openai-php/client

What's Changed

• build(deps): bump shivammathur/setup-php from 2.37.1 to 2.37.2 by @dependabot[bot] in #782
• docs: fix typo in README.md (reponse -> response) by @lingxiaoyiyu-hub in #783
• build(deps): bump actions/checkout from 6.0.3 to 7.0.0 by @dependabot[bot] in #784
• build(deps): bump actions/cache from 5.0.5 to 6.1.0 by @dependabot[bot] in #785
• fix(OpenAI): Support streaming 'compaction' output by @e4se in #787
• fix(OpenAI): default missing optional keys to null in from() by @lazerg in #786
• fix(OpenAI): Preserve function call namespaces by @e4se in #788
• fix(OpenAI): Support 'tool_search' output by @e4se in #789
• release: v0.20.1 by @iBotPeaches in #791

New Contributors

• @lingxiaoyiyu-hub made their first contribution in #783
• @lazerg made their first contribution in #786

Full Changelog: v0.20.0...v0.20.1

What's Changed

• fix missing sequence numbers by @madskildegaard in #764
• fix: guard missing vector store response description for Azure OpenAI compatibility by @jesse-bos in #765
• add support for extra_content in chat response tool calls returned by Gemini models by @leonardfischer in #768
• fix: Handle new OpenAI response keep_alive type by @Fox-Islam in #770
• build(deps): bump shivammathur/setup-php from 2.37.0 to 2.37.1 by @dependabot[bot] in #769
• feat(OpenAI): Add 'tool_search' functionality. by @iBotPeaches in #772
• build(deps): bump actions/checkout from 6.0.2 to 6.0.3 by @dependabot[bot] in #776
• fix(OpenAI): add support for response 'compaction' by @iBotPeaches in #778
• release: v0.20.0 by @iBotPeaches in #779

New Contributors

• @jesse-bos made their first contribution in #765
• @Fox-Islam made their first contribution in #770

Full Changelog: v0.19.2...v0.20.0

What's Changed

• fix: reasoning streaming by @L3o-pold in #751
• Add phase property to OutputMessage by @Copilot in #754
• fix(OpenAI): React properly to server and 'high demand' errors (#730) by @leonardfischer in #757
• fix VectorStoreResponseFileCounts attribute order by @madskildegaard in #756
• Ratelimit event by @iBotPeaches in #761

New Contributors

• @Copilot made their first contribution in #754
• @leonardfischer made their first contribution in #757

Full Changelog: v0.19.1...v0.19.2

What's Changed

• Fix syntax error in README.md example code by @simonschaufi in #741
• fix: default tool call type to function for Mistral compatibility by @ivanmestre in #744
• Add missing fields to OutputImageGenerationToolCall by @Androbin in #742
• feat files missing expiration by @madskildegaard in #746
• fix: vector store description by @madskildegaard in #747
• fix: vector store file contract missing updateAttributes function by @madskildegaard in #748
• chore: format against modern pint defaults by @iBotPeaches in #750
• release: v0.19.1 by @iBotPeaches in #749

New Contributors

• @simonschaufi made their first contribution in #741
• @ivanmestre made their first contribution in #744
• @Androbin made their first contribution in #742

Full Changelog: v0.19.0...v0.19.1

What's Changed

• feat: Responses streaming types by @madskildegaard in #711
• Add 'response.queued' event to CreateStreamedResponse by @boboldehampsink in #712
• Response Retrieve streamed by @boboldehampsink in #713
• build(core): test on php 8.5 by @iBotPeaches in #714
• build(deps): bump actions/checkout from 5 to 6 by @dependabot[bot] in #716
• fix: List items for a conversation. file_id is null and file_data is not present in the API response by @romainnorberg in #715
• Add image streaming support by @boboldehampsink in #720
• Feat: Add Webhook Signature Verification by @Radiergummi in #722
• build(deps): bump actions/cache from 4 to 5 by @dependabot[bot] in #724
• Responses\CreateResponseType optional values are not handled properly by @bbrala in #728
• fix(OpenAI): add support for missing url on web search output by @iBotPeaches in #733
• fix(OpenAI): Add support for empty 'keepalive' stream event. by @iBotPeaches in #734
• fix(OpenAI): don't bail out early on text/plain - only if JSON parsing errors occurred. by @iBotPeaches in #736
• feat: add reasoning_content field to CreateResponseMessage  by @Kemel91 in #737
• release: v0.19.0 by @iBotPeaches in #740

New Contributors

• @madskildegaard made their first contribution in #711
• @boboldehampsink made their first contribution in #712
• @romainnorberg made their first contribution in #715
• @Radiergummi made their first contribution in #722
• @bbrala made their first contribution in #728
• @Kemel91 made their first contribution in #737

Full Changelog: v0.18.0...v0.19.0

What's Changed

• Feature/nano banana by @nmdimas in #685
• fix: Missing properties on container file annotation by @knash94 in #703
• feat: Add containers interface to client by @knash94 in #704
• fix: Allow bytes to be nullable on ContainerFileResponse by @knash94 in #705
• fix(OpenAI): Handle diarized json response in TranscriptionResponseSegment by @olivier-drieux in #706
• feat(OpenAI): add support for actions on web_search_call by @iBotPeaches in #707
• Feat: Add usage to streamed completions by @math625f in #708
• [Release] v0.18.0 by @iBotPeaches in #710

New Contributors

• @nmdimas made their first contribution in #685
• @olivier-drieux made their first contribution in #706
• @math625f made their first contribution in #708

Full Changelog: v0.17.1...v0.18.0

What's Changed

• Add filename property to OutputMessageContentOutputTextAnnotationsF… by @qwertyquest in #696
• chore(OpenAI): unify typing on file citation object by @iBotPeaches in #698
• fix(OpenAI): Apply OpenAI-Beta to all Assistant type resources by @iBotPeaches in #701
• release: v0.17.1 by @iBotPeaches in #702

New Contributors

• @qwertyquest made their first contribution in #696

Full Changelog: v0.17.0...v0.17.1

What's Changed

• chore(OpenAI): deprecate Assistants API officially by @iBotPeaches in #679
• Adds @iBotPeaches to the suggested sponsors in the README by @ianhawes in #677
• fix(OpenAI): have a robust ErrorException to handle object/string error responses. by @iBotPeaches in #682
• feat(OpenAI): add Conversation API by @iBotPeaches in #658
• fix(Doubao): increase nullability on image usage types by @iBotPeaches in #684
• fix(OpenAI) - add missing pagination fields to files.list by @iBotPeaches in #687
• Fix undefined array key errors for xAI Responses API by @dnnp2011 in #689
• fix(OpenAI): prevent registration of headers on all requests by @iBotPeaches in #688
• Update README.md by @carvemerson in #691
• release: v0.17.0 by @iBotPeaches in #694

New Contributors

• @ianhawes made their first contribution in #677
• @dnnp2011 made their first contribution in #689
• @carvemerson made their first contribution in #691

Full Changelog: v0.16.1...v0.17.0

What's Changed

• Handle optional attributes in CreateResponse by @louisbels in #662
• Add sequence_number support to OutputTextDelta. by @e4se in #664
• fix(OpenAI): support mcp error objects in response api by @iBotPeaches in #661
• feat: hosted-tool-choice-web-search by @ymktmk in #665
• fix(OpenAI): Add missing properties to ListInputItems call by @iBotPeaches in #668
• fix(OpenAI): handle null require_approval in Response API by @iBotPeaches in #669
• fix(OpenAI): support nested file search properties by @iBotPeaches in #670
• refactor(meta): unify response types into Actions by @iBotPeaches in #671
• Add support for reasoning text streaming events by @louisbels in #673
• Fix fixture typos. Remove extra spaces from json keys in ThreadRunStreamResponseFixture.txt by @ruslan-polutsygan in #674
• release: v0.16.1 by @iBotPeaches in #676

New Contributors

• @louisbels made their first contribution in #662
• @e4se made their first contribution in #664
• @ymktmk made their first contribution in #665
• @ruslan-polutsygan made their first contribution in #674

Full Changelog: v0.16.0...v0.16.1

What's Changed

• feat(OpenAI): GPT5 support by @iBotPeaches in #639
• fix(OpenAI): add support for reasoning.summary by @iBotPeaches in #642
• #581: Add OverrideStrategy enum for the fakeable trait to support merge/replace by @droath in #646
• chore(meta): rework exception handling by @iBotPeaches in #643
• feat(OpenAI): Add Container File API by @iBotPeaches in #648
• fix(meta): use raw response on ErrorException by @iBotPeaches in #649
• chore(meta): use pest throws instead of internal phpunit methods by @iBotPeaches in #650
• fix(OpenAI): support fine tuning with failed tuning job by @iBotPeaches in #651
• fix(meta): handle 429 (rate limit) gracefully by @iBotPeaches in #652
• fix(OpenAI): augment support for Response API - MCP Connectors by @iBotPeaches in #654
• build(deps): bump actions/checkout from 4 to 5 by @dependabot[bot] in #657
• release: v0.16.0 by @iBotPeaches in #659

New Contributors

• @droath made their first contribution in #646
• @dependabot[bot] made their first contribution in #657

Full Changelog: v0.15.0...v0.16.0

Added

• Add updateAttributes method to VectorStoresFiles (#626)
• Add support for chat completion audio modality (#629)
• Add Containers API (#636)
• Add model field to CreateResponse for embeddings (#634)

Fixed

• Fix streamed response tool call without arguments in VLLM (#623)
• Fix support for code_interpreter_call on retrieve response (#632)
• Fix JSON encoding to preserve UTF-8 characters using JSON_UNESCAPED_UNICODE (#628)

Added

• Add helper method output_text to Responses API (#579)
• Add support for response cancel in Responses API (#588)
• Add support for Image Generation Tool to Responses API (#594)
• Add streaming for Image Generation in Responses API (#602)
• Add support for Code Interpreter to Responses API (#610)
• Add support for Remote MCP Tool in Responses API (#601)
• Add realtime ephemeral tokens (#591)
• Add streaming support for Audio transcriptions (#603)
• Add realtime key documentation (#597)

Fixed

• Add missing index to CreateStreamedResponseToolCall (#562)
• Make $parameters optional in thread create() method (#577)
• Support Azure model.list endpoint (#599)
• Add reasoning_effort support to Assistants (#606)
• Use proper parameter order in Response constructor (#615)
• Support reused prompts/instructions in Responses API (#616)

Changed

• Use proper header notation for Responses API docs (#596)
• Collapse legacy/deprecated sections by default in docs (#609)

Deprecated

• mark Assistants API as deprecated (#607)
• mark Completions API as legacy (#608)

Added

• Add support for Responses API (#541)

Fixed

• Add Throwable type support to ClientFake responses (#576)

Changed

• Removed PHP 8.1 support

Added

• Add logprobs to Chat Response (#533)
• Add ResponseHasMetaInformationContract contract to ThreadRunStepResponse (#523)
• Add support for 'attributes' on vector store files (#551)
• Add OpenAI compatibility support for Google Gemini (#502)
• Add compatibility for Aliyun LLM APIs (#530)
• Add ability to pass arguments to files list request (#557)
• Add search vector store functionality (#559)
• Add Image Response usage (#571)
• Add category applied input types to moderation response (#572)
• Add support for annotations in Chat response (Web Search) (#564)
• Add test coverage for assistants streaming and related functionality (#444)

Changed

• Update GitHub Action deprecations & opt into Dependabot (#544)
• Draw attention away from deprecated completions endpoints in docs (#548)

Fixed

• Fix type definition for responses in ClientFake::addResponses method (#382)
• Fix Content retrieval in HttpTransport with custom HttpClient (#343)
• Fix correct completion endpoint when logprobs missing (#550)
• Fix chat completion choices to allow responses without logprobs field (#554)
• Fix support for streaming of non-OpenAI models that return "ping" (#556)
• Fix OpenRouter token usage response (#560)
• Fix Gemini list models (#567)

Added

• Add http status to ErrorException (#487)
• Add cached_usage to CreateResponseUsage for Chat (#494)
• Add moderation categories (Illicit*) (#495)

Fixed

• Fix missing parameters on FineTuning RetrieveJobResponse (#496)
• Fix nullable description on Assistants Tool Function (#484)
• Fix attachment key missing on ThreadMessageResponse (#471)

Added

• Add thread.run.incomplete to ThreadRunStreamResponse (#421)
• Add withProject to configure the project for the client (#377)
• Add fake b64_json to support mocking (#462)

Fixed

• Fix image url content type to use url instead of file_id (#422)
• Fix type error on VectorStoresFilesTestResources (#460)
• Fix vector store cancel method (#435)

Added

• Add support for Assistants API v2 and Vector Stores endpoints (#420)

Docs

• Add vector store endpoints documentation (#420)

Added

• Add support for Assistants API v2 and Vector Stores endpoint (#405)

Added

• Support for usage stream option on chat endpoint (#398)

Fixed

• Missing output parameter on streamed code interpreter output (#406)

Added

• Add support for Batches endpoint (#403)

Added

• Assistants: add streaming support (#367)

Added

• Audio: add support for timestamp_granularities (#374)

Fixed

• Fix default fake data for meta information (#332)

Added

• ThreadRun: Add "usage" property to the response (#330)

Fixed

• ThreadRunStep: "content" missing in response if result has not been submitted (#319)
• Files: "bytes" in retrieve response is may null (#325)

Added

• Add support for Assistants and Threads endpoint (#271)
• Add stream support for Text To Speech (#235)
• Add test resources for Assistants and Threads (#279)

Changed

• Remove thread messages delete endpoint (#309)

Fixed

• Handle x-request-id in meta information (#283)
• Handle meta information from azure headers (#307)
• Add missing default system_fingerprint to chat create response fixture (#308)
• Convert headers to lower case before creation meta information (#306)

Docs

• Remove threads list endpoint from README.md (#275)
• Clarify assistants files docs (#278)
• Fix image creation example (#297)
• Fix outdated links (#299)
• Add troubleshooting section and explain how to configure HTTP client timeouts

Added

• Add support for Assistants and Threads endpoint (#271)

Removed

• Remove list() from Threads resource

Fixed

• instruction on ThreadRunResponse may be nullable

Added

• Add support for Assistants and Threads endpoint (#243)

Added

• Add RetrieveJobResponseError and batch_size, learning_rate_multiplier parameters on RetrieveJobResponseHyperparameters for fine-tuning endpoint (#255)

Added

• Add revised_prompt property to CreateResponseData on the image create endpoint (#257)

Docs

• Fix model in one of the examples

Added

• Add support for GTP-4 vision on the chat completion endpoint (#241)

Added

• Add support for tool calls on the chat completion endpoint (#239)

Added

• Add support for the audio speech endpoint (#237)

Changed

• Update Models endpoint response object to the latest API changes (#235)

Docs

• Update FineTuning job id names (#230)
• Use Chat resource as the primary example

Fixed

• nEpochs on RetrieveJobResponseHyperparameters may be string
• processingMs ond MetaInformationOpenAI may be null (#218)

Added

• Add "has_more" to fine-tuning jobs and events list responses (#206)

Changed

• Add parameters to the fine-tuning jobs list request to filter the results (#206)

Fixed

• error_code may be int

Fixed

• Missing openai-version header from Azure

Fixed

• Typo in class name MetaInformationOpenAI

Added

• Add support for the fine-tuning API (#199)
• Provide access to header / meta information for all responses (#195)

Changed

• Mark FineTunes resource as deprecated
• Mark Edits resource as deprecated
• Add missing moderation enums (#178)

Fixed

• Chat completion create response with function calling on Azure (#184)
• Breaking change on OpenAI API regarding "transient" field in Audio translations (#168)
• Docs: fix OpenAI URL

Fixed

• Breaking change on OpenAI API regarding "transient" field in Audio (#160)

Changed

• Error handling: use error code as exception message if error message is empty (#150)

Fixed

• Error handling: Catch error in stream responses (#150)
• Error handling: Handle errors where message is an array (#150)

Fixed

• Chat/CreateResponse faking with function_call (#145)

Added

• Add support for function calling in the Chat Completions API (#144)

Fixed

• Exception handling for server error with non default content type header (#134)
• Faking embedding responses for multidimensional vectors (#131)

Added

• Add support for psr/http-message ^2.0 (#130)

Fixed

• fix: stream broken after checking for errors (regression of #113)

Added

• Support for HTTP base uri (#106)

Changed

• unify exception handling between HTTP client implementations (#113)

Fixed

• fix toArray() on CreateStreamedResponseDelta to match the original API response (#108)

Docs

• explain usage for "OpenAI on Azure" (#109)

Added

• Testing support (#71)

Changed

• Trim ApiKey before sending it to the API (#101)

Fixed

• Nullable fields on error response (#102)

Added

• Stream support (#84)

Changed

• Removed dependency for guzzlehttp/guzzle and use PSR-18 client discovery instead (#75)
• Add Client factory which allows for a custom HTTP client
• Client factory further accepts custom HTTP headers, query parameters and API URI

Fixed

• status_details can be a string in file responses. Affects Files and FineTunes resources (#68)

Added

• Audio resource to turn audio into text powered by whisper-1 (#62)

Added

• Chat resource aka ChatGPT powered by gpt-3.5-turbo (#60)

Fixed

• Nullable finish_reason on Completions CreateResponse (#52, 545e0ab)

Fixed

• Missing events on FineTunes RetrieveResponse (#41)

Changed

• OpenAI::client() first argument changed from apiToken to apiKey (#25)

Fixed

• Getting contents from Guzzle's response causing issues with middleware (#33)