docs: create roadmap (4 phases)

This commit is contained in:
2026-03-13 16:06:47 +08:00
parent ab952f4c69
commit 2ed555ccc2
3 changed files with 172 additions and 3 deletions
+3 -3
View File
@@ -81,13 +81,13 @@ Which phases cover which requirements. Updated during roadmap creation.
| PLAT-01 | Phase 2 | Pending |
| PLAT-02 | Phase 2 | Pending |
| PLAT-03 | Phase 2 | Pending |
| MNT-01 | Phase 5 | Pending |
| MNT-01 | Phase 4 | Pending |
**Coverage:**
- v1 requirements: 12 total
- Mapped to phases: 12
- Unmapped: 0 ✓
- Unmapped: 0
---
*Requirements defined: 2026-03-13*
*Last updated: 2026-03-13 after initial definition*
*Last updated: 2026-03-13 after roadmap creation*
+103
View File
@@ -0,0 +1,103 @@
# Roadmap: kb-skills 工作流重构
## 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。
## Phases
**Phase Numbering:**
- Integer phases (1, 2, 3): Planned milestone work
- Decimal phases (2.1, 2.2): Urgent insertions (marked with INSERTED)
Decimal phases appear between their surrounding integers in numeric order.
- [ ] **Phase 1: Foundation** - 状态管理、Schema验证、错误处理、统一配置
- [ ] **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 4: Analysis & Orchestration** - 深度分析集成、完整管道编排、端到端验证
## Phase Details
### Phase 1: Foundation
**Goal**: 建立可靠的基础设施,支持步骤级状态持久化、Schema验证和结构化错误处理
**Depends on**: Nothing (first phase)
**Requirements**: PIPE-01, PIPE-02, PIPE-03, REL-01, REL-02, REL-03, VAL-01, MNT-02, MNT-03
**Success Criteria** (what must be TRUE):
1. 执行任意步骤后,workflow_state.json 正确记录该步骤的完成状态
2. 中断后重新执行,已完成的步骤被跳过,从中断点继续
3. 每个步骤输出通过 Pydantic Schema 验证,格式错误阻止进入下一步
4. 所有环境变量集中在 ~/.kb_env,启动时验证必需变量
5. 错误信息包含步骤名、输入摘要、失败原因、可操作建议
**Plans**: TBD
Plans:
- [ ] 01-01: State Manager - workflow_state.json 管理
- [ ] 01-02: Schema Registry - 统一输入输出格式定义
- [ ] 01-03: Error Handler & Config - 结构化错误处理和统一配置
### Phase 2: Platform Skills
**Goal**: 集成B站和知乎平台的内容获取能力,形成从链接到原始内容的完整流程
**Depends on**: Phase 1
**Requirements**: PLAT-01, PLAT-02, PLAT-03
**Success Criteria** (what must be TRUE):
1. 输入B站视频链接,自动提取元数据(标题、作者、时长等)并保存为结构化JSON
2. 输入B站专栏链接,自动提取文章内容并保存为Markdown
3. 输入知乎问答/专栏链接,自动提取内容和元数据
4. 重复执行同一链接,不产生重复文件(幂等)
5. 403/超时错误触发降级策略,记录失败原因到状态文件
**Plans**: TBD
Plans:
- [ ] 02-01: Link Parser & B站 Metadata 集成
- [ ] 02-02: B站 Content (视频/专栏) 集成
- [ ] 02-03: 知乎 Metadata & Content 集成
### 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
**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
Plans:
- [ ] 03-01: B站字幕下载 & Whisper/FunASR 集成
- [ ] 03-02: OCR 处理集成
### 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
**Depends on**: Phase 3
**Requirements**: MNT-01
**Success Criteria** (what must be TRUE):
1. 输入任意支持的平台链接,自动完成解析→下载→识别→分析全流程
2. 深度分析报告保存到对应内容目录,包含结构化的核心观点和洞察
3. 整个工作流可通过单个命令触发,无需手动干预
4. 新人能通过清晰的模块结构和文档理解代码,在30分钟内定位并修改任意步骤
5. 所有步骤的状态可通过 workflow_state.json 查询
**Plans**: TBD
Plans:
- [ ] 04-01: Deep Analyzer 集成
- [ ] 04-02: Pipeline Engine 完整编排
- [ ] 04-03: 代码结构整理与文档
## Progress
**Execution Order:**
Phases execute in numeric order: 1 → 2 → 3 → 4
| Phase | Plans Complete | Status | Completed |
|-------|----------------|--------|-----------|
| 1. Foundation | 0/3 | Not started | - |
| 2. Platform Skills | 0/3 | Not started | - |
| 3. Processing Skills | 0/2 | Not started | - |
| 4. Analysis & Orchestration | 0/3 | Not started | - |
---
*Roadmap created: 2026-03-13*
*Granularity: coarse (4 phases)*
+66
View File
@@ -0,0 +1,66 @@
# Project State
## Project Reference
See: .planning/PROJECT.md (updated 2026-03-13)
**Core value:** 可靠、可维护的处理管道 - 每个步骤独立、可验证、可恢复
**Current focus:** Phase 1 - Foundation
## Current Position
Phase: 1 of 4 (Foundation)
Plan: 0 of 3 in current phase
Status: Ready to plan
Last activity: 2026-03-13 — Roadmap created, phases defined
Progress: [░░░░░░░░░░] 0%
## Performance Metrics
**Velocity:**
- Total plans completed: 0
- Average duration: - min
- Total execution time: 0.0 hours
**By Phase:**
| Phase | Plans | Total | Avg/Plan |
|-------|-------|-------|----------|
| 1. Foundation | 0 | - | - |
| 2. Platform Skills | 0 | - | - |
| 3. Processing Skills | 0 | - | - |
| 4. Analysis & Orchestration | 0 | - | - |
**Recent Trend:**
- Last 5 plans: -
- Trend: -
*Updated after each plan completion*
## Accumulated Context
### Decisions
Decisions are logged in PROJECT.md Key Decisions table.
Recent decisions affecting current work:
- [Roadmap]: 采用4阶段结构(coarse粒度),合并Processing和Analysis相关需求
### Pending Todos
[From .planning/todos/pending/ — ideas captured during sessions]
None yet.
### Blockers/Concerns
[Issues that affect future work]
None yet.
## Session Continuity
Last session: 2026-03-13
Stopped at: Roadmap creation complete, ready for Phase 1 planning
Resume file: None