open-webui/backend
Classic298 9d2c3965ff
fix: send max_completion_tokens for Bedrock-prefixed OpenAI models (#30976)
On an Amazon Bedrock OpenAI-compatible connection, GPT-5.6 and GPT-6 models have ids like `us.openai.gpt-6-sol` or `openai.gpt-6-luna`. These were not recognised as new OpenAI models, so `max_tokens` went upstream unchanged and Bedrock rejected it with a 400. Title and emoji generation failed on every chat, and any request with a token limit failed too. Setting `max_completion_tokens` by hand did not help, because non-OpenAI URLs convert it back to `max_tokens`.

`is_openai_new_model()` now drops a leading `openai.` or `<region>.openai.` (`us.`, `eu.`, `global.`, `us-gov.`) before matching, so these ids get the same handling as bare `gpt-5` ids. Ids that are not new models, such as `openai.gpt-oss-120b-1:0` and `gpt-4o`, are unchanged, and so is the LiteLLM `openai/` prefix.

Fixes #30510
2026-09-30 20:09:06 +04:00
..
data refac: mv backend files to /open_webui dir 2024-09-04 16:54:48 +02:00
open_webui fix: send max_completion_tokens for Bedrock-prefixed OpenAI models (#30976) 2026-09-30 20:09:06 +04:00
.dockerignore fix: litellm config issue 2024-02-24 22:35:11 -08:00
.gitignore refac 2024-09-06 04:59:20 +02:00
dev.sh perf: allow disabling websocket per-message-deflate (#28613) 2026-08-24 18:46:07 -04:00
requirements-slim.txt chore: bump pycrdt to 0.14.8 (#31636) 2026-09-30 19:00:23 +04:00
requirements.txt chore: bump pycrdt to 0.14.8 (#31636) 2026-09-30 19:00:23 +04:00
start.sh refac 2026-09-06 16:48:30 -04:00
start_windows.bat chore: drop nltk, unused at the pinned versions (#29725) 2026-09-06 16:39:05 -04:00