langchain-ai/langgraphjs
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraphjs.git synced 2026-07-22 17:15:25 -04:00
Code Issues 108 Packages Projects Releases 20 Wiki Activity

Add tool details to tool call stream event metadata #57

New Issue
Closed
opened 2026-02-15 17:15:09 -05:00 by yindo · 3 comments
yindo commented 2026-02-15 17:15:09 -05:00
Owner
Copy Link
Copy Source

Originally created by @airhorns on GitHub (Aug 7, 2024).

The on_tool_call_start event and end event don't tell you which tool is actually being invoked. It'd be very helpful to be able to get that metadata in there somehow if you want to show the user what you're doing under the hood. ChatGPT does this for example when it searches the web -- you get a structured little widget in the UI that shows that that is happening under the hood, and if we want to use ToolNode, you can't actually tell which tool is doing its thing under the hood right now. Can this metadata be exposed on the stream events so that we can tell?

Thanks!

Originally created by @airhorns on GitHub (Aug 7, 2024). The `on_tool_call_start` event and end event don't tell you which tool is actually being invoked. It'd be very helpful to be able to get that metadata in there somehow if you want to show the user what you're doing under the hood. ChatGPT does this for example when it searches the web -- you get a structured little widget in the UI that shows that that is happening under the hood, and if we want to use `ToolNode`, you can't actually tell which tool is doing its thing under the hood right now. Can this metadata be exposed on the stream events so that we can tell? Thanks!
yindo closed this issue 2026-02-15 17:15:09 -05:00
yindo commented 2026-02-15 17:15:10 -05:00
Author
Owner
Copy Link
Copy Source

@hinthornw commented on GitHub (Aug 7, 2024):

(oops was responding with python 1 sec)

@hinthornw commented on GitHub (Aug 7, 2024): (oops was responding with python 1 sec)
yindo commented 2026-02-15 17:15:10 -05:00
Author
Owner
Copy Link
Copy Source

@hinthornw commented on GitHub (Aug 7, 2024):

Running this code:

import { TavilySearchResults } from "@langchain/community/tools/tavily_search";
import { ChatOpenAI } from "@langchain/openai";
import { MemorySaver } from "@langchain/langgraph";
import { HumanMessage } from "@langchain/core/messages";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

// Define the tools for the agent to use
const agentTools = [new TavilySearchResults({ maxResults: 3 })];
const agentModel = new ChatOpenAI({ temperature: 0 });

// Initialize memory to persist state between graph runs
const agentCheckpointer = new MemorySaver();
const agent = createReactAgent({
  llm: agentModel,
  tools: agentTools,
  checkpointSaver: agentCheckpointer,
});

// Now it's time to use!
const agentFinalState = await agent.invoke(
  { messages: [new HumanMessage("what is the current weather in sf")] },
  { configurable: { thread_id: "42" } },
);

console.log(
  agentFinalState.messages[agentFinalState.messages.length - 1].content,
);

let events = agent.streamEvents(
  { messages: [new HumanMessage("what about ny")] },
  { configurable: { thread_id: "42" }, version: "v2" },
);
for await (const event of events) {
  if (event?.event == 'on_tool_start')
  {
    console.log(event);
  
  }

I get:

{
event: 'on_tool_start',
data: { input: { input: 'current weather in New York' } },
name: 'TavilySearchResults',
run_id: 'a5d4d5c7-c150-4616-879c-5f610049f56c',
tags: [ 'seq:step:1' ],
metadata: { thread_id: '42' }
}

The on_tool_start gets the name of the tool and the tags and metadata provided to it, as well as the data inputs.

Are you seeing something different?

@hinthornw commented on GitHub (Aug 7, 2024): Running this code: ``` import { TavilySearchResults } from "@langchain/community/tools/tavily_search"; import { ChatOpenAI } from "@langchain/openai"; import { MemorySaver } from "@langchain/langgraph"; import { HumanMessage } from "@langchain/core/messages"; import { createReactAgent } from "@langchain/langgraph/prebuilt"; // Define the tools for the agent to use const agentTools = [new TavilySearchResults({ maxResults: 3 })]; const agentModel = new ChatOpenAI({ temperature: 0 }); // Initialize memory to persist state between graph runs const agentCheckpointer = new MemorySaver(); const agent = createReactAgent({ llm: agentModel, tools: agentTools, checkpointSaver: agentCheckpointer, }); // Now it's time to use! const agentFinalState = await agent.invoke( { messages: [new HumanMessage("what is the current weather in sf")] }, { configurable: { thread_id: "42" } }, ); console.log( agentFinalState.messages[agentFinalState.messages.length - 1].content, ); let events = agent.streamEvents( { messages: [new HumanMessage("what about ny")] }, { configurable: { thread_id: "42" }, version: "v2" }, ); for await (const event of events) { if (event?.event == 'on_tool_start') { console.log(event); } ``` I get: ``` { event: 'on_tool_start', data: { input: { input: 'current weather in New York' } }, name: 'TavilySearchResults', run_id: 'a5d4d5c7-c150-4616-879c-5f610049f56c', tags: [ 'seq:step:1' ], metadata: { thread_id: '42' } } ``` The `on_tool_start` gets the name of the tool and the tags and metadata provided to it, as well as the data inputs. Are you seeing something different?
yindo commented 2026-02-15 17:15:10 -05:00
Author
Owner
Copy Link
Copy Source

@airhorns commented on GitHub (Aug 7, 2024):

Ah frig 🤦 My logger overrides the name attribute and was hiding it, my apologies! Thanks!

@airhorns commented on GitHub (Aug 7, 2024): Ah frig 🤦 My logger overrides the `name` attribute and was hiding it, my apologies! Thanks!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
checkpointer
docs-needed
documentation
enhancement
good first issue
good writeup
help wanted
invalid
langgraph-supervisor
open-swe-auto
platform
prebuilt
pull-request
Mirrored from GitHub Pull Request
 question
No Label
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/langgraphjs#57
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?