github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-05-06 10:58:17 -05:00
Code Issues 1.2k Packages Projects Releases 126 Wiki Activity

[PR #22556] [CLOSED] fix: use max_completion_tokens for newer OpenAI models #26755

New Issue
Closed
opened 2026-04-20 06:41:31 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-20 06:41:31 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/22556
Author: @alvinttang
Created: 3/11/2026
Status: ❌ Closed

Base: dev ← Head: fix/max-completion-tokens

📝 Commits (10+)

📊 Changes

1 file changed (+42 additions, -20 deletions)

View changed files

📝 backend/open_webui/routers/openai.py (+42 -20)

📄 Description

Summary

  • Newer OpenAI models (gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, gpt-5, gpt-5.2) reject the deprecated max_tokens parameter and require max_completion_tokens instead, causing 400 errors during title/emoji/task generation.
  • Introduces is_openai_new_api_model() to match all models that use the newer API conventions (o-series + gpt-4.1+ + gpt-5+), while keeping is_openai_reasoning_model() for reasoning-specific behavior (system→developer role conversion, temperature restrictions).
  • Adds _extract_model_name() helper to handle provider-prefixed model names (e.g. openai/gpt-5.2 from LiteLLM proxies).

Fixes #22524

Changes

backend/open_webui/routers/openai.py:

  • New _extract_model_name(): strips provider prefixes (openai/gpt-5 → gpt-5)
  • New is_openai_new_api_model(): matches o1, o3, o4, gpt-4.1, gpt-5 families
  • Renamed openai_reasoning_model_handler → openai_new_api_model_handler: applies max_completion_tokens conversion to all newer models, but only applies system→developer role conversion for reasoning models
  • Updated convert_to_azure_payload to use is_openai_new_api_model for token param conversion, while keeping temperature restriction for reasoning models only
  • Updated generate_chat_completion to use the new broader model check

Test plan

  • Verify title generation works with gpt-5.2 as task model (no 400 error)
  • Verify title generation works with gpt-4.1-mini as task model
  • Verify title generation still works with gpt-4o (uses max_tokens)
  • Verify reasoning models (o3, o4-mini) still get system→developer role conversion
  • Verify Ollama models still use max_tokens
  • Verify LiteLLM proxy with prefixed model names (e.g. openai/gpt-5.2) works correctly

Contributor License Agreement

Note

Deleting the CLA section will lead to immediate closure of your PR and it will not be merged in.

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/open-webui/pull/22556 **Author:** [@alvinttang](https://github.com/alvinttang) **Created:** 3/11/2026 **Status:** ❌ Closed **Base:** `dev` ← **Head:** `fix/max-completion-tokens` --- ### 📝 Commits (10+) - [`fe6783c`](https://github.com/open-webui/open-webui/commit/fe6783c16699911c7be17392596d579333fb110c) Merge pull request #19030 from open-webui/dev - [`fc05e0a`](https://github.com/open-webui/open-webui/commit/fc05e0a6c5d39da60b603b4d520f800d6e36f748) Merge pull request #19405 from open-webui/dev - [`e3faec6`](https://github.com/open-webui/open-webui/commit/e3faec62c58e3a83d89aa3df539feacefa125e0c) Merge pull request #19416 from open-webui/dev - [`9899293`](https://github.com/open-webui/open-webui/commit/9899293f050ad50ae12024cbebee7e018acd851e) Merge pull request #19448 from open-webui/dev - [`140605e`](https://github.com/open-webui/open-webui/commit/140605e660b8186a7d5c79fb3be6ffb147a2f498) Merge pull request #19462 from open-webui/dev - [`6f1486f`](https://github.com/open-webui/open-webui/commit/6f1486ffd0cb288d0e21f41845361924e0d742b3) Merge pull request #19466 from open-webui/dev - [`d95f533`](https://github.com/open-webui/open-webui/commit/d95f533214e3fe5beb5e41ec1f349940bc4c7043) Merge pull request #19729 from open-webui/dev - [`a727153`](https://github.com/open-webui/open-webui/commit/a7271532f8a38da46785afcaa7e65f9a45e7d753) 0.6.43 (#20093) - [`6adde20`](https://github.com/open-webui/open-webui/commit/6adde203cd292a9e3af9c64a2ae36b603fed096a) Merge pull request #20394 from open-webui/dev - [`f9b0534`](https://github.com/open-webui/open-webui/commit/f9b0534e0c442631d1cb7205169588b9b6204179) Merge pull request #20522 from open-webui/dev ### 📊 Changes **1 file changed** (+42 additions, -20 deletions) <details> <summary>View changed files</summary> 📝 `backend/open_webui/routers/openai.py` (+42 -20) </details> ### 📄 Description ## Summary - Newer OpenAI models (`gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `gpt-5`, `gpt-5.2`) reject the deprecated `max_tokens` parameter and require `max_completion_tokens` instead, causing 400 errors during title/emoji/task generation. - Introduces `is_openai_new_api_model()` to match all models that use the newer API conventions (o-series + gpt-4.1+ + gpt-5+), while keeping `is_openai_reasoning_model()` for reasoning-specific behavior (system→developer role conversion, temperature restrictions). - Adds `_extract_model_name()` helper to handle provider-prefixed model names (e.g. `openai/gpt-5.2` from LiteLLM proxies). Fixes #22524 ## Changes **`backend/open_webui/routers/openai.py`**: - New `_extract_model_name()`: strips provider prefixes (`openai/gpt-5` → `gpt-5`) - New `is_openai_new_api_model()`: matches `o1`, `o3`, `o4`, `gpt-4.1`, `gpt-5` families - Renamed `openai_reasoning_model_handler` → `openai_new_api_model_handler`: applies `max_completion_tokens` conversion to all newer models, but only applies system→developer role conversion for reasoning models - Updated `convert_to_azure_payload` to use `is_openai_new_api_model` for token param conversion, while keeping temperature restriction for reasoning models only - Updated `generate_chat_completion` to use the new broader model check ## Test plan - [ ] Verify title generation works with `gpt-5.2` as task model (no 400 error) - [ ] Verify title generation works with `gpt-4.1-mini` as task model - [ ] Verify title generation still works with `gpt-4o` (uses `max_tokens`) - [ ] Verify reasoning models (`o3`, `o4-mini`) still get system→developer role conversion - [ ] Verify Ollama models still use `max_tokens` - [ ] Verify LiteLLM proxy with prefixed model names (e.g. `openai/gpt-5.2`) works correctly ### Contributor License Agreement <!-- 🚨 DO NOT DELETE THE TEXT BELOW 🚨 Keep the "Contributor License Agreement" confirmation text intact. Deleting it will trigger the CLA-Bot to INVALIDATE your PR. Your PR will NOT be reviewed or merged until you check the box below confirming that you have read and agree to the terms of the CLA. --> - [x] By submitting this pull request, I confirm that I have read and fully agree to the [Contributor License Agreement (CLA)](https://github.com/open-webui/open-webui/blob/main/CONTRIBUTOR_LICENSE_AGREEMENT), and I am providing my contributions under its terms. > [!NOTE] > Deleting the CLA section will lead to immediate closure of your PR and it will not be merged in. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-20 06:41:31 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#26755
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?