LangChain Agent Skills 实战：构建 GitHub 仓库分析能力

3. 实现 Python 工具逻辑

接下来是核心部分。我们在 github_analysis.py 中实现具体的 API 调用逻辑。注意这里需要处理时间差计算和错误捕获，确保代理不会因为网络波动而崩溃。

import os
import requests
from typing import Dict, List, Optional, Tuple
from datetime import datetime

def fetch_github_repo(owner: str, repo: str) -> Dict:
    """Fetch basic repository information from GitHub API."""
    url = f"https://api.github.com/repos/{owner}/{repo}"
    headers = {"Authorization": f"token {os.getenv('GITHUB_TOKEN')}"}
    response = requests.get(url, headers=headers)
    response.raise_for_status()
    return response.json()

def analyze_issues(owner: str, repo: str) -> Dict:
    """Analyze issue statistics for a GitHub repository."""
    url = f"https://api.github.com/repos/{owner}/{repo}/issues?state=all"
    headers = {"Authorization": f"token {os.getenv('GITHUB_TOKEN')}"}
    response = requests.get(url, headers=headers)
    response.raise_for_status()
    issues = response.json()

    total_issues = len(issues)
    open_issues = sum(1 for issue in issues if issue['state'] == 'open')
    closed_issues = total_issues - open_issues

    # Calculate average time to close
    close_times = []
    for issue in issues:
        if issue['state'] == 'closed' and issue['closed_at']:
            created_at = issue['created_at']
            closed_at = issue['closed_at']
            # Convert to seconds
            time_diff = (datetime.strptime(closed_at, "%Y-%m-%dT%H:%M:%SZ") - 
                         datetime.strptime(created_at, "%Y-%m-%dT%H:%M:%SZ")).total_seconds()
            close_times.append(time_diff)

    avg_close_time = sum(close_times) / len(close_times) if close_times else 0

    # Get most active contributors
    contributors = {}
    for issue in issues:
        if issue['user']:
            user = issue['user']['login']
            contributors[user] = contributors.get(user, 0) + 1

    top_contributors = sorted(contributors.items(), key=lambda x: x[1], reverse=True)[:3]

    return {
        "total_issues": total_issues,
        "open_issues": open_issues,
        "closed_issues": closed_issues,
        "avg_close_time_days": avg_close_time / (24 * 3600) if avg_close_time else 0,
        "top_contributors": top_contributors
    }

def get_commit_history(owner: str, repo: str, branch: str = "main") -> Dict:
    """Get commit history for a GitHub repository branch."""
    url = f"https://api.github.com/repos/{owner}/{repo}/commits?sha={branch}"
    headers = {"Authorization": f"token {os.getenv('GITHUB_TOKEN')}"}
    response = requests.get(url, headers=headers)
    response.raise_for_status()
    commits = response.json()

    return {
        "total_commits": len(commits),
        "recent_commits": commits[:10],
        "commit_authors": {commit['author']['login']: 0 for commit in commits},
        "changes_per_commit": []
    }

4. 集成到深度代理

现在我们将上述技能加载到代理环境中。这里使用了 deepagents 框架来创建深度代理，并配置了检查点（Checkpointer）以支持状态持久化。

import os
import json
from deepagents import create_deep_agent
from langgraph.checkpoint.memory import MemorySaver
from deepagents.backends.filesystem import FilesystemBackend

# 设置环境变量（实际应用中应从安全位置获取）
os.environ["GITHUB_TOKEN"] = "your_github_token_here"

# 创建技能目录结构
skills_dir = "./skills/github-analysis"
os.makedirs(skills_dir, exist_ok=True)

# 初始化代理
checkpointer = MemorySaver()
agent = create_deep_agent(
    backend=FilesystemBackend(root_dir="./"),
    skills=["./skills/"],
    interrupt_on={"write_file": True, "read_file": False, "edit_file": True},
    checkpointer=checkpointer
)

# 运行代理
result = agent.invoke(
    {"messages": [{"role": "user", "content": "Can you analyze the LangChain repository on GitHub?"}]},
    config={"configurable": {"thread_id": "github_analysis_1"}}
)

# 打印结果
print("Agent Response:")
print(json.dumps(result, indent=2))

5. 关键点与注意事项

在实际落地过程中，有几个细节值得注意：

• API 限制：GitHub API 有严格的速率限制。如果请求频繁，记得添加重试机制或缓存策略。
• 安全性：Token 永远不要硬编码在代码里。环境变量是最基础的保护层，生产环境建议使用密钥管理服务。
• 错误处理：上面的示例为了清晰省略了部分异常捕获，实际开发中建议在工具函数内部包裹 try-except 块，防止单个请求失败导致整个任务中断。
• 性能考量：对于大型仓库，拉取所有 Issue 或 Commits 可能耗时较长。可以考虑分页处理或限制返回数量。

通过这个案例，我们可以看到 Agent Skills 如何有效扩展 LangChain 代理的功能，使代理能够执行更复杂的任务，同时保持系统提示的简洁和高效。这种模块化设计也便于后续复用其他类型的技能。