wrap_model_call() — langchain Function Reference

Architecture documentation for the wrap_model_call() function in anthropic_tools.py from the langchain codebase.

Function python LangChainCore MessageInterface calls 1 called by 1

Entity Profile

LangChainCore→ MessageInterface→ wrap_model_call() — langchain Function Reference

Dependency Diagram

graph TD
  dc9524e3_cb43_2481_1aee_b82424bafcfe["wrap_model_call()"]
  cc57e604_ebeb_0d7e_259e_ae26b40e03fa["_StateClaudeFileToolMiddleware"]
  dc9524e3_cb43_2481_1aee_b82424bafcfe -->|defined in| cc57e604_ebeb_0d7e_259e_ae26b40e03fa
  219d4c7d_e796_f766_c3b6_e8cfd03bb8de["wrap_model_call()"]
  219d4c7d_e796_f766_c3b6_e8cfd03bb8de -->|calls| dc9524e3_cb43_2481_1aee_b82424bafcfe
  219d4c7d_e796_f766_c3b6_e8cfd03bb8de["wrap_model_call()"]
  dc9524e3_cb43_2481_1aee_b82424bafcfe -->|calls| 219d4c7d_e796_f766_c3b6_e8cfd03bb8de
  style dc9524e3_cb43_2481_1aee_b82424bafcfe fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/anthropic/langchain_anthropic/middleware/anthropic_tools.py lines 262–290

    def wrap_model_call(
        self,
        request: ModelRequest,
        handler: Callable[[ModelRequest], ModelResponse],
    ) -> ModelResponse:
        """Inject Anthropic tool descriptor and optional system prompt."""
        # Replace our BaseTool with Anthropic's native tool descriptor
        tools = [
            t
            for t in (request.tools or [])
            if getattr(t, "name", None) != self.tool_name
        ] + [{"type": self.tool_type, "name": self.tool_name}]

        # Inject system prompt if provided
        overrides: _ModelRequestOverrides = {"tools": tools}
        if self.system_prompt:
            if request.system_message is not None:
                new_system_content = [
                    *request.system_message.content_blocks,
                    {"type": "text", "text": f"\n\n{self.system_prompt}"},
                ]
            else:
                new_system_content = [{"type": "text", "text": self.system_prompt}]
            new_system_message = SystemMessage(
                content=cast("list[str | dict[str, str]]", new_system_content)
            )
            overrides["system_message"] = new_system_message

        return handler(request.override(**overrides))