fix(openai): bridge gpt-5.6+ tools to /v1/responses without reasoning… - #50
Merged
lkapadiya-DO merged 4 commits intoJul 29, 2026
Conversation
…_effort OpenAI rejects gpt-5.6 family tool calls on chat/completions when a default reasoning_effort is applied server-side. Port BerriAI#34043 onto the DO release bridge so tools-only requests auto-route to Responses. Co-authored-by: Cursor <cursoragent@cursor.com>
Google's live Interactions OpenAPI spec now includes queued alongside budget_exceeded; update the DO compliance assertion to match. Co-authored-by: Cursor <cursoragent@cursor.com>
Reformat 15 files that fail black --check on the DO release line; unrelated to the gpt-5.6 responses bridge but required for PR CI to pass. Co-authored-by: Cursor <cursoragent@cursor.com>
Match __anext__; Black reformatting pushed sync __next__ over the statement limit and fails release-branch ruff CI. Co-authored-by: Cursor <cursoragent@cursor.com>
lkapadiya-DO
marked this pull request as ready for review
July 28, 2026 17:31
d-isaacson
approved these changes
Jul 29, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
…_effort
OpenAI rejects gpt-5.6 family tool calls on chat/completions when a default reasoning_effort is applied server-side. Port BerriAI#34043 onto the DO release bridge so tools-only requests auto-route to Responses.
JIRA: https://do-internal.atlassian.net/browse/INF-991
Summary
Port BerriAI/litellm#34043 onto the DO release bridge so gpt-5.6+ + function tools on /v1/chat/completions auto-route to /v1/responses even when reasoning_effort is omitted.
OpenAI applies a default reasoning_effort server-side for this family and rejects tools on chat/completions (use /v1/responses or set reasoning_effort to 'none'), which was blocking IR from rolling out gpt-5.6.
Add is_model_gpt_5_6_plus_model / shared minor-version helper; keep gpt-5.4/5.5 tools-only on chat completions (unchanged).
Also includes DO release-branch CI fixes needed for this PR: OpenAPI status enum (queued), Black formatting, and Ruff PLR0915 noqa on Anthropic stream next.
Relevant issues
BerriAI#33221
Test
Case 1: 5.6 + tools, no reasoning_effort
Request:
Response(Before this change):
Response(After this change):
Case 2: Streaming + tools, no reasoning_effort
Request:
Response(Before this change):
Response(After this change):
Case 3: Multi-tool call
Request:
Response(Before this change):
Response(After this change):
Test plan
[x] Unit: responses_api_bridge + is_model_gpt_5_6_plus tests
[x] Preview via inference-proxy