Sync fork with upstream: openai-python 3.1.0 - #2
Merged
Conversation
…ate websocket events (openai#3617) ## Summary - Add GPT-5.5 dated and Pro model identifiers, the `ultrafast` Responses service tier, and optional model shutdown dates, including support in the handwritten Responses streaming and parsing helpers. - Represent MCP tool-call failures with one reusable, discriminated structured error model covering protocol, tool-execution, and HTTP errors. Remove the previously advertised string variant because the API neither returns nor accepts it. - Correct Responses WebSocket error events to expose their actual nested error payload, status, headers, sequence numbers, and stream IDs. - Add typed output-text annotations, cache-only web-search controls, and text/image completion-token usage; clarify completed reasoning-item reuse and file-content responses. Co-authored-by: apcha-oai <228803254+apcha-oai@users.noreply.github.com>
Automated Release PR --- ## [3.1.0](openai/openai-python@v3.0.0...v3.1.0) (2026-08-14) ### Features * **api:** add WebSocket stream IDs ([openai#3612](openai#3612)) ([d9029e3](openai@d9029e3)) * **api:** add workload identity access token issued event ([openai#3601](openai#3601)) ([df274d4](openai@df274d4)) * **api:** deprecate Sora video APIs ([openai#3610](openai#3610)) ([721cb1c](openai@721cb1c)) * **api:** Ultrafast tier, structured MCP and websocket errors, separate websocket events ([openai#3617](openai#3617)) ([f38355e](openai@f38355e)) ### Chores * remove Stainless attribution and infrastructure ([openai#3599](openai#3599)) ([a1eeab5](openai@a1eeab5)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). Co-authored-by: openai-sdks[bot] <284451331+openai-sdks[bot]@users.noreply.github.com>
virelai2604
marked this pull request as ready for review
August 15, 2026 00:53
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.
(Fork-sync PR against
virelai2604/openai-python, not a contribution to upstream.)Changes being requested
Brings the fork up to
openai/openai-python@10ee3f0d, picking up 2 upstream commits:10ee3f0df38355ec62 files changed, 249 insertions, 1679 deletions.
Verified after merging:
git diff upstream/main HEADis empty — the fork is byte-identical to official again.Additional context & links
The fork had drifted because upstream released 3.1.0 after the last sync. The merge was clean, as expected — the fork carries no content of its own, only the merge commits from these sync PRs.
Downstream note for
chatgpt-team: its pin isopenai>=3.0,<4.0, so 3.1.0 is already in range and will be picked up on the next dependency install with no change needed. The relay uses the SDK only for theOpenAIErrortype — forwarding is a transparent httpx pass-through — so the new MCP/websocket error types don't affect it.Generated by Claude Code