feat(chat): support web_search_options parameter for search#438
Open
Komdosh wants to merge 1 commit intoaallam:mainfrom
Open
feat(chat): support web_search_options parameter for search#438Komdosh wants to merge 1 commit intoaallam:mainfrom
Komdosh wants to merge 1 commit intoaallam:mainfrom
Conversation
aallam
added a commit
that referenced
this pull request
Feb 7, 2026
- add Responses API support (create/retrieve/cancel/delete/list input items) - add response models and structured input serialization - add chat compatibility fields: web_search_options, annotations, reasoning_content - fix ChatCompletionRequestBuilder mutability for reasoningEffort/store/maxCompletionTokens - improve ChatResponseFormat compatibility for primitive/object payloads - add compatibility tests and update docs/changelog/api baselines Related PRs: #437 #438 #439 #441 #450 Fixes #440 Refs #446 #454 #377
aallam
added a commit
that referenced
this pull request
Feb 7, 2026
* feat: refresh OpenAI API compatibility - add Responses API support (create/retrieve/cancel/delete/list input items) - add response models and structured input serialization - add chat compatibility fields: web_search_options, annotations, reasoning_content - fix ChatCompletionRequestBuilder mutability for reasoningEffort/store/maxCompletionTokens - improve ChatResponseFormat compatibility for primitive/object payloads - add compatibility tests and update docs/changelog/api baselines Related PRs: #437 #438 #439 #441 #450 Fixes #440 Refs #446 #454 #377 * ci(test): make live API tests opt-in - gate openai-client test execution behind OPENAI_LIVE_TESTS=1 - update shared test harness and misc tests to avoid billable calls by default - disable test retries in live test config to reduce accidental cost - split CI into offline checks + JVM live smoke - add separate scheduled/manual full live workflow - document test-cost behavior in README * ci: run live test jobs only on main Restrict live-smoke-jvm and live-full jobs to refs/heads/main. * ci: run offline checks on PRs and full live tests on main - keep lint/offline checks for pull requests - run full openai-client live suite only on push to main - remove scheduled full-live workflow trigger * ci: remove standalone live-full workflow Live tests now run from build.yml only on pushes to main. * ci: fix workflow expression for live tests Remove secrets context from job-level if and guard live test step with a shell check for OPENAI_API_KEY.
rasharab
added a commit
to unblocked/openai-kotlin
that referenced
this pull request
Apr 2, 2026
… additive changes (#17) * feat: refresh OpenAI API compatibility (aallam#458) * feat: refresh OpenAI API compatibility - add Responses API support (create/retrieve/cancel/delete/list input items) - add response models and structured input serialization - add chat compatibility fields: web_search_options, annotations, reasoning_content - fix ChatCompletionRequestBuilder mutability for reasoningEffort/store/maxCompletionTokens - improve ChatResponseFormat compatibility for primitive/object payloads - add compatibility tests and update docs/changelog/api baselines Related PRs: aallam#437 aallam#438 aallam#439 aallam#441 aallam#450 Fixes aallam#440 Refs aallam#446 aallam#454 aallam#377 * ci(test): make live API tests opt-in - gate openai-client test execution behind OPENAI_LIVE_TESTS=1 - update shared test harness and misc tests to avoid billable calls by default - disable test retries in live test config to reduce accidental cost - split CI into offline checks + JVM live smoke - add separate scheduled/manual full live workflow - document test-cost behavior in README * ci: run live test jobs only on main Restrict live-smoke-jvm and live-full jobs to refs/heads/main. * ci: run offline checks on PRs and full live tests on main - keep lint/offline checks for pull requests - run full openai-client live suite only on push to main - remove scheduled full-live workflow trigger * ci: remove standalone live-full workflow Live tests now run from build.yml only on pushes to main. * ci: fix workflow expression for live tests Remove secrets context from job-level if and guard live test step with a shell check for OPENAI_API_KEY. * fix(images,tests): stabilize live suites for image edits and vector stores (aallam#459) * test(vector-stores): avoid flaky immediate list containment assertion Vector store list responses are paginated/eventually consistent; keep create/retrieve/update/delete assertions and make list check non-brittle. * fix(images): align edit uploads with current API requirements - include default model for image edit requests when omitted - send PNG mime type for image edit/variation file parts - make live image edit tests explicit with model=dall-e-2 * test(chat-vision): remove flaky external image URL dependency Use a deterministic data URL generated from bundled test resources for common live vision tests. * chore(release): prepare 4.1.0 * chore: update maven-publish version * docs: align README and guides with current API surface [skip ci] * Remove upstream-only files: TestResponses.kt, ResponseInput.kt, ResponseId.kt * feat: rename response API methods and reasoning config Agent-Id: agent-d3cedbcf-047f-4488-b327-4bc989eab49d Linked-Note-Id: 95dee90b-6003-487e-82ff-40897eeceace * feat: add response retrieval, deletion, and cancellation endpoints Agent-Id: agent-e1e893ed-1378-4eb9-9911-3c6c4b2c5a7c Linked-Note-Id: fc3a8998-aa78-4d48-a5f2-8b9c3e21ce31 * feat: restore ResponseId value class for response identification Agent-Id: agent-91b7b111-1dd4-45c1-bc0c-5b0615a04d39 * chore: update API surface files * style: fix spotless formatting * ci: update to JDK 17 * fix: regenerate API files for JDK 17 compatibility * build: exclude dokkaHtml from build-maven-local * build: fix signing disable flag in Makefile * build: minimize build-maven-local to JVM-only publications * build: add BOM back to build-maven-local * build: include KMP metadata modules in build-maven-local * build: clean up checksums, javadoc, and tooling metadata from .maven --------- Co-authored-by: Mouaad Aallam <[email protected]>
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
1 participant
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.
Describe your change
Added a web_search_options parameter for web search.
https://platform.openai.com/docs/guides/tools-web-search?api-mode=chat
What problem is this fixing?
Now it is possible to set
search_context_size