docs: create milestone v1.6 roadmap (3 phases, 30 requirements)
This commit is contained in:
@@ -92,7 +92,7 @@
|
||||
|
||||
## Traceability
|
||||
|
||||
需求与阶段的映射关系（在路线图创建时填充）。
|
||||
需求与阶段的映射关系。
|
||||
|
||||
| Requirement | Phase | Status |
|
||||
|-------------|-------|--------|
|
||||
@@ -131,9 +131,11 @@
|
||||
|
||||
**Coverage:**
|
||||
- v1.6 requirements: 30 total
|
||||
- Mapped to phases: 0 (待路线图创建)
|
||||
- Unmapped: 30 ⚠️
|
||||
- Mapped to phases: 30 (100%) ✓
|
||||
- Phase 13: 18 requirements (60%)
|
||||
- Phase 14: 7 requirements (23%)
|
||||
- Phase 15: 5 requirements (17%)
|
||||
|
||||
---
|
||||
*Requirements defined: 2026-03-21*
|
||||
*Last updated: 2026-03-21 after initial definition*
|
||||
*Last updated: 2026-03-21 after roadmap creation*
|
||||
|
||||
+76
-3
@@ -8,6 +8,7 @@
|
||||
- ✅ **v1.3 Proxy Pool** - Phase 10 (shipped 2026-03-18)
|
||||
- ✅ **v1.4 Zhihu Anti-Crawler** - Phase 11 (shipped 2026-03-18)
|
||||
- ✅ **v1.5 B站字幕简化处理** - Phase 12 (shipped 2026-03-21)
|
||||
- 🔄 **v1.6 语义分段改进** - Phases 13-15 (in progress)
|
||||
|
||||
## Phases
|
||||
|
||||
@@ -148,10 +149,52 @@ Plans:
|
||||
|
||||
---
|
||||
|
||||
## 🔄 v1.6 语义分段改进 (IN PROGRESS)
|
||||
|
||||
**Milestone Goal:** 使用 LLM 实现智能语义分段，识别视频类型并适配分段策略，保持内容完整性
|
||||
|
||||
### Phase 13: 核心 LLM 分段功能
|
||||
**Goal**: 实现基于 LLM 的智能语义分段，识别视频类型并生成主题标题
|
||||
**Depends on**: Phase 12
|
||||
**Requirements**: VIDEO-01, VIDEO-02, VIDEO-03, BOUND-01, BOUND-02, BOUND-03, BOUND-04, COMP-01, COMP-02, COMP-03, TITLE-01, TITLE-02, TITLE-03, SENT-01, SENT-02, SENT-03, STRAT-01, STRAT-02, STRAT-03
|
||||
**Success Criteria** (what must be TRUE):
|
||||
1. 系统能正确识别 B站视频的类型（知识类、故事类等），并根据类型选择分段策略
|
||||
2. 语义分段在主题切换处正确创建边界，不会混入不同话题的内容
|
||||
3. 分段不会在句子中间或论点未完成时截断，保持内容的语义完整性
|
||||
4. 主题/章节分段生成简洁准确的标题，论点/观点分段不加标题
|
||||
5. 不同类型视频使用对应的分段策略，策略可扩展
|
||||
**Plans**: TBD
|
||||
|
||||
### Phase 14: 鲁棒性与成本控制
|
||||
**Goal**: 提高系统稳定性，实现优雅降级和成本优化
|
||||
**Depends on**: Phase 13
|
||||
**Requirements**: ROBUST-01, ROBUST-02, ROBUST-03, ROBUST-04, COST-01, COST-02, COST-03
|
||||
**Success Criteria** (what must be TRUE):
|
||||
1. LLM 调用失败时自动降级到简单规则分段，不影响整体流程
|
||||
2. LLM 响应解析失败时自动重试或降级，有日志记录便于诊断
|
||||
3. AI 不可用时自动使用简单规则分段，保证基本功能可用
|
||||
4. 长视频字幕自动分块处理，避免上下文窗口溢出
|
||||
5. 相同内容使用缓存结果，避免重复 LLM 调用
|
||||
**Plans**: TBD
|
||||
|
||||
### Phase 15: 输出优化与兼容性
|
||||
**Goal**: 优化输出格式，确保向后兼容和可配置性
|
||||
**Depends on**: Phase 14
|
||||
**Requirements**: OUTPUT-01, OUTPUT-02, OUTPUT-03, CONFIG-01, CONFIG-02, CONFIG-03
|
||||
**Success Criteria** (what must be TRUE):
|
||||
1. 主题/章节分段输出带标题的 Markdown 结构，论点/观点分段输出纯文本
|
||||
2. 输出格式与现有 SRTProcessor 兼容，不影响其他平台处理
|
||||
3. LLM 分段功能可通过配置开关启用/禁用
|
||||
4. 向后兼容，禁用时使用简单规则分段，不破坏现有功能
|
||||
5. 知乎/文章平台继续使用 AnalyzeProcessor，不受影响
|
||||
**Plans**: TBD
|
||||
|
||||
---
|
||||
|
||||
## Progress
|
||||
|
||||
**Execution Order:**
|
||||
Phases execute in numeric order: 1 → 2 → ... → 10 → 11 → 12
|
||||
Phases execute in numeric order: 1 → 2 → ... → 12 → 13 → 14 → 15
|
||||
|
||||
| Phase | Milestone | Plans Complete | Status | Completed |
|
||||
|-------|-----------|----------------|--------|-----------|
|
||||
@@ -166,8 +209,38 @@ Phases execute in numeric order: 1 → 2 → ... → 10 → 11 → 12
|
||||
| 9. Pipeline 整合 | v1.2 | 1/1 | Complete | 2026-03-17 |
|
||||
| 10. Proxy Pool | v1.3 | 2/2 | Complete | 2026-03-18 |
|
||||
| 11. Stealth Fingerprinting | v1.4 | 2/2 | Complete | 2026-03-18 |
|
||||
| 12. SRT 简化处理器 | v1.5 | Complete | 2026-03-19 | 2026-03-19 |
|
||||
| 12. SRT 简化处理器 | v1.5 | 2/2 | Complete | 2026-03-21 |
|
||||
| 13. 核心 LLM 分段功能 | v1.6 | 0/0 | Not started | - |
|
||||
| 14. 鲁棒性与成本控制 | v1.6 | 0/0 | Not started | - |
|
||||
| 15. 输出优化与兼容性 | v1.6 | 0/0 | Not started | - |
|
||||
|
||||
---
|
||||
|
||||
*Last updated: 2026-03-19*
|
||||
## Context
|
||||
|
||||
### 技术栈
|
||||
- Python 3.12+
|
||||
- Pydantic v2 (数据验证)
|
||||
- SimpleAIClient (LLM 调用)
|
||||
- 现有 SemanticSegmenter (扩展点)
|
||||
|
||||
### v1.6 关键集成点
|
||||
- **SemanticSegmentationEngine**: 新模块，负责 LLM 调用和语义分析
|
||||
- **SRTProcessor**: 扩展现有处理器，添加 LLM 分支
|
||||
- **Pydantic Schemas**: 严格验证 LLM 输出格式
|
||||
|
||||
### 三层 Fallback 策略
|
||||
1. 直接 JSON 解析（理想情况）
|
||||
2. Markdown 代码块提取（常见情况）
|
||||
3. 启发式均匀分段（保底方案）
|
||||
|
||||
### 需要避免的陷阱
|
||||
- **LLM-1**: 上下文窗口溢出 — 实施分块策略
|
||||
- **LLM-2**: 输出格式不稳定 — 多层 fallback
|
||||
- **LLM-3**: 边界破坏完整性 — 句边界保护
|
||||
- **LLM-4**: 分段不一致性 — 温度控制
|
||||
- **LLM-5**: 成本失控 — 缓存策略
|
||||
|
||||
---
|
||||
|
||||
*Last updated: 2026-03-21*
|
||||
|
||||
+54
-11
@@ -3,11 +3,11 @@ gsd_state_version: 1.0
|
||||
milestone: v1.6
|
||||
milestone_name: 语义分段改进
|
||||
status: in_progress
|
||||
stopped_at: Defining requirements
|
||||
last_updated: "2026-03-21T16:00:00.000Z"
|
||||
last_activity: 2026-03-21 — Milestone v1.6 started
|
||||
stopped_at: Planning Phase 13
|
||||
last_updated: "2026-03-21T16:30:00.000Z"
|
||||
last_activity: 2026-03-21 — Roadmap created for v1.6
|
||||
progress:
|
||||
total_phases: 0
|
||||
total_phases: 3
|
||||
completed_phases: 0
|
||||
total_plans: 0
|
||||
completed_plans: 0
|
||||
@@ -25,12 +25,23 @@ See: .planning/PROJECT.md (updated 2026-03-21)
|
||||
|
||||
## Current Position
|
||||
|
||||
Phase: Not started (defining requirements)
|
||||
Plan: —
|
||||
Status: Defining requirements
|
||||
Last activity: 2026-03-21 — Milestone v1.6 started
|
||||
Phase: Phase 13 - 核心 LLM 分段功能
|
||||
Plan: TBD
|
||||
Status: Planning
|
||||
Last activity: 2026-03-21 — Roadmap created for v1.6
|
||||
|
||||
Progress: [░░░░░░░░░░] 0%
|
||||
Progress: [░░░░░░░░░░] 0% (Phase 13/15)
|
||||
|
||||
### Phase 13 Goal
|
||||
实现基于 LLM 的智能语义分段，识别视频类型并生成主题标题
|
||||
|
||||
### Phase 13 Requirements (18 total)
|
||||
- VIDEO-01, VIDEO-02, VIDEO-03 (视频类型识别)
|
||||
- BOUND-01, BOUND-02, BOUND-03, BOUND-04 (语义边界检测)
|
||||
- COMP-01, COMP-02, COMP-03 (内容完整性保护)
|
||||
- TITLE-01, TITLE-02, TITLE-03 (主题标题生成)
|
||||
- SENT-01, SENT-02, SENT-03 (中文句边界检测)
|
||||
- STRAT-01, STRAT-02, STRAT-03 (分段策略)
|
||||
|
||||
## Accumulated Context
|
||||
|
||||
@@ -51,6 +62,38 @@ v1.6 scope (待验证):
|
||||
- 主题识别与标题 — 主题章节生成标题
|
||||
- 内容完整性 — 避免错误截断话题
|
||||
|
||||
### Technical Context
|
||||
|
||||
**架构集成:**
|
||||
- 扩展现有 `SemanticSegmenter`，保持向后兼容
|
||||
- 新增 `SemanticSegmentationEngine` 模块（`kb_workflow/srt/semantic_engine.py`）
|
||||
- 在 `SRTProcessor` 中添加 LLM 分支（`enable_semantic_segmentation` 参数）
|
||||
|
||||
**技术栈:**
|
||||
- SimpleAIClient（已集成 zhipu/openai/minimax）
|
||||
- Pydantic v2（LLM 响应验证）
|
||||
- 现有 SemanticSegmenter（规则分段保留）
|
||||
|
||||
**数据流:**
|
||||
```
|
||||
SRT Input → Parse Subtitles → Video Type Detection →
|
||||
Semantic Segmentation → Extract Paragraphs → ASR Correction →
|
||||
Deep Analysis
|
||||
```
|
||||
|
||||
### Known Risks
|
||||
|
||||
**高优先级风险:**
|
||||
1. **上下文窗口溢出** — 长视频（>1小时）字幕超10万字符，需分块处理
|
||||
2. **LLM 输出格式不稳定** — 需多层 fallback 策略
|
||||
3. **分段边界破坏完整性** — 需句边界保护机制
|
||||
4. **分段不一致性** — LLM 随机性导致多次运行结果不同
|
||||
5. **成本失控** — 高频 LLM 调用可能导致费用激增
|
||||
|
||||
**缓解策略:**
|
||||
- Phase 13: 实现 Pydantic 验证 + 句边界保护
|
||||
- Phase 14: 实现分块处理 + 缓存 + 温度控制
|
||||
|
||||
### Blockers/Concerns
|
||||
|
||||
None.
|
||||
@@ -58,7 +101,7 @@ None.
|
||||
## Session Continuity
|
||||
|
||||
Last session: 2026-03-21
|
||||
Stopped at: Milestone v1.6 started
|
||||
Stopped at: Roadmap created for v1.6
|
||||
Resume file: None
|
||||
|
||||
**Next step:** Define requirements for semantic segmentation
|
||||
**Next step:** `/gsd:plan-phase 13` - 开始 Phase 13 的详细规划
|
||||
|
||||
Reference in New Issue
Block a user