feat: Add multi-tool support for CLAUDE.md documentation generation (v3.4.1)

Add flexible tool selection (gemini/qwen/codex) for documentation updates, allowing users to choose the best tool for their analysis needs. Changes: - Add --tool parameter to /update-memory-full and /update-memory-related - Enhance update_module_claude.sh with tool routing (gemini|qwen|codex) - Update command documentation with tool selection examples - Add CHANGELOG entry for v3.4.1 Tool features: - Gemini (default): Documentation generation, pattern recognition - Qwen: Architecture analysis, system design (direct command, no wrapper) - Codex: Implementation validation, code quality analysis Backward compatible: Commands default to gemini without --tool parameter 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
2026-02-05 01:50:27 +08:00 · 2025-10-04 20:44:10 +08:00
parent 7f920cb33d
commit 437897faff
4 changed files with 149 additions and 44 deletions
--- a/.claude/commands/update-memory-full.md
+++ b/.claude/commands/update-memory-full.md
@@ -1,33 +1,46 @@
 ---
 name: update-memory-full
 description: Complete project-wide CLAUDE.md documentation update
-usage: /update-memory-full
+usage: /update-memory-full [--tool <gemini|qwen|codex>]
+argument-hint: "[--tool gemini|qwen|codex]"
 examples:
-  - /update-memory-full                      # Full project documentation update
+  - /update-memory-full                      # Full project documentation update (gemini default)
+  - /update-memory-full --tool qwen          # Use Qwen for architecture analysis
+  - /update-memory-full --tool codex         # Use Codex for implementation validation
 ---

 ### 🚀 Command Overview: `/update-memory-full`

 Complete project-wide documentation update using depth-parallel execution.

+**Tool Selection**:
+- **Gemini (default)**: Documentation generation, pattern recognition, architecture review
+- **Qwen**: Architecture analysis, system design documentation
+- **Codex**: Implementation validation, code quality analysis
+
 ### 📝 Execution Template

 ```bash
 #!/bin/bash
 # Complete project-wide CLAUDE.md documentation update

-# Step 1: Code Index architecture analysis
+# Step 1: Parse tool selection (default: gemini)
+tool="gemini"
+[[ "$*" == *"--tool qwen"* ]] && tool="qwen"
+[[ "$*" == *"--tool codex"* ]] && tool="codex"
+
+# Step 2: Code Index architecture analysis
 mcp__code-index__search_code_advanced(pattern="class|function|interface", file_pattern="**/*.{ts,js,py}")
 mcp__code-index__find_files(pattern="**/*.{md,json,yaml,yml}")

-# Step 2: Cache git changes
+# Step 3: Cache git changes
 Bash(git add -A 2>/dev/null || true)

-# Step 3: Get and display project structure
+# Step 4: Get and display project structure
 modules=$(Bash(~/.claude/scripts/get_modules_by_depth.sh list))
 count=$(echo "$modules" | wc -l)

-# Step 3: Analysis handover → Model takes control
+# Step 5: Analysis handover → Model takes control
 # BASH_EXECUTION_STOPS → MODEL_ANALYSIS_BEGINS

 # Pseudocode flow:
@@ -35,6 +48,8 @@ count=$(echo "$modules" | wc -l)
 #     → Task "Complex project full update" subagent_type: "memory-gemini-bridge"
 # ELSE:
 #     → Present plan and WAIT FOR USER APPROVAL before execution
+#
+# Pass tool parameter to update_module_claude.sh: "$tool"
 ```

 ### 🧠 Model Analysis Phase
@@ -43,7 +58,7 @@ After the bash script completes the initial analysis, the model takes control to

 1. **Analyze Complexity**: Review module count and project context
 2. **Parse CLAUDE.md Status**: Extract which modules have/need CLAUDE.md files
-3. **Choose Strategy**: 
+3. **Choose Strategy**:
   - Simple projects: Present execution plan with CLAUDE.md paths to user
   - Complex projects: Delegate to memory-gemini-bridge agent
 4. **Present Detailed Plan**: Show user exactly which CLAUDE.md files will be created/updated
@@ -56,17 +71,19 @@ After the bash script completes the initial analysis, the model takes control to
 Model will present detailed plan:
 ```
 📋 Update Plan:
+  Tool: [gemini|qwen|codex] (from --tool parameter)
+
  NEW CLAUDE.md files (X):
    - ./src/components/CLAUDE.md
    - ./src/services/CLAUDE.md
-  
+
  UPDATE existing CLAUDE.md files (Y):
    - ./CLAUDE.md
    - ./src/CLAUDE.md
    - ./tests/CLAUDE.md

  Total: N CLAUDE.md files will be processed
-  
+
  ⚠️ Confirm execution? (y/n)
 ```

@@ -84,7 +101,7 @@ depth_modules = organize_by_depth(modules)
 FOR depth FROM max_depth DOWN TO 0:
    FOR each module IN depth_modules[depth]:
        WHILE active_jobs >= 4: wait(0.1)
-        Bash(~/.claude/scripts/update_module_claude.sh "$module" "full" &)
+        Bash(~/.claude/scripts/update_module_claude.sh "$module" "full" "$tool" &)
    wait_all_jobs()

 # Step 6: Safety check and restore staging state
@@ -105,7 +122,7 @@ Bash(git status --short)
 The model will delegate to the memory-gemini-bridge agent using the Task tool:
 ```
 Task "Complex project full update"
-prompt: "Execute full documentation update for [count] modules using depth-parallel execution"
+prompt: "Execute full documentation update for [count] modules using [tool] with depth-parallel execution"
 subagent_type: "memory-gemini-bridge"
 ```

--- a/.claude/commands/update-memory-related.md
+++ b/.claude/commands/update-memory-related.md
@@ -1,15 +1,23 @@
 ---
 name: update-memory-related
 description: Context-aware CLAUDE.md documentation updates based on recent changes
-usage: /update-memory-related
+usage: /update-memory-related [--tool <gemini|qwen|codex>]
+argument-hint: "[--tool gemini|qwen|codex]"
 examples:
-  - /update-memory-related                    # Update documentation based on recent changes
+  - /update-memory-related                    # Update documentation based on recent changes (gemini default)
+  - /update-memory-related --tool qwen        # Use Qwen for architecture analysis
+  - /update-memory-related --tool codex       # Use Codex for implementation validation
 ---

 ### 🚀 Command Overview: `/update-memory-related`

 Context-aware documentation update for modules affected by recent changes.

+**Tool Selection**:
+- **Gemini (default)**: Documentation generation, pattern recognition, architecture review
+- **Qwen**: Architecture analysis, system design documentation
+- **Codex**: Implementation validation, code quality analysis
+

 ### 📝 Execution Template

@@ -17,23 +25,28 @@ Context-aware documentation update for modules affected by recent changes.
 #!/bin/bash
 # Context-aware CLAUDE.md documentation update

-# Step 1: Code Index refresh and architecture analysis
+# Step 1: Parse tool selection (default: gemini)
+tool="gemini"
+[[ "$*" == *"--tool qwen"* ]] && tool="qwen"
+[[ "$*" == *"--tool codex"* ]] && tool="codex"
+
+# Step 2: Code Index refresh and architecture analysis
 mcp__code-index__refresh_index()
 mcp__code-index__search_code_advanced(pattern="class|function|interface", file_pattern="**/*.{ts,js,py}")

-# Step 2: Detect changed modules (before staging)
+# Step 3: Detect changed modules (before staging)
 changed=$(Bash(~/.claude/scripts/detect_changed_modules.sh list))

-# Step 3: Cache git changes (protect current state)
+# Step 4: Cache git changes (protect current state)
 Bash(git add -A 2>/dev/null || true)

-# Step 3: Use detected changes or fallback
+# Step 5: Use detected changes or fallback
 if [ -z "$changed" ]; then
    changed=$(Bash(~/.claude/scripts/get_modules_by_depth.sh list | head -10))
 fi
 count=$(echo "$changed" | wc -l)

-# Step 4: Analysis handover → Model takes control  
+# Step 6: Analysis handover → Model takes control
 # BASH_EXECUTION_STOPS → MODEL_ANALYSIS_BEGINS

 # Pseudocode flow:
@@ -41,6 +54,8 @@ count=$(echo "$changed" | wc -l)
 #     → Task "Complex project related update" subagent_type: "memory-gemini-bridge"
 # ELSE:
 #     → Present plan and WAIT FOR USER APPROVAL before execution
+#
+# Pass tool parameter to update_module_claude.sh: "$tool"
 ```

 ### 🧠 Model Analysis Phase
@@ -62,18 +77,20 @@ After the bash script completes change detection, the model takes control to:
 Model will present detailed plan for affected modules:
 ```
 📋 Related Update Plan:
+  Tool: [gemini|qwen|codex] (from --tool parameter)
+
  CHANGED modules affecting CLAUDE.md:
-  
+
  NEW CLAUDE.md files (X):
    - ./src/api/auth/CLAUDE.md  [new module]
    - ./src/utils/helpers/CLAUDE.md  [new module]
-  
+
  UPDATE existing CLAUDE.md files (Y):
    - ./src/api/CLAUDE.md  [parent of changed auth/]
    - ./src/CLAUDE.md  [root level]

  Total: N CLAUDE.md files will be processed for recent changes
-  
+
  ⚠️ Confirm execution? (y/n)
 ```

@@ -91,7 +108,7 @@ depth_modules = organize_by_depth(changed_modules)
 FOR depth FROM max_depth DOWN TO 0:
    FOR each module IN depth_modules[depth]:
        WHILE active_jobs >= 4: wait(0.1)
-        Bash(~/.claude/scripts/update_module_claude.sh "$module" "related" &)
+        Bash(~/.claude/scripts/update_module_claude.sh "$module" "related" "$tool" &)
    wait_all_jobs()

 # Step 6: Safety check and restore staging state
@@ -112,7 +129,7 @@ Bash(git diff --stat)
 The model will delegate to the memory-gemini-bridge agent using the Task tool:
 ```
 Task "Complex project related update"
-prompt: "Execute context-aware update for [count] changed modules using depth-parallel execution"
+prompt: "Execute context-aware update for [count] changed modules using [tool] with depth-parallel execution"
 subagent_type: "memory-gemini-bridge"
 ```

--- a/.claude/scripts/update_module_claude.sh
+++ b/.claude/scripts/update_module_claude.sh
@@ -1,13 +1,15 @@
 #!/bin/bash
 # Update CLAUDE.md for a specific module with automatic layer detection
-# Usage: update_module_claude.sh <module_path> [update_type]
+# Usage: update_module_claude.sh <module_path> [update_type] [tool]
 #   module_path: Path to the module directory
 #   update_type: full|related (default: full)
+#   tool: gemini|qwen|codex (default: gemini)
 #   Script automatically detects layer depth and selects appropriate template

 update_module_claude() {
    local module_path="$1"
    local update_type="${2:-full}"
+    local tool="${3:-gemini}"
    
    # Validate parameters
    if [ -z "$module_path" ]; then
@@ -61,9 +63,9 @@ update_module_claude() {
    
    # Prepare logging info
    local module_name=$(basename "$module_path")
-    
+
    echo "⚡ Updating: $module_path"
-    echo "   Layer: $layer | Type: $update_type | Files: $file_count"
+    echo "   Layer: $layer | Type: $update_type | Tool: $tool | Files: $file_count"
    echo "   Template: $(basename "$template_path") | Strategy: $analysis_strategy"
    
    # Generate prompt with template injection
@@ -106,31 +108,50 @@ update_module_claude() {
    # Execute update
    local start_time=$(date +%s)
    echo "   🔄 Starting update..."
-    
+
    if cd "$module_path" 2>/dev/null; then
-        # Execute gemini command with layer-specific analysis strategy
-        local gemini_result=0
-        if [ "$analysis_strategy" = "--all-files" ]; then
-            gemini --all-files --yolo -p "$base_prompt
+        local tool_result=0
+        local final_prompt="$base_prompt

        Module Information:
        - Name: $module_name
        - Path: $module_path
        - Layer: $layer
-        - Analysis Strategy: $analysis_strategy" 2>&1
-            gemini_result=$?
-        else
-            gemini --yolo -p "$analysis_strategy $base_prompt
+        - Tool: $tool
+        - Analysis Strategy: $analysis_strategy"

-        Module Information:
-        - Name: $module_name
-        - Path: $module_path
-        - Layer: $layer
-        - Analysis Strategy: $analysis_strategy" 2>&1
-            gemini_result=$?
-        fi
-        
-        if [ $gemini_result -eq 0 ]; then
+        # Execute with selected tool
+        case "$tool" in
+            qwen)
+                if [ "$analysis_strategy" = "--all-files" ]; then
+                    qwen --all-files --yolo -p "$final_prompt" 2>&1
+                    tool_result=$?
+                else
+                    qwen --yolo -p "$analysis_strategy $final_prompt" 2>&1
+                    tool_result=$?
+                fi
+                ;;
+            codex)
+                if [ "$analysis_strategy" = "--all-files" ]; then
+                    codex --full-auto exec "$final_prompt" --skip-git-repo-check -s danger-full-access 2>&1
+                    tool_result=$?
+                else
+                    codex --full-auto exec "$final_prompt CONTEXT: $analysis_strategy" --skip-git-repo-check -s danger-full-access 2>&1
+                    tool_result=$?
+                fi
+                ;;
+            gemini|*)
+                if [ "$analysis_strategy" = "--all-files" ]; then
+                    gemini --all-files --yolo -p "$final_prompt" 2>&1
+                    tool_result=$?
+                else
+                    gemini --yolo -p "$analysis_strategy $final_prompt" 2>&1
+                    tool_result=$?
+                fi
+                ;;
+        esac
+
+        if [ $tool_result -eq 0 ]; then
            local end_time=$(date +%s)
            local duration=$((end_time - start_time))
            echo "   ✅ Completed in ${duration}s"
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -5,6 +5,56 @@ All notable changes to Claude Code Workflow (CCW) will be documented in this fil
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).

+## [3.4.1] - 2025-10-04
+
+### 🎯 Multi-Tool Support for Documentation Updates
+
+This release adds flexible tool selection for CLAUDE.md documentation generation, allowing users to choose between Gemini, Qwen, or Codex based on their analysis needs.
+
+#### Added
+
+**Multi-Tool Support**:
+- **`/update-memory-full --tool <gemini|qwen|codex>`**: Choose tool for full project documentation update
+- **`/update-memory-related --tool <gemini|qwen|codex>`**: Choose tool for context-aware documentation update
+- **Default**: Gemini (documentation generation, pattern recognition)
+- **Qwen**: Architecture analysis, system design documentation
+- **Codex**: Implementation validation, code quality analysis
+
+**Script Enhancement** (`update_module_claude.sh`):
+- Added third parameter for tool selection: `<module_path> [update_type] [tool]`
+- Support for three tools with consistent parameter syntax:
+  - `gemini --all-files --yolo -p` (default)
+  - `qwen --all-files --yolo -p` (direct command, no wrapper)
+  - `codex --full-auto exec` (with danger-full-access)
+- Automatic tool routing via case statement
+- Improved logging with tool information display
+
+#### Changed
+
+**Command Documentation**:
+- Updated `/update-memory-full.md` with tool selection usage and examples
+- Updated `/update-memory-related.md` with tool selection usage and examples
+- Added tool selection strategy and rationale documentation
+
+#### Technical Details
+
+**Tool Execution Patterns**:
+```bash
+# Gemini (default)
+gemini --all-files --yolo -p "$prompt"
+
+# Qwen (architecture analysis)
+qwen --all-files --yolo -p "$prompt"
+
+# Codex (implementation validation)
+codex --full-auto exec "$prompt" --skip-git-repo-check -s danger-full-access
+```
+
+**Backward Compatibility**:
+- ✅ Existing commands without `--tool` parameter default to Gemini
+- ✅ All three tools support Layer 1-4 template system
+- ✅ No breaking changes to existing workflows
+
 ## [3.3.0] - 2025-10-04

 ### 🚀 CLI Tool Enhancements & Codex Multi-Step Execution