chore(deps): update dependency openai to v2
This PR contains the following updates:
| Package | Change | Age | Confidence |
|---|---|---|---|
| openai | ==1.68.2 -> ==2.0.1 |
||
| openai | ==1.99.1 -> ==2.0.1 |
[!WARNING] Some dependencies could not be looked up. Check the Dependency Dashboard for more information.
Release Notes
openai/openai-python (openai)
v2.0.1
Full Changelog: v2.0.0...v2.0.1
Bug Fixes
- api: add status, approval_request_id to MCP tool call (2a02255)
v2.0.0
Full Changelog: v1.109.1...v2.0.0
⚠ BREAKING CHANGES
-
api:
ResponseFunctionToolCallOutputItem.outputandResponseCustomToolCallOutput.outputnow returnstring | Array<ResponseInputText | ResponseInputImage | ResponseInputFile>instead ofstringonly. This may break existing callsites that assumeoutputis always a string.
Features
- api: Support images and files for function call outputs in responses, BatchUsage (4105376)
v1.109.1
Full Changelog: v1.109.0...v1.109.1
Bug Fixes
-
compat: compat with
pydantic<2.8.0when using additional fields (5d95ecf)
v1.109.0
Full Changelog: v1.109.0...v1.109.1
Bug Fixes
-
compat: compat with
pydantic<2.8.0when using additional fields (5d95ecf)
v1.108.2
Full Changelog: v1.108.2...v1.109.0
Features
- api: gpt-5-codex (34502b5)
v1.108.1
Full Changelog: v1.108.1...v1.108.2
Bug Fixes
- api: fix mcp tool name (fd1c673)
Chores
- api: openapi updates for conversations (3224f6f)
- do not install brew dependencies in ./scripts/bootstrap by default (6764b00)
- improve example values (20b58e1)
v1.108.0
Full Changelog: v1.108.0...v1.108.1
Features
- api: add reasoning_text (18d8e12)
Chores
- types: change optional parameter type from NotGiven to Omit (acc190a)
v1.107.3
Full Changelog: v1.107.3...v1.108.0
Features
- api: type updates for conversations, reasoning_effort and results for evals (c2ee28c)
Chores
- internal: update pydantic dependency (369d10a)
v1.107.2
Full Changelog: v1.107.2...v1.107.3
Chores
v1.107.1
Full Changelog: v1.107.1...v1.107.2
Chores
v1.107.0
Full Changelog: v1.107.0...v1.107.1
Chores
- api: fix realtime GA types (570fc5a)
v1.106.1
Full Changelog: v1.106.1...v1.107.0
Features
- api: ship the RealtimeGA API shape (dc319d8)
Chores
- internal: codegen related update (b79b7ca)
v1.106.0
Full Changelog: v1.106.0...v1.106.1
Chores
-
internal: move mypy configurations to
pyproject.tomlfile (ca413a2)
v1.105.0
Full Changelog: v1.105.0...v1.106.0
Features
- client: support callable api_key (#2588) (e1bad01)
- improve future compat with pydantic v3 (6645d93)
v1.104.2
Full Changelog: v1.104.2...v1.105.0
Features
- api: Add gpt-realtime models (8502041)
v1.104.1
Full Changelog: v1.104.1...v1.104.2
Bug Fixes
- types: add aliases back for web search tool types (2521cd8)
v1.104.0
Full Changelog: v1.104.0...v1.104.1
Chores
- api: manual updates for ResponseInputAudio (0db5061)
v1.103.0
Full Changelog: v1.103.0...v1.104.0
Features
- types: replace List[str] with SequenceNotStr in params (bc00bda)
Bug Fixes
- types: update more types to use SequenceNotStr (cff135c)
- types: update some types to SequenceNotStr (03f8b88)
Chores
- remove unused import (ac7795b)
v1.102.0
Full Changelog: v1.102.0...v1.103.0
Features
- api: realtime API updates (b7c2ddc)
Bug Fixes
- responses: add missing params to stream() method (bfc0673)
Chores
- bump
inline-snapshotversion to 0.28.0 (#2590) (a6b0872) - client: format imports (7ae3020)
- internal: add Sequence related utils (d3d72b9)
- internal: fix formatting (3ab273f)
- internal: minor formatting change (478a348)
- internal: update pyright exclude list (66e440f)
v1.101.0
Full Changelog: v1.101.0...v1.102.0
Features
- api: add web search filters (1c199a8)
Bug Fixes
- avoid newer type syntax (bd0c668)
Chores
v1.100.2
Full Changelog: v1.100.2...v1.100.3
Chores
- internal/ci: setup breaking change detection (ca2f936)
v1.100.1
Full Changelog: v1.100.1...v1.100.2
Chores
- api: accurately represent shape for verbosity on Chat Completions (c39d5fd)
v1.100.0
Full Changelog: v1.100.0...v1.100.1
Bug Fixes
- types: revert response text config deletion (ac4fb19)
v1.99.9
Full Changelog: v1.99.9...v1.100.0
Features
- api: add new text parameters, expiration options (e3dfa7c)
v1.99.8
Full Changelog: v1.99.8...v1.99.9
Bug Fixes
- types: actually fix ChatCompletionMessageToolCall type (20cb0c8)
v1.99.7
Full Changelog: v1.99.7...v1.99.8
Bug Fixes
- internal/tests: correct snapshot update comment (2784a7a)
- types: revert ChatCompletionMessageToolCallUnion breaking change (ba54e03)
Chores
- internal/tests: add inline snapshot format command (8107db8)
- internal: fix formatting (f03a03d)
- tests: add responses output_text test (971347b)
Refactors
- tests: share snapshot utils (791c567)
v1.99.6
Full Changelog: v1.99.6...v1.99.7
Bug Fixes
- types: rename ChatCompletionMessageToolCallParam (48085e2)
- types: revert ChatCompletionMessageToolCallParam to a TypedDict (c8e9cec)
v1.99.5
Full Changelog: v1.99.5...v1.99.6
Bug Fixes
- types: re-export more tool call types (8fe5741)
Chores
- internal: update comment in script (e407bb5)
- update @stainless-api/prism-cli to v5.15.0 (a1883fc)
v1.99.4
Full Changelog: v1.99.4...v1.99.5
Bug Fixes
- client: fix verbosity parameter location in Responses (2764ff4)
v1.99.3
Full Changelog: v1.99.3...v1.99.4
Bug Fixes
- types: rename chat completion tool (8d3bf88)
- types: revert ChatCompletionToolParam to a TypedDict (3f4ae72)
v1.99.2
Full Changelog: v1.99.2...v1.99.3
Bug Fixes
- responses: add output_text back (585a4f1)
v1.99.1
Full Changelog: v1.99.1...v1.99.2
Features
- api: adds GPT-5 and new API features: platform.openai.com/docs/guides/gpt-5 (ed370d8)
Bug Fixes
- types: correct tool types (0c57bd7)
Chores
- tests: bump inline-snapshot dependency (e236fde)
v1.99.0
Full Changelog: v1.99.0...v1.99.1
Bug Fixes
- internal: correct event imports (2a6d143)
v1.98.0
Full Changelog: v1.98.0...v1.99.0
Features
Bug Fixes
- add missing prompt_cache_key & prompt_cache_key params (00b49ae)
Chores
- internal: fix ruff target version (aa6b252)
v1.97.2
Full Changelog: v1.97.2...v1.98.0
Features
- api: manual updates (88a8036)
v1.97.1
Full Changelog: v1.97.1...v1.97.2
Chores
- client: refactor streaming slightly to better future proof it (71c0c74)
- project: add settings file for vscode (29c22c9)
v1.97.0
Full Changelog: v1.97.0...v1.97.1
Bug Fixes
Chores
- api: event shapes more accurate (f3a9a92)
v1.96.1
Full Changelog: v1.96.1...v1.97.0
Features
- api: manual updates (ed8e899)
v1.96.0
Full Changelog: v1.96.0...v1.96.1
Chores
- api: update realtime specs (b68b71b)
v1.95.1
Full Changelog: v1.95.1...v1.96.0
Features
- clean up environment call outs (87c2e97)
Chores
- api: update realtime specs, build config (bf06d88)
v1.95.0
Full Changelog: v1.95.0...v1.95.1
Bug Fixes
- client: don't send Content-Type header on GET requests (182b763)
v1.94.0
Full Changelog: v1.94.0...v1.95.0
Features
- api: add file_url, fix event ID (265e216)
Chores
- readme: fix version rendering on pypi (1eee5ca)
v1.93.3
Full Changelog: v1.93.3...v1.94.0
Features
v1.93.2
Full Changelog: v1.93.2...v1.93.3
Bug Fixes
- parsing: correctly handle nested discriminated unions (fc8a677)
v1.93.1
Full Changelog: v1.93.1...v1.93.2
Chores
v1.93.0
Full Changelog: v1.93.0...v1.93.1
Bug Fixes
- ci: correct conditional (de6a9ce)
- responses: add missing arguments to parse (05590ec)
- vector stores: add missing arguments to files.create_and_poll (3152134)
- vector stores: add missing arguments to files.upload_and_poll (9d4f425)
Chores
- ci: change upload type (cd4aa88)
- ci: only run for pushes and fork pull requests (f89c7eb)
- internal: codegen related update (bddb8d2)
- tests: ensure parse method is in sync with create (4f58e18)
- tests: ensure vector store files create and poll method is in sync (0fe75a2)
v1.92.3
Full Changelog: v1.92.3...v1.93.0
Features
v1.92.2
Full Changelog: v1.92.2...v1.92.3
Bug Fixes
- client: avoid encoding error with empty API keys (5a3e64e)
Documentation
v1.92.1
Full Changelog: v1.92.1...v1.92.2
Chores
- api: remove unsupported property (ec24408)
v1.92.0
Full Changelog: v1.92.0...v1.92.1
Chores
- client: sync stream/parse methods over (e2536cf)
- docs: update README to include links to docs on Webhooks (ddbf9f1)
v1.91.0
Full Changelog: v1.91.0...v1.92.0
Features
- api: webhook and deep research support (d3bb116)
- client: move stream and parse out of beta (0e358ed)
Bug Fixes
- ci: release-doctor — report correct token name (ff8c556)
Chores
- internal: add tests for breaking change detection (710fe8f)
- tests: skip some failing tests on the latest python versions (93ccc38)
v1.90.0
Full Changelog: v1.90.0...v1.91.0
Features
- api: update api shapes for usage and code interpreter (060d566)
v1.89.0
Full Changelog: v1.89.0...v1.90.0
Features
- api: make model and inputs not required to create response (11bd62e)
v1.88.0
Full Changelog: v1.88.0...v1.89.0
Features
- client: add support for aiohttp (9218b07)
Bug Fixes
- tests: fix: tests which call HTTP endpoints directly with the example parameters (35bcc4b)
Chores
- readme: update badges (68044ee)
v1.87.0
Full Changelog: v1.87.0...v1.88.0
Features
- api: manual updates (5d18a84)
Chores
v1.86.0
Full Changelog: v1.86.0...v1.87.0
Features
- api: add reusable prompt IDs (36bfe6e)
Bug Fixes
-
client: update service_tier on
client.beta.chat.completions(aa488d5)
Chores
- internal: codegen related update (b1a31e5)
- internal: update conftest.py (bba0213)
- tests: add tests for httpx client instantiation & proxies (bc93712)
v1.85.0
Full Changelog: v1.85.0...v1.86.0
Features
- api: Add o3-pro model IDs (d8dd80b)
v1.84.0
Full Changelog: v1.84.0...v1.85.0
Features
- api: Add tools and structured outputs to evals (002cc7b)
Bug Fixes
-
responses: support raw responses for
parse()(d459943)
v1.83.0
Full Changelog: v1.83.0...v1.84.0
Features
- api: add new realtime and audio models, realtime session options (0acd0da)
Chores
- api: update type names (1924559)
v1.82.1
Full Changelog: v1.82.1...v1.83.0
Features
- api: Config update for pakrym-stream-param (88bcf3a)
- client: add follow_redirects request option (26d715f)
Bug Fixes
- api: Fix evals and code interpreter interfaces (2650159)
-
client: return binary content from
get /containers/{container_id}/files/{file_id}/content(f7c80c4)
Chores
- api: mark some methods as deprecated (3e2ca57)
- deprecate Assistants API (9d166d7)
- docs: remove reference to rye shell (c7978e9)
v1.82.0
Full Changelog: v1.82.0...v1.82.1
Bug Fixes
-
responses: don't include
parsed_argumentswhen re-serialising (6d04193)
Chores
- internal: fix release workflows (361a909)
v1.81.0
Full Changelog: v1.81.0...v1.82.0
Features
- api: new streaming helpers for background responses (2a65d4d)
Bug Fixes
Documentation
v1.80.0
Full Changelog: v1.80.0...v1.81.0
Features
- api: add container endpoint (054a210)
v1.79.0
Full Changelog: v1.79.0...v1.80.0
Features
- api: new API tools (d36ae52)
Chores
- docs: grammar improvements (e746145)
v1.78.1
Full Changelog: v1.78.1...v1.79.0
Features
- api: further updates for evals API (32c99a6)
- api: manual updates (25245e5)
- api: responses x eval api (fd586cb)
- api: Updating Assistants and Evals API schemas (98ba7d3)
Bug Fixes
- fix create audio transcription endpoint (e9a89ab)
Chores
v1.78.0
Full Changelog: v1.78.0...v1.78.1
Bug Fixes
- internal: fix linting due to broken test annotation (5a7d7a0)
- package: support direct resource imports (2293fc0)
v1.77.0
Full Changelog: v1.77.0...v1.78.0
Features
- api: Add reinforcement fine-tuning api support (bebe361)
Bug Fixes
Chores
- internal: update proxy tests (b8e848d)
- use lazy imports for module level client (4d0f409)
- use lazy imports for resources (834813c)
v1.76.2
Full Changelog: v1.76.2...v1.77.0
Features
- api: add image sizes, reasoning encryption (473469a)
Bug Fixes
Chores
- only strip leading whitespace (8467d66)
v1.76.1
Full Changelog: v1.76.1...v1.76.2
Chores
- api: API spec cleanup (0a4d3e2)
v1.76.0
Full Changelog: v1.76.0...v1.76.1
Chores
- broadly detect json family of content-type headers (b4b1b08)
- ci: only use depot for staging repos (35312d8)
- ci: run on more branches and use depot runners (a6a45d4)
v1.75.0
Full Changelog: v1.75.0...v1.76.0
Features
- api: adding new image model support (74d7692)
Bug Fixes
-
pydantic v1: more robust
ModelField.annotationcheck (#2163) (7351b12) - pydantic v1: more robust ModelField.annotation check (eba7856)
Chores
- ci: add timeout thresholds for CI jobs (0997211)
- internal: fix list file params (da2113c)
- internal: import reformatting (b425fb9)
- internal: minor formatting changes (aed1d76)
- internal: refactor retries to not use recursion (8cb8cfa)
- internal: update models test (870ad4e)
- update completion parse signature (a44016c)
v1.74.1
Full Changelog: v1.74.1...v1.75.0
Features
- api: add o3 and o4-mini model IDs (4bacbd5)
v1.74.0
Full Changelog: v1.74.0...v1.74.1
Chores
v1.73.0
Full Changelog: v1.73.0...v1.74.0
Features
- api: adding gpt-4.1 family of model IDs (d4dae55)
Bug Fixes
Chores
v1.72.0
Full Changelog: v1.72.0...v1.73.0
Features
- api: manual updates (a3253dd)
Bug Fixes
Chores
Configuration
📅 Schedule: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined).
🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.
♻ Rebasing: Never, or you tick the rebase/retry checkbox.
🔕 Ignore: Close this PR and you won't be reminded about these updates again.
- [ ] If you want to rebase/retry this PR, check this box
This PR was generated by Mend Renovate. View the repository job log.
Summary of Changes
Hello @renovate-bot, I'm Gemini Code Assist[^1]! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!
This pull request performs a significant upgrade of the openai Python client library across multiple requirements.txt files to version 2.0.1. This update is crucial for maintaining compatibility with the latest OpenAI API features and improvements. Developers should be aware of a breaking change introduced in v2.0.0 concerning the return types of tool call outputs, which may necessitate code modifications. The upgrade also incorporates a wide array of new functionalities, model support, and stability enhancements.
Highlights
-
Major Version Update: The
openaiPython library has been updated to version2.0.1, a significant jump from previous1.xversions (specifically1.68.2and1.99.1). -
Breaking Change in v2.0.0: Version
2.0.0introduces a breaking change whereResponseFunctionToolCallOutputItem.outputandResponseCustomToolCallOutput.outputnow return a more flexible type (string | Array<ResponseInputText | ResponseInputImage | ResponseInputFile>) instead of solely astring. This may require code adjustments in consuming applications. -
API Enhancements: Numerous new API features have been integrated, including support for images and files in function call outputs, new model IDs (e.g.,
gpt-5-codex,gpt-realtime,o3-pro,o4-mini), webhook and deep research support, and updates to the evals API. -
Bug Fixes and Chores: The update includes various bug fixes, such as compatibility with
pydantic<2.8.0, handling of tool call types, and performance optimizations. It also contains numerous internal chore updates and refactorings.
Using Gemini Code Assist
The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.
Invoking Gemini
You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.
| Feature | Command | Description |
|---|---|---|
| Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
| Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
| Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in pull request comments and review comments. |
| Help | /gemini help |
Displays a list of available commands. |
Customization
To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.
Limitations & Feedback
Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with :thumbsup: and :thumbsdown: on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
[^1]: Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.