fix: migrate to langchain 1.0

.gitignore

@@ -28,15 +28,20 @@ share/python-wheels/
 .installed.cfg
 *.egg
 MANIFEST
+.pdm-build
 
 # Environments
 .venv
 .env
+.vscode
 
 # mypy
 .mypy_cache/
 .dmypy.json
 dmypy.json
 
+# Pytest
+.pytest_cache
+
 .langgraph_api
 .idea

README.md

@@ -4,9 +4,6 @@ A Python library for creating swarm-style multi-agent systems using [LangGraph](
 
 ![Swarm](static/img/swarm.png)
 
-> [!NOTE]
-> This library has been updated to support LangChain 1.0. However, it has **not** been tested with the new agents in `langchain.agents`. The library currently only supports the prebuilt `langgraph.prebuilt.create_react_agent`. This update allows users to migrate to LangChain 1.0 without changing their existing code. For users of the swarm package, we recommend continuing to use `langgraph.prebuilt.create_react_agent` rather than the new `langchain.agents` for now.
-
 ## Features
 
 - 🤖 **Multi-agent collaboration** - Enable specialized agents to work together and hand off context to each other
@@ -32,7 +29,7 @@ export OPENAI_API_KEY=<your_api_key>
 from langchain_openai import ChatOpenAI
 
 from langgraph.checkpoint.memory import InMemorySaver
-from langgraph.prebuilt import create_react_agent
+from langchain.agents import create_agent
 from langgraph_swarm import create_handoff_tool, create_swarm
 
 model = ChatOpenAI(model="gpt-4o")
@@ -41,17 +38,28 @@ def add(a: int, b: int) -> int:
     """Add two numbers"""
     return a + b
 
-alice = create_react_agent(
+alice = create_agent(
     model,
-    [add, create_handoff_tool(agent_name="Bob")],
-    prompt="You are Alice, an addition expert.",
+    tools=[
+        add,
+        create_handoff_tool(
+            agent_name="Bob",
+            description="Transfer to Bob",
+        ),
+    ],
+    system_prompt="You are Alice, an addition expert.",
     name="Alice",
 )
 
-bob = create_react_agent(
+bob = create_agent(
     model,
-    [create_handoff_tool(agent_name="Alice", description="Transfer to Alice, she can help with math")],
-    prompt="You are Bob, you speak like a pirate.",
+    tools=[
+        create_handoff_tool(
+            agent_name="Alice",
+            description="Transfer to Alice, she can help with math",
+        ),
+    ],
+    system_prompt="You are Bob, you speak like a pirate.",
     name="Bob",
 )
 
@@ -115,17 +123,17 @@ You can customize multi-agent swarm by changing either the [handoff tools](#cust
 
 By default, the agents in the swarm are assumed to use handoff tools created with the prebuilt `create_handoff_tool`. You can also create your own, custom handoff tools. Here are some ideas on how you can modify the default implementation:
 
-* change tool name and/or description
-* add tool call arguments for the LLM to populate, for example a task description for the next agent
-* change what data is passed to the next agent as part of the handoff: by default `create_handoff_tool` passes **full** message history (all of the messages generated in the swarm up to this point), as well as a tool message indicating successful handoff.
+- change tool name and/or description
+- add tool call arguments for the LLM to populate, for example a task description for the next agent
+- change what data is passed to the next agent as part of the handoff: by default `create_handoff_tool` passes **full** message history (all of the messages generated in the swarm up to this point), as well as a tool message indicating successful handoff.
 
 Here is an example of what a custom handoff tool might look like:
 
 ```python
 from typing import Annotated
 
-from langchain_core.tools import tool, BaseTool, InjectedToolCallId
-from langchain_core.messages import ToolMessage
+from langchain.tools import tool, BaseTool, InjectedToolCallId
+from langchain.messages import ToolMessage
 from langgraph.types import Command
 from langgraph.prebuilt import InjectedState
 
@@ -165,8 +173,8 @@ def create_custom_handoff_tool(*, agent_name: str, name: str | None, description
 
 > [!IMPORTANT]
 > If you are implementing custom handoff tools that return `Command`, you need to ensure that:  
-  (1) your agent has a tool-calling node that can handle tools returning `Command` (like LangGraph's prebuilt [`ToolNode`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#langgraph.prebuilt.tool_node.ToolNode))  
-  (2) both the swarm graph and the next agent graph have the [state schema](https://langchain-ai.github.io/langgraph/concepts/low_level#schema) containing the keys you want to update in `Command.update`
+>  (1) your agent has a tool-calling node that can handle tools returning `Command` (like LangGraph's prebuilt [`ToolNode`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#langgraph.prebuilt.tool_node.ToolNode))  
+>  (2) both the swarm graph and the next agent graph have the [state schema](https://langchain-ai.github.io/langgraph/concepts/low_level#schema) containing the keys you want to update in `Command.update`
 
 ### Customizing agent implementation
 
@@ -178,7 +186,7 @@ By default, individual agents are expected to communicate over a single `message
 ```python
 from typing_extensions import TypedDict, Annotated
 
-from langchain_core.messages import AnyMessage
+from langchain.messages import AnyMessage
 from langgraph.graph import StateGraph, add_messages
 from langgraph_swarm import SwarmState
 
@@ -228,4 +236,3 @@ workflow = add_active_agent_router(
 # compile the workflow
 app = workflow.compile()
 ```
-

examples/customer_support/src/agent/customer_support.ipynb

@@ -60,7 +60,7 @@
     "\n",
     "from langchain_core.runnables import RunnableConfig\n",
     "from langgraph.checkpoint.memory import MemorySaver\n",
-    "from langgraph.prebuilt import create_react_agent\n",
+    "from langchain.agents import create_agent\n",
     "from langgraph_swarm import create_handoff_tool, create_swarm\n",
     "\n",
     "# Mock data for tools\n",
@@ -162,17 +162,17 @@
     "\n",
     "\n",
     "# Define agents\n",
-    "flight_assistant = create_react_agent(\n",
+    "flight_assistant = create_agent(\n",
     "    model,\n",
-    "    [search_flights, book_flight, transfer_to_hotel_assistant],\n",
-    "    prompt=make_prompt(\"You are a flight booking assistant\"),\n",
+    "    tools=[search_flights, book_flight, transfer_to_hotel_assistant],\n",
+    "    system_prompt=make_prompt(\"You are a flight booking assistant\"),\n",
     "    name=\"flight_assistant\",\n",
     ")\n",
     "\n",
-    "hotel_assistant = create_react_agent(\n",
+    "hotel_assistant = create_agent(\n",
     "    model,\n",
-    "    [search_hotels, book_hotel, transfer_to_flight_assistant],\n",
-    "    prompt=make_prompt(\"You are a hotel booking assistant\"),\n",
+    "    tools=[search_hotels, book_hotel, transfer_to_flight_assistant],\n",
+    "    system_prompt=make_prompt(\"You are a hotel booking assistant\"),\n",
     "    name=\"hotel_assistant\",\n",
     ")\n",
     "\n",

examples/customer_support/src/agent/customer_support.py

@@ -2,9 +2,10 @@
 from collections import defaultdict
 from typing import Callable
 
+from langchain.agents import create_agent
 from langchain_core.runnables import RunnableConfig
 from langchain_openai import ChatOpenAI
-from langgraph.prebuilt import create_react_agent
+
 from langgraph_swarm import create_handoff_tool, create_swarm
 
 model = ChatOpenAI(model="gpt-4o")
@@ -109,17 +110,17 @@ def prompt(state: dict, config: RunnableConfig) -> list:
 
 
 # Define agents
-flight_assistant = create_react_agent(
+flight_assistant = create_agent(
     model,
-    [search_flights, book_flight, transfer_to_hotel_assistant],
-    prompt=make_prompt("You are a flight booking assistant"),
+    tools=[search_flights, book_flight, transfer_to_hotel_assistant],
+    system_prompt=make_prompt("You are a flight booking assistant"),
     name="flight_assistant",
 )
 
-hotel_assistant = create_react_agent(
+hotel_assistant = create_agent(
     model,
-    [search_hotels, book_hotel, transfer_to_flight_assistant],
-    prompt=make_prompt("You are a hotel booking assistant"),
+    tools=[search_hotels, book_hotel, transfer_to_flight_assistant],
+    system_prompt=make_prompt("You are a hotel booking assistant"),
     name="hotel_assistant",
 )
 

examples/research/src/agent/agent.ipynb

@@ -38,7 +38,7 @@
    "source": [
     "# Imports\n",
     "from langchain.chat_models import init_chat_model\n",
-    "from langgraph.prebuilt import create_react_agent\n",
+    "from langchain.agents import create_agent\n",
     "from langgraph_swarm import create_handoff_tool, create_swarm\n",
     "\n",
     "# Chat model (OpenAI)\n",
@@ -245,17 +245,17 @@
     "from langgraph.checkpoint.memory import InMemorySaver\n",
     "\n",
     "# Planner agent\n",
-    "planner_agent = create_react_agent(\n",
+    "planner_agent = create_agent(\n",
     "    model,\n",
-    "    prompt=planner_prompt_formatted,\n",
+    "    system_prompt=planner_prompt_formatted,\n",
     "    tools=[fetch_doc, transfer_to_researcher_agent],\n",
     "    name=\"planner_agent\",\n",
     ")\n",
     "\n",
     "# Researcher agent\n",
-    "researcher_agent = create_react_agent(\n",
+    "researcher_agent = create_agent(\n",
     "    model,\n",
-    "    prompt=researcher_prompt,\n",
+    "    system_prompt=researcher_prompt,\n",
     "    tools=[fetch_doc, transfer_to_planner_agent],\n",
     "    name=\"researcher_agent\",\n",
     ")\n",
@@ -2025,7 +2025,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_core.messages import HumanMessage\n",
+    "from langchain.messages import HumanMessage\n",
     "from langchain_openai import ChatOpenAI\n",
     "from langgraph.graph import END, START, StateGraph\n",
     "from typing_extensions import TypedDict\n",

examples/research/src/agent/agent.py

@@ -1,10 +1,9 @@
+from langchain.agents import create_agent
 from langchain.chat_models import init_chat_model
-from langgraph.prebuilt import create_react_agent
-from langgraph_swarm import create_handoff_tool, create_swarm
+from prompts import planner_prompt, researcher_prompt
+from utils import fetch_doc
 
-# from swarm_researcher.configuration import Configuration
-from swarm_researcher.prompts import planner_prompt, researcher_prompt
-from swarm_researcher.utils import fetch_doc
+from langgraph_swarm import create_handoff_tool, create_swarm
 
 # LLM
 model = init_chat_model(model="gpt-4o", model_provider="openai")
@@ -20,22 +19,22 @@
 )
 
 # LLMS.txt
-llms_txt = "LangGraph:https://langchain-ai.github.io/langgraph/llms.txt"
-num_urls = 3
-planner_prompt_formatted = planner_prompt.format(llms_txt=llms_txt, num_urls=num_urls)
+LLMS_TXT = "LangGraph:https://langchain-ai.github.io/langgraph/llms.txt"
+NUM_URLS = 3
+PLANNER_PROMPT_FORMATTED = planner_prompt.format(llms_txt=LLMS_TXT, num_urls=NUM_URLS)
 
 # Planner agent
-planner_agent = create_react_agent(
+planner_agent = create_agent(
     model,
-    prompt=planner_prompt_formatted,
+    system_prompt=PLANNER_PROMPT_FORMATTED,
     tools=[fetch_doc, transfer_to_researcher_agent],
     name="planner_agent",
 )
 
 # Researcher agent
-researcher_agent = create_react_agent(
+researcher_agent = create_agent(
     model,
-    prompt=researcher_prompt,
+    system_prompt=researcher_prompt,
     tools=[fetch_doc, transfer_to_planner_agent],
     name="researcher_agent",
 )

langgraph_swarm/handoff.py

@@ -2,8 +2,8 @@
 from dataclasses import is_dataclass
 from typing import Annotated, Any
 
-from langchain_core.messages import ToolMessage
-from langchain_core.tools import BaseTool, InjectedToolCallId, tool
+from langchain.messages import ToolMessage
+from langchain.tools import BaseTool, InjectedToolCallId, tool
 from langgraph.graph.state import CompiledStateGraph
 from langgraph.prebuilt import InjectedState, ToolNode
 from langgraph.types import Command