[Bug]: GET /api/v1/models/all-models returns null rows or panics when a page straddles the end, and page=1 skips the first page
![[Bug]: GET /api/v1/models/all-models returns null rows or panics when a page straddles the end, and page=1 skips the first page](https://www.chat-gpts.plus/wp-content/uploads/2026/11/21727-74cc2885-768x403.jpg)
该报错通常出现在调用 RAGFlow 的模型目录分页接口( GET /api/v1/models/all-models 或其管理端副本 GET /api/v1/admin/all-models )并传入 page / page_size 参数时,分页切片上界未按实际长度裁剪,且页码按 0 起始偏移处
![[Bug]: Router retries and Retry-After sleeps ignore the caller's request timeout (x-litellm-timeout / x-stainless-timeout)](https://www.chat-gpts.plus/wp-content/uploads/2026/11/49751-63f458d7-768x403.jpg)
![[Bug]: Xiaomi MiMo models: 'output_config' parameter causes AsyncCompletions.create() to fail with Claude Code](https://www.chat-gpts.plus/wp-content/uploads/2026/11/24549-4769d317-768x403.jpg)
![[Bug]: rust vllm-bench result is quite different from vllm bench serve](https://www.chat-gpts.plus/wp-content/uploads/2026/11/59154-ea9f2c53-768x403.jpg)
![[Bug]: [ROCm] Qwen4Exp (AMD path): PLE n-gram IDs read a stale query_start_loc tail during PIECEWISE CUDA-graph replay](https://www.chat-gpts.plus/wp-content/uploads/2026/11/61486-25e2f379-768x403.jpg)
![[Bug]: V1 thinking budget corrupts a multi-token reasoning_end_str under speculative decoding](https://www.chat-gpts.plus/wp-content/uploads/2026/11/58485-85e0f342-768x403.jpg)


![[eager MOE] Selected expert IDs should probably not be treated as 0-d GPU tensors](https://www.chat-gpts.plus/wp-content/uploads/2026/11/49190-31d17efb-768x403.jpg)
