vrr/qwen-code
2
0
Fork 0
mirror of https://github.com/QwenLM/qwen-code.git synced 2026-05-05 23:42:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 11
qwen-code/packages/core/src/models
History
mingholy.lmh 4f58306a15 fix: improve max_tokens handling with conservative defaults 
- Increase DEFAULT_OUTPUT_TOKEN_LIMIT from 16K to 32K
- Remove auto-detection from modelsConfig, apply at provider level
- Use conservative default (min of model limit and 32K) when user hasn't configured max_tokens
- Respect user configuration but cap at model's max output limit to avoid API errors

Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
2026-03-17 17:01:41 +08:00
..
constants.ts Merge pull request #1982 from QwenLM/fix/modality-defaults-pdf-error 2026-03-02 17:42:17 +08:00
index.ts feat: support runtime model selection for both interactive and ACP 2026-02-02 17:52:50 +08:00
modelConfigErrors.ts fix: refine auth message to give explicit tip 2026-01-07 22:58:11 +08:00
modelConfigResolver.test.ts fix: 修复模型常量更新导致的单测失败 2026-02-26 15:45:06 +08:00
modelConfigResolver.ts fix: add model resolution warnings to start warnings 2026-02-26 14:43:07 +08:00
modelRegistry.test.ts refactor: merge coder-model and qwen3.5-plus, remove vision model switching 2026-02-26 14:43:07 +08:00
modelRegistry.ts fix: add modality defaults to prevent API errors when reading PDFs 2026-02-27 20:00:38 +08:00
modelsConfig.test.ts fix: improve max_tokens handling with conservative defaults 2026-03-17 17:01:41 +08:00
modelsConfig.ts fix: improve max_tokens handling with conservative defaults 2026-03-17 17:01:41 +08:00
types.ts Merge pull request #1982 from QwenLM/fix/modality-defaults-pdf-error 2026-03-02 17:42:17 +08:00