feat: add support for OpenAI gpt-5-chat-latest model #7058
Merged
+12
−0
Conversation
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
![roomote[bot]](https://avatars.githubusercontent.com/in/1546624?s=60&v=4){kind=small}
- Added gpt-5-chat-latest model configuration to openAiNativeModels - Updated OpenAiNativeHandler to recognize gpt-5-chat-latest as a Responses API model - Added comprehensive tests for the new model - Model is optimized for conversational AI and non-reasoning tasks Fixes #7057
dosubot
bot
added
size:L
src/api/providers/openai-native.ts
Outdated
| @@ -1139,7 +1139,8 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio | |||
|
|
|||
| private isResponsesApiModel(modelId: string): boolean { | |||
| // Both GPT-5 and Codex Mini use the v1/responses endpoint | |||
| return modelId.startsWith("gpt-5") || modelId === "codex-mini-latest" | |||
| // gpt-5-chat-latest also uses the Responses API | |||
There was a problem hiding this comment.
It can also use the completions API
src/api/providers/openai-native.ts
Outdated
| @@ -1139,7 +1139,8 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio | |||
|
|
|||
| private isResponsesApiModel(modelId: string): boolean { | |||
| // Both GPT-5 and Codex Mini use the v1/responses endpoint | |||
| return modelId.startsWith("gpt-5") || modelId === "codex-mini-latest" | |||
| // gpt-5-chat-latest also uses the Responses API | |||
| return modelId.startsWith("gpt-5") || modelId === "codex-mini-latest" || modelId === "gpt-5-chat-latest" | |||
There was a problem hiding this comment.
Is this intentional? The condition modelId === "gpt-5-chat-latest" will never be evaluated because modelId.startsWith("gpt-5") already returns true for "gpt-5-chat-latest". The third condition is redundant and can be removed:
Suggested change
| return modelId.startsWith("gpt-5") || modelId === "codex-mini-latest" || modelId === "gpt-5-chat-latest" | |
| return modelId.startsWith("gpt-5") || modelId === "codex-mini-latest" |
| expect(requestBody.previous_response_id).toBe("previous-response-456") | ||
| }) | ||
| }) | ||
| }) |
There was a problem hiding this comment.
Could we add error handling tests similar to other GPT-5 models? For example:
- API error responses (400, 401, 429, etc.)
- Network failures
- Invalid response formats
This would ensure the gpt-5-chat-latest model handles errors consistently with other models.
| const requestBody = JSON.parse(mockFetch.mock.calls[0][1].body) | ||
| expect(requestBody.previous_response_id).toBe("previous-response-456") | ||
| }) | ||
| }) |
There was a problem hiding this comment.
Should we add a test to verify that completePrompt() throws an error for gpt-5-chat-latest? Since this model uses the Responses API, it doesn't support non-streaming completion. Adding this test would prevent regressions:
Suggested change
| }) | |
| describe("Unsupported Operations", () => { | |
| it("should throw error for completePrompt since gpt-5-chat-latest uses Responses API", async () => { | |
| await expect(handler.completePrompt("Test prompt")).rejects.toThrow( | |
| "completePrompt is not supported for gpt-5-chat-latest. Use createMessage (Responses API) instead." | |
| ) | |
| }) | |
| }) | |
| }) |
| @@ -0,0 +1,147 @@ | |||
| import { describe, it, expect, vi, beforeEach } from "vitest" | |||
There was a problem hiding this comment.
Consider moving these tests into the existing "GPT-5 models" describe block in openai-native.spec.ts for better organization. Having all GPT-5 model tests in one place would make it easier to maintain and ensure consistency across similar models.
hannesrudolph
added
the
Issue/PR - Triage
4 tasks
hannesrudolph
added
PR - Needs Preliminary Review
and removed
Issue/PR - Triage
- Remove redundant gpt-5-chat-latest check in isResponsesApiModel since startsWith('gpt-5') already covers it
- Remove unnecessary dedicated test file for gpt-5-chat-latest
dosubot
bot
added
size:S
daniel-lxs
moved this from PR [Needs Prelim Review]
to PR [Needs Review]
in Roo Code Roadmap
mrubens
approved these changes
Aug 16, 2025
github-project-automation
bot
moved this from PR [Needs Review]
to Done
in Roo Code Roadmap
fxcl
added a commit
to tameslabs/Roo-Cline
that referenced
this pull request
Aug 16, 2025
* main: (70 commits) fix: use native Ollama API instead of OpenAI compatibility layer (RooCodeInc#7137) feat: add support for OpenAI gpt-5-chat-latest model (RooCodeInc#7058) Make enhance with task history default to true (RooCodeInc#7140) Bump cloud version to 0.16.0 (RooCodeInc#7135) Release: v1.51.0 (RooCodeInc#7130) Add an API for resuming tasks by ID (RooCodeInc#7122) Add support for task page event population (RooCodeInc#7117) fix: add type check before calling .match() on diffItem.content (RooCodeInc#6905) (RooCodeInc#6906) Fix: Enable save button for provider dropdown and checkbox changes (RooCodeInc#7113) fix: Use cline.cwd as primary source for workspace path in codebaseSearchTool (RooCodeInc#6902) Hotfix multiple folder workspace checkpoint (RooCodeInc#6903) fix: prevent XML entity decoding in diff tools (RooCodeInc#7107) (RooCodeInc#7108) Refactor task execution system: improve call stack management (RooCodeInc#7035) Changeset version bump (RooCodeInc#7104) feat(web): fill missing SEO-related values (RooCodeInc#7096) Update contributors list (RooCodeInc#6883) Release v3.25.15 (RooCodeInc#7103) fix: add /evals page to sitemap generation (RooCodeInc#7102) feat: implement sitemap generation in TypeScript and remove XML file (RooCodeInc#6206) fix: reset condensing state when switching tasks (RooCodeInc#6922) ...
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.
This PR adds support for the OpenAI gpt-5-chat-latest model for non-reasoning tasks.
Changes
gpt-5-chat-latestmodel configuration toopenAiNativeModelsinpackages/types/src/providers/openai.tsOpenAiNativeHandlerto recognizegpt-5-chat-latestas a Responses API modelsrc/api/providers/__tests__/openai-native-gpt5-chat.spec.tsDetails
The
gpt-5-chat-latestmodel is optimized for conversational AI and non-reasoning tasks. It:supportsReasoningEffort: false)Testing
Fixes #7057
Important
Add support for
gpt-5-chat-latestmodel in OpenAI provider, optimized for conversational AI and non-reasoning tasks, with tests and handler updates.gpt-5-chat-latesttoopenAiNativeModelsinopenai.tswith specific features: no reasoning support, supports images, prompt caching, verbosity, and specific pricing.OpenAiNativeHandlerto recognizegpt-5-chat-latestas a Responses API model.gpt-5-chat-latestinopenai-native-gpt5-chat.spec.ts.This description was created by
for ff06f8d. You can customize this summary. It will automatically update as commits are pushed.