+        logger.warning("MediaKit 智能选片异常，降级为随机选择: %s", e)
         return {}
 
 
@@ -860,7 +860,7 @@ def create_clips_from_assets_editor(
     duplicate_warning = None
     if dup_rate > 50:
         duplicate_warning = f"查重率 {dup_rate:.1f}% 超过50%，建议更换素材或模板"
-        logger.exception(
+        logger.warning(
             "from-assets 成片查重率超标: plan_id=%s dup_rate=%.1f%%",
             plan_id,
             dup_rate,
@@ -960,8 +960,8 @@ def _update_mediakit_recommendations_async(  # pragma: no cover
         # 尝试获取存储服务（用于生成视频 URL）
         try:
             storage = get_storage_service()
-        except Exception as e:
-            logger.exception("后台任务: 获取存储服务失败，跳过 SceneChange 更新: %s", e)
+        except Exception:
+            logger.warning("后台任务: 获取存储服务失败，跳过 SceneChange 更新")
             return
 
         # 获取 MediaKit 客户端
@@ -987,8 +987,8 @@ def _update_mediakit_recommendations_async(  # pragma: no cover
             if storage_key and mime.startswith("video/"):
                 try:
                     video_url = storage.get_download_url(storage_key)
-                except Exception:
-                    logger.exception("后台任务: 获取素材URL失败: asset_id=%s", asset_id)
+                except Exception as e:
+                    logger.warning("后台任务: 获取素材URL失败: asset_id=%s error=%s", asset_id, e)
 
             # 构建该素材的占用区间列表（排除已更新片段）
             def _get_other_segments(asset_id_inner, clip_id_inner):
@@ -1039,11 +1039,12 @@ def _update_mediakit_recommendations_async(  # pragma: no cover
                             asset_id,
                             len(scene_changes),
                         )
-                    except Exception:
+                    except Exception as cache_err:
                         # 缓存写入失败不影响本次片段更新
-                        logger.exception(
-                            "后台任务: 场景点缓存写入失败: asset_id=%s",
+                        logger.warning(
+                            "后台任务: 场景点缓存写入失败: asset_id=%s error=%s",
                             asset_id,
+                            cache_err,
                         )
 
             # SceneChange 未获得有效结果 → 尝试 analyze_videos 作为 fallback
@@ -1123,10 +1124,11 @@ def _update_mediakit_recommendations_async(  # pragma: no cover
                                 recommended_start + clip_duration,
                                 plan_id,
                             )
-                    except Exception:
-                        logger.exception(
-                            "后台任务: 同步素材区间记录失败，回滚本次片段更新: clip_id=%s",
+                    except Exception as me:
+                        logger.warning(
+                            "后台任务: 同步素材区间记录失败，回滚本次片段更新: clip_id=%s error=%s",
                             clip.id,
+                            me,
                         )
                         db.rollback()
                         continue
@@ -1142,8 +1144,8 @@ def _update_mediakit_recommendations_async(  # pragma: no cover
                         asset_id,
                         recommended_start,
                     )
-                except Exception:
-                    logger.exception("后台任务: 单个片段更新失败: clip_id=%s", clip.id)
+                except Exception as ue:
+                    logger.warning("后台任务: 单个片段更新失败: clip_id=%s error=%s", clip.id, ue)
                     try:
                         db.rollback()
                     except Exception:
@@ -1152,9 +1154,9 @@ def _update_mediakit_recommendations_async(  # pragma: no cover
 
         logger.info("后台任务完成: plan_id=%s 成功更新 %d 个片段", plan_id, updated_count)
 
-    except Exception:
+    except Exception as e:
         # 后台任务失败不影响已创建的片段，静默处理
-        logger.exception("后台任务异常: plan_id=%s", plan_id)
+        logger.warning("后台任务异常: plan_id=%s error=%s", plan_id, e, exc_info=True)
         if db:
             try:
                 db.rollback()

apps/api/app/api/routes/tts.py

@@ -173,14 +173,6 @@ def synthesize(
         # job.voice_id 统一存解析后的 CosyVoice voice_id
         actual_voice_id = resolved_profile.voice_id
 
-    # 语速/情绪等合成参数随 metadata 落库，workflow 提交 CosyVoice 时读取透传
-    synthesis_meta = {
-        "speed": request.speed,
-        "emotion": request.emotion or "",
-    }
-    if request.metadata_:
-        synthesis_meta.update(request.metadata_)
-
     use_case = CreateTTSJobUseCase(repository)
     job = use_case.execute(
         user_id=user_id,
@@ -188,7 +180,7 @@ def synthesize(
         voice_id=actual_voice_id,
         voice_model=request.voice_model,
         voice_clone_profile_id=voice_clone_profile_id,
-        metadata=synthesis_meta,
+        metadata=request.metadata_,
     )
 
     # 提交 CosyVoice 合成任务
@@ -575,7 +567,6 @@ def preview_tts(
             text=request.text,
             voice_id=actual_voice_id,
             speed=request.speed,
-            emotion=request.emotion,
         )
     except CosyVoiceError as e:
         raise HTTPException(

apps/api/app/api/routes/voice_clones.py

@@ -163,12 +163,12 @@ def create_voice_clone(
             celery_app.send_task("worker.process_voice_clone", args=[profile.id])
             logger.info(f"Celery task dispatched for voice clone {profile.id}")
         except Exception as e:
-            logger.exception("Failed to dispatch Celery task")
+            logger.error(f"Failed to dispatch Celery task: {e}")
             # P2-3: Celery 调度失败时标记 profile 为 failed，避免永久卡在 processing
             try:
                 workflow.process_clone_failure(profile.id, f"Celery 任务调度失败: {e}")
-            except Exception:
-                logger.exception("Failed to mark profile as failed after dispatch error")
+            except Exception as inner_e:
+                logger.error(f"Failed to mark profile as failed after dispatch error: {inner_e}")
 
     return _to_response(profile)
 
@@ -277,12 +277,12 @@ def retry_voice_clone(
             celery_app.send_task("worker.process_voice_clone", args=[profile.id])
             logger.info(f"Celery task dispatched for voice clone retry {profile.id}")
         except Exception as e:
-            logger.exception("Failed to dispatch Celery task")
+            logger.error(f"Failed to dispatch Celery task: {e}")
             # P2-3: Celery 调度失败时标记 profile 为 failed，避免永久卡在 processing
             try:
                 workflow.process_clone_failure(profile.id, f"Celery 任务调度失败: {e}")
-            except Exception:
-                logger.exception("Failed to mark profile as failed after dispatch error")
+            except Exception as inner_e:
+                logger.error(f"Failed to mark profile as failed after dispatch error: {inner_e}")
 
     return _to_response(profile)
 

apps/api/app/api/routes/voices.py

@@ -105,8 +105,8 @@ def _resolve_preset_preview_url(
         _preset_preview_cache[voice_id] = (audio_url, time.time())
         logger.info("Preset voice preview generated: %s", voice_id)
         return audio_url
-    except Exception:
-        logger.exception("Failed to generate preset voice preview: voice_id=%s", voice_id)
+    except Exception as e:
+        logger.warning("Failed to generate preview for %s, using fallback: %s", voice_id, e)
         return fallback_url
 
 
@@ -127,7 +127,6 @@ def _resolve_all_preset_preview_urls(
         try:
             result_map[p.voice_id] = _resolve_preset_preview_url(p.voice_id, p.preview_url, cosyvoice)
         except Exception:
-            logger.exception("Failed to resolve preset preview URL: voice_id=%s", p.voice_id)
             result_map[p.voice_id] = p.preview_url
     return result_map
 
@@ -733,7 +732,7 @@ def _find_or_create_voice_library_for_extract(*, user_id, project_repository, as
             try:
                 session.rollback()
             except Exception:
-                logger.exception("session rollback failed in _find_or_create_voice_library")
+                pass
         for lib in asset_library_repository.find_by_project(project.id):
             kind = lib.kind.value if hasattr(lib.kind, "value") else lib.kind
             if kind == AssetLibraryKind.VOICE.value:

apps/api/app/schemas/ai_avatar_render.py

@@ -50,7 +50,7 @@ class CreateAiAvatarRenderRequest(BaseModel):
     """创建渲染任务请求."""
 
     lipsync_job_id: str = Field(..., description="对口型任务 ID")
-    script_id: str = Field("", description="文案 ID（选自文案库时传；手动输入文案直生场景可留空）")
+    script_id: str = Field(..., description="文案 ID")
     b_roll_segments: list[BRollSegment] = Field(default_factory=list, description="B-roll 片段列表")
     title_config: dict[str, Any] = Field(default_factory=dict, description="标题配置")
     cover_config: dict[str, Any] = Field(default_factory=dict, description="封面配置")
@@ -67,8 +67,10 @@ class CreateAiAvatarRenderRequest(BaseModel):
     @field_validator("script_id")
     @classmethod
     def validate_script_id(cls, v: str) -> str:
-        # script_id 可选：手动输入文案（TTS 直生）场景不关联文案库条目
-        return (v or "").strip()
+        v = v.strip()
+        if not v:
+            raise ValueError("script_id 不能为空")
+        return v
 
 
 class AiAvatarRenderJobResponse(BaseModel):
@@ -78,7 +80,7 @@ class AiAvatarRenderJobResponse(BaseModel):
     user_id: str
     project_id: str
     lipsync_job_id: str
-    script_id: str = ""
+    script_id: str
     b_roll_segments: list[dict[str, Any]]
     title_config: dict[str, Any]
     cover_config: dict[str, Any]
@@ -107,18 +109,3 @@ class AiAvatarRenderProgressResponse(BaseModel):
     output_cover_url: str
     output_duration: float
     error_message: str
-
-
-class SmartCoverRequest(BaseModel):
-    """智能封面请求 — MediaKit 抽帧 + 质量评分选最佳帧."""
-
-    video_url: str = Field(..., description="数字人视频 URL（对口型/渲染成片）")
-    max_frames: int = Field(5, ge=1, le=10, description="抽帧数量（默认 5）")
-
-
-class SmartCoverResponse(BaseModel):
-    """智能封面响应."""
-
-    cover_url: str = Field("", description="封面图公网 URL（OSS，非临时）；失败为空")
-    status: str = Field("completed", description="completed / fallback_failed")
-    message: str = Field("", description="失败原因（如有）")

apps/api/app/schemas/lipsync.py

@@ -1,17 +1,11 @@
-"""对口型 API Schema 定义 — #1796 / #1809 / #1822.
-
-支持两种输入模式（二选一）：
-1. TTS 直生模式（推荐）：传 voice_id + script_text（+ speed/emotion），
-   后端内部先调 CosyVoice 合成音频，再提交 MediaKit 对口型。
-2. 直接音频模式：传 video_url + audio_url（音频已由调用方准备好）。
-"""
+"""对口型 API Schema 定义 — #1796, #1809 参数调整."""
 
 from __future__ import annotations
 
 from datetime import datetime
 from typing import Optional
 
-from pydantic import BaseModel, Field, model_validator
+from pydantic import BaseModel, Field, field_validator
 
 
 class LipsyncJobResponse(BaseModel):
@@ -23,10 +17,6 @@ class LipsyncJobResponse(BaseModel):
     video_url: str
     audio_url: str
     enable_video_loop: bool
-    voice_id: str = ""
-    script_text: str = ""
-    speed: float = 1.0
-    emotion: str = ""
     mediakit_task_id: str
     status: str
     output_video_url: str
@@ -43,58 +33,45 @@ class LipsyncJobResponse(BaseModel):
 
 
 class CreateLipsyncJobRequest(BaseModel):
-    """创建对口型任务请求.
+    """创建对口型任务请求 — #1809.
 
-    两种模式（二选一）：
-    - TTS 直生：voice_id + script_text 必填（+ 可选 speed/emotion）；audio_url 留空。
-    - 直接音频：video_url + audio_url 必填。
+    前端传 {voice_id, script_text, video_url}，
+    后端内部调 TTS 生成 audio_url 再提交 MediaKit。
     """
 
     video_url: str = Field(..., description="人物视频 URL（MP4，≤30min，单人真人）")
-
-    # 模式 2：直接音频
-    audio_url: str = Field("", description="驱动音频 URL（mp3/aac/wav/m4a/flac）；直生模式留空")
-
-    # 模式 1：TTS 直生
-    voice_id: str = Field("", description="音色 ID（预置音色或克隆音色 profile UUID）")
-    script_text: str = Field("", description="要合成的文案（直生模式必填，最长 5000 字符）")
-    speed: float = Field(1.0, ge=0.5, le=2.0, description="语速（0.5-2.0），默认 1.0")
-    emotion: str = Field("", description="情绪（natural/excited/calm/friendly 或中文 自然/兴奋/沉稳/亲切）")
-
+    voice_id: str = Field(..., description="音色 ID（预设音色或克隆音色 profile ID）")
+    script_text: str = Field(..., description="要合成的脚本文本")
     enable_video_loop: bool = Field(False, description="音频长于视频时是否循环画面")
     project_id: str = Field("", description="项目 ID（可选）")
 
-    @model_validator(mode="after")
-    def _validate_input_mode(self) -> "CreateLipsyncJobRequest":
-        video = (self.video_url or "").strip()
-        if not video:
+    @field_validator("video_url")
+    @classmethod
+    def validate_video_url(cls, v: str) -> str:
+        v = v.strip()
+        if not v:
             raise ValueError("video_url 不能为空")
-        if not video.startswith(("http://", "https://")):
+        if not v.startswith(("http://", "https://")):
             raise ValueError("video_url 必须是 HTTP/HTTPS URL")
-        lower = video.lower().split("?")[0]
+        lower = v.lower().split("?")[0]
         if not lower.endswith(".mp4"):
             raise ValueError("video_url 仅支持 MP4 格式")
+        return v
 
-        has_audio = bool((self.audio_url or "").strip())
-        has_tts = bool((self.voice_id or "").strip()) and bool((self.script_text or "").strip())
+    @field_validator("voice_id")
+    @classmethod
+    def validate_voice_id(cls, v: str) -> str:
+        v = v.strip()
+        if not v:
+            raise ValueError("voice_id 不能为空")
+        return v
 
-        if not has_audio and not has_tts:
-            raise ValueError(
-                "必须提供驱动音频：要么传 audio_url（直接音频模式），"
-                "要么同时传 voice_id + script_text（TTS 直生模式）"
-            )
-
-        if has_tts and len(self.script_text) > 5000:
+    @field_validator("script_text")
+    @classmethod
+    def validate_script_text(cls, v: str) -> str:
+        v = v.strip()
+        if not v:
+            raise ValueError("script_text 不能为空")
+        if len(v) > 5000:
             raise ValueError("script_text 最长 5000 字符")
-
-        if has_audio:
-            au = self.audio_url.strip()
-            if not au.startswith(("http://", "https://")):
-                raise ValueError("audio_url 必须是 HTTP/HTTPS URL")
-            au_lower = au.lower().split("?")[0]
-            allowed = (".mp3", ".aac", ".wav", ".m4a", ".flac")
-            if not any(au_lower.endswith(ext) for ext in allowed):
-                raise ValueError(f"audio_url 格式不支持，仅支持: {', '.join(allowed)}")
-            self.audio_url = au
-
-        return self
+        return v

apps/api/app/schemas/tts.py

@@ -16,7 +16,6 @@ class TTSSynthesizeRequest(BaseModel):
     output_name: str = Field("", description="输出文件名")
     language: str = Field("zh-CN", description="语言")
     speed: float = Field(1.0, ge=0.5, le=2.0, description="语速")
-    emotion: str = Field("", description="情绪（natural/excited/calm/friendly，或中文 自然/兴奋/沉稳/亲切）")
     voice_model: str = Field("", description="语音模型名称")
     voice_clone_profile_id: str = Field("", description="关联的音色克隆档案 ID")
     format: str = Field("mp3", description="输出格式（mp3/wav/pcm）")
@@ -110,7 +109,6 @@ class TTSPreviewRequest(BaseModel):
     text: str = Field(..., min_length=1, max_length=200, description="合成文本，限制 200 字")
     voice_id: str = Field(..., min_length=1, description="音色 ID")
     speed: float = Field(1.0, ge=0.5, le=2.0, description="语速")
-    emotion: str = Field("", description="情绪（natural/excited/calm/friendly，或中文）")
     pitch: float = Field(1.0, ge=0.5, le=2.0, description="音调（预留，当前未使用）")
 
 

apps/api/app/services/ai_avatar_cover_service.py

@@ -1,222 +0,0 @@
-"""AI 数字人封面服务 — 复用智能剪辑的 MediaKit 抽帧 + 质量评分选最佳帧.
-
-与 generation_cover.py 的智能选帧能力对齐（不再用 FFmpeg 简单截帧）：
-1. MediaKit extract_frames 抽取多帧（默认 5 帧，SpecifiedFrames 策略）
-2. cover_frame_scorer.score_frames 按清晰度/亮度/色彩评分选最佳
-3. 下载最佳帧并转存 OSS，返回公网封面 URL
-
-降级：MediaKit 不可用或抽帧失败时返回空字符串，由调用方决定回退策略。
-"""
-
-from __future__ import annotations
-
-import logging
-import tempfile
-import uuid
-from pathlib import Path
-from typing import Optional
-from urllib.parse import urlparse
-
-logger = logging.getLogger(__name__)
-
-# MediaKit 抽帧轮询参数（与 MediaKit API timeout=60s 对齐）
-COVER_POLL_INTERVAL = 3.0
-COVER_MAX_POLL_ATTEMPTS = 20  # 最多等 60 秒
-
-# 帧图片下载超时（秒）
-FRAME_DOWNLOAD_TIMEOUT = 20
-# 最佳帧下载超时（用于 persist）
-BEST_FRAME_DOWNLOAD_TIMEOUT = 30
-
-# 自家 OSS 私有桶 URL 重签有效期（供 MediaKit GPU worker 拉取）
-MEDIAKIT_URL_TTL_SECONDS = 7 * 24 * 3600
-
-
-def _sign_video_url_for_mediakit(video_url: str) -> str:
-    """如果 video_url 是自家 OSS 私有桶 URL，重新签名为长有效期预签名 URL。
-
-    MediaKit GPU worker 需要能公网访问 video_url，裸 public_url 在私有桶下会 403。
-    """
-    if not video_url:
-        return video_url
-    try:
-        from packages.shared.storage import get_shared_storage_service
-
-        storage = get_shared_storage_service()
-        public_base = getattr(storage, "public_url", "")
-        if not isinstance(public_base, str) or not public_base:
-            return video_url
-        own_host = urlparse(public_base).netloc.lower()
-        url_host = urlparse(video_url).netloc.lower()
-        if own_host and url_host == own_host:
-            # 是自家 OSS URL，重签 7 天有效期供 MediaKit 拉取
-            signed = storage.get_download_url(video_url, expires_seconds=MEDIAKIT_URL_TTL_SECONDS)
-            if signed:
-                logger.info("[数字人封面] video_url 已重签（自家 OSS 私有桶）")
-                return signed
-    except Exception:
-        logger.warning("[数字人封面] video_url 重签失败，使用原始 URL", exc_info=True)
-    return video_url
-
-
-def select_best_cover_frame(video_url: str, *, max_frames: int = 5) -> str:
-    """从视频抽取多帧并评分选最佳帧，返回最佳帧的临时 URL.
-
-    Args:
-        video_url: 可公网访问的视频 URL
-        max_frames: 抽帧数量
-
-    Returns:
-        最佳帧图片 URL；失败返回空字符串
-    """
-    if not video_url:
-        return ""
-
-    # 确保 MediaKit 能访问 video_url（自家 OSS 私有桶需重签）
-    video_url = _sign_video_url_for_mediakit(video_url)
-
-    try:
-        from packages.shared.cover_frame_scorer import score_frames
-        from packages.shared.mediakit_client import get_mediakit_client
-
-        mk = get_mediakit_client()
-        if not mk.is_available:
-            logger.warning("[数字人封面] MediaKit 未配置，无法智能抽帧")
-            return ""
-
-        logger.info(
-            "[数字人封面] 开始抽帧: video_url=%s max_frames=%d poll_interval=%.1f max_poll=%d",
-            video_url[:80],
-            max_frames,
-            COVER_POLL_INTERVAL,
-            COVER_MAX_POLL_ATTEMPTS,
-        )
-
-        snapshots = mk.extract_frames(
-            video_url=video_url,
-            strategy="SpecifiedFrames",
-            max_frames=max_frames,
-            poll_interval=COVER_POLL_INTERVAL,
-            max_poll_attempts=COVER_MAX_POLL_ATTEMPTS,
-            max_retries=1,
-        )
-        if not snapshots:
-            logger.warning("[数字人封面] MediaKit 未返回帧: %s", video_url[:80])
-            return ""
-
-        if len(snapshots) == 1:
-            return snapshots[0].get("image_url") or snapshots[0].get("url") or ""
-
-        # 使用连接池下载各帧（复用 TCP 连接，减少延迟）
-        import httpx
-
-        candidates = []
-        with httpx.Client(timeout=FRAME_DOWNLOAD_TIMEOUT, follow_redirects=True) as client:
-            for snap in snapshots:
-                url = snap.get("image_url") or snap.get("url") or ""
-                if not url:
-                    continue
-                tmp_path: Optional[str] = None
-                try:
-                    resp = client.get(url)
-                    resp.raise_for_status()
-                    with tempfile.NamedTemporaryFile(suffix=".jpg", delete=False) as tmp:
-                        tmp.write(resp.content)
-                        tmp_path = tmp.name
-                    candidates.append({"image_path": tmp_path, "url": url})
-                except Exception as e:
-                    logger.warning("[数字人封面] 帧下载失败，跳过: url=%s err=%s", url[:80], e)
-                    candidates.append({"image_path": None, "url": url, "score": 0.0})
-
-        if not candidates:
-            return snapshots[0].get("image_url") or snapshots[0].get("url") or ""
-
-        scored = score_frames(candidates)
-        best = scored[0] if scored else None
-        best_url = best.get("url", "") if best else ""
-
-        # 清理临时文件
-        for c in candidates:
-            p = c.get("image_path")
-            if p:
-                try:
-                    Path(p).unlink(missing_ok=True)
-                except Exception:
-                    pass
-
-        logger.info(
-            "[数字人封面] 智能选帧完成: candidates=%d best_score=%s",
-            len(candidates),
-            best.get("score") if best else "n/a",
-        )
-        return best_url
-
-    except Exception:
-        logger.warning("[数字人封面] 智能选帧失败", exc_info=True)
-        return ""
-
-
-def persist_cover_to_oss(frame_url: str, *, job_id: str = "", prefix: str = "ai-avatar/covers") -> str:
-    """下载帧图并转存到 OSS，返回公网封面 URL.
-
-    Args:
-        frame_url: MediaKit 返回的临时帧图 URL
-        job_id: 关联任务 ID（用于 OSS key 命名）
-        prefix: OSS key 前缀
-
-    Returns:
-        OSS 公网 URL；失败回退原始 frame_url
-    """
-    if not frame_url:
-        return ""
-    tmp_path: Optional[str] = None
-    try:
-        import httpx
-
-        with httpx.Client(timeout=BEST_FRAME_DOWNLOAD_TIMEOUT, follow_redirects=True) as client:
-            resp = client.get(frame_url)
-            resp.raise_for_status()
-            if not resp.content:
-                logger.warning("[数字人封面] 帧图内容为空: %s", frame_url[:80])
-                return frame_url
-
-            with tempfile.NamedTemporaryFile(suffix=".jpg", delete=False) as tmp:
-                tmp.write(resp.content)
-                tmp_path = tmp.name
-
-        from packages.shared.storage import get_shared_storage_service
-
-        storage = get_shared_storage_service()
-        token = job_id or uuid.uuid4().hex[:12]
-        cover_key = f"{prefix}/{token}/cover_{uuid.uuid4().hex[:8]}.jpg"
-        public_url = storage.upload_file(
-            file_or_path=tmp_path,
-            storage_key=cover_key,
-            content_type="image/jpeg",
-        )
-        logger.info("[数字人封面] 封面已转存 OSS: key=%s", cover_key)
-        # 私有桶：返回预签名 URL（前端才能加载）
-        if public_url:
-            signed = storage.get_download_url(cover_key, expires_seconds=86400)
-            return signed
-        return frame_url
-    except Exception:
-        logger.warning("[数字人封面] 封面转存 OSS 失败，返回原始 URL", exc_info=True)
-        return frame_url
-    finally:
-        if tmp_path:
-            try:
-                Path(tmp_path).unlink(missing_ok=True)
-            except Exception:
-                pass
-
-
-def generate_smart_cover(video_url: str, *, job_id: str = "", max_frames: int = 5) -> str:
-    """一站式：MediaKit 智能抽帧选最佳 → 转存 OSS，返回封面公网 URL.
-
-    供独立封面接口与渲染管线复用。失败返回空字符串。
-    """
-    best_frame = select_best_cover_frame(video_url, max_frames=max_frames)
-    if not best_frame:
-        return ""
-    return persist_cover_to_oss(best_frame, job_id=job_id)

apps/api/app/services/ai_avatar_render_service.py

@@ -53,8 +53,8 @@ class AiAvatarRenderService:
         *,
         user_id: str,
         lipsync_job_id: str,
-        script_id: str = "",
-        b_roll_segments: list[dict[str, Any]] | None = None,
+        script_id: str,
+        b_roll_segments: list[dict[str, Any]],
         title_config: dict[str, Any],
         cover_config: dict[str, Any],
         project_id: str = "",
@@ -83,19 +83,17 @@ class AiAvatarRenderService:
         if not lipsync_job.output_video_url:
             raise AiAvatarRenderError("对口型任务输出视频 URL 为空", code="LipsyncJobNoOutput")
 
-        # 2. 验证文案归属（仅当选了文案库条目时；手动输入文案直生场景 script_id 可空）
-        script_id = (script_id or "").strip()
-        if script_id:
-            script = (
-                self.db.query(ScriptModel)
-                .filter(
-                    ScriptModel.id == script_id,
-                    ScriptModel.user_id == user_id,
-                )
-                .first()
+        # 2. 验证文案归属
+        script = (
+            self.db.query(ScriptModel)
+            .filter(
+                ScriptModel.id == script_id,
+                ScriptModel.user_id == user_id,
             )
-            if script is None:
-                raise AiAvatarRenderError("文案不存在或无权访问", code="ScriptNotFound")
+            .first()
+        )
+        if script is None:
+            raise AiAvatarRenderError("文案不存在或无权访问", code="ScriptNotFound")
 
         # 3. 创建渲染任务
         job_id = str(uuid.uuid4())
@@ -105,7 +103,7 @@ class AiAvatarRenderService:
             project_id=project_id,
             lipsync_job_id=lipsync_job_id,
             script_id=script_id,
-            b_roll_segments=[s if isinstance(s, dict) else s.model_dump() for s in (b_roll_segments or [])],
+            b_roll_segments=[s if isinstance(s, dict) else s.model_dump() for s in b_roll_segments],
             title_config=title_config,
             cover_config=cover_config,
             status="pending",
@@ -290,22 +288,7 @@ class AiAvatarRenderService:
                 output_video_url = self._upload_to_oss(output_video_path, f"ai-avatar/{job_id}/output.mp4")
                 job.output_video_url = output_video_url
 
-                # 封面：优先复用智能剪辑的 MediaKit 抽帧 + 质量评分选最佳帧；
-                # MediaKit 不可用时回退到 FFmpeg 已按 cover_config 抽取的 cover_path
-                smart_cover_url = ""
-                if output_video_url:
-                    try:
-                        from app.services.ai_avatar_cover_service import (
-                            generate_smart_cover,
-                        )
-
-                        smart_cover_url = generate_smart_cover(output_video_url, job_id=job_id, max_frames=5)
-                    except Exception:
-                        logger.warning("智能封面(MediaKit)失败，回退 FFmpeg 封面 job_id=%s", job_id, exc_info=True)
-
-                if smart_cover_url:
-                    job.output_cover_url = smart_cover_url
-                elif cover_path:
+                if cover_path:
                     output_cover_url = self._upload_to_oss(cover_path, f"ai-avatar/{job_id}/cover.jpg")
                     job.output_cover_url = output_cover_url
 
@@ -322,38 +305,6 @@ class AiAvatarRenderService:
             self.db.commit()
             logger.info("渲染任务完成: %s", job_id)
 
-            # 7. 自动保存成片记录到成片库
-            if job.output_video_url:
-                try:
-                    from packages.adapters.sqlalchemy_impl.generated_video_repository import (
-                        SQLAlchemyGeneratedVideoRepository,
-                    )
-                    from packages.domain.generated_video import GeneratedVideo
-
-                    clip_name = f"AI数字人_{job_id[:8]}"
-                    clip = GeneratedVideo.create(
-                        project_id=job.project_id,
-                        generation_task_id=job.lipsync_job_id,
-                        name=clip_name,
-                        file_url=job.output_video_url,
-                        user_id=job.user_id,
-                        duration=job.output_duration or 0.0,
-                        thumbnail_url=job.output_cover_url or None,
-                        generation_params={
-                            "source": "ai_avatar_render",
-                            "render_job_id": job.id,
-                        },
-                    )
-                    video_repo = SQLAlchemyGeneratedVideoRepository(self.db)
-                    video_repo.create(clip)
-                    logger.info("成片记录已保存到成片库: clip_id=%s, render_job=%s", clip.id, job_id)
-                except Exception as clip_err:
-                    logger.warning(
-                        "自动保存成片记录失败（不影响渲染任务状态）: render_job=%s, error=%s",
-                        job_id,
-                        clip_err,
-                    )
-
         except AiAvatarRenderError as exc:
             job.status = "failed"
             job.error_message = str(exc)
@@ -408,7 +359,7 @@ class AiAvatarRenderService:
         else:
             filter_arg = ""
 
-        return f"ffmpeg {inputs} {filter_arg} -c:v libx264 -preset veryfast -crf 23 -y {output_path}"
+        return f"ffmpeg {inputs} {filter_arg} -c:v libx264 -preset fast -crf 23 -y {output_path}"
 
     def _upload_to_oss(self, local_path: str, oss_key: str) -> str:
         """上传文件到 OSS，返回 URL.

apps/api/app/services/lipsync_service.py

@@ -1,21 +1,19 @@
 """对口型 Service — #1796 MediaKit 对口型业务逻辑, #1809 参数调整.
 
 职责：
-- 创建/查询对口型任务
-- 双输入模式：TTS 直生（voice_id + script_text，内部先合成音频转存 OSS）或直接音频（audio_url）
+- 创建/查询/取消对口型任务
+- 调用 TTS 合成音频（#1809：前端不再传 audio_url）
 - 调用 MediaKit 客户端提交异步任务
-- 轮询更新任务状态（中间状态同步 DB，成片转存自家 OSS）
+- 轮询更新任务状态
 - 用户隔离（每个用户只能操作自己的任务）
 """
 
 from __future__ import annotations
 
-import io
 import logging
 import uuid
 from datetime import datetime, timezone
 from typing import Optional
-from urllib.parse import urlparse
 
 from app.services.mediakit_client import (
     STATUS_COMPLETED,
@@ -25,22 +23,13 @@ from app.services.mediakit_client import (
     MediaKitError,
     get_mediakit_client,
 )
-
-# Celery 异步任务：TTS 合成 + MediaKit 提交（#lipsync-speed-optimization）
-from app.tasks.lipsync_tts import tts_synthesize_and_submit
 from sqlalchemy.orm import Session
 
 from packages.adapters.sqlalchemy_impl.models import LipsyncJobModel
-from packages.application.cosyvoice_service import CosyVoiceError, normalize_emotion
-from packages.shared.storage import get_shared_storage_service
-from packages.shared.url_security import ALLOWED_AUDIO_MIME_TYPES, safe_download_bytes
+from packages.application.cosyvoice_service import CosyVoiceError, CosyVoiceService
 
 logger = logging.getLogger(__name__)
 
-# 传给 MediaKit GPU worker / 回给前端播放的 OSS 预签名有效期：7 天。
-# MediaKit 排队 + 拉取可能延迟，私有桶裸 URL 或 1 小时短预签名都会 403，故统一重签长有效期。
-MEDIAKIT_URL_TTL_SECONDS = 7 * 24 * 3600
-
 
 class LipsyncService:
     """对口型任务 Service."""
@@ -49,98 +38,19 @@ class LipsyncService:
         self,
         db: Session,
         client: Optional[MediaKitClient] = None,
-        cosyvoice_service=None,
-        voice_clone_repo=None,
+        cosyvoice_service: Optional[CosyVoiceService] = None,
     ):
         self.db = db
         self.client = client or get_mediakit_client()
-        self._cosyvoice = cosyvoice_service
-        self._voice_clone_repo = voice_clone_repo
+        self._cosyvoice_service = cosyvoice_service
 
-    def _get_cosyvoice(self):
-        """延迟获取 CosyVoiceService（与 tts 路由一致，含 OSS 预签名配置）."""
-        if self._cosyvoice is None:
+    @property
+    def cosyvoice_service(self) -> CosyVoiceService:
+        if self._cosyvoice_service is None:
             from app.dependencies import get_cosyvoice_service
 
-            self._cosyvoice = get_cosyvoice_service()
-        return self._cosyvoice
-
-    def _resolve_voice_id(self, voice_id: str, user_id: str) -> str:
-        """将克隆音色 profile UUID 解析为 CosyVoice voice_id。
-
-        与 /tts/synthesize 保持一致：命中 profile → 校验归属 → 返回其 voice_id；
-        未命中（预置音色 ID 或克隆 CosyVoice voice_id）原样返回。
-        """
-        if not voice_id:
-            return ""
-        if self._voice_clone_repo is None:
-            try:
-                from app.dependencies import get_voice_clone_profile_repository
-
-                self._voice_clone_repo = get_voice_clone_profile_repository(self.db)
-            except Exception:
-                return voice_id
-        try:
-            profile = self._voice_clone_repo.get(voice_id)
-        except Exception:
-            return voice_id
-        if profile is None:
-            return voice_id
-        if getattr(profile, "user_id", "") != user_id:
-            raise MediaKitError("无权访问该音色", code="VoiceForbidden")
-        if not getattr(profile, "voice_id", ""):
-            raise MediaKitError("音色克隆尚未完成，请稍后再试", code="VoiceNotReady")
-        return profile.voice_id
-
-    def _synthesize_and_persist_audio(
-        self,
-        *,
-        user_id: str,
-        job_id: str,
-        voice_id: str,
-        script_text: str,
-        speed: float,
-        emotion: str,
-    ) -> str:
-        """TTS 直生：调 CosyVoice 合成音频并转存 OSS，返回可公网访问的音频 URL.
-
-        Raises:
-            MediaKitError: 合成失败
-        """
-        actual_voice_id = self._resolve_voice_id(voice_id, user_id)
-        cosyvoice = self._get_cosyvoice()
-        try:
-            result = cosyvoice.submit_synthesize_task(
-                text=script_text,
-                voice_id=actual_voice_id,
-                speed=speed,
-                emotion=normalize_emotion(emotion),
-            )
-        except CosyVoiceError as exc:
-            raise MediaKitError(f"TTS 合成失败: {exc}", code="TTSSynthesisFailed") from exc
-        except ValueError as exc:
-            raise MediaKitError(f"TTS 参数错误: {exc}", code="TTSInvalidParam") from exc
-
-        temp_url = result.get("audio_url", "")
-        if not temp_url:
-            raise MediaKitError("TTS 未返回音频 URL", code="TTSNoAudio")
-
-        # 转存到自家 OSS，避免临时 URL 过期导致 MediaKit 拉取失败
-        try:
-            audio_data = safe_download_bytes(
-                temp_url,
-                purpose="lipsync_tts_audio",
-                allowed_mime_types=ALLOWED_AUDIO_MIME_TYPES,
-                timeout=60.0,
-            )
-            storage = get_shared_storage_service()
-            storage_key = f"lipsync-tts/{user_id}/{job_id}.mp3"
-            permanent_url = storage.upload_file(io.BytesIO(audio_data), storage_key, content_type="audio/mpeg")
-            logger.info("对口型 TTS 音频已转存 OSS: job_id=%s key=%s", job_id, storage_key)
-            return permanent_url
-        except Exception as exc:
-            logger.warning("TTS 音频转存 OSS 失败，回退临时 URL: job_id=%s err=%s", job_id, exc)
-            return temp_url
+            self._cosyvoice_service = get_cosyvoice_service()
+        return self._cosyvoice_service
 
     # ── 创建任务 ──────────────────────────────────────────────────────────
 
@@ -149,39 +59,48 @@ class LipsyncService:
         *,
         user_id: str,
         video_url: str,
-        audio_url: str = "",
-        voice_id: str = "",
-        script_text: str = "",
-        speed: float = 1.0,
-        emotion: str = "",
+        voice_id: str,
+        script_text: str,
         enable_video_loop: bool = False,
         project_id: str = "",
     ) -> LipsyncJobModel:
-        """创建对口型任务.
+        """创建对口型任务并提交到 MediaKit.
 
-        两种输入模式：
-        - TTS 直生：voice_id + script_text（audio_url 留空）
-          → 先创建 DB 记录（状态 tts_processing），再 dispatch Celery 异步任务
-            执行 TTS 合成 + MediaKit 提交。API 响应 <1s。
-        - 直接音频：提供 audio_url
-          → 同步提交 MediaKit，状态直接设为 submitted。
+        #1809: 内部调 TTS 合成音频，不再由前端传 audio_url。
 
         Raises:
-            MediaKitError: 参数校验失败或 MediaKit 提交失败（仅直接音频模式）
+            CosyVoiceError: TTS 合成失败
+            MediaKitError: API 调用失败
         """
-        # 0. 输入校验
-        if not audio_url:
-            if not (voice_id and script_text):
-                raise MediaKitError(
-                    "必须提供 audio_url 或 voice_id+script_text",
-                    code="InvalidInput",
-                )
-            # TTS 模式：在 HTTP 请求中同步校验音色归属，快速失败
-            self._resolve_voice_id(voice_id, user_id)
+        # 1. 调 TTS 合成音频
+        try:
+            tts_result = self.cosyvoice_service.synthesize_speech(
+                text=script_text,
+                voice_id=voice_id,
+            )
+            audio_url = tts_result.audio_url
+        except CosyVoiceError as exc:
+            logger.error("TTS 合成失败: voice_id=%s, error=%s", voice_id, exc)
+            # 创建失败记录
+            job_id = str(uuid.uuid4())
+            job = LipsyncJobModel(
+                id=job_id,
+                user_id=user_id,
+                project_id=project_id,
+                video_url=video_url,
+                audio_url="",
+                enable_video_loop=enable_video_loop,
+                status="failed",
+                error_message=f"TTS 合成失败: {exc}",
+                error_code="TTSSynthesisFailed",
+            )
+            self.db.add(job)
+            self.db.commit()
+            self.db.refresh(job)
+            raise
 
-        # 1. 创建数据库记录
+        # 2. 创建数据库记录
         job_id = str(uuid.uuid4())
-        is_tts_mode = not bool(audio_url)
         job = LipsyncJobModel(
             id=job_id,
             user_id=user_id,
@@ -189,57 +108,28 @@ class LipsyncService:
             video_url=video_url,
             audio_url=audio_url,
             enable_video_loop=enable_video_loop,
-            voice_id=voice_id or "",
-            script_text=script_text or "",
-            speed=speed,
-            emotion=normalize_emotion(emotion),
-            status="tts_processing" if is_tts_mode else "pending",
+            status="pending",
         )
         self.db.add(job)
         self.db.flush()
 
-        if is_tts_mode:
-            # 2a. TTS 模式：dispatch Celery 异步任务处理 TTS 合成 + MediaKit 提交
-            try:
-                tts_synthesize_and_submit.apply_async(
-                    args=(
-                        job_id,
-                        user_id,
-                        voice_id,
-                        script_text,
-                        speed,
-                        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",
-                    job_id,
-                    exc_info=True,
-                )
-        else:
-            # 2b. 直接音频模式：同步签名并提交 MediaKit
-            video_url = self._sign_media_url(video_url)
-            if audio_url:
-                audio_url = self._sign_media_url(audio_url)
-                job.audio_url = audio_url
-
-            try:
-                result = self.client.submit_lipsync(
-                    video_url=video_url,
-                    audio_url=audio_url,
-                    enable_video_loop=enable_video_loop,
-                    client_token=job_id,
-                )
-                job.mediakit_task_id = result["task_id"]
-                job.status = "submitted"
-                job.submitted_at = datetime.now(timezone.utc)
-            except MediaKitError as exc:
-                job.status = "failed"
-                job.error_message = str(exc)
-                job.error_code = exc.code
-                logger.error("提交对口型任务失败: %s", exc)
-                raise
+        # 3. 提交到 MediaKit
+        try:
+            result = self.client.submit_lipsync(
+                video_url=video_url,
+                audio_url=audio_url,
+                enable_video_loop=enable_video_loop,
+                client_token=job_id,  # 幂等控制
+            )
+            job.mediakit_task_id = result["task_id"]
+            job.status = "submitted"
+            job.submitted_at = datetime.now(timezone.utc)
+        except MediaKitError as exc:
+            job.status = "failed"
+            job.error_message = str(exc)
+            job.error_code = exc.code
+            logger.error("提交对口型任务失败: %s", exc)
+            raise
 
         self.db.commit()
         self.db.refresh(job)
@@ -302,14 +192,11 @@ class LipsyncService:
             return job
 
         mk_status = status_data.get("status", STATUS_RUNNING)
-        logger.info("MediaKit 对口型状态 [%s]: %s", job_id, mk_status)
 
         if mk_status == STATUS_COMPLETED:
             result = status_data.get("result", {})
             job.status = STATUS_COMPLETED
-            output_url = result.get("video_url", "")
-            # MediaKit 输出为临时 URL，转存自家 OSS 防止过期（失败则回退临时 URL）
-            job.output_video_url = self._persist_output_video(output_url, job_id, user_id)
+            job.output_video_url = result.get("video_url", "")
             job.output_duration = result.get("duration", 0.0)
             job.completed_at = datetime.now(timezone.utc)
         elif mk_status == STATUS_FAILED:
@@ -318,72 +205,21 @@ class LipsyncService:
             job.error_message = error.get("message", "任务执行失败")
             job.error_code = error.get("code", "TaskFailed")
             job.completed_at = datetime.now(timezone.utc)
-        else:
-            # 中间状态（running/processing/queued 等）同步到 DB，避免前端永远卡在 submitted
-            if isinstance(mk_status, str) and mk_status:
-                job.status = mk_status
+        # running 状态只更新时间戳
         job.updated_at = datetime.now(timezone.utc)
         self.db.commit()
         self.db.refresh(job)
         return job
 
-    def _persist_output_video(self, temp_url: str, job_id: str, user_id: str) -> str:
-        """将 MediaKit 输出的临时视频 URL 转存到自家 OSS.
-
-        失败时回退返回原始临时 URL，不影响任务完成。
-        """
-        if not temp_url:
-            return ""
-        try:
-            import httpx
-
-            with httpx.Client(timeout=180.0, follow_redirects=True) as client:
-                resp = client.get(temp_url)
-                resp.raise_for_status()
-                data = resp.content
-            storage = get_shared_storage_service()
-            storage_key = f"lipsync-outputs/{user_id}/{job_id}.mp4"
-            permanent_url = storage.upload_file(io.BytesIO(data), storage_key, content_type="video/mp4")
-            logger.info("对口型输出视频已转存 OSS: job_id=%s key=%s", job_id, storage_key)
-            return self._sign_media_url(permanent_url) or temp_url
-        except Exception as exc:
-            logger.warning("对口型输出视频转存 OSS 失败，回退临时 URL: job_id=%s err=%s", job_id, exc)
-            return temp_url
-
-    def _sign_media_url(self, url: str) -> str:
-        """对自家 OSS 私有桶 URL 重签长有效期预签名，供 MediaKit 拉取 / 前端播放。
-
-        - 裸 public_url（upload_file 返回，不带签名）→ 私有桶匿名访问 403，重签。
-        - 已带签名但即将过期的 URL（如前端 1h 预签名）→ 抽 storage_key 后重签。
-        - 外部 URL（CosyVoice/MediaKit 临时链接，非本桶 host）→ 原样透传。
-        - 任何异常都降级原样返回，不阻断主流程。
-        """
-        if not url:
-            return url
-        try:
-            storage = get_shared_storage_service()
-            public_base = getattr(storage, "public_url", "")
-            if not isinstance(public_base, str) or not public_base:
-                return url  # 无法判定归属，保守透传
-            own_host = urlparse(public_base).netloc.lower()
-            host = urlparse(url).netloc.lower()
-            if not own_host or host != own_host:
-                return url  # 非自家 OSS（外部临时链接），不处理
-            signed = storage.get_download_url(url, expires_seconds=MEDIAKIT_URL_TTL_SECONDS)
-            return signed or url
-        except Exception as exc:  # noqa: BLE001 - 签名失败不阻断，降级原 URL
-            logger.warning("对口型 URL 重签失败，原样返回: url_prefix=%s err=%s", url[:80], exc)
-            return url
-
     # ── 取消任务 ──────────────────────────────────────────────────────────
 
     def cancel_job(self, job_id: str, user_id: str) -> Optional[LipsyncJobModel]:
-        """取消任务（仅 pending/tts_processing/submitted 状态可取消）."""
+        """取消任务（仅 pending/submitted 状态可取消）."""
         job = self.get_job(job_id, user_id)
         if job is None:
             return None
 
-        if job.status in ("pending", "tts_processing", "submitted"):
+        if job.status in ("pending", "submitted"):
             job.status = "cancelled"
             job.updated_at = datetime.now(timezone.utc)
             self.db.commit()

apps/api/app/tasks/lipsync_tts.py

@@ -1,166 +0,0 @@
-"""AI 数字人对口型 TTS 异步任务 — 将 TTS 合成从 HTTP 请求移至 Celery 后台执行.
-
-优化目标：将 create_job 的 API 响应时间从 6~35s 降到 <1s。
-任务流程：
-1. 创建新 DB session，加载 job 记录
-2. 调用 CosyVoice 合成音频
-3. 下载音频并转存到自家 OSS
-4. 更新 job 的 audio_url
-5. 签名 URL 并提交到 MediaKit
-6. 更新 job 状态为 submitted
-7. 异常时标记 job 为 failed
-"""
-
-import io
-import logging
-from datetime import datetime, timezone
-
-from app.core.celery_app import celery_app
-
-logger = logging.getLogger(__name__)
-
-
-@celery_app.task(
-    bind=True,
-    name="lipsync_tts.synthesize_and_submit",
-    max_retries=2,
-    default_retry_delay=30,
-)
-def tts_synthesize_and_submit(
-    self,
-    job_id: str,
-    user_id: str,
-    voice_id: str,
-    script_text: str,
-    speed: float,
-    emotion: str,
-):
-    """异步执行 TTS 合成 + OSS 转存 + MediaKit 提交.
-
-    在 Celery worker 中运行，不阻塞 HTTP 请求。
-    """
-    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.storage import get_shared_storage_service
-    from packages.shared.url_security import safe_download_bytes
-
-    db: DBSession = SessionLocal()
-    try:
-        job = (
-            db.query(LipsyncJobModel)
-            .filter(
-                LipsyncJobModel.id == job_id,
-                LipsyncJobModel.user_id == user_id,
-            )
-            .first()
-        )
-
-        if job is None:
-            logger.error("[lipsync_tts] Job not found: job_id=%s", job_id)
-            return
-
-        # 已取消的任务不再处理
-        if job.status == "cancelled":
-            logger.info("[lipsync_tts] Job already cancelled, skipping: job_id=%s", job_id)
-            return
-
-        # 1. TTS 合成
-        try:
-            cosyvoice = CosyVoiceService()
-            result = cosyvoice.submit_synthesize_task(
-                text=script_text,
-                voice_id=voice_id,
-                speed=speed,
-                emotion=emotion,
-            )
-        except CosyVoiceError as exc:
-            logger.error("[lipsync_tts] TTS 合成失败: job_id=%s err=%s", job_id, exc)
-            job.status = "failed"
-            job.error_message = f"TTS 合成失败: {exc}"
-            job.error_code = "TTSSynthesisFailed"
-            job.updated_at = datetime.now(timezone.utc)
-            db.commit()
-            return
-        except ValueError as exc:
-            logger.error("[lipsync_tts] TTS 参数错误: job_id=%s err=%s", job_id, exc)
-            job.status = "failed"
-            job.error_message = f"TTS 参数错误: {exc}"
-            job.error_code = "TTSInvalidParam"
-            job.updated_at = datetime.now(timezone.utc)
-            db.commit()
-            return
-
-        temp_url = result.get("audio_url", "")
-        if not temp_url:
-            logger.error("[lipsync_tts] TTS 未返回音频 URL: job_id=%s", job_id)
-            job.status = "failed"
-            job.error_message = "TTS 未返回音频 URL"
-            job.error_code = "TTSNoAudio"
-            job.updated_at = datetime.now(timezone.utc)
-            db.commit()
-            return
-
-        # 2. 下载并转存到自家 OSS
-        try:
-            audio_data = safe_download_bytes(
-                temp_url,
-                purpose="lipsync_tts_audio",
-                allowed_mime_types=("audio/mpeg", "audio/mp3", "audio/wav", "audio/mp4", "audio/x-m4a"),
-                timeout=60.0,
-            )
-            storage = get_shared_storage_service()
-            storage_key = f"lipsync-tts/{user_id}/{job_id}.mp3"
-            permanent_url = storage.upload_file(io.BytesIO(audio_data), storage_key, content_type="audio/mpeg")
-            logger.info("[lipsync_tts] TTS 音频已转存 OSS: job_id=%s key=%s", job_id, storage_key)
-            job.audio_url = permanent_url
-        except Exception as exc:
-            logger.warning("[lipsync_tts] TTS 音频转存 OSS 失败，回退临时 URL: job_id=%s err=%s", job_id, exc)
-            job.audio_url = temp_url
-
-        db.commit()
-
-        # 3. 签名 URL 并提交到 MediaKit
-        from app.services.lipsync_service import LipsyncService
-
-        temp_service = LipsyncService.__new__(LipsyncService)
-        audio_url = temp_service._sign_media_url(job.audio_url)
-        video_url = temp_service._sign_media_url(job.video_url)
-
-        client = get_mediakit_client()
-        try:
-            mk_result = client.submit_lipsync(
-                video_url=video_url,
-                audio_url=audio_url,
-                enable_video_loop=job.enable_video_loop,
-                client_token=job_id,
-            )
-            job.mediakit_task_id = mk_result["task_id"]
-            job.status = "submitted"
-            job.submitted_at = datetime.now(timezone.utc)
-            logger.info("[lipsync_tts] 已提交 MediaKit: job_id=%s task_id=%s", job_id, mk_result["task_id"])
-        except MediaKitError as exc:
-            job.status = "failed"
-            job.error_message = str(exc)
-            job.error_code = exc.code
-            logger.error("[lipsync_tts] 提交 MediaKit 失败: job_id=%s err=%s", job_id, exc)
-
-        db.commit()
-
-    except Exception:
-        logger.exception("[lipsync_tts] 未预期的异常: job_id=%s", job_id)
-        try:
-            job = db.query(LipsyncJobModel).filter(LipsyncJobModel.id == job_id).first()
-            if job and job.status not in ("cancelled", "failed", "completed"):
-                job.status = "failed"
-                job.error_message = "TTS 异步任务执行异常"
-                job.error_code = "AsyncTaskError"
-                job.updated_at = datetime.now(timezone.utc)
-                db.commit()
-        except Exception:
-            logger.exception("[lipsync_tts] 回写失败状态时异常: job_id=%s", job_id)
-    finally:
-        db.close()

apps/web/src/api/tts/types.ts

@@ -103,7 +103,6 @@ export interface TTSPreviewRequest {
   voice_id: string
   speed?: number
   pitch?: number
-  emotion?: string // 情绪参数：natural/excited/calm/friendly
 }
 
 /** TTS 试听响应 */

apps/web/src/pages/ai-avatar/AiAvatar.css

@@ -486,16 +486,14 @@
 
 .aa-lipsync-preview {
   width: 100%;
-  max-width: 240px;
   aspect-ratio: 9/16;
   background: #0f0f1a;
   border-radius: 10px;
   overflow: hidden;
-  margin: 0 auto 12px auto;
+  margin-bottom: 12px;
   display: flex;
   align-items: center;
   justify-content: center;
-  position: relative;
 }
 
 .aa-lipsync-preview video {
@@ -549,23 +547,21 @@
 /* ── 封面 & 生成 ── */
 .aa-cover-preview {
   width: 100%;
-  max-width: 240px;
   aspect-ratio: 9/16;
+  max-height: 160px;
   background: #f0f0f5;
-  border-radius: 8px;
+  border-radius: 10px;
   overflow: hidden;
   display: flex;
   align-items: center;
   justify-content: center;
-  margin: 0 auto 12px auto;
-  position: relative;
+  margin-bottom: 12px;
 }
 
 .aa-cover-preview img {
   width: 100%;
   height: 100%;
   object-fit: cover;
-  display: block;
 }
 
 .aa-cover-preview__placeholder {
@@ -1154,99 +1150,3 @@
   flex-direction: column;
   gap: 4px;
 }
-
-/* ─ 对口型生成弹窗 Spinner ── */
-.aa-lipsync-spinner {
-  width: 48px;
-  height: 48px;
-  border: 4px solid #f0f0f5;
-  border-top-color: #6366f1;
-  border-radius: 50%;
-  animation: aa-spin 0.8s linear infinite;
-}
-
-@keyframes aa-spin {
-  to {
-    transform: rotate(360deg);
-  }
-}
-
-.aa-btn--danger {
-  background: #ff4d4f;
-  color: #fff;
-  border: none;
-}
-
-.aa-btn--danger:hover {
-  background: #ff7875;
-}
-
-/* ── v3.1 两步骤导航（仅追加，不改动上方任何原有样式） ── */
-.aa-step-nav {
-  display: flex;
-  align-items: center;
-  gap: 24px;
-  padding: 10px 24px;
-  background: #fff;
-  border-bottom: 1px solid #e8e8ec;
-  flex-shrink: 0;
-}
-
-.aa-step-nav__item {
-  font-size: 13px;
-  font-weight: 500;
-  color: #8c8ca1;
-  position: relative;
-  padding-bottom: 6px;
-}
-
-.aa-step-nav__item.active {
-  color: #4f46e5;
-  font-weight: 600;
-}
-
-.aa-step-nav__item.active::after {
-  content: "";
-  position: absolute;
-  left: 0;
-  right: 0;
-  bottom: -11px;
-  height: 2px;
-  background: #4f46e5;
-  border-radius: 1px;
-}
-
-/* 步骤切换按钮行 */
-.aa-step-btn-row {
-  display: flex;
-  justify-content: flex-end;
-  gap: 8px;
-  margin-top: 16px;
-  padding-top: 12px;
-  border-top: 1px dashed #f0f0f5;
-}
-
-.aa-step-btn-row .aa-btn {
-  min-width: 120px;
-}
-
-/* 分步布局：每个步骤 3 个横向面板等宽撑满（沿用原 .aa-panel 外观，仅改宽度） */
-.aa-page-body > .aa-panel--s1,
-.aa-page-body > .aa-panel--s2 {
-  flex: 1 1 0;
-  width: auto;
-  min-width: 220px;
-}
-
-/* 文案 / 对口型预览面板内容较多，给更宽的弹性比例 */
-.aa-page-body > .aa-panel--s1-wide {
-  flex: 1.4 1 0;
-  width: auto;
-  min-width: 280px;
-}
-
-.aa-page-body > .aa-panel--s2-wide {
-  flex: 1.4 1 0;
-  width: auto;
-  min-width: 300px;
-}

apps/web/src/pages/ai-avatar/AiAvatarPage.tsx

@@ -1,17 +1,14 @@
 /**
- * AI数字人 — 主页面（v3 两步骤版）
- * 步骤1：出镜视频 / 配音库 / 文案
- * 步骤2：对口型预览（含插入画面）/ 标题配置 / 封面&生成
+ * AI数字人 — 主页面（v3）
+ * 5列水平面板布局
  */
 import React, { useState, useCallback, useEffect, useRef } from "react"
 import { message } from "antd"
-import { useNavigate } from "react-router-dom"
 import "./AiAvatar.css"
 import { useAiAvatar } from "./hooks/useAiAvatar"
 import { PanelVideoSelector } from "./components/PanelVideoSelector"
 import PanelVoiceSelector from "./components/PanelVoiceSelector"
-import PanelScript from "./components/PanelScript"
-import PanelLipsyncPreview from "./components/PanelLipsyncPreview"
+import PanelScriptAndLipsync from "./components/PanelScriptAndLipsync"
 import PanelTitleConfig from "./components/PanelTitleConfig"
 import PanelCoverAndGenerate from "./components/PanelCoverAndGenerate"
 import { ModalAssetPicker } from "./components/ModalAssetPicker"
@@ -22,73 +19,28 @@ import {
   createLipsyncJob,
   getLipsyncJob,
   submitRender,
-  getRenderJob,
-  generateSmartCover,
 } from "./api/aiAvatar"
-import {
-  normalizeEmotion,
-  buildTitleConfigPayload,
-  buildCoverConfigPayload,
-} from "./utils/contract"
 
 /** 面板折叠状态 */
-type PanelKey = "video" | "voice" | "script" | "lipsync" | "title" | "cover"
+type PanelKey = "video" | "voice" | "script" | "title" | "cover"
 
 const AiAvatarPage: React.FC = () => {
   const state = useAiAvatar()
-  const navigate = useNavigate()
-  const [currentStep, setCurrentStep] = useState<1 | 2>(1)
   const [collapsed, setCollapsed] = useState<Record<PanelKey, boolean>>({
     video: false,
     voice: false,
     script: false,
-    lipsync: false,
     title: false,
     cover: false,
   })
 
-  /* ── 对口型生成弹窗 ── */
-  const [showLipsyncModal, setShowLipsyncModal] = useState(false)
-  const [lipsyncStatus, setLipsyncStatus] = useState<"generating" | "completed" | "failed">(
-    "generating",
-  )
-  const [lipsyncErrorMessage, setLipsyncErrorMessage] = useState("")
-  /* ── 智能封面加载态 ── */
-  const [smartCoverLoading, setSmartCoverLoading] = useState(false)
-  /* ── 渲染进度弹窗 ── */
-  const [showRenderModal, setShowRenderModal] = useState(false)
-  const [renderStatus, setRenderStatus] = useState<"generating" | "completed" | "failed">(
-    "generating",
-  )
-  const [renderProgress, setRenderProgress] = useState(0)
-  const [renderErrorMessage, setRenderErrorMessage] = useState("")
-
   /* ── 对口型轮询 ── */
   const lipsyncTimerRef = useRef<ReturnType<typeof setInterval> | null>(null)
-  /* ── 渲染进度轮询 ── */
-  const renderTimerRef = useRef<ReturnType<typeof setInterval> | null>(null)
 
   const togglePanel = useCallback((key: PanelKey) => {
     setCollapsed((prev) => ({ ...prev, [key]: !prev[key] }))
   }, [])
 
-  /* ── 步骤切换 ── */
-  const handleNextStep = useCallback(() => {
-    const missing: string[] = []
-    if (!state.selectedVideo) missing.push("出镜视频")
-    if (!state.selectedVoice) missing.push("配音")
-    if (!state.scriptText.trim()) missing.push("文案")
-    if (missing.length > 0) {
-      message.warning(`请先完成${missing.join("、")}`)
-      return
-    }
-    setCurrentStep(2)
-  }, [state.selectedVideo, state.selectedVoice, state.scriptText])
-
-  const handlePrevStep = useCallback(() => {
-    setCurrentStep(1)
-  }, [])
-
   /* ── 对口型 ── */
   const handleGenerateLipsync = useCallback(async () => {
     // ② 缺项明确提示（#1809）：不再静默 return
@@ -104,150 +56,72 @@ const AiAvatarPage: React.FC = () => {
       return
     }
     try {
-      // 显示生成弹窗
-      setShowLipsyncModal(true)
-      setLipsyncStatus("generating")
-      setLipsyncErrorMessage("")
-
       // ① 先按素材 id 拿 file_url（#1809 补充：对齐后端新参数 video_url）
-      console.log("[对口型] 开始生成:", {
-        videoId: video.id,
-        voiceId: voice.voice_id,
-        voiceType: voice.type,
-        textLen: state.scriptText.length,
-      })
       const asset = await getAssetById(video.id)
-      console.log("[对口型] getAssetById 响应:", {
-        id: asset?.id,
-        file_url: asset?.file_url?.substring(0, 100),
-      })
       const videoUrl = asset?.file_url
       if (!videoUrl) {
-        console.error("[对口型] file_url 为空，asset:", asset)
-        setShowLipsyncModal(false)
         message.error("获取出镜视频播放地址失败，请重新选择素材")
         return
       }
-      // ② 模式A TTS直生：video_url + voice_id + script_text，语速/情绪英文枚举透传（#1822）
-      const payload = {
+      // ② voice_id（预设/克隆 UUID 均由后端内部调 TTS）+ script_text + video_url
+      const job = await createLipsyncJob({
         voice_id: voice.voice_id,
         script_text: state.scriptText,
         video_url: videoUrl,
-        speed: state.speed, // 语速 0.5~2.0
-        emotion: normalizeEmotion(state.emotion), // natural/excited/calm/friendly
-      }
-      console.log("[对口型] createLipsyncJob 请求:", payload)
-      const job = await createLipsyncJob(payload)
-      console.log("[对口型] createLipsyncJob 响应:", { id: job.id, status: job.status })
+      })
       state.setLipsyncJob(job)
+      message.success("对口型任务已提交，生成中…")
       // 开始轮询
       if (lipsyncTimerRef.current) clearInterval(lipsyncTimerRef.current)
       lipsyncTimerRef.current = setInterval(async () => {
         try {
           const updated = await getLipsyncJob(job.id)
           state.setLipsyncJob(updated)
-          console.log("[对口型] 轮询状态:", {
-            id: updated.id,
-            status: updated.status,
-            error: updated.error_message,
-          })
-          if (updated.status === "completed") {
+          if (updated.status === "completed" || updated.status === "failed") {
             if (lipsyncTimerRef.current) clearInterval(lipsyncTimerRef.current)
-            setLipsyncStatus("completed")
-            setTimeout(() => {
-              setShowLipsyncModal(false)
+            if (updated.status === "completed") {
               message.success("对口型视频生成完成")
-            }, 1000)
-          } else if (updated.status === "failed") {
-            if (lipsyncTimerRef.current) clearInterval(lipsyncTimerRef.current)
-            setLipsyncStatus("failed")
-            setLipsyncErrorMessage(updated.error_message || "对口型生成失败")
+            } else {
+              message.error(updated.error_message || "对口型生成失败")
+            }
           }
-        } catch (err) {
-          console.error("[对口型] 轮询错误:", err)
+        } catch {
+          // 忽略轮询错误（轮询期间不打扰用户）
         }
       }, 3000)
     } catch (err) {
-      console.error("[对口型] 创建失败:", {
-        status: (err as { response?: { status?: number } })?.response?.status,
-        data: (err as { response?: { data?: unknown } })?.response?.data,
-        message: err instanceof Error ? err.message : String(err),
-      })
-      setShowLipsyncModal(false)
+      // ② 接口失败弹错误提示，不只 console
+      console.error("对口型任务创建失败:", err)
       message.error(err instanceof Error ? err.message : "对口型任务提交失败，请重试")
     }
     // eslint-disable-next-line react-hooks/exhaustive-deps
-  }, [state.selectedVideo, state.selectedVoice, state.scriptText, state.speed, state.emotion])
-
-  // 取消对口型生成
-  const handleCancelLipsync = useCallback(() => {
-    if (lipsyncTimerRef.current) {
-      clearInterval(lipsyncTimerRef.current)
-      lipsyncTimerRef.current = null
-    }
-    setShowLipsyncModal(false)
-    setLipsyncStatus("generating")
-    setLipsyncErrorMessage("")
-  }, [])
+  }, [state.selectedVideo, state.selectedVoice, state.scriptText])
 
   // 清理轮询
   useEffect(() => {
     return () => {
       if (lipsyncTimerRef.current) clearInterval(lipsyncTimerRef.current)
-      if (renderTimerRef.current) clearInterval(renderTimerRef.current)
     }
   }, [])
 
-  /* ── 生成视频（含实时进度轮询） ── */
+  /* ── 生成视频 ── */
   const handleGenerate = useCallback(async () => {
+    // ② 前置条件提示（#1809）
     if (!state.lipsyncJob || state.lipsyncJob.status !== "completed") {
       message.warning("请先生成对口型视频，待对口型完成后再提交渲染")
       return
     }
     state.setIsGenerating(true)
     try {
-      const job = await submitRender({
+      await submitRender({
         lipsync_job_id: state.lipsyncJob.id,
         script_id: state.script?.id,
-        b_roll_segments: state.bRollSegments.map((seg) => ({
-          script_segment_index: seg.script_segment_index,
-          asset_url: seg.asset.file_url || "",
-          mode: seg.mode,
-          start_time: seg.start_time,
-          end_time: seg.end_time,
-          pip_position: seg.pip_position,
-          pip_scale: seg.pip_scale,
-        })) as never,
-        title_config: buildTitleConfigPayload(state.titleConfig),
-        cover_config: buildCoverConfigPayload(state.coverConfig, state.coverConfig.smart_cover_url),
+        b_roll_segments: state.bRollSegments as never,
+        title_config: state.titleConfig as unknown as Record<string, unknown>,
+        cover_config: state.coverConfig as unknown as Record<string, unknown>,
+        resolution: state.resolution,
       })
-
-      // 打开渲染进度弹窗，启动轮询
-      setShowRenderModal(true)
-      setRenderStatus("generating")
-      setRenderProgress(job.progress ?? 0)
-      setRenderErrorMessage("")
-
-      if (renderTimerRef.current) clearInterval(renderTimerRef.current)
-      renderTimerRef.current = setInterval(async () => {
-        try {
-          const updated = await getRenderJob(job.id)
-          setRenderProgress(updated.progress ?? 0)
-          if (updated.status === "completed") {
-            if (renderTimerRef.current) clearInterval(renderTimerRef.current)
-            renderTimerRef.current = null
-            setRenderStatus("completed")
-            message.success("视频已生成并保存到成片库")
-          } else if (updated.status === "failed") {
-            if (renderTimerRef.current) clearInterval(renderTimerRef.current)
-            renderTimerRef.current = null
-            setRenderStatus("failed")
-            setRenderErrorMessage(updated.error_message || "渲染失败，请重试")
-          }
-        } catch (pollErr) {
-          console.error("[渲染] 轮询失败:", pollErr)
-        }
-      }, 3000)
+      message.success("渲染任务已提交，可在视频管理中查看进度")
     } catch (err) {
       console.error("渲染任务提交失败:", err)
       message.error(err instanceof Error ? err.message : "渲染任务提交失败，请重试")
@@ -255,50 +129,14 @@ const AiAvatarPage: React.FC = () => {
       state.setIsGenerating(false)
     }
     // eslint-disable-next-line react-hooks/exhaustive-deps
-  }, [state.lipsyncJob, state.script, state.bRollSegments, state.titleConfig, state.coverConfig])
-
-  /* ── 关闭渲染进度弹窗 ── */
-  const handleCancelRender = useCallback(() => {
-    if (renderTimerRef.current) {
-      clearInterval(renderTimerRef.current)
-      renderTimerRef.current = null
-    }
-    setShowRenderModal(false)
-    setRenderStatus("generating")
-    setRenderProgress(0)
-    setRenderErrorMessage("")
-  }, [])
-
-  /* ── 智能封面：调后端 MediaKit 选帧接口（#1822） ── */
-  const handleSmartCover = useCallback(async () => {
-    // 基于对口型成片抽帧，必须先完成对口型
-    const videoUrl = state.lipsyncJob?.output_video_url
-    if (state.lipsyncJob?.status !== "completed" || !videoUrl) {
-      message.warning("请先生成对口型视频，完成后再智能获取封面")
-      return
-    }
-    setSmartCoverLoading(true)
-    try {
-      const res = await generateSmartCover(videoUrl, 5)
-      if (res.cover_url) {
-        state.setCoverConfig((prev) => ({
-          ...prev,
-          mode: "auto_frame",
-          smart_cover_url: res.cover_url,
-          thumbnail_url: res.cover_url,
-        }))
-        message.success("智能封面已生成")
-      } else {
-        message.error(res.message || "智能封面生成失败，请稍后重试")
-      }
-    } catch (err) {
-      console.error("智能封面生成失败:", err)
-      message.error(err instanceof Error ? err.message : "智能封面生成失败，请重试")
-    } finally {
-      setSmartCoverLoading(false)
-    }
-    // eslint-disable-next-line react-hooks/exhaustive-deps
-  }, [state.lipsyncJob])
+  }, [
+    state.lipsyncJob,
+    state.script,
+    state.bRollSegments,
+    state.titleConfig,
+    state.coverConfig,
+    state.resolution,
+  ])
 
   /* ── 配置汇总 ── */
   const summary = {
@@ -316,147 +154,95 @@ const AiAvatarPage: React.FC = () => {
       <div className="aa-page-header">
         <h1>AI数字人</h1>
       </div>
-
-      {/* 步骤切换导航条 */}
-      <div className="aa-step-nav">
-        <span className={`aa-step-nav__item${currentStep === 1 ? " active" : ""}`}>
-          1. 视频 / 配音 / 文案
-        </span>
-        <span className={`aa-step-nav__item${currentStep === 2 ? " active" : ""}`}>
-          2. 对口型 / 标题 / 封面 / 生成
-        </span>
-      </div>
-
       <div className="aa-page-body">
-        {/* ════ 步骤 1：出镜视频 / 配音库 / 文案 ════ */}
-        {currentStep === 1 && (
-          <>
-            {/* 面板1：出镜视频 */}
-            <div className={`aa-panel aa-panel--s1${collapsed.video ? " collapsed" : ""}`}>
-              <div className="aa-panel__header" onClick={() => togglePanel("video")}>
-                <span className="aa-panel__title">出镜视频</span>
-                <span className="aa-panel__toggle">▼</span>
-              </div>
-              <div className="aa-panel__body">
-                <PanelVideoSelector
-                  selectedVideo={state.selectedVideo}
-                  onSelectVideo={() => state.setShowAssetPicker(true)}
-                  onRemoveVideo={state.removeVideo}
-                  titleConfig={state.titleConfig}
-                />
-              </div>
-            </div>
+        {/* 面板1：出镜视频 */}
+        <div className={`aa-panel aa-panel--p1${collapsed.video ? " collapsed" : ""}`}>
+          <div className="aa-panel__header" onClick={() => togglePanel("video")}>
+            <span className="aa-panel__title">出镜视频</span>
+            <span className="aa-panel__toggle">▼</span>
+          </div>
+          <div className="aa-panel__body">
+            <PanelVideoSelector
+              selectedVideo={state.selectedVideo}
+              onSelectVideo={() => state.setShowAssetPicker(true)}
+              onRemoveVideo={state.removeVideo}
+            />
+          </div>
+        </div>
 
-            {/* 面板2：配音库 */}
-            <div className={`aa-panel aa-panel--s1${collapsed.voice ? " collapsed" : ""}`}>
-              <div className="aa-panel__header" onClick={() => togglePanel("voice")}>
-                <span className="aa-panel__title">配音库</span>
-                <span className="aa-panel__toggle">▼</span>
-              </div>
-              <div className="aa-panel__body">
-                <PanelVoiceSelector
-                  voiceSource={state.voiceSource}
-                  onVoiceSourceChange={state.setVoiceSource}
-                  selectedVoice={state.selectedVoice}
-                  onSelectVoice={state.setSelectedVoice}
-                  emotion={state.emotion}
-                  onEmotionChange={state.setEmotion}
-                  speed={state.speed}
-                  onSpeedChange={state.setSpeed}
-                  language={state.language}
-                  onLanguageChange={state.setLanguage}
-                />
-              </div>
-            </div>
+        {/* 面板2：配音库 */}
+        <div className={`aa-panel aa-panel--p2${collapsed.voice ? " collapsed" : ""}`}>
+          <div className="aa-panel__header" onClick={() => togglePanel("voice")}>
+            <span className="aa-panel__title">配音库</span>
+            <span className="aa-panel__toggle">▼</span>
+          </div>
+          <div className="aa-panel__body">
+            <PanelVoiceSelector
+              voiceSource={state.voiceSource}
+              onVoiceSourceChange={state.setVoiceSource}
+              selectedVoice={state.selectedVoice}
+              onSelectVoice={state.setSelectedVoice}
+              emotion={state.emotion}
+              onEmotionChange={state.setEmotion}
+              speed={state.speed}
+              onSpeedChange={state.setSpeed}
+              language={state.language}
+              onLanguageChange={state.setLanguage}
+            />
+          </div>
+        </div>
 
-            {/* 面板3：文案 */}
-            <div className={`aa-panel aa-panel--s1-wide${collapsed.script ? " collapsed" : ""}`}>
-              <div className="aa-panel__header" onClick={() => togglePanel("script")}>
-                <span className="aa-panel__title">文案 & 对口型</span>
-                <span className="aa-panel__toggle">▼</span>
-              </div>
-              <div className="aa-panel__body">
-                <PanelScript
-                  scriptText={state.scriptText}
-                  onScriptTextChange={state.setScriptText}
-                  onOpenScriptModal={() => state.setShowScriptModal(true)}
-                />
-                <div className="aa-step-btn-row">
-                  <button type="button" className="aa-btn aa-btn--primary" onClick={handleNextStep}>
-                    下一步 →
-                  </button>
-                </div>
-              </div>
-            </div>
-          </>
-        )}
+        {/* 面板3：文案 & 对口型 */}
+        <div className={`aa-panel aa-panel--p3${collapsed.script ? " collapsed" : ""}`}>
+          <div className="aa-panel__header" onClick={() => togglePanel("script")}>
+            <span className="aa-panel__title">文案 & 对口型</span>
+            <span className="aa-panel__toggle">▼</span>
+          </div>
+          <div className="aa-panel__body">
+            <PanelScriptAndLipsync
+              scriptText={state.scriptText}
+              onScriptTextChange={state.setScriptText}
+              onOpenScriptModal={() => state.setShowScriptModal(true)}
+              lipsyncJob={state.lipsyncJob}
+              onGenerateLipsync={handleGenerateLipsync}
+              bRollSegments={state.bRollSegments}
+              onOpenBRollModal={() => state.setShowBRollModal(true)}
+              onRemoveBRoll={state.removeBRollSegment}
+            />
+          </div>
+        </div>
 
-        {/* ════ 步骤 2：对口型预览（含插入画面）/ 标题配置 / 封面&生成 ════ */}
-        {currentStep === 2 && (
-          <>
-            {/* 面板：对口型预览 + 插入画面 */}
-            <div className={`aa-panel aa-panel--s2-wide${collapsed.lipsync ? " collapsed" : ""}`}>
-              <div className="aa-panel__header" onClick={() => togglePanel("lipsync")}>
-                <span className="aa-panel__title">对口型预览</span>
-                <span className="aa-panel__toggle">▼</span>
-              </div>
-              <div className="aa-panel__body">
-                <PanelLipsyncPreview
-                  lipsyncJob={state.lipsyncJob}
-                  onGenerateLipsync={handleGenerateLipsync}
-                  bRollSegments={state.bRollSegments}
-                  onOpenBRollModal={() => state.setShowBRollModal(true)}
-                  onRemoveBRoll={state.removeBRollSegment}
-                  titleConfig={state.titleConfig}
-                  onTitlePositionChange={(pos) => state.updateTitleConfig(pos)}
-                />
-                <div className="aa-step-btn-row">
-                  <button type="button" className="aa-btn" onClick={handlePrevStep}>
-                    ← 上一步
-                  </button>
-                </div>
-              </div>
-            </div>
+        {/* 面板4：标题配置 */}
+        <div className={`aa-panel aa-panel--p4${collapsed.title ? " collapsed" : ""}`}>
+          <div className="aa-panel__header" onClick={() => togglePanel("title")}>
+            <span className="aa-panel__title">标题配置</span>
+            <span className="aa-panel__toggle">▼</span>
+          </div>
+          <div className="aa-panel__body">
+            <PanelTitleConfig titleConfig={state.titleConfig} onUpdate={state.updateTitleConfig} />
+          </div>
+        </div>
 
-            {/* 面板4：标题配置 */}
-            <div className={`aa-panel aa-panel--s2${collapsed.title ? " collapsed" : ""}`}>
-              <div className="aa-panel__header" onClick={() => togglePanel("title")}>
-                <span className="aa-panel__title">标题配置</span>
-                <span className="aa-panel__toggle">▼</span>
-              </div>
-              <div className="aa-panel__body">
-                <PanelTitleConfig
-                  titleConfig={state.titleConfig}
-                  onUpdate={state.updateTitleConfig}
-                />
-              </div>
-            </div>
-
-            {/* 面板5：封面 & 生成 */}
-            <div className={`aa-panel aa-panel--s2${collapsed.cover ? " collapsed" : ""}`}>
-              <div className="aa-panel__header" onClick={() => togglePanel("cover")}>
-                <span className="aa-panel__title">封面 & 生成</span>
-                <span className="aa-panel__toggle">▼</span>
-              </div>
-              <div className="aa-panel__body">
-                <PanelCoverAndGenerate
-                  coverConfig={state.coverConfig}
-                  onCoverConfigChange={(partial) =>
-                    state.setCoverConfig((prev) => ({ ...prev, ...partial }))
-                  }
-                  onSmartCover={handleSmartCover}
-                  smartCoverLoading={smartCoverLoading}
-                  canSmartCover={state.lipsyncJob?.status === "completed"}
-                  resolution={state.resolution}
-                  onResolutionChange={state.setResolution}
-                  isGenerating={state.isGenerating}
-                  onGenerate={handleGenerate}
-                  summary={summary}
-                />
-              </div>
-            </div>
-          </>
-        )}
+        {/* 面板5：封面 & 生成 */}
+        <div className={`aa-panel aa-panel--p5${collapsed.cover ? " collapsed" : ""}`}>
+          <div className="aa-panel__header" onClick={() => togglePanel("cover")}>
+            <span className="aa-panel__title">封面 & 生成</span>
+            <span className="aa-panel__toggle">▼</span>
+          </div>
+          <div className="aa-panel__body">
+            <PanelCoverAndGenerate
+              coverConfig={state.coverConfig}
+              onCoverConfigChange={(partial) =>
+                state.setCoverConfig((prev) => ({ ...prev, ...partial }))
+              }
+              resolution={state.resolution}
+              onResolutionChange={state.setResolution}
+              isGenerating={state.isGenerating}
+              onGenerate={handleGenerate}
+              summary={summary}
+            />
+          </div>
+        </div>
       </div>
 
       {/* 素材库弹窗 */}
@@ -490,180 +276,6 @@ const AiAvatarPage: React.FC = () => {
           onRemove={state.removeBRollSegment}
         />
       )}
-
-      {/* 对口型生成弹窗 */}
-      {showLipsyncModal && (
-        <div className="aa-modal-overlay">
-          <div className="aa-modal" onClick={(e) => e.stopPropagation()}>
-            <div className="aa-modal__header">
-              <span className="aa-modal__title">对口型生成</span>
-              <button className="aa-modal__close" onClick={handleCancelLipsync}>
-                ✕
-              </button>
-            </div>
-            <div
-              className="aa-modal__body"
-              style={{
-                display: "flex",
-                flexDirection: "column",
-                alignItems: "center",
-                padding: "40px 20px",
-              }}
-            >
-              {lipsyncStatus === "generating" && (
-                <>
-                  <div className="aa-lipsync-spinner" />
-                  <div style={{ marginTop: 20, fontSize: 15, color: "#1a1a2e" }}>
-                    对口型视频生成中…
-                  </div>
-                  <div style={{ marginTop: 8, fontSize: 13, color: "#8c8ca1" }}>
-                    请勿关闭页面，完成后将自动提示
-                  </div>
-                </>
-              )}
-              {lipsyncStatus === "completed" && (
-                <>
-                  <div style={{ fontSize: 48 }}>✅</div>
-                  <div style={{ marginTop: 16, fontSize: 15, color: "#1a1a2e" }}>
-                    对口型视频生成完成
-                  </div>
-                </>
-              )}
-              {lipsyncStatus === "failed" && (
-                <>
-                  <div style={{ fontSize: 48 }}>❌</div>
-                  <div style={{ marginTop: 16, fontSize: 15, color: "#1a1a2e" }}>
-                    对口型生成失败
-                  </div>
-                  {lipsyncErrorMessage && (
-                    <div style={{ marginTop: 8, fontSize: 13, color: "#ff4d4f" }}>
-                      {lipsyncErrorMessage}
-                    </div>
-                  )}
-                </>
-              )}
-            </div>
-            <div className="aa-modal__footer">
-              {lipsyncStatus === "generating" && (
-                <button className="aa-btn aa-btn--danger" onClick={handleCancelLipsync}>
-                  取消生成
-                </button>
-              )}
-              {lipsyncStatus !== "generating" && (
-                <button className="aa-btn" onClick={handleCancelLipsync}>
-                  关闭
-                </button>
-              )}
-            </div>
-          </div>
-        </div>
-      )}
-
-      {/* 渲染进度弹窗 */}
-      {showRenderModal && (
-        <div className="aa-modal-overlay">
-          <div className="aa-modal" onClick={(e) => e.stopPropagation()}>
-            <div className="aa-modal__header">
-              <span className="aa-modal__title">视频渲染</span>
-              <button className="aa-modal__close" onClick={handleCancelRender}>
-                ✕
-              </button>
-            </div>
-            <div
-              className="aa-modal__body"
-              style={{
-                display: "flex",
-                flexDirection: "column",
-                alignItems: "center",
-                padding: "40px 20px",
-              }}
-            >
-              {renderStatus === "generating" && (
-                <>
-                  <div className="aa-lipsync-spinner" />
-                  <div style={{ marginTop: 20, fontSize: 15, color: "#1a1a2e" }}>
-                    正在生成视频，请稍后
-                  </div>
-                  <div
-                    style={{
-                      marginTop: 16,
-                      fontSize: 32,
-                      fontWeight: 700,
-                      color: "#1890ff",
-                    }}
-                  >
-                    {renderProgress}%
-                  </div>
-                  <div
-                    style={{
-                      marginTop: 12,
-                      width: "80%",
-                      height: 8,
-                      backgroundColor: "#f0f0f0",
-                      borderRadius: 4,
-                      overflow: "hidden",
-                    }}
-                  >
-                    <div
-                      style={{
-                        width: `${renderProgress}%`,
-                        height: "100%",
-                        backgroundColor: "#1890ff",
-                        borderRadius: 4,
-                        transition: "width 0.5s ease",
-                      }}
-                    />
-                  </div>
-                  <div style={{ marginTop: 12, fontSize: 13, color: "#8c8ca1" }}>
-                    请勿关闭页面，完成后将自动提示
-                  </div>
-                </>
-              )}
-              {renderStatus === "completed" && (
-                <>
-                  <div style={{ fontSize: 48 }}>✅</div>
-                  <div style={{ marginTop: 16, fontSize: 15, color: "#1a1a2e" }}>
-                    视频已保存到成片库
-                  </div>
-                  <button
-                    className="aa-btn"
-                    style={{ marginTop: 16 }}
-                    onClick={() => {
-                      setShowRenderModal(false)
-                      navigate("/app/products")
-                    }}
-                  >
-                    📁 查看成片
-                  </button>
-                </>
-              )}
-              {renderStatus === "failed" && (
-                <>
-                  <div style={{ fontSize: 48 }}>❌</div>
-                  <div style={{ marginTop: 16, fontSize: 15, color: "#1a1a2e" }}>视频渲染失败</div>
-                  {renderErrorMessage && (
-                    <div style={{ marginTop: 8, fontSize: 13, color: "#ff4d4f" }}>
-                      {renderErrorMessage}
-                    </div>
-                  )}
-                </>
-              )}
-            </div>
-            <div className="aa-modal__footer">
-              {renderStatus === "generating" && (
-                <button className="aa-btn aa-btn--danger" onClick={handleCancelRender}>
-                  关闭窗口
-                </button>
-              )}
-              {renderStatus !== "generating" && (
-                <button className="aa-btn" onClick={handleCancelRender}>
-                  关闭
-                </button>
-              )}
-            </div>
-          </div>
-        </div>
-      )}
     </div>
   )
 }

apps/web/src/pages/ai-avatar/api/aiAvatar.ts

@@ -1,5 +1,5 @@
 /**
- * AI数字人 — API 封装（#1822 契约对齐）
+ * AI数字人 — API 封装
  */
 import apiClient from "@/api/client"
 import type { Script, LipsyncJob, RenderJob, BRollSegment } from "../types"
@@ -28,26 +28,17 @@ export const deleteScript = async (id: string): Promise<void> => {
   await apiClient.delete(`/scripts/${id}`)
 }
 
-/* ── 素材单查（拿到 file_url 作为对口型的 video_url） ── */
+/* ── 素材单查（用于拿到 file_url 传给对口型等新接口） ── */
 export const getAssetById = async (id: string): Promise<{ file_url?: string; id: string }> => {
   const response = await apiClient.get<{ file_url?: string; id: string }>(`/assets/${id}`)
   return response.data
 }
 
-/* ── 对口型（模式A：TTS 直生，后端内部合成音频；不要先调 TTS 拿 audio_url） ── */
+/* ── 对口型 ── */
 export const createLipsyncJob = async (data: {
-  /** 人物视频 URL（MP4）；由素材 id 经 getAssetById 拿 file_url，禁止传 video_asset_id */
-  video_url: string
-  /** 音色 ID（预置音色 或 克隆音色 profile UUID，后端会解析） */
   voice_id: string
-  /** 要合成的文案（手动输入或文案库内容） */
   script_text: string
-  /** 语速 0.5~2.0，默认 1.0 */
-  speed?: number
-  /** 情绪英文枚举：natural/excited/calm/friendly */
-  emotion?: string
-  enable_video_loop?: boolean
-  project_id?: string
+  video_url: string
 }): Promise<LipsyncJob> => {
   const response = await apiClient.post<LipsyncJob>("/lipsync/jobs", data)
   return response.data
@@ -58,19 +49,6 @@ export const getLipsyncJob = async (id: string): Promise<LipsyncJob> => {
   return response.data
 }
 
-/* ── 智能封面（MediaKit 抽帧 + 质量评分选最佳帧，独立于渲染任务） ── */
-export const generateSmartCover = async (
-  video_url: string,
-  max_frames = 5,
-): Promise<{ cover_url: string; status: string; message: string }> => {
-  const response = await apiClient.post<{ cover_url: string; status: string; message: string }>(
-    "/ai-avatar/render/smart-cover",
-    { video_url, max_frames },
-    { timeout: 60000 },
-  )
-  return response.data
-}
-
 /* ── 渲染 ── */
 export const submitRender = async (data: {
   lipsync_job_id: string
@@ -79,6 +57,7 @@ export const submitRender = async (data: {
   title_config?: Record<string, unknown>
   cover_config?: Record<string, unknown>
   project_id?: string
+  resolution?: string
 }): Promise<RenderJob> => {
   const response = await apiClient.post<RenderJob>("/ai-avatar/render", data)
   return response.data

apps/web/src/pages/ai-avatar/components/PanelCoverAndGenerate.tsx

@@ -17,10 +17,6 @@ interface PanelCoverAndGenerateProps {
   onResolutionChange: (r: string) => void
   isGenerating: boolean
   onGenerate: () => void
-  /** 智能获取封面（MediaKit 选帧） */
-  onSmartCover: () => void
-  smartCoverLoading: boolean
-  canSmartCover: boolean
   /** 配置汇总信息 */
   summary: {
     videoName: string | null
@@ -54,9 +50,6 @@ const PanelCoverAndGenerate: React.FC<PanelCoverAndGenerateProps> = ({
   onResolutionChange,
   isGenerating,
   onGenerate,
-  onSmartCover,
-  smartCoverLoading,
-  canSmartCover,
   summary,
 }) => {
   const uploadInputRef = useRef<HTMLInputElement>(null)
@@ -76,10 +69,9 @@ const PanelCoverAndGenerate: React.FC<PanelCoverAndGenerateProps> = ({
     e.target.value = ""
   }
 
-  /** 智能获取封面（调后端 MediaKit 抽帧评分选最佳帧，#1822） */
-  const handleSmartCover = () => {
+  /** 从视频截取（使用配置的帧时间，默认首帧） */
+  const handleCaptureFromVideo = () => {
     onCoverConfigChange({ mode: "auto_frame" })
-    onSmartCover()
   }
 
   const lipsync = summary.lipsyncStatus ? LIPSYNC_STATUS_LABEL[summary.lipsyncStatus] : null
@@ -101,11 +93,9 @@ const PanelCoverAndGenerate: React.FC<PanelCoverAndGenerateProps> = ({
         <button
           type="button"
           className={`aa-btn aa-btn--ghost${coverConfig.mode === "auto_frame" ? " active" : ""}`}
-          onClick={handleSmartCover}
-          disabled={smartCoverLoading || !canSmartCover}
-          title={canSmartCover ? "基于对口型成片智能选帧" : "请先完成对口型生成"}
+          onClick={handleCaptureFromVideo}
         >
-          {smartCoverLoading ? "⏳ 智能选帧中…" : "🎬 智能获取封面"}
+          🎬 从视频截取
         </button>
         <button
           type="button"

apps/web/src/pages/ai-avatar/components/PanelScript.tsx

@@ -1,67 +0,0 @@
-/**
- * AI数字人 — 文案面板（步骤1用）
- * 文案库选择 / 手动输入 + 字数统计
- */
-import { useState } from "react"
-
-interface PanelScriptProps {
-  scriptText: string
-  onScriptTextChange: (text: string) => void
-  onOpenScriptModal: () => void
-}
-
-type ScriptTab = "library" | "manual"
-
-export function PanelScript({
-  scriptText,
-  onScriptTextChange,
-  onOpenScriptModal,
-}: PanelScriptProps) {
-  const [scriptTab, setScriptTab] = useState<ScriptTab>("library")
-
-  return (
-    <div className="aa-script-lipsync">
-      {/* ── Tab 切换 ── */}
-      <div className="aa-script-tabs">
-        <button
-          type="button"
-          className={`aa-script-tab${scriptTab === "library" ? " active" : ""}`}
-          onClick={() => setScriptTab("library")}
-        >
-          从文案库选择
-        </button>
-        <button
-          type="button"
-          className={`aa-script-tab${scriptTab === "manual" ? " active" : ""}`}
-          onClick={() => setScriptTab("manual")}
-        >
-          手动输入
-        </button>
-      </div>
-
-      {scriptTab === "library" && (
-        <button
-          type="button"
-          className="aa-btn aa-btn--ghost aa-btn--full"
-          style={{ marginBottom: 8 }}
-          onClick={onOpenScriptModal}
-        >
-          📚 从文案库选择文案
-        </button>
-      )}
-
-      <textarea
-        className="aa-textarea"
-        value={scriptText}
-        readOnly={scriptTab === "library"}
-        placeholder={
-          scriptTab === "library" ? "点击上方按钮，从文案库选择文案…" : "请输入数字人口播文案…"
-        }
-        onChange={(e) => onScriptTextChange(e.target.value)}
-      />
-      <div className="aa-char-count">{scriptText.length} 字</div>
-    </div>
-  )
-}
-
-export default PanelScript

apps/web/src/pages/ai-avatar/components/PanelScriptAndLipsync.tsx

@@ -1,23 +1,23 @@
 /**
- * AI数字人 — 对口型预览面板（步骤2用）
- * B-roll 画面插入 + 对口型视频预览 + 生成/重新生成按钮
- * v3.1: 预览容器按 1/2 缩放、标题实时叠加预览
+ * AI数字人 — 文案 & 对口型面板（面板4）
+ * 上半区：文案（文案库选择 / 手动输入）；下半区：对口型视频预览（9:16）+ B-roll 画面
  */
-import React, { useRef } from "react"
-import type { LipsyncJob, BRollSegment, AiAvatarTitleConfig } from "../types"
+import { useState } from "react"
+import type { LipsyncJob, BRollSegment } from "../types"
 
-interface PanelLipsyncPreviewProps {
+interface PanelScriptAndLipsyncProps {
+  scriptText: string
+  onScriptTextChange: (text: string) => void
+  onOpenScriptModal: () => void
   lipsyncJob: LipsyncJob | null
   onGenerateLipsync: () => void
   bRollSegments: BRollSegment[]
   onOpenBRollModal: () => void
   onRemoveBRoll: (id: string) => void
-  /** 标题配置（实时叠加预览用） */
-  titleConfig?: AiAvatarTitleConfig
-  /** 标题位置变更回调（拖拽结束时调用） */
-  onTitlePositionChange?: (pos: { pos_x: number; pos_y: number }) => void
 }
 
+type ScriptTab = "library" | "manual"
+
 const BROLL_MODE_LABEL: Record<BRollSegment["mode"], string> = {
   fullscreen: "全屏",
   pip: "画中画",
@@ -29,18 +29,19 @@ function formatTime(seconds: number): string {
   return `${m}:${s.toString().padStart(2, "0")}`
 }
 
-export function PanelLipsyncPreview({
+export function PanelScriptAndLipsync({
+  scriptText,
+  onScriptTextChange,
+  onOpenScriptModal,
   lipsyncJob,
   onGenerateLipsync,
   bRollSegments,
   onOpenBRollModal,
   onRemoveBRoll,
-  titleConfig,
-  onTitlePositionChange,
-}: PanelLipsyncPreviewProps) {
-  const titleDragRef = useRef<HTMLDivElement>(null)
-  const draggingTitleRef = useRef(false)
-  const previewContainerRef = useRef<HTMLDivElement>(null)
+}: PanelScriptAndLipsyncProps) {
+  const [scriptTab, setScriptTab] = useState<ScriptTab>("library")
+
+  /* 对口型状态判断 */
   const isGenerating = lipsyncJob?.status === "pending" || lipsyncJob?.status === "processing"
   const isDone = lipsyncJob?.status === "completed"
   const isFailed = lipsyncJob?.status === "failed"
@@ -52,66 +53,48 @@ export function PanelLipsyncPreview({
         ? "排队中…"
         : "对口型生成中…"
 
-  /** 标题叠加样式 */
-  const titleOverlayStyle: React.CSSProperties | null = titleConfig?.title
-    ? {
-        position: "absolute",
-        left: "50%",
-        transform: "translateX(-50%)",
-        color: titleConfig.color || "#ffffff",
-        fontFamily: titleConfig.font || "思源黑体",
-        fontSize: `${(titleConfig.size || 36) * 0.55}px`, // 预览等比缩
-        fontWeight: titleConfig.bold ? 700 : 400,
-        fontStyle: titleConfig.italic ? "italic" : "normal",
-        textAlign: "center",
-        width: "90%",
-        padding: "4px 8px",
-        textShadow: titleConfig.shadow ? "0 2px 4px rgba(0,0,0,0.8)" : undefined,
-        WebkitTextStroke: titleConfig.stroke ? "1.5px #000" : undefined,
-        ...(titleConfig.position === "top"
-          ? { top: 8 }
-          : titleConfig.position === "bottom"
-            ? { bottom: 8 }
-            : { top: "50%", transform: "translateX(-50%) translateY(-50%)" }),
-      }
-    : null
-
-  const handleTitlePointerDown = (e: React.PointerEvent<HTMLDivElement>) => {
-    if (!onTitlePositionChange || !previewContainerRef.current) return
-    e.preventDefault()
-    e.stopPropagation()
-    ;(e.target as Element).setPointerCapture(e.pointerId)
-    draggingTitleRef.current = true
-    ;(e.currentTarget as HTMLDivElement).style.cursor = "grabbing"
-  }
-  const handleTitlePointerMove = (e: React.PointerEvent<HTMLDivElement>) => {
-    if (!draggingTitleRef.current || !previewContainerRef.current) return
-    e.preventDefault()
-    e.stopPropagation()
-    if (titleDragRef.current) {
-      const rect = previewContainerRef.current.getBoundingClientRect()
-      const relX = Math.max(0, Math.min(rect.width, e.clientX - rect.left))
-      const relY = Math.max(0, Math.min(rect.height, e.clientY - rect.top))
-      const xpct = (relX / rect.width) * 100
-      const ypct = (relY / rect.height) * 100
-      titleDragRef.current.style.left = `${xpct}%`
-      titleDragRef.current.style.top = `${ypct}%`
-    }
-  }
-  const handleTitlePointerUp = (e: React.PointerEvent<HTMLDivElement>) => {
-    if (!draggingTitleRef.current) return
-    draggingTitleRef.current = false
-    if (onTitlePositionChange && previewContainerRef.current) {
-      const rect = previewContainerRef.current.getBoundingClientRect()
-      const relX = Math.max(0, Math.min(rect.width, e.clientX - rect.left))
-      const relY = Math.max(0, Math.min(rect.height, e.clientY - rect.top))
-      onTitlePositionChange({ pos_x: relX, pos_y: relY })
-    }
-    ;(e.currentTarget as HTMLDivElement).style.cursor = "grab"
-  }
-
   return (
     <div className="aa-script-lipsync">
+      {/* ── 上半区：文案 ── */}
+      <div className="aa-script-tabs">
+        <button
+          type="button"
+          className={`aa-script-tab${scriptTab === "library" ? " active" : ""}`}
+          onClick={() => setScriptTab("library")}
+        >
+          从文案库选择
+        </button>
+        <button
+          type="button"
+          className={`aa-script-tab${scriptTab === "manual" ? " active" : ""}`}
+          onClick={() => setScriptTab("manual")}
+        >
+          手动输入
+        </button>
+      </div>
+
+      {scriptTab === "library" && (
+        <button
+          type="button"
+          className="aa-btn aa-btn--ghost aa-btn--full"
+          style={{ marginBottom: 8 }}
+          onClick={onOpenScriptModal}
+        >
+          📚 从文案库选择文案
+        </button>
+      )}
+
+      <textarea
+        className="aa-textarea"
+        value={scriptText}
+        readOnly={scriptTab === "library"}
+        placeholder={
+          scriptTab === "library" ? "点击上方按钮，从文案库选择文案…" : "请输入数字人口播文案…"
+        }
+        onChange={(e) => onScriptTextChange(e.target.value)}
+      />
+      <div className="aa-char-count">{scriptText.length} 字</div>
+
       {/* ── B-roll 画面 ── */}
       <div className="aa-lipsync-section">
         <div className="aa-lipsync-section__title">
@@ -174,36 +157,13 @@ export function PanelLipsyncPreview({
         )}
       </div>
 
-      {/* ── 对口型预览（v3.1: 缩放1/2 + 标题叠加） ─ */}
+      {/* ── 下半区：对口型预览（竖屏 9:16） ── */}
       <div className="aa-lipsync-section">
         <div className="aa-lipsync-section__title">对口型预览</div>
 
-        <div className="aa-lipsync-preview" ref={previewContainerRef}>
+        <div className="aa-lipsync-preview">
           {isDone && lipsyncJob?.output_video_url ? (
-            <div style={{ position: "relative", width: "100%", height: "100%" }}>
-              <video src={lipsyncJob.output_video_url} controls />
-              {titleOverlayStyle && (
-                <div
-                  ref={titleDragRef}
-                  style={{
-                    ...titleOverlayStyle,
-                    cursor: onTitlePositionChange ? "grab" : "default",
-                    pointerEvents: onTitlePositionChange ? "auto" : "none",
-                  }}
-                  onPointerDown={handleTitlePointerDown}
-                  onPointerMove={handleTitlePointerMove}
-                  onPointerUp={handleTitlePointerUp}
-                  onPointerCancel={handleTitlePointerUp}
-                >
-                  {titleConfig!.title.split(/[/／]/).map((part, i) => (
-                    <span key={i}>
-                      {i > 0 && <br />}
-                      {part}
-                    </span>
-                  ))}
-                </div>
-              )}
-            </div>
+            <video src={lipsyncJob.output_video_url} controls />
           ) : isGenerating ? (
             <div style={{ width: "80%", textAlign: "center", color: "#fff" }}>
               <div style={{ fontSize: 13, marginBottom: 8 }}>
@@ -223,13 +183,7 @@ export function PanelLipsyncPreview({
                   <div style={{ fontSize: 28, marginBottom: 8 }}>❌</div>
                   <div>对口型生成失败</div>
                   {lipsyncJob?.error_message && (
-                    <div
-                      style={{
-                        fontSize: 11,
-                        marginTop: 4,
-                        color: "#fca5a5",
-                      }}
-                    >
+                    <div style={{ fontSize: 11, marginTop: 4, color: "#fca5a5" }}>
                       {lipsyncJob.error_message}
                     </div>
                   )}
@@ -265,4 +219,4 @@ export function PanelLipsyncPreview({
   )
 }
 
-export default PanelLipsyncPreview
+export default PanelScriptAndLipsync

apps/web/src/pages/ai-avatar/components/PanelTitleConfig.tsx

@@ -7,17 +7,16 @@
  * - AiAvatarTitleConfig ↔ TitleSettings 的双向适配
  * - 自动生成字幕开关
  */
-import React, { useMemo, useState, useEffect } from "react"
-import { Input } from "antd"
+import React, { useMemo, useState } from "react"
 import TitleStylePanel from "@/pages/generate/components/title/TitleStylePanel"
-import TitleLibraryAutoComplete from "@/pages/generate/components/title/TitleLibraryAutoComplete"
-import type { TitleOption } from "@/pages/generate/components/title/TitleLibraryAutoComplete"
 import type { TitleSettings } from "@/pages/generate/types"
-import { POSITION_OPTIONS, FONT_OPTIONS, TITLE_PRESETS } from "@/pages/generate/constants"
+import {
+  POSITION_OPTIONS,
+  FONT_OPTIONS,
+  TITLE_PRESETS,
+  getFontFamily,
+} from "@/pages/generate/constants"
 import type { AiAvatarTitleConfig } from "../types"
-import { getTitles } from "@/api/titles"
-
-const { TextArea } = Input
 
 interface PanelTitleConfigProps {
   titleConfig: AiAvatarTitleConfig
@@ -28,14 +27,6 @@ const PanelTitleConfig: React.FC<PanelTitleConfigProps> = ({ titleConfig, onUpda
   /** TitleStylePanel 内部高亮的预设 key（面板本地状态） */
   const [activePreset, setActivePreset] = useState<string | null>(null)
 
-  /** 标题库选项（复用智能剪辑的标题库） */
-  const [titleOptions, setTitleOptions] = useState<TitleOption[]>([])
-  useEffect(() => {
-    getTitles()
-      .then((items) => setTitleOptions(items.map((t) => ({ label: t.content, value: t.content }))))
-      .catch(() => setTitleOptions([]))
-  }, [])
-
   /** AiAvatarTitleConfig → TitleSettings（补齐 aiAutoSelect / 自由坐标字段） */
   const titleSettings: TitleSettings = useMemo(
     () => ({
@@ -71,32 +62,37 @@ const PanelTitleConfig: React.FC<PanelTitleConfigProps> = ({ titleConfig, onUpda
 
   return (
     <div className="aa-title-config">
-      {/* 主标题输入 — TextArea 多行 + 标题库选择 */}
+      {/* 主标题输入 */}
       <div className="aa-form-field">
         <label className="aa-label">主标题</label>
-        <TextArea
-          className="aa-title-input"
-          placeholder="输入视频标题（支持 / 分行）"
+        <input
+          className="aa-input aa-title-input"
+          type="text"
+          placeholder="输入视频标题（留空则不显示标题）"
           value={titleConfig.title}
-          autoSize={{ minRows: 2, maxRows: 4 }}
-          maxLength={200}
+          maxLength={30}
           onChange={(e) => onUpdate({ title: e.target.value })}
-          style={{ fontSize: 15 }}
         />
-        <div style={{ marginTop: 8, display: "flex", alignItems: "center", gap: 8 }}>
-          <span style={{ fontSize: 12, color: "#8c8ca1", whiteSpace: "nowrap" }}>📚 标题库</span>
-          <TitleLibraryAutoComplete
-            key={titleConfig.title}
-            placeholder="选择标题填入上方"
-            value=""
-            onChange={(val) => {
-              if (val) onUpdate({ title: val })
+        {titleConfig.title && (
+          <div
+            style={{
+              fontSize: 13,
+              padding: "6px 8px",
+              background: "#f8f8fc",
+              borderRadius: 6,
+              fontFamily: getFontFamily(titleConfig.font),
+              fontWeight: titleConfig.bold ? 700 : 400,
+              fontStyle: titleConfig.italic ? "italic" : "normal",
+              color: titleConfig.color,
+              textShadow: titleConfig.shadow ? "1px 1px 3px rgba(0,0,0,0.6)" : undefined,
+              overflow: "hidden",
+              textOverflow: "ellipsis",
+              whiteSpace: "nowrap",
             }}
-            options={titleOptions}
-            maxLength={200}
-            style={{ flex: 1 }}
-          />
-        </div>
+          >
+            {titleConfig.title}
+          </div>
+        )}
       </div>
 
       {/* 标题样式：直接复用智能剪辑 TitleStylePanel（位置/字体/字号/样式/预设） */}

apps/web/src/pages/ai-avatar/components/PanelVideoSelector.tsx

@@ -4,15 +4,12 @@
  * - 已选视频：竖屏 9:16 预览播放器 + 视频信息卡片 + 移除按钮
  */
 import type { AssetItem } from "@/api/assets"
-import type { AiAvatarTitleConfig } from "../types"
-import { getFontFamily } from "@/pages/generate/constants"
 
 export interface PanelVideoSelectorProps {
   selectedVideo: AssetItem | null
   /** 触发打开素材库弹窗 */
   onSelectVideo: () => void
   onRemoveVideo: () => void
-  titleConfig?: AiAvatarTitleConfig
 }
 
 /** 格式化时长（秒 → mm:ss） */
@@ -27,7 +24,6 @@ export function PanelVideoSelector({
   selectedVideo,
   onSelectVideo,
   onRemoveVideo,
-  titleConfig,
 }: PanelVideoSelectorProps) {
   /* 未选视频：虚线上传区，点击打开素材库弹窗 */
   if (!selectedVideo) {
@@ -57,42 +53,13 @@ export function PanelVideoSelector({
 
   return (
     <div>
-      {/* 竖屏 9:16 视频预览播放器 + 标题实时预览 */}
-      <div className="aa-video-preview" style={{ position: "relative" }}>
+      {/* 竖屏 9:16 视频预览播放器 */}
+      <div className="aa-video-preview">
         {fileUrl ? (
           <video src={fileUrl} poster={selectedVideo.thumbnail_url} controls playsInline />
         ) : (
           <div className="aa-video-preview__placeholder">视频暂不可预览</div>
         )}
-        {titleConfig?.title && (
-          <div
-            style={{
-              position: "absolute",
-              left: "50%",
-              transform: "translateX(-50%)",
-              ...(titleConfig.position === "top"
-                ? { top: "10%" }
-                : titleConfig.position === "bottom"
-                  ? { bottom: "10%" }
-                  : { top: "50%", transform: "translate(-50%, -50%)" }),
-              fontSize: Math.max(titleConfig.size, 32),
-              fontFamily: getFontFamily(titleConfig.font),
-              color: titleConfig.color,
-              fontWeight: titleConfig.bold ? 700 : 400,
-              fontStyle: titleConfig.italic ? "italic" : "normal",
-              textShadow: "0 2px 4px rgba(0,0,0,0.5)",
-              WebkitTextStroke: "2px #000",
-              pointerEvents: "none",
-              zIndex: 10,
-              maxWidth: "90%",
-              textAlign: "center",
-              whiteSpace: "pre-wrap",
-              lineHeight: 1.3,
-            }}
-          >
-            {titleConfig.title}
-          </div>
-        )}
       </div>
 
       {/* 视频信息卡片：文件名 / 时长 / 分辨率 */}

apps/web/src/pages/ai-avatar/components/PanelVoiceSelector.tsx

@@ -6,7 +6,6 @@ import { useEffect, useRef, useState } from "react"
 import { message } from "antd"
 import { fetchVoices } from "@/api/voices/voices"
 import { previewTts } from "@/api/tts"
-import { normalizeEmotion } from "../utils/contract"
 import type { UnifiedVoiceItem } from "@/api/voices/types"
 import {
   type VoiceSource,
@@ -93,14 +92,11 @@ export function PanelVoiceSelector({
 
   /** 用指定 URL 真实播放（抽取公共） */
   const playAudioUrl = (voiceId: string, url: string) => {
-    // 临时兼容：后端 /tts/preview 返回 HTTP URL，staging 是 HTTPS，Mixed Content 会阻止加载
-    // OSS 同时支持 HTTP/HTTPS，直接替换协议即可
-    const safeUrl = url.startsWith("http://") ? url.replace("http://", "https://") : url
     if (audioRef.current) {
       audioRef.current.pause()
       audioRef.current = null
     }
-    const audio = new Audio(safeUrl)
+    const audio = new Audio(url)
     audioRef.current = audio
     setPreviewingId(voiceId)
     audio.onended = () => {
@@ -151,8 +147,7 @@ export function PanelVoiceSelector({
         const res = await previewTts({
           text: VOICE_PREVIEW_TEXT,
           voice_id: targetId,
-          speed: speed, // 透传用户选择的语速（#1822）
-          emotion: normalizeEmotion(emotion), // 情绪中文→英文枚举
+          speed: 1.0,
         })
         console.log("[AI数字人-克隆试听] previewTts 响应:", {
           audio_url: res.audio_url?.substring(0, 80),
@@ -252,7 +247,7 @@ export function PanelVoiceSelector({
                   type="button"
                   className="aa-voice-card__preview"
                   title={previewingId === voice.id ? "停止试听" : "试听"}
-                  disabled={voice.type === "preset" && !previewUrl}
+                  disabled={!previewUrl}
                   onClick={(e) => {
                     e.stopPropagation()
                     handlePreview(voice)

apps/web/src/pages/ai-avatar/components/TitleLibraryModal.tsx

@@ -1,97 +0,0 @@
-/**
- * AI数字人 — 标题库选择弹窗
- * 复用智能剪辑的标题库 API，选择标题后填入输入框
- */
-import React, { useEffect, useState } from "react"
-import { getTitles } from "@/api/titles"
-import type { TitleItem } from "@/api/titles/types"
-
-interface TitleLibraryModalProps {
-  open: boolean
-  onClose: () => void
-  onSelect: (title: string) => void
-}
-
-const TitleLibraryModal: React.FC<TitleLibraryModalProps> = ({ open, onClose, onSelect }) => {
-  const [titles, setTitles] = useState<TitleItem[]>([])
-  const [loading, setLoading] = useState(false)
-  const [search, setSearch] = useState("")
-
-  useEffect(() => {
-    if (!open) return
-    setLoading(true)
-    getTitles()
-      .then((items) => setTitles(items))
-      .catch(() => setTitles([]))
-      .finally(() => setLoading(false))
-  }, [open])
-
-  const filtered = titles.filter(
-    (t) => !search || t.content.toLowerCase().includes(search.toLowerCase()),
-  )
-
-  if (!open) return null
-
-  return (
-    <div className="aa-modal-overlay" onClick={onClose}>
-      <div className="aa-modal" onClick={(e) => e.stopPropagation()} style={{ maxWidth: 600 }}>
-        <div className="aa-modal__header">
-          <span className="aa-modal__title">从标题库选择</span>
-          <button className="aa-modal__close" onClick={onClose}></button>
-        </div>
-        <div className="aa-modal__body">
-          <div style={{ marginBottom: 12 }}>
-            <input
-              className="aa-input"
-              placeholder="搜索标题..."
-              value={search}
-              onChange={(e) => setSearch(e.target.value)}
-            />
-          </div>
-          {loading ? (
-            <div style={{ textAlign: "center", padding: 40, color: "#8c8ca1" }}>加载中...</div>
-          ) : filtered.length === 0 ? (
-            <div style={{ textAlign: "center", padding: 40, color: "#8c8ca1" }}>
-              暂无标题，请先在标题库创建
-            </div>
-          ) : (
-            <div style={{ maxHeight: 400, overflowY: "auto" }}>
-              {filtered.map((t) => (
-                <div
-                  key={t.id}
-                  style={{
-                    padding: "12px 16px",
-                    marginBottom: 8,
-                    background: "#f8f8fc",
-                    borderRadius: 8,
-                    cursor: "pointer",
-                    transition: "background 0.2s",
-                  }}
-                  onMouseEnter={(e) => (e.currentTarget.style.background = "#eef0ff")}
-                  onMouseLeave={(e) => (e.currentTarget.style.background = "#f8f8fc")}
-                  onClick={() => {
-                    onSelect(t.content)
-                    onClose()
-                  }}
-                >
-                  <div style={{ fontSize: 14, color: "#1a1a2e", marginBottom: 4 }}>{t.content}</div>
-                  <div style={{ fontSize: 12, color: "#8c8ca1" }}>
-                    {t.word_count ?? t.content.length}字 ·{" "}
-                    {t.created_at ? new Date(t.created_at).toLocaleDateString() : ""}
-                  </div>
-                </div>
-              ))}
-            </div>
-          )}
-        </div>
-        <div className="aa-modal__footer">
-          <button className="aa-btn" onClick={onClose}>
-            取消
-          </button>
-        </div>
-      </div>
-    </div>
-  )
-}
-
-export default TitleLibraryModal

apps/web/src/pages/ai-avatar/types.ts

@@ -77,9 +77,6 @@ export interface AiAvatarTitleConfig {
   shadow: boolean
   color: string
   auto_subtitle: boolean
-  /** 自定义位置坐标（position=custom 时生效，像素） */
-  pos_x?: number
-  pos_y?: number
 }
 
 /* ── 封面配置 ── */
@@ -89,8 +86,6 @@ export interface AiAvatarCoverConfig {
   frame_time: number
   upload_url: string | null
   thumbnail_url: string | null
-  /** 智能封面（MediaKit 选帧）返回的 OSS 非临时 URL（#1822） */
-  smart_cover_url: string | null
 }
 
 /* ── 渲染任务 ── */
@@ -108,7 +103,7 @@ export interface RenderJob {
 /* ── 默认值 ── */
 export const DEFAULT_TITLE_CONFIG: AiAvatarTitleConfig = {
   title: "",
-  position: "bottom",
+  position: "top",
   font: "思源黑体",
   size: 28,
   bold: true,
@@ -117,8 +112,6 @@ export const DEFAULT_TITLE_CONFIG: AiAvatarTitleConfig = {
   shadow: false,
   color: "#ffffff",
   auto_subtitle: true,
-  pos_x: undefined,
-  pos_y: undefined,
 }
 
 export const DEFAULT_COVER_CONFIG: AiAvatarCoverConfig = {
@@ -127,5 +120,4 @@ export const DEFAULT_COVER_CONFIG: AiAvatarCoverConfig = {
   frame_time: 0,
   upload_url: null,
   thumbnail_url: null,
-  smart_cover_url: null,
 }

apps/web/src/pages/ai-avatar/utils/contract.ts

@@ -1,76 +0,0 @@
-/**
- * AI数字人 — 前后端接口契约转换工具（#1822）
- *
- * 以 packages/domain/video_filter_builder.py 的 build_title_drawtext_filter() 为唯一口径
- * （契约文档第 5 节的 titles[]/fontSize/frame/start/end 为误写，后端不认，禁止使用）。
- */
-import type { AiAvatarTitleConfig, AiAvatarCoverConfig, VoiceEmotion } from "../types"
-
-/* ── 情绪：中文 → 英文（防御性映射；state 默认已是英文） ── */
-const EMOTION_ZH_TO_EN: Record<string, VoiceEmotion> = {
-  自然: "natural",
-  兴奋: "excited",
-  沉稳: "calm",
-  亲切: "friendly",
-}
-const VALID_EMOTIONS: VoiceEmotion[] = ["natural", "excited", "calm", "friendly"]
-
-/** 归一化为后端英文枚举 natural/excited/calm/friendly；非法/空值回退 natural。 */
-export function normalizeEmotion(raw: string | undefined | null): VoiceEmotion {
-  if (!raw) return "natural"
-  const v = raw.trim()
-  if ((VALID_EMOTIONS as string[]).includes(v)) return v as VoiceEmotion
-  return EMOTION_ZH_TO_EN[v] ?? "natural"
-}
-
-/* ── 标题：前端 state → 后端 build_title_drawtext_filter 字段（单个 title_config dict） ── */
-/**
- * 后端真实字段：text(或content)、font(或font_preset)、font_size(或size)、
- * font_color(或color，可传 #RRGGBB)、position(top/center/bottom/custom)、
- * enabled、bold、stroke{enabled,width,color}、shadow{enabled,color,offset_x,offset_y}、
- * pos_x/pos_y(custom 时)。
- * 口播标题默认 position=bottom（不传后端会默认 top 跑到画面顶部）。
- */
-export function buildTitleConfigPayload(cfg: AiAvatarTitleConfig): Record<string, unknown> {
-  const text = (cfg.title || "").trim()
-  if (!text) return {}
-  const position = cfg.position || "bottom"
-  const payload: Record<string, unknown> = {
-    text,
-    enabled: true,
-    font: cfg.font || "思源黑体",
-    font_size: Math.round(cfg.size) || 36,
-    font_color: cfg.color || "#ffffff",
-    position,
-    bold: !!cfg.bold,
-    stroke: cfg.stroke ? { enabled: true, width: 2, color: "#000000" } : { enabled: false },
-    shadow: cfg.shadow
-      ? { enabled: true, color: "#000000", offset_x: 2, offset_y: 2 }
-      : { enabled: false },
-  }
-  // 自定义坐标（custom 位置）
-  if (position === "custom" && typeof cfg.pos_x === "number" && typeof cfg.pos_y === "number") {
-    payload.pos_x = cfg.pos_x
-    payload.pos_y = cfg.pos_y
-  }
-  return payload
-}
-
-/* ── 封面：前端 state → 后端 render cover_config ── */
-export function buildCoverConfigPayload(
-  cfg: AiAvatarCoverConfig,
-  smartCoverUrl: string | null,
-): Record<string, unknown> {
-  const payload: Record<string, unknown> = {
-    enabled: !!cfg.enabled,
-    mode: cfg.mode,
-    // build_cover_extract_command 读取 timestamp（截帧秒数）
-    timestamp: cfg.frame_time || 0,
-  }
-  if (smartCoverUrl) payload.cover_url = smartCoverUrl
-  // 自定义上传：blob: 本地预览地址无法给后端，仅 OSS URL 可用
-  if (cfg.mode === "upload" && cfg.upload_url && !cfg.upload_url.startsWith("blob:")) {
-    payload.upload_url = cfg.upload_url
-  }
-  return payload
-}

apps/web/src/pages/assets/hooks/asset-operations/batch/index.ts

@@ -0,0 +1,4 @@
+export { useBatchDelete } from "./useBatchDelete"
+export { useBatchTag } from "./useBatchTag"
+export { useBatchClassify } from "./useBatchClassify"
+export { useBatchMark } from "./useBatchMark"

apps/web/src/pages/assets/hooks/asset-operations/batch/useBatchClassify.ts

@@ -0,0 +1,58 @@
+import { useState, useCallback } from "react"
+import { message } from "antd"
+import { batchClassifyAssets, type BatchOperationResult } from "@/api/assets"
+
+interface UseBatchClassifyOptions {
+  selectedIds: Set<string>
+  queryClient: ReturnType<typeof import("@tanstack/react-query").useQueryClient>
+  showResult: (result: BatchOperationResult, title: string, clear?: boolean) => void
+}
+
+export const useBatchClassify = ({
+  selectedIds,
+  queryClient,
+  showResult,
+}: UseBatchClassifyOptions) => {
+  const [classifyModalOpen, setClassifyModalOpen] = useState(false)
+  const [batchCategory, setBatchCategory] = useState("")
+  const [batchLoading, setBatchLoading] = useState(false)
+
+  const handleBatchClassify = useCallback(async () => {
+    if (!batchCategory) {
+      message.warning("请选择分类")
+      return
+    }
+    const ids = Array.from(selectedIds)
+    setBatchLoading(true)
+    try {
+      const result = await batchClassifyAssets({
+        asset_ids: ids,
+        category: batchCategory,
+      })
+      queryClient.invalidateQueries({ queryKey: ["assets"] })
+      showResult(result, "批量改分类")
+      setClassifyModalOpen(false)
+      setBatchCategory("")
+      if (result.failure_count === 0) {
+        message.success(`成功将 ${result.success_count} 个素材改为「${batchCategory}」`)
+      } else {
+        message.warning(
+          `改分类完成：成功 ${result.success_count} 个，失败 ${result.failure_count} 个`,
+        )
+      }
+    } catch {
+      message.error("批量改分类失败，请重试")
+    } finally {
+      setBatchLoading(false)
+    }
+  }, [batchCategory, selectedIds, queryClient, showResult])
+
+  return {
+    classifyModalOpen,
+    setClassifyModalOpen,
+    batchCategory,
+    setBatchCategory,
+    batchLoading,
+    handleBatchClassify,
+  }
+}

apps/web/src/pages/assets/hooks/asset-operations/batch/useBatchDelete.ts

@@ -0,0 +1,40 @@
+import { useState, useCallback } from "react"
+import { message } from "antd"
+import { batchDeleteAssets, type BatchOperationResult } from "@/api/assets"
+
+interface UseBatchDeleteOptions {
+  selectedIds: Set<string>
+  invalidateAssets: () => void
+  showResult: (result: BatchOperationResult, title: string, clear?: boolean) => void
+}
+
+export const useBatchDelete = ({
+  selectedIds,
+  invalidateAssets,
+  showResult,
+}: UseBatchDeleteOptions) => {
+  const [batchLoading, setBatchLoading] = useState(false)
+
+  const handleBatchDelete = useCallback(async () => {
+    const ids = Array.from(selectedIds)
+    setBatchLoading(true)
+    try {
+      const result = await batchDeleteAssets(ids)
+      invalidateAssets()
+      showResult(result, "批量删除")
+      if (result.failure_count === 0) {
+        message.success(`成功删除 ${result.success_count} 个素材`)
+      } else {
+        message.warning(
+          `删除完成：成功 ${result.success_count} 个，失败 ${result.failure_count} 个`,
+        )
+      }
+    } catch {
+      message.error("批量删除失败，请重试")
+    } finally {
+      setBatchLoading(false)
+    }
+  }, [selectedIds, invalidateAssets, showResult])
+
+  return { batchLoading, handleBatchDelete }
+}

apps/web/src/pages/assets/hooks/asset-operations/batch/useBatchMark.ts

@@ -0,0 +1,53 @@
+import { useState, useCallback } from "react"
+import { message } from "antd"
+import { batchMarkAssets, type BatchOperationResult } from "@/api/assets"
+import type { SmartViewType } from "../../../components/BatchMarkModal"
+import { SMART_VIEW_LABELS } from "../constants"
+
+interface UseBatchMarkOptions {
+  selectedIds: Set<string>
+  queryClient: ReturnType<typeof import("@tanstack/react-query").useQueryClient>
+  showResult: (result: BatchOperationResult, title: string, clear?: boolean) => void
+}
+
+export const useBatchMark = ({ selectedIds, queryClient, showResult }: UseBatchMarkOptions) => {
+  const [markModalOpen, setMarkModalOpen] = useState(false)
+  const [batchSmartView, setBatchSmartView] = useState<SmartViewType>("recommended")
+  const [batchLoading, setBatchLoading] = useState(false)
+
+  const handleBatchMark = useCallback(async () => {
+    const ids = Array.from(selectedIds)
+    setBatchLoading(true)
+    try {
+      const result = await batchMarkAssets({
+        asset_ids: ids,
+        smart_view: batchSmartView,
+      })
+      queryClient.invalidateQueries({ queryKey: ["assets"] })
+      showResult(result, "批量智能标记")
+      setMarkModalOpen(false)
+      if (result.failure_count === 0) {
+        message.success(
+          `成功将 ${result.success_count} 个素材标记为「${SMART_VIEW_LABELS[batchSmartView]}」`,
+        )
+      } else {
+        message.warning(
+          `智能标记完成：成功 ${result.success_count} 个，失败 ${result.failure_count} 个`,
+        )
+      }
+    } catch {
+      message.error("批量智能标记失败，请重试")
+    } finally {
+      setBatchLoading(false)
+    }
+  }, [batchSmartView, selectedIds, queryClient, showResult])
+
+  return {
+    markModalOpen,
+    setMarkModalOpen,
+    batchSmartView,
+    setBatchSmartView,
+    batchLoading,
+    handleBatchMark,
+  }
+}

apps/web/src/pages/assets/hooks/asset-operations/batch/useBatchTag.ts

@@ -0,0 +1,86 @@
+import { useState, useCallback } from "react"
+import { message } from "antd"
+import { batchTagAssets, type BatchOperationResult } from "@/api/assets"
+
+interface UseBatchTagOptions {
+  selectedIds: Set<string>
+  queryClient: ReturnType<typeof import("@tanstack/react-query").useQueryClient>
+  showResult: (result: BatchOperationResult, title: string, clear?: boolean) => void
+}
+
+export const useBatchTag = ({ selectedIds, queryClient, showResult }: UseBatchTagOptions) => {
+  const [tagModalOpen, setTagModalOpen] = useState(false)
+  const [batchTagInput, setBatchTagInput] = useState("")
+  const [batchTags, setBatchTags] = useState<string[]>([])
+  const [tagMode, setTagMode] = useState<"add" | "replace">("add")
+  const [batchLoading, setBatchLoading] = useState(false)
+
+  const handleBatchTag = useCallback(async () => {
+    if (batchTags.length === 0) {
+      message.warning("请至少输入一个标签")
+      return
+    }
+    const ids = Array.from(selectedIds)
+    setBatchLoading(true)
+    try {
+      const result = await batchTagAssets({
+        asset_ids: ids,
+        tags: batchTags,
+        mode: tagMode,
+      })
+      queryClient.invalidateQueries({ queryKey: ["assets"] })
+      showResult(result, "批量打标签")
+      setTagModalOpen(false)
+      setBatchTags([])
+      setBatchTagInput("")
+      setTagMode("add")
+      if (result.failure_count === 0) {
+        message.success(`成功为 ${result.success_count} 个素材打标签`)
+      } else {
+        message.warning(
+          `打标签完成：成功 ${result.success_count} 个，失败 ${result.failure_count} 个`,
+        )
+      }
+    } catch {
+      message.error("批量打标签失败，请重试")
+    } finally {
+      setBatchLoading(false)
+    }
+  }, [batchTags, selectedIds, tagMode, queryClient, showResult])
+
+  const handleTagInputKeyDown = useCallback(
+    (e: React.KeyboardEvent) => {
+      if (e.key === "Enter" && batchTagInput.trim()) {
+        e.preventDefault()
+        const tag = batchTagInput.trim()
+        if (!batchTags.includes(tag)) {
+          setBatchTags([...batchTags, tag])
+        }
+        setBatchTagInput("")
+      }
+    },
+    [batchTagInput, batchTags],
+  )
+
+  const removeBatchTag = useCallback(
+    (tag: string) => {
+      setBatchTags(batchTags.filter((t) => t !== tag))
+    },
+    [batchTags],
+  )
+
+  return {
+    tagModalOpen,
+    setTagModalOpen,
+    batchTagInput,
+    setBatchTagInput,
+    batchTags,
+    setBatchTags,
+    tagMode,
+    setTagMode,
+    batchLoading,
+    handleBatchTag,
+    handleTagInputKeyDown,
+    removeBatchTag,
+  }
+}

apps/web/src/pages/assets/hooks/asset-operations/batchOperations.ts

@@ -0,0 +1,8 @@
+/**
+ * @deprecated 请从 ./batch/ 目录导入子模块
+ * 保持向后兼容，re-export 所有批量操作 Hook
+ */
+export { useBatchDelete } from "./batch/useBatchDelete"
+export { useBatchTag } from "./batch/useBatchTag"
+export { useBatchClassify } from "./batch/useBatchClassify"
+export { useBatchMark } from "./batch/useBatchMark"

apps/web/src/pages/editing-planner/components/pip-config/LayerConfig.tsx

@@ -0,0 +1,5 @@
+/**
+ * LayerConfig 入口（向后兼容）
+ * 实际实现位于 ./layer-config/ 目录
+ */
+export { default } from "./layer-config"

apps/web/src/pages/editing-planner/components/pip-config/LayerList.tsx

@@ -0,0 +1,65 @@
+/**
+ * 混剪图层列表
+ */
+import React from "react"
+import type { PipLayer } from "@/pages/editing-planner/types"
+import { LAYER_COLORS } from "@/pages/editing-planner/constants/pipConfig"
+
+interface LayerListProps {
+  layers: PipLayer[]
+  selectedId: string
+  onSelect: (id: string) => void
+  onAdd: () => void
+  onDelete: (id: string) => void
+}
+
+const LayerList: React.FC<LayerListProps> = ({ layers, selectedId, onSelect, onAdd, onDelete }) => {
+  return (
+    <div className="pip-layer-list">
+      <div className="pip-toolbar" style={{ marginBottom: 8 }}>
+        <button className="pip-add-btn" onClick={onAdd}>
+          + 添加图层
+        </button>
+      </div>
+      {layers.length === 0 ? (
+        <div className="pip-layer-empty">暂无图层，点击上方添加</div>
+      ) : (
+        layers.map((layer, idx) => (
+          <div
+            key={layer.id}
+            className={`pip-layer-item${selectedId === layer.id ? " active" : ""}`}
+            onClick={() => onSelect(layer.id)}
+          >
+            {layer.thumbnail_url || layer.material_url ? (
+              <img
+                className="pip-layer-thumb"
+                src={layer.thumbnail_url || layer.material_url}
+                alt={layer.name}
+              />
+            ) : (
+              <div
+                className="pip-layer-thumb"
+                style={{
+                  background: LAYER_COLORS[idx % LAYER_COLORS.length],
+                }}
+              />
+            )}
+            <span className="pip-layer-name">{layer.name}</span>
+            <button
+              className="pip-layer-delete"
+              onClick={(e) => {
+                e.stopPropagation()
+                onDelete(layer.id)
+              }}
+              title="删除图层"
+            >
+              ✕
+            </button>
+          </div>
+        ))
+      )}
+    </div>
+  )
+}
+
+export default LayerList

apps/web/src/pages/editing-planner/components/pip-config/layer-config/LayerPositionSize.tsx

@@ -0,0 +1,172 @@
+import React from "react"
+import type { PipLayer, PipGridPosition } from "@/pages/editing-planner/types"
+import { GRID_POSITIONS } from "@/pages/editing-planner/constants/pipConfig"
+
+interface LayerPositionSizeProps {
+  layer: PipLayer
+  onUpdate: (id: string, partial: Partial<PipLayer>) => void
+  onGridClick: (pos: PipGridPosition) => void
+  onWidthChange: (val: number) => void
+  onHeightChange: (val: number) => void
+}
+
+/**
+ * 图层位置与尺寸配置面板
+ */
+export const LayerPositionSize: React.FC<LayerPositionSizeProps> = ({
+  layer,
+  onUpdate,
+  onGridClick,
+  onWidthChange,
+  onHeightChange,
+}) => (
+  <>
+    {/* 素材类型 */}
+    <div className="pip-field">
+      <label className="pip-field-label">素材类型</label>
+      <div className="pip-type-btns">
+        <button
+          className={`pip-type-btn${layer.material_type === "image" ? " active" : ""}`}
+          onClick={() => onUpdate(layer.id, { material_type: "image" })}
+        >
+          🖼️ 图片
+        </button>
+        <button
+          className={`pip-type-btn${layer.material_type === "video" ? " active" : ""}`}
+          onClick={() => onUpdate(layer.id, { material_type: "video" })}
+        >
+          🎬 视频
+        </button>
+      </div>
+    </div>
+
+    {/* 素材 URL */}
+    <div className="pip-field">
+      <label className="pip-field-label">
+        {layer.material_type === "image" ? "图片" : "视频"} URL
+      </label>
+      <input
+        className="pip-input"
+        type="text"
+        placeholder={
+          layer.material_type === "image"
+            ? "https://example.com/image.png"
+            : "https://example.com/video.mp4"
+        }
+        value={layer.material_url}
+        onChange={(e) => onUpdate(layer.id, { material_url: e.target.value })}
+      />
+    </div>
+
+    {/* 位置：九宫格 + 坐标 */}
+    <div className="pip-field">
+      <label className="pip-field-label">位置</label>
+      <div style={{ display: "flex", gap: 16, alignItems: "flex-start" }}>
+        <div className="pip-grid">
+          {GRID_POSITIONS.map((pos) => (
+            <button
+              key={pos}
+              className={`pip-grid-btn${layer.grid_position === pos ? " active" : ""}`}
+              onClick={() => onGridClick(pos)}
+            >
+              <span className="pip-grid-dot" />
+            </button>
+          ))}
+        </div>
+        <div className="pip-field-row" style={{ flex: 1 }}>
+          <div>
+            <label className="pip-field-label">X (%)</label>
+            <input
+              className="pip-number"
+              type="number"
+              min={0}
+              max={100}
+              value={layer.x}
+              onChange={(e) => onUpdate(layer.id, { x: Number(e.target.value) })}
+            />
+          </div>
+          <div>
+            <label className="pip-field-label">Y (%)</label>
+            <input
+              className="pip-number"
+              type="number"
+              min={0}
+              max={100}
+              value={layer.y}
+              onChange={(e) => onUpdate(layer.id, { y: Number(e.target.value) })}
+            />
+          </div>
+        </div>
+      </div>
+    </div>
+
+    {/* 尺寸 */}
+    <div className="pip-field">
+      <label className="pip-field-label">尺寸</label>
+      <div className="pip-slider-row">
+        <span style={{ fontSize: 12, color: "#999", width: 20 }}>宽</span>
+        <input
+          className="pip-slider"
+          type="range"
+          min={10}
+          max={80}
+          value={layer.width}
+          onChange={(e) => onWidthChange(Number(e.target.value))}
+        />
+        <span className="pip-slider-value">{layer.width}%</span>
+      </div>
+      <div className="pip-slider-row" style={{ marginTop: 6 }}>
+        <span style={{ fontSize: 12, color: "#999", width: 20 }}>高</span>
+        <input
+          className="pip-slider"
+          type="range"
+          min={10}
+          max={80}
+          value={layer.height}
+          onChange={(e) => onHeightChange(Number(e.target.value))}
+        />
+        <span className="pip-slider-value">{layer.height}%</span>
+      </div>
+      <div
+        className="pip-lock-row"
+        style={{ marginTop: 6 }}
+        onClick={() => onUpdate(layer.id, { aspect_lock: !layer.aspect_lock })}
+      >
+        <span className="pip-lock-icon">{layer.aspect_lock ? "🔒" : "🔓"}</span>
+        <span>{layer.aspect_lock ? "已锁定比例" : "锁定宽高比"}</span>
+      </div>
+    </div>
+
+    {/* 圆角 */}
+    <div className="pip-field">
+      <label className="pip-field-label">圆角</label>
+      <div className="pip-slider-row">
+        <input
+          className="pip-slider"
+          type="range"
+          min={0}
+          max={50}
+          value={layer.border_radius}
+          onChange={(e) => onUpdate(layer.id, { border_radius: Number(e.target.value) })}
+        />
+        <span className="pip-slider-value">{layer.border_radius}%</span>
+      </div>
+    </div>
+
+    {/* 透明度 */}
+    <div className="pip-field">
+      <label className="pip-field-label">透明度</label>
+      <div className="pip-slider-row">
+        <input
+          className="pip-slider"
+          type="range"
+          min={0}
+          max={100}
+          value={layer.opacity}
+          onChange={(e) => onUpdate(layer.id, { opacity: Number(e.target.value) })}
+        />
+        <span className="pip-slider-value">{layer.opacity}%</span>
+      </div>
+    </div>
+  </>
+)

apps/web/src/pages/editing-planner/components/pip-config/layer-config/LayerTimingAnimation.tsx

@@ -0,0 +1,87 @@
+import React from "react"
+import type { PipLayer, PipAnimType, PipSlideDirection } from "@/pages/editing-planner/types"
+import { ANIM_OPTIONS, SLIDE_DIR_OPTIONS } from "@/pages/editing-planner/constants/pipConfig"
+
+interface LayerTimingAnimationProps {
+  layer: PipLayer
+  totalDuration: number
+  onUpdate: (id: string, partial: Partial<PipLayer>) => void
+}
+
+/**
+ * 图层时间与动画配置面板
+ */
+export const LayerTimingAnimation: React.FC<LayerTimingAnimationProps> = ({
+  layer,
+  totalDuration,
+  onUpdate,
+}) => (
+  <>
+    {/* 时间 */}
+    <div className="pip-field">
+      <label className="pip-field-label">时间</label>
+      <div className="pip-field-row">
+        <div>
+          <label className="pip-field-label">开始 (s)</label>
+          <input
+            className="pip-number"
+            type="number"
+            min={0}
+            max={totalDuration || 999}
+            step={0.1}
+            value={layer.start_time}
+            onChange={(e) => onUpdate(layer.id, { start_time: Number(e.target.value) })}
+          />
+        </div>
+        <div>
+          <label className="pip-field-label">持续 (s)</label>
+          <input
+            className="pip-number"
+            type="number"
+            min={0.1}
+            max={totalDuration || 999}
+            step={0.1}
+            value={layer.duration}
+            onChange={(e) => onUpdate(layer.id, { duration: Number(e.target.value) })}
+          />
+        </div>
+      </div>
+    </div>
+
+    {/* 入场动画 */}
+    <div className="pip-field">
+      <label className="pip-field-label">入场动画</label>
+      <select
+        className="pip-select"
+        value={layer.animation}
+        onChange={(e) => onUpdate(layer.id, { animation: e.target.value as PipAnimType })}
+      >
+        {ANIM_OPTIONS.map((opt) => (
+          <option key={opt.value} value={opt.value}>
+            {opt.label}
+          </option>
+        ))}
+      </select>
+    </div>
+
+    {/* 滑入方向（仅 slide_in 时显示） */}
+    {layer.animation === "slide_in" && (
+      <div className="pip-field">
+        <label className="pip-field-label">滑入方向</label>
+        <select
+          className="pip-select"
+          value={layer.slide_direction}
+          onChange={(e) =>
+            onUpdate(layer.id, { slide_direction: e.target.value as PipSlideDirection })
+          }
+        >
+          {SLIDE_DIR_OPTIONS.map((opt) => (
+            <option key={opt.value} value={opt.value}>
+              {opt.label}
+            </option>
+          ))}
+        </select>
+      </div>
+    )}
+  </>
+)

apps/web/src/pages/editing-planner/components/pip-config/layer-config/PipPreview.tsx

@@ -0,0 +1,33 @@
+import React from "react"
+import type { PipLayer } from "@/pages/editing-planner/types"
+import { LAYER_COLORS } from "@/pages/editing-planner/constants/pipConfig"
+
+interface PipPreviewProps {
+  layers: PipLayer[]
+  selectedId: string
+}
+
+/**
+ * PIP 图层迷你预览组件
+ */
+export const PipPreview: React.FC<PipPreviewProps> = ({ layers, selectedId }) => (
+  <div className="pip-preview-box">
+    {layers.map((l, idx) => (
+      <div
+        key={l.id}
+        className={`pip-preview-layer${selectedId === l.id ? " selected" : ""}`}
+        style={{
+          left: `${l.x}%`,
+          top: `${l.y}%`,
+          width: `${l.width}%`,
+          height: `${l.height}%`,
+          background: LAYER_COLORS[idx % LAYER_COLORS.length],
+          opacity: l.opacity / 100,
+          borderRadius: `${l.border_radius}%`,
+        }}
+      >
+        <span className="pip-preview-label">{l.name}</span>
+      </div>
+    ))}
+  </div>
+)

apps/web/src/pages/editing-planner/components/pip-config/layer-config/index.tsx

@@ -0,0 +1,57 @@
+/**
+ * 混剪单图层配置区
+ */
+import React from "react"
+import type { PipLayer, PipGridPosition } from "@/pages/editing-planner/types"
+import { PipPreview } from "./PipPreview"
+import { LayerPositionSize } from "./LayerPositionSize"
+import { LayerTimingAnimation } from "./LayerTimingAnimation"
+
+interface LayerConfigProps {
+  layer: PipLayer | null
+  layers: PipLayer[]
+  totalDuration: number
+  onUpdate: (id: string, partial: Partial<PipLayer>) => void
+  onGridClick: (pos: PipGridPosition) => void
+  onWidthChange: (val: number) => void
+  onHeightChange: (val: number) => void
+}
+
+const LayerConfig: React.FC<LayerConfigProps> = ({
+  layer,
+  layers,
+  totalDuration,
+  onUpdate,
+  onGridClick,
+  onWidthChange,
+  onHeightChange,
+}) => {
+  if (!layer) {
+    return (
+      <div className="pip-config-area">
+        <div className="pip-config-empty">选择或添加图层以配置</div>
+      </div>
+    )
+  }
+
+  return (
+    <div className="pip-config-area">
+      {/* 迷你预览 */}
+      <PipPreview layers={layers} selectedId={layer.id} />
+
+      {/* 位置与尺寸 */}
+      <LayerPositionSize
+        layer={layer}
+        onUpdate={onUpdate}
+        onGridClick={onGridClick}
+        onWidthChange={onWidthChange}
+        onHeightChange={onHeightChange}
+      />
+
+      {/* 时间与动画 */}
+      <LayerTimingAnimation layer={layer} totalDuration={totalDuration} onUpdate={onUpdate} />
+    </div>
+  )
+}
+
+export default LayerConfig

apps/web/src/pages/editing-planner/components/sticker/StickerLibrary.tsx

@@ -0,0 +1,142 @@
+/**
+ * 贴纸素材库（emoji / 图片 / 文字花字）
+ */
+import React, { useState } from "react"
+import type { StickerType, TextStickerPreset } from "@/pages/editing-planner/types"
+import {
+  EMOJI_LIST,
+  STICKER_TYPE_TABS,
+  TEXT_PRESET_STYLES,
+  TEXT_STICKER_PRESET_LABELS,
+} from "@/pages/editing-planner/constants/sticker"
+
+interface StickerLibraryProps {
+  activeTab: StickerType
+  onTabChange: (tab: StickerType) => void
+  onAddSticker: (type: StickerType, content: string) => void
+}
+
+const StickerLibrary: React.FC<StickerLibraryProps> = ({
+  activeTab,
+  onTabChange,
+  onAddSticker,
+}) => {
+  const [textInput, setTextInput] = useState("")
+  const imageInputRef = React.useRef<HTMLInputElement>(null)
+
+  const handleAddImage = () => {
+    const val = imageInputRef.current?.value.trim()
+    if (val) {
+      onAddSticker("image", val)
+      if (imageInputRef.current) imageInputRef.current.value = ""
+    }
+  }
+
+  const handleAddText = () => {
+    if (textInput.trim()) {
+      onAddSticker("text", textInput.trim())
+      setTextInput("")
+    }
+  }
+
+  return (
+    <>
+      {/* 类型 Tab */}
+      <div className="sticker-tabs">
+        {STICKER_TYPE_TABS.map((t) => (
+          <button
+            key={t.value}
+            className={`sticker-tab${activeTab === t.value ? " active" : ""}`}
+            onClick={() => onTabChange(t.value)}
+          >
+            {t.label}
+          </button>
+        ))}
+      </div>
+
+      {/* Tab 内容区 */}
+      <div className="sticker-tab-content">
+        {/* Emoji 素材库 */}
+        {activeTab === "emoji" && (
+          <div className="sticker-emoji-grid">
+            {EMOJI_LIST.map((emoji) => (
+              <button
+                key={emoji}
+                className="sticker-emoji-btn"
+                onClick={() => onAddSticker("emoji", emoji)}
+              >
+                {emoji}
+              </button>
+            ))}
+          </div>
+        )}
+
+        {/* 图片贴纸 */}
+        {activeTab === "image" && (
+          <div className="sticker-image-input">
+            <input
+              ref={imageInputRef}
+              type="text"
+              className="sticker-url-input"
+              placeholder="输入图片 URL 添加贴纸..."
+              onKeyDown={(e) => {
+                if (e.key === "Enter" && e.currentTarget.value.trim()) {
+                  handleAddImage()
+                }
+              }}
+            />
+            <button className="sticker-url-add-btn" onClick={handleAddImage}>
+              添加
+            </button>
+          </div>
+        )}
+
+        {/* 文字花字 */}
+        {activeTab === "text" && (
+          <div className="sticker-text-section">
+            <div className="sticker-text-input-row">
+              <input
+                type="text"
+                className="sticker-text-input"
+                placeholder="输入文字内容..."
+                value={textInput}
+                onChange={(e) => setTextInput(e.target.value)}
+              />
+              <button
+                className="sticker-text-add-btn"
+                disabled={!textInput.trim()}
+                onClick={handleAddText}
+              >
+                添加
+              </button>
+            </div>
+            <div className="sticker-text-presets">
+              <div className="sticker-preset-title">花字预设预览</div>
+              <div className="sticker-preset-grid">
+                {(Object.keys(TEXT_STICKER_PRESET_LABELS) as TextStickerPreset[]).map((p) => (
+                  <div
+                    key={p}
+                    className="sticker-preset-preview"
+                    style={{
+                      background:
+                        p === "bubble"
+                          ? "rgba(0,0,0,0.5)"
+                          : p === "gradient"
+                            ? "linear-gradient(90deg,#f093fb,#f5576c)"
+                            : "#1a1a2e",
+                    }}
+                  >
+                    <span style={TEXT_PRESET_STYLES[p]}>示例</span>
+                    <div className="sticker-preset-name">{TEXT_STICKER_PRESET_LABELS[p]}</div>
+                  </div>
+                ))}
+              </div>
+            </div>
+          </div>
+        )}
+      </div>
+    </>
+  )
+}
+
+export default StickerLibrary

apps/web/src/pages/editing-planner/components/sticker/StickerList.tsx

@@ -0,0 +1,54 @@
+/**
+ * 已添加贴纸列表
+ */
+import React from "react"
+import type { StickerItem } from "@/pages/editing-planner/types"
+
+interface StickerListProps {
+  items: StickerItem[]
+  selectedId: string | null
+  onSelect: (id: string) => void
+  onDelete: (id: string) => void
+}
+
+const StickerList: React.FC<StickerListProps> = ({ items, selectedId, onSelect, onDelete }) => {
+  if (items.length === 0) return null
+
+  const getDisplayContent = (item: StickerItem) => {
+    if (item.type === "emoji") return { icon: item.content, name: "表情贴纸" }
+    if (item.type === "text") return { icon: "T", name: item.content.slice(0, 10) }
+    return { icon: "🖼", name: "图片贴纸" }
+  }
+
+  return (
+    <div className="sticker-list-section">
+      <div className="sticker-section-title">已添加贴纸 ({items.length})</div>
+      <div className="sticker-list">
+        {items.map((item) => {
+          const { icon, name } = getDisplayContent(item)
+          return (
+            <div
+              key={item.id}
+              className={`sticker-list-item${selectedId === item.id ? " active" : ""}`}
+              onClick={() => onSelect(item.id)}
+            >
+              <span className="sticker-list-icon">{icon}</span>
+              <span className="sticker-list-name">{name}</span>
+              <button
+                className="sticker-list-delete"
+                onClick={(e) => {
+                  e.stopPropagation()
+                  onDelete(item.id)
+                }}
+              >
+                ✕
+              </button>
+            </div>
+          )
+        })}
+      </div>
+    </div>
+  )
+}
+
+export default StickerList

apps/web/src/pages/editing-planner/components/sticker/StickerPreview.tsx

@@ -0,0 +1,39 @@
+import React from "react"
+import type { StickerItem } from "@/pages/editing-planner/types"
+import { TEXT_PRESET_STYLES } from "@/pages/editing-planner/constants/sticker"
+
+interface StickerPreviewProps {
+  sticker: StickerItem
+}
+
+export const StickerPreview: React.FC<StickerPreviewProps> = ({ sticker }) => (
+  <div className="sticker-preview-box">
+    <div
+      className="sticker-preview-item"
+      style={{
+        left: `${sticker.x}%`,
+        top: `${sticker.y}%`,
+        width: `${sticker.width}%`,
+        height: `${sticker.height}%`,
+        transform: `translate(-50%, -50%) rotate(${sticker.rotation}deg)`,
+        opacity: sticker.opacity / 100,
+        fontSize: sticker.type === "text" ? `${sticker.font_size}px` : undefined,
+        ...TEXT_PRESET_STYLES[sticker.text_preset],
+      }}
+    >
+      {sticker.type === "emoji" && sticker.content}
+      {sticker.type === "text" && sticker.content}
+      {sticker.type === "image" && (
+        <img
+          src={sticker.content}
+          alt="sticker"
+          style={{
+            width: "100%",
+            height: "100%",
+            objectFit: "contain",
+          }}
+        />
+      )}
+    </div>
+  </div>
+)

apps/web/src/pages/editing-planner/components/sticker/StickerPropsEditor.tsx

@@ -0,0 +1,130 @@
+/**
+ * 选中贴纸的属性编辑器
+ */
+import React from "react"
+import type { StickerItem } from "@/pages/editing-planner/types"
+import { StickerPreview } from "./StickerPreview"
+import { TextStickerPropsEditor } from "./TextStickerPropsEditor"
+
+interface StickerPropsEditorProps {
+  sticker: StickerItem
+  totalDuration: number
+  onUpdate: (id: string, partial: Partial<StickerItem>) => void
+}
+
+const StickerPropsEditor: React.FC<StickerPropsEditorProps> = ({
+  sticker,
+  totalDuration,
+  onUpdate,
+}) => {
+  return (
+    <div className="sticker-props-section">
+      <div className="sticker-section-title">属性调整</div>
+
+      {/* 位置 */}
+      <div className="sticker-prop-row">
+        <span className="sticker-prop-label">位置 X</span>
+        <input
+          type="range"
+          className="sticker-prop-slider"
+          min={0}
+          max={100}
+          value={sticker.x}
+          onChange={(e) => onUpdate(sticker.id, { x: Number(e.target.value) })}
+        />
+        <span className="sticker-prop-value">{sticker.x}%</span>
+      </div>
+      <div className="sticker-prop-row">
+        <span className="sticker-prop-label">位置 Y</span>
+        <input
+          type="range"
+          className="sticker-prop-slider"
+          min={0}
+          max={100}
+          value={sticker.y}
+          onChange={(e) => onUpdate(sticker.id, { y: Number(e.target.value) })}
+        />
+        <span className="sticker-prop-value">{sticker.y}%</span>
+      </div>
+
+      {/* 尺寸 */}
+      <div className="sticker-prop-row">
+        <span className="sticker-prop-label">大小</span>
+        <input
+          type="range"
+          className="sticker-prop-slider"
+          min={5}
+          max={50}
+          value={sticker.width}
+          onChange={(e) =>
+            onUpdate(sticker.id, {
+              width: Number(e.target.value),
+              height: Number(e.target.value),
+            })
+          }
+        />
+        <span className="sticker-prop-value">{sticker.width}%</span>
+      </div>
+
+      {/* 旋转 */}
+      <div className="sticker-prop-row">
+        <span className="sticker-prop-label">旋转</span>
+        <input
+          type="range"
+          className="sticker-prop-slider"
+          min={-180}
+          max={180}
+          value={sticker.rotation}
+          onChange={(e) => onUpdate(sticker.id, { rotation: Number(e.target.value) })}
+        />
+        <span className="sticker-prop-value">{sticker.rotation}°</span>
+      </div>
+
+      {/* 透明度 */}
+      <div className="sticker-prop-row">
+        <span className="sticker-prop-label">透明度</span>
+        <input
+          type="range"
+          className="sticker-prop-slider"
+          min={0}
+          max={100}
+          value={sticker.opacity}
+          onChange={(e) => onUpdate(sticker.id, { opacity: Number(e.target.value) })}
+        />
+        <span className="sticker-prop-value">{sticker.opacity}%</span>
+      </div>
+
+      {/* 时间 */}
+      <div className="sticker-prop-row">
+        <span className="sticker-prop-label">开始</span>
+        <input
+          type="number"
+          className="sticker-prop-number"
+          min={0}
+          max={totalDuration}
+          step={0.1}
+          value={sticker.start_time}
+          onChange={(e) => onUpdate(sticker.id, { start_time: Number(e.target.value) })}
+        />
+        <span className="sticker-prop-label">时长</span>
+        <input
+          type="number"
+          className="sticker-prop-number"
+          min={0}
+          max={totalDuration}
+          step={0.1}
+          value={sticker.duration}
+          onChange={(e) => onUpdate(sticker.id, { duration: Number(e.target.value) })}
+        />
+      </div>
+
+      {/* 文字贴纸特有属性 */}
+      <TextStickerPropsEditor sticker={sticker} onUpdate={onUpdate} />
+
+      {/* 预览 */}
+      <StickerPreview sticker={sticker} />
+    </div>
+  )
+}
+
+export default StickerPropsEditor

apps/web/src/pages/editing-planner/components/sticker/TextStickerPropsEditor.tsx

@@ -0,0 +1,57 @@
+import React from "react"
+import type { StickerItem, TextStickerPreset } from "@/pages/editing-planner/types"
+import { TEXT_STICKER_PRESET_LABELS } from "@/pages/editing-planner/constants/sticker"
+
+interface TextStickerPropsEditorProps {
+  sticker: StickerItem
+  onUpdate: (id: string, partial: Partial<StickerItem>) => void
+}
+
+export const TextStickerPropsEditor: React.FC<TextStickerPropsEditorProps> = ({
+  sticker,
+  onUpdate,
+}) => {
+  if (sticker.type !== "text") return null
+
+  return (
+    <>
+      <div className="sticker-prop-row">
+        <span className="sticker-prop-label">花字</span>
+        <select
+          className="sticker-prop-select"
+          value={sticker.text_preset}
+          onChange={(e) =>
+            onUpdate(sticker.id, { text_preset: e.target.value as TextStickerPreset })
+          }
+        >
+          {(Object.keys(TEXT_STICKER_PRESET_LABELS) as TextStickerPreset[]).map((p) => (
+            <option key={p} value={p}>
+              {TEXT_STICKER_PRESET_LABELS[p]}
+            </option>
+          ))}
+        </select>
+      </div>
+      <div className="sticker-prop-row">
+        <span className="sticker-prop-label">字号</span>
+        <input
+          type="range"
+          className="sticker-prop-slider"
+          min={12}
+          max={72}
+          value={sticker.font_size}
+          onChange={(e) => onUpdate(sticker.id, { font_size: Number(e.target.value) })}
+        />
+        <span className="sticker-prop-value">{sticker.font_size}px</span>
+      </div>
+      <div className="sticker-prop-row">
+        <span className="sticker-prop-label">颜色</span>
+        <input
+          type="color"
+          className="sticker-prop-color"
+          value={sticker.text_color}
+          onChange={(e) => onUpdate(sticker.id, { text_color: e.target.value })}
+        />
+      </div>
+    </>
+  )
+}

apps/web/src/pages/editing-planner/components/tts/TtsSlider.tsx

@@ -0,0 +1,62 @@
+/**
+ * TTS 滑块组件（语速/语调/音量）
+ */
+import React from "react"
+import { Slider } from "antd"
+
+interface TtsSliderProps {
+  label: string
+  value: number
+  min: number
+  max: number
+  step: number
+  unit?: string
+  onChange: (val: number) => void
+  marks?: string[]
+  tooltipFormatter?: (v: number) => string
+}
+
+const TtsSlider: React.FC<TtsSliderProps> = ({
+  label,
+  value,
+  min,
+  max,
+  step,
+  unit = "",
+  onChange,
+  marks,
+  tooltipFormatter,
+}) => {
+  const displayValue =
+    unit === "x"
+      ? `${value.toFixed(2)}x`
+      : label === "语调"
+        ? `${value > 0 ? "+" : ""}${value} 半音`
+        : `${value}${unit}`
+
+  return (
+    <div className="tts-slider-section">
+      <div className="tts-slider-header">
+        <span className="tts-slider-label">{label}</span>
+        <span className="tts-slider-value">{displayValue}</span>
+      </div>
+      <Slider
+        min={min}
+        max={max}
+        step={step}
+        value={value}
+        onChange={(v) => onChange(v as number)}
+        tooltip={tooltipFormatter ? { formatter: (v) => tooltipFormatter(v as number) } : undefined}
+      />
+      {marks && (
+        <div className="tts-slider-marks">
+          {marks.map((m, i) => (
+            <span key={i}>{m}</span>
+          ))}
+        </div>
+      )}
+    </div>
+  )
+}
+
+export default TtsSlider

apps/web/src/pages/editing-planner/components/tts/VoiceSelector.tsx

@@ -0,0 +1,50 @@
+/**
+ * TTS 音色选择组件
+ */
+import React from "react"
+import type { TTSVoice } from "@/api/tts"
+import { VOICE_CATEGORY_MAP } from "../../constants/tts"
+
+interface VoiceSelectorProps {
+  voices: TTSVoice[]
+  voicesLoading: boolean
+  selectedVoiceId: string
+  onVoiceSelect: (voiceId: string) => void
+}
+
+const VoiceSelector: React.FC<VoiceSelectorProps> = ({
+  voices,
+  voicesLoading,
+  selectedVoiceId,
+  onVoiceSelect,
+}) => {
+  const voiceCategories = Object.entries(VOICE_CATEGORY_MAP)
+
+  return (
+    <div className="tts-voice-section">
+      <div className="tts-voice-label">
+        选择音色
+        {voicesLoading && <span className="tts-voice-loading">加载中...</span>}
+      </div>
+      <div className="tts-voice-grid">
+        {voiceCategories.map(([cat, info]) => {
+          const voice = voices.find((v) => v.category === cat)
+          const isSelected = voice && selectedVoiceId === voice.id
+          return (
+            <button
+              key={cat}
+              className={`tts-voice-card${isSelected ? " active" : ""}`}
+              onClick={() => voice && onVoiceSelect(voice.id)}
+              disabled={!voice || voicesLoading}
+            >
+              <span className="tts-voice-card-icon">{info.icon}</span>
+              <span className="tts-voice-card-name">{voice?.name || info.label}</span>
+            </button>
+          )
+        })}
+      </div>
+    </div>
+  )
+}
+
+export default VoiceSelector

apps/web/src/pages/generate/GeneratePage.tsx

@@ -548,21 +548,10 @@ const GeneratePage: React.FC = () => {
             <div
               style={{
                 display: "flex",
-                flexDirection: "column",
-                alignItems: "center",
+                justifyContent: "center",
                 marginTop: 16,
               }}
             >
-              <h2
-                style={{
-                  textAlign: "center",
-                  marginBottom: 12,
-                  fontSize: "1.5rem",
-                  fontWeight: 600,
-                }}
-              >
-                🎬 确认生成
-              </h2>
               <div
                 style={{
                   display: "flex",

apps/web/src/test/pages/assets/smoke.test.tsx

@@ -36,10 +36,10 @@ import "@/pages/assets/hooks/useLibraryManagement"
 import "@/pages/assets/hooks/useAssetUpload"
 import "@/pages/assets/hooks/useAssetSelection"
 import "@/pages/assets/hooks/useAssetOperations"
-import "@/pages/assets/hooks/asset-operations/batch-operations/useBatchDelete"
-import "@/pages/assets/hooks/asset-operations/batch-operations/useBatchTag"
-import "@/pages/assets/hooks/asset-operations/batch-operations/useBatchClassify"
-import "@/pages/assets/hooks/asset-operations/batch-operations/useBatchMark"
+import "@/pages/assets/hooks/asset-operations/batch/useBatchDelete"
+import "@/pages/assets/hooks/asset-operations/batch/useBatchTag"
+import "@/pages/assets/hooks/asset-operations/batch/useBatchClassify"
+import "@/pages/assets/hooks/asset-operations/batch/useBatchMark"
 
 describe("AssetLibrary module smoke test", () => {
   it("should load all asset modules", () => {

apps/web/src/test/pages/editing-planner/smoke.test.tsx

@@ -53,6 +53,13 @@ import "@/pages/editing-planner/components/clip-properties/SubtitleSettingsSecti
 import "@/pages/editing-planner/components/clip-properties/BgmSettingsSection"
 import "@/pages/editing-planner/components/clip-properties/ClipDetailSection"
 import "@/pages/editing-planner/components/clip-properties/StatsSection"
+import "@/pages/editing-planner/components/pip-config/LayerList"
+import "@/pages/editing-planner/components/pip-config/LayerConfig"
+import "@/pages/editing-planner/components/sticker/StickerLibrary"
+import "@/pages/editing-planner/components/sticker/StickerList"
+import "@/pages/editing-planner/components/sticker/StickerPropsEditor"
+import "@/pages/editing-planner/components/sticker/StickerPreview"
+import "@/pages/editing-planner/components/sticker/TextStickerPropsEditor"
 import "@/pages/editing-planner/components/filter/FilterPresetGrid"
 import "@/pages/editing-planner/components/filter/FilterManualAdjust"
 import "@/pages/editing-planner/components/intro-outro/IntroOutroBlock"
@@ -60,6 +67,8 @@ import "@/pages/editing-planner/components/subtitle-style/SubtitlePreview"
 import "@/pages/editing-planner/components/subtitle-style/SubtitleModeSwitch"
 import "@/pages/editing-planner/components/subtitle-style/SubtitlePositionSelector"
 import "@/pages/editing-planner/components/subtitle-style/SubtitleEffectButtons"
+import "@/pages/editing-planner/components/tts/VoiceSelector"
+import "@/pages/editing-planner/components/tts/TtsSlider"
 import "@/pages/editing-planner/components/watermark/WatermarkTypeTabs"
 import "@/pages/editing-planner/components/watermark/ImageWatermarkSection"
 import "@/pages/editing-planner/components/watermark/TextWatermarkSection"

apps/worker/worker_app/celery_app.py

@@ -37,7 +37,6 @@ celery_app.conf.imports = (
     "worker_app.tasks._startup",
     "apps.worker.video_processing.dedup",
     "worker_app.tasks.cleanup",
-    "apps.api.app.tasks.lipsync_tts",
 )
 
 # Celery Beat 定时任务调度

docs/ai-avatar-api-contract-1822.md

@@ -1,169 +0,0 @@
-# AI 数字人前后端接口契约（#1797 / #1822）
-
-> 分支：`fix/ai-avatar-v3-1797`
-> 范围：TTS→对口型链路打通、语速/情绪透传、封面智能选帧、标题字段对齐
-> 本文档为前后端联调的唯一字段口径。
-
----
-
-## 1. 对口型创建接口 `POST /api/v1/lipsync/jobs`
-
-支持两种输入模式，**二选一**：
-
-### 模式 A（推荐）：TTS 直生 —— 传音色 + 文案，后端内部合成音频
-
-前端无需先调 TTS。后端收到请求后：先调 CosyVoice 合成音频 → 转存 OSS → 再提交 MediaKit 对口型。
-
-```jsonc
-{
-  "video_url": "https://oss.../person.mp4",   // 必填，人物视频（MP4）
-  "voice_id": "cosyvoice-v3-flash-99-xxxx",    // 必填，音色 ID（预置音色 或 克隆 profile UUID）
-  "script_text": "省是浙江省，市是永康市……",     // 必填，要合成的文案
-  "speed": 1.0,                                 // 可选，语速 0.5~2.0，默认 1.0
-  "emotion": "excited",                         // 可选，情绪，见 §3
-  "enable_video_loop": false,                   // 可选，音频长于视频时是否循环画面
-  "project_id": ""                              // 可选
-}
-```
-
-### 模式 B：直接音频 —— 前端已准备好音频
-
-```jsonc
-{
-  "video_url": "https://oss.../person.mp4",     // 必填
-  "audio_url": "https://oss.../voice.mp3",      // 必填，mp3/aac/wav/m4a/flac
-  "enable_video_loop": false
-}
-```
-
-### 校验与错误码
-
-| 场景 | HTTP | detail.code |
-|------|------|-------------|
-| 既无 audio_url 又无 voice_id+script_text | 422 | （schema 校验） |
-| video_url 非 MP4 / audio_url 格式不支持 | 422 | （schema 校验） |
-| 克隆音色不属于当前用户 | 403 | `VoiceForbidden` |
-| 克隆音色尚未合成完成 | 400 | `VoiceNotReady` |
-| TTS 合成失败（如 CosyVoice 欠费） | 502 | `TTSSynthesisFailed` |
-| MediaKit 提交失败 | 502 | `*`（透传 MediaKit code） |
-
-### 轮询
-
-- `GET /api/v1/lipsync/jobs/{id}`：非终态任务先返回 DB 缓存，**后台异步刷新 MediaKit**（不会阻塞轮询）。
-- `status` 流转：`pending` → `submitted` → `running`/`processing`（MediaKit 中间态同步）→ `completed` / `failed`。
-- `completed` 时 `output_video_url` 为**已转存自家 OSS 的非临时 URL**（不会过期）。
-- 前端每 3s 轮询，命中 `completed`/`failed` 即停。
-
----
-
-## 2. TTS 合成接口语速/情绪透传
-
-- `POST /api/v1/tts/synthesize`（异步任务）与 `POST /api/v1/tts/preview`（即时试听）均新增：
-  - `speed`：float，0.5~2.0，默认 1.0 → 透传 CosyVoice payload 的 `rate`
-  - `emotion`：string，见 §3 映射 → 透传 `emotion`
-- 透传链路：`route → CreateTTSJobUseCase(metadata) → TTSJobWorkflow.start_synthesis / 分段合成 → CosyVoiceService.submit_synthesize_task(rate/emotion)`。
-- 分段合成（长文案）与失败重合成路径同样透传 speed/emotion。
-
----
-
-## 3. 情绪枚举（前后端统一）
-
-前端把中文选项映射成英文后传后端；后端同时接受中文/英文，非法值忽略（走默认自然）。
-
-| 前端选项 | 传参值 | CosyVoice 枚举 |
-|---------|--------|---------------|
-| 自然 | `natural` | natural |
-| 兴奋 | `excited` | excited |
-| 沉稳 | `calm` | calm |
-| 亲切 | `friendly` | friendly |
-
-后端 `normalize_emotion()` 也接受中文（自然/兴奋/沉稳/亲切）做兜底映射。
-
----
-
-## 4. 智能封面接口 `POST /api/v1/ai-avatar/render/smart-cover`
-
-独立接口，**不依赖渲染任务**，前端「智能获取封面」按钮直接调用。
-
-**请求**
-```jsonc
-{
-  "video_url": "https://oss.../avatar_output.mp4",  // 必填，数字人视频
-  "max_frames": 5                                    // 可选，抽帧数量 1~10，默认 5
-}
-```
-
-**响应**
-```jsonc
-{
-  "cover_url": "https://oss.../ai-avatar/covers/xxx/cover_yy.jpg", // OSS 非临时 URL
-  "status": "completed",       // completed / fallback_failed
-  "message": ""                // 失败原因
-}
-```
-
-**实现**：复用智能剪辑同款能力 —— MediaKit `extract_frames(SpecifiedFrames)` 抽 5 帧 → `cover_frame_scorer.score_frames`（清晰度+亮度+色彩）评分选最佳 → 转存 OSS。
-**不再使用 FFmpeg 简单首帧**。渲染管线最终封面也优先走该智能选帧，MediaKit 不可用时才回退 FFmpeg。
-
----
-
-## 5. 渲染接口 `POST /api/v1/ai-avatar/render`
-
-```jsonc
-{
-  "lipsync_job_id": "7c29a3b2-...",     // 必填，已 completed 的对口型任务
-  "script_id": "",                       // 可选！见下方说明
-  "b_roll_segments": [],                 // 可选，B-roll 片段
-  "title_config": { ... },               // 可选，单个标题配置 dict（见 §6）
-  "cover_config": { ... },               // 可选，封面配置（建议改用 smart-cover）
-  "project_id": ""
-}
-```
-
-**`script_id` 是否必填：可选。**
-- 从文案库选了文案时传对应文案 ID（后端做归属校验）。
-- **手动输入文案、走 TTS 直生模式时不传（留空）即可**——渲染管线不依赖文案内容，`script_id` 仅用于归属校验。留空不会卡手动文案用户。
-
----
-
-## 6. 标题配置 `title_config` 字段清单（以 build_title_drawtext_filter 为准）
-
-渲染请求收的是**单个 `title_config` dict**（不是 `titles[]` 数组），字段与 `packages/domain/video_filter_builder.py` 的 `build_title_drawtext_filter()` 完全对齐：
-
-| 字段 | 别名 | 类型 | 必填 | 默认 | 说明 |
-|------|------|------|------|------|------|
-| `text` | `content` | string | ✅ | — | 标题文字；为空或 `enabled=false` 时不渲染标题 |
-| `enabled` | — | bool | ❌ | `true` | 是否启用标题；false 跳过 |
-| `font` | `font_preset` | string | ❌ | 思源黑体 | 字体名（后端按名字解析字体文件） |
-| `font_size` | `size` | int | ❌ | 36 | 字号（像素） |
-| `font_color` | `color` | string | ❌ | `#ffffff` | 文字颜色，`#RRGGBB`；后端自动去掉 `#`，也可传 `RRGGBB` 或颜色名 |
-| `position` | — | string | ❌ | `top` | 预设位置：`top`(y=50) / `center`(垂直居中) / `bottom`(底部上移50px) / `custom` |
-| `pos_x` | — | int/float | ❌ | — | 自定义 X 坐标（像素），仅 `position=custom` 生效 |
-| `pos_y` | — | int/float | ❌ | — | 自定义 Y 坐标（像素），仅 `position=custom` 生效 |
-| `bold` | — | bool | ❌ | `true` | 粗体（Bold 字体变体，回退 borderw 模拟） |
-| `stroke` | — | bool/object | ❌ | — | 描边。`true`=黑描边宽2；object 见下 |
-| `stroke.enabled` | — | bool | ❌ | true | 是否描边 |
-| `stroke.width` | — | int | ❌ | 2 | 描边宽度 |
-| `stroke.color` | — | string | ❌ | `#000000` | 描边颜色 |
-| `shadow` | — | bool/object | ❌ | — | 阴影。`true`=黑色阴影偏移2px；object 见下 |
-| `shadow.enabled` | — | bool | ❌ | true | 是否阴影 |
-| `shadow.color` | — | string | ❌ | `#000000` | 阴影颜色 |
-| `shadow.offset_x` | — | int | ❌ | 2 | 阴影 X 偏移 |
-| `shadow.offset_y` | — | int | ❌ | 2 | 阴影 Y 偏移 |
-
-**前端注意事项**
-- 标题是**整条成片一个标题**（单个 dict），不是按时间段的标题数组；没有 `start`/`end`/`frame`/`fontSize` 这些字段。
-- 位置用 `position` 四档枚举；自由摆放用 `position="custom"` + `pos_x`/`pos_y`（像素坐标，非比例）。
-- 颜色统一传 `#RRGGBB` 即可，后端会处理 `#`；三档预设位置下标题始终水平居中。
-- `stroke`/`shadow` 传 `true` 用默认样式，或传 object 精细控制颜色/宽度/偏移。
-
----
-
-## 7. 前端对接清单
-
-1. 对口型：改用**模式 A**（voice_id + script_text + speed + emotion），不要再先调 TTS 拿 audio_url。
-2. 音色 ID：`voice_id` 可直接传克隆音色的 profile UUID，后端会解析为 CosyVoice voice_id（与 /tts 一致）。
-3. 情绪下拉：自然/兴奋/沉稳/亲切 → natural/excited/calm/friendly。
-4. 封面：点「智能获取封面」→ POST `/ai-avatar/render/smart-cover`，用返回的 `cover_url`。
-5. 渲染：手动文案直生场景 `script_id` 留空；标题传**单个** `title_config` dict（字段见 §6）。
-6. 轮询：识别 `running` 等中间态，不要只认 `submitted`。

infra/docker/compose.yml

@@ -128,9 +128,9 @@ services:
       - xiaoxia-net
 
     # 健康检查配置
-    # 注：容器内无 pgrep/ps，扫描 /proc 所有进程的 cmdline 查找 celery 进程
+    # 注：celery inspect ping 依赖 broker 连接，在容器内不可靠，改用进程检查
     healthcheck:
-      test: ["CMD-SHELL", "grep -lq celery /proc/[0-9]*/cmdline 2>/dev/null || exit 1"]
+      test: ["CMD-SHELL", "for pid in /proc/[0-9]*/cmdline; do if grep -ql celery \"$pid\" 2>/dev/null; then exit 0; fi; done; exit 1"]
       interval: 30s
       timeout: 10s
       retries: 3

infra/docker/deploy-production-registry.sh

@@ -155,7 +155,7 @@ docker run -d \
   --restart unless-stopped \
   --cpus 2 \
   --memory 2g \
-  --health-cmd "sh -c \"grep -lq celery /proc/[0-9]*/cmdline 2>/dev/null || exit 1\"" \
+  --health-cmd "sh -c \"for pid in /proc/[0-9]*/cmdline; do if grep -ql celery \"$pid\" 2>/dev/null; then exit 0; fi; done; exit 1\"" \
   --health-interval 30s \
   --health-timeout 10s \
   --health-retries 3 \

infra/docker/deploy-staging-registry.sh

@@ -116,7 +116,7 @@ docker run -d \
   -v "$GENERATED_DIR:/app/generated" \
   --restart unless-stopped \
   --label com.centurylinklabs.watchtower.enable=true \
-  --health-cmd "sh -c \"grep -lq celery /proc/[0-9]*/cmdline 2>/dev/null || exit 1\"" \
+  --health-cmd "sh -c \"for pid in /proc/[0-9]*/cmdline; do if grep -ql celery \"$pid\" 2>/dev/null; then exit 0; fi; done; exit 1\"" \
   --health-interval 30s \
   --health-timeout 10s \
   --health-retries 3 \

infra/docker/worker.Dockerfile

@@ -38,10 +38,6 @@ RUN chmod +x /usr/local/bin/entrypoint-worker.sh
 # 业务代码（变化最频繁，放最后）
 COPY apps/worker/ /app/apps/worker/
 
-# 健康检查：扫描所有进程的 cmdline 查找 celery 进程
-HEALTHCHECK --interval=30s --timeout=10s --start-period=40s --retries=3 \
-    CMD grep -lq celery /proc/[0-9]*/cmdline 2>/dev/null || exit 1
-
 USER celery
 WORKDIR /app/apps/worker
 CMD ["/usr/local/bin/entrypoint-worker.sh"]

packages/adapters/sqlalchemy_impl/models.py

@@ -684,15 +684,9 @@ class LipsyncJobModel(Base):
 
     # 输入参数
     video_url = Column(Text, nullable=False)
-    audio_url = Column(Text, nullable=True)  # 直生模式（voice_id+script_text）下 TTS 合成后回填
+    audio_url = Column(Text, nullable=False)
     enable_video_loop = Column(Boolean, nullable=False, default=False)
 
-    # TTS 直生字段：传音色 + 文案，由后端先合成音频再对口型
-    voice_id = Column(String(200), nullable=False, default="")
-    script_text = Column(Text, nullable=False, default="")
-    speed = Column(Float, nullable=False, default=1.0)
-    emotion = Column(String(20), nullable=False, default="")
-
     # MediaKit 任务状态
     mediakit_task_id = Column(String(200), nullable=False, default="", index=True)
     status = Column(
@@ -721,8 +715,7 @@ class AiAvatarRenderJob(Base):
 
     # 输入参数
     lipsync_job_id = Column(String(36), nullable=False)
-    # 文案 ID 可选：手动输入文案（TTS 直生）场景不关联文案库条目
-    script_id = Column(String(36), nullable=False, default="")
+    script_id = Column(String(36), nullable=False)
     b_roll_segments = Column(JSON, nullable=False, default=list)
     # b_roll_segments 格式: [{"script_segment_index": 0, "asset_url": "...", "mode": "fullscreen|pip", "start_time": 5.0, "end_time": 10.0}, ...]
     title_config = Column(JSON, nullable=False, default=dict)

packages/application/cosyvoice_service.py

@@ -25,35 +25,6 @@ from packages.shared.config import get_shared_settings
 logger = logging.getLogger(__name__)
 
 
-# CosyVoice 支持的情绪：中文标签 → API 英文值
-EMOTION_MAP = {
-    "自然": "natural",
-    "兴奋": "excited",
-    "沉稳": "calm",
-    "亲切": "friendly",
-    "natural": "natural",
-    "excited": "excited",
-    "calm": "calm",
-    "friendly": "friendly",
-}
-VALID_EMOTIONS = {"natural", "excited", "calm", "friendly"}
-
-
-def normalize_emotion(emotion: str) -> str:
-    """将前端情绪值归一化为 CosyVoice 英文枚举。
-
-    支持中文（自然/兴奋/沉稳/亲切）和英文；非法值返回空串（不传，走默认）。
-    """
-    if not emotion:
-        return ""
-    key = emotion.strip().lower()
-    mapped = EMOTION_MAP.get(emotion.strip()) or EMOTION_MAP.get(key)
-    if mapped and mapped in VALID_EMOTIONS:
-        return mapped
-    logger.warning("未知的 emotion 值，忽略: %r", emotion)
-    return ""
-
-
 class CosyVoiceError(Exception):
     """CosyVoice API 调用异常。"""
 
@@ -460,7 +431,6 @@ class CosyVoiceService:
         format: str = "",
         speed: float = 1.0,
         volume: int = 50,
-        emotion: str = "",
     ) -> dict:
         """提交语音合成任务（同步非流式，直接返回结果）.
 
@@ -474,7 +444,6 @@ class CosyVoiceService:
             format: 输出格式（mp3/wav/pcm），空表示使用配置默认值
             speed: 语速（0.5-2.0），1.0 为正常速度
             volume: 音量（0-100），默认 50
-            emotion: 情绪（natural/excited/calm/friendly），空串不传
 
         Returns:
             dict: {"audio_url": str, "request_id": str,
@@ -494,20 +463,17 @@ class CosyVoiceService:
 
         settings = get_shared_settings()
 
-        input_payload: dict[str, Any] = {
-            "text": text,
-            "voice": voice_id,
-            "format": format or settings.cosyvoice_format,
-            "sample_rate": sample_rate or settings.cosyvoice_sample_rate,
-            "rate": speed,
-            "volume": volume,
+        payload = {
+            "model": self._model,
+            "input": {
+                "text": text,
+                "voice": voice_id,
+                "format": format or settings.cosyvoice_format,
+                "sample_rate": sample_rate or settings.cosyvoice_sample_rate,
+                "rate": speed,
+                "volume": volume,
+            },
         }
-        # 情绪：归一化（中文→英文）后透传；空/非法则不传，走 CosyVoice 默认
-        norm_emotion = normalize_emotion(emotion)
-        if norm_emotion:
-            input_payload["emotion"] = norm_emotion
-
-        payload = {"model": self._model, "input": input_payload}
 
         response = self._call_api(
             method="POST",
@@ -524,10 +490,6 @@ class CosyVoiceService:
         if not audio_url:
             raise CosyVoiceError(f"CosyVoice API 未返回 audio_url: {response}")
 
-        # DashScope 返回 http://，统一升级为 https://
-        if audio_url.startswith("http://"):
-            audio_url = audio_url.replace("http://", "https://", 1)
-
         return {
             "task_id": "",  # 同步接口无 task_id，兼容旧接口
             "audio_url": audio_url,
@@ -555,7 +517,6 @@ class CosyVoiceService:
         format: str = "",
         speed: float = 1.0,
         volume: int = 50,
-        emotion: str = "",
         timeout: float = 120.0,
     ) -> SynthesizeResult:
         """语音合成（同步非流式）.
@@ -587,7 +548,6 @@ class CosyVoiceService:
             format=format,
             speed=speed,
             volume=volume,
-            emotion=emotion,
         )
 
         return SynthesizeResult(

packages/application/tts_job/workflow.py

@@ -143,16 +143,11 @@ class TTSWorkflowService:
             return self._start_segment_synthesis(job)
 
         try:
-            _meta = dict(job.metadata)
-            _speed = float(_meta.get("speed", 1.0) or 1.0)
-            _emotion = str(_meta.get("emotion", "") or "")
             submit_result = self.cosyvoice_service.submit_synthesize_task(
                 text=job.input_text,
                 voice_id=job.voice_id,
                 sample_rate=job.sample_rate,
                 format=job.format,
-                speed=_speed,
-                emotion=_emotion,
             )
 
             # 保存 task_id / request_id 到 metadata
@@ -288,7 +283,6 @@ class TTSWorkflowService:
             job_metadata = job.metadata or {}
             speed = float(job_metadata.get("speed", 1.0))
             volume = int(job_metadata.get("volume", 50))
-            emotion = str(job_metadata.get("emotion", "") or "")
 
             result = self.cosyvoice_service.submit_synthesize_task(
                 text=job.input_text,
@@ -297,7 +291,6 @@ class TTSWorkflowService:
                 format=job.format,
                 speed=speed,
                 volume=volume,
-                emotion=emotion,
             )
             audio_url = result.get("audio_url", "")
             if not audio_url:
@@ -408,9 +401,6 @@ class TTSWorkflowService:
         """
         max_workers = min(len(segments), _MAX_SEGMENT_WORKERS)
         results: list[dict | None] = [None] * len(segments)
-        _seg_meta = job.metadata or {}
-        _seg_speed = float(_seg_meta.get("speed", 1.0) or 1.0)
-        _seg_emotion = str(_seg_meta.get("emotion", "") or "")
 
         with ThreadPoolExecutor(max_workers=max_workers) as executor:
             future_to_idx = {}
@@ -421,8 +411,6 @@ class TTSWorkflowService:
                     voice_id=job.voice_id,
                     sample_rate=job.sample_rate,
                     format=job.format,
-                    speed=_seg_speed,
-                    emotion=_seg_emotion,
                 )
                 future_to_idx[future] = idx
 
@@ -512,7 +500,6 @@ class TTSWorkflowService:
         job_metadata = job.metadata or {}
         speed = float(job_metadata.get("speed", 1.0))
         volume = int(job_metadata.get("volume", 50))
-        emotion = str(job_metadata.get("emotion", "") or "")
 
         # 分段文本（用于缺失段重新合成）
         segments = split_text(job.input_text, max_chars=_SEGMENT_THRESHOLD)
@@ -547,7 +534,6 @@ class TTSWorkflowService:
                         format=job.format,
                         speed=speed,
                         volume=volume,
-                        emotion=emotion,
                     )
                     future_to_idx[future] = idx
 

scripts/ci/auto_fix_formatting.py

@@ -1,13 +1,10 @@
 #!/usr/bin/env python3
-"""CI中自动修复代码格式（Python: black + isort + ruff | Frontend: prettier），并推送回原分支。
+"""CI中自动修复代码格式（Python: black + isort | Frontend: prettier），并推送回原分支。
 
 - PR事件：所有PR只要Code Quality因格式问题失败，自动修复并push回源分支
 - Push事件（develop/main）：自动修复并push回原分支，保持主干格式永远正确
 - 防循环：修复commit带 [skip ci-format-check] 标记，检测到该标记则跳过修复
-- black/isort/prettier 修格式；ruff check --fix --unsafe-fixes 自动修复
-  ruff 可修复的 lint 规则（含 F401 未使用 import 等 unsafe fix）
-- ruff 目标范围与 validate_style.sh 的检查范围对齐：apps packages tests
-  （alembic/scripts 不在 ruff 检查范围内，不做修复）
+- 只修格式（black/isort/prettier），ruff逻辑类错误不动
 当code quality检查因格式问题失败时触发。
 """
 
@@ -138,7 +135,7 @@ def get_pr_head_branch(pr_number, api_url, token):
 
 
 def fix_python(target_py_files, scan_mode):
-    """修复 Python 文件 (black 格式化 + isort 排序 + ruff lint 自动修复)"""
+    """修复 Python 文件格式 (black + isort)"""
     if not target_py_files:
         print("没有需要修复的 Python 文件，跳过")
         return
@@ -149,48 +146,14 @@ def fix_python(target_py_files, scan_mode):
     result = run(f"python3 -m black {target_str}", check=False)
     print(result.stdout[-500:] if result.stdout else "")
     if result.returncode != 0:
-        print("black执行失败，但继续尝试isort/ruff", file=sys.stderr)
+        print("black执行失败，但继续尝试isort", file=sys.stderr)
 
     print()
     print("--- isort 排序 ---")
     result = run(f"python3 -m isort {target_str}", check=False)
     print(result.stdout[-500:] if result.stdout else "")
     if result.returncode != 0:
-        print("isort执行失败，继续尝试ruff", file=sys.stderr)
-
-    # ruff lint 自动修复
-    # 与 validate_style.sh 的检查范围对齐：只修 apps/packages/tests
-    # （alembic 在 pyproject.toml 中被 exclude，scripts 不在 ruff 检查范围内）
-    ruff_scopes = ("apps/", "packages/", "tests/")
-    ruff_files = [f for f in target_py_files if f.startswith(ruff_scopes)]
-    if scan_mode != "incremental":
-        ruff_targets = "apps packages tests"
-    elif ruff_files:
-        ruff_targets = " ".join(ruff_files)
-    else:
-        ruff_targets = ""
-
-    if ruff_targets:
-        # ruff 由 style job 的 requirements-dev.txt 安装；不可用时跳过（不阻断 black/isort 的修复）
-        avail = run("python3 -m ruff --version", check=False)
-        if avail.returncode != 0:
-            print("ruff 不可用，跳过 ruff 自动修复", file=sys.stderr)
-        else:
-            print()
-            print("--- ruff lint 自动修复 (--fix --unsafe-fixes) ---")
-            # --unsafe-fixes 用于启用 F401（未使用 import）等 ruff 归类为 unsafe 的自动修复；
-            # 安全性由修复后重跑的完整 CI（单测/构建/staging 健康检查）兜底
-            result = run(
-                f"python3 -m ruff check {ruff_targets} --fix --unsafe-fixes",
-                check=False,
-            )
-            print(result.stdout[-1500:] if result.stdout else "")
-            if result.returncode != 0:
-                # 可能是仍有不可自动修复的 lint 错误（留待 style check 再次拦截），或修复过程出错
-                print("ruff 自动修复后仍有未修复项或执行失败，剩余问题由 style check 继续拦截", file=sys.stderr)
-    else:
-        print()
-        print("增量模式且无 apps/packages/tests 范围内的 Python 变更，跳过 ruff 自动修复")
+        print("isort执行失败", file=sys.stderr)
 
 
 def fix_frontend(target_fe_files, scan_mode, repo_root):
@@ -371,7 +334,7 @@ def main():
     # 提交修复
     run("git clean -fd")
     run("git add -u")
-    run('git commit -m "style: auto-format with black + isort + ruff + prettier [skip ci-format-check]"')
+    run('git commit -m "style: auto-format with black + isort + prettier [skip ci-format-check]"')
 
     # 推送（head_branch已从ensure_git_repo获取）
     print(f"\nPR来源分支: {head_branch}")

tests/unit/test_ai_avatar_emotion_tts_lipsync.py

@@ -1,365 +0,0 @@
-"""#1822 情绪/语速透传 + 对口型 TTS 直生 + 智能封面 单元测试.
-
-CI 增量映射:
-  cosyvoice_service.normalize_emotion / payload emotion
-  lipsync_service TTS 直生分支（voice_id+script_text）
-  ai_avatar_cover_service 智能选帧
-"""
-
-import os
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-os.environ.setdefault("JWT_SECRET_KEY", "dev-secret-key-for-testing")
-
-
-# ── 情绪归一化 ──────────────────────────────────────────────────────────
-
-
-def test_normalize_emotion_english_values():
-    from packages.application.cosyvoice_service import normalize_emotion
-
-    assert normalize_emotion("natural") == "natural"
-    assert normalize_emotion("excited") == "excited"
-    assert normalize_emotion("calm") == "calm"
-    assert normalize_emotion("friendly") == "friendly"
-    # 大小写 / 空白容错
-    assert normalize_emotion("  Excited  ") == "excited"
-
-
-def test_normalize_emotion_chinese_values():
-    from packages.application.cosyvoice_service import normalize_emotion
-
-    assert normalize_emotion("自然") == "natural"
-    assert normalize_emotion("兴奋") == "excited"
-    assert normalize_emotion("沉稳") == "calm"
-    assert normalize_emotion("亲切") == "friendly"
-
-
-def test_normalize_emotion_invalid_returns_empty():
-    from packages.application.cosyvoice_service import normalize_emotion
-
-    assert normalize_emotion("") == ""
-    assert normalize_emotion("angry") == ""
-    assert normalize_emotion("喜怒哀乐") == ""
-
-
-# ── CosyVoice payload 携带 emotion + rate ──────────────────────────────
-
-
-def _make_service_with_captured_client(captured: dict):
-    """构造 CosyVoiceService，拦截 post 请求体到 captured['json']."""
-    import httpx as _httpx
-
-    from packages.application import cosyvoice_service as mod
-
-    mock_client = MagicMock(spec=_httpx.Client)
-    resp = MagicMock()
-    resp.status_code = 200
-    resp.json.return_value = {
-        "request_id": "req-1",
-        "output": {"audio": {"url": "https://tts/a.mp3", "duration": 1.0}},
-    }
-    resp.raise_for_status = MagicMock()
-
-    def fake_request(method, url, headers, json, timeout):
-        captured["json"] = json
-        return resp
-
-    mock_client.request.side_effect = fake_request
-
-    with patch.object(mod, "get_shared_settings") as settings_patch:
-        s = MagicMock()
-        s.cosyvoice_api_key = "sk-test"
-        s.cosyvoice_base_url = "https://x/api/v1"
-        s.cosyvoice_model = "cosyvoice-v3-flash"
-        s.cosyvoice_clone_model = "voice-enrollment"
-        s.cosyvoice_format = "mp3"
-        s.cosyvoice_sample_rate = 22050
-        s.cosyvoice_voice = "longxiaochun"
-        settings_patch.return_value = s
-        svc = mod.CosyVoiceService(http_client=mock_client)
-    return svc
-
-
-def test_submit_synthesize_payload_includes_emotion_and_rate():
-    captured: dict = {}
-    svc = _make_service_with_captured_client(captured)
-
-    svc.submit_synthesize_task(text="你好", voice_id="v-1", speed=1.5, emotion="兴奋")
-
-    inp = captured["json"]["input"]
-    assert inp["emotion"] == "excited"
-    assert inp["rate"] == 1.5
-
-
-def test_submit_synthesize_payload_omits_emotion_when_empty():
-    captured: dict = {}
-    svc = _make_service_with_captured_client(captured)
-
-    svc.submit_synthesize_task(text="你好", voice_id="v-1")
-
-    assert "emotion" not in captured["json"]["input"]
-
-
-# ── 对口型 TTS 直生分支 ─────────────────────────────────────────────────
-
-
-def _lipsync_service_with_mocks():
-    from app.services.lipsync_service import LipsyncService
-
-    db = MagicMock()
-    client = MagicMock()
-    client.is_available = True
-    client.submit_lipsync.return_value = {
-        "success": True,
-        "task_id": "mk-1",
-        "request_id": "req-1",
-    }
-    cosy = MagicMock()
-    cosy.submit_synthesize_task.return_value = {
-        "audio_url": "https://tts/raw.mp3",
-        "request_id": "tts-req",
-        "audio_duration": 3.0,
-    }
-    svc = LipsyncService(db, client=client, cosyvoice_service=cosy, voice_clone_repo=MagicMock())
-    # _resolve_voice_id 默认原样返回（repo.get 返回 None）
-    svc._voice_clone_repo.get.return_value = None
-    return svc, client, cosy
-
-
-def test_create_job_tts_direct_mode_synthesizes_audio():
-    svc, client, cosy = _lipsync_service_with_mocks()
-
-    with patch("app.services.lipsync_service.tts_synthesize_and_submit") as mock_task:
-        mock_task.apply_async.return_value = MagicMock(id="celery-task-123")
-
-        job = svc.create_job(
-            user_id="user-1",
-            video_url="https://oss/person.mp4",
-            voice_id="cosy-v1",
-            script_text="你好世界",
-            speed=1.2,
-            emotion="兴奋",
-        )
-
-    # v4: TTS 模式下 create_job 返回 tts_processing 状态，dispatch Celery 任务
-    assert job.status == "tts_processing"
-    assert job.emotion == "excited"
-    assert job.speed == 1.2
-    # 不直接调用 CosyVoice（由 Celery 任务处理）
-    cosy.submit_synthesize_task.assert_not_called()
-    # 不直接提交 MediaKit（由 Celery 任务处理）
-    client.submit_lipsync.assert_not_called()
-    # dispatch 了 Celery 任务
-    mock_task.apply_async.assert_called_once()
-
-
-def test_create_job_direct_audio_mode_skips_tts():
-    svc, client, cosy = _lipsync_service_with_mocks()
-
-    job = svc.create_job(
-        user_id="user-1",
-        video_url="https://oss/person.mp4",
-        audio_url="https://oss/ready.mp3",
-    )
-
-    cosy.submit_synthesize_task.assert_not_called()
-    _, submit_kwargs = client.submit_lipsync.call_args
-    assert submit_kwargs["audio_url"] == "https://oss/ready.mp3"
-
-
-def test_create_job_tts_failure_raises():
-    """v4: TTS 模式下 create_job 不再同步失败，而是 dispatch Celery 任务。
-    TTS 合成失败由 Celery 任务内部处理并更新 job 状态。"""
-    svc, client, cosy = _lipsync_service_with_mocks()
-
-    with patch("app.services.lipsync_service.tts_synthesize_and_submit") as mock_task:
-        mock_task.apply_async.return_value = MagicMock(id="celery-task-456")
-
-        job = svc.create_job(
-            user_id="user-1",
-            video_url="https://oss/person.mp4",
-            voice_id="v-1",
-            script_text="文本",
-        )
-
-    # create_job 成功返回 tts_processing，不直接调用 TTS
-    assert job.status == "tts_processing"
-    cosy.submit_synthesize_task.assert_not_called()
-    client.submit_lipsync.assert_not_called()
-    mock_task.apply_async.assert_called_once()
-
-
-# ── refresh 同步中间状态 ────────────────────────────────────────────────
-
-
-def test_refresh_syncs_running_status():
-    from app.services.lipsync_service import LipsyncService
-
-    db = MagicMock()
-    client = MagicMock()
-    client.get_task_status.return_value = {"success": True, "status": "running"}
-    svc = LipsyncService(db, client=client)
-
-    job = MagicMock()
-    job.status = "submitted"
-    job.mediakit_task_id = "mk-1"
-    job.id = "j-1"
-    svc.get_job = MagicMock(return_value=job)
-
-    result = svc.refresh_job_status("j-1", "user-1")
-    assert result.status == "running"
-
-
-# ── 智能封面 ────────────────────────────────────────────────────────────
-
-
-def test_smart_cover_selects_best_frame_and_persists():
-    from app.services import ai_avatar_cover_service as cov
-
-    snapshots = [
-        {"image_url": "https://mk/f0.jpg"},
-        {"image_url": "https://mk/f1.jpg"},
-    ]
-    with (
-        patch("packages.shared.mediakit_client.get_mediakit_client") as mk_patch,
-        patch("packages.shared.cover_frame_scorer.score_frames") as score_patch,
-        patch("httpx.Client") as http_client_cls,
-        patch("packages.shared.storage.get_shared_storage_service") as storage_patch,
-    ):
-        mk = MagicMock()
-        mk.is_available = True
-        mk.extract_frames.return_value = snapshots
-        mk_patch.return_value = mk
-        # score_frames 把 f1 选为最佳
-        score_patch.side_effect = lambda cands: [
-            {"url": "https://mk/f1.jpg", "score": 90.0, "image_path": cands[1]["image_path"]},
-            {"url": "https://mk/f0.jpg", "score": 60.0, "image_path": cands[0]["image_path"]},
-        ]
-        # httpx.Client 连接池 mock
-        client_instance = MagicMock()
-        resp = MagicMock()
-        resp.content = b"IMGDATA"
-        resp.raise_for_status = MagicMock()
-        client_instance.get.return_value = resp
-        client_instance.__enter__ = MagicMock(return_value=client_instance)
-        client_instance.__exit__ = MagicMock(return_value=False)
-        http_client_cls.return_value = client_instance
-
-        storage = MagicMock()
-        storage.public_url = "https://oss.example.com"
-        # video_url 不是自家 OSS，不重签
-        storage.get_download_url.side_effect = lambda url, **kw: f"{url}?signed=1"
-        storage.upload_file.return_value = "https://oss.example.com/cover.jpg"
-        storage_patch.return_value = storage
-
-        url = cov.generate_smart_cover("https://other-host/avatar.mp4", job_id="job-1")
-
-    assert "signed=1" in url or url == "https://oss.example.com/cover.jpg"
-    mk.extract_frames.assert_called_once()
-    score_patch.assert_called_once()
-    # 验证使用了增大的轮询参数
-    call_kwargs = mk.extract_frames.call_args
-    assert call_kwargs.kwargs.get("poll_interval") == 3.0 or call_kwargs[1].get("poll_interval") == 3.0
-    assert call_kwargs.kwargs.get("max_poll_attempts") == 20 or call_kwargs[1].get("max_poll_attempts") == 20
-
-
-def test_smart_cover_returns_empty_when_mediakit_unavailable():
-    from app.services import ai_avatar_cover_service as cov
-
-    with (
-        patch("packages.shared.mediakit_client.get_mediakit_client") as mk_patch,
-        patch("packages.shared.storage.get_shared_storage_service") as storage_patch,
-    ):
-        mk = MagicMock()
-        mk.is_available = False
-        mk_patch.return_value = mk
-        storage = MagicMock()
-        storage.public_url = "https://oss.example.com"
-        storage_patch.return_value = storage
-        url = cov.generate_smart_cover("https://oss.example.com/avatar.mp4")
-    assert url == ""
-
-
-def test_sign_video_url_resigns_own_oss_url():
-    """自家 OSS 私有桶 URL 应被重签为长有效期预签名 URL"""
-    from app.services.ai_avatar_cover_service import _sign_video_url_for_mediakit
-
-    with patch("packages.shared.storage.get_shared_storage_service") as storage_patch:
-        storage = MagicMock()
-        storage.public_url = "https://oss.example.com"
-        storage.get_download_url.return_value = "https://oss.example.com/file.mp4?Expires=xxx&Signature=yyy"
-        storage_patch.return_value = storage
-
-        result = _sign_video_url_for_mediakit("https://oss.example.com/file.mp4")
-
-    assert "Signature=yyy" in result
-    storage.get_download_url.assert_called_once()
-
-
-def test_sign_video_url_skips_external_url():
-    """外部 URL（非自家 OSS）应原样返回，不做重签"""
-    from app.services.ai_avatar_cover_service import _sign_video_url_for_mediakit
-
-    with patch("packages.shared.storage.get_shared_storage_service") as storage_patch:
-        storage = MagicMock()
-        storage.public_url = "https://oss.example.com"
-        storage_patch.return_value = storage
-
-        result = _sign_video_url_for_mediakit("https://external-cdn.com/video.mp4")
-
-    assert result == "https://external-cdn.com/video.mp4"
-    storage.get_download_url.assert_not_called()
-
-
-def test_extract_frames_uses_extended_poll_params():
-    """验证 select_best_cover_frame 使用增大后的轮询参数"""
-    from app.services import ai_avatar_cover_service as cov
-
-    with (
-        patch("packages.shared.mediakit_client.get_mediakit_client") as mk_patch,
-        patch("packages.shared.storage.get_shared_storage_service") as storage_patch,
-    ):
-        mk = MagicMock()
-        mk.is_available = True
-        mk.extract_frames.return_value = [{"image_url": "https://mk/f0.jpg"}]
-        mk_patch.return_value = mk
-
-        storage = MagicMock()
-        storage.public_url = "https://oss.example.com"
-        storage_patch.return_value = storage
-
-        cov.select_best_cover_frame("https://other/avatar.mp4", max_frames=3)
-
-    call_kwargs = mk.extract_frames.call_args
-    assert call_kwargs.kwargs.get("poll_interval") == 3.0 or call_kwargs[1].get("poll_interval") == 3.0
-    assert call_kwargs.kwargs.get("max_poll_attempts") == 20 or call_kwargs[1].get("max_poll_attempts") == 20
-    assert call_kwargs.kwargs.get("max_retries") == 1 or call_kwargs[1].get("max_retries") == 1
-
-
-# ── 渲染 script_id 可选（手动文案直生场景）──────────────────────────────
-
-
-def test_render_request_script_id_optional():
-    import os
-    import sys
-
-    sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "apps", "api"))
-    from app.schemas.ai_avatar_render import CreateAiAvatarRenderRequest
-
-    # 手动文案直生：不传 script_id 也合法
-    req = CreateAiAvatarRenderRequest(lipsync_job_id="j-1")
-    assert req.script_id == ""
-
-    # 空白被 strip
-    req2 = CreateAiAvatarRenderRequest(lipsync_job_id="j-1", script_id="   ")
-    assert req2.script_id == ""
-
-    # title_config 是单个 dict
-    req3 = CreateAiAvatarRenderRequest(
-        lipsync_job_id="j-1",
-        title_config={"text": "标题", "position": "top", "font_size": 40},
-    )
-    assert req3.title_config["position"] == "top"

tests/unit/test_ai_avatar_render_service.py

@@ -176,23 +176,13 @@ class TestSchemaValidation:
                 script_id="script-1",
             )
 
-    def test_create_request_empty_script_id_normalized(self):
-        """script_id 改为可选（TTS 直生场景）：空白值应规范化为空串而非抛错。"""
+    def test_create_request_empty_script_id(self):
         from app.schemas.ai_avatar_render import CreateAiAvatarRenderRequest
 
-        req = CreateAiAvatarRenderRequest(
-            lipsync_job_id="lipsync-1",
-            script_id="  ",
-        )
-        assert req.script_id == ""
-
-    def test_create_request_empty_lipsync_job_id_raises(self):
-        from app.schemas.ai_avatar_render import CreateAiAvatarRenderRequest
-
-        with pytest.raises(ValueError, match="lipsync_job_id 不能为空"):
+        with pytest.raises(ValueError, match="script_id 不能为空"):
             CreateAiAvatarRenderRequest(
-                lipsync_job_id="  ",
-                script_id="script-1",
+                lipsync_job_id="lipsync-1",
+                script_id="  ",
             )
 
 
@@ -519,103 +509,6 @@ class TestAiAvatarRenderService:
         # 不应执行渲染逻辑
         mock_db.commit.assert_not_called()
 
-    def test_execute_render_success_creates_clip_record(self):
-        """execute_render 完成后自动创建成片记录到成片库."""
-        from app.services.ai_avatar_render_service import AiAvatarRenderService
-
-        mock_db = _make_mock_db()
-        mock_lipsync_job = _make_mock_lipsync_job(
-            status="completed",
-            output_video_url="https://oss/lipsync.mp4",
-            output_duration=30.0,
-        )
-        mock_job = _make_mock_render_job(
-            job_id="render-ok",
-            status="pending",
-            output_video_url="",
-            output_cover_url="",
-            output_duration=0.0,
-        )
-        mock_filter = MagicMock()
-        mock_filter.first.side_effect = [mock_job, mock_lipsync_job]
-        mock_query = MagicMock()
-        mock_query.filter.return_value = mock_filter
-        mock_db.query.return_value = mock_query
-
-        svc = AiAvatarRenderService(mock_db)
-
-        with (
-            patch.object(svc, "_download_video", return_value="/tmp/video.mp4"),
-            patch.object(svc, "_upload_to_oss", side_effect=lambda path, key: f"https://oss/{key}"),
-            patch("os.system", return_value=0),
-            patch("tempfile.TemporaryDirectory") as tmpdir_mock,
-            patch(
-                "app.services.ai_avatar_cover_service.generate_smart_cover", return_value="https://oss/smart_cover.jpg"
-            ),
-            patch("packages.domain.generated_video.GeneratedVideo.create") as gv_create,
-            patch(
-                "packages.adapters.sqlalchemy_impl.generated_video_repository.SQLAlchemyGeneratedVideoRepository"
-            ) as repo_cls,
-        ):
-            import tempfile as _tf
-
-            tmpdir_mock.return_value.__enter__ = MagicMock(return_value="/tmp/testdir")
-            tmpdir_mock.return_value.__exit__ = MagicMock(return_value=False)
-
-            mock_clip = MagicMock()
-            mock_clip.id = "clip-001"
-            gv_create.return_value = mock_clip
-            mock_repo = MagicMock()
-            repo_cls.return_value = mock_repo
-
-            svc.execute_render("render-ok")
-
-        assert mock_job.status == "completed"
-        gv_create.assert_called_once()
-        call_kwargs = gv_create.call_args
-        assert "https://oss/" in call_kwargs.kwargs["file_url"]
-        assert call_kwargs.kwargs["user_id"] == "user-1"
-        mock_repo.create.assert_called_once_with(mock_clip)
-
-    def test_execute_render_clip_failure_does_not_affect_render(self):
-        """成片创建失败不影响渲染任务标记为成功."""
-        from app.services.ai_avatar_render_service import AiAvatarRenderService
-
-        mock_db = _make_mock_db()
-        mock_lipsync_job = _make_mock_lipsync_job(
-            status="completed",
-            output_video_url="https://oss/lipsync.mp4",
-            output_duration=30.0,
-        )
-        mock_job = _make_mock_render_job(
-            job_id="render-clip-fail",
-            status="pending",
-            output_video_url="",
-            output_cover_url="",
-            output_duration=0.0,
-        )
-        mock_filter = MagicMock()
-        mock_filter.first.side_effect = [mock_job, mock_lipsync_job]
-        mock_query = MagicMock()
-        mock_query.filter.return_value = mock_filter
-        mock_db.query.return_value = mock_query
-
-        svc = AiAvatarRenderService(mock_db)
-
-        with (
-            patch.object(svc, "_download_video", return_value="/tmp/video.mp4"),
-            patch.object(svc, "_upload_to_oss", side_effect=lambda path, key: f"https://oss/{key}"),
-            patch("os.system", return_value=0),
-            patch("tempfile.TemporaryDirectory") as tmpdir_mock,
-            patch("app.services.ai_avatar_cover_service.generate_smart_cover", side_effect=RuntimeError("DB error")),
-        ):
-            tmpdir_mock.return_value.__enter__ = MagicMock(return_value="/tmp/testdir")
-            tmpdir_mock.return_value.__exit__ = MagicMock(return_value=False)
-            svc.execute_render("render-clip-fail")
-
-        # 即使成片创建失败，渲染任务仍应标记为 completed
-        assert mock_job.status == "completed"
-
     def test_error_exception_has_code(self):
         from app.services.ai_avatar_render_service import AiAvatarRenderError
 

tests/unit/test_lipsync_routes.py

@@ -35,14 +35,14 @@ def mock_mediakit():
 
 @pytest.fixture
 def mock_cosyvoice():
-    """Mock CosyVoice 服务（v3: service 内部走 submit_synthesize_task，返回 dict）."""
+    """Mock CosyVoice 服务."""
     service = MagicMock()
-    service.submit_synthesize_task.return_value = {
-        "audio_url": "https://oss.example.com/tts-output.mp3",
-        "request_id": "tts-req-789",
-    }
-    # synthesize_speech 保留给直接同步调用场景
-    service.synthesize_speech.return_value = MagicMock(audio_url="https://oss.example.com/tts-output.mp3")
+    service.synthesize_speech.return_value = MagicMock(
+        audio_url="https://oss.example.com/tts-output.mp3",
+        duration=15.0,
+        file_size=12345,
+        request_id="tts-req-789",
+    )
     return service
 
 
@@ -172,129 +172,103 @@ class TestSchemaValidation:
         )
         assert "?token=" in req.video_url
 
-    def test_dual_mode_fields_present(self):
-        """v3 契约: 双模式——支持直接音频 audio_url，也支持 TTS 直生 voice_id+script_text."""
-        from app.schemas.lipsync import CreateLipsyncJobRequest
-
-        fields = CreateLipsyncJobRequest.model_fields.keys()
-        # 直接音频模式
-        assert "audio_url" in fields
-        # TTS 直生模式
-        assert "voice_id" in fields
-        assert "script_text" in fields
-        # 语速/情绪透传
-        assert "speed" in fields
-        assert "emotion" in fields
-
-    def test_direct_audio_mode_accepted(self):
-        """v3 契约: 只传 audio_url（直接音频模式）也合法，无需 voice_id/script_text."""
+    def test_no_audio_url_in_request(self):
+        """#1809: 请求体不应包含 audio_url 字段."""
         from app.schemas.lipsync import CreateLipsyncJobRequest
 
         req = CreateLipsyncJobRequest(
             video_url="https://example.com/video.mp4",
-            audio_url="https://example.com/audio.mp3",
+            voice_id="longxiaochun_v3",
+            script_text="测试文本",
         )
-        assert req.audio_url == "https://example.com/audio.mp3"
-
-    def test_neither_mode_rejected(self):
-        """v3 契约: audio_url 与 voice_id+script_text 都缺时应报错."""
-        from app.schemas.lipsync import CreateLipsyncJobRequest
-
-        with pytest.raises(ValueError):
-            CreateLipsyncJobRequest(video_url="https://example.com/video.mp4")
+        assert not hasattr(req, "audio_url")
+        fields = req.model_fields.keys()
+        assert "audio_url" not in fields
+        assert "voice_id" in fields
+        assert "script_text" in fields
 
 
 class TestLipsyncServiceUnit:
     """Service 层单元测试（纯 mock，不依赖数据库）— #1809 更新."""
 
     def test_create_job_success(self, mock_mediakit, mock_cosyvoice):
-        """TTS 直生——v4 异步模式：create_job 只创建 DB 记录 + dispatch Celery 任务."""
         from app.services.lipsync_service import LipsyncService
 
         mock_db = MagicMock()
-        mock_repo = MagicMock()
-        mock_repo.get.return_value = None  # 预置音色，原样返回 voice_id
+        mock_db.add = MagicMock()
+        mock_db.flush = MagicMock()
+        mock_db.commit = MagicMock()
+        mock_db.refresh = MagicMock()
 
-        with patch(
-            "app.services.lipsync_service.tts_synthesize_and_submit"
-        ) as mock_task:
-            mock_task.apply_async.return_value = MagicMock(id="celery-task-123")
+        svc = LipsyncService(mock_db, client=mock_mediakit, cosyvoice_service=mock_cosyvoice)
 
-            svc = LipsyncService(
-                mock_db,
-                client=mock_mediakit,
-                voice_clone_repo=mock_repo,
-            )
-
-            job = svc.create_job(
-                user_id="user-1",
-                video_url="https://example.com/video.mp4",
-                voice_id="longxiaochun_v3",
-                script_text="大家好，欢迎来到直播间",
-                speed=1.2,
-                emotion="兴奋",
-            )
-
-        # TTS 模式：异步返回，状态为 tts_processing
-        assert job.status == "tts_processing"
-        assert not job.audio_url  # TTS 音频尚未合成（默认空字符串）
-        # 不直接调用 CosyVoice
-        mock_cosyvoice.submit_synthesize_task.assert_not_called()
-        # dispatch 了 Celery 任务
-        mock_task.apply_async.assert_called_once()
-        # job 记录透传字段
-        assert job.speed == 1.2
-        assert job.emotion == "excited"
-        # MediaKit 尚未提交（由 Celery 任务处理）
-        mock_mediakit.submit_lipsync.assert_not_called()
-
-    def test_create_job_tts_failure(self, mock_mediakit):
-        """v4: TTS 模式下 create_job 不再同步失败，而是 dispatch Celery 任务。
-        TTS 合成失败由 Celery 任务内部处理（见 test_lipsync_speed_optimization.py）。"""
-        from app.services.lipsync_service import LipsyncService
-
-        mock_db = MagicMock()
-        mock_repo = MagicMock()
-        mock_repo.get.return_value = None
-
-        svc = LipsyncService(
-            mock_db,
-            client=mock_mediakit,
-            voice_clone_repo=mock_repo,
+        job = svc.create_job(
+            user_id="user-1",
+            video_url="https://example.com/video.mp4",
+            voice_id="longxiaochun_v3",
+            script_text="大家好，欢迎来到直播间",
         )
 
-        with patch(
-            "app.services.lipsync_service.tts_synthesize_and_submit"
-        ) as mock_task:
-            mock_task.apply_async.return_value = MagicMock(id="celery-task-456")
+        assert job.status == "submitted"
+        assert job.mediakit_task_id == "mk-task-123"
+        # TTS 应该被调用
+        mock_cosyvoice.synthesize_speech.assert_called_once_with(
+            text="大家好，欢迎来到直播间",
+            voice_id="longxiaochun_v3",
+        )
+        # MediaKit 应该用 TTS 生成的 audio_url
+        mock_mediakit.submit_lipsync.assert_called_once()
+        call_kwargs = mock_mediakit.submit_lipsync.call_args
+        assert call_kwargs.kwargs["audio_url"] == "https://oss.example.com/tts-output.mp3"
 
-            job = svc.create_job(
+    def test_create_job_tts_failure(self, mock_mediakit):
+        """TTS 合成失败时，应创建 failed 记录并抛出 CosyVoiceError."""
+        from app.services.lipsync_service import LipsyncService
+
+        from packages.application.cosyvoice_service import CosyVoiceError
+
+        mock_cosyvoice = MagicMock()
+        mock_cosyvoice.synthesize_speech.side_effect = CosyVoiceError("TTS 服务不可用")
+
+        mock_db = MagicMock()
+        mock_db.add = MagicMock()
+        mock_db.flush = MagicMock()
+        mock_db.commit = MagicMock()
+        mock_db.refresh = MagicMock()
+
+        svc = LipsyncService(mock_db, client=mock_mediakit, cosyvoice_service=mock_cosyvoice)
+
+        with pytest.raises(CosyVoiceError, match="TTS 服务不可用"):
+            svc.create_job(
                 user_id="user-1",
                 video_url="https://example.com/video.mp4",
                 voice_id="longxiaochun_v3",
                 script_text="测试文本",
             )
 
-        # TTS 模式下 create_job 成功返回，状态为 tts_processing
-        assert job.status == "tts_processing"
+        # 不应提交到 MediaKit
         mock_mediakit.submit_lipsync.assert_not_called()
-        mock_task.apply_async.assert_called_once()
+        # 应该记录了失败状态
+        added_job = mock_db.add.call_args[0][0]
+        assert added_job.status == "failed"
+        assert "TTS" in added_job.error_message
 
-    def test_create_job_api_failure(self, mock_mediakit):
-        """MediaKit 提交失败（直传音频模式同步触发）."""
+    def test_create_job_api_failure(self, mock_mediakit, mock_cosyvoice):
+        """MediaKit 提交失败."""
         from app.services.lipsync_service import LipsyncService
         from app.services.mediakit_client import MediaKitError
 
         mock_mediakit.submit_lipsync.side_effect = MediaKitError("API 调用失败", code="SubmitFailed")
 
         mock_db = MagicMock()
-        svc = LipsyncService(mock_db, client=mock_mediakit)
+        svc = LipsyncService(mock_db, client=mock_mediakit, cosyvoice_service=mock_cosyvoice)
 
         with pytest.raises(MediaKitError, match="API 调用失败"):
             svc.create_job(
                 user_id="user-1",
                 video_url="https://example.com/video.mp4",
-                audio_url="https://example.com/audio.mp3",
+                voice_id="longxiaochun_v3",
+                script_text="测试文本",
             )
 
     def test_get_job_delegates_to_db(self, mock_mediakit, mock_cosyvoice):
@@ -425,284 +399,78 @@ class TestLipsyncServiceUnit:
         assert result.status == "completed"
 
     def test_create_job_stores_tts_audio_url(self, mock_mediakit, mock_cosyvoice):
-        """v4: TTS 模式下 create_job 返回 tts_processing 状态，audio_url 尚未设置（由 Celery 任务处理）."""
+        """#1809: 验证 job 的 audio_url 来自 TTS 合成结果."""
         from app.services.lipsync_service import LipsyncService
 
         mock_db = MagicMock()
-        mock_repo = MagicMock()
-        mock_repo.get.return_value = None
+        mock_db.add = MagicMock()
+        mock_db.flush = MagicMock()
+        mock_db.commit = MagicMock()
+        mock_db.refresh = MagicMock()
 
-        with patch(
-            "app.services.lipsync_service.tts_synthesize_and_submit"
-        ) as mock_task:
-            mock_task.apply_async.return_value = MagicMock(id="celery-task-789")
+        svc = LipsyncService(mock_db, client=mock_mediakit, cosyvoice_service=mock_cosyvoice)
 
-            svc = LipsyncService(
-                mock_db,
-                client=mock_mediakit,
-                voice_clone_repo=mock_repo,
-            )
-            job = svc.create_job(
-                user_id="user-1",
-                video_url="https://example.com/video.mp4",
-                voice_id="my-clone-voice",
-                script_text="这是一段测试文本",
-            )
-
-        # TTS 模式下 create_job 返回 tts_processing 状态
-        assert job.status == "tts_processing"
-        # audio_url 尚未设置（由 Celery 任务异步处理），模型默认为空字符串
-        assert not job.audio_url
-        mock_task.apply_async.assert_called_once()
-
-    def test_create_job_direct_audio_skips_tts(self, mock_mediakit, mock_cosyvoice):
-        """v3: 直接音频模式（传 audio_url）不触发 TTS，原样把 audio_url 提交 MediaKit."""
-        from app.services.lipsync_service import LipsyncService
-
-        mock_db = MagicMock()
-        svc = LipsyncService(
-            mock_db,
-            client=mock_mediakit,
-            cosyvoice_service=mock_cosyvoice,
-            voice_clone_repo=MagicMock(),
-        )
         job = svc.create_job(
             user_id="user-1",
             video_url="https://example.com/video.mp4",
-            audio_url="https://example.com/direct-audio.mp3",
+            voice_id="my-clone-voice",
+            script_text="这是一段测试文本",
         )
 
-        mock_cosyvoice.submit_synthesize_task.assert_not_called()
-        call_kwargs = mock_mediakit.submit_lipsync.call_args
-        assert call_kwargs.kwargs["audio_url"] == "https://example.com/direct-audio.mp3"
-        assert job.audio_url == "https://example.com/direct-audio.mp3"
+        # job.audio_url 应该是 TTS 返回的 URL
+        assert job.audio_url == "https://oss.example.com/tts-output.mp3"
 
 
 class TestErrorHandling:
-    """v3: 音色解析与错误码在 service 层处理，路由层做 HTTP 状态码映射."""
+    """#1809 补充：错误返回 400 而非 500."""
 
-    def test_voice_id_resolve_forbidden(self, mock_mediakit, mock_cosyvoice):
-        """v3: 克隆音色属于他人时 service._resolve_voice_id 抛 VoiceForbidden（路由映射 403）."""
-        from app.services.lipsync_service import LipsyncService
-        from app.services.mediakit_client import MediaKitError
+    def test_voice_id_resolve_failure_returns_400(self, mock_mediakit, mock_cosyvoice):
+        """voice_clone_repo 查询异常时返回 400 而非 500."""
+        from app.api.routes.lipsync import _resolve_voice_id
+        from fastapi import HTTPException
 
-        mock_db = MagicMock()
         mock_repo = MagicMock()
-        other_profile = MagicMock()
-        other_profile.user_id = "user-other"
-        other_profile.voice_id = "cv-voice-1"
-        mock_repo.get.return_value = other_profile
+        mock_repo.get.side_effect = Exception("DB connection error")
 
-        svc = LipsyncService(
-            mock_db,
-            client=mock_mediakit,
-            cosyvoice_service=mock_cosyvoice,
-            voice_clone_repo=mock_repo,
-        )
+        with pytest.raises(HTTPException) as exc_info:
+            _resolve_voice_id("bad-voice-id", "user-1", mock_repo)
+        assert exc_info.value.status_code == 400
+        assert "voice_id" in str(exc_info.value.detail)
 
-        with pytest.raises(MediaKitError) as exc_info:
-            svc.create_job(
-                user_id="user-1",
-                video_url="https://example.com/video.mp4",
-                voice_id="clone-profile-id",
-                script_text="测试",
-            )
-        assert exc_info.value.code == "VoiceForbidden"
-        mock_mediakit.submit_lipsync.assert_not_called()
-
-    def test_voice_id_resolve_not_ready(self, mock_mediakit, mock_cosyvoice):
-        """v3: 克隆音色尚未生成 voice_id 时抛 VoiceNotReady（路由映射 400）."""
-        from app.services.lipsync_service import LipsyncService
-        from app.services.mediakit_client import MediaKitError
-
-        mock_db = MagicMock()
-        mock_repo = MagicMock()
-        profile = MagicMock()
-        profile.user_id = "user-1"
-        profile.voice_id = ""  # 克隆未完成
-        mock_repo.get.return_value = profile
-
-        svc = LipsyncService(
-            mock_db,
-            client=mock_mediakit,
-            cosyvoice_service=mock_cosyvoice,
-            voice_clone_repo=mock_repo,
-        )
-
-        with pytest.raises(MediaKitError) as exc_info:
-            svc.create_job(
-                user_id="user-1",
-                video_url="https://example.com/video.mp4",
-                voice_id="clone-profile-id",
-                script_text="测试",
-            )
-        assert exc_info.value.code == "VoiceNotReady"
-
-    def test_tts_value_error_mapped_to_invalid_param(self, mock_mediakit):
-        """v4: TTS 模式下 create_job 不再同步调用 CosyVoice，
-        而是 dispatch Celery 任务。ValueError 由 Celery 任务内部处理。"""
+    def test_create_job_value_error_returns_400(self, mock_mediakit):
+        """ValueError（参数无效）返回 400 而非 500."""
         from app.services.lipsync_service import LipsyncService
 
         mock_cosyvoice = MagicMock()
-        mock_cosyvoice.submit_synthesize_task.side_effect = ValueError("voice_id 为空")
+        mock_cosyvoice.synthesize_speech.side_effect = ValueError("voice_id 为空")
 
         mock_db = MagicMock()
-        mock_repo = MagicMock()
-        mock_repo.get.return_value = None
+        svc = LipsyncService(mock_db, client=mock_mediakit, cosyvoice_service=mock_cosyvoice)
 
-        svc = LipsyncService(
-            mock_db,
-            client=mock_mediakit,
-            voice_clone_repo=mock_repo,
-        )
-
-        with patch(
-            "app.services.lipsync_service.tts_synthesize_and_submit"
-        ) as mock_task:
-            mock_task.apply_async.return_value = MagicMock(id="celery-task-789")
-
-            # TTS 模式下 create_job 不再同步失败
-            job = svc.create_job(
+        # Service 层会 catch CosyVoiceError 但 ValueError 会穿透
+        # 路由层 catch ValueError → 400
+        with pytest.raises(ValueError):
+            svc.create_job(
                 user_id="user-1",
                 video_url="https://example.com/video.mp4",
-                voice_id="some-voice",
+                voice_id="",
                 script_text="test",
             )
 
-        # 确认返回 tts_processing 状态
-        assert job.status == "tts_processing"
-        # TTS 合成由 Celery 任务处理，不直接调用 CosyVoice
-        mock_cosyvoice.submit_synthesize_task.assert_not_called()
-        mock_task.apply_async.assert_called_once()
-
-    def test_missing_both_inputs_raises_invalid_input(self, mock_mediakit, mock_cosyvoice):
-        """v3: 既无 audio_url 又无 voice_id+script_text 时抛 InvalidInput（路由映射 400）."""
+    def test_create_job_unexpected_exception_returns_400(self, mock_mediakit):
+        """未预期的异常应被路由层捕获返回 400 而非 500."""
         from app.services.lipsync_service import LipsyncService
-        from app.services.mediakit_client import MediaKitError
+
+        mock_cosyvoice = MagicMock()
+        mock_cosyvoice.synthesize_speech.side_effect = RuntimeError("unexpected")
 
         mock_db = MagicMock()
-        svc = LipsyncService(
-            mock_db,
-            client=mock_mediakit,
-            cosyvoice_service=mock_cosyvoice,
-            voice_clone_repo=MagicMock(),
-        )
+        svc = LipsyncService(mock_db, client=mock_mediakit, cosyvoice_service=mock_cosyvoice)
 
-        with pytest.raises(MediaKitError) as exc_info:
+        with pytest.raises(RuntimeError):
             svc.create_job(
                 user_id="user-1",
                 video_url="https://example.com/video.mp4",
+                voice_id="test-voice",
+                script_text="test",
             )
-        assert exc_info.value.code == "InvalidInput"
-        mock_cosyvoice.submit_synthesize_task.assert_not_called()
-        mock_mediakit.submit_lipsync.assert_not_called()
-
-
-class TestSignMediaUrl403Fix:
-    """#1839 私有桶 OSS URL 重签：MediaKit GPU worker 拉取裸/过期 URL 会 403.
-
-    - 自家 OSS 的裸 public_url / 已过期短预签名 → 重签 7 天长有效期
-    - 外部临时 URL（CosyVoice/MediaKit）→ 原样透传
-    - 签名异常 → 降级原 URL，不阻断
-    """
-
-    OSS_PUBLIC_BASE = "https://xiaoxia-autocut.oss-cn-hangzhou.aliyuncs.com"
-
-    def _svc(self, mock_mediakit, mock_cosyvoice):
-        from app.services.lipsync_service import LipsyncService
-
-        return LipsyncService(
-            MagicMock(),
-            client=mock_mediakit,
-            cosyvoice_service=mock_cosyvoice,
-            voice_clone_repo=MagicMock(),
-        )
-
-    def test_own_oss_unsigned_url_gets_resigned(self, mock_mediakit, mock_cosyvoice):
-        """裸 public_url（不带签名，私有桶匿名 403）必须被重签."""
-        from app.services.lipsync_service import MEDIAKIT_URL_TTL_SECONDS
-
-        svc = self._svc(mock_mediakit, mock_cosyvoice)
-        raw = f"{self.OSS_PUBLIC_BASE}/lipsync-tts/user-1/audio.mp3"
-        signed = raw + "?Expires=999&Signature=abc&OSSAccessKeyId=key"
-
-        storage = MagicMock()
-        storage.public_url = self.OSS_PUBLIC_BASE
-        storage.get_download_url.return_value = signed
-        with patch("app.services.lipsync_service.get_shared_storage_service", return_value=storage):
-            out = svc._sign_media_url(raw)
-
-        assert out == signed
-        storage.get_download_url.assert_called_once_with(raw, expires_seconds=MEDIAKIT_URL_TTL_SECONDS)
-        assert MEDIAKIT_URL_TTL_SECONDS == 7 * 24 * 3600
-
-    def test_own_oss_expired_presign_gets_resigned(self, mock_mediakit, mock_cosyvoice):
-        """已带过期签名的旧预签名 URL 也要抽 key 后重签（不把旧 query 带进新签名）."""
-        svc = self._svc(mock_mediakit, mock_cosyvoice)
-        old = f"{self.OSS_PUBLIC_BASE}/avatar/video.mp4?Expires=111&Signature=old"
-        fresh = f"{self.OSS_PUBLIC_BASE}/avatar/video.mp4?Expires=999&Signature=fresh"
-
-        storage = MagicMock()
-        storage.public_url = self.OSS_PUBLIC_BASE
-        storage.get_download_url.return_value = fresh
-        with patch("app.services.lipsync_service.get_shared_storage_service", return_value=storage):
-            out = svc._sign_media_url(old)
-
-        assert out == fresh
-        # 传给 get_download_url 的是原始完整 URL（内部抽 key），有效期 7 天
-        called_url = storage.get_download_url.call_args.args[0]
-        assert called_url == old
-
-    def test_external_url_passthrough(self, mock_mediakit, mock_cosyvoice):
-        """CosyVoice/MediaKit 外部临时链接不处理，原样透传."""
-        svc = self._svc(mock_mediakit, mock_cosyvoice)
-        external = "https://cv-tts.cosyvoice.aliyuncs.com/output/x.mp3"
-
-        storage = MagicMock()
-        storage.public_url = self.OSS_PUBLIC_BASE
-        with patch("app.services.lipsync_service.get_shared_storage_service", return_value=storage):
-            out = svc._sign_media_url(external)
-
-        assert out == external
-        storage.get_download_url.assert_not_called()
-
-    def test_empty_url_returns_empty(self, mock_mediakit, mock_cosyvoice):
-        svc = self._svc(mock_mediakit, mock_cosyvoice)
-        assert svc._sign_media_url("") == ""
-
-    def test_sign_error_falls_back_to_raw(self, mock_mediakit, mock_cosyvoice):
-        """签名抛异常时降级返回原 URL，不阻断对口型提交."""
-        svc = self._svc(mock_mediakit, mock_cosyvoice)
-        raw = f"{self.OSS_PUBLIC_BASE}/lipsync-tts/u/a.mp3"
-
-        storage = MagicMock()
-        storage.public_url = self.OSS_PUBLIC_BASE
-        storage.get_download_url.side_effect = RuntimeError("oss down")
-        with patch("app.services.lipsync_service.get_shared_storage_service", return_value=storage):
-            out = svc._sign_media_url(raw)
-
-        assert out == raw
-
-    def test_create_job_resigns_oss_urls_before_submit(self, mock_mediakit, mock_cosyvoice):
-        """端到端：create_job 提交 MediaKit 前，自家 OSS 的 video_url 必须是重签后的长签名 URL."""
-        svc = self._svc(mock_mediakit, mock_cosyvoice)
-        raw_video = f"{self.OSS_PUBLIC_BASE}/avatar/person.mp4"
-        signed_video = raw_video + "?Expires=999&Signature=fresh"
-        raw_audio = f"{self.OSS_PUBLIC_BASE}/direct/audio.mp3"
-        signed_audio = raw_audio + "?Expires=999&Signature=afresh"
-
-        storage = MagicMock()
-        storage.public_url = self.OSS_PUBLIC_BASE
-        storage.get_download_url.side_effect = lambda u, expires_seconds=0: (
-            signed_video if u == raw_video else signed_audio
-        )
-        with patch("app.services.lipsync_service.get_shared_storage_service", return_value=storage):
-            svc.create_job(
-                user_id="user-1",
-                video_url=raw_video,
-                audio_url=raw_audio,
-            )
-
-        kw = mock_mediakit.submit_lipsync.call_args.kwargs
-        assert kw["video_url"] == signed_video
-        assert kw["audio_url"] == signed_audio

tests/unit/test_lipsync_speed_optimization.py

@@ -1,623 +0,0 @@
-"""AI 数字人口型视频生成速度优化 — 单元测试.
-
-验证两个优化点：
-1. FFmpeg 编码 preset 从 fast 改为 veryfast（提速 30~50%）
-2. TTS 合成从同步改为 Celery 异步任务（API 响应从 6~35s 降到 <1s）
-
-Issue: lipsync-speed-optimization
-"""
-
-import os
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-os.environ.setdefault("JWT_SECRET_KEY", "dev-secret-key-for-testing")
-
-
-# ═══════════════════════════════════════════════════════════════════════════════
-# 优化1: FFmpeg 编码提速 — preset veryfast
-# ═══════════════════════════════════════════════════════════════════════════════
-
-
-class TestFFmpegPresetOptimization:
-    """验证 FFmpeg 编码命令从 -preset fast 改为 -preset veryfast."""
-
-    def test_preset_is_veryfast(self):
-        """_build_ffmpeg_command 输出必须包含 -preset veryfast."""
-        from app.services.ai_avatar_render_service import AiAvatarRenderService
-
-        svc = AiAvatarRenderService.__new__(AiAvatarRenderService)
-        cmd = svc._build_ffmpeg_command(
-            input_video="https://example.com/video.mp4",
-            b_roll_segments=[],
-            filter_complex="",
-            final_label=None,
-            output_path="/tmp/output.mp4",
-        )
-        assert "-preset veryfast" in cmd, f"期望 -preset veryfast，实际命令: {cmd}"
-
-    def test_preset_veryfast_with_filter(self):
-        """带滤镜场景下也必须使用 veryfast."""
-        from app.services.ai_avatar_render_service import AiAvatarRenderService
-
-        svc = AiAvatarRenderService.__new__(AiAvatarRenderService)
-        cmd = svc._build_ffmpeg_command(
-            input_video="https://example.com/video.mp4",
-            b_roll_segments=[],
-            filter_complex="overlay=0:0",
-            final_label="[v]",
-            output_path="/tmp/output.mp4",
-        )
-        assert "-preset veryfast" in cmd
-        assert "-filter_complex" in cmd
-
-    def test_preset_not_fast(self):
-        """确保不再使用旧的 -preset fast."""
-        from app.services.ai_avatar_render_service import AiAvatarRenderService
-
-        svc = AiAvatarRenderService.__new__(AiAvatarRenderService)
-        cmd = svc._build_ffmpeg_command(
-            input_video="https://example.com/video.mp4",
-            b_roll_segments=[],
-            filter_complex="",
-            final_label=None,
-            output_path="/tmp/output.mp4",
-        )
-        # 确保是 veryfast 而不是 fast
-        assert "-preset veryfast" in cmd
-        # 排除 "fast" 单独出现（veryfast 包含 fast 子串，需精确判断）
-        parts = cmd.split()
-        preset_idx = parts.index("-preset")
-        assert parts[preset_idx + 1] == "veryfast"
-
-
-# ═══════════════════════════════════════════════════════════════════════════════
-# 优化2: TTS 合成 Celery 异步化
-# ═══════════════════════════════════════════════════════════════════════════════
-
-
-def _make_service_with_mocks():
-    """构造 LipsyncService 测试实例及 mock 依赖."""
-    from app.services.lipsync_service import LipsyncService
-
-    db = MagicMock()
-    client = MagicMock()
-    client.is_available = True
-    client.submit_lipsync.return_value = {
-        "success": True,
-        "task_id": "mk-1",
-        "request_id": "req-1",
-    }
-    cosy = MagicMock()
-    cosy.submit_synthesize_task.return_value = {
-        "audio_url": "https://tts/raw.mp3",
-        "request_id": "tts-req",
-        "audio_duration": 3.0,
-    }
-    svc = LipsyncService(db, client=client, cosyvoice_service=cosy, voice_clone_repo=MagicMock())
-    # _resolve_voice_id 默认原样返回（repo.get 返回 None）
-    svc._voice_clone_repo.get.return_value = None
-    return svc, client, cosy
-
-
-class TestCreateJobAsyncTTS:
-    """验证 TTS 模式改为 Celery 异步后的行为."""
-
-    def test_tts_mode_returns_tts_processing_status(self):
-        """TTS 模式下 create_job 立即返回，状态为 tts_processing."""
-        svc, client, cosy = _make_service_with_mocks()
-
-        with patch("app.services.lipsync_service.tts_synthesize_and_submit") as mock_task:
-            mock_task.apply_async = MagicMock()
-
-            job = svc.create_job(
-                user_id="user-1",
-                video_url="https://example.com/video.mp4",
-                voice_id="longxiaochun_v3",
-                script_text="大家好",
-                speed=1.0,
-                emotion="",
-            )
-
-        assert job.status == "tts_processing"
-
-    def test_tts_mode_dispatches_celery_task(self):
-        """TTS 模式必须 dispatch Celery 异步任务."""
-        svc, client, cosy = _make_service_with_mocks()
-
-        with patch("app.services.lipsync_service.tts_synthesize_and_submit") as mock_task:
-            mock_task.apply_async = MagicMock()
-
-            svc.create_job(
-                user_id="user-1",
-                video_url="https://example.com/video.mp4",
-                voice_id="v-1",
-                script_text="测试文本",
-            )
-
-        mock_task.apply_async.assert_called_once()
-        call_kwargs = mock_task.apply_async.call_args
-        args = call_kwargs.kwargs.get("args") or call_kwargs[1].get("args", call_kwargs[0][0] if call_kwargs[0] else ())
-        assert args[1] == "user-1"  # user_id
-        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."""
-        svc, client, cosy = _make_service_with_mocks()
-
-        with patch("app.services.lipsync_service.tts_synthesize_and_submit") as mock_task:
-            mock_task.apply_async = MagicMock(side_effect=Exception("Celery broker down"))
-
-            job = svc.create_job(
-                user_id="user-1",
-                video_url="https://example.com/video.mp4",
-                voice_id="v-1",
-                script_text="测试文本",
-            )
-
-        # job 已创建
-        assert job is not None
-        assert job.status == "tts_processing"
-        # MediaKit 未被调用
-        client.submit_lipsync.assert_not_called()
-
-    def test_tts_mode_voice_validation_still_sync(self):
-        """TTS 模式下音色校验仍在 HTTP 请求中同步执行."""
-        from app.services.mediakit_client import MediaKitError
-
-        svc, client, cosy = _make_service_with_mocks()
-        # 模拟音色属于其他用户
-        other_profile = MagicMock()
-        other_profile.user_id = "user-other"
-        svc._voice_clone_repo.get.return_value = other_profile
-
-        with patch("app.tasks.lipsync_tts.tts_synthesize_and_submit"):
-            with pytest.raises(MediaKitError) as exc:
-                svc.create_job(
-                    user_id="user-1",
-                    video_url="https://example.com/video.mp4",
-                    voice_id="clone-profile-id",
-                    script_text="测试",
-                )
-        assert exc.value.code == "VoiceForbidden"
-
-    def test_tts_mode_missing_input_raises_immediately(self):
-        """缺少 voice_id 或 script_text 时立即报错，不 dispatch Celery 任务."""
-        from app.services.mediakit_client import MediaKitError
-
-        svc, client, cosy = _make_service_with_mocks()
-
-        with patch("app.tasks.lipsync_tts.tts_synthesize_and_submit") as mock_task:
-            mock_task.delay = MagicMock()
-
-            with pytest.raises(MediaKitError) as exc:
-                svc.create_job(
-                    user_id="user-1",
-                    video_url="https://example.com/video.mp4",
-                    # 缺少 voice_id 和 script_text
-                )
-            assert exc.value.code == "InvalidInput"
-
-        # Celery 任务未被 dispatch
-        mock_task.delay.assert_not_called()
-        # TTS 和 MediaKit 均未调用
-        cosy.submit_synthesize_task.assert_not_called()
-        client.submit_lipsync.assert_not_called()
-
-
-class TestCreateJobDirectAudio:
-    """验证直接音频模式不受异步化影响."""
-
-    def test_direct_audio_still_submits_synchronously(self):
-        """直接音频模式仍然同步提交 MediaKit，状态为 submitted."""
-        svc, client, cosy = _make_service_with_mocks()
-
-        with patch("app.tasks.lipsync_tts.tts_synthesize_and_submit") as mock_task:
-            mock_task.delay = MagicMock()
-
-            job = svc.create_job(
-                user_id="user-1",
-                video_url="https://example.com/video.mp4",
-                audio_url="https://example.com/audio.mp3",
-            )
-
-        assert job.status == "submitted"
-        assert job.mediakit_task_id == "mk-1"
-        client.submit_lipsync.assert_called_once()
-        # TTS Celery 任务不应被调用
-        mock_task.delay.assert_not_called()
-
-    def test_direct_audio_skips_tts(self):
-        """直接音频模式不调用 CosyVoice TTS."""
-        svc, client, cosy = _make_service_with_mocks()
-
-        job = svc.create_job(
-            user_id="user-1",
-            video_url="https://example.com/video.mp4",
-            audio_url="https://example.com/audio.mp3",
-        )
-
-        cosy.submit_synthesize_task.assert_not_called()
-        call_kwargs = client.submit_lipsync.call_args
-        assert call_kwargs.kwargs["audio_url"] == "https://example.com/audio.mp3"
-
-
-class TestCancelJobTtsProcessing:
-    """验证 tts_processing 状态的任务可以被取消."""
-
-    def test_cancel_tts_processing(self):
-        """tts_processing 状态的任务可以成功取消."""
-        svc, client, cosy = _make_service_with_mocks()
-
-        mock_job = MagicMock()
-        mock_job.status = "tts_processing"
-        mock_job.id = "job-1"
-        svc.get_job = MagicMock(return_value=mock_job)
-
-        result = svc.cancel_job("job-1", "user-1")
-        assert result.status == "cancelled"
-
-    def test_cancel_pending_still_works(self):
-        """pending 状态仍可取消."""
-        svc, client, cosy = _make_service_with_mocks()
-
-        mock_job = MagicMock()
-        mock_job.status = "pending"
-        mock_job.id = "job-1"
-        svc.get_job = MagicMock(return_value=mock_job)
-
-        result = svc.cancel_job("job-1", "user-1")
-        assert result.status == "cancelled"
-
-    def test_cancel_submitted_still_works(self):
-        """submitted 状态仍可取消."""
-        svc, client, cosy = _make_service_with_mocks()
-
-        mock_job = MagicMock()
-        mock_job.status = "submitted"
-        mock_job.id = "job-1"
-        svc.get_job = MagicMock(return_value=mock_job)
-
-        result = svc.cancel_job("job-1", "user-1")
-        assert result.status == "cancelled"
-
-
-# ═══════════════════════════════════════════════════════════════════════════════
-# lipsync_tts.py — Celery 异步任务单元测试
-# ═══════════════════════════════════════════════════════════════════════════════
-
-import sys
-import types
-
-
-class _FakeQuery:
-    """模拟 SQLAlchemy query.filter().first() 链式调用."""
-
-    def __init__(self, job):
-        self._job = job
-
-    def filter(self, *args, **kwargs):
-        return self
-
-    def first(self):
-        return self._job
-
-
-def _make_fake_job(**kwargs):
-    """构造可 setattr 的 job 记录."""
-    job = MagicMock()
-    job.id = kwargs.get("job_id", "job-1")
-    job.user_id = kwargs.get("user_id", "user-1")
-    job.status = kwargs.get("status", "tts_processing")
-    job.audio_url = kwargs.get("audio_url", "")
-    job.video_url = kwargs.get("video_url", "https://oss/video.mp4")
-    job.mediakit_task_id = kwargs.get("mediakit_task_id", "")
-    job.enable_video_loop = kwargs.get("enable_video_loop", False)
-    job.error_code = ""
-    job.error_message = ""
-    job.submitted_at = None
-    job.updated_at = None
-    return job
-
-
-def _build_session(job):
-    """构造 mock DB session + factory. 返回 (session, factory_patch_ctx_value)."""
-    session = MagicMock()
-    session.query.return_value = _FakeQuery(job)
-    session.commit = MagicMock()
-    session.close = MagicMock()
-    factory = MagicMock(return_value=session)
-    return session, factory
-
-
-def _apply_all_patches(
-    *,
-    job=None,
-    cosyvoice_service=None,
-    cosyvoice_side_effect=None,
-    cosyvoice_error=None,
-    download_bytes=b"AUDIO",
-    download_error=None,
-    storage=None,
-    mk_client=None,
-    mk_submit_return=None,
-    mk_submit_error=None,
-):
-    """统一构造测试需要的 patch 列表.
-
-    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。
-    """
-    # 构造不存在的 database 模块
-    fake_db_mod = types.ModuleType("packages.adapters.sqlalchemy_impl.database")
-    session, factory = _build_session(job)
-    fake_db_mod.SessionLocal = factory
-
-    patches = [
-        patch.dict(sys.modules, {"packages.adapters.sqlalchemy_impl.database": fake_db_mod}),
-        patch(
-            "app.services.lipsync_service.LipsyncService._sign_media_url",
-            side_effect=lambda url: url + "?signed" if url else url,
-        ),
-    ]
-
-    # CosyVoice
-    if cosyvoice_service is not None:
-        cosy_instance = cosyvoice_service
-    else:
-        cosy_instance = MagicMock()
-        if cosyvoice_side_effect is not None:
-            cosy_instance.submit_synthesize_task.side_effect = cosyvoice_side_effect
-        elif cosyvoice_error is not None:
-            cosy_instance.submit_synthesize_task.side_effect = cosyvoice_error
-        else:
-            cosy_instance.submit_synthesize_task.return_value = {"audio_url": "https://tts/raw.mp3"}
-    patches.append(patch("packages.application.cosyvoice_service.CosyVoiceService", return_value=cosy_instance))
-
-    # safe_download_bytes
-    if download_error is not None:
-        patches.append(patch("packages.shared.url_security.safe_download_bytes", side_effect=download_error))
-    else:
-        patches.append(patch("packages.shared.url_security.safe_download_bytes", return_value=download_bytes))
-
-    # Storage
-    if storage is None:
-        storage = MagicMock()
-        storage.public_url = "https://oss.example.com"
-        storage.upload_file.return_value = "https://oss.example.com/tts.mp3"
-    patches.append(patch("packages.shared.storage.get_shared_storage_service", return_value=storage))
-
-    # MediaKit client
-    if mk_client is not None:
-        patches.append(patch("app.services.mediakit_client.get_mediakit_client", return_value=mk_client))
-    else:
-        client = MagicMock()
-        if mk_submit_error is not None:
-            client.submit_lipsync.side_effect = mk_submit_error
-        else:
-            client.submit_lipsync.return_value = mk_submit_return or {"task_id": "mk-1"}
-        patches.append(patch("app.services.mediakit_client.get_mediakit_client", return_value=client))
-
-    return session, patches
-
-
-class TestTtsSynthesizeAndSubmit:
-    """测试 Celery 任务 tts_synthesize_and_submit.run 的所有分支."""
-
-    def test_job_not_found_returns_early(self):
-        """Job 不存在 → 日志报错直接返回，不抛异常."""
-        from app.tasks.lipsync_tts import tts_synthesize_and_submit
-
-        session, patches = _apply_all_patches(job=None)
-        entered = [p.__enter__() for p in patches]
-        try:
-            tts_synthesize_and_submit.run("missing-job", "user-1", "v1", "你好", 1.0, "")
-        finally:
-            for p in reversed(patches):
-                p.__exit__(None, None, None)
-
-        session.commit.assert_not_called()
-        session.close.assert_called_once()
-
-    def test_cancelled_job_skipped(self):
-        """Job 已 cancelled → 跳过不处理，不调用 TTS/MediaKit."""
-        from app.tasks.lipsync_tts import tts_synthesize_and_submit
-
-        job = _make_fake_job(status="cancelled")
-        session, patches = _apply_all_patches(job=job)
-        entered = [p.__enter__() for p in patches]
-        try:
-            tts_synthesize_and_submit.run("job-1", "user-1", "v1", "你好", 1.0, "")
-        finally:
-            for p in reversed(patches):
-                p.__exit__(None, None, None)
-
-        session.commit.assert_not_called()
-        session.close.assert_called_once()
-        assert job.status == "cancelled"
-
-    def test_happy_path_tts_to_mediakit(self):
-        """正常流程：TTS 合成 → 下载 → OSS → 签名 → 提交 MediaKit → submitted."""
-        from app.tasks.lipsync_tts import tts_synthesize_and_submit
-
-        job = _make_fake_job(status="tts_processing")
-        storage = MagicMock()
-        storage.public_url = "https://oss.example.com"
-        storage.upload_file.return_value = "https://oss.example.com/lipsync-tts/u/j.mp3"
-
-        session, patches = _apply_all_patches(
-            job=job,
-            storage=storage,
-            mk_submit_return={"task_id": "mk-999"},
-        )
-        for p in patches:
-            p.__enter__()
-        try:
-            tts_synthesize_and_submit.run("job-1", "user-1", "v1", "你好", 1.0, "")
-        finally:
-            for p in reversed(patches):
-                p.__exit__(None, None, None)
-
-        assert job.audio_url == "https://oss.example.com/lipsync-tts/u/j.mp3"
-        assert job.mediakit_task_id == "mk-999"
-        assert job.status == "submitted"
-        assert job.submitted_at is not None
-        session.close.assert_called_once()
-
-    def test_tts_cosyvoice_error_marks_failed(self):
-        """CosyVoiceError → 标记 failed，error_code=TTSSynthesisFailed."""
-        from app.tasks.lipsync_tts import tts_synthesize_and_submit
-
-        from packages.application.cosyvoice_service import CosyVoiceError
-
-        job = _make_fake_job(status="tts_processing")
-        session, patches = _apply_all_patches(
-            job=job,
-            cosyvoice_error=CosyVoiceError("TTS 服务异常"),
-        )
-        for p in patches:
-            p.__enter__()
-        try:
-            tts_synthesize_and_submit.run("job-1", "user-1", "v1", "你好", 1.0, "")
-        finally:
-            for p in reversed(patches):
-                p.__exit__(None, None, None)
-
-        assert job.status == "failed"
-        assert job.error_code == "TTSSynthesisFailed"
-        assert "TTS 合成失败" in job.error_message
-        session.close.assert_called_once()
-
-    def test_tts_value_error_marks_failed(self):
-        """ValueError → 标记 failed，error_code=TTSInvalidParam."""
-        from app.tasks.lipsync_tts import tts_synthesize_and_submit
-
-        job = _make_fake_job(status="tts_processing")
-        session, patches = _apply_all_patches(
-            job=job,
-            cosyvoice_error=ValueError("speed 参数非法"),
-        )
-        for p in patches:
-            p.__enter__()
-        try:
-            tts_synthesize_and_submit.run("job-1", "user-1", "v1", "你好", 1.0, "")
-        finally:
-            for p in reversed(patches):
-                p.__exit__(None, None, None)
-
-        assert job.status == "failed"
-        assert job.error_code == "TTSInvalidParam"
-        assert "TTS 参数错误" in job.error_message
-        session.close.assert_called_once()
-
-    def test_tts_no_audio_url_marks_failed(self):
-        """TTS 返回空 audio_url → 标记 failed，error_code=TTSNoAudio."""
-        from app.tasks.lipsync_tts import tts_synthesize_and_submit
-
-        job = _make_fake_job(status="tts_processing")
-        cosy = MagicMock()
-        cosy.submit_synthesize_task.return_value = {"audio_url": ""}
-        session, patches = _apply_all_patches(job=job, cosyvoice_service=cosy)
-        for p in patches:
-            p.__enter__()
-        try:
-            tts_synthesize_and_submit.run("job-1", "user-1", "v1", "你好", 1.0, "")
-        finally:
-            for p in reversed(patches):
-                p.__exit__(None, None, None)
-
-        assert job.status == "failed"
-        assert job.error_code == "TTSNoAudio"
-        session.close.assert_called_once()
-
-    def test_oss_upload_failure_falls_back_to_temp_url(self):
-        """OSS 上传失败 → 回退临时 URL，继续提交 MediaKit."""
-        from app.tasks.lipsync_tts import tts_synthesize_and_submit
-
-        job = _make_fake_job(status="tts_processing")
-        storage = MagicMock()
-        storage.public_url = "https://oss.example.com"
-        storage.upload_file.side_effect = Exception("OSS 上传超时")
-        session, patches = _apply_all_patches(
-            job=job,
-            storage=storage,
-            mk_submit_return={"task_id": "mk-77"},
-        )
-        for p in patches:
-            p.__enter__()
-        try:
-            tts_synthesize_and_submit.run("job-1", "user-1", "v1", "你好", 1.0, "")
-        finally:
-            for p in reversed(patches):
-                p.__exit__(None, None, None)
-
-        # 回退到临时 URL
-        assert job.audio_url == "https://tts/raw.mp3"
-        assert job.status == "submitted"
-        assert job.mediakit_task_id == "mk-77"
-        session.close.assert_called_once()
-
-    def test_mediakit_submit_failure_marks_failed(self):
-        """MediaKit 提交失败（MediaKitError）→ 标记 failed."""
-        from app.services.mediakit_client import MediaKitError
-        from app.tasks.lipsync_tts import tts_synthesize_and_submit
-
-        job = _make_fake_job(status="tts_processing")
-        err = MediaKitError("GPU 不可用", code="MediaKitUnavailable")
-        session, patches = _apply_all_patches(
-            job=job,
-            mk_submit_error=err,
-        )
-        for p in patches:
-            p.__enter__()
-        try:
-            tts_synthesize_and_submit.run("job-1", "user-1", "v1", "你好", 1.0, "")
-        finally:
-            for p in reversed(patches):
-                p.__exit__(None, None, None)
-
-        assert job.status == "failed"
-        assert job.error_code == "MediaKitUnavailable"
-        session.close.assert_called_once()
-
-    def test_top_level_exception_marks_async_task_error(self):
-        """顶层意外异常 → except 分支回写 failed，error_code=AsyncTaskError."""
-        from app.tasks.lipsync_tts import tts_synthesize_and_submit
-
-        job = _make_fake_job(status="tts_processing")
-        # 不调用 _apply_all_patches，手动构造所有 patch，让 CosyVoiceService 抛异常
-        fake_db_mod = types.ModuleType("packages.adapters.sqlalchemy_impl.database")
-        session_mock = MagicMock()
-        session_mock.query.return_value = _FakeQuery(job)
-        session_mock.commit = MagicMock()
-        session_mock.close = MagicMock()
-        fake_db_mod.SessionLocal = MagicMock(return_value=session_mock)
-
-        all_patches = [
-            patch.dict(sys.modules, {"packages.adapters.sqlalchemy_impl.database": fake_db_mod}),
-            patch(
-                "app.services.lipsync_service.LipsyncService._sign_media_url",
-                side_effect=lambda url: url + "?signed" if url else url,
-            ),
-            patch(
-                "packages.application.cosyvoice_service.CosyVoiceService",
-                side_effect=RuntimeError("unexpected init failure"),
-            ),
-            patch("packages.shared.url_security.safe_download_bytes", return_value=b"AUDIO"),
-            patch("packages.shared.storage.get_shared_storage_service", return_value=MagicMock()),
-            patch("app.services.mediakit_client.get_mediakit_client", return_value=MagicMock()),
-        ]
-        for p in all_patches:
-            p.__enter__()
-        try:
-            tts_synthesize_and_submit.run("job-1", "user-1", "v1", "你好", 1.0, "")
-        finally:
-            for p in reversed(all_patches):
-                p.__exit__(None, None, None)
-
-        assert job.status == "failed"
-        assert job.error_code == "AsyncTaskError"
-        assert "TTS 异步任务执行异常" in job.error_message
-        session_mock.close.assert_called_once()

tests/unit/test_tts_preview.py

@@ -101,7 +101,6 @@ class TestTTSPreviewEndpoint:
             text="你好世界",
             voice_id="longxiaochun",
             speed=1.0,
-            emotion="",
         )
 
     def test_preview_with_speed(self):
@@ -147,7 +146,6 @@ class TestTTSPreviewEndpoint:
             text="测试",
             voice_id="v1",
             speed=1.5,
-            emotion="",
         )
 
     def test_preview_cosyvoice_error_returns_502(self):
@@ -332,7 +330,6 @@ class TestTTSPreviewEndpoint:
             text="克隆音色测试",
             voice_id="cosyvoice_actual_voice_123",
             speed=1.0,
-            emotion="",
         )
         # Verify repo was queried with the UUID
         mock_clone_repo.get.assert_called_once_with("abc123-uuid-of-profile")
@@ -409,7 +406,6 @@ class TestTTSPreviewEndpoint:
             text="预设音色测试",
             voice_id="longxiaoxia_v3",
             speed=1.0,
-            emotion="",
         )
 
     def test_preview_clone_voice_wrong_user_returns_403(self):