构建 SQL 代理

export LANGSMITH_TRACING="true"
export LANGSMITH_API_KEY="..."

import fs from "node:fs/promises";
import path from "node:path";

const url = "https://storage.googleapis.com/benchmarks-artifacts/chinook/Chinook.db";
const localPath = path.resolve("Chinook.db");

async function resolveDbPath() {
  if (await fs.exists(localPath)) {
    return localPath;
  }
  const resp = await fetch(url);
  if (!resp.ok) throw new Error(`Failed to download DB. Status code: ${resp.status}`);
  const buf = Buffer.from(await resp.arrayBuffer());
  await fs.writeFile(localPath, buf);
  return localPath;
}

import { SqlDatabase } from "@langchain/classic/sql_db";
import { DataSource } from "typeorm";

let db: SqlDatabase | undefined;
async function getDb() {
  if (!db) {
    const dbPath = await resolveDbFile();
    const datasource = new DataSource({ type: "sqlite", database: dbPath });
    db = await SqlDatabase.fromDataSourceParams({ appDataSource: datasource });
  }
  return db;
}

async function getSchema() {
  const db = await getDb();
  return await db.getTableInfo();
}

from langchain.agents import create_agent
from langchain.agents.middleware import HumanInTheLoopMiddleware 
from langgraph.checkpoint.memory import InMemorySaver 


agent = create_agent(
    model,
    tools,
    system_prompt=system_prompt,
    middleware=[
        HumanInTheLoopMiddleware(
            interrupt_on={"sql_db_query": True},
            description_prefix="Tool execution pending approval",
        ),
    ],
    checkpointer=InMemorySaver(),
)

question = "Which genre on average has the longest tracks?"
config = {"configurable": {"thread_id": "1"}}

for step in agent.stream(
    {"messages": [{"role": "user", "content": question}]},
    config,
    stream_mode="values",
):
    if "__interrupt__" in step:
        print("INTERRUPTED:")
        interrupt = step["__interrupt__"][0]
        for request in interrupt.value["action_requests"]:
            print(request["description"])
    elif "messages" in step:
        step["messages"][-1].pretty_print()
    else:
        pass

...

INTERRUPTED:
Tool execution pending approval

Tool: sql_db_query
Args: {'query': 'SELECT g.Name AS Genre, AVG(t.Milliseconds) AS AvgTrackLength FROM Track t JOIN Genre g ON t.GenreId = g.GenreId GROUP BY g.Name ORDER BY AvgTrackLength DESC LIMIT 1;'}

from langgraph.types import Command 

for step in agent.stream(
    Command(resume={"decisions": [{"type": "approve"}]}),
    config,
    stream_mode="values",
):
    if "messages" in step:
        step["messages"][-1].pretty_print()
    elif "__interrupt__" in step:
        print("INTERRUPTED:")
        interrupt = step["__interrupt__"][0]
        for request in interrupt.value["action_requests"]:
            print(request["description"])
    else:
        pass

================================== Ai Message ==================================
Tool Calls:
  sql_db_query (call_7oz86Epg7lYRqi9rQHbZPS1U)
 Call ID: call_7oz86Epg7lYRqi9rQHbZPS1U
  Args:
    query: SELECT Genre.Name, AVG(Track.Milliseconds) AS AvgDuration FROM Track JOIN Genre ON Track.GenreId = Genre.GenreId GROUP BY Genre.Name ORDER BY AvgDuration DESC LIMIT 5;
================================= Tool Message =================================
Name: sql_db_query

[('Sci Fi & Fantasy', 2911783.0384615385), ('Science Fiction', 2625549.076923077), ('Drama', 2575283.78125), ('TV Shows', 2145041.0215053763), ('Comedy', 1585263.705882353)]
================================== Ai Message ==================================

The genre with the longest average track length is "Sci Fi & Fantasy" with an average duration of about 2,911,783 milliseconds, followed by "Science Fiction" and "Drama."

const DENY_RE = /\b(INSERT|UPDATE|DELETE|ALTER|DROP|CREATE|REPLACE|TRUNCATE)\b/i;
const HAS_LIMIT_TAIL_RE = /\blimit\b\s+\d+(\s*,\s*\d+)?\s*;?\s*$/i;

function sanitizeSqlQuery(q) {
  let query = String(q ?? "").trim();

  // block multiple statements (allow one optional trailing ;)
  const semis = [...query].filter((c) => c === ";").length;
  if (semis > 1 || (query.endsWith(";") && query.slice(0, -1).includes(";"))) {
    throw new Error("multiple statements are not allowed.")
  }
  query = query.replace(/;+\s*$/g, "").trim();

  // read-only gate
  if (!query.toLowerCase().startsWith("select")) {
    throw new Error("Only SELECT statements are allowed")
  }
  if (DENY_RE.test(query)) {
    throw new Error("DML/DDL detected. Only read-only queries are permitted.")
  }

  // append LIMIT only if not already present
  if (!HAS_LIMIT_TAIL_RE.test(query)) {
    query += " LIMIT 5";
  }
  return query;
}

import { tool } from "langchain"
import * as z from "zod";

const executeSql = tool(
  async ({ query }) => {
    const q = sanitizeSqlQuery(query);
    try {
      const result = await db.run(q);
      return typeof result === "string" ? result : JSON.stringify(result, null, 2);
    } catch (e) {
      throw new Error(e?.message ?? String(e))
    }
  },
  {
    name: "execute_sql",
    description: "Execute a READ-ONLY SQLite SELECT query and return results.",
    schema: z.object({
      query: z.string().describe("SQLite SELECT query to execute (read-only)."),
    }),
  }
);

import { SystemMessage } from "langchain";

const getSystemPrompt = async () => new SystemMessage(`You are a careful SQLite analyst.

Authoritative schema (do not invent columns/tables):
${await getSchema()}

Rules:
- Think step-by-step.
- When you need data, call the tool \`execute_sql\` with ONE SELECT query.
- Read-only only; no INSERT/UPDATE/DELETE/ALTER/DROP/CREATE/REPLACE/TRUNCATE.
- Limit to 5 rows unless user explicitly asks otherwise.
- If the tool returns 'Error:', revise the SQL and try again.
- Limit the number of attempts to 5.
- If you are not successful after 5 attempts, return a note to the user.
- Prefer explicit column lists; avoid SELECT *.
`);

import { createAgent } from "langchain";

const agent = createAgent({
  model: "gpt-5",
  tools: [executeSql],
  systemPrompt: getSystemPrompt,
});

const question = "Which genre, on average, has the longest tracks?";
const stream = await agent.stream(
  { messages: [{ role: "user", content: question }] },
  { streamMode: "values" }
);
for await (const step of stream) {
  const message = step.messages.at(-1);
  console.log(`${message.role}: ${JSON.stringify(message.content, null, 2)}`);
}

human: Which genre, on average, has the longest tracks?
ai:
tool: [{"Genre":"Sci Fi & Fantasy","AvgMilliseconds":2911783.0384615385}]
ai: Sci Fi & Fantasy — average track length ≈ 48.5 minutes (about 2,911,783 ms).