Python: Fix #3970: Python: [Bug]: AgentResponse.value is None when streaming workflow#4283
Closed
moonbox3 wants to merge 1 commit intomicrosoft:mainfrom
Closed
Python: Fix #3970: Python: [Bug]: AgentResponse.value is None when streaming workflow#4283moonbox3 wants to merge 1 commit intomicrosoft:mainfrom
AgentResponse.value is None when streaming workflow#4283moonbox3 wants to merge 1 commit intomicrosoft:mainfrom
Conversation
microsoft#3970) The streaming path in Agent.run() was reading response_format from the raw options parameter, which doesn't include values from default_options. The non-streaming path correctly read from ctx["chat_options"] which merges default_options with runtime options. Changed the streaming finalizer to lazily read response_format from the prepared run context (ctx_holder), ensuring default_options.response_format is properly propagated when the stream is finalized. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
github-actions
bot
changed the title
AgentResponse.value is None when streaming workflowAgentResponse.value is None when streaming workflow
Contributor
There was a problem hiding this comment.
Pull request overview
Fixes a Python streaming bug where AgentResponse.value is not populated when response_format is provided via an agent’s default_options (reported in #3970), by ensuring the streaming finalizer uses the merged run context options.
Changes:
- Update the streaming
Agent.run(..., stream=True)finalizer to deriveresponse_formatfrom the prepared run context (chat_options) rather than the rawoptionsargument. - Add a regression test verifying structured output parsing works in streaming when
response_formatis set indefault_options. - Minor test-only formatting cleanup for long assertion messages.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| python/packages/core/agent_framework/_agents.py | Fixes streaming finalization to use merged context options (including default_options response_format). |
| python/packages/core/tests/core/test_agents.py | Adds regression coverage for streaming + default_options["response_format"] parsing (#3970). |
| python/packages/core/tests/core/test_function_invocation_logic.py | Collapses multi-line f-strings in assertions (formatting only). |
|
|
||
| def _finalize_with_context(updates: Sequence[AgentResponseUpdate]) -> AgentResponse: | ||
| ctx = ctx_holder["ctx"] | ||
| response_format = ctx["chat_options"].get("response_format") if ctx else None |
There was a problem hiding this comment.
Streaming finalizer pulls response_format from ctx["chat_options"] but doesn’t apply the same BaseModel subclass validation that the non-streaming path does (where non-BaseModel values are normalized to None). This can lead to inconsistent AgentResponse.response_format contents between streaming and non-streaming runs and can violate the annotated type. Consider reusing the non-streaming validation logic here (or inside _finalize_response_updates) so only type[BaseModel] is propagated for parsing.
Suggested change
| response_format = ctx["chat_options"].get("response_format") if ctx else None | |
| raw_response_format = ctx["chat_options"].get("response_format") if ctx else None | |
| # Normalize response_format so only BaseModel subclasses are propagated, matching non-streaming behavior. | |
| if isinstance(raw_response_format, type) and issubclass(raw_response_format, BaseModel): | |
| response_format = raw_response_format | |
| else: | |
| response_format = None |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Automated fix for #3970.
Verification passed after 0 retries.