Common Issues

This page covers common issues and how to fix them.

Agent Not Responding

Symptoms: Agent connects but does not respond to messages.

Possible causes and fixes:

Check your implementation:

1
async def generate_response(self):
2
    # This must yield strings
3
    yield "Hello!"  # Not return, yield

Tool Not Being Called

Symptoms: LLM never calls your tool even when it should.

Possible causes and fixes:

Check your setup:

1
def __init__(self):
2
    super().__init__(name="my-agent")
3
    
4
    self.tool_registry = ToolRegistry()
5
    self.tool_registry.discover(self)  # Must call this
6
    self.tool_schemas = self.tool_registry.get_schemas()  # Must get schemas
7
8
async def generate_response(self):
9
    response = await self.llm.chat(
10
        messages=self.context.messages,
11
        tools=self.tool_schemas,  # Must pass schemas
12
        stream=True
13
    )

Audio Not Playing

Symptoms: Agent responds in logs but user hears nothing.

Possible causes and fixes:

Connection Errors

Symptoms: CLI cannot connect to agent.

Fixes:

1. Check server is running:

   $
   python agent.py

2. Verify port:

   $
   # Should show your agent process
   $
   lsof -i :8080

3. Check for port conflicts:

   1
   app = AtomsCrewApp(setup_handler=setup, port=8081)  # Use different port

LLM Errors

Symptoms: LLM calls fail with errors.

Common errors and fixes:

Add error handling:

1
async def generate_response(self):
2
    try:
3
        response = await self.llm.chat(
4
            messages=self.context.messages,
5
            stream=True
6
        )
7
        async for chunk in response:
8
            if chunk.content:
9
                yield chunk.content
10
                
11
    except Exception as e:
12
        logger.error(f"LLM error: {e}")
13
        yield "I'm having trouble connecting. One moment."

Session Ending Early

Symptoms: Conversation ends unexpectedly.

Possible causes:

Proper setup pattern:

1
async def setup(session: CrewSession):
2
    agent = MyAgent()
3
    session.add_node(agent)
4
    
5
    await session.start()
6
    await session.wait_until_complete()  # Do not forget this

Slow Response Times

Symptoms: Agent takes too long to respond.

Optimization strategies:

Limit context length:

1
async def generate_response(self):
2
    # Keep only last 10 messages
3
    messages = self.context.messages[-10:]
4
    
5
    response = await self.llm.chat(
6
        messages=messages,
7
        stream=True
8
    )

Memory Issues

Symptoms: Agent uses too much memory or crashes.

Fixes:

1. Clear old context periodically:

   1
   if len(self.context.messages) > 50:
   2
       self.context.messages = self.context.messages[-20:]

2. Do not store large data in instance variables

3. Clean up resources in stop:

   1
   async def stop(self):
   2
       self.cached_data = None
   3
       await super().stop()

Import Errors

Symptoms: Module not found or import errors.

Fixes:

1. Install the package:

   $
   pip install smallestai

2. Check Python version (requires 3.10+):

   $
   python --version

3. Check virtual environment is active:

   $
   source venv/bin/activate

Getting Help

If you cannot resolve an issue:

1. Check the Discord for community help
2. Search existing GitHub issues
3. Open a new issue with:
   • Python version
   • SDK version (pip show smallestai)
   • Minimal code to reproduce
   • Full error traceback

Next Steps