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

https://github.com/langchain-ai/langchain/pull/34842

Reproduction Steps / Example Code (Python)

from dataclasses import dataclass

from langchain.agents import create_agent
from langchain.agents.middleware import AgentMiddleware, ModelRequest, ToolCallRequest
from langchain.tools import ToolRuntime, tool


@dataclass
class Context:
    user_id: str


# This tool will be added dynamically at runtime
@tool
def calculate_tip(bill_amount: float, tip_percentage: float, runtime: ToolRuntime[Context]) -> str:
    """Calculate the tip amount for a bill."""
    tip = bill_amount * (tip_percentage / 100)
    return f"Tip: ${tip:.2f}, Total: ${bill_amount + tip:.2f}"


# This tool is added at compile time
@tool
def get_weather(location: str) -> str:
    """Get the weather in a given location."""
    return f"The weather in {location} is sunny."


class DynamicToolMiddleware(AgentMiddleware):
    """Middleware that registers and handles dynamic tools."""

    def wrap_model_call(self, request: ModelRequest, handler):
        # Add dynamic tool to the request
        # This could be loaded from an MCP server, database, etc.
        updated = request.override(tools=[*request.tools, calculate_tip])
        return handler(updated)

    def wrap_tool_call(self, request: ToolCallRequest, handler):
        # Handle execution of the dynamic tool
        if request.tool_call["name"] == "calculate_tip":
            return handler(
                request.override(tool=calculate_tip)
            )
        return handler(request)


agent = create_agent(
    model="gpt-4o",
    tools=[get_weather],  # Only static tools registered here
    middleware=[DynamicToolMiddleware()],
)

# The agent can now use both get_weather AND calculate_tip
result = agent.invoke({"messages": [{"role": "user", "content": "Calculate a 20% tip on $85"}]})

Error Message and Stack Trace (if applicable)

calculate_tip call will result in an error because runtime wont be injected

Description

I've been testing dynamic tool registration via a middleware. I've noticed that runtime is not injected into dynamic tools. This is because _inject_tool_args in ToolNode is skipping injection since it does not know about the dynamic tool.

System Info

System Information

OS: Linux OS Version: #1 SMP Tue Nov 5 00:21:55 UTC 2024 Python Version: 3.12.11 (main, Aug 8 2025, 17:06:48) [Clang 20.1.4 ]

Package Information

langchain_core: 1.2.13 langchain: 1.2.10 langsmith: 0.4.31 langchain_openai: 1.1.10 langchain_text_splitters: 1.1.0 langgraph_sdk: 0.3.6

Optional packages not installed

langserve

Other Dependencies

httpx: 0.27.2 jsonpatch: 1.33 langgraph: 1.0.8 openai: 2.21.0 opentelemetry-api: 1.31.1 opentelemetry-exporter-otlp-proto-http: 1.31.1 opentelemetry-sdk: 1.31.1 orjson: 3.11.3 packaging: 24.2 pydantic: 2.11.7 pytest: 8.3.5 pyyaml: 6.0.2 requests: 2.32.3 requests-toolbelt: 1.0.0 rich: 14.0.0 tenacity: 9.1.2 tiktoken: 0.9.0 typing-extensions: 4.13.0 uuid-utils: 0.12.0 zstandard: 0.25.0