[GH-ISSUE #19739] issue: gemini-3-pro returns no response when using native tools #34506

Closed
opened 2026-04-25 08:31:25 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @FujinoXiao on GitHub (Dec 4, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/19739

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

Git Clone

Open WebUI Version

v0.641

Ollama Version (if applicable)

No response

Operating System

ubuntu22.04

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

Model should respond after native tool execution.

Actual Behavior

gemini-3-pro returns empty/no response when using native tools. The tool executes successfully but the model produces no output.

Steps to Reproduce

  1. Connect gemini-3-pro via OpenRouter
  2. Enable any native tool (e.g., a simple random word generator)
  3. Send a prompt that triggers the tool
  4. Observe: tool executes but model returns no response

Logs & Screenshots

Image

Additional Information

No response

Originally created by @FujinoXiao on GitHub (Dec 4, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/19739 ### 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 Git Clone ### Open WebUI Version v0.641 ### Ollama Version (if applicable) _No response_ ### Operating System ubuntu22.04 ### 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 Model should respond after native tool execution. ### Actual Behavior gemini-3-pro returns empty/no response when using native tools. The tool executes successfully but the model produces no output. ### Steps to Reproduce 1. Connect gemini-3-pro via OpenRouter 2. Enable any native tool (e.g., a simple random word generator) 3. Send a prompt that triggers the tool 4. Observe: tool executes but model returns no response ### Logs & Screenshots <img width="1488" height="510" alt="Image" src="https://github.com/user-attachments/assets/45cbb134-2e3c-4b26-8409-4191cfbc224f" /> ### Additional Information _No response_
GiteaMirror added the bug label 2026-04-25 08:31:25 -05:00
Author
Owner

@owui-terminator[bot] commented on GitHub (Dec 4, 2025):

🔍 Similar Issues Found

I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:

  1. #19425 issue: Can't connect to Gemini in v0.6.38
    by davidpede • Nov 24, 2025 • bug

  2. #19532 issue: using the gemini-3-pro-image-preview model via OpenRouter to generate images, multiple identical images are displayed.
    by liuuuu-pro • Nov 27, 2025 • bug

  3. #14440 issue:
    by ehsan8203 • May 28, 2025 • bug

  4. #11598 issue: Gemma3 not giving output
    by tiago375 • Mar 12, 2025 • bug

  5. #19136 issue: tool servers don't work anymore in the latest version v0.6.36
    by isNotOkay • Nov 12, 2025 • bug

Show 5 more related issues
  1. #19563 issue:
    by naruto7g • Nov 28, 2025 • bug

  2. #19518 issue: Duplicate images displayed in gemini-3-pro-image-preview chats
    by davidpede • Nov 26, 2025 • bug

  3. #13918 issue: Problems with responses
    by washcontacnet1 • May 15, 2025 • bug

  4. #16833 issue: OpenWebUI executes user tools only if browser window is visible
    by semyonc • Aug 22, 2025 • bug

  5. #19170 issue: Settings not honored or understood
    by itguy327 • Nov 13, 2025 • bug


💡 Tips:

  • If this is a duplicate, please consider closing this issue and adding any additional details to the existing one
  • If you found a solution in any of these issues, please share it here to help others

This comment was generated automatically by a bot. Please react with a 👍 if this comment was helpful, or a 👎 if it was not.

<!-- gh-comment-id:3610794449 --> @owui-terminator[bot] commented on GitHub (Dec 4, 2025): 🔍 **Similar Issues Found** I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions: 1. [#19425](https://github.com/open-webui/open-webui/issues/19425) **issue: Can't connect to Gemini in v0.6.38** *by davidpede • Nov 24, 2025 • `bug`* 2. [#19532](https://github.com/open-webui/open-webui/issues/19532) **issue: using the gemini-3-pro-image-preview model via OpenRouter to generate images, multiple identical images are displayed.** *by liuuuu-pro • Nov 27, 2025 • `bug`* 3. [#14440](https://github.com/open-webui/open-webui/issues/14440) **issue:** *by ehsan8203 • May 28, 2025 • `bug`* 4. [#11598](https://github.com/open-webui/open-webui/issues/11598) **issue: Gemma3 not giving output** *by tiago375 • Mar 12, 2025 • `bug`* 5. [#19136](https://github.com/open-webui/open-webui/issues/19136) **issue: tool servers don't work anymore in the latest version v0.6.36** *by isNotOkay • Nov 12, 2025 • `bug`* <details> <summary>Show 5 more related issues</summary> 6. [#19563](https://github.com/open-webui/open-webui/issues/19563) **issue:** *by naruto7g • Nov 28, 2025 • `bug`* 7. [#19518](https://github.com/open-webui/open-webui/issues/19518) **issue: Duplicate images displayed in gemini-3-pro-image-preview chats** *by davidpede • Nov 26, 2025 • `bug`* 8. [#13918](https://github.com/open-webui/open-webui/issues/13918) **issue: Problems with responses** *by washcontacnet1 • May 15, 2025 • `bug`* 9. [#16833](https://github.com/open-webui/open-webui/issues/16833) **issue: OpenWebUI executes user tools only if browser window is visible** *by semyonc • Aug 22, 2025 • `bug`* 10. [#19170](https://github.com/open-webui/open-webui/issues/19170) **issue: Settings not honored or understood** *by itguy327 • Nov 13, 2025 • `bug`* </details> --- 💡 **Tips:** - If this is a duplicate, please consider closing this issue and adding any additional details to the existing one - If you found a solution in any of these issues, please share it here to help others *This comment was generated automatically by a bot.* Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
Author
Owner

@FujinoXiao commented on GitHub (Dec 4, 2025):

Reviewed related issues - no duplicates found. This issue can be reliably reproduced with the steps provided.

<!-- gh-comment-id:3610796954 --> @FujinoXiao commented on GitHub (Dec 4, 2025): Reviewed related issues - no duplicates found. This issue can be reliably reproduced with the steps provided.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#34506