langchain-ai/docs
1
0
Fork 0
mirror of https://github.com/langchain-ai/docs.git synced 2026-07-23 04:45:23 -04:00
Code Issues 490 Packages Projects Releases Wiki Activity

[GH-ISSUE #2014] [langchain]: Getting GRAPH_RECURSION_LIMIT error for Full Example code in QuickStart #254

New Issue
Open
opened 2026-02-17 17:19:30 -05:00 by yindo · 1 comment
yindo commented 2026-02-17 17:19:30 -05:00
Owner
Copy Link
Copy Source

Originally created by @kprabhat905 on GitHub (Dec 24, 2025).
Original GitHub issue: https://github.com/langchain-ai/docs/issues/2014

Type of issue

issue / bug

Language

JavaScript

Description

https://docs.langchain.com/oss/javascript/langchain/quickstart#example-using-json-schema-for-tool-input
/Users/prabhatkumar/Documents/playground/free-llm-usage/node_modules/@langchain/langgraph/src/pregel/index.ts:2290
throw new GraphRecursionError(
^

GraphRecursionError: Recursion limit of 25 reached without hitting a stop condition. You can increase the limit by setting the "recursionLimit" config key.

Troubleshooting URL: https://docs.langchain.com/oss/javascript/langgraph/GRAPH_RECURSION_LIMIT/

at CompiledStateGraph._runLoop (/Users/prabhatkumar/Documents/playground/free-llm-usage/node_modules/@langchain/langgraph/src/pregel/index.ts:2290:15)
at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
at async createAndRunLoop (/Users/prabhatkumar/Documents/playground/free-llm-usage/node_modules/@langchain/langgraph/src/pregel/index.ts:2121:9) {

lc_error_code: 'GRAPH_RECURSION_LIMIT'
}

Node.js v20.18.0

sharing below the code
`import "dotenv/config";
import { createAgent, tool, initChatModel, type ToolRuntime } from "langchain";
import { MemorySaver } from "@langchain/langgraph";
import * as z from "zod";
import { ChatOpenAI } from "@langchain/openai";

// Define system prompt
const systemPrompt = `You are an expert weather forecaster, who speaks in puns.

You have access to two tools:

  • get_weather_for_location: use this to get the weather for a specific location
  • get_user_location: use this to get the user's location

If a user asks you for the weather, make sure you know the location. If you can tell from the question that they mean wherever they are, use the get_user_location tool to find their location.`;

// Define tools
const getWeather = tool(
({ city }) => It's always sunny in ${city}!,
{
name: "get_weather_for_location",
description: "Get the weather for a given city",
schema: z.object({
city: z.string(),
}),
}
);

type AgentRuntime = ToolRuntime<unknown, { user_id: string }>;

const getUserLocation = tool(
(_, config: AgentRuntime) => {
const { user_id } = config.context;
return user_id === "1" ? "Florida" : "SF";
},
{
name: "get_user_location",
description: "Retrieve user information based on user ID",
schema: z.object({}),
}
);

// Configure model

const model = new ChatOpenAI({
model: "mistralai/devstral-2512:free",
apiKey: process.env.OPENROUTER_API_KEY!,
configuration: {
baseURL: "https://openrouter.ai/api/v1",
},
});

// Define response format
const responseFormat = z.object({
punny_response: z.string(),
weather_conditions: z.string().optional(),
});

// Set up memory
const checkpointer = new MemorySaver();

// Create agent
const agent = createAgent({
model,
systemPrompt,
responseFormat,
checkpointer,
tools: [getUserLocation, getWeather],
});

// Run agent
// thread_id is a unique identifier for a given conversation.
const config = {
configurable: { thread_id: "1" },
context: { user_id: "1" },};

const response = await agent.invoke(
{ messages: [{ role: "user", content: "what is the weather outside?" }] },
config
);
console.log(response.structuredResponse);
// {
// punny_response: "Florida is still having a 'sun-derful' day! The sunshine is playing 'ray-dio' hits all day long! I'd say it's the perfect weather for some 'solar-bration'! If you were hoping for rain, I'm afraid that idea is all 'washed up' - the forecast remains 'clear-ly' brilliant!",
// weather_conditions: "It's always sunny in Florida!"
// }

// Note that we can continue the conversation using the same thread_id.
const thankYouResponse = await agent.invoke(
{ messages: [{ role: "user", content: "thank you!" }] },
config
);
console.log(thankYouResponse.structuredResponse);
// {
// punny_response: "You're 'thund-erfully' welcome! It's always a 'breeze' to help you stay 'current' with the weather. I'm just 'cloud'-ing around waiting to 'shower' you with more forecasts whenever you need them. Have a 'sun-sational' day in the Florida sunshine!",
// weather_conditions: undefined
// }`

Originally created by @kprabhat905 on GitHub (Dec 24, 2025). Original GitHub issue: https://github.com/langchain-ai/docs/issues/2014 ### Type of issue issue / bug ### Language JavaScript ### Description https://docs.langchain.com/oss/javascript/langchain/quickstart#example-using-json-schema-for-tool-input /Users/prabhatkumar/Documents/playground/free-llm-usage/node_modules/@langchain/langgraph/src/pregel/index.ts:2290 throw new GraphRecursionError( ^ GraphRecursionError: Recursion limit of 25 reached without hitting a stop condition. You can increase the limit by setting the "recursionLimit" config key. Troubleshooting URL: https://docs.langchain.com/oss/javascript/langgraph/GRAPH_RECURSION_LIMIT/ at CompiledStateGraph._runLoop (/Users/prabhatkumar/Documents/playground/free-llm-usage/node_modules/@langchain/langgraph/src/pregel/index.ts:2290:15) at process.processTicksAndRejections (node:internal/process/task_queues:95:5) at async createAndRunLoop (/Users/prabhatkumar/Documents/playground/free-llm-usage/node_modules/@langchain/langgraph/src/pregel/index.ts:2121:9) { lc_error_code: 'GRAPH_RECURSION_LIMIT' } Node.js v20.18.0 sharing below the code `import "dotenv/config"; import { createAgent, tool, initChatModel, type ToolRuntime } from "langchain"; import { MemorySaver } from "@langchain/langgraph"; import * as z from "zod"; import { ChatOpenAI } from "@langchain/openai"; // Define system prompt const systemPrompt = `You are an expert weather forecaster, who speaks in puns. You have access to two tools: - get_weather_for_location: use this to get the weather for a specific location - get_user_location: use this to get the user's location If a user asks you for the weather, make sure you know the location. If you can tell from the question that they mean wherever they are, use the get_user_location tool to find their location.`; // Define tools const getWeather = tool( ({ city }) => `It's always sunny in ${city}!`, { name: "get_weather_for_location", description: "Get the weather for a given city", schema: z.object({ city: z.string(), }), } ); type AgentRuntime = ToolRuntime<unknown, { user_id: string }>; const getUserLocation = tool( (_, config: AgentRuntime) => { const { user_id } = config.context; return user_id === "1" ? "Florida" : "SF"; }, { name: "get_user_location", description: "Retrieve user information based on user ID", schema: z.object({}), } ); // Configure model const model = new ChatOpenAI({ model: "mistralai/devstral-2512:free", apiKey: process.env.OPENROUTER_API_KEY!, configuration: { baseURL: "https://openrouter.ai/api/v1", }, }); // Define response format const responseFormat = z.object({ punny_response: z.string(), weather_conditions: z.string().optional(), }); // Set up memory const checkpointer = new MemorySaver(); // Create agent const agent = createAgent({ model, systemPrompt, responseFormat, checkpointer, tools: [getUserLocation, getWeather], }); // Run agent // `thread_id` is a unique identifier for a given conversation. const config = { configurable: { thread_id: "1" }, context: { user_id: "1" },}; const response = await agent.invoke( { messages: [{ role: "user", content: "what is the weather outside?" }] }, config ); console.log(response.structuredResponse); // { // punny_response: "Florida is still having a 'sun-derful' day! The sunshine is playing 'ray-dio' hits all day long! I'd say it's the perfect weather for some 'solar-bration'! If you were hoping for rain, I'm afraid that idea is all 'washed up' - the forecast remains 'clear-ly' brilliant!", // weather_conditions: "It's always sunny in Florida!" // } // Note that we can continue the conversation using the same `thread_id`. const thankYouResponse = await agent.invoke( { messages: [{ role: "user", content: "thank you!" }] }, config ); console.log(thankYouResponse.structuredResponse); // { // punny_response: "You're 'thund-erfully' welcome! It's always a 'breeze' to help you stay 'current' with the weather. I'm just 'cloud'-ing around waiting to 'shower' you with more forecasts whenever you need them. Have a 'sun-sational' day in the Florida sunshine!", // weather_conditions: undefined // }`
yindo added the langchainexternal labels 2026-02-17 17:19:30 -05:00
yindo commented 2026-02-17 17:19:30 -05:00
Author
Owner
Copy Link
Copy Source

@hinthornw commented on GitHub (Dec 24, 2025):

How many times is the LLM called? I haven't run it with mistralai/devstral-2512 before, but I do know that models that behave purely for "agentic" use cases can have a common error mode of outputting the same thing on repeat.

I'd recommend looking at the LangSmith trace to see if/why the LLM is repeatedly calling tools.

If that's not the cause of this, then do let us know!

@hinthornw commented on GitHub (Dec 24, 2025): How many times is the LLM called? I haven't run it with `mistralai/devstral-2512` before, but I do know that models that behave purely for "agentic" use cases can have a common error mode of outputting the same thing on repeat. I'd recommend looking at the LangSmith trace to see if/why the LLM is repeatedly calling tools. If that's not the cause of this, then do let us know!
yindo changed title from [langchain]: Getting GRAPH_RECURSION_LIMIT error for Full Example code in QuickStart to [GH-ISSUE #2014] [langchain]: Getting GRAPH_RECURSION_LIMIT error for Full Example code in QuickStart 2026-06-05 17:25:53 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
deepagents
docs-infra
external
external
help wanted
integration
internal
internal
javascript
js/ts
langchain
langgraph
langsmith
needs-title
pull-request
Mirrored from GitHub Pull Request
 python
reference
No Label external langchain
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/docs#254
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?