fix: reject multiple response candidates - #6519
Closed
svfat wants to merge 1 commit into
Closed
Conversation
copybara-service Bot
pushed a commit
that referenced
this pull request
Sep 5, 2026
Merge #6519 Only the first candidate was ever used; the extra ones were dropped silently. In streaming (both LiteLLM and Gemini) this also narrows what reaches the caller: candidates or choices carrying a non-zero index are skipped instead of being concatenated into the first candidate's text. PiperOrigin-RevId: 976670666
Collaborator
This was referenced Sep 7, 2026
claxman
added a commit
to claxman/adk-python
that referenced
this pull request
Sep 7, 2026
LlmAgent accepted GenerateContentConfig(candidate_count=2). Gemini and Apigee then billed extra candidates and LlmResponse kept the first one. 25f5214 logs that drop. Construction now errors, same validator as generate_content_config.tools. svfat proposed a request-side raise in google#6519. The landed import kept the log-only half. This check is on LlmAgent, not the adapters. Fixes google#6518
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Closes #6518.
candidate_count > 1before sending model requestWhy
ADK exposes one model result through
LlmResponse, but behavior forcandidate_count > 1was inconsistent:This can give false expectation that multiple results are available. It can
also waste billed candidate tokens when extra outputs are generated and then
discarded.
Complete multi-candidate support would require change to
LlmResponseanddownstream event/streaming APIs. This patch keeps current single-candidate
contract and returns clear error instead of silently ignoring or discarding
results.
Testing
pytest -q tests/unittests/models/test_llm_response.py tests/unittests/models/test_google_llm.py tests/unittests/models/test_litellm.py tests/unittests/models/test_completions_http_client.py