Retry

Review retry settings and why invalid model IDs cannot reliably exercise the retry path.

The pinned v2.7.4 source uses the unavailable import from agno.models.cohere import CohereChat and fails before testing retries. It also assumes an invalid model ID reaches the retry path, while invalid-model responses commonly use terminal 400 or 404 statuses.

retry.py

"""Example demonstrating how to set up retries with Cohere."""

from agno.agent import Agent
from agno.models.cohere import CohereChat

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

# We will use a deliberately wrong model ID, to trigger retries.
wrong_model_id = "cohere-wrong-id"

agent = Agent(
    model=CohereChat(
        id=wrong_model_id,
        retries=3,  # Number of times to retry the request.
        delay_between_retries=1,  # Delay between retries in seconds.
        exponential_backoff=True,  # If True, the delay between retries is doubled each time.
    ),
)

agent.print_response("What is the capital of France?")

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass

Current Alternative

Replace from agno.models.cohere import CohereChat with from agno.models.cohere import Cohere and update the constructor name when its capitalization changed. Configure retries, delay_between_retries, and exponential_backoff as shown in Retry Model Requests, then test with a controlled transient 429, connection failure, or 5xx response.

Full source: cookbook/90_models/cohere/retry.py