Add internationalization support for help view and implement help rendering logic

- Introduced `help-i18n.js` for managing translations in Chinese and English for the help view.
- Created `help.js` to render the help view, including command categories, workflow diagrams, and CodexLens quick-start.
- Implemented search functionality with debounce for command filtering.
- Added workflow diagram rendering with Cytoscape.js integration.
- Developed tests for write-file verification, ensuring proper handling of small and large JSON files.

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

@@ -470,14 +470,14 @@ function computeCliStrategy(task, allTasks) {
   // Pattern: Gemini CLI deep analysis
   {
     "step": "gemini_analyze_[aspect]",
-    "command": "ccw cli exec 'PURPOSE: [goal]\\nTASK: [tasks]\\nMODE: analysis\\nCONTEXT: @[paths]\\nEXPECTED: [output]\\nRULES: $(cat [template]) | [constraints] | analysis=READ-ONLY' --tool gemini --cd [path]",
+    "command": "ccw cli exec 'PURPOSE: [goal]\\nTASK: [tasks]\\nMODE: analysis\\nCONTEXT: @[paths]\\nEXPECTED: [output]\\nRULES: $(cat [template]) | [constraints] | analysis=READ-ONLY' --tool gemini --mode analysis --cd [path]",
     "output_to": "analysis_result"
   },
 
   // Pattern: Qwen CLI analysis (fallback/alternative)
   {
     "step": "qwen_analyze_[aspect]",
-    "command": "ccw cli exec '[similar to gemini pattern]' --tool qwen --cd [path]",
+    "command": "ccw cli exec '[similar to gemini pattern]' --tool qwen --mode analysis --cd [path]",
     "output_to": "analysis_result"
   },
 
@@ -518,7 +518,7 @@ The examples above demonstrate **patterns**, not fixed requirements. Agent MUST:
 4. **Command Composition Patterns**:
    - **Single command**: `bash([simple_search])`
    - **Multiple commands**: `["bash([cmd1])", "bash([cmd2])"]`
-   - **CLI analysis**: `ccw cli exec '[prompt]' --tool gemini --cd [path]`
+   - **CLI analysis**: `ccw cli exec '[prompt]' --tool gemini --mode analysis --cd [path]`
    - **MCP integration**: `mcp__[tool]__[function]([params])`
 
 **Key Principle**: Examples show **structure patterns**, not specific implementations. Agent must create task-appropriate steps dynamically.

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

@@ -155,7 +155,7 @@ MODE: analysis
 CONTEXT: @**/*
 EXPECTED: {output}
 RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt)
-" --tool gemini --cd {dir}
+" --tool gemini --mode analysis --cd {dir}
 
 # Qwen fallback: Replace '--tool gemini' with '--tool qwen'
 ```
@@ -172,7 +172,7 @@ ccw cli exec "..." --tool codex --mode auto --cd {dir}
 
 **Cross-Directory** (Gemini/Qwen):
 ```bash
-ccw cli exec "CONTEXT: @**/* @../shared/**/*" --tool gemini --cd src/auth --includeDirs ../shared
+ccw cli exec "CONTEXT: @**/* @../shared/**/*" --tool gemini --mode analysis --cd src/auth --includeDirs ../shared
 ```
 
 **Directory Scope**:

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

@@ -85,7 +85,7 @@ MODE: analysis
 CONTEXT: @**/*
 EXPECTED: {from prompt}
 RULES: {from prompt, if template specified} | analysis=READ-ONLY
-" --tool gemini --cd {dir} 
+" --tool gemini --mode analysis --cd {dir} 
 ```
 
 **Fallback Chain**: Gemini → Qwen → Codex → Bash-only

.claude/agents/cli-lite-planning-agent.md

@@ -111,7 +111,7 @@ RULES: $(cat ~/.claude/workflows/cli-templates/prompts/planning/02-breakdown-tas
 - Acceptance/verification must be quantified
 - Dependencies use task IDs
 - analysis=READ-ONLY
-" --tool {cli_tool} --cd {project_root}
+" --tool {cli_tool} --mode analysis --cd {project_root}
 ```
 
 ## Core Functions

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

@@ -134,7 +134,7 @@ RULES: $(cat ~/.claude/workflows/cli-templates/prompts/{template}) |
 - Consider previous iteration failures
 - Validate fix doesn't introduce new vulnerabilities
 - analysis=READ-ONLY
-" --tool {cli_tool} --cd {project_root} --timeout {timeout_value}
+" --tool {cli_tool} --mode analysis --cd {project_root} --timeout {timeout_value}
 ```
 
 **Layer-Specific Guidance Injection**:
@@ -529,7 +529,7 @@ See: `.process/iteration-{iteration}-cli-output.txt`
    ```bash
    ccw cli exec "PURPOSE: Analyze integration test failure...
    TASK: Examine component interactions, data flow, interface contracts...
-   RULES: Analyze full call stack and data flow across components" --tool gemini
+   RULES: Analyze full call stack and data flow across components" --tool gemini --mode analysis
    ```
 3. **Parse Output**: Extract RCA, 修复建议, 验证建议 sections
 4. **Generate Task JSON** (IMPL-fix-1.json):