> ## Documentation Index
> Fetch the complete documentation index at: https://shinydapps-bd9fa40b.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# LangChain 工具

> 即插即用的 LangChain 工具，让你的 Python 智能体能够调用 L402 保护的 API，并自动完成 Lightning 支付。

## 安装

```bash theme={null}
pip install l402kit langchain langchain-community
```

***

## 基本用法

```python theme={null}
import os
from l402kit.langchain import L402Tool
from l402kit.wallets import BlinkWallet
from langchain.agents import AgentExecutor, create_react_agent
from langchain_openai import ChatOpenAI
from langchain import hub

# 1. 创建工具
tools = [
    L402Tool(
        wallet=BlinkWallet(
            os.environ["BLINK_API_KEY"],
            os.environ["BLINK_WALLET_ID"],
        ),
        budget_sats=1000,
    )
]

# 2. 将其接入 LangChain 智能体
llm = ChatOpenAI(model="gpt-4o")
prompt = hub.pull("hwchase17/react")
agent = create_react_agent(llm, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)

# 3. 运行 — 智能体在需要时自动完成支付
result = agent_executor.invoke({
    "input": "What is the BTC price from https://api.example.com/btc-price?"
})
print(result["output"])
```

***

## 使用 Alby

```python theme={null}
from l402kit.wallets import AlbyWallet

tools = [
    L402Tool(
        wallet=AlbyWallet(os.environ["ALBY_TOKEN"]),
        budget_sats=500,
    )
]
```

***

## 工具参考

### 构造函数

```python theme={null}
L402Tool(
    wallet: L402Wallet,
    budget_sats: int | None = None,
    budget_per_domain: dict[str, int] | None = None,
    on_spend: Callable[[int, str], None] | None = None,
)
```

| 参数                  | 类型           | 描述              |
| ------------------- | ------------ | --------------- |
| `wallet`            | `L402Wallet` | 用于支付发票的钱包       |
| `budget_sats`       | `int`        | 本次会话最多可消费的 sats |
| `budget_per_domain` | `dict`       | 每个域名的消费限额       |
| `on_spend`          | `callable`   | 每次支付后调用         |

### 工具 Schema（LLM 可见）

```
name: "l402_fetch"
description: "Fetch data from an L402-protected API that requires a Lightning micropayment.
              Handles the payment automatically.
              Input: a URL (and optionally method/body).
              Output: the API response as text."

inputs:
  url:    string  — The URL to fetch
  method: string  — HTTP method: GET, POST, PUT, DELETE (default: GET)
  body:   string  — Request body as JSON string (for POST/PUT)
```

### 方法

```python theme={null}
tool._run(url, method="GET", body=None)     # 同步
await tool._arun(url, method="GET", body=None)  # 异步

tool.spending_report()  # → SpendingReport | None
```

***

## 响应格式

该工具返回 LLM 可直接读取的字符串：

```
# 免费端点
HTTP 200
{"price": 97500, "currency": "USD"}

# 付费端点（priceSats 包含在 402 响应中）
[Paid 10 sats] HTTP 200
{"price": 97500, "currency": "USD"}

# 超出预算
[BLOCKED] Budget exceeded: need 50 sats but only 10 remaining (https://...)

# 网络/钱包错误
[ERROR] Connection refused
```

***

## POST 示例

```python theme={null}
result = agent_executor.invoke({
    "input": "Submit this query to https://api.example.com/search: {\"q\": \"bitcoin\"}"
})
# 智能体以 method=POST 和 body='{"q":"bitcoin"}' 调用 l402_fetch
```

***

## 消费报告

```python theme={null}
tool = L402Tool(wallet=wallet, budget_sats=1000)
# ... 智能体运行中 ...

report = tool.spending_report()
if report:
    print(f"Spent {report.total} sats across {len(report.transactions)} calls")
    for tx in report.transactions:
        print(f"  {tx['sats']} sats → {tx['url']}")
```

***

## 自定义智能体框架

`L402Tool` 是 `langchain.tools.BaseTool` 的子类——它适用于任何接受 LangChain 工具的框架：LangGraph、CrewAI、AutoGen（通过适配器）等。

```python theme={null}
# LangGraph 示例
from langgraph.prebuilt import create_react_agent

app = create_react_agent(llm, tools=[L402Tool(wallet=wallet, budget_sats=500)])
result = app.invoke({"messages": [("user", "fetch https://api.example.com/data")]})
```

***

## 错误处理

`BudgetExceededError` 在内部被捕获——工具返回 `[BLOCKED]` 字符串而不是抛出异常，这样智能体可以在其推理循环中优雅地处理该情况。

所有其他异常（网络错误、钱包故障）均以 `[ERROR] <message>` 的形式返回。

如果你需要以编程方式访问：

```python theme={null}
from l402kit import BudgetExceededError

class MyL402Tool(L402Tool):
    def _run(self, url, method="GET", body=None, run_manager=None):
        result = super()._run(url, method, body, run_manager)
        if result.startswith("[BLOCKED]"):
            raise BudgetExceededError(url, 0, 0)  # 重新抛出供外部处理器捕获
        return result
```

***

## 未安装 LangChain 的情况

如果未安装 `langchain`，在模块级别导入 `L402Tool` 会成功（优雅降级），但实例化时会抛出：

```
ImportError: langchain is required to use L402Tool.
Install it with: pip install langchain langchain-community
```