I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.
Installation Method
Git Clone
Open WebUI Version
0.6.14
Ollama Version (if applicable)
No response
Operating System
Windows 10
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
Code interpreter should display analyzed and then return to the model
Actual Behavior
The code interpreter may show execution success on the console but still display "Analyzing" on the interface
Steps to Reproduce
Enable code interpreter, requiring the model to output "hello"
Observation of prolonged analysis without completion
Open the console and find that the code has already been executed
Finally, the code interpreter timed out and the model generated a response, but did not actually receive the output from the code interpreter
In fact, any code has a probability of encountering this situation
Logs & Screenshots
Additional Information
This issue is not always triggered, but it does exist.
Please don't rush to close; there may be others who will encounter it
Originally created by @EntropyYue on GitHub (Jun 12, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/14936
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
- [x] I am using the latest version of Open WebUI.
### Installation Method
Git Clone
### Open WebUI Version
0.6.14
### Ollama Version (if applicable)
_No response_
### Operating System
Windows 10
### 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
Code interpreter should display analyzed and then return to the model
### Actual Behavior
The code interpreter may show execution success on the console but still display "Analyzing" on the interface
### Steps to Reproduce
Enable code interpreter, requiring the model to output "hello"
Observation of prolonged analysis without completion
Open the console and find that the code has already been executed
Finally, the code interpreter timed out and the model generated a response, but did not actually receive the output from the code interpreter
In fact, any code has a probability of encountering this situation
### Logs & Screenshots
### Additional Information
This issue is not always triggered, but it does exist.
Please don't rush to close; there may be others who will encounter it
GiteaMirror
added the bug label 2026-05-13 03:59:03 -05:00
This happened when I tried to use the code-interpreter today (first time actually) it seems like the output was never sent to the llm and it repeatedly called the interpreter with the same task. So this seems to be quite broken at the moment.
<!-- gh-comment-id:3120055502 -->
@matthid commented on GitHub (Jul 25, 2025):
<img width="1077" height="786" alt="Image" src="https://github.com/user-attachments/assets/20204e1c-735a-4948-bafe-a937770cdf6f" />
This happened when I tried to use the code-interpreter today (first time actually) it seems like the output was never sent to the llm and it repeatedly called the interpreter with the same task. So this seems to be quite broken at the moment.
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 @EntropyYue on GitHub (Jun 12, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/14936
Check Existing Issues
Installation Method
Git Clone
Open WebUI Version
0.6.14
Ollama Version (if applicable)
No response
Operating System
Windows 10
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
Code interpreter should display analyzed and then return to the model
Actual Behavior
The code interpreter may show execution success on the console but still display "Analyzing" on the interface
Steps to Reproduce
Enable code interpreter, requiring the model to output "hello"
Observation of prolonged analysis without completion
Open the console and find that the code has already been executed
Finally, the code interpreter timed out and the model generated a response, but did not actually receive the output from the code interpreter
In fact, any code has a probability of encountering this situation
Logs & Screenshots
Additional Information
This issue is not always triggered, but it does exist.
Please don't rush to close; there may be others who will encounter it
@matthid commented on GitHub (Jul 25, 2025):
This happened when I tried to use the code-interpreter today (first time actually) it seems like the output was never sent to the llm and it repeatedly called the interpreter with the same task. So this seems to be quite broken at the moment.