代码执行优化系统

vibethinker-code-execution/
├── README.md                        # Project overview
├── package.json                     # Root Node.js package
├── unified-system.sh                # Unified installer/orchestrator
├── mlx-servers/                     # MLX inference backend
│   ├── config.json                  # Default MLX/port config
│   ├── ecosystem.config.cjs         # PM2 process file
│   ├── enhanced_server_manager.py   # Supervisor & metrics
│   ├── optimized_load_balancer.py   # HTTP load balancer (port 8090)
│   ├── optimized_mlx_server.py      # Individual MLX worker
│   └── logs/
├── mcp-server/                      # Model Context Protocol server
│   ├── package.json / tsconfig.json
│   ├── src/
│   │   ├── index.ts                 # MCP entry point
│   │   ├── client.ts                # Load balancer client
│   │   ├── orchestrator.ts          # Tool orchestration
│   │   └── tools/definitions/…      # Progressive disclosure tools
│   └── dist/                        # Build output
├── hooks/
│   ├── pre-tool-use/
│   │   ├── context-gatherer.js
│   │   └── security-validator.js
│   ├── post-tool-use/
│   │   ├── analyze-changes.js
│   │   ├── update-context.js
│   │   └── run-tests.js
│   ├── session-start.js
│   └── session-stop.js
├── skills/
│   ├── deep-repo-research/
│   │   ├── SKILL.md
│   │   └── index.js
│   ├── dependency-analysis/
│   │   ├── SKILL.md
│   │   └── index.js
│   ├── context-aware-editing/
│   │   ├── SKILL.md
│   │   └── index.js
│   └── architectural-analysis.js
├── scripts/
│   ├── convert_model.py
│   ├── health-server.js
│   └── monitoring-dashboard.js
├── docs/
│   ├── README.md and guides
│   └── …
├── src/
│   └── index.ts                     # Root TypeScript entry
├── tests/
│   └── integration/system.test.js
└── requirements.txt                 # Python dependencies

git clone <repository-url>
cd vibethinker-code-execution
npm install
chmod +x unified-system.sh

# Copies MLX servers, MCP server, hooks, and skills into ~/qwen3-claude-system
./unified-system.sh install --install-dir ~/qwen3-claude-system

source ~/qwen3-claude-system/setup-env.sh
~/qwen3-claude-system/start-system.sh   # or run ./unified-system.sh start
./unified-system.sh status              # verifies MCP/MLX/monitor ports

cd /path/to/your/project
/path/to/vibethinker-code-execution/unified-system.sh use

./unified-system.sh health          # end-to-end check (throughput + MLX import)
npm run health-check                # Python diagnostics in scripts/health_check.py
npm run setup-mcp                   # Builds/runs just the MCP server via stdio
curl http://localhost:8090/health   # Load balancer/monitor endpoint

import * as repo from './servers';

// Automatic progressive disclosure - only loads needed tools
const auth = await repo.architectural.synthesizeFindings({
  topic: "authentication flow",
  depth: "comprehensive"
});

// Result: 2k token summary vs 150k tokens of raw files
console.log(auth.summary);
console.log(`Analyzed ${auth.metadata.filesCount} files`);
console.log(`Found ${auth.findings.length} insights`);

// SessionStart hook loads repo structure into .claude/context/
// PreToolUse hook gathers file dependencies before edits
// PostToolUse hook analyzes impact after changes
// Skills activate automatically based on user intent

# Deep repository research
claude-code "Research the authentication system in this repo"

# Architectural analysis
claude-code "Analyze the dependency injection patterns"

# Context-aware editing
claude-code "Update the user service without breaking auth"

{
  "mlx_servers": {
    "instances": 27,
    "base_port": 8107,
    "model_path": "lmstudio-community/Qwen3-VL-2B-Thinking-MLX-8bit",
    "quantization": "8bit",
    "max_tokens": 32768,
    "temperature": 1.0,
    "top_p": 0.95,
    "top_k": 20,
    "repetition_penalty": 1.0,
    "presence_penalty": 1.5,
    "gpu_memory_fraction": 0.85,
    "batch_size": 6
  },
  "load_balancer": {
    "algorithm": "least_connections",
    "health_check_interval": 60,
    "circuit_breaker": { "failure_threshold": 5, "recovery_timeout": 600000 }
  },
  "performance": {
    "target_tokens_per_second": 55,
    "request_timeout": 180000,
    "keep_alive": true,
    "compression": true
  }
}

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Write|Edit|Read",
        "hooks": [
          { "type": "command", "command": "node $QWEN3_SYSTEM_DIR/hooks/pre-tool-use/context-gatherer.js" },
          { "type": "command", "command": "node $QWEN3_SYSTEM_DIR/hooks/pre-tool-use/security-validator.js" }
        ]
      }
    ],
    "PostToolUse": [
      {
        "matcher": "Write|Edit",
        "hooks": [
          { "type": "command", "command": "node $QWEN3_SYSTEM_DIR/hooks/post-tool-use/analyze-changes.js" },
          { "type": "command", "command": "node $QWEN3_SYSTEM_DIR/hooks/post-tool-use/update-context.js" },
          { "type": "command", "command": "node $QWEN3_SYSTEM_DIR/hooks/post-tool-use/run-tests.js" }
        ]
      }
    ],
    "SessionStart": [
      {
        "hooks": [
          { "type": "command", "command": "node $QWEN3_SYSTEM_DIR/hooks/session-start.js" }
        ]
      }
    ]
  },
  "skills": {
    "auto_load": true,
    "skills_path": "$QWEN3_SYSTEM_DIR/skills"
  },
  "mcp": {
    "transport": "stdio",
    "server_url": "http://localhost:8090",
    "model_config": {
      "temperature": 1.0,
      "top_p": 0.95,
      "max_tokens": 32768
    }
  }
}

# Run all tests
cd mcp-server && pnpm test

# Run with coverage
pnpm test -- --coverage

# Run specific test files
pnpm vitest run tests/tools/registry.test.ts

import { z } from 'zod';
import { ToolDefinition } from '../../types.js';
import { validatePath, logger, ErrorCodes, createToolFailure } from '../../utils.js';

export const myTool: ToolDefinition = {
  name: 'myTool',
  description: 'Description of what the tool does',
  category: 'repo-search',  // or 'code-analysis', 'architectural', 'context-building'
  version: '1.0.0',
  capabilities: ['read-files', 'pattern-matching'],
  resourceHints: {
    estimatedMemoryMB: 50,
    estimatedTimeMs: 3000,
    cpuIntensive: false,
  },
  inputSchema: z.object({
    path: z.string().describe('Path to analyze'),
    options: z.object({
      depth: z.number().default(2),
    }).optional(),
  }),
  handler: async (args) => {
    const validPath = await validatePath(args.path);
    // Implementation...
    return { result: 'success', data: analysisResult };
  },
  tags: ['search', 'analysis'],
  complexity: 'moderate',
  externalDependencies: ['ripgrep'],
  npmDependencies: [],
  internalDependencies: ['../../utils.js:validatePath'],
};

// Execute tool with structured result
const result = await registry.executeTool('searchByQuery', { query: 'function' });

if (result.success) {
  console.log(result.data);           // Tool output
  console.log(result.metadata);       // Execution time, version
} else {
  console.log(result.error?.code);    // Error code (e.g., 'TOOL_NOT_FOUND')
  console.log(result.error?.message); // Human-readable message
  console.log(result.error?.recoveryHint); // Suggested fix
}

// Get metrics for monitoring
const metrics = registry.getToolMetrics('searchByQuery');
console.log(`Success rate: ${metrics.successCount / metrics.totalCalls}`);

// Health check
const health = registry.isHealthy();
if (!health.healthy) {
  console.log('Issues:', health.issues);
}

# System health
npm run health-check

# MLX instances
pm2 list

# Performance metrics
curl http://localhost:8107/metrics