[PR #23305] [CLOSED] fix: improve OpenAI reasoning models support and fix reasoning_effort #50189

New Issue

GiteaMirror · 2026-04-30T02:47:50-05:00

GiteaMirror commented

2026-04-30 02:47:50 -05:00

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/23305
Author: @Kookiejarz
Created: 4/1/2026
Status: ❌ Closed

Base: dev ← Head: fix/openai-reasoning-v2

📝 Commits (1)

8d352b8 fix: improve OpenAI reasoning models support and fix reasoning_effort for Responses API

📊 Changes

3 files changed (+23 additions, -7 deletions)

View changed files

📝 backend/open_webui/routers/openai.py (+20 -5)
📝 backend/open_webui/utils/payload.py (+1 -0)
📝 src/lib/components/chat/Settings/Advanced/AdvancedParams.svelte (+2 -2)

📄 Description

Pull Request Checklist

Note to first-time contributors: Please open a discussion post in Discussions to discuss your idea/fix with the community before creating a pull request, and describe your changes before submitting a pull request.

This is to ensure large feature PRs are discussed with the community first, before starting work on it. If the community does not want this feature or it is not relevant for Open WebUI as a project, it can be identified in the discussion before working on the feature and submitting the PR.

Before submitting, make sure you've checked the following:

Target branch: Verify that the pull request targets the dev branch. PRs targeting main will be immediately closed.
Description: Provide a concise description of the changes made in this pull request down below.
Changelog: Ensure a changelog entry following the format of Keep a Changelog is added at the bottom of the PR description.
Documentation: Add docs in Open WebUI Docs Repository. Document user-facing behavior, environment variables, public APIs/interfaces, or deployment steps.
Dependencies: Are there any new or upgraded dependencies? If so, explain why, update the changelog/docs, and include any compatibility notes. Actually run the code/function that uses updated library to ensure it doesn't crash.
Testing: Perform manual tests to verify the implemented fix/feature works as intended AND does not break any other functionality. Include reproducible steps to demonstrate the issue before the fix. Test edge cases (URL encoding, HTML entities, types). Take this as an opportunity to make screenshots of the feature/fix and include them in the PR description.
Agentic AI Code: Confirm this Pull Request is not written by any AI Agent or has at least gone through additional human review AND manual testing. If any AI Agent is the co-author of this PR, it may lead to immediate closure of the PR.
Code review: Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards?
Design & Architecture: Prefer smart defaults over adding new settings; use local state for ephemeral UI logic. Open a Discussion for major architectural or UX changes.
Git Hygiene: Keep PRs atomic (one logical change). Clean up commits and rebase on dev to ensure no unrelated commits (e.g. from main) are included. Push updates to the existing PR branch instead of closing and reopening.
Title Prefix: To clearly categorize this pull request, prefix the pull request title using one of the following:
- BREAKING CHANGE: Significant changes that may affect compatibility
- build: Changes that affect the build system or external dependencies
- ci: Changes to our continuous integration processes or workflows
- chore: Refactor, cleanup, or other non-functional code changes
- docs: Documentation update or addition
- feat: Introduces a new feature or enhancement to the codebase
- fix: Bug fix or error correction
- i18n: Internationalization or localization changes
- perf: Performance improvement
- refactor: Code restructuring for better maintainability, readability, or scalability
- style: Changes that do not affect the meaning of the code (white space, formatting, missing semi-colons, etc.)
- test: Adding missing tests or correcting existing tests
- WIP: Work in progress, a temporary label for incomplete or ongoing work

Changelog Entry

Description

Note to maintainers: This is a resubmission of PR #23302. I have cleaned up the git history, removed redundant merge commits, and rebased onto the latest dev branch. Sorry for the confusion earlier! :3

This PR improves support for OpenAI reasoning models (such as o1 and o3). It primarily resolves an issue where models were not correctly identified as reasoning models when using model names with prefixes (such as openai/o3-mini and azure/gpt-5). Additionally, it standardises the conversion of the reasoning_effort to reasoning.effort parameter format between the Chat Completions API and the Responses API.

Added

Added support for the reasoning.effort parameter format according to OpenAI's recent API changes for newer models.

Changed

The regular expression logic for is_openai_new_model has been updated to recognise inference models with provider prefixes.
The role mapping logic for inference models has been updated to ensure that prefixed o1-mini and o1-preview models
are correctly downgraded to the user role, whilst other models use the developer role.

Deprecated

[List any deprecated functionality or features that have been removed]

Removed

[List any removed features, files, or functionalities]

Fixed

Fixed an issue where reasoning_effort in the OpenAI Responses API was not correctly nested within the {‘reasoning’: {“effort”: ‘...’}} object.
Fixed a bug where prefixed reasoning models were unable to automatically convert max_tokens to max_completion_tokens.
Prevents Unsupported parameter errors for non-reasoning models (like gpt-4) by automatically stripping reasoning-related parameters from the payload before sending.

Security

[List any new or updated security-related changes, including vulnerability fixes]

Breaking Changes

BREAKING CHANGE: [List any breaking changes affecting compatibility or functionality]

Additional Information

Manual testing and verification: The following scenarios have been verified using a dedicated test_logic.py script:
- Models with prefixes such as openai/o3-mini are correctly identified.
- max_tokens is correctly converted to max_completion_tokens.
- The system role is correctly converted to developer or user depending on the model version.
- Parameters under the Responses API are correctly nested.
- Non-inference models such as gpt-4 are not affected.

Screenshots or Videos

Contributor

License Agreement

By submitting this pull request, I confirm that I have read and fully agree to the Contributor License Agreement (CLA), 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.

_{🔄 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/23305 **Author:** [@Kookiejarz](https://github.com/Kookiejarz) **Created:** 4/1/2026 **Status:** ❌ Closed **Base:** `dev` ← **Head:** `fix/openai-reasoning-v2` --- ### 📝 Commits (1) - [`8d352b8`](https://github.com/open-webui/open-webui/commit/8d352b8774683e2f0abf2a39bcbf7209c723ac60) fix: improve OpenAI reasoning models support and fix reasoning_effort for Responses API ### 📊 Changes **3 files changed** (+23 additions, -7 deletions) <details> <summary>View changed files</summary> 📝 `backend/open_webui/routers/openai.py` (+20 -5) 📝 `backend/open_webui/utils/payload.py` (+1 -0) 📝 `src/lib/components/chat/Settings/Advanced/AdvancedParams.svelte` (+2 -2) </details> ### 📄 Description  # Pull Request Checklist ### Note to first-time contributors: Please open a discussion post in [Discussions](https://github.com/open-webui/open-webui/discussions) to discuss your idea/fix with the community before creating a pull request, and describe your changes before submitting a pull request. This is to ensure large feature PRs are discussed with the community first, before starting work on it. If the community does not want this feature or it is not relevant for Open WebUI as a project, it can be identified in the discussion before working on the feature and submitting the PR. **Before submitting, make sure you've checked the following:** - [x] **Target branch:** Verify that the pull request targets the `dev` branch. **PRs targeting `main` will be immediately closed.** - [x] **Description:** Provide a concise description of the changes made in this pull request down below. - [x] **Changelog:** Ensure a changelog entry following the format of [Keep a Changelog](https://keepachangelog.com/) is added at the bottom of the PR description. - [x] **Documentation:** Add docs in [Open WebUI Docs Repository](https://github.com/open-webui/docs). Document user-facing behavior, environment variables, public APIs/interfaces, or deployment steps. - [x] **Dependencies:** Are there any new or upgraded dependencies? If so, explain why, update the changelog/docs, and include any compatibility notes. Actually run the code/function that uses updated library to ensure it doesn't crash. - [x] **Testing:** Perform manual tests to **verify the implemented fix/feature works as intended AND does not break any other functionality**. Include reproducible steps to demonstrate the issue before the fix. Test edge cases (URL encoding, HTML entities, types). Take this as an opportunity to **make screenshots of the feature/fix and include them in the PR description**. - [x] **Agentic AI Code:** Confirm this Pull Request is **not written by any AI Agent** or has at least **gone through additional human review AND manual testing**. If any AI Agent is the co-author of this PR, it may lead to immediate closure of the PR. - [x] **Code review:** Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards? - [x] **Design & Architecture:** Prefer smart defaults over adding new settings; use local state for ephemeral UI logic. Open a Discussion for major architectural or UX changes. - [x] **Git Hygiene:** Keep PRs atomic (one logical change). Clean up commits and rebase on `dev` to ensure no unrelated commits (e.g. from `main`) are included. Push updates to the existing PR branch instead of closing and reopening. - [x] **Title Prefix:** To clearly categorize this pull request, prefix the pull request title using one of the following: - **BREAKING CHANGE**: Significant changes that may affect compatibility - **build**: Changes that affect the build system or external dependencies - **ci**: Changes to our continuous integration processes or workflows - **chore**: Refactor, cleanup, or other non-functional code changes - **docs**: Documentation update or addition - **feat**: Introduces a new feature or enhancement to the codebase - **fix**: Bug fix or error correction - **i18n**: Internationalization or localization changes - **perf**: Performance improvement - **refactor**: Code restructuring for better maintainability, readability, or scalability - **style**: Changes that do not affect the meaning of the code (white space, formatting, missing semi-colons, etc.) - **test**: Adding missing tests or correcting existing tests - **WIP**: Work in progress, a temporary label for incomplete or ongoing work # Changelog Entry ### Description Note to maintainers: This is a resubmission of PR #23302. I have cleaned up the git history, removed redundant merge commits, and rebased onto the latest dev branch. Sorry for the confusion earlier! :3 - This PR improves support for OpenAI reasoning models (such as o1 and o3). It primarily resolves an issue where models were not correctly identified as reasoning models when using model names with prefixes (such as openai/o3-mini and azure/gpt-5). Additionally, it standardises the conversion of the `reasoning_effort` to `reasoning.effort` parameter format between the Chat Completions API and the Responses API. ### Added - Added support for the `reasoning.effort` parameter format according to OpenAI's recent API changes for newer models. ### Changed - The regular expression logic for `is_openai_new_model` has been updated to recognise inference models with provider prefixes. - The role mapping logic for inference models has been updated to ensure that prefixed `o1-mini` and `o1-preview` models are correctly downgraded to the `user` role, whilst other models use the `developer` role. ### Deprecated - [List any deprecated functionality or features that have been removed] ### Removed - [List any removed features, files, or functionalities] ### Fixed - Fixed an issue where `reasoning_effort` in the OpenAI Responses API was not correctly nested within the {‘reasoning’: {“effort”: ‘...’}} object. - Fixed a bug where prefixed reasoning models were unable to automatically convert `max_tokens` to `max_completion_tokens`. - Prevents Unsupported parameter errors for non-reasoning models (like gpt-4) by automatically stripping reasoning-related parameters from the payload before sending. ### Security - [List any new or updated security-related changes, including vulnerability fixes] ### Breaking Changes - **BREAKING CHANGE**: [List any breaking changes affecting compatibility or functionality] --- ### Additional Information - Manual testing and verification: The following scenarios have been verified using a dedicated test_logic.py script: - [x] Models with prefixes such as openai/o3-mini are correctly identified. - [x] `max_tokens` is correctly converted to `max_completion_tokens`. - [x] The `system` role is correctly converted to `developer` or `user` depending on the model version. - [x] Parameters under the Responses API are correctly nested. - [x] Non-inference models such as `gpt-4` are not affected. ### Screenshots or Videos <img width="1280" height="661" alt="Screenshot 2026-04-01 at 1 20 30 AM" src="https://github.com/user-attachments/assets/350636f3-4f1d-414f-9d29-8c05c5f53af5" /> <img width="1280" height="659" alt="Screenshot 2026-04-01 at 1 16 05 AM" src="https://github.com/user-attachments/assets/9e1e24c2-a4ea-43e3-b2e3-637e2d7ba40a" /> <img width="1277" height="659" alt="Screenshot 2026-04-01 at 1 15 44 AM" src="https://github.com/user-attachments/assets/7a844ac8-f4bf-4568-a56c-c9e85b31f3fb" /> <img width="1058" height="506" alt="Screenshot 2026-04-01 at 1 33 32 AM" src="https://github.com/user-attachments/assets/bbde524e-0b9d-470b-a071-5a014535a2d5" /> ### Contributor License Agreement  - [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 2026-04-30 02:47:50 -05:00

GiteaMirror closed this issue

2026-04-30 02:47:52 -05:00

Sign in to join this conversation.

Branches Tags

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/open-webui#50189