feat(core): option with type narrowing

[eyurtsev]

We need to look at a few more options

---

run time cast makes it behave like old code:

                block = cast("dict[str, Any]", block)
                if block.get("type") == "text":
                    all_contents.append(block["text"])

---

type narrowing allows making it more typing friendly

def is_reasoning_block(block: Mapping[str, Any]) -> TypeGuard[ReasoningContentBlock]:
    """Check if a block is a ReasoningContentBlock."""
    return block.get("type") == "reasoning"


def is_text_block(block: Mapping[str, Any]) -> TypeGuard[TextContentBlock]:
    """Check if a block is a TextContentBlock."""
    return block.get("type") == "text"


def test_typing() -> None:
    """Test typing on things"""
    message = AIMessage(
        content="Hello",
    )
    if isinstance(message.content, str):
        # This should not raise an error
        message.content = message.content + " world"
    elif isinstance(message.content, list):
        all_contents = []
        for block in message.content:
            if isinstance(block, dict):
                if is_text_block(block):
                    all_contents.append(block["text"])
                if is_reasoning_block(block):
                    all_contents.append(block.get("reasoning", "foo"))

[vercel]

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

1 Skipped Deployment

Name	Status	Preview	Comments	Updated (UTC)
langchain	⬜️ Ignored (Inspect)	Visit Preview		Jul 28, 2025 10:57pm

[codspeed-hq]

CodSpeed WallTime Performance Report

Merging #31945 will not alter performance

_{Comparing eugene/add_some_refactors (2276392) with v04_standard_outputs (5de65de)}

⚠️ 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 #31945 will not alter performance

_{Comparing eugene/add_some_refactors (2276392) with v04_standard_outputs (5de65de)}

Summary

✅ 11 untouched benchmarks
⁉️ 3 dropped benchmarks

⚠️ Please fix the performance issues or acknowledge them on CodSpeed.

Benchmarks breakdown

	Benchmark	BASE	HEAD	Change
⁉️	test_stream_time	15.9 ms	N/A	N/A
⁉️	test_init_time	3.7 ms	N/A	N/A
⁉️	test_init_time_with_client	5.2 ms	N/A	N/A