> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.vapi.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.vapi.ai/_mcp/server.

1. **Enhanced Tool Retry Logic with Backoff Plans**: You can now use [`Assistant.hooks.do[type=tool].tool.backoffPlan`](https://api.vapi.ai/api#:~:text=CartesiaTranscriber-,BackoffPlan,-%7B) and [`Assistant.hooks.do[type=tool].tool.server.backoffPlan`](https://api.vapi.ai/api#:~:text=CartesiaTranscriber-,BackoffPlan,-%7B) to configure retry behavior for tool calls. Options include:

* **`fixed` backoff** (default): Consistent delay between retries.
* **`exponential` backoff**: Increasing delays for subsequent retries
* **Configurable retry limits**: Set `maxRetries` (0-10, default: 0)
* **Flexible timing**: Adjust `baseDelaySeconds` (0-10 seconds)
* **Smart status code handling**: Exclude specific HTTP status codes from retry attempts.