TrackingModel Class — langchain Architecture

Architecture documentation for the TrackingModel class in test_wrap_model_call.py from the langchain codebase.

Class python

Entity Profile

Dependency Diagram

graph TD
  cc22cf3f_0dfb_c182_97b3_3fe7902d0b04["TrackingModel"]
  0f829642_e361_67a1_cbca_f82839bbbd31["GenericFakeChatModel"]
  cc22cf3f_0dfb_c182_97b3_3fe7902d0b04 -->|extends| 0f829642_e361_67a1_cbca_f82839bbbd31
  573473e5_eb93_a7d7_84ba_c975071c09af["test_wrap_model_call.py"]
  cc22cf3f_0dfb_c182_97b3_3fe7902d0b04 -->|defined in| 573473e5_eb93_a7d7_84ba_c975071c09af
  18f8f001_75cf_0af2_02e1_dde21f0800e3["_generate()"]
  cc22cf3f_0dfb_c182_97b3_3fe7902d0b04 -->|method| 18f8f001_75cf_0af2_02e1_dde21f0800e3

Relationship Graph

Source Code

libs/langchain_v1/tests/unit_tests/agents/middleware/core/test_wrap_model_call.py lines 521–531

        class TrackingModel(GenericFakeChatModel):
            @override
            def _generate(
                self,
                messages: list[BaseMessage],
                stop: list[str] | None = None,
                run_manager: CallbackManagerForLLMRun | None = None,
                **kwargs: Any,
            ) -> ChatResult:
                model_calls.append(len(messages))
                return super()._generate(messages, **kwargs)