Repository navigation
Closed
Labels
bugUnexpected behavior, regression, or defect in Cherry StudioUnexpected behavior, regression, or defect in Cherry StudiomodelsRelated to model providers, configuration, capabilities, or compatibilityRelated to model providers, configuration, capabilities, or compatibility
Description
Issue Checklist
- I understand that issues are for feedback and problem solving, not for complaining in the comment section, and will provide as much information as possible to help solve the problem.
- My issue is not listed in the FAQ.
- I've looked at pinned issues and searched for existing Open Issues, Closed Issues, and Discussions, no similar issue or discussion was found.
- I've filled in short, clear headings so that developers can quickly identify a rough idea of what to expect when flipping through the list of issues. And not "a suggestion", "stuck", etc.
- I've confirmed that I am using the latest version of Cherry Studio.
Platform
macOS
Version
v1.6.2
Bug Description
GPT-5 Codex from GitHub Copilot is currently unsupported. The error message says "model gpt-5-codex is not supported in this VS Code version. Please update it to version 1.104.1 or newer".
According to the discussion at zed-industries/zed#38858, /responses endpoint should be used for GPT-5 Codex from GitHub Copilot instead of /chat/completion endpoint.
Steps To Reproduce
- Set up GitHub Copilot Provider
- Add the model with ID
gpt-5-codex - Send a random message to it
- Encounter error
Expected Behavior
The model should respond normally like other models.
Relevant Log Output
Error name: AI_APICallError
Error Message: model gpt-5-codex is not supported in this VS Code version. Please update it to version 1.104.1 or newer
Stack Trace: AI_APICallError: model gpt-5-codex is not supported in this VS Code version. Please update it to version 1.104.1 or newer
at file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/dist-DljPbAPG.js:4456:11
at async postToApi (file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/dist-DljPbAPG.js:4352:24)
at async OpenAICompatibleChatLanguageModel.doStream (file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/store-D-H00nsq.js:48200:48)
at async wrapStream (file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/store-D-H00nsq.js:41532:31)
at async fn (file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/store-D-H00nsq.js:39723:17)
at async file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/store-D-H00nsq.js:37132:19
at async _retryWithExponentialBackoff (file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/store-D-H00nsq.js:37234:10)
at async streamStep (file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/store-D-H00nsq.js:39691:108)
at async fn (file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/store-D-H00nsq.js:39970:5)
at async file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/store-D-H00nsq.js:37132:19
Error cause: "[undefined]"
Status Code: 400
Request URL: https://api.githubcopilot.com/chat/completions
Request Body Values: {
"model": "gpt-5-codex",
"user": "[undefined]",
"max_tokens": "[undefined]",
"temperature": "[undefined]",
"top_p": "[undefined]",
"frequency_penalty": "[undefined]",
"presence_penalty": "[undefined]",
"response_format": "[undefined]",
"stop": "[undefined]",
"seed": "[undefined]",
"reasoning_effort": "[undefined]",
"serviceTier": "[undefined]",
"messages": [
{
"role": "user",
"content": "hi"
}
],
"tools": "[undefined]",
"tool_choice": "[undefined]",
"stream": true,
"stream_options": {
"include_usage": true
}
}
Response Header: {
"content-length": "169",
"content-type": "text/plain; charset=utf-8",
"date": "Tue, 07 Oct 2025 12:55:16 GMT",
"strict-transport-security": "max-age=31536000",
"x-content-type-options": "nosniff",
"x-github-backend": "Kubernetes",
"x-github-request-id": "E257:2E82E8:331F5CD:3D4DD15:68E50DB4",
"x-request-id": "00000-9449d4ca-d4b6-4465-967c-6eb45d2dff45"
}
Response Body: {
"error": {
"message": "model gpt-5-codex is not supported in this VS Code version. Please update it to version 1.104.1 or newer",
"code": "model_not_supported_in_version"
}
}
Data: {
"error": {
"message": "model gpt-5-codex is not supported in this VS Code version. Please update it to version 1.104.1 or newer",
"code": "model_not_supported_in_version"
}
}Additional Context
No response
Reacted by dosubot
Metadata
Metadata
Assignees
Labels
bugUnexpected behavior, regression, or defect in Cherry StudioUnexpected behavior, regression, or defect in Cherry StudiomodelsRelated to model providers, configuration, capabilities, or compatibilityRelated to model providers, configuration, capabilities, or compatibility
Activity
ous50 commentedon Oct 7, 2025
This is interesting. I may like to have a look, although I am not familiar with OpenAI response format. Just to confirm, is
gpt-5-codexthe only model that requires/supports response format?PeronGH commentedon Oct 7, 2025
According to OpenAI docs, both GPT-5 Codex and GPT-5 Pro do not support the
/chat/completionsendpoint and only support the/responsesendpoint. I guess GitHub Copilot is forced to use the/responsesendpoint for GPT-5 Codex due to this.