regenerate files.json

Author: maxkorp

typescript-sdk/apps/dojo/src/files.json

@@ -758,7 +758,7 @@
     },
     {
       "name": "agent.py",
-      "content": "\"\"\"\nA simple agentic chat flow using LangGraph instead of CrewAI.\n\"\"\"\n\nfrom typing import List, Any, Optional\nfrom langchain_core.runnables import RunnableConfig\nfrom langchain_core.messages import SystemMessage\nfrom langchain_openai import ChatOpenAI\nfrom langchain_anthropic import ChatAnthropic\nfrom langchain_google_genai import ChatGoogleGenerativeAI\nfrom langgraph.graph import StateGraph, END, START\nfrom langgraph.graph import MessagesState\nfrom langgraph.types import Command\nfrom langgraph.checkpoint.memory import MemorySaver\n\nclass AgentState(MessagesState):\n    \"\"\"\n    State of our graph.\n    \"\"\"\n    tools: List[Any]\n    model: str\n\nasync def chat_node(state: AgentState, config: Optional[RunnableConfig] = None):\n    \"\"\"\n    Standard chat node based on the ReAct design pattern. It handles:\n    - The model to use (and binds in CopilotKit actions and the tools defined above)\n    - The system prompt\n    - Getting a response from the model\n    - Handling tool calls\n\n    For more about the ReAct design pattern, see:\n    https://www.perplexity.ai/search/react-agents-NcXLQhreS0WDzpVaS4m9Cg\n    \"\"\"\n\n\n    # 1. Define the model\n    model = ChatOpenAI(model=\"o3\")\n    if state[\"model\"] == \"Anthropic\":\n        model = ChatAnthropic(\n            model=\"claude-sonnet-4-20250514\",\n            thinking={\"type\": \"enabled\", \"budget_tokens\": 2000}\n        )\n    elif state[\"model\"] == \"Gemini\":\n        model = ChatGoogleGenerativeAI(model=\"gemini-2.5-pro\", thinking_budget=1024)\n\n    # Define config for the model\n    if config is None:\n        config = RunnableConfig(recursion_limit=25)\n\n    # 2. Bind the tools to the model\n    model_with_tools = model.bind_tools(\n        [\n            *state[\"tools\"],\n            # your_tool_here\n        ],\n    )\n\n    # 3. Define the system message by which the chat model will be run\n    system_message = SystemMessage(\n        content=\"You are a helpful assistant.\"\n    )\n\n    # 4. Run the model to generate a response\n    response = await model_with_tools.ainvoke([\n        system_message,\n        *state[\"messages\"],\n    ], config)\n\n    # 6. We've handled all tool calls, so we can end the graph.\n    return Command(\n        goto=END,\n        update={\n            \"messages\": response\n        }\n    )\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\nworkflow.add_node(\"chat_node\", chat_node)\nworkflow.set_entry_point(\"chat_node\")\n\n# Add explicit edges, matching the pattern in other examples\nworkflow.add_edge(START, \"chat_node\")\nworkflow.add_edge(\"chat_node\", END)\n\n# Conditionally use a checkpointer based on the environment\n# Check for multiple indicators that we're running in LangGraph dev/API mode\nis_fast_api = os.environ.get(\"LANGGRAPH_FAST_API\", \"false\").lower() == \"true\"\n\n# Compile the graph\nif is_fast_api:\n    # For CopilotKit and other contexts, use MemorySaver\n    from langgraph.checkpoint.memory import MemorySaver\n    memory = MemorySaver()\n    graph = workflow.compile(checkpointer=memory)\nelse:\n    # When running in LangGraph API/dev, don't use a custom checkpointer\n    graph = workflow.compile()",
+      "content": "\"\"\"\nA simple agentic chat flow using LangGraph instead of CrewAI.\n\"\"\"\n\nfrom typing import List, Any, Optional\nimport os\n\nfrom langchain_core.runnables import RunnableConfig\nfrom langchain_core.messages import SystemMessage\nfrom langchain_openai import ChatOpenAI\nfrom langchain_anthropic import ChatAnthropic\nfrom langchain_google_genai import ChatGoogleGenerativeAI\nfrom langgraph.graph import StateGraph, END, START\nfrom langgraph.graph import MessagesState\nfrom langgraph.types import Command\nfrom langgraph.checkpoint.memory import MemorySaver\n\nclass AgentState(MessagesState):\n    \"\"\"\n    State of our graph.\n    \"\"\"\n    tools: List[Any]\n    model: str\n\nasync def chat_node(state: AgentState, config: Optional[RunnableConfig] = None):\n    \"\"\"\n    Standard chat node based on the ReAct design pattern. It handles:\n    - The model to use (and binds in CopilotKit actions and the tools defined above)\n    - The system prompt\n    - Getting a response from the model\n    - Handling tool calls\n\n    For more about the ReAct design pattern, see:\n    https://www.perplexity.ai/search/react-agents-NcXLQhreS0WDzpVaS4m9Cg\n    \"\"\"\n\n\n    # 1. Define the model\n    model = ChatOpenAI(model=\"o3\")\n    if state[\"model\"] == \"Anthropic\":\n        model = ChatAnthropic(\n            model=\"claude-sonnet-4-20250514\",\n            thinking={\"type\": \"enabled\", \"budget_tokens\": 2000}\n        )\n    elif state[\"model\"] == \"Gemini\":\n        model = ChatGoogleGenerativeAI(model=\"gemini-2.5-pro\", thinking_budget=1024)\n\n    # Define config for the model\n    if config is None:\n        config = RunnableConfig(recursion_limit=25)\n\n    # 2. Bind the tools to the model\n    model_with_tools = model.bind_tools(\n        [\n            *state[\"tools\"],\n            # your_tool_here\n        ],\n    )\n\n    # 3. Define the system message by which the chat model will be run\n    system_message = SystemMessage(\n        content=\"You are a helpful assistant.\"\n    )\n\n    # 4. Run the model to generate a response\n    response = await model_with_tools.ainvoke([\n        system_message,\n        *state[\"messages\"],\n    ], config)\n\n    # 6. We've handled all tool calls, so we can end the graph.\n    return Command(\n        goto=END,\n        update={\n            \"messages\": response\n        }\n    )\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\nworkflow.add_node(\"chat_node\", chat_node)\nworkflow.set_entry_point(\"chat_node\")\n\n# Add explicit edges, matching the pattern in other examples\nworkflow.add_edge(START, \"chat_node\")\nworkflow.add_edge(\"chat_node\", END)\n\n# Conditionally use a checkpointer based on the environment\n# Check for multiple indicators that we're running in LangGraph dev/API mode\nis_fast_api = os.environ.get(\"LANGGRAPH_FAST_API\", \"false\").lower() == \"true\"\n\n# Compile the graph\nif is_fast_api:\n    # For CopilotKit and other contexts, use MemorySaver\n    from langgraph.checkpoint.memory import MemorySaver\n    memory = MemorySaver()\n    graph = workflow.compile(checkpointer=memory)\nelse:\n    # When running in LangGraph API/dev, don't use a custom checkpointer\n    graph = workflow.compile()",
       "language": "python",
       "type": "file"
     }