"""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 注意：使用 @shared_task 而非绑定到某个 celery_app 实例， 确保任务能被 Worker 侧 celery_app 正确注册，同时 API 侧 send_task/apply_async 仍可正常调用。 #1845：句子时间戳计算已提取至 packages/domain/sentence_timings.py，本模块保留 _ 开头别名兼容历史导入，但 _compute_sentence_timings/_split_script_into_sentences/ _estimate_sentence_timings_by_chars 等内部函数已复用共享实现，避免重复代码。 """ import io import logging from datetime import datetime, timezone from urllib.parse import urlparse from celery import shared_task # 复用共享的句子时间戳工具（#1845 配音前置） from packages.domain.sentence_timings import compute_sentence_timings as _compute_sentence_timings from packages.domain.sentence_timings import ( probe_audio_duration, ) logger = logging.getLogger(__name__) # MediaKit 预签名 URL 有效期（7天，秒），与 LipsyncService._sign_media_url 保持一致 _MEDIAKIT_URL_TTL_SECONDS = 7 * 24 * 3600 def _sign_media_url(url: str) -> str: """对自家 OSS 私有桶 URL 重签长有效期预签名. - 自家 OSS URL → 重签 7 天有效期 - 外部临时 URL → 原样透传 - 任何异常降级原样返回，不阻断主流程 """ if not url: return 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 url own_host = urlparse(public_base).netloc.lower() host = urlparse(url).netloc.lower() if not own_host or host != own_host: return url signed = storage.get_download_url(url, expires_seconds=_MEDIAKIT_URL_TTL_SECONDS) return signed or url except Exception as exc: # noqa: BLE001 logger.warning("[lipsync_tts] URL 重签失败，原样返回: url_prefix=%s err=%s", url[:80], exc) return url @shared_task( bind=True, name="lipsync_tts.synthesize_and_submit", max_retries=5, # 事务竞态重试3次（job not found）+ TTS偶发错误2次 default_retry_delay=30, autoretry_for=(OSError, ConnectionError), # 网络/连接错误自动重试 retry_backoff=True, retry_backoff_max=30, soft_time_limit=180, time_limit=200, ) 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。保留作为降级路径 （预合成失败 / 旧版前端未传 audio_url 时走此路径）。 """ from app.services.mediakit_client import MediaKitError, get_mediakit_client from sqlalchemy.orm import Session as DBSession from packages.adapters.sqlalchemy_impl.models import LipsyncJobModel from packages.application.cosyvoice_service import CosyVoiceError, CosyVoiceService from packages.shared.url_security import safe_download_bytes # SessionLocal 获取： # - API 容器：app.db.SessionLocal（环境变量完整，导入即建引擎） # - Worker 容器：worker_app.db.SessionLocal（Worker 自己的 settings 初始化引擎） # API 侧没有 worker_app 模块 → ImportError 直接回退； # Worker 侧 app.db 会因缺少 API 专有环境变量抛 pydantic ValidationError， # 此时也要回退到 worker_app.db。 try: from worker_app.db import SessionLocal # type: ignore except Exception: # noqa: BLE001 from app.db import SessionLocal # type: ignore db: DBSession = SessionLocal() try: job = ( db.query(LipsyncJobModel) .filter( LipsyncJobModel.id == job_id, LipsyncJobModel.user_id == user_id, ) .first() ) if job is None: # 事务竞态防御：API 在 commit 前投递了任务，worker 消费时事务尚未提交。 retries = getattr(self.request, "retries", 0) max_retries = 3 if retries < max_retries: backoff = (2**retries) + (retries * 1) # 1s, 3s, 7s logger.warning( "[lipsync_tts] Job not found yet (retry %d/%d, backoff %ds): job_id=%s", retries + 1, max_retries, backoff, job_id, ) self.db.close() raise self.retry(countdown=backoff, max_retries=max_retries) logger.error( "[lipsync_tts] Job not found after %d retries, giving up: job_id=%s", max_retries, 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 logger.info( "[lipsync_tts] 开始 TTS 合成: job_id=%s voice_id=%s text_len=%d speed=%.2f", job_id, voice_id, len(script_text), speed, ) try: cosyvoice = CosyVoiceService() result = cosyvoice.submit_synthesize_task( text=script_text, voice_id=voice_id, speed=speed, emotion=emotion, language="zh", ) 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 TTS 音频到内存（用于 2.5 静音检测；不转存自家 OSS，直接使用 CosyVoice 临时 URL） audio_data: bytes | None = None try: audio_data = safe_download_bytes( temp_url, purpose="lipsync_tts_audio", allowed_mime_types={ "audio/mpeg", "audio/mp3", "audio/wav", "audio/x-wav", # CosyVoice 部分接口返回 audio/x-wav "audio/mp4", "audio/x-m4a", }, timeout=60.0, ) logger.info( "[lipsync_tts] TTS 音频已下载到内存: job_id=%s size=%d", job_id, len(audio_data) if audio_data else 0, ) except Exception as exc: logger.warning( "[lipsync_tts] TTS 音频下载失败，跳过静音检测，直接使用临时 URL 提交: job_id=%s err=%s", job_id, exc, ) # TTS 音频使用 CosyVoice 临时 URL，跳过自家 OSS 转存（加速，步骤⑥） job.audio_url = temp_url logger.info("[lipsync_tts] TTS 音频使用 CosyVoice 临时 URL（跳过 OSS 转存）: job_id=%s", job_id) db.commit() # 2.5 计算精确句子时间戳（基于 TTS 音频静音检测）—— 复用共享工具 try: if not audio_data: logger.warning("[lipsync_tts] 无音频数据，跳过句子时间戳计算: job_id=%s", job_id) else: _audio_duration = probe_audio_duration(audio_data) logger.info( "[lipsync_tts] 音频时长探测: job_id=%s duration=%.2f", job_id, _audio_duration, ) if _audio_duration > 0: _timings = _compute_sentence_timings(audio_data, script_text, _audio_duration) if _timings: job.sentence_timings = _timings logger.info( "[lipsync_tts] 句子时间戳已计算: job_id=%s sentences=%d duration=%.1f", job_id, len(_timings), _audio_duration, ) else: logger.warning("[lipsync_tts] 句子时间戳计算返回空结果: job_id=%s", job_id) else: logger.warning( "[lipsync_tts] ffprobe 未获取到有效时长，跳过句子时间戳: job_id=%s", job_id, ) db.commit() except Exception as _st_err: logger.warning( "[lipsync_tts] 句子时间戳计算失败（不影响主流程）: job_id=%s err=%s", job_id, _st_err, exc_info=True ) # 3. 签名 URL 并提交到 MediaKit（复用模块内 _sign_media_url，避免对 LipsyncService 的耦合） audio_url = _sign_media_url(job.audio_url) video_url = _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) # 三层防御 ③：链式触发 Celery 兜底轮询——MediaKit 提交成功后由 worker # 主动拉取状态到终态，不依赖前端轮询触发的 FastAPI background task # （background task 可能静默失败导致永久卡 running）。 if job.status == "submitted" and job.mediakit_task_id: try: poll_mediakit_status.apply_async( kwargs={"job_id": job_id, "user_id": user_id}, countdown=10, # 10 秒后开始轮询，给 MediaKit 一点处理时间 ) except Exception as exc: # noqa: BLE001 logger.warning("[lipsync_tts] 提交兜底轮询任务失败（不影响主流程）: 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() @shared_task( bind=True, name="lipsync_tts.poll_mediakit_status", max_retries=60, # 最多轮询 60 次 default_retry_delay=10, # 每次间隔 10 秒（总兜底时长 10 分钟） ) def poll_mediakit_status(self, job_id: str, user_id: str): """Celery 兜底轮询：TTS 提交 MediaKit 后，由 worker 主动拉取状态直到终态。 不依赖前端轮询，避免 background task 静默失败导致任务永久卡 running/submitted。 """ from sqlalchemy.orm import Session as DBSession from packages.adapters.sqlalchemy_impl.models import LipsyncJobModel try: from worker_app.db import SessionLocal # type: ignore except Exception: # noqa: BLE001 from app.db import SessionLocal # type: ignore db: DBSession = SessionLocal() try: job = db.query(LipsyncJobModel).filter(LipsyncJobModel.id == job_id, LipsyncJobModel.user_id == user_id).first() if job is None: logger.warning("[lipsync_poll] Job not found: job_id=%s", job_id) return # 已终态，不需要再轮询 if job.status in ("completed", "failed", "cancelled"): return if not job.mediakit_task_id: logger.warning("[lipsync_poll] Job has no mediakit_task_id: job_id=%s status=%s", job_id, job.status) return from app.services.lipsync_service import STATUS_COMPLETED as _SC from app.services.lipsync_service import STATUS_FAILED as _SF from app.services.lipsync_service import LipsyncService from app.services.mediakit_client import MediaKitError, get_mediakit_client client = get_mediakit_client() try: status_data = client.get_task_status(job.mediakit_task_id) except MediaKitError as exc: logger.warning("[lipsync_poll] 拉取 MediaKit 状态失败，将重试: job_id=%s err=%s", job_id, exc) raise self.retry(exc=exc) from exc mk_status = status_data.get("status", "running") if mk_status in ("succeeded", _SC): svc = LipsyncService(db) result = status_data.get("result", {}) job.status = "completed" output_url = result.get("video_url", "") try: job.output_video_url = svc._persist_output_video(output_url, job_id, user_id) except Exception as exc: # noqa: BLE001 logger.warning("[lipsync_poll] 转存 OSS 失败，保留临时 URL: job_id=%s err=%s", job_id, exc) job.output_video_url = output_url job.output_duration = result.get("duration", 0.0) job.completed_at = datetime.now(timezone.utc) job.updated_at = datetime.now(timezone.utc) db.commit() logger.info("[lipsync_poll] 任务完成: job_id=%s", job_id) elif mk_status in ("failed", "error", _SF): error = status_data.get("error", {}) job.status = "failed" 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) job.updated_at = datetime.now(timezone.utc) db.commit() logger.info("[lipsync_poll] 任务失败: job_id=%s err=%s", job_id, job.error_message) else: # 中间状态，更新时间戳，继续重试 job.updated_at = datetime.now(timezone.utc) if isinstance(mk_status, str) and mk_status: job.status = mk_status db.commit() logger.debug("[lipsync_poll] 任务仍在 %s，继续轮询: job_id=%s", mk_status, job_id) raise self.retry() except Exception as exc: logger.exception("[lipsync_poll] 未预期异常: job_id=%s", job_id) try: db.rollback() except Exception: pass raise self.retry(exc=exc) from exc finally: db.close() @shared_task( name="lipsync_tts.persist_output_video", max_retries=2, default_retry_delay=30, ) def persist_output_video_task(job_id: str, user_id: str, temp_url: str): """异步转存对口型输出视频到自家 OSS（步骤⑦ — 将同步阻塞挪到后台，加速前端响应）.""" try: from worker_app.db import SessionLocal # type: ignore except Exception: # noqa: BLE001 from app.db import SessionLocal # type: ignore from packages.adapters.sqlalchemy_impl.models import LipsyncJobModel from packages.shared.storage import get_shared_storage_service db = 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.persist] Job not found: job_id=%s", job_id) return if not temp_url: logger.warning("[lipsync_tts.persist] temp_url 为空，跳过转存: job_id=%s", job_id) 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") final_url = _sign_media_url(permanent_url) if permanent_url else temp_url job.output_video_url = final_url job.updated_at = datetime.now(timezone.utc) db.commit() logger.info("[lipsync_tts.persist] 输出视频已转存 OSS: job_id=%s key=%s", job_id, storage_key) except Exception as exc: logger.warning( "[lipsync_tts.persist] 输出视频转存失败，保留临时 URL: job_id=%s err=%s", job_id, exc, ) except Exception: logger.exception("[lipsync_tts.persist] 未预期异常: job_id=%s", job_id) finally: db.close()