starmen1265/kb-skills
Archived
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix/crawler-proxy-config #42

Merged
starmen1265 merged 74 commits from fix/crawler-proxy-config into main 2026-03-24 00:21:02 +08:00
Conversation 0 Commits 74 Files Changed 70
+17347 -615
starmen1265 commented 2026-03-23 23:29:08 +08:00
Owner
Copy Link
Copy Source
No description provided.
starmen1265 added 73 commits 2026-03-23 23:29:09 +08:00
docs: start milestone v1.6 语义分段改进 cf858027d4
docs: complete v1.6 semantic segmentation research 440c885448
docs: define milestone v1.6 requirements (30 requirements) 6279ab4268
docs: create milestone v1.6 roadmap (3 phases, 30 requirements) ea2d6e4740
docs(13): capture phase context 6ae74f423d
docs(state): record phase 13 context session eecaccf288
docs(13): research phase 13 LLM semantic segmentation da4b2d563a
docs(13): create phase 13 plan (7 plans) 2bcaf05d52
docs(state): record phase 13 planning complete 47cd84b30a
test(13-01): add failing tests for video type detection 9862da7085 
- 创建 conftest.py 共享 fixtures（MockAIClient, sample_segments）
- 创建 test_semantic_engine.py 包含 8 个测试用例
  - test_video_type_detection_from_title: 测试从标题推断类型
  - test_video_type_detection_from_category: 测试从分类推断类型
  - test_video_type_fallback_to_default: 测试默认类型回退
  - test_video_type_in_prompt: 测试类型出现在 Prompt 中
  - test_prompt_format: 测试 Prompt 格式
  - test_video_segment_model: 测试 VideoSegment 模型
  - test_segmentation_result_model: 测试 SegmentationResult 模型
  - test_model_validation: 测试字段验证

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
feat(13-04): 实现主题标题生成功能 8c2b3e079a 
实现 VideoSegment.title 字段和验证，Prompt 中的标题生成指令。

功能：
- VideoSegment.title: Optional[str] 字段
- @field_validator 验证标题长度（不超过 15 字）
- SEGMENTATION_PROMPT 包含标题生成指令
- LLM 自主判断是否需要标题（主题/章节有标题，论点/观点无标题）
- 测试验证标题生成和省略

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
feat(13-01): implement video type detection and Pydantic models 00319f523f 
- 创建 SemanticSegmentationEngine 类
- 实现 VideoSegment 和 SegmentationResult Pydantic 模型
  - VideoSegment: title(可选), content(必填), start_index, end_index
  - SegmentationResult: video_type, segments[], actual_segment_count
  - 添加标题长度验证器（5-15字）
- 实现 _infer_video_type() 方法
  - 从元数据推断视频类型（知识类/故事类/访谈类/新闻类/vlog）
  - 支持从 title, category, tags 推断
  - 默认类型为"知识类"
- 实现 _build_prompt() 方法
  - 包含视频类型信息
  - 包含完整的分段要求（数量控制、句边界保护、标题生成等）
  - 包含 JSON 输出格式规范
- 添加 extract_json_from_llm_response() 工具函数
- 添加 AIClientProtocol 协议定义
- 添加 deferred-items.md 记录超出范围的测试

所有计划 13-01 测试通过（10个测试）

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(13-04): complete plan summary and state updates 321b097492 
- Create 13-04-SUMMARY.md with execution details
- Update STATE.md with position and performance metrics
- Update ROADMAP.md with plan progress (1/7 complete)
- Mark TITLE-01, TITLE-02, TITLE-03 requirements complete

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
feat(13-05): 实现中文句边界检测指令 759503f48a 
更新 SEGMENTATION_PROMPT，增强句边界检测：
- 列举所有中文句末标点（。？！……）
- 强调「自然停顿处」和「语义停顿」
- 说明「不仅依赖标点符号」

添加测试验证句边界检测效果：
- test_chinese_sentence_boundary_punctuations
- test_prompt_emphasizes_semantic_pause
- test_prompt_not_only_punctuation
- test_sentence_boundary_in_segmentation

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
test(13-03): add content completeness protection tests adc1aa3b1d 
- 添加 TestSentenceBoundaryProtection 测试类（COMP-01）
  - test_sentence_boundary_protection: 验证分段边界在标点符号后
  - test_sentence_boundary_in_prompt: 验证 Prompt 包含句边界指令

- 添加 TestArgumentCompleteness 测试类（COMP-02）
  - test_argument_completeness: 验证论点结构完整性
  - test_argument_completeness_in_prompt: 验证 Prompt 包含论点完整性指令

- 添加 TestParallelStructurePreservation 测试类（COMP-03）
  - test_parallel_structure_preserved: 验证并列结构不被错误拆分
  - test_no_special_handling_for_parallel_in_prompt: 验证遵守用户决策（不特别指定并列结构处理）

所有测试通过（29/29），semantic_engine.py 已包含所需的内容完整性保护指令：
- 第 337 行：保持句子完整性，列举所有中文句末标点（。？！……）
- 第 340 行：保持论点完整性，不在前提-结论结构中间截断
- 不包含并列结构特殊处理（符合用户决策）

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(13-05): complete Chinese sentence boundary detection plan 9a34b7df5a 
- Created SUMMARY.md for plan 13-05
- Updated STATE.md with progress and metrics
- Updated ROADMAP.md with plan progress
- Marked requirements SENT-01, SENT-02, SENT-03 as complete
- Duration: 2 minutes, 1 task completed

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(13-03): complete content completeness protection plan 9dbb1a7026 
- 创建 SUMMARY.md：内容完整性保护功能已完成
- 更新 STATE.md：进度 87% (33/38 plans)
- 更新 ROADMAP.md：Phase 13 进展中（3/7 summaries）
- 标记需求完成：COMP-01, COMP-02, COMP-03

完成内容：
- 添加内容完整性保护测试（6 个测试方法）
- 验证 SEGMENTATION_PROMPT 包含句边界和论点完整性指令
- 确认不包含并列结构特殊处理（符合用户决策）
- 所有 29 个测试通过

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(13-03): add self-check to SUMMARY.md fc1f457a7f
docs(13-01): complete plan summary e9c60e0704 
- 创建 13-01-SUMMARY.md 记录计划执行结果
- 记录 2 个 TDD 提交（RED + GREEN）
- 记录 3 个偏差（标题验证、Prompt 扩展、中文句边界测试）
- 所有测试通过（10个）
- 准备好进入计划 13-02

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(13-01): update state, roadmap, and requirements 20a80fcb04 
- 更新 STATE.md 记录执行指标和决策
- 添加 5 个关键决策到 Accumulated Context
- 更新 ROADMAP.md 进度（计划 13-01 完成）
- 标记 VIDEO-01, VIDEO-02, VIDEO-03 为已完成
- 记录会话信息：完成 Phase 13 Plan 01

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(13-02): complete semantic boundary detection plan 35f8a78d13 
完成计划 13-02 的执行和文档化：

功能验证：
- ✅ SEGMENTATION_PROMPT 包含话题转换检测指令
- ✅ extract_json_from_llm_response() 能处理多种格式
- ✅ _parse_result() 使用 Pydantic 验证 LLM 输出
- ✅ VideoSegment.start_index/end_index 验证 (ge=0)

测试覆盖：
- ✅ TestTopicBoundaryDetection (3 tests)
- ✅ TestJSONExtraction (4 tests)
- ✅ TestPydanticValidationExtended (2 tests)
- ✅ 所有 29 个测试通过

需求完成：
- ✅ BOUND-01: 话题转换点检测
- ✅ BOUND-02: 基于语义分析（非时间/字符）
- ✅ BOUND-03: 话题切换正确创建分段
- ✅ BOUND-04: 单个话题内容完整

文档：
- 创建 13-02-SUMMARY.md
- 更新 STATE.md (进度: 29%, 2/7 plans complete)
- 更新 ROADMAP.md
- 更新 REQUIREMENTS.md (标记 BOUND-* 为完成)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
feat(13-06): implement extensible strategy architecture for segmentation 0d8ed1f22f 
- Define SegmentationStrategy Protocol interface (Plan 13-06)
- Implement UnifiedSegmentationStrategy with unified approach for all video types
- Update SemanticSegmentationEngine to use strategy pattern
- Add comprehensive tests for strategy extensibility (STRAT-01, STRAT-02, STRAT-03)

Key changes:
- SegmentationStrategy Protocol defines the strategy interface
- UnifiedSegmentationStrategy implements unified approach (per user decision)
- SemanticSegmentationEngine now uses strategy injection pattern
- Tests verify strategy protocol, unified strategy, custom strategy injection, and extensibility

The architecture supports future extension (e.g., knowledge-type specific strategies)
while Phase 13 uses the unified strategy approach.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(13-06): complete extensible strategy architecture plan a6c0293c01
feat(13-07): integrate SemanticSegmentationEngine into SRTProcessor ef4a660faa 
- 添加 enable_semantic_segmentation 参数到 SRTProcessor.__init__
- 启用时使用 SemanticSegmentationEngine，禁用时使用 SemanticSegmenter
- AI 不可用时自动降级到规则分段
- 更新 _generate_markdown() 支持带标题的 VideoSegment 输出
- 调整步骤顺序：先加载元数据，再进行语义分段
- 更新 UnifiedSegmentationStrategy.segment() 返回 List[VideoSegment]
- 添加代理方法到 SemanticSegmentationEngine 以保持向后兼容
- 创建全面的集成测试（9 个测试用例）
- 更新现有语义引擎测试以适配新 API

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(13-07): complete SRTProcessor integration plan 548bb35cef 
- Create SUMMARY.md documenting SRTProcessor integration with LLM semantic segmentation
- Update STATE.md with completed plan position and performance metrics
- Update ROADMAP.md marking Phase 13 plans 01-07 as complete

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(phase-13): complete phase execution e445986d6d
docs(14): capture phase context 2dde3a3dc8
docs(state): record phase 14 context session 897ef95a87
docs(14): research phase 14 robustness and cost optimization 6d53ce47d4
docs(14): add validation strategy 3c9859c30d
docs(14): create phase 14 plans (5 plans + wave 0 tests) cefb79d311
docs(14): update ROADMAP with plan list and wave structure 1f51ea1408
docs(14): move plan 04 to wave 2 f8275a9846
docs(14): set nyquist compliant c378a0eb32
test(14-03): add failing tests for SemanticCache b6e923c4a4 
- TestComputeContentHash: 测试内容哈希计算（SHA256）
- TestSemanticCache: 测试缓存读写功能
- 测试覆盖：缓存命中/未命中、版本控制、错误处理、多缓存项

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
feat(14-03): implement SemanticCache for content-based caching baf7c0f521 
- compute_content_hash(): 计算 SHA256 内容哈希
- SemanticCache.get(): 从缓存读取 SegmentationResult
- SemanticCache.set(): 保存 SegmentationResult 到缓存
- 支持版本控制（CACHE_VERSION = '1.0'）
- 缓存存储在 .planning/cache/semantic/ 目录
- 错误容错：缓存失败不影响主流程
- 自动创建缓存目录

遵守用户决策：
- 缓存键: SHA256 内容哈希
- 缓存存储: 本地文件系统
- 缓存 TTL: 永久有效
- 缓存内容: 完整的 SegmentationResult

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
test(14-02): add failing test for parse error retry and fallback 970c13a93b 
- Test JSONDecodeError triggers retry 1 time before fallback
- Test ValidationError directly fallbacks without retry
- Test parse error logs LLM output fragment (first 500 chars)
- Test fallback logs error type and message
- Test retry uses INFO level logging

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(14-03): complete semantic cache implementation plan bf359628fc 
- Created SUMMARY.md with implementation details
- Updated STATE.md with new decisions and session info
- Updated ROADMAP.md progress (1/6 plans complete)
- Marked COST-02 requirement complete

Duration: 1 min (72s)
Tasks: 1 (TDD: RED → GREEN)
Tests: 11 passed

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
test(14-00): add test infrastructure for robustness and cost control 92c300bb21 
- Add comprehensive test suite in test_semantic_robustness.py
  - TestLLMFailureFallback: LLM调用失败自动降级 (ROBUST-01)
  - TestNonRecoverableErrorDetection: 不可恢复错误检测
  - TestRecoverableErrorDetection: 可恢复错误检测
  - TestRetryMechanism: 重试机制测试
  - TestFallbackToRuleBased: 降级到规则分段 (ROBUST-03)
  - TestLoggingBehavior: 日志记录行为 (ROBUST-04)
  - TestParseFailureRetry: 解析失败重试 (ROBUST-02)
  - TestExtractJSON: JSON提取功能

- Update conftest.py with Phase 14 fixtures:
  - Mock AI clients for different failure scenarios
  - Long text samples for chunking tests (COST-01)
  - Cache-related fixtures (COST-02)
  - Long subtitle segments for testing

- Add TestSemanticSegmentationToggle to test_srt_processor.py (COST-03):
  - Test enabling/disabling semantic segmentation
  - Test cache enable/disable functionality
  - Test configuration switches

All tests follow TDD RED state - failing tests for future implementation
docs(14-00): complete test infrastructure plan e4c704a582 
- Create 14-00-SUMMARY.md documenting test infrastructure
- Update STATE.md with position and progress
- Update ROADMAP.md for Phase 14

Summary details:
- 26 tests created/modified covering ROBUST-01 to COST-03
- Test infrastructure ready for Phase 14 implementation plans
- TDD RED state established for unimplemented features
- 18 tests passing (existing functionality)
- 8 tests failing (expected - features not yet implemented)
test(14-01): 实现 LLM 调用的可恢复错误检测和重试逻辑 5c32cfdf69 
- 添加 _is_recoverable_error() 静态方法判断错误类型
- 可恢复错误: ConnectionError, Timeout, HTTPError (429/500/502/503/504)
- 不可恢复错误: 其他 HTTPError (4xx), ValidationError
- 重试逻辑: 仅对可恢复错误重试 1 次，立即重试（无延迟）
- 改进日志记录: 重试用 info 级别，降级用 warning 级别
- 降级时记录具体错误类型和消息

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(14-01): complete LLM call graceful degradation strategy dfbbabceea 
- 添加可恢复错误检测和重试逻辑
- 实现自动降级到规则分段
- 18 个测试全部通过
- 执行时间: 219s

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(14-02): complete parse error retry and fallback plan 83b89d4725
feat(14-05): integrate cache into UnifiedSegmentationStrategy 87a1740cd3 
- Add cache parameter to UnifiedSegmentationStrategy.__init__()
- Add cache logic to segment() method (check before LLM, save after)
- Pass cache parameter through SemanticSegmentationEngine.__init__()
- Implement missing chunking methods (_segment_single_chunk, _segment_multiple_chunks, etc.)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
feat(14-04): 实现长文本分块处理方法 faff7903a4 
- 添加 _split_into_chunks() 方法，按句子边界分割长文本（5000字符阈值）
- 添加 _merge_segment_results() 方法，合并分块结果并修正索引
- 添加 _segment_single_chunk() 方法，处理单个文本块
- 添加 _segment_multiple_chunks() 方法，处理多个文本块（分块）
- 添加 _fallback_chunk() 方法，用于单个分块失败时的降级处理
- 修改 segment() 方法，添加分块判断逻辑（len(content) > 5000）

遵守用户决策：
- 分块阈值: 5000 字符
- 按句子边界分割（。！？\n）
- 直接拼接各分块结果
- start_index/end_index 相对于原文

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
feat(14-05): integrate cache into SRTProcessor bb321d9cd4 
- Add enable_cache parameter to SRTProcessor.__init__()
- Create SemanticCache instance when semantic segmentation is enabled
- Pass cache to UnifiedSegmentationStrategy through SemanticSegmentationEngine
- Add logging for cache status (enabled/disabled)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
test(14-05): fix semantic segmentation toggle tests 537f009934 
- Fix patch path for SimpleAIClient (deep_analyzer not semantic_engine)
- Remove config parameter from SRTProcessor initialization
- Add proper assertions for cache enabled/disabled states
- Import Mock from unittest.mock
- Remove duplicate test functions

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(14-05): create SUMMARY.md for Plan 14-05 88302adb9d 
Summarize the execution of Plan 14-05:
- Completed 3 tasks (integrate cache, integrate SRTProcessor, fix tests)
- 3 atomic commits
- All tests passing (28/28 robustness, 23/23 SRTProcessor)
- Cache integration and configuration toggle working as expected
- Bonus: Implemented chunking methods from Plan 14-04

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
test(14-04): 添加长文本分块处理测试 ee5062ca9c 
- 添加 TestSplitIntoChunks 测试类：测试文本分块功能
- 添加 TestLongTextChunking 测试类：测试长文本自动分块分段
- 添加 TestChunkIndexCorrection 测试类：测试分块索引修正
- 添加 TestChunkFallback 测试类：测试单个分块失败时降级到规则分段

测试覆盖：
- 分块边界条件（空文本、短文本、长文本）
- 句子边界分割（。！？\n）
- 索引修正（start_index/end_index 相对于原文）
- 分块失败降级

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(14-05): update STATE.md for Plan 14-05 completion 50141a5545 
- Update current position to Phase 14 Plan 05 (completed)
- Update progress to 34% (42/44 plans)
- Add Phase 14 Plan 05 decisions to Accumulated Context
- Update performance metrics table with Plan 14-05 data
- Update session continuity information

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(14-05): update ROADMAP.md for Plan 14-05 completion 865d06ba10 
- Mark Plan 14-05 as complete in plans list
- Update progress table: Phase 14 now 5/6 plans complete
- Mark Phase 13 as 7/7 complete (corrected)
- Update Phase 13 completion date to 2026-03-22
- Note Plan 14-04 partially implemented in 14-05

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(14-04): complete long text chunking plan ffc6b85081
fix(14-04): correct Segment constructor parameter 1eacc23c99 
Change Segment(index=1, ...) to Segment(id=1, ...) to match
the actual Segment class definition in parser.py.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(phase-14): complete phase execution db2c1602e5
docs(15): capture phase context f484efb3b8
docs(state): record phase 15 context session 39ee6e1fb8
docs(phase-15): research configuration integration and output compatibility f2038c4676
docs(15): add validation strategy 6ea21ad565
docs(phase-15): create phase 15 plans 405761c6ea
fix(15-00): add <automated> verification commands for Nyquist compliance bc26765d17
test(15-01): add failing test for enable_semantic_segmentation field f2a1847557 
- Test KBSettings has enable_semantic_segmentation field with bool type
- Test default value is True
- Test environment variable override (KB_ENABLE_SEMANTIC_SEGMENTATION)
- Test boolean string parsing (true/false, yes/no, 1/0)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
feat(15-01): add enable_semantic_segmentation field to KBSettings 8303cea018 
- Add enable_semantic_segmentation: bool field with default=True
- Allow override via KB_ENABLE_SEMANTIC_SEGMENTATION env var
- Pydantic automatically parses boolean strings (true/false, yes/no, 1/0)
- Update docstring to document new field

CONFIG-01: LLM segmentation can be enabled/disabled via configuration

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
test(15-00): add test infrastructure placeholders for Phase 15 1c1c88e2cf 
创建了测试基础设施，为后续计划提供测试框架。

## 创建的文件

1. **tests/test_processors/test_srt.py** - SRTProcessor 配置集成测试占位符
   - TestConfigIntegration 测试类
   - 5 个测试占位符（pytest.skip）

2. **tests/test_backward_compat.py** - 向后兼容性测试
   - TestBackwardCompatibility 测试类
   - 部分测试已实现（来自计划 15-01）
   - 部分测试占位符（pytest.skip）

3. **tests/conftest.py** - 添加共享 fixtures
   - temp_env_vars fixture：临时环境变量管理
   - mock_kbsettings fixture：Mock KBSettings 实例
   - 添加 os 模块导入

## 偏离说明

计划要求所有测试都是占位符（pytest.skip），但实际上：
- test_config.py 已由计划 15-01 实现完整测试
- test_backward_compat.py 有部分实现

原因：计划 15-01 在 15-00 之前执行，导致测试不是占位符。

## 验证

- pytest 发现所有新增测试类和测试函数
- 测试文件结构符合项目规范

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(15-01): complete enable_semantic_segmentation config integration plan 2df27e277f
test(15-03): add rule-based segmentation backward compatibility tests 8577571eda 
- test_rule_based_segmentation_unchanged: 验证 enable_semantic_segmentation=False 时使用规则分段器
- test_rule_based_no_llm_calls: 验证规则分段不调用 LLM
- test_rule_based_thresholds_unchanged: 验证规则分段阈值（时间/长度）未改变

Task 1 完成：规则分段向后兼容性验证（CONFIG-02）

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(15-00): record Phase 15 Plan 00 completion 9e33df7154 
更新项目状态和进度：

- 完成 Phase 15 Plan 00（测试基础设施）
- 进度: 92% (44/48 计划完成)
- 执行时长: 94秒
- 任务数: 4
- 文件数: 3

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
test(15-03): add AnalyzeProcessor independence tests 7371c6e8c0 
- test_analyze_processor_unaffected_by_config: 验证 AnalyzeProcessor 不受 enable_semantic_segmentation 配置影响
- test_analyze_processor_normal_initialization: 验证 AnalyzeProcessor 正常初始化
- test_analyze_processor_output_unchanged: 验证 AnalyzeProcessor 输出格式未改变

Task 2 完成：AnalyzeProcessor 独立性验证（CONFIG-03）
现有 test_analyze.py 测试全部通过，未被配置变更破坏

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
test(15-03): add API compatibility tests 5debdd6f36 
- test_existing_api_compatibility: 验证不传参数时使用配置默认值
- test_explicit_false_overrides_config: 验证显式传 False 覆盖配置
- test_migration_path: 验证两种启用语义分段的方式

Task 3 完成：API 调用兼容性验证
所有向后兼容性测试通过（9/9）

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
feat(15-02): integrate KBSettings config for semantic segmentation 5983e95352 
- Modified SRTProcessor to read enable_semantic_segmentation from KBSettings
- Changed constructor parameter default from False to None (None = read from config)
- Added config priority: constructor parameter > KBSettings > default (True)
- Added logging for config status (INFO level)
- Added comprehensive tests for config integration (TestConfigIntegration)
- Added tests for output format compatibility (TestOutputFormatBenefits)
- Fixed MockAIClient to accept disable_reasoning parameter
- All 34 tests passing

Requirements satisfied:
- CONFIG-01: SRTProcessor reads from KBSettings
- CONFIG-02: Disabled config uses rule-based segmentation
- OUTPUT-01: LLM segmentation outputs H2 titles
- OUTPUT-02: title=null skips title output
- OUTPUT-03: Rule-based segmentation outputs "## 内容"

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(15-03): complete backward compatibility verification plan 79c678b48a 
- Created SUMMARY.md: 3 tasks, 9 tests, all passed
- Updated STATE.md: recorded decisions and session info
- Updated ROADMAP.md: phase 15 progress (3/4 summaries)
- Marked CONFIG-02 and CONFIG-03 complete

Backward compatibility verified:
- Rule-based segmentation unchanged (CONFIG-02)
- AnalyzeProcessor independent (CONFIG-03)
- API calls remain compatible
- All 24 tests pass (9 new + 15 existing)

Duration: 3min

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(15-02): complete configuration integration plan 7a1da86851 
- Created SUMMARY.md documenting config integration
- Updated STATE.md with decisions and metrics
- Updated ROADMAP.md progress (3/4 summaries complete)
- Marked requirements OUTPUT-01, OUTPUT-02, OUTPUT-03 complete

Plan 15-02 complete:
- SRTProcessor reads enable_semantic_segmentation from KBSettings
- Config priority: parameter > KBSettings > default (True)
- 34/34 tests passing (9 new tests added)
- Duration: ~15 minutes

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs(phase-15): complete phase execution - output compatibility and configuration integration 5dc8e32924
chore: complete v1.6 milestone - 语义分段改进
PR Test / lint (pull_request) Successful in 2s
Details
cb181c9d9f
starmen1265 added 1 commit 2026-03-24 00:20:35 +08:00
refactor(semantic): 移除语义分段降级功能，LLM失败直接报错
PR Test / lint (pull_request) Successful in 1s
Details
bbc8816d16 
主要变更：
- 移除 _segment_single_chunk() 中的降级逻辑，失败直接抛出 RuntimeError
- 移除 _segment_multiple_chunks() 中的降级逻辑，分块失败直接抛出异常
- 移除 segment() 中 AI 客户端不可用时的降级逻辑，直接报错
- _fallback_chunk() 方法已弃用，调用时直接抛出异常
- VideoSegment 标题长度限制从 15 字增加到 30 字
- 将 ValidationError 从不可恢复错误改为可恢复错误，允许重试
- 更新相关 docstring，将 fallback_segmenter 标记为已弃用

现在 LLM 语义分段失败时会抛出明确的 RuntimeError 异常，
包含失败原因（HTTP 错误、JSON 解析错误等）。

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
starmen1265 scheduled this pull request to auto merge when all checks succeed 2026-03-24 00:20:41 +08:00
starmen1265 merged commit 390d497558 into main 2026-03-24 00:21:02 +08:00
This repo is archived. You cannot comment on pull requests.
Reviewers
No Reviewers
Labels
No items
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
starmen1265
No Assignees
1 Participants
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: starmen1265/kb-skills#42
Delete Branch "fix/crawler-proxy-config"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?