github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-05-06 19:08:59 -05:00
Code Issues 1.3k Packages Projects Releases 126 Wiki Activity

[GH-ISSUE #23566] bug: [Bug] OpenAI gpt-5.1 API rejection: reasoning_effort parameter mismatch and local 500 error on Custom Param bypass #35544

New Issue
Closed
opened 2026-04-25 09:44:47 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-25 09:44:47 -05:00
Owner
Copy Link

Originally created by @NinesRepo on GitHub (Apr 10, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/23566

Check Existing Issues

  • I have searched for any existing and/or related issues.
  • I have searched for any existing and/or related discussions.
  • I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
  • I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

v0.8.12

Ollama Version (if applicable)

No response

Operating System

Windows 11 / Docker

Browser (if applicable)

No response

Confirmation

  • I have read and followed all instructions in README.md.
  • I am using the latest version of both Open WebUI and Ollama.
  • I have included the browser console logs.
  • I have included the Docker container logs.
  • I have provided every relevant configuration, setting, and environment variable used in my setup.
  • I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
  • I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
  • Start with the initial platform/version/OS and dependencies used,
  • Specify exact install/launch/configure commands,
  • List URLs visited, user input (incl. example values/emails/passwords if needed),
  • Describe all options and toggles enabled or changed,
  • Include any files or environmental changes,
  • Identify the expected and actual result at each stage,
  • Ensure any reasonably skilled user can follow and hit the same issue.

Expected Behavior

Note:
• Open WebUI Version: v0.8.12
• API Endpoint: OpenAI
• Model ID: gpt-5.1-2025-11-13

Expected Behavior:

Open WebUI should map the UI toggle to the updated reasoning.effort key at the root level of the JSON payload before sending it to OpenAI, bypassing the need for a custom parameter injection.

Actual Behavior

OpenAI’s updated API schema for GPT-5.1 models requires the reasoning parameter to be formatted with dot-notation as reasoning.effort. Currently, Open WebUI sends this parameter with an underscore (reasoning_effort), resulting in an instant API rejection.

Attempting to bypass this using the Custom Parameters feature wraps the correct parameter in a custom_params object, which triggers a local 500 Internal Server Error when routing.

Steps to Reproduce

Steps to Reproduce:

Path A (The API Rejection):

  1. Create a custom Workspace model using gpt-5.1-2025-11-13.
  2. Under Advanced Params, toggle "Reasoning Effort" to Medium.
  3. Send a chat message.
  4. Result: OpenAI rejects the payload with the error: Unsupported parameter: 'reasoning_effort'. In the Responses API, this parameter has moved to 'reasoning.effort'.

Path B (The local 500 Crash):

  1. Return Advanced Params to Default.
  2. Add a Custom Parameter: Key: reasoning.effort, Value: medium.
  3. (Preview JSON confirms it is wrapped as "custom_params": {"reasoning.effort": "medium"})
  4. Send a chat message.
  5. Result: Instant local crash returning 500: Open WebUI: Server Connection Error.

Logs & Screenshots

Image

Additional Information

Additional Context:

I avoided manually editing the SQLite webui.db to force the parameter to the root level due to the risk of database corruption and breaking chat history links.
Currently unable to enable reasoning for 5.1 via API.

Originally created by @NinesRepo on GitHub (Apr 10, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/23566 ### Check Existing Issues - [x] I have searched for any existing and/or related issues. - [x] I have searched for any existing and/or related discussions. - [x] I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!). - [x] I am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version v0.8.12 ### Ollama Version (if applicable) _No response_ ### Operating System Windows 11 / Docker ### Browser (if applicable) _No response_ ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have included the browser console logs. - [x] I have included the Docker container logs. - [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.** - [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc). - [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps: - Start with the initial platform/version/OS and dependencies used, - Specify exact install/launch/configure commands, - List URLs visited, user input (incl. example values/emails/passwords if needed), - Describe all options and toggles enabled or changed, - Include any files or environmental changes, - Identify the expected and actual result at each stage, - Ensure any reasonably skilled user can follow and hit the same issue. ### Expected Behavior Note: • Open WebUI Version: v0.8.12 • API Endpoint: OpenAI • Model ID: gpt-5.1-2025-11-13 **Expected Behavior:** Open WebUI should map the UI toggle to the updated `reasoning.effort` key at the root level of the JSON payload before sending it to OpenAI, bypassing the need for a custom parameter injection. ### Actual Behavior OpenAI’s updated API schema for GPT-5.1 models requires the reasoning parameter to be formatted with dot-notation as `reasoning.effort`. Currently, Open WebUI sends this parameter with an underscore (`reasoning_effort`), resulting in an instant API rejection. Attempting to bypass this using the Custom Parameters feature wraps the correct parameter in a custom_params object, which triggers a local 500 Internal Server Error when routing. ### Steps to Reproduce **Steps to Reproduce:** Path A (The API Rejection): 1. Create a custom Workspace model using gpt-5.1-2025-11-13. 2. Under Advanced Params, toggle "Reasoning Effort" to Medium. 3. Send a chat message. 4. Result: OpenAI rejects the payload with the error: Unsupported parameter: 'reasoning_effort'. In the Responses API, this parameter has moved to 'reasoning.effort'. Path B (The local 500 Crash): 1. Return Advanced Params to Default. 2. Add a Custom Parameter: Key: reasoning.effort, Value: medium. 3. (Preview JSON confirms it is wrapped as "custom_params": {"reasoning.effort": "medium"}) 4. Send a chat message. 5. Result: Instant local crash returning 500: Open WebUI: Server Connection Error. ### Logs & Screenshots ![Image](https://github.com/user-attachments/assets/d6ab4e74-592c-4119-9330-5433dc3d4040) ### Additional Information **Additional Context:** I avoided manually editing the SQLite `webui.db` to force the parameter to the root level due to the risk of database corruption and breaking chat history links. Currently unable to enable reasoning for 5.1 via API.
GiteaMirror added the bug label 2026-04-25 09:44:47 -05:00
GiteaMirror commented 2026-04-25 09:44:49 -05:00
Author
Owner
Copy Link

@pr-validator-bot commented on GitHub (Apr 10, 2026):

⚠️ Missing Issue Title Prefix

@NinesRepo, your issue title is missing a prefix (e.g., bug:, feat:, docs:).

Please update your issue title to include one of the following prefixes:

  • bug: Bug report or error you've encountered
  • feat: Feature request or enhancement suggestion
  • docs: Documentation issue or improvement request
  • question: Question about usage or functionality
  • help: Request for help or support

Example: bug: Login fails when using special characters in password

<!-- gh-comment-id:4220839574 --> @pr-validator-bot commented on GitHub (Apr 10, 2026): # ⚠️ Missing Issue Title Prefix @NinesRepo, your issue title is missing a prefix (e.g., `bug:`, `feat:`, `docs:`). Please update your issue title to include one of the following prefixes: - **bug**: Bug report or error you've encountered - **feat**: Feature request or enhancement suggestion - **docs**: Documentation issue or improvement request - **question**: Question about usage or functionality - **help**: Request for help or support Example: `bug: Login fails when using special characters in password`
GiteaMirror commented 2026-04-25 09:44:49 -05:00
Author
Owner
Copy Link

@Classic298 commented on GitHub (Apr 10, 2026):

Open WebUI should map the UI toggle

Which UI toggle?

Currently, Open WebUI sends this parameter with an underscore (reasoning_effort), resulting in an instant API rejection.

If you mean reasoning effort in advanced model parameters, this is for chat completions

If you use Responses API, which you appear to be using, then you should use the custom parameters. You can add custom paramater in the advanced model settings at the end.

This was asked a few days ago already. Search for existing issues, especially for closed issues. Custom param should be used here

<!-- gh-comment-id:4224706520 --> @Classic298 commented on GitHub (Apr 10, 2026): > Open WebUI should map the UI toggle Which UI toggle? > Currently, Open WebUI sends this parameter with an underscore (reasoning_effort), resulting in an instant API rejection. If you mean reasoning effort in advanced model parameters, this is for chat completions If you use Responses API, which you appear to be using, then you should use the custom parameters. You can add custom paramater in the advanced model settings at the end. This was asked a few days ago already. Search for existing issues, especially for closed issues. Custom param should be used here
GiteaMirror commented 2026-04-25 09:44:50 -05:00
Author
Owner
Copy Link

@Classic298 commented on GitHub (Apr 10, 2026):

Path B
Result: Instant local crash returning 500: Open WebUI: Server Connection Error.

Cannot reproduce - how did you configure your connection

<!-- gh-comment-id:4224712573 --> @Classic298 commented on GitHub (Apr 10, 2026): > Path B > Result: Instant local crash returning 500: Open WebUI: Server Connection Error. Cannot reproduce - how did you configure your connection
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 bug
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#35544
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?