Betas

Enable Anthropic beta features like context-management with Claude on Vertex AI.

Beta features are experimental capability extensions for Anthropic models. You can use them with the betas parameter of the Agno Claude model class.

betas.py

"""Example demonstrating how to use Anthropic beta features.

Beta features are experimental capability extensions for Anthropic models.
You can use them with the `betas` parameter of the Agno Claude model class.
"""

import anthropic
from agno.agent import Agent
from agno.models.vertexai.claude import Claude

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
# Setup the beta features we want to use
betas = ["context-management-2025-06-27"]
model = Claude(id="claude-sonnet-4@20250514", betas=betas)

# Note: you can see all beta features available in your Anthropic version like this:
all_betas = anthropic.types.AnthropicBetaParam
agent = Agent(model=model, debug_mode=True)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
# The beta features are now activated, the model will have access to use them.
if __name__ == "__main__":
    print("\n=== All available Anthropic beta features ===")
    beta_lines = "\n- ".join(str(b) for b in all_betas.__args__[1].__args__)
    print(f"- {beta_lines}")
    print("=============================================\n")

    print(
        "Note: Not all beta features are available across all inference providers. Read more here: https://platform.claude.com/docs/en/api/overview"
    )

    agent.print_response(
        "My name is John Doe and I live in New York City. I like to bike and hike in the Catskill Mountains."
    )

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U agno "anthropic[vertex]"
   
3. Export environment variables

   Mac/Linux

   export ANTHROPIC_VERTEX_PROJECT_ID="your_anthropic_vertex_project_id_here"
   export CLOUD_ML_REGION="your_cloud_ml_region_here"
   

   $Env:ANTHROPIC_VERTEX_PROJECT_ID="your_anthropic_vertex_project_id_here"
   $Env:CLOUD_ML_REGION="your_cloud_ml_region_here"
   
4. Authenticate with Google Cloud

   Sign in with Application Default Credentials:

   gcloud auth application-default login
   
5. Run the example

   Save the code above as betas.py, then run:

   python betas.py
   

Full source: cookbook/90_models/vertexai/claude/betas.py