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

createReactAgent no longer works with ChatAnthropic #97

New Issue
Closed
opened 2026-02-15 17:15:44 -05:00 by yindo · 5 comments
yindo commented 2026-02-15 17:15:44 -05:00
Owner
Copy Link
Copy Source

Originally created by @Pckool on GitHub (Sep 26, 2024).

I'm using createReactAgent, and when I pass an OpenAI model it works fine, but when I pass an anthropic model, the model never get's the messages passed to the agent graph, even though it's there on the top level of the trace. Once it get's into the RunnableLanbda scope, the messages property is lost somehow? The system message is still there, but the other messages passed are not. I'm on the latest version for all packages:

{
  "@langchain/community": "0.3.2",
  "@langchain/core": "0.3.3",
  "@langchain/langgraph": "0.2.8",
  "@langchain/anthropic": "0.3.3",
  "@langchain/openai": "0.3.2",
  "langchain": "0.3.2",
}

Pics of langsmith traces below:
CleanShot 2024-09-26 at 15 39 10@2x
CleanShot 2024-09-26 at 15 39 54@2x

Here's an example of how I'm calling it:

export const claude35Sonnet = new ChatAnthropic({
  modelName: 'claude-3-5-sonnet-20240620',
  temperature: 0.45,
  streaming: true,
  anthropicApiKey: env.ANTHROPIC_API_KEY,
});

const prompt = ChatPromptTemplate.fromMessages(
  [
    SystemMessagePromptTemplate.fromTemplate(`some custom system instructions`),
  ]
);

const agent = createReactAgent({ 
  llm: claude35Sonnet, 
  tools: [
    // imagine a list of tools here
  ], 
  messageModifier: prompt 
});

const res = await agent.invoke({
  messages: [
    ['human', 'some random text, please do something for me AI :)']
  ]
})
Originally created by @Pckool on GitHub (Sep 26, 2024). I'm using createReactAgent, and when I pass an OpenAI model it works fine, but when I pass an anthropic model, the model never get's the messages passed to the agent graph, even though it's there on the top level of the trace. Once it get's into the `RunnableLanbda` scope, the `messages` property is lost somehow? The system message is still there, but the other messages passed are not. I'm on the latest version for all packages: ```json { "@langchain/community": "0.3.2", "@langchain/core": "0.3.3", "@langchain/langgraph": "0.2.8", "@langchain/anthropic": "0.3.3", "@langchain/openai": "0.3.2", "langchain": "0.3.2", } ``` Pics of langsmith traces below: ![CleanShot 2024-09-26 at 15 39 10@2x](https://github.com/user-attachments/assets/fc8ff843-bb80-4cea-b23a-09914b5bcc55) ![CleanShot 2024-09-26 at 15 39 54@2x](https://github.com/user-attachments/assets/9ed4a389-be3d-4afc-a57d-d928315200fa) Here's an example of how I'm calling it: ```ts export const claude35Sonnet = new ChatAnthropic({ modelName: 'claude-3-5-sonnet-20240620', temperature: 0.45, streaming: true, anthropicApiKey: env.ANTHROPIC_API_KEY, }); const prompt = ChatPromptTemplate.fromMessages( [ SystemMessagePromptTemplate.fromTemplate(`some custom system instructions`), ] ); const agent = createReactAgent({ llm: claude35Sonnet, tools: [ // imagine a list of tools here ], messageModifier: prompt }); const res = await agent.invoke({ messages: [ ['human', 'some random text, please do something for me AI :)'] ] }) ```
yindo closed this issue 2026-02-15 17:15:44 -05:00
yindo commented 2026-02-15 17:15:44 -05:00
Author
Owner
Copy Link
Copy Source

@jacoblee93 commented on GitHub (Sep 26, 2024):

Hey @Pckool, you need to add a MessagesPlaceholder to your prompt where the agent will inject messages:

export const claude35Sonnet = new ChatAnthropic({
  modelName: 'claude-3-5-sonnet-20240620',
  temperature: 0.45,
  streaming: true,
  anthropicApiKey: env.ANTHROPIC_API_KEY,
});

const prompt = ChatPromptTemplate.fromMessages(
  [
    ["system", `some custom system instructions`],
    ["placeholder", "{messages}"],
  ]
);

const agent = createReactAgent({ 
  llm: model, 
  tools: [
    // imagine a list of tools here
  ], 
  messageModifier: prompt 
});

const res = await agent.invoke({
  messages: [
    { role: 'user', content: 'some random text, please do something for me AI :)'}
  ]
})

Please reopen if the above doesn't fix it!

@jacoblee93 commented on GitHub (Sep 26, 2024): Hey @Pckool, you need to add a `MessagesPlaceholder` to your prompt where the agent will inject messages: ```ts export const claude35Sonnet = new ChatAnthropic({ modelName: 'claude-3-5-sonnet-20240620', temperature: 0.45, streaming: true, anthropicApiKey: env.ANTHROPIC_API_KEY, }); const prompt = ChatPromptTemplate.fromMessages( [ ["system", `some custom system instructions`], ["placeholder", "{messages}"], ] ); const agent = createReactAgent({ llm: model, tools: [ // imagine a list of tools here ], messageModifier: prompt }); const res = await agent.invoke({ messages: [ { role: 'user', content: 'some random text, please do something for me AI :)'} ] }) ``` Please reopen if the above doesn't fix it!
yindo commented 2026-02-15 17:15:44 -05:00
Author
Owner
Copy Link
Copy Source

@Pckool commented on GitHub (Sep 26, 2024):

Hey @jacoblee93 !
That was the first thing I tried and it throws an error saying messages is missing. Although, I looked at the code and createReactAgent already adds this placeholder so this shouldn't be needed (and as I mentioned, this code works perfectly when using an openai model).

CleanShot 2024-09-26 at 16 20 26@2x

Here's the traces:
CleanShot 2024-09-26 at 16 21 14@2x
CleanShot 2024-09-26 at 16 21 54@2x

After that didn't work I tried formattingMessages before sending it to the react agent like so:

const agent = createReactAgent({ 
  llm: claude35Sonnet, 
  tools: [
    // imagine a list of tools here
  ], 
  messageModifier: () => prompt.formatMessages({ messages: cleanedMessages })
});

but that doesn't work either, the messages get lost again in the RunnableLambda scope like above

@Pckool commented on GitHub (Sep 26, 2024): Hey @jacoblee93 ! That was the first thing I tried and it throws an error saying `messages` is missing. Although, I looked at the code and createReactAgent already adds this placeholder so this shouldn't be needed (and as I mentioned, this code works perfectly when using an openai model). ![CleanShot 2024-09-26 at 16 20 26@2x](https://github.com/user-attachments/assets/82592de4-178a-4d83-8f64-ee9c299e3899) Here's the traces: ![CleanShot 2024-09-26 at 16 21 14@2x](https://github.com/user-attachments/assets/ae07586c-ff17-464f-a3cb-cf08b172c816) ![CleanShot 2024-09-26 at 16 21 54@2x](https://github.com/user-attachments/assets/40f40737-d458-44b8-9948-6015d0fe5020) After that didn't work I tried formattingMessages before sending it to the react agent like so: ```ts const agent = createReactAgent({ llm: claude35Sonnet, tools: [ // imagine a list of tools here ], messageModifier: () => prompt.formatMessages({ messages: cleanedMessages }) }); ``` but that doesn't work either, the messages get lost again in the RunnableLambda scope like above
yindo commented 2026-02-15 17:15:45 -05:00
Author
Owner
Copy Link
Copy Source

@Pckool commented on GitHub (Sep 26, 2024):

I can't reopen this issue from here, but I created another issue here adding the context above: https://github.com/langchain-ai/langgraphjs/issues/521

@Pckool commented on GitHub (Sep 26, 2024): I can't reopen this issue from here, but I created another issue here adding the context above: https://github.com/langchain-ai/langgraphjs/issues/521
yindo commented 2026-02-15 17:15:45 -05:00
Author
Owner
Copy Link
Copy Source

@Pckool commented on GitHub (Sep 26, 2024):

Found the issue, it was a silly issue with how I was creating the messages, anthropic couldn't recognize the roles I was giving. Gave the full reason in #521

@Pckool commented on GitHub (Sep 26, 2024): Found the issue, it was a silly issue with how I was creating the messages, anthropic couldn't recognize the roles I was giving. Gave the full reason in #521
yindo commented 2026-02-15 17:15:45 -05:00
Author
Owner
Copy Link
Copy Source

@jacoblee93 commented on GitHub (Sep 26, 2024):

Ah ok great! Glad you figured it out.

@jacoblee93 commented on GitHub (Sep 26, 2024): Ah ok great! Glad you figured it out.
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#97
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?