From 2039a45bf05bc5f8ad34bdd200800944c1b708cb Mon Sep 17 00:00:00 2001 From: starmen1265 Date: Fri, 13 Mar 2026 19:11:29 +0800 Subject: [PATCH] docs(03): create ASR processing plan --- .planning/ROADMAP.md | 20 +- .../phases/03-processing-skills/03-01-PLAN.md | 612 ++++++++++++++++++ 2 files changed, 621 insertions(+), 11 deletions(-) create mode 100644 .planning/phases/03-processing-skills/03-01-PLAN.md diff --git a/.planning/ROADMAP.md b/.planning/ROADMAP.md index b8ff5f9..5fbf4e4 100644 --- a/.planning/ROADMAP.md +++ b/.planning/ROADMAP.md @@ -2,7 +2,7 @@ ## Overview -将现有分散的技能模块重构为统一的管道处理系统。从基础设施（状态管理、Schema验证）开始，逐步集成平台技能（B站/知乎）、处理技能（ASR/OCR），最终形成完整的端到端工作流。每个阶段都交付可独立验证的能力，确保长时任务可恢复、可追溯。 +将现有分散的技能模块重构为统一的管道处理系统。从基础设施（状态管理、Schema验证）开始，逐步集成平台技能（B站/知乎）、处理技能（ASR），最终形成完整的端到端工作流。每个阶段都交付可独立验证的能力，确保长时任务可恢复、可追溯。 ## Phases @@ -14,7 +14,7 @@ Decimal phases appear between their surrounding integers in numeric order. - [x] **Phase 1: Foundation** - 状态管理、Schema验证、错误处理、统一配置 - [x] **Phase 2: Platform Skills** - B站/知乎链接解析、元数据提取、内容下载 -- [ ] **Phase 3: Processing Skills** - ASR/OCR集成、多模态内容处理 +- [ ] **Phase 3: Processing Skills** - ASR 集成、视频内容文字提取 - [ ] **Phase 4: Analysis & Orchestration** - 深度分析集成、完整管道编排、端到端验证 ## Phase Details @@ -54,20 +54,18 @@ Plans: - [x] 02-03-PLAN.md — Zhihu Adapter: 问答 + 专栏内容 (PLAT-03) ### Phase 3: Processing Skills -**Goal**: 集成ASR和OCR处理能力，支持视频和图片的多模态内容提取 +**Goal**: 集成 ASR 处理能力，支持视频内容的文字提取（官方字幕优先，无字幕时使用 Whisper.cpp） **Depends on**: Phase 2 **Requirements**: None (平台支持已在Phase 2覆盖) **Success Criteria** (what must be TRUE): 1. B站视频自动下载字幕（优先官方字幕），无字幕时调用语音识别 2. Whisper识别完成后，转录结果保存为结构化JSON（含时间戳） - 3. 视频帧自动提取并OCR识别，文字结果与时间戳关联 - 4. 处理结果自动关联到对应的内容目录 - 5. HF_TOKEN配置时自动启用带说话者分离的Whisper -**Plans**: TBD + 3. 处理结果自动关联到对应的内容目录 + 4. HF_TOKEN配置时自动启用带说话者分离的Whisper +**Plans:** 1 plan Plans: -- [ ] 03-01: B站字幕下载 & Whisper/FunASR 集成 -- [ ] 03-02: OCR 处理集成 +- [ ] 03-01-PLAN.md — ASRProcessor: 官方字幕下载 + Whisper.cpp 集成 + 说话者分离 ### Phase 4: Analysis & Orchestration **Goal**: 集成深度分析能力，完成端到端工作流编排，实现从链接到分析报告的全自动处理 @@ -95,10 +93,10 @@ Phases execute in numeric order: 1 → 2 → 3 → 4 |-------|----------------|--------|-----------| | 1. Foundation | 3/3 | Complete | 01-02, 01-01, 01-03 | | 2. Platform Skills | 3/3 | Complete | 02-01, 02-02, 02-03 | -| 3. Processing Skills | 0/2 | Not started | - | +| 3. Processing Skills | 0/1 | Not started | - | | 4. Analysis & Orchestration | 0/3 | Not started | - | --- *Roadmap created: 2026-03-13* -*Last updated: 2026-03-13 - Phase 2 complete (3/3 plans)* +*Last updated: 2026-03-13 - Phase 3 planned (OCR excluded per user decision)* *Granularity: coarse (4 phases)* diff --git a/.planning/phases/03-processing-skills/03-01-PLAN.md b/.planning/phases/03-processing-skills/03-01-PLAN.md new file mode 100644 index 0000000..dd4638c --- /dev/null +++ b/.planning/phases/03-processing-skills/03-01-PLAN.md @@ -0,0 +1,612 @@ +--- +phase: 03-processing-skills +plan: 01 +type: execute +wave: 1 +depends_on: [] +files_modified: + - kb_pipeline/processors/__init__.py + - kb_pipeline/processors/asr.py + - kb_pipeline/schemas.py + - tests/test_processors/__init__.py + - tests/test_processors/test_asr.py +autonomous: true +requirements: [] # 平台支持已在Phase 2覆盖，ASR是内部处理能力 +user_setup: + - service: whisper.cpp + why: "本地语音识别引擎" + env_vars: [] + dashboard_config: + - task: "安装 whisper.cpp 和下载模型" + location: "git clone https://github.com/ggml-org/whisper.cpp.git ~/whisper.cpp && cd ~/whisper.cpp && make && ./models/download-ggml-model.sh base" + - service: pyannote.audio (可选) + why: "说话者分离功能" + env_vars: + - name: HF_TOKEN + source: "HuggingFace Settings -> Access Tokens" + dashboard_config: + - task: "接受 pyannote 模型用户协议" + location: "https://huggingface.co/pyannote/speaker-diarization-3.1" + +must_haves: + truths: + - "B站视频可以自动下载官方字幕" + - "无官方字幕时自动调用 Whisper.cpp 进行语音识别" + - "HF_TOKEN 配置时自动启用说话者分离" + - "输出包含 txt/srt/json 三种格式" + - "ASR 完成后状态记录到 workflow_state.json" + - "临时音频文件处理后自动清理" + artifacts: + - path: "kb_pipeline/processors/__init__.py" + provides: "处理器模块初始化" + exports: ["ASRProcessor"] + - path: "kb_pipeline/processors/asr.py" + provides: "ASR 处理器实现" + contains: "class ASRProcessor" + min_lines: 150 + - path: "kb_pipeline/schemas.py" + provides: "ASR 输入输出 Schema" + contains: "class ASRInput" + contains: "class ASROutput" + key_links: + - from: "kb_pipeline/processors/asr.py" + to: "kb_pipeline/schemas.py" + via: "from ..schemas import ASRInput, ASROutput" + pattern: "ASRInput|ASROutput" + - from: "kb_pipeline/processors/asr.py" + to: "kb_pipeline/state.py" + via: "WorkflowStateManager" + pattern: "state_manager\\.mark_step" + - from: "kb_pipeline/processors/asr.py" + to: "kb-bilibili-content/bilibili_content.py" + via: "download_subtitle 逻辑复用" + pattern: "download_subtitle|has_subtitle" + - from: "kb_pipeline/processors/asr.py" + to: "kb-whisper/whisper.py" + via: "Whisper.cpp 调用逻辑复用" + pattern: "whisper-cli|convert_to_wav" +--- + + +创建 ASRProcessor 处理器，统一封装 B站官方字幕下载和 Whisper.cpp 语音识别，遵循 Phase 1/2 建立的管道模式。 + +Purpose: 为视频内容提供统一的文字提取入口，优先使用高质量官方字幕，无字幕时自动降级到本地语音识别。 +Output: ASRProcessor 类，支持官方字幕下载、Whisper.cpp 调用、说话者分离、状态记录。 + + + +@/home/starmen1265/.claude/get-shit-done/workflows/execute-plan.md +@/home/starmen1265/.claude/get-shit-done/templates/summary.md + + + +@.planning/PROJECT.md +@.planning/ROADMAP.md +@.planning/STATE.md +@.planning/phases/03-processing-skills/03-CONTEXT.md +@.planning/phases/03-processing-skills/03-RESEARCH.md + +## 现有代码模式 + +### Phase 1 Schema 体系 (kb_pipeline/schemas.py) +```python +class StepInput(BaseModel): + content_id: str + platform: Literal["bilibili", "zhihu"] + +class StepOutput(BaseModel): + success: bool + error_message: Optional[str] = None + completed_at: datetime = Field(default_factory=datetime.now) + +class WorkflowState(BaseModel): + def mark_step_completed(self, step_name: str, output_summary: Optional[str] = None) -> None + def mark_step_failed(self, step_name: str, error_message: str) -> None +``` + +### Phase 2 平台适配器模式 (kb_pipeline/platforms/bilibili.py) +```python +class BilibiliAdapter(PlatformAdapter): + async def fetch_metadata(self, content_id: str, content_type: str) -> Dict[str, Any] + async def fetch_content(self, content_id: str, content_type: str) -> str +``` + +### 现有 ASR 工具 (kb-whisper/whisper.py) +- `convert_to_wav()`: 音频转换逻辑 +- `run_whisper()`: Whisper.cpp 调用 +- `create_workflow_json()`: 标准输出格式 + +### 现有字幕下载 (kb-bilibili-content/bilibili_content.py) +- `download_subtitle()`: B站官方字幕下载和 SRT 转换 +- 返回格式：`{success, has_subtitle, filepath, message}` + + + + + + +From kb_pipeline/schemas.py: +```python +class StepInput(BaseModel): + content_id: str = Field(..., min_length=1) + platform: Literal["bilibili", "zhihu"] = Field(...) + +class StepOutput(BaseModel): + success: bool = Field(...) + error_message: Optional[str] = Field(None) + completed_at: datetime = Field(default_factory=datetime.now) + +class WorkflowState(BaseModel): + def mark_step_completed(self, step_name: str, output_summary: Optional[str] = None) -> None + def mark_step_failed(self, step_name: str, error_message: str) -> None +``` + +From kb_pipeline/state.py: +```python +class WorkflowStateManager: + STATE_FILENAME = "workflow_state.json" + def load(self) -> Optional[WorkflowState] + def save(self, state: WorkflowState) -> None + def get_or_create(self, content_id: str, platform: str, source_url: str) -> WorkflowState +``` + +From kb_pipeline/config.py: +```python +class KBSettings(BaseSettings): + hf_token: SecretStr = Field(default=SecretStr("")) + # 其他配置... +``` + +From kb_pipeline/retry.py: +```python +retry_on_network_error = retry( + stop=stop_after_attempt(3), + wait=wait_exponential(multiplier=1, min=2, max=10), + retry=retry_if_exception_type(NetworkError), +) +``` + + + + + + Task 1: Define ASR Schemas + kb_pipeline/schemas.py, tests/test_processors/test_asr.py + + - Test 1: ASRInput 继承 StepInput，包含 video_path 和 content_type 字段 + - Test 2: ASROutput 继承 StepOutput，包含 tool/has_subtitle/output_files/segments/text/duration_seconds 字段 + - Test 3: ASROutput 的 tool 字段只能是 "subtitle" | "whisper" | "whisper-diarization" + + +在 kb_pipeline/schemas.py 中添加 ASR 专用 Schema： + +1. ASRInput 类（继承 StepInput）： + - video_path: str - 视频文件路径 + - content_type: str = "video" - 内容类型 + +2. ASROutput 类（继承 StepOutput）： + - tool: Literal["subtitle", "whisper", "whisper-diarization"] - 使用的工具 + - has_subtitle: bool - 是否有官方字幕 + - output_files: Dict[str, str] - 输出文件路径 {txt, srt, json} + - segments: List[Dict] - 带时间戳的分段列表 + - text: str - 完整文本 + - duration_seconds: float - 音频时长 + - speakers: Optional[List[str]] - 说话者列表（仅说话者分离时） + +3. 添加必要的 import（List, Dict, Literal, Optional） + +确保 Schema 符合 Phase 1 的 StepInput/StepOutput 继承体系。 + + + pytest tests/test_processors/test_asr.py::test_asr_input_schema -x -v + pytest tests/test_processors/test_asr.py::test_asr_output_schema -x -v + + + - ASRInput 类定义完整，继承 StepInput + - ASROutput 类定义完整，继承 StepOutput + - 两个测试通过 + + + + + Task 2: Create ASRProcessor with subtitle download + kb_pipeline/processors/__init__.py, kb_pipeline/processors/asr.py, tests/test_processors/test_asr.py + + - Test 1: ASRProcessor 初始化成功 + - Test 2: _try_official_subtitle 调用成功时返回 ASROutput (tool="subtitle") + - Test 3: _try_official_subtitle 无字幕时返回 None + - Test 4: process() 方法优先尝试官方字幕 + + +创建 kb_pipeline/processors/ 目录和 ASRProcessor 类： + +1. 创建 kb_pipeline/processors/__init__.py： + ```python + from .asr import ASRProcessor + __all__ = ["ASRProcessor"] + ``` + +2. 创建 kb_pipeline/processors/asr.py： + + ASRProcessor 类结构： + ```python + class ASRProcessor: + STEP_NAME = "asr" + + def __init__(self, state_manager: Optional[WorkflowStateManager] = None): + self.settings = get_settings() + self.state_manager = state_manager + + async def process(self, input_data: ASRInput) -> ASROutput: + """主入口：先尝试官方字幕，无则调用 Whisper""" + # 1. 如果是 B站视频，尝试官方字幕 + # 2. 无官方字幕则调用 Whisper + # 3. 记录状态 + + async def _try_official_subtitle(self, input_data: ASRInput) -> Optional[ASROutput]: + """尝试下载 B站官方字幕""" + # 复用 kb-bilibili-content/bilibili_content.py 的 download_subtitle 逻辑 + # 返回 None 表示无字幕（不是错误） + ``` + +3. _try_official_subtitle 实现： + - 使用 aiohttp 调用 B站 API 获取字幕列表 + - API: https://api.bilibili.com/x/player/pagelist?bvid={bvid} + - API: https://api.bilibili.com/x/player/v2?bvid={bvid}&cid={cid} + - 下载字幕 JSON 并转换为 SRT 格式 + - 同时生成 txt 和 json 输出 + - 参考 kb-bilibili-content/bilibili_content.py 的 download_subtitle 方法 + +4. 关键点： + - 无字幕返回 None（不是抛异常），让流程继续到 Whisper + - 有字幕时返回 ASROutput，tool="subtitle" + - 使用 @retry_on_network_error 装饰器处理网络错误 + +不要实现 Whisper 调用部分（Task 3）。 + + + pytest tests/test_processors/test_asr.py::test_asr_processor_init -x -v + pytest tests/test_processors/test_asr.py::test_official_subtitle_found -x -v + pytest tests/test_processors/test_asr.py::test_official_subtitle_not_found -x -v + + + - ASRProcessor 类创建完成 + - _try_official_subtitle 方法实现 + - 三个测试通过 + + + + + Task 3: Implement Whisper.cpp integration + kb_pipeline/processors/asr.py, tests/test_processors/test_asr.py + + - Test 1: _run_whisper 调用成功返回 ASROutput (tool="whisper") + - Test 2: 临时音频文件处理后自动清理 + - Test 3: Whisper 路径不存在时抛出 RuntimeError + + +在 ASRProcessor 中添加 Whisper.cpp 调用逻辑： + +1. _run_whisper 方法： + ```python + async def _run_whisper(self, input_data: ASRInput) -> ASROutput: + """执行 Whisper.cpp 语音识别""" + # 1. 检查 HF_TOKEN 决定是否启用说话者分离 + # 2. 转换音频格式 + # 3. 调用 whisper-cli + # 4. 清理临时文件 + ``` + +2. 复用 kb-whisper/whisper.py 的核心逻辑： + - get_whisper_cpp_path(): 获取 whisper.cpp 路径 + - convert_to_wav(): 音频转换（ffmpeg 16kHz WAV） + - run_whisper(): 调用 whisper-cli 命令 + +3. 命令构建： + ```python + cmd = [ + os.path.join(whisper_path, 'whisper-cli'), + '-m', os.path.join(whisper_path, 'models', 'ggml-base.bin'), + '-f', audio_path, + '-of', output_file, + '-l', 'zh', + '--output-txt', '--output-srt', '--output-json', + ] + ``` + +4. 临时文件清理： + - 处理完成后删除 *_audio.wav 文件 + - 使用 try/except 静默处理删除失败 + +5. HF_TOKEN 检查： + ```python + hf_token = self.settings.hf_token.get_secret_value() + if hf_token: + return await self._run_whisper_with_diarization(input_data) + else: + return await self._run_whisper_basic(input_data) + ``` + +6. 错误处理： + - whisper.cpp 路径不存在 → RuntimeError + - 模型不存在 → FileNotFoundError + - whisper-cli 执行失败 → RuntimeError + +先实现 _run_whisper_basic，_run_whisper_with_diarization 在 Task 4 实现。 + + + pytest tests/test_processors/test_asr.py::test_whisper_basic -x -v + pytest tests/test_processors/test_asr.py::test_temp_file_cleanup -x -v + pytest tests/test_processors/test_asr.py::test_whisper_path_not_found -x -v + + + - _run_whisper 方法实现完成 + - _run_whisper_basic 实现完成 + - 临时文件清理逻辑正确 + - 三个测试通过 + + + + + Task 4: Implement speaker diarization + kb_pipeline/processors/asr.py, tests/test_processors/test_asr.py + + - Test 1: HF_TOKEN 未配置时使用普通 Whisper + - Test 2: HF_TOKEN 配置时自动启用说话者分离 + - Test 3: 说话者分离结果包含 speaker 字段 + + +在 ASRProcessor 中添加说话者分离支持： + +1. _run_whisper_with_diarization 方法： + ```python + async def _run_whisper_with_diarization(self, input_data: ASRInput) -> ASROutput: + """执行带说话者分离的 Whisper""" + # 1. 先运行普通 Whisper + # 2. 运行 pyannote.audio 说话者分离 + # 3. 合并结果 + ``` + +2. 复用 kb-whisper-diarization/whisper_diarization.py 的逻辑： + - run_diarization(): pyannote.audio 调用 + - assign_speaker(): 为段落分配说话者 + - merge_results(): 合并 Whisper 和说话者分离结果 + +3. pyannote.audio 调用： + ```python + from huggingface_hub import login + from pyannote.audio import Pipeline + + login(token=hf_token) + pipeline = Pipeline.from_pretrained("pyannote/speaker-diarization-3.1") + diarization = pipeline(audio_path) + ``` + +4. 合并逻辑： + - 遍历 Whisper 的每个 segment + - 根据 start/end 时间匹配说话者 + - 在 segment 中添加 speaker 字段 + +5. 输出格式： + - tool: "whisper-diarization" + - speakers: ["SPEAKER_00", "SPEAKER_01", ...] + - 每个 segment 包含 speaker 字段 + +6. 依赖处理： + - 使用 try/except 导入 pyannote.audio + - 导入失败时回退到普通 Whisper + + + pytest tests/test_processors/test_asr.py::test_no_hf_token_uses_basic_whisper -x -v + pytest tests/test_processors/test_asr.py::test_diarization_with_hf_token -x -v + pytest tests/test_processors/test_asr.py::test_diarization_result_has_speaker -x -v + + + - _run_whisper_with_diarization 方法实现 + - HF_TOKEN 自动检测逻辑正确 + - 说话者分离结果格式正确 + - 三个测试通过 + + + + + Task 5: Add state recording + kb_pipeline/processors/asr.py, tests/test_processors/test_asr.py + + - Test 1: ASR 成功时状态记录为 completed + - Test 2: ASR 失败时状态记录为 failed + - Test 3: output_summary 包含 tool 和 segments 数量 + + +在 ASRProcessor.process() 方法中添加状态记录： + +1. 成功时记录： + ```python + if self.state_manager: + state = self.state_manager.load() + if state: + state.mark_step_completed( + self.STEP_NAME, + output_summary=f"tool={result.tool}, segments={len(result.segments)}" + ) + self.state_manager.save(state) + ``` + +2. 失败时记录： + ```python + except Exception as e: + if self.state_manager: + state = self.state_manager.load() + if state: + state.mark_step_failed(self.STEP_NAME, str(e)) + self.state_manager.save(state) + raise + ``` + +3. 状态记录时机： + - 只在所有重试都失败后记录失败（不是每次重试） + - 成功后立即记录 + +4. output_summary 格式： + - "tool=subtitle, segments=120" + - "tool=whisper, segments=85" + - "tool=whisper-diarization, segments=85, speakers=2" + +5. 确保 state_manager 是可选的（None 时不记录状态） + + + pytest tests/test_processors/test_asr.py::test_state_recording_success -x -v + pytest tests/test_processors/test_asr.py::test_state_recording_failure -x -v + pytest tests/test_processors/test_asr.py::test_state_no_manager -x -v + + + - 状态记录逻辑正确 + - output_summary 格式正确 + - state_manager 可选处理正确 + - 三个测试通过 + + + + + Task 6: Create test infrastructure + tests/test_processors/__init__.py, tests/test_processors/conftest.py, tests/test_processors/test_asr.py + +创建测试基础设施： + +1. 创建 tests/test_processors/__init__.py（空文件） + +2. 创建 tests/test_processors/conftest.py： + ```python + import pytest + from pathlib import Path + from unittest.mock import AsyncMock, MagicMock, patch + + @pytest.fixture + def mock_whisper_path(tmp_path): + """Mock whisper.cpp 路径""" + whisper_dir = tmp_path / "whisper.cpp" + whisper_dir.mkdir() + (whisper_dir / "whisper-cli").write_text("") + (whisper_dir / "models").mkdir() + (whisper_dir / "models" / "ggml-base.bin").write_text("") + return str(whisper_dir) + + @pytest.fixture + def mock_bilibili_api(): + """Mock B站 API 响应""" + with patch("aiohttp.ClientSession.get") as mock_get: + yield mock_get + + @pytest.fixture + def sample_video(tmp_path): + """创建测试视频文件""" + video_path = tmp_path / "test_video.mp4" + video_path.write_text("fake video content") + return str(video_path) + + @pytest.fixture + def sample_subtitle_response(): + """B站字幕 API 响应示例""" + return { + "data": { + "subtitle": { + "list": [{ + "lan": "ai-zh", + "lan_doc": "中文（自动生成）", + "subtitle_url": "//example.com/subtitle.json" + }] + } + } + } + ``` + +3. 创建 tests/test_processors/test_asr.py 骨架： + - 包含所有测试用例的占位符 + - 每个测试使用 pytest.raises 或 assert 验证 + +4. 测试文件结构： + ```python + # Schema tests + def test_asr_input_schema(): ... + def test_asr_output_schema(): ... + + # Processor tests + def test_asr_processor_init(): ... + def test_official_subtitle_found(): ... + def test_official_subtitle_not_found(): ... + def test_whisper_basic(): ... + def test_temp_file_cleanup(): ... + def test_whisper_path_not_found(): ... + def test_no_hf_token_uses_basic_whisper(): ... + def test_diarization_with_hf_token(): ... + def test_diarization_result_has_speaker(): ... + def test_state_recording_success(): ... + def test_state_recording_failure(): ... + def test_state_no_manager(): ... + ``` + +使用 unittest.mock 来模拟外部依赖（aiohttp、subprocess、whisper.cpp）。 + + + pytest tests/test_processors/test_asr.py --collect-only | grep "test_" | wc -l + + + - tests/test_processors/ 目录创建完成 + - conftest.py 包含所有 fixtures + - test_asr.py 包含所有测试用例骨架 + - 测试数量 >= 13 个 + + + + + + +## Phase Verification + +完成所有任务后，验证以下条件： + +1. **Schema 验证** + ```bash + pytest tests/test_processors/test_asr.py::test_asr_input_schema tests/test_processors/test_asr.py::test_asr_output_schema -v + ``` + +2. **官方字幕下载** + ```bash + pytest tests/test_processors/test_asr.py::test_official_subtitle_found tests/test_processors/test_asr.py::test_official_subtitle_not_found -v + ``` + +3. **Whisper 集成** + ```bash + pytest tests/test_processors/test_asr.py::test_whisper_basic tests/test_processors/test_asr.py::test_temp_file_cleanup -v + ``` + +4. **说话者分离** + ```bash + pytest tests/test_processors/test_asr.py::test_diarization_with_hf_token tests/test_processors/test_asr.py::test_diarization_result_has_speaker -v + ``` + +5. **状态记录** + ```bash + pytest tests/test_processors/test_asr.py::test_state_recording_success tests/test_processors/test_asr.py::test_state_recording_failure -v + ``` + +6. **完整测试套件** + ```bash + pytest tests/test_processors/test_asr.py -v + ``` + + + +1. ASRProcessor 类可被实例化和调用 +2. B站视频可以自动下载官方字幕（优先策略） +3. 无官方字幕时自动调用 Whisper.cpp 进行语音识别 +4. HF_TOKEN 配置时自动启用说话者分离 +5. 输出包含 txt/srt/json 三种格式 +6. ASR 完成后状态正确记录到 workflow_state.json +7. 临时音频文件处理后自动清理 +8. 所有测试通过（>= 13 个测试） + + + +After completion, create `.planning/phases/03-processing-skills/03-01-SUMMARY.md` +