Checked other resources

• This is a bug, not a usage question.
• I added a clear and descriptive title that summarizes this issue.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
• This is not related to the langchain-community package.
• I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.

Package (Required)

• langchain
• langchain-openai
• langchain-anthropic
• langchain-classic
• langchain-core
• langchain-model-profiles
• langchain-tests
• langchain-text-splitters
• langchain-chroma
• langchain-deepseek
• langchain-exa
• langchain-fireworks
• langchain-groq
• langchain-huggingface
• langchain-mistralai
• langchain-nomic
• langchain-ollama
• langchain-openrouter
• langchain-perplexity
• langchain-qdrant
• langchain-xai
• Other / not sure / general

Related Issues / PRs

No response

Reproduction Steps / Example Code (Python)

from langchain_core.language_models.chat_models import BaseChatModel
from typing import Any
from langchain_core.messages import BaseMessage, AIMessage
from langchain_core.outputs import ChatResult, ChatGeneration
from langchain_core.callbacks import CallbackManagerForLLMRun

class TestModel(BaseChatModel):
    model: str = "test"
    temperature: float = 0.1
    max_tokens: int = 1024

    def _generate(self, messages: list[BaseMessage], stop: list[str] | None = None,
                  run_manager: CallbackManagerForLLMRun | None = None, **kwargs: Any) -> ChatResult:
        return ChatResult(generations=[ChatGeneration(message=AIMessage(content="test"))])

    @property
    def _llm_type(self) -> str:
        return "test"

model = TestModel()

# BUG: integer temperature is silently dropped
ls_params = model._get_ls_params(temperature=0)
print("ls_temperature" in ls_params)  # False — temperature=0 is lost!

# Works fine with float
ls_params = model._get_ls_params(temperature=0.0)
print("ls_temperature" in ls_params)  # True

# Inconsistency: max_tokens with int works fine
ls_params = model._get_ls_params(max_tokens=2048)
print("ls_max_tokens" in ls_params)  # True

Error Message and Stack Trace (if applicable)

Description

BaseChatModel._get_ls_params() and BaseLLM._get_ls_params() use isinstance(kwargs["temperature"], float) to check the temperature parameter before adding it to LangSmith tracing metadata. However, in Python, isinstance(0, float) is False — integer values like temperature=0 or temperature=1 are silently dropped from tracing.

This is a silent data loss bug: no error or warning is raised, the temperature value simply doesn't appear in LangSmith traces when passed as an integer.

Affected Code. libs/core/langchain_core/language_models/chat_models.py

(lines 815-818):

if "temperature" in kwargs and isinstance(kwargs["temperature"], float):
    ls_params["ls_temperature"] = kwargs["temperature"]
elif hasattr(self, "temperature") and isinstance(self.temperature, float):
    ls_params["ls_temperature"] = self.temperature
libs/core/langchain_core/language_models/llms.py

(lines 354-357):

if "temperature" in kwargs and isinstance(kwargs["temperature"], float):
    ls_params["ls_temperature"] = kwargs["temperature"]
elif hasattr(self, "temperature") and isinstance(self.temperature, float):
    ls_params["ls_temperature"] = self.temperature

Root Cause ;

isinstance(0, float) returns False in Python. int is not a subclass of float. Note the inconsistency: the adjacent max_tokens check correctly uses isinstance(kwargs["max_tokens"], int), while temperature only checks for float.

Suggested Fix Change isinstance(..., float) to isinstance(..., (int, float)) in all 4 locations (2 in chat_models.py, 2 in llms.py):

- if "temperature" in kwargs and isinstance(kwargs["temperature"], float):
+ if "temperature" in kwargs and isinstance(kwargs["temperature"], (int, float)):
      ls_params["ls_temperature"] = kwargs["temperature"]
- elif hasattr(self, "temperature") and isinstance(self.temperature, float):
+ elif hasattr(self, "temperature") and isinstance(self.temperature, (int, float)):
      ls_params["ls_temperature"] = self.temperature

Existing tests should also be updated to cover integer temperature kwargs (currently only temperature=0.2 is tested).

Impact

• High: temperature=0 is one of the most common settings for deterministic LLM outputs
• Silent failure: Users won't know their temperature values are missing from LangSmith traces
• Affects all language models (both BaseChatModel and BaseLLM)

System Info

System Information

OS: Darwin OS Version: Darwin Kernel Version 25.2.0: Tue Nov 18 21:08:48 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T8132 Python Version: 3.13.0rc3 (v3.13.0rc3:fae84c70fbd, Oct 1 2024, 00:10:10) [Clang 15.0.0 (clang-1500.3.9.4)]

Package Information

langchain_core: 1.2.13 langsmith: 0.7.4

Optional packages not installed

langserve

Other Dependencies

httpx: 0.28.1 jsonpatch: 1.33 orjson: 3.11.7 packaging: 26.0 pydantic: 2.12.5 pyyaml: 6.0.3 requests: 2.32.5 requests-toolbelt: 1.0.0 tenacity: 9.1.4 typing-extensions: 4.15.0 uuid-utils: 0.14.0 xxhash: 3.6.0 zstandard: 0.25.0