Skip to main content

​
Exception Types

The SDK provides typed exceptions for common error scenarios. All exceptions extend the base APIError class. 
from reminix import APIError, AuthenticationError, NotFoundError, RateLimitError

​
APIError (Base)

All SDK errors extend APIError. Catch this to handle any API error. 
try:
    response = client.agents.invoke("my-agent", input={"prompt": "Hello"})
except APIError as e:
    print(e.status_code)  # HTTP status code
    print(e.message)      # Error message
    print(e.body)         # Full error response body

​
Specific Exception Types

ExceptionStatus CodeDescription
AuthenticationError401Invalid or missing API key
NotFoundError404Agent or resource not found
RateLimitError429Too many requests
APIErrorOtherAny other API error

​
Common Patterns

Use specific exception types to handle different failure modes appropriately. 
from reminix import Reminix, APIError, NotFoundError, AuthenticationError

client = Reminix(api_key="your-api-key")

try:
    response = client.agents.invoke("my-agent", input={"prompt": "Hello"})
except AuthenticationError:
    print("Check your API key")
except NotFoundError:
    print("Agent not found — check the name")
except APIError as e:
    if e.status_code == 502:
        print("Agent runtime error — check execution logs")
    elif e.status_code == 504:
        print("Agent timed out")
    else:
        print(f"API error: {e.status_code} {e.message}")
Always catch specific exceptions before the base APIError to ensure proper handling of known error types.

​
Retry Pattern

Implement exponential backoff for rate limits and transient server errors. 
import time
from reminix import APIError, RateLimitError

def invoke_with_retry(client, agent_name, input, max_retries=3):
    for attempt in range(max_retries):
        try:
            return client.agents.invoke(agent_name, input=input)
        except RateLimitError:
            if attempt < max_retries - 1:
                time.sleep(2 ** attempt)
            else:
                raise
        except APIError as e:
            if e.status_code >= 500 and attempt < max_retries - 1:
                time.sleep(2 ** attempt)
            else:
                raise
Only retry on rate limits (429) and server errors (5xx). Retrying on client errors (4xx) other than 429 will always produce the same result.

​
Async Error Handling

Error handling works the same way with the async client. 
from reminix import AsyncReminix, APIError

client = AsyncReminix(api_key="your-api-key")

try:
    response = await client.agents.invoke("my-agent", input={"prompt": "Hello"})
except APIError as e:
    print(f"Error: {e.status_code} {e.message}")

​
Next steps

Errors

Error format, status codes, and execution metadata.

Troubleshooting

Common failures and how to diagnose them.

invoke()

Back to the invoke reference.

chat()

Back to the chat reference.