I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.
Installation Method
Docker
Open WebUI Version
0.6.18
Ollama Version (if applicable)
No response
Operating System
unraid
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
tools calling normally
Actual Behavior
toos names are doubled, and the chat will stopped
Steps to Reproduce
I have tested several llm and the problems are same
Logs & Screenshots
Additional Information
No response
Originally created by @latel on GitHub (Jul 30, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/16138
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
- [x] I am using the latest version of Open WebUI.
### Installation Method
Docker
### Open WebUI Version
0.6.18
### Ollama Version (if applicable)
_No response_
### Operating System
unraid
### 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
tools calling normally
### Actual Behavior
toos names are doubled, and the chat will stopped
### Steps to Reproduce
I have tested several llm and the problems are same
### Logs & Screenshots
<img width="685" height="122" alt="Image" src="https://github.com/user-attachments/assets/f703d20f-969c-4ec4-8396-ec67be0a326d" />
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-05-05 19:27:18 -05:00
Intended behaviour for external tool servers, with that being said PR welcome!
<!-- gh-comment-id:3135402292 -->
@tjbck commented on GitHub (Jul 30, 2025):
Intended behaviour for external tool servers, with that being said PR welcome!
I've seen this cause problems with models; they can see the name repetition as a mistake, and correct it to a single instance, thereby becoming unable to call the tool.
Essentially what we have here is open-webui attempting to enforce uniqueness of tool names by doubling them up, when it should simply respect the tool names that are provided, but flag duplicates and refuse to save such a config or to add conflicting tools, imho.
<!-- gh-comment-id:4295786309 -->
@lee-b commented on GitHub (Apr 22, 2026):
I've seen this cause problems with models; they can see the name repetition as a mistake, and correct it to a single instance, thereby becoming unable to call the tool.
Essentially what we have here is open-webui attempting to enforce uniqueness of tool names by doubling them up, when it should simply respect the tool names that are provided, but flag duplicates and refuse to save such a config or to add conflicting tools, imho.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @latel on GitHub (Jul 30, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/16138
Check Existing Issues
Installation Method
Docker
Open WebUI Version
0.6.18
Ollama Version (if applicable)
No response
Operating System
unraid
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
tools calling normally
Actual Behavior
toos names are doubled, and the chat will stopped
Steps to Reproduce
I have tested several llm and the problems are same
Logs & Screenshots
Additional Information
No response
@tjbck commented on GitHub (Jul 30, 2025):
Intended behaviour for external tool servers, with that being said PR welcome!
@lee-b commented on GitHub (Apr 22, 2026):
I've seen this cause problems with models; they can see the name repetition as a mistake, and correct it to a single instance, thereby becoming unable to call the tool.
Essentially what we have here is open-webui attempting to enforce uniqueness of tool names by doubling them up, when it should simply respect the tool names that are provided, but flag duplicates and refuse to save such a config or to add conflicting tools, imho.