refactor: 优化 brainstorm 上下文溢出保护文档

- conceptual-planning-agent.md: 34行 → 10行（-71%）
- auto-parallel.md: 42行 → 9行（-79%）
- 消除重复定义，workflow 引用 agent 限制
- 移除冗余的策略列表、自检清单、代码示例
- 保留核心功能：限制数字、简要策略、恢复方法

.claude/agents/conceptual-planning-agent.md

@@ -308,37 +308,14 @@ When analysis is complete, ensure:
 - **Relevance**: Directly addresses user's specified requirements
 - **Actionability**: Provides concrete next steps and recommendations
 
-## Output Size Limits (Context Overflow Prevention)
+## Output Size Limits
 
-**⚠️ CRITICAL**: To prevent API context overflow in brainstorm workflows, enforce these limits:
+**Per-role limits** (prevent context overflow):
+- `analysis.md`: < 3000 words
+- `analysis-*.md`: < 2000 words each (max 5 sub-documents)
+- Total: < 15000 words per role
 
-### Document Size Limits
+**Strategies**: Be concise, use bullet points, reference don't repeat, prioritize top 3-5 items, defer details
-- `analysis.md` (main): **< 3000 words** (~12KB)
-- `analysis-*.md` (sub-docs): **< 2000 words each** (~8KB)
-- Maximum 5 sub-documents per role
-- **Total per-role**: **< 15000 words** (~60KB)
 
-### Strategies for Staying Within Limits
+**If exceeded**: Split essential vs nice-to-have, move extras to `analysis-appendix.md` (counts toward limit), use executive summary style
-1. **Be concise**: Focus on key insights, not exhaustive detail
-2. **Use bullet points**: More efficient than prose paragraphs
-3. **Reference don't repeat**: Use `@filename.md` references instead of duplicating content
-4. **Prioritize**: Include top 3-5 recommendations per section, not all possible ones
-5. **Defer details**: Mark "further analysis needed" for complex areas instead of expanding
-
-### Self-Check Before Output
-```
-Before writing files, verify:
-□ Main analysis.md < 3000 words
-□ Each sub-document < 2000 words
-□ Total sub-documents ≤ 5
-□ No duplicated content across files
-□ References used where appropriate
-```
-
-### If Limit Exceeded
-If analysis naturally exceeds limits:
-1. Split into essential vs nice-to-have content
-2. Move nice-to-have to a separate `analysis-appendix.md` (counts toward 5 sub-doc limit)
-3. Use executive summary style for main document
-4. Note "detailed analysis available on request" for deferred topics
 

.claude/commands/workflow/brainstorm/auto-parallel.md

@@ -428,44 +428,13 @@ CONTEXT_VARS:
 
 ## Context Overflow Protection
 
-**⚠️ IMPORTANT**: Brainstorm workflows can generate substantial content across multiple roles. To prevent API context limit issues:
+**Per-role limits**: See `conceptual-planning-agent.md` (< 3000 words main, < 2000 words sub-docs, max 5 sub-docs)
 
-### Per-Role Output Limits
+**Synthesis protection**: If total analysis > 100KB, synthesis reads only `analysis.md` files (not sub-documents)
-- Each `analysis.md` should be **< 3000 words**
-- Sub-documents (`analysis-*.md`) should be **< 2000 words each**
-- Maximum 5 sub-documents per role
-- Total per-role content: **< 15000 words**
 
-### Synthesis Phase Protection
+**Recovery**: Check logs → reduce scope (--count 2) → use --summary-only → manual synthesis
-Before Phase 3 (synthesis), check total analysis size:
-```javascript
-// Check combined analysis size before synthesis
-const analysisFiles = Glob(".workflow/active/WFS-{session}/.brainstorming/*/analysis*.md");
-let totalSize = 0;
-for (const file of analysisFiles) {
-  totalSize += getFileSize(file);
-}
 
-// If total > 100KB, use summary mode
+**Prevention**: Start with --count 3, use structured topic format, review output sizes before synthesis
-if (totalSize > 100 * 1024) {
-  console.log("⚠️ Large context detected. Using summary mode for synthesis.");
-  // Synthesis will read only analysis.md (index) files, not sub-documents
-  useSummaryMode = true;
-}
-```
-
-### Recovery from Context Overflow
-If API returns empty response or timeout:
-1. **Identify overflow**: Check last request size in logs
-2. **Reduce scope**: Re-run synthesis with fewer roles (use `--count 2`)
-3. **Use summary mode**: Pass `--summary-only` to synthesis command
-4. **Manual synthesis**: Combine key insights from each role's `analysis.md` manually
-
-### Prevention Best Practices
-- Start with `--count 3` (default) before trying more roles
-- Use structured topic format: `"GOAL: [x] SCOPE: [y] CONTEXT: [z]"`
-- Review each role's output size before proceeding to synthesis
-- For complex topics, consider running brainstorm in phases (3 roles at a time)
 
 ## Reference Information