abbyswag/qwen-code
1
0
Fork 0
mirror of https://github.com/QwenLM/qwen-code.git synced 2025-12-21 17:27:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Vision model support for Qwen-OAuth (#525)

Browse Source 
* refactor: openaiContentGenerator

* refactor: optimize stream handling

* refactor: re-organize refactored files

* fix: unit test cases

* feat: `/model` command for switching to vision model

* fix: lint error

* feat: add image tokenizer to fit vlm context window

* fix: lint and type errors

* feat: add `visionModelPreview` to control default visibility of vision models

* fix: remove deprecated files

* fix: align supported image formats with bailian doc
This commit is contained in:
Mingholy
2025-09-18 13:32:00 +08:00
committed by GitHub
parent 56808ac210
commit 761833c915
41 changed files with 4083 additions and 5336 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
packages/core/src/qwen/qwenContentGenerator.ts
View File

@@ -180,9 +180,7 @@ export class QwenContentGenerator extends OpenAIContentGenerator {
override async countTokens(
request: CountTokensParameters,
): Promise<CountTokensResponse> {
return this.executeWithCredentialManagement(() =>
super.countTokens(request),
);
return super.countTokens(request);
}
/**