Genkit Python SDK v0.11.0 Improves Error Handling, Video Integration, and Model Configuration

The Genkit Python SDK v0.11.0 enhances developer experience by preventing loss of model replies during certain `generate()` failures, allowing retries from successful tool rounds. It introduces a new asynchronous `Veo` model for video generation via polling operations, treating video as a background job. Additionally, the update unifies provider HTTP errors into a single `GenkitError` type, simplifying error handling and retries across different AI models. Developers can now also use typed model references, ensuring configuration compatibility and better auto-completion for `generate()` calls.

• →Telemetry export no longer stalls generate() or dumps httpx tracebacks onto the shared genkit start TTY (#5978)
• →The Python reflection server no longer sends a wildcard Access-Control-Allow-Origin (#6198)
• →OpenAI gpt-image-1 no longer sends response_format (the endpoint rejects it). DALL-E still defaults to b64_json (#6167)
• →OpenAI streaming now requests and populates token usage (include_usage) (#6229)
• →Responses-API-only ids (gpt-5.1-codex, o3-pro, …) are gone from the OpenAI chat catalog. This plugin speaks Chat Completions (#6223)