[langchain]: Improve clarity and examples in “Trim Messages” section of short-term memory documentation

[donMichaelL]

Type of issue

issue / bug

Language

Python

Description

The current Trim Messages section of the documentation is less clear compared to the previous version.

• The explanation of the trim message mechanism is somewhat hard to follow, and it’s not immediately clear how to use it effectively.
• The example focuses mainly on manually deleting messages, without referencing or illustrating the strategy mentioned earlier in the description.
• Additionally, the trim_message function does not appear to be deprecated in v1.0, so it likely remains the correct function to reference and demonstrate in this section.

@before_model
def trim_messages(state: AgentState, runtime: Runtime) -> dict[str, Any] | None:
    """Keep only the last few messages to fit context window."""
    messages = state["messages"]

    trimmed_messages = trim_messages(
        messages,
        max_tokens=45,
        strategy="last",
        token_counter=ChatOpenAI(model="gpt-4o"),
        start_on="human",
        include_system=True,
        allow_partial=False,
    )

    return trimmed_messages