github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-07-17 17:02:01 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

[GH-ISSUE #24315] bug: Voice Mode Custom Prompt toggle always re-enables #74864

New Issue
Closed
opened 2026-05-13 07:42:18 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-13 07:42:18 -05:00
Owner
Copy Link

Originally created by @Soakedcardinal on GitHub (May 2, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/24315

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

v0.9.12

Ollama Version (if applicable)

No response

Operating System

linux

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

Admin should be able to disable the voice mode custom prompt UI toggle via env (e.g. ~ENABLE_VOICE_MODE_PROMPT)

Actual Behavior

Environment vars allow changing the prompt, but no way to disable the UI toggle. So users see mixed state after update/restart.

Setting voice mode prompt template variables to empty strings does not disable the voice mode constraints. Model always reports voice mode constraints from the default voice mode prompt when asked in voice mode with the prompt enabled.

Steps to Reproduce

  1. Deploy Open WebUI (Docker)
  2. Set VOICE_MODE_PROMPT_TEMPLATE: "" and DEFAULT_VOICE_MODE_PROMPT_TEMPLATE: ""
  3. Go to Admin Settings > Interface > Voice Mode Custom Prompt
  4. Disable the toggle
  5. Restart container
  6. Toggle is visually re-enabled
  7. Model reports constraints from default voice mode prompt when asked

Logs & Screenshots

UI screenshot would just show toggle state after restart

when pressing save button:

2026-05-02 12:01:36.431 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - <ip-redacted>:0 - "GET /api/models HTTP/1.1" 200
2026-05-02 12:01:41.429 | INFO     | open_webui.config:async_save:266 - Saving 'TASK_MODEL' to the database
2026-05-02 12:01:41.430 | INFO     | open_webui.config:async_save:266 - Saving 'TASK_MODEL_EXTERNAL' to the database
2026-05-02 12:01:41.431 | INFO     | open_webui.config:async_save:266 - Saving 'ENABLE_TITLE_GENERATION' to the database
2026-05-02 12:01:41.432 | INFO     | open_webui.config:async_save:266 - Saving 'TITLE_GENERATION_PROMPT_TEMPLATE' to the database
2026-05-02 12:01:41.433 | INFO     | open_webui.config:async_save:266 - Saving 'ENABLE_FOLLOW_UP_GENERATION' to the database
2026-05-02 12:01:41.434 | INFO     | open_webui.config:async_save:266 - Saving 'FOLLOW_UP_GENERATION_PROMPT_TEMPLATE' to the database
2026-05-02 12:01:41.436 | INFO     | open_webui.config:async_save:266 - Saving 'IMAGE_PROMPT_GENERATION_PROMPT_TEMPLATE' to the database
2026-05-02 12:01:41.436 | INFO     | open_webui.config:async_save:266 - Saving 'ENABLE_AUTOCOMPLETE_GENERATION' to the database
2026-05-02 12:01:41.436 | INFO     | open_webui.config:async_save:266 - Saving 'AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH' to the database
2026-05-02 12:01:41.437 | INFO     | open_webui.config:async_save:266 - Saving 'TAGS_GENERATION_PROMPT_TEMPLATE' to the database
2026-05-02 12:01:41.437 | INFO     | open_webui.config:async_save:266 - Saving 'ENABLE_TAGS_GENERATION' to the database
2026-05-02 12:01:41.438 | INFO     | open_webui.config:async_save:266 - Saving 'ENABLE_SEARCH_QUERY_GENERATION' to the database
2026-05-02 12:01:41.438 | INFO     | open_webui.config:async_save:266 - Saving 'ENABLE_RETRIEVAL_QUERY_GENERATION' to the database
2026-05-02 12:01:41.438 | INFO     | open_webui.config:async_save:266 - Saving 'QUERY_GENERATION_PROMPT_TEMPLATE' to the database
2026-05-02 12:01:41.439 | INFO     | open_webui.config:async_save:266 - Saving 'TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE' to the database
2026-05-02 12:01:41.439 | INFO     | open_webui.config:async_save:266 - Saving 'VOICE_MODE_PROMPT_TEMPLATE' to the database
2026-05-02 12:01:41.439 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - <ip-redacted>:0 - "POST /api/v1/tasks/config/update HTTP/1.1" 200

see the ENABLE_ vars for the other switches, but none for voice mode prompt

docker exec -it <owui-container-name> printenv | grep VOICE_MODE
VOICE_MODE_PROMPT_TEMPLATE=
DEFAULT_VOICE_MODE_PROMPT_TEMPLATE=

Additional Information

default voice prompt conflicts/duplicates heavily with my existing system prompts

Originally created by @Soakedcardinal on GitHub (May 2, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/24315 ### 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 v0.9.12 ### Ollama Version (if applicable) _No response_ ### Operating System linux ### 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 Admin should be able to disable the voice mode custom prompt UI toggle via env (e.g. ~`ENABLE_VOICE_MODE_PROMPT`) ### Actual Behavior Environment vars allow changing the prompt, but no way to disable the UI toggle. So users see mixed state after update/restart. Setting voice mode prompt template variables to empty strings does not disable the voice mode constraints. Model always reports voice mode constraints from the default voice mode prompt when asked in voice mode with the prompt enabled. ### Steps to Reproduce 1. Deploy Open WebUI (Docker) 2. Set `VOICE_MODE_PROMPT_TEMPLATE: ""` and `DEFAULT_VOICE_MODE_PROMPT_TEMPLATE: ""` 3. Go to Admin Settings > Interface > Voice Mode Custom Prompt 4. Disable the toggle 5. Restart container 6. Toggle is visually re-enabled 7. Model reports constraints from default voice mode prompt when asked ### Logs & Screenshots UI screenshot would just show toggle state after restart when pressing save button: ``` 2026-05-02 12:01:36.431 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - <ip-redacted>:0 - "GET /api/models HTTP/1.1" 200 2026-05-02 12:01:41.429 | INFO | open_webui.config:async_save:266 - Saving 'TASK_MODEL' to the database 2026-05-02 12:01:41.430 | INFO | open_webui.config:async_save:266 - Saving 'TASK_MODEL_EXTERNAL' to the database 2026-05-02 12:01:41.431 | INFO | open_webui.config:async_save:266 - Saving 'ENABLE_TITLE_GENERATION' to the database 2026-05-02 12:01:41.432 | INFO | open_webui.config:async_save:266 - Saving 'TITLE_GENERATION_PROMPT_TEMPLATE' to the database 2026-05-02 12:01:41.433 | INFO | open_webui.config:async_save:266 - Saving 'ENABLE_FOLLOW_UP_GENERATION' to the database 2026-05-02 12:01:41.434 | INFO | open_webui.config:async_save:266 - Saving 'FOLLOW_UP_GENERATION_PROMPT_TEMPLATE' to the database 2026-05-02 12:01:41.436 | INFO | open_webui.config:async_save:266 - Saving 'IMAGE_PROMPT_GENERATION_PROMPT_TEMPLATE' to the database 2026-05-02 12:01:41.436 | INFO | open_webui.config:async_save:266 - Saving 'ENABLE_AUTOCOMPLETE_GENERATION' to the database 2026-05-02 12:01:41.436 | INFO | open_webui.config:async_save:266 - Saving 'AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH' to the database 2026-05-02 12:01:41.437 | INFO | open_webui.config:async_save:266 - Saving 'TAGS_GENERATION_PROMPT_TEMPLATE' to the database 2026-05-02 12:01:41.437 | INFO | open_webui.config:async_save:266 - Saving 'ENABLE_TAGS_GENERATION' to the database 2026-05-02 12:01:41.438 | INFO | open_webui.config:async_save:266 - Saving 'ENABLE_SEARCH_QUERY_GENERATION' to the database 2026-05-02 12:01:41.438 | INFO | open_webui.config:async_save:266 - Saving 'ENABLE_RETRIEVAL_QUERY_GENERATION' to the database 2026-05-02 12:01:41.438 | INFO | open_webui.config:async_save:266 - Saving 'QUERY_GENERATION_PROMPT_TEMPLATE' to the database 2026-05-02 12:01:41.439 | INFO | open_webui.config:async_save:266 - Saving 'TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE' to the database 2026-05-02 12:01:41.439 | INFO | open_webui.config:async_save:266 - Saving 'VOICE_MODE_PROMPT_TEMPLATE' to the database 2026-05-02 12:01:41.439 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - <ip-redacted>:0 - "POST /api/v1/tasks/config/update HTTP/1.1" 200 ``` see the `ENABLE_` vars for the other switches, but none for voice mode prompt ``` docker exec -it <owui-container-name> printenv | grep VOICE_MODE VOICE_MODE_PROMPT_TEMPLATE= DEFAULT_VOICE_MODE_PROMPT_TEMPLATE= ``` ### Additional Information default voice prompt conflicts/duplicates heavily with my existing system prompts
GiteaMirror added the bug label 2026-05-13 07:42:18 -05:00
GiteaMirror commented 2026-05-13 07:42:20 -05:00
Author
Owner
Copy Link

@pr-validator-bot commented on GitHub (May 2, 2026):

⚠️ Missing Issue Title Prefix

@Soakedcardinal, 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:4364225767 --> @pr-validator-bot commented on GitHub (May 2, 2026): # ⚠️ Missing Issue Title Prefix @Soakedcardinal, 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 2026-05-13 07:42:20 -05:00
Author
Owner
Copy Link

@tjbck commented on GitHub (May 8, 2026):

Addressed in dev to introduce a dedicated toggle.

<!-- gh-comment-id:4409663996 --> @tjbck commented on GitHub (May 8, 2026): Addressed in dev to introduce a dedicated toggle.
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#74864
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?