Adding response_id in Streaming Response

[Vidit-Ostwal]

More context here

Fixes #3845

#3739 (comment)

---

Note

Add response_id to LLMStreamChunkEvent and plumb it through streaming flows (LiteLLM and native providers) with updated tests.

• Events
  • Add response_id to LLMStreamChunkEvent in events/types/llm_events.py.
• Core LLM (LiteLLM streaming)
  • Capture chunk id as response_id and include in LLMStreamChunkEvent emissions.
  • Pass response_id into _handle_streaming_tool_calls and related emissions in llm.py.
• Base LLM
  • Extend _emit_stream_chunk_event to accept and emit response_id.
• Native Providers (streaming)
  • Anthropic: extract event.message.id and emit with chunks.
  • Azure: include update.id in chunk events.
  • Bedrock: use contentBlockIndex as response_id for deltas.
  • Gemini: forward chunk.response_id in chunk events.
  • OpenAI: forward chunk.id during streaming (including structured streaming path).
• Tests
  • Update streaming tests to set/validate response_id in Azure, OpenAI, and event utility tests.

^{Written by Cursor Bugbot for commit 51b78f3. This will update automatically on new commits. Configure here.}

[cursor]

This is the final PR Bugbot will review for you during this billing cycle

Your free Bugbot reviews will reset on November 28

Details

Your team is on the Bugbot Free tier. On this plan, Bugbot will review limited PRs each billing cycle for each member of your team.

To receive Bugbot reviews on all of your PRs, visit the Cursor dashboard to activate Pro and start your 14-day free trial.

[Vidit-Ostwal]

Adding documentation for easy references.

[Vidit-Ostwal]

Fixes #3845

[Vidit-Ostwal]

Requesting this one for a review @lucasgomide

[Vidit-Ostwal]

Adding every documentation here:

1. Litellm : https://docs.litellm.ai/docs/completion/stream
2. Anthropic : https://docs.claude.com/en/docs/build-with-claude/streaming#basic-streaming-request
3. Azure : https://learn.microsoft.com/en-us/python/api/azure-ai-inference/azure.ai.inference.models.streamingchatcompletionsupdate?view=azure-python-preview
4. Bedrock : https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference-call.html
5. Gemini : https://googleapis.github.io/python-genai/genai.html#genai.types.GenerateContentResponse
6. OpenAI : https://platform.openai.com/docs/api-reference/responses-streaming/response/in_progress

[Vidit-Ostwal]

Just a gentle ping on this one @greysonlalonde,
I think this will be complement on the recent PR on streaming support on crew and flows.

[greysonlalonde]

Hey @Vidit-Ostwal thanks for this! Will get it in soon, we're on holiday right now

[Vidit-Ostwal]

Hey @Vidit-Ostwal thanks for this! Will get it in soon, we're on holiday right now

Yup no worries..