fix(langchain,openai): only set strict=True on tools for OpenAI-compatible models in ProviderStrategy

[ccurme (ccurme)]

When using ProviderStrategy, create_agent unnecessarily sets strict=True on tools for all providers. This is only needed for OpenAI / chat completions. Here we unset strict. For OpenAI:

1. We set it in BaseChatOpenAI.bind_tools (as a convenience to users calling model.bind_tools directly)
2. We (redundantly) special-case OpenAI in the create_agent factory logic so that things will not break for users who upgrade langchain but not langchain-openai.

Note: payloads for OpenAI are tested here and appear unchanged: https://github.com/langchain-ai/langchain/blob/master/libs/langchain_v1/tests/unit_tests/agents/test_response_format_integration.py

Quick test:

from langchain.agents import create_agent
from langchain.agents.structured_output import ProviderStrategy
from pydantic import BaseModel

class Weather(BaseModel):
    temperature: float
    condition: str

def weather_tool(location: str) -> str:
    """Get the weather at a location."""
    return "Sunny and 75 degrees F."

for model in [
    "anthropic:claude-sonnet-4-6",
    "openai:gpt-5.4",
    "google_genai:gemini-3.5-flash",
]:

    agent = create_agent(
        model=model,
        tools=[weather_tool],
        response_format=ProviderStrategy(Weather),
    )
    
    result = agent.invoke({
        "messages": [{"role": "user", "content": "What's the weather in SF?"}]
    })
    
    print(result["structured_response"])

[open-swe]

✅ Open SWE Review: No issues found

Open SWE reviewed this PR and found no potential bugs to report.

Open in Web • View Open SWE trace

[Colin Francis (colifran)]

LGTM!

[codspeed-hq]

Merging this PR will not alter performance

✅ 2 untouched benchmarks
⏩ 13 skipped benchmarks¹

---

_{Comparing cc/strict (1115efc) with master (36be77b)²}

Footnotes

1. 13 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩

2. No successful run was found on master (05b5af1) during the generation of this report, so 36be77b was used instead as the comparison base. There might be some changes unrelated to this pull request in this report. ↩