docs(13-01): update state, roadmap, and requirements

- 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>

.planning/STATE.md

@@ -3,14 +3,14 @@ gsd_state_version: 1.0
 milestone: v1.4
 milestone_name: Zhihu Anti-Crawler
 status: executing
-stopped_at: Completed 13-03-PLAN.md
-last_updated: "2026-03-21T16:26:42.744Z"
+stopped_at: Completed Phase 13 Plan 01 - Video Type Detection
+last_updated: "2026-03-21T16:27:13.803Z"
 last_activity: 2026-03-22 — Phase 13 plan created (7 plans)
 progress:
   total_phases: 15
   completed_phases: 10
   total_plans: 38
-  completed_plans: 33
+  completed_plans: 35
   percent: 0
 ---
 
@@ -73,6 +73,11 @@ v1.6 Phase 13 decisions (from 13-CONTEXT.md):
 - **Pydantic Schema 位置**: `semantic_engine.py` 内
 - [Phase 13]: 确认 semantic_engine.py 已包含内容完整性保护指令（在之前的计划中实现）
 - [Phase 13]: 遵守用户决策：不添加并列结构特殊处理指令
+- [Phase 13]: 视频类型关键词映射 - 使用 VIDEO_TYPE_KEYWORDS 字典定义 5 种类型
+- [Phase 13]: 默认视频类型设置为知识类
+- [Phase 13]: 标题长度验证使用 Pydantic field_validator (5-15字)
+- [Phase 13]: start_index/end_index 表示字符位置(0-based)不是字幕索引(1-based)
+- [Phase 13]: Lazy AI Client 初始化采用 ASRCorrector 模式
 
 ### Technical Context
 
@@ -117,11 +122,12 @@ None.
 | 13 | 04 | 140s (2min) | 1 | 2 | 2026-03-22 |
 | Phase 13 P05 | 2 | 1 tasks | 2 files |
 | Phase 13 P03 | 5min | 1 tasks | 1 files |
+| Phase 13 P01 | 35min | 1 tasks | 4 files |
 
 ## Session Continuity
 
-Last session: 2026-03-21T16:26:42.742Z
-Stopped at: Completed 13-03-PLAN.md
+Last session: 2026-03-21T16:27:13.801Z
+Stopped at: Completed Phase 13 Plan 01 - Video Type Detection
 Resume file: None
 
 **Next step:** Continue with Phase 13 remaining plans (01-03, 05-07)