[Feat] Return response_id == upstream response ID for VertexAI + Google AI studio (Stream+Non stream)

[ishaan-jaff]

[Feat] Return response_id == upstream response ID for VertexAI + Google AI studio (Stream+Non stream)

Returns the upstream response ID from Vertex AI and Google AI Studio for both streaming and non-streaming responses.

Key changes

• stream + non-stream response ids from litellm will now be the same as the upstream api response IDs
• we follow this pattern for openai, azure and are working towards following this standard for all providers.

Relevant issues

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

• I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement - see details
• I have added a screenshot of my new test passing locally
• My PR passes all unit tests on make test-unit
• My PR's scope is as isolated as possible, it only solves 1 specific problem

Type

🆕 New Feature
✅ Test

Changes

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
litellm	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Jun 6, 2025 0:03am

[Copilot]

Pull Request Overview

This PR implements a new feature that returns the upstream response ID from Vertex AI and Google AI Studio for both streaming and non-streaming responses.

• A new test has been added to verify that the response ID is preserved.
• The transformation logic in the Vertex AI Gemini module has been updated to extract and assign the response ID from the API responses.
• Minor formatting adjustments have been made in supporting files, including the streaming handler.

Reviewed Changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated no comments.

File	Description
tests/test_litellm/llms/vertex_ai/gemini/test_vertex_and_google_ai_studio_gemini.py	Adds a test verifying proper response ID assignment for non-streaming responses
litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py	Updates response transformation to extract and assign the upstream response ID
litellm/litellm_core_utils/streaming_handler.py	Adjusts formatting and removes a fallback assignment regarding the response ID

Comments suppressed due to low confidence (1)

litellm/litellm_core_utils/streaming_handler.py:621

• Consider verifying that the removal of the fallback assignment for self.response_id is intentional, ensuring that the response ID is properly propagated in all relevant scenarios.

else:
            self.response_id = model_response.id  # type: ignore