Update lintin

Author: hinthornw

README.md

@@ -1,3 +1,55 @@
+<!--
+Configuration auto-generated by `langgraph template lock`. DO NOT EDIT MANUALLY.
+{
+  "config_schemas": {
+    "agent": {
+      "type": "object",
+      "properties": {
+        "system_prompt": {
+          "type": "string",
+          "default": "You are a helpful AI assistant.\nSystem time: {system_time}"
+        },
+        "model_name": {
+          "type": "string",
+          "default": "claude-3-5-sonnet-20240620",
+          "environment": [
+            {
+              "value": "anthropic",
+              "variables": "ANTHROPIC_API_KEY"
+            },
+            {
+              "value": "fireworks",
+              "variables": "FIREWORKS_API_KEY"
+            },
+            {
+              "value": "openai",
+              "variables": "OPENAI_API_KEY"
+            }
+          ]
+        },
+        "scraper_tool_model_name": {
+          "type": "string",
+          "default": "accounts/fireworks/models/firefunction-v2",
+          "environment": [
+            {
+              "value": "anthropic",
+              "variables": "ANTHROPIC_API_KEY"
+            },
+            {
+              "value": "fireworks",
+              "variables": "FIREWORKS_API_KEY"
+            },
+            {
+              "value": "openai",
+              "variables": "OPENAI_API_KEY"
+            }
+          ]
+        }
+      }
+    }
+  }
+}
+-->
 # LangGraph ReAct Agent Template
 
 This LangGraph template implements a simple, extensible ReAct agent.

pyproject.toml

@@ -26,10 +26,10 @@ requires = ["setuptools>=73.0.0", "wheel"]
 build-backend = "setuptools.build_meta"
 
 [tool.setuptools]
-packages = ["langgraph.templates.retrieval_graph", "retrieval_graph"]
+packages = ["langgraph.templates.react_agent", "react_agent"]
 [tool.setuptools.package-dir]
-"langgraph.templates.retrieval_graph" = "src/retrieval_graph"
-"retrieval_graph" = "src/retrieval_graph"
+"langgraph.templates.react_agent" = "src/react_agent"
+"react_agent" = "src/react_agent"
 
 
 [tool.setuptools.package-data]

src/react_agent/configuration.py

@@ -13,9 +13,9 @@ class Configuration:
     """The configuration for the agent."""
 
     system_prompt: str = "You are a helpful AI assistant.\nSystem time: {system_time}"
-    model_name: Annotated[
-        str, {"__template_metadata__": {"kind": "llm"}}
-    ] = "claude-3-5-sonnet-20240620"
+    model_name: Annotated[str, {"__template_metadata__": {"kind": "llm"}}] = (
+        "claude-3-5-sonnet-20240620"
+    )
     scraper_tool_model_name: Annotated[
         str, {"__template_metadata__": {"kind": "llm"}}
     ] = "accounts/fireworks/models/firefunction-v2"

src/react_agent/graph.py

@@ -4,7 +4,7 @@
 """
 
 from datetime import datetime, timezone
-from typing import Literal
+from typing import Dict, List, Literal, cast
 
 from langchain.chat_models import init_chat_model
 from langchain_core.messages import AIMessage
@@ -20,7 +20,9 @@
 # Define the function that calls the model
 
 
-async def call_model(state: State, config: RunnableConfig):
+async def call_model(
+    state: State, config: RunnableConfig
+) -> Dict[str, List[AIMessage]]:
     """Call the LLM powering our "agent".
 
     This function prepares the prompt, initializes the model, and processes the response.
@@ -36,22 +38,26 @@ async def call_model(state: State, config: RunnableConfig):
 
     # Create a prompt template. Customize this to change the agent's behavior.
     prompt = ChatPromptTemplate.from_messages(
-        [("system", configuration["system_prompt"]), ("placeholder", "{messages}")]
+        [("system", configuration.system_prompt), ("placeholder", "{messages}")]
     )
 
     # Initialize the model with tool binding. Change the model or add more tools here.
-    model = init_chat_model(configuration["model_name"]).bind_tools(TOOLS)
+    model = init_chat_model(configuration.model_name).bind_tools(TOOLS)
 
     # Prepare the input for the model, including the current system time
     message_value = await prompt.ainvoke(
-        {**state, "system_time": datetime.now(tz=timezone.utc).isoformat()}, config
+        {
+            "messages": state.messages,
+            "system_time": datetime.now(tz=timezone.utc).isoformat(),
+        },
+        config,
     )
 
     # Get the model's response
-    response: AIMessage = await model.ainvoke(message_value, config)
+    response = cast(AIMessage, await model.ainvoke(message_value, config))
 
     # Handle the case when it's the last step and the model still wants to use a tool
-    if state["is_last_step"] and response.tool_calls:
+    if state.is_last_step and response.tool_calls:
         return {
             "messages": [
                 AIMessage(
@@ -89,14 +95,16 @@ def route_model_output(state: State) -> Literal["__end__", "tools"]:
     Returns:
         str: The name of the next node to call ("__end__" or "tools").
     """
-    messages = state["messages"]
-    last_message = messages[-1]
-    # If there is no function call, then we finish
+    last_message = state.messages[-1]
+    if not isinstance(last_message, AIMessage):
+        raise ValueError(
+            f"Expected AIMessage in output edges, but got {type(last_message).__name__}"
+        )
+    # If there is no tool call, then we finish
     if not last_message.tool_calls:
         return "__end__"
-    # Otherwise if there are tools called, we continue
-    else:
-        return "tools"
+    # Otherwise we execute the requested actions
+    return "tools"
 
 
 # Add a conditional edge to determine the next step after `call_model`

src/react_agent/tools.py

@@ -9,12 +9,13 @@
 """
 
 from datetime import datetime, timezone
+from typing import Any, Callable, Dict, List, cast
 
 import httpx
 from langchain.chat_models import init_chat_model
 from langchain_core.runnables import RunnableConfig
 
-from react_agent.configuration import ensure_configurable
+from react_agent.configuration import Configuration
 from react_agent.utils import get_message_text
 
 
@@ -33,8 +34,8 @@ async def scrape_webpage(url: str, instructions: str, *, config: RunnableConfig)
         response = await client.get(url)
         web_text = response.text
 
-    configuration = ensure_configurable(config)
-    model = init_chat_model(configuration["model_name"])
+    configuration = Configuration.from_runnable_config(config)
+    model = init_chat_model(configuration.model_name)
     response_msg = await model.ainvoke(
         [
             (
@@ -53,7 +54,7 @@ async def scrape_webpage(url: str, instructions: str, *, config: RunnableConfig)
 
 
 # Note, in a real use case, you'd want to use a more robust search API.
-async def search_duckduckgo(query: str) -> dict:
+async def search_duckduckgo(query: str) -> Dict[str, Any]:
     """Search DuckDuckGo for the given query and return the JSON response.
 
     Results are limited, as this is the free public API.
@@ -62,13 +63,13 @@ async def search_duckduckgo(query: str) -> dict:
         response = await client.get(
             "https://api.duckduckgo.com/", params={"q": query, "format": "json"}
         )
-        result = response.json()
+        result = cast(Dict[str, Any], response.json())
 
         result.pop("meta", None)
         return result
 
 
-async def search_wikipedia(query: str) -> dict:
+async def search_wikipedia(query: str) -> Dict[str, Any]:
     """Search Wikipedia for the given query and return the JSON response."""
     url = "https://en.wikipedia.org/w/api.php"
     async with httpx.AsyncClient() as client:
@@ -81,10 +82,10 @@ async def search_wikipedia(query: str) -> dict:
                 "format": "json",
             },
         )
-        return response.json()
+        return cast(Dict[str, Any], response.json())
 
 
-TOOLS = [
+TOOLS: List[Callable[..., Any]] = [
     scrape_webpage,
     search_duckduckgo,
     search_wikipedia,

src/react_agent/utils.py

@@ -1,9 +1,9 @@
 """Utility & helper functions."""
 
-from langchain_core.messages import AnyMessage
+from langchain_core.messages import BaseMessage
 
 
-def get_message_text(msg: AnyMessage) -> str:
+def get_message_text(msg: BaseMessage) -> str:
     """Get the text content of a message."""
     content = msg.content
     if isinstance(content, str):