fix(core): (v1) update BaseChatModel return type to AIMessage

[ccurme]

Can plumb through ChatGeneration, LLMResult, etc. if we want.

This is a minimal change, impact looks small and will fix more issues than it introduces.

Current state of things:

def get_weather(location: str) -> str:
    """Get the weather at a location."""
    ...

llm = init_chat_model("openai:gpt-5")
llm_with_tools = llm.bind_tools([get_weather])

response = llm_with_tools.invoke("query")
response.tool_calls  # Cannot access attribute "tool_calls" for class "BaseMessage"

Integration packages should update return type of bind_tools to Runnable[LanguageModelInput, AIMessage].

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

1 Skipped Deployment

Project	Deployment	Preview	Comments	Updated (UTC)
langchain	Ignored	Preview		Aug 21, 2025 5:51pm

[codspeed-hq]

CodSpeed WallTime Performance Report

Merging #32626 will not alter performance

_{Comparing cc/chat_model_return_type (b0a39b4) with wip-v1.0 (dbc5a3b)}

⚠️ Unknown Walltime execution environment detected

Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data.

For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.

Summary

✅ 13 untouched benchmarks

[codspeed-hq]

CodSpeed Instrumentation Performance Report

Merging #32626 will not alter performance

_{Comparing cc/chat_model_return_type (b0a39b4) with wip-v1.0 (dbc5a3b)}

Summary

✅ 14 untouched benchmarks