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
v0.8.10
Ollama Version (if applicable)
No response
Operating System
Kubernetes
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
When using agentic web search content is automatically truncated to 50K characters to prevent context window overload. However, with the ability to use models which have context windows as large as 1 million tokens we should have the ability to set this value higher and/or disable the truncation all together.
Actual Behavior
The tool has hard-coded a fetch limit of 50K characters.
Steps to Reproduce
Use agentic web-search with your prompt
Any fetch results is truncated to 50K characters.
Danger of this ...
A simple LinkedIn webpage can be 20K+ characters. There is large potential for actual context to be lost and with the availability of models with 1 million token context windows we should have the option to include more data from the request.
Logs & Screenshots
None
Additional Information
No response
Originally created by @cmbaatz on GitHub (Mar 17, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/22774
### 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
v0.8.10
### Ollama Version (if applicable)
_No response_
### Operating System
Kubernetes
### 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
When using agentic web search content is automatically truncated to 50K characters to prevent context window overload. However, with the ability to use models which have context windows as large as 1 million tokens we should have the ability to set this value higher and/or disable the truncation all together.
### Actual Behavior
The tool has hard-coded a fetch limit of 50K characters.
### Steps to Reproduce
1. Use agentic web-search with your prompt
2. Any fetch results is truncated to 50K characters.
Danger of this ...
A simple LinkedIn webpage can be 20K+ characters. There is large potential for actual context to be lost and with the availability of models with 1 million token context windows we should have the option to include more data from the request.
### Logs & Screenshots
None
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-05-05 23:15:37 -05:00
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 @cmbaatz on GitHub (Mar 17, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/22774
Check Existing Issues
Installation Method
Docker
Open WebUI Version
v0.8.10
Ollama Version (if applicable)
No response
Operating System
Kubernetes
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
When using agentic web search content is automatically truncated to 50K characters to prevent context window overload. However, with the ability to use models which have context windows as large as 1 million tokens we should have the ability to set this value higher and/or disable the truncation all together.
Actual Behavior
The tool has hard-coded a fetch limit of 50K characters.
Steps to Reproduce
Danger of this ...
A simple LinkedIn webpage can be 20K+ characters. There is large potential for actual context to be lost and with the availability of models with 1 million token context windows we should have the option to include more data from the request.
Logs & Screenshots
None
Additional Information
No response
@tjbck commented on GitHub (Mar 17, 2026):
Addressed in dev.