feat: 添加搜索工具优先级指南，优化CLI工具调用和执行策略

.claude/CLAUDE.md

@@ -24,6 +24,14 @@ Available CLI endpoints are dynamically defined by the config file:
 - **Always use `run_in_background: false`** for Task tool agent calls: `Task({ subagent_type: "xxx", prompt: "...", run_in_background: false })` to ensure synchronous execution and immediate result visibility
 - **TaskOutput usage**: Only use `TaskOutput({ task_id: "xxx", block: false })` + sleep loop to poll completion status. NEVER read intermediate output during agent/CLI execution - wait for final result only
 
+### CLI Tool Calls (ccw cli)
+- **Default: `run_in_background: true`** - Unless otherwise specified, always use background execution for CLI calls:
+  ```
+  Bash({ command: "ccw cli -p '...' --tool gemini", run_in_background: true })
+  ```
+- **After CLI call**: Stop immediately - let CLI execute in background, do NOT
+ poll with TaskOutput
+ 
 ### CLI Analysis Calls
 - **Wait for results**: MUST wait for CLI analysis to complete before taking any write action. Do NOT proceed with fixes while analysis is running
 - **Value every call**: Each CLI invocation is valuable and costly. NEVER waste analysis results:

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

@@ -855,6 +855,7 @@ Use `analysis_results.complexity` or task count to determine structure:
 ### 3.3 Guidelines Checklist
 
 **ALWAYS:**
+- **Search Tool Priority**: ACE (`mcp__ace-tool__search_context`) → CCW (`mcp__ccw-tools__smart_search`) → Built-in (`Grep`, `Glob`, `Read`)
 - Apply Quantification Requirements to all requirements, acceptance criteria, and modification points
 - Load IMPL_PLAN template: `Read(~/.claude/workflows/cli-templates/prompts/workflow/impl-plan-template.txt)` before generating IMPL_PLAN.md
 - Use provided context package: Extract all information from structured context

.claude/agents/cli-discuss-agent.md

@@ -372,7 +372,8 @@ Write({
 ## Key Reminders
 
 **ALWAYS**:
-1. Execute multiple CLIs for cross-verification
+1. **Search Tool Priority**: ACE (`mcp__ace-tool__search_context`) → CCW (`mcp__ccw-tools__smart_search`) → Built-in (`Grep`, `Glob`, `Read`)
+2. Execute multiple CLIs for cross-verification
 2. Parse CLI outputs with fallback extraction
 3. Include file:line references in affected_files
 4. Calculate convergence score accurately

.claude/agents/cli-execution-agent.md

@@ -65,6 +65,8 @@ Score = 0
 
 ## Phase 2: Context Discovery
 
+**Search Tool Priority**: ACE (`mcp__ace-tool__search_context`) → CCW (`mcp__ccw-tools__smart_search`) → Built-in (`Grep`, `Glob`, `Read`)
+
 **1. Project Structure**:
 ```bash
 ccw tool exec get_modules_by_depth '{}'

.claude/agents/cli-explore-agent.md

@@ -165,7 +165,8 @@ Brief summary:
 ## Key Reminders
 
 **ALWAYS**:
-1. Read schema file FIRST before generating any output (if schema specified)
+1. **Search Tool Priority**: ACE (`mcp__ace-tool__search_context`) → CCW (`mcp__ccw-tools__smart_search`) → Built-in (`Grep`, `Glob`, `Read`)
+2. Read schema file FIRST before generating any output (if schema specified)
 2. Copy field names EXACTLY from schema (case-sensitive)
 3. Verify root structure matches schema (array vs object)
 4. Match nested/flat structures as schema requires

.claude/agents/code-developer.md

@@ -389,6 +389,7 @@ Before completing any task, verify:
 - Use `run_in_background=false` for all Bash/CLI calls to ensure foreground execution
 
 **ALWAYS:**
+- **Search Tool Priority**: ACE (`mcp__ace-tool__search_context`) → CCW (`mcp__ccw-tools__smart_search`) → Built-in (`Grep`, `Glob`, `Read`)
 - Verify module/package existence with rg/grep/search before referencing
 - Write working code incrementally
 - Test your implementation thoroughly

.claude/agents/context-search-agent.md

@@ -565,6 +565,7 @@ Output: .workflow/session/{session}/.process/context-package.json
 - Use `run_in_background=false` for all Bash/CLI calls to ensure foreground execution
 
 **ALWAYS**:
+- **Search Tool Priority**: ACE (`mcp__ace-tool__search_context`) → CCW (`mcp__ccw-tools__smart_search`) → Built-in (`Grep`, `Glob`, `Read`)
 - Initialize CodexLens in Phase 0
 - Execute get_modules_by_depth.sh
 - Load CLAUDE.md/README.md (unless in memory)

.claude/agents/debug-explore-agent.md

@@ -10,6 +10,8 @@ You are an intelligent debugging specialist that autonomously diagnoses bugs thr
 
 ## Tool Selection Hierarchy
 
+**Search Tool Priority**: ACE (`mcp__ace-tool__search_context`) → CCW (`mcp__ccw-tools__smart_search`) → Built-in (`Grep`, `Glob`, `Read`)
+
 1. **Gemini (Primary)** - Log analysis, hypothesis validation, root cause reasoning
 2. **Qwen (Fallback)** - Same capabilities as Gemini, use when unavailable
 3. **Codex (Alternative)** - Fix implementation, code modification

.claude/agents/doc-generator.md

@@ -311,6 +311,7 @@ Before completing the task, you must verify the following:
 ## Key Reminders
 
 **ALWAYS**:
+- **Search Tool Priority**: ACE (`mcp__ace-tool__search_context`) → CCW (`mcp__ccw-tools__smart_search`) → Built-in (`Grep`, `Glob`, `Read`)
 - **Detect Mode**: Check `meta.cli_execute` to determine execution mode (Agent or CLI).
 - **Follow `flow_control`**: Execute the `pre_analysis` steps exactly as defined in the task JSON.
 - **Execute Commands Directly**: All commands are tool-specific and ready to run.

.claude/agents/issue-plan-agent.md

@@ -308,7 +308,8 @@ Each line is a solution JSON containing tasks. Schema: `cat .claude/workflows/cl
 - Use `run_in_background=false` for all Bash/CLI calls to ensure foreground execution
 
 **ALWAYS**:
-1. Read schema first: `cat .claude/workflows/cli-templates/schemas/solution-schema.json`
+1. **Search Tool Priority**: ACE (`mcp__ace-tool__search_context`) → CCW (`mcp__ccw-tools__smart_search`) → Built-in (`Grep`, `Glob`, `Read`)
+2. Read schema first: `cat .claude/workflows/cli-templates/schemas/solution-schema.json`
 2. Use ACE semantic search as PRIMARY exploration tool
 3. Fetch issue details via `ccw issue status <id> --json`
 4. Quantify acceptance.criteria with testable conditions

.claude/agents/test-fix-agent.md

@@ -332,6 +332,7 @@ When generating test results for orchestrator (saved to `.process/test-results.j
 ## Important Reminders
 
 **ALWAYS:**
+- **Search Tool Priority**: ACE (`mcp__ace-tool__search_context`) → CCW (`mcp__ccw-tools__smart_search`) → Built-in (`Grep`, `Glob`, `Read`)
 - **Execute tests first** - Understand what's failing before fixing
 - **Diagnose thoroughly** - Find root cause, not just symptoms
 - **Fix minimally** - Change only what's needed to pass tests

.claude/agents/universal-executor.md

@@ -124,6 +124,7 @@ Before completing any task, verify:
 - Use `run_in_background=false` for all Bash/CLI calls to ensure foreground execution
 
 **ALWAYS:**
+- **Search Tool Priority**: ACE (`mcp__ace-tool__search_context`) → CCW (`mcp__ccw-tools__smart_search`) → Built-in (`Grep`, `Glob`, `Read`)
 - Verify resource/dependency existence before referencing
 - Execute tasks systematically and incrementally
 - Test and validate work thoroughly

.claude/workflows/cli-tools-usage.md

@@ -18,33 +18,6 @@
 
 All tool availability, model selection, and routing are defined in this configuration file.
 
-### Configuration Schema
-
-```json
-{
-  "version": "3.0.0",
-  "models": {
-    "<tool-id>": ["<model-1>", "<model-2>", ...]
-  },
-  "tools": {
-    "<tool-id>": {
-      "enabled": true|false,
-      "primaryModel": "<model-id>",
-      "secondaryModel": "<model-id>",
-      "tags": ["<tag-1>", "<tag-2>", ...]
-    }
-  },
-  "customEndpoints": [
-    {
-      "id": "<endpoint-id>",
-      "name": "<display-name>",
-      "enabled": true|false,
-      "tags": ["<tag-1>", "<tag-2>", ...]
-    }
-  ]
-}
-```
-
 ### Configuration Fields
 
 | Field | Description |
@@ -492,20 +465,6 @@ RULES: $(cat ~/.claude/workflows/cli-templates/protocols/write-protocol.md) $(ca
 
 ---
 
-## Execution Configuration
-
-### Dynamic Timeout Allocation
-
-**Minimum timeout: 5 minutes (300000ms)** - Never set below this threshold.
-
-**Timeout Ranges**:
-- **Simple** (analysis, search): 5-10min (300000-600000ms)
-- **Medium** (refactoring, documentation): 10-20min (600000-1200000ms)
-- **Complex** (implementation, migration): 20-60min (1200000-3600000ms)
-- **Heavy** (large codebase, multi-file): 60-120min (3600000-7200000ms)
-
-**Auto-detection**: Analyze PURPOSE and TASK fields to determine timeout
-
 ### Permission Framework
 
 **Single-Use Authorization**: Each execution requires explicit user instruction. Previous authorization does NOT carry over.