docs(13): create phase 13 plan (7 plans)
This commit is contained in:
@@ -0,0 +1,222 @@
|
||||
---
|
||||
phase: 13
|
||||
plan: 07
|
||||
type: execute
|
||||
wave: 2
|
||||
depends_on:
|
||||
- 13-01
|
||||
- 13-02
|
||||
- 13-03
|
||||
- 13-04
|
||||
- 13-05
|
||||
- 13-06
|
||||
files_modified:
|
||||
- kb_workflow/pipeline/processors/srt.py
|
||||
- tests/test_srt_processor_integration.py
|
||||
autonomous: true
|
||||
requirements:
|
||||
- CONFIG-03
|
||||
must_haves:
|
||||
truths:
|
||||
- "SRTProcessor 支持启用/禁用 LLM 语义分段"
|
||||
- "启用时使用 SemanticSegmentationEngine,禁用时使用规则分段"
|
||||
- "知乎/文章平台继续使用 AnalyzeProcessor,不受影响"
|
||||
artifacts:
|
||||
- path: "kb_workflow/pipeline/processors/srt.py"
|
||||
provides: "SRTProcessor 集成 LLM 分段"
|
||||
min_lines: 350
|
||||
exports: ["SRTProcessor.__init__", "SRTProcessor.process"]
|
||||
- path: "tests/test_srt_processor_integration.py"
|
||||
provides: "SRTProcessor 集成测试"
|
||||
min_lines: 100
|
||||
key_links:
|
||||
- from: "SRTProcessor.__init__"
|
||||
to: "SemanticSegmentationEngine"
|
||||
via: "enable_semantic_segmentation 参数"
|
||||
pattern: "enable_semantic.*segmentation"
|
||||
- from: "SRTProcessor.process"
|
||||
to: "SemanticSegmentationEngine.segment"
|
||||
via: "条件分支选择分段方式"
|
||||
pattern: "if.*semantic.*else.*rule"
|
||||
- from: "Pipeline.run"
|
||||
to: "AnalyzeProcessor/SRTProcessor"
|
||||
via: "平台路由逻辑(保持不变)"
|
||||
pattern: "platform.*bilibili.*srt"
|
||||
---
|
||||
|
||||
<objective>
|
||||
集成 SemanticSegmentationEngine 到 SRTProcessor
|
||||
|
||||
目的:让 SRTProcessor 支持 LLM 语义分段(可选),保持向后兼容
|
||||
输出:更新的 SRTProcessor,集成测试
|
||||
</objective>
|
||||
|
||||
<execution_context>
|
||||
@/home/starmen1265/.claude/get-shit-done/workflows/execute-plan.md
|
||||
@/home/starmen1265/.claude/get-shit-done/templates/summary.md
|
||||
</execution_context>
|
||||
|
||||
<context>
|
||||
@.planning/phases/13-llm/13-CONTEXT.md
|
||||
@.planning/phases/13-llm/13-RESEARCH.md
|
||||
|
||||
# User Decision (Locked)
|
||||
- **SRTProcessor 集成**: 配置开关控制 — 新增 `enable_semantic_segmentation` 参数,True 时用 LLM 分段,False 时保留规则分段作为后备选项
|
||||
- **现有 SemanticSegmenter**: 完全替代 — 新代码完全替代旧代码,SemanticSegmenter 被 SemanticSegmentationEngine 取代
|
||||
|
||||
# Existing Code (from srt.py)
|
||||
```python
|
||||
class SRTProcessor(BaseProcessor):
|
||||
def __init__(
|
||||
self,
|
||||
state_manager: Optional[WorkflowStateManager] = None,
|
||||
enable_correction: bool = True
|
||||
):
|
||||
...
|
||||
self.segmenter = SemanticSegmenter() # 规则分段
|
||||
```
|
||||
</context>
|
||||
|
||||
<tasks>
|
||||
<task type="auto">
|
||||
<name>Task 1: 集成 SemanticSegmentationEngine 到 SRTProcessor</name>
|
||||
<files>kb_workflow/pipeline/processors/srt.py, tests/test_srt_processor_integration.py</files>
|
||||
<action>
|
||||
更新 SRTProcessor,集成 LLM 语义分段:
|
||||
|
||||
1. 在 __init__ 中添加 `enable_semantic_segmentation` 参数:
|
||||
```python
|
||||
def __init__(
|
||||
self,
|
||||
state_manager: Optional[WorkflowStateManager] = None,
|
||||
enable_correction: bool = True,
|
||||
enable_semantic_segmentation: bool = False # 新增参数
|
||||
):
|
||||
super().__init__(state_manager)
|
||||
self.enable_correction = enable_correction
|
||||
self.enable_semantic_segmentation = enable_semantic_segmentation
|
||||
|
||||
# 初始化分段器
|
||||
if enable_semantic_segmentation:
|
||||
try:
|
||||
from kb_workflow.srt.semantic_engine import SemanticSegmentationEngine
|
||||
from kb_workflow.deep_analyzer import SimpleAIClient
|
||||
|
||||
ai_client = SimpleAIClient()
|
||||
if ai_client.api_key:
|
||||
self.segmenter = SemanticSegmentationEngine(ai_client=ai_client)
|
||||
logger.info("Semantic segmentation enabled")
|
||||
else:
|
||||
logger.info("AI API key not configured, using rule-based segmenter")
|
||||
self.segmenter = SemanticSegmenter()
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to initialize semantic engine: {e}, using rule-based segmenter")
|
||||
self.segmenter = SemanticSegmenter()
|
||||
else:
|
||||
self.segmenter = SemanticSegmenter()
|
||||
|
||||
# 初始化纠错器(保持不变)
|
||||
...
|
||||
```
|
||||
|
||||
2. 更新 process() 方法中的分段调用:
|
||||
```python
|
||||
# Step 2: 语义分段
|
||||
logger.info("Segmenting subtitles into paragraphs")
|
||||
if self.enable_semantic_segmentation and isinstance(self.segmenter, SemanticSegmentationEngine):
|
||||
# LLM 语义分段
|
||||
paragraphs = self.segmenter.segment(segments, metadata=metadata)
|
||||
else:
|
||||
# 规则分段
|
||||
paragraphs = self.segmenter.segment(segments)
|
||||
logger.info(f"Generated {len(paragraphs)} paragraphs")
|
||||
```
|
||||
|
||||
3. 更新 _generate_markdown() 以支持带标题的分段:
|
||||
```python
|
||||
def _generate_markdown(
|
||||
self,
|
||||
output_file: Path,
|
||||
metadata: Dict[str, Any],
|
||||
paragraphs: List[str], # 或 List[VideoSegment]
|
||||
tags: List[str]
|
||||
) -> None:
|
||||
...
|
||||
# 如果 paragraphs 包含 VideoSegment(LLM 分段结果)
|
||||
if paragraphs and hasattr(paragraphs[0], 'title'):
|
||||
for seg in paragraphs:
|
||||
if seg.title:
|
||||
content_parts.append(f"## {seg.title}")
|
||||
content_parts.append(seg.content)
|
||||
content_parts.append("")
|
||||
else:
|
||||
# 规则分段(纯文本)
|
||||
content_parts.append("## 内容")
|
||||
content_parts.append("")
|
||||
for para in paragraphs:
|
||||
content_parts.append(para)
|
||||
content_parts.append("")
|
||||
...
|
||||
```
|
||||
|
||||
4. 更新 SRTInput/Output Schema(如果需要):
|
||||
- 考虑是否需要添加 semantic_segmentation_enabled 字段
|
||||
|
||||
5. 创建集成测试:
|
||||
```python
|
||||
# tests/test_srt_processor_integration.py
|
||||
def test_srt_processor_semantic_mode():
|
||||
"""测试 SRTProcessor 语义分段模式"""
|
||||
# mock AI client
|
||||
# enable_semantic_segmentation=True
|
||||
# 验证调用 SemanticSegmentationEngine
|
||||
|
||||
def test_srt_processor_rule_based_mode():
|
||||
"""测试 SRTProcessor 规则分段模式"""
|
||||
# enable_semantic_segmentation=False
|
||||
# 验证使用 SemanticSegmenter
|
||||
|
||||
def test_srt_processor_semantic_fallback():
|
||||
"""测试 AI 不可用时降级到规则分段"""
|
||||
# AI client 无效
|
||||
# 验证降级到 SemanticSegmenter
|
||||
```
|
||||
|
||||
6. 确保 Pipeline 平台路由逻辑不受影响(Phase 12 已实现):
|
||||
- B站视频使用 SRTProcessor
|
||||
- 知乎/文章继续使用 AnalyzeProcessor
|
||||
- 不修改 Pipeline.run() 中的路由逻辑
|
||||
</action>
|
||||
<verify>
|
||||
<automated>pytest tests/test_srt_processor_integration.py::test_srt_processor_semantic_mode -x</automated>
|
||||
</verify>
|
||||
<done>
|
||||
- SRTProcessor 支持 enable_semantic_segmentation 参数
|
||||
- 启用时使用 SemanticSegmentationEngine
|
||||
- 禁用时使用 SemanticSegmenter(向后兼容)
|
||||
- AI 不可用时自动降级到规则分段
|
||||
- _generate_markdown() 支持带标题的分段
|
||||
- 集成测试验证所有场景
|
||||
- 平台路由逻辑不受影响(知乎/文章继续使用 AnalyzeProcessor)
|
||||
</done>
|
||||
</task>
|
||||
</tasks>
|
||||
|
||||
<verification>
|
||||
- pytest tests/test_srt_processor_integration.py -v 全部通过
|
||||
- pytest tests/test_srt_processor.py -v 现有测试不回归
|
||||
- 平台路由逻辑不受影响
|
||||
- 向后兼容(enable_semantic_segmentation=False 时行为不变)
|
||||
</verification>
|
||||
|
||||
<success_criteria>
|
||||
1. SRTProcessor 支持 enable_semantic_segmentation 参数
|
||||
2. 启用时使用 LLM 分段,禁用时使用规则分段
|
||||
3. AI 不可用时自动降级
|
||||
4. 集成测试验证所有场景
|
||||
5. 平台路由逻辑不受影响
|
||||
</success_criteria>
|
||||
|
||||
<output>
|
||||
After completion, create `.planning/phases/13-llm/13-07-SUMMARY.md`
|
||||
</output>
|
||||
Reference in New Issue
Block a user