> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# AWS Append Trailing User Message

> Append trailing user messages when Claude 4.6+ ends with an assistant response.

Claude 4.6+ does not support assistant message prefill. Enable `append_trailing_user_message` to append a trailing user turn when the conversation ends with an assistant message (e.g. during reasoning).

```python append_trailing_user_message.py theme={null}
"""
Aws Append Trailing User Message
=================================

Claude 4.6+ does not support assistant message prefill. Enable
`append_trailing_user_message` to append a trailing user turn when the
conversation ends with an assistant message (e.g. during reasoning).

Use `trailing_user_message_content` to customise the appended text (defaults to "continue").

Note: Claude 4.6+ models auto-detect and enable this flag automatically.
"""

from agno.agent import Agent
from agno.models.aws import Claude

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

agent = Agent(
    model=Claude(
        id="us.anthropic.claude-sonnet-4-6",
        append_trailing_user_message=True,
    ),
    markdown=True,
)

# With custom trailing content
agent_custom = Agent(
    model=Claude(
        id="us.anthropic.claude-sonnet-4-6",
        append_trailing_user_message=True,
        trailing_user_message_content=".",
    ),
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response("What is 15 + 27?")
    agent_custom.print_response("What is 15 + 27?")
```

## Run the Example

<Snippet file="create-venv-step.mdx" />

**1. Install dependencies**

```bash theme={null}
uv pip install -U agno "anthropic[bedrock]" aioboto3 boto3
```

**2. Export environment variables**

```bash Mac/Linux theme={null}
export AWS_ACCESS_KEY_ID="your_aws_access_key_id_here"
export AWS_REGION="your_aws_region_here"
export AWS_SECRET_ACCESS_KEY="your_aws_secret_access_key_here"
```

```bash Windows theme={null}
$Env:AWS_ACCESS_KEY_ID="your_aws_access_key_id_here"
$Env:AWS_REGION="your_aws_region_here"
$Env:AWS_SECRET_ACCESS_KEY="your_aws_secret_access_key_here"
```

**3. Run the example**

Save the code above as `append_trailing_user_message.py`, then run:

```bash theme={null}
python append_trailing_user_message.py
```

Full source: [cookbook/90\_models/aws/claude/append\_trailing\_user\_message.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/90_models/aws/claude/append_trailing_user_message.py)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.