open-webui / open-webui/computer
issue: ui/ux improvement - add more details on placeholders like `run_command`
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 569
- Forks
- 79
- PR merge metrics
- No merged PRs in 30d
Description
Before Submitting
- I searched open and closed issues and discussions for an existing report.
- I checked whether this is already fixed on the
devbranch or latest source. - I understand that maintainers want a well-written issue before any code pull request.
- I am using the latest available version of Open WebUI for my install method.
- This is not a security vulnerability.
Installation Method
Docker
Open WebUI Version
v0.11.0
Operating System
macOS 26.5.1 (25F80)
Browser
No response
Ollama Version
No response
Summary
A discussion and some exploration took place already, and confirmed it is a real issue with both Open WebUI Interface (rendering) as well as Computer (data source).
https://github.com/open-webui/open-webui/discussions/28762
Expected Behavior
Would be better to add more details on it. e.g. run_command: command name, parameters, ... (similar to Bash)
Or something constant with current ui, like below
Actual Behavior
Currently run_command appears in answers more like a placeholder without giving much information.
Steps to Reproduce
Any prompts that trigger tools, such as bash, fetch
Logs, Screenshots, and Config
Additional Information
No response
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by tracing the Open WebUI Interface rendering path and the Computer data-source path for tool outputs such as run_command, bash, and fetch. Compare the current placeholder-style output with the requested Bash-like command and parameter details, then verify the result with prompts that trigger these tools.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- backend, frontend
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100