langchain-ai/langgraphjs
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraphjs.git synced 2026-07-22 00:55:26 -04:00
Code Issues 108 Packages Projects Releases 20 Wiki Activity

Cannot extract Reasoning tokens from ChatGoogleGenerativeAI #390

New Issue
Open
opened 2026-02-15 18:16:23 -05:00 by yindo · 0 comments
yindo commented 2026-02-15 18:16:23 -05:00
Owner
Copy Link
Copy Source

Originally created by @DevDeepakBhattarai on GitHub (Dec 29, 2025).

Checked other resources

  • I added a very descriptive title to this issue.
  • I searched the LangGraph.js documentation with the integrated search.
  • I used the GitHub search to find a similar question and didn't find it.
  • I am sure that this is a bug in LangGraph.js rather than my code.
  • The bug is not resolved by updating to the latest stable version of LangGraph (or the specific integration package).

Example Code

     new ChatGoogleGenerativeAI({
        model: resolvedModelId, // gemini-3-flash-preview for this case
        apiKey: env.GOOGLE_AI_API_KEY,
        outputVersion: "v1",
        thinkingConfig: {
          includeThoughts: true,
          thinkingLevel:"HIGH"
        },
      });

This is my code that defines the model and I am using the model.invoke() in some node of my langgraph agent. I want the ability to see the reasoning data. When ever i try to run it. I cannot extract the reasoning data.

This is the langsmith trace for my run

https://smith.langchain.com/public/7868aca0-a15c-4e1d-a879-118737d2d859/r

Seems like the reasoning data and the actual ai response are in the same field.

Error Message and Stack Trace (if applicable)

There are no visible errors but, the result is not as expected.

Description

I am trying to extract the reasoning data form the AI. But I can't do it !

System Info

Node version: v20.19.1
Operating system: win32 x64
Package manager: pnpm
Package manager version: 10.17.0

zod -> 3.25.76
@langchain/anthropic -> 1.3.3
@langchain/core -> 1.1.8
langsmith -> 0.4.2
@langchain/classic -> 1.0.7
@langchain/openai -> 1.2.0
@langchain/textsplitters -> 1.0.1, 0.1.0
@langchain/community -> 1.1.1
@langchain/exa -> 1.0.1
@langchain/google-genai -> 2.1.3
@langchain/google-vertexai -> 2.1.3
@langchain/google-gauth -> 2.1.3
@langchain/google-common -> 2.1.3
@langchain/google-vertexai-web -> 2.1.3
@langchain/google-webauth -> 2.1.3
@langchain/groq -> 1.0.2
@langchain/langgraph -> 1.0.7
@langchain/langgraph-checkpoint -> 1.0.0
@langchain/langgraph-sdk -> 1.3.1
@langchain/langgraph-checkpoint-postgres -> 1.0.0
@langchain/ollama -> 1.1.0
@langchain/pinecone -> 1.0.1
@langchain/tavily -> 1.2.0
langchain -> 1.2.3

Originally created by @DevDeepakBhattarai on GitHub (Dec 29, 2025). ### Checked other resources - [x] I added a very descriptive title to this issue. - [x] I searched the LangGraph.js documentation with the integrated search. - [x] I used the GitHub search to find a similar question and didn't find it. - [x] I am sure that this is a bug in LangGraph.js rather than my code. - [x] The bug is not resolved by updating to the latest stable version of LangGraph (or the specific integration package). ### Example Code ```ts new ChatGoogleGenerativeAI({ model: resolvedModelId, // gemini-3-flash-preview for this case apiKey: env.GOOGLE_AI_API_KEY, outputVersion: "v1", thinkingConfig: { includeThoughts: true, thinkingLevel:"HIGH" }, }); ``` This is my code that defines the model and I am using the `model.invoke()` in some node of my langgraph agent. I want the ability to see the reasoning data. When ever i try to run it. I cannot extract the reasoning data. This is the langsmith trace for my run https://smith.langchain.com/public/7868aca0-a15c-4e1d-a879-118737d2d859/r Seems like the reasoning data and the actual ai response are in the same field. ### Error Message and Stack Trace (if applicable) There are no visible errors but, the result is not as expected. ### Description I am trying to extract the reasoning data form the AI. But I can't do it ! ### System Info Node version: v20.19.1 Operating system: win32 x64 Package manager: pnpm Package manager version: 10.17.0 -------------------- zod -> 3.25.76 @langchain/anthropic -> 1.3.3 @langchain/core -> 1.1.8 langsmith -> 0.4.2 @langchain/classic -> 1.0.7 @langchain/openai -> 1.2.0 @langchain/textsplitters -> 1.0.1, 0.1.0 @langchain/community -> 1.1.1 @langchain/exa -> 1.0.1 @langchain/google-genai -> 2.1.3 @langchain/google-vertexai -> 2.1.3 @langchain/google-gauth -> 2.1.3 @langchain/google-common -> 2.1.3 @langchain/google-vertexai-web -> 2.1.3 @langchain/google-webauth -> 2.1.3 @langchain/groq -> 1.0.2 @langchain/langgraph -> 1.0.7 @langchain/langgraph-checkpoint -> 1.0.0 @langchain/langgraph-sdk -> 1.3.1 @langchain/langgraph-checkpoint-postgres -> 1.0.0 @langchain/ollama -> 1.1.0 @langchain/pinecone -> 1.0.1 @langchain/tavily -> 1.2.0 langchain -> 1.2.3
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#390
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?