feat: 更新 CLI 自动调用触发器和执行原则，增强文档说明

.claude/CLAUDE.md

@@ -37,21 +37,9 @@ Available CLI endpoints are dynamically defined by the config file:
   - Aggregate multiple analysis results before proposing solutions
 
 ### CLI Auto-Invoke Triggers
-
+- **Reference**: See `cli-tools-usage.md` → [Auto-Invoke Triggers](#auto-invoke-triggers) for full specification
-**Proactive CLI invocation scenarios** - Auto-invoke `ccw cli` for external analysis in these cases:
+- **Key scenarios**: Self-repair fails, ambiguous requirements, architecture decisions, pattern uncertainty, critical code paths
-
+- **Principles**: Default `--mode analysis`, no confirmation needed, wait for completion, flexible rule selection
-| Trigger Condition | Recommended Mode | Description |
-|-------------------|------------------|-------------|
-| **Bug fix fails after 1+ attempts** | `--mode analysis --rule analysis-diagnose-bug-root-cause` | Invoke CLI for root cause analysis when self-repair attempts fail |
-| **Unclear task description** | `--mode analysis --rule planning-breakdown-task-steps` | Invoke CLI for task decomposition when requirements are ambiguous |
-| **Quick planning needed** | `--mode analysis --rule planning-plan-architecture-design` | Invoke CLI for architecture design on complex feature requests |
-| **Uncertain code patterns** | `--mode analysis --rule analysis-analyze-code-patterns` | Invoke CLI to analyze existing code style/patterns when uncertain |
-| **Security/performance critical paths** | `--mode analysis --rule analysis-assess-security-risks` | Proactively request review for security or performance-sensitive code |
-
-**Execution principles**:
-- When trigger conditions are met, invoke CLI **without user confirmation**
-- Wait for results before determining next steps
-- Tool fallback chain: `gemini` → `qwen` → `codex`
 
 ## Code Diagnostics
 

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

@@ -5,7 +5,7 @@
 2. [Tool Selection](#tool-selection)
 3. [Prompt Template](#prompt-template)
 4. [CLI Execution](#cli-execution)
-5. [Execution Configuration](#execution-configuration)
+5. [Auto-Invoke Triggers](#auto-invoke-triggers)
 6. [Best Practices](#best-practices)
 
 ---
@@ -462,6 +462,41 @@ ccw cli --tool codex --mode review --commit abc123
 
 ---
 
+## Auto-Invoke Triggers
+
+**Proactive CLI invocation** - Auto-invoke `ccw cli` when encountering these scenarios:
+
+| Trigger Condition | Suggested Rule | When to Use |
+|-------------------|----------------|-------------|
+| **Self-repair fails** | `analysis-diagnose-bug-root-cause` | After 1+ failed fix attempts |
+| **Ambiguous requirements** | `planning-breakdown-task-steps` | Task description lacks clarity |
+| **Architecture decisions** | `planning-plan-architecture-design` | Complex feature needs design |
+| **Pattern uncertainty** | `analysis-analyze-code-patterns` | Unsure of existing conventions |
+| **Critical code paths** | `analysis-assess-security-risks` | Security/performance sensitive |
+
+### Execution Principles
+
+- **Default mode**: `--mode analysis` (read-only, safe for auto-execution)
+- **No confirmation needed**: Invoke proactively when triggers match
+- **Wait for results**: Complete analysis before next action
+- **Tool selection**: Use context-appropriate tool or fallback chain (`gemini` → `qwen` → `codex`)
+- **Rule flexibility**: Suggested rules are guidelines, not requirements - choose the most appropriate template for the situation
+
+### Example: Bug Fix with Auto-Invoke
+
+```bash
+# After 1+ failed fix attempts, auto-invoke root cause analysis
+ccw cli -p "PURPOSE: Identify root cause of [bug description]; success = actionable fix strategy
+TASK: • Trace execution flow • Identify failure point • Analyze state at failure • Determine fix approach
+MODE: analysis
+CONTEXT: @src/module/**/* | Memory: Previous fix attempts failed at [location]
+EXPECTED: Root cause analysis with: failure mechanism, stack trace interpretation, fix recommendation with code
+CONSTRAINTS: Focus on [specific area]
+" --tool gemini --mode analysis --rule analysis-diagnose-bug-root-cause
+```
+
+---
+
 ## Best Practices
 
 ### Core Principles

codex-lens/examples/simple_search_comparison.py

@@ -12,8 +12,15 @@ Usage:
 import subprocess
 import time
 import json
+import re
+import os
 from pathlib import Path
 
+def strip_ansi(text: str) -> str:
+    """Remove ANSI color codes from text."""
+    ansi_escape = re.compile(r'\x1b\[[0-9;]*m')
+    return ansi_escape.sub('', text)
+
 def run_search(query: str, method: str, limit: int = 20) -> tuple[list, float]:
     """Run search via CLI and measure time."""
     cmd = [
@@ -31,19 +38,25 @@ def run_search(query: str, method: str, limit: int = 20) -> tuple[list, float]:
         cwd=str(Path("D:/Claude_dms3/codex-lens/src")),
         capture_output=True,
         text=True,
+        env={**os.environ, "NO_COLOR": "1"},  # Try to disable colors
     )
     elapsed = time.perf_counter() - start
 
     if result.returncode != 0:
         print(f"Error running {method} search:")
-        print(result.stderr)
+        print(result.stderr[:200])
         return [], elapsed
 
     try:
-        data = json.loads(result.stdout)
+        # Strip ANSI codes and parse JSON
+        clean_output = strip_ansi(result.stdout)
+        data = json.loads(clean_output)
+        # Results are nested in "result" object
+        if "result" in data and "results" in data["result"]:
+            return data["result"]["results"], elapsed
         return data.get("results", []), elapsed
-    except json.JSONDecodeError:
+    except json.JSONDecodeError as e:
-        print(f"Failed to parse JSON output for {method}")
+        print(f"Failed to parse JSON output for {method}: {e}")
         return [], elapsed