mirror of
https://github.com/langchain-ai/langgraph.git
synced 2026-09-02 14:08:42 +02:00
Sydney RunkleandClaude Sonnet 4.6
aa992adf57
`_get_all_injected_args` runs `get_input_schema()`, `get_type_hints`, and `inspect.signature` on every tool for every `ToolNode` construction. When the same tool objects are passed to repeated `create_agent` calls (the common case), this work was repeated from scratch each time. Add a module-level cache keyed by `id(tool)`. The cache entry stores a strong reference to the tool alongside the result, which prevents GC from reusing the id for a different object and making an incorrect cache hit. The `entry[0] is tool` identity check provides a second safety guard. `BaseTool` (Pydantic v2 BaseModel) is not hashable, so `@lru_cache` cannot be used directly — hence the id-based dict approach. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
LangGraph Prebuilt
This library defines high-level APIs for creating and executing LangGraph agents and tools.
Important
This library is meant to be bundled with
langgraph, don't install it directly
Agents
langgraph-prebuilt provides an implementation of a tool-calling ReAct-style agent - create_react_agent:
pip install langchain-anthropic
from langchain_anthropic import ChatAnthropic
from langgraph.prebuilt import create_react_agent
# Define the tools for the agent to use
def search(query: str):
"""Call to surf the web."""
# This is a placeholder, but don't tell the LLM that...
if "sf" in query.lower() or "san francisco" in query.lower():
return "It's 60 degrees and foggy."
return "It's 90 degrees and sunny."
tools = [search]
model = ChatAnthropic(model="claude-3-7-sonnet-latest")
app = create_react_agent(model, tools)
# run the agent
app.invoke(
{"messages": [{"role": "user", "content": "what is the weather in sf"}]},
)
Tools
ToolNode
langgraph-prebuilt provides an implementation of a node that executes tool calls - ToolNode:
from langgraph.prebuilt import ToolNode
from langchain_core.messages import AIMessage
def search(query: str):
"""Call to surf the web."""
# This is a placeholder, but don't tell the LLM that...
if "sf" in query.lower() or "san francisco" in query.lower():
return "It's 60 degrees and foggy."
return "It's 90 degrees and sunny."
tool_node = ToolNode([search])
tool_calls = [{"name": "search", "args": {"query": "what is the weather in sf"}, "id": "1"}]
ai_message = AIMessage(content="", tool_calls=tool_calls)
# execute tool call
tool_node.invoke({"messages": [ai_message]})
ValidationNode
langgraph-prebuilt provides an implementation of a node that validates tool calls against a pydantic schema - ValidationNode:
from pydantic import BaseModel, field_validator
from langgraph.prebuilt import ValidationNode
from langchain_core.messages import AIMessage
class SelectNumber(BaseModel):
a: int
@field_validator("a")
def a_must_be_meaningful(cls, v):
if v != 37:
raise ValueError("Only 37 is allowed")
return v
validation_node = ValidationNode([SelectNumber])
validation_node.invoke({
"messages": [AIMessage("", tool_calls=[{"name": "SelectNumber", "args": {"a": 42}, "id": "1"}])]
})
Agent Inbox
The library contains schemas for using the Agent Inbox with LangGraph agents. Learn more about how to use Agent Inbox here.
from langgraph.types import interrupt
from langgraph.prebuilt.interrupt import HumanInterrupt, HumanResponse
def my_graph_function():
# Extract the last tool call from the `messages` field in the state
tool_call = state["messages"][-1].tool_calls[0]
# Create an interrupt
request: HumanInterrupt = {
"action_request": {
"action": tool_call['name'],
"args": tool_call['args']
},
"config": {
"allow_ignore": True,
"allow_respond": True,
"allow_edit": False,
"allow_accept": False
},
"description": _generate_email_markdown(state) # Generate a detailed markdown description.
}
# Send the interrupt request inside a list, and extract the first response
response = interrupt([request])[0]
if response['type'] == "response":
# Do something with the response
...