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
Ubuntu
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
Task message truncation doesn't work. OWU still passes over 500 tokens to AI model.
Originally created by @cloudtuotuo on GitHub (Mar 12, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/22605
### 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
Ubuntu
### 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
Task message truncation doesn't work. OWU still passes over 500 tokens to AI model.
My Title Generation Prompt:
### Chat history
<chat_history>
{{MESSAGES:MIDDLETRUNCATE:500}}
</chat_history>
### Actual Behavior
Only pass 500 tokens to AI model.
### Steps to Reproduce
Title Generation Prompt:
...
### Chat history
<chat_history>
{{MESSAGES:MIDDLETRUNCATE:500}}
</chat_history>
### Logs & Screenshots
There's no error info.
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-05-13 07:06:45 -05:00
MESSAGES:MIDDLETRUNCATE:500 selects up to 500 MESSAGES, not 500 tokens. It takes the first ~250 messages and last ~250 messages if there are more than 500 messages total.
To truncate each message's content, you need to filter it via pipe: {{MESSAGES|middletruncate:500}} (truncates each message's content to 500 characters) or {{MESSAGES:MIDDLETRUNCATE:10|middletruncate:50}} (selects 10 messages, truncates each to 50 chars).
<!-- gh-comment-id:4045183016 -->
@Classic298 commented on GitHub (Mar 12, 2026):
MESSAGES:MIDDLETRUNCATE:500 selects up to **500 MESSAGES**, not 500 tokens. It takes the first ~250 messages and last ~250 messages if there are more than 500 messages total.
To truncate each message's content, you need to filter it via pipe: {{MESSAGES|middletruncate:500}} (truncates each message's content to 500 characters) or {{MESSAGES:MIDDLETRUNCATE:10|middletruncate:50}} (selects 10 messages, truncates each to 50 chars).
MESSAGES:MIDDLETRUNCATE:500 selects up to 500 MESSAGES, not 500 tokens. It takes the first ~250 messages and last ~250 messages if there are more than 500 messages total.
To truncate each message's content, you need to filter it via pipe: {{MESSAGES|middletruncate:500}} (truncates each message's content to 500 characters) or {{MESSAGES:MIDDLETRUNCATE:10|middletruncate:50}} (selects 10 messages, truncates each to 50 chars).
Thanks a lot. It works.
<!-- gh-comment-id:4045473575 -->
@cloudtuotuo commented on GitHub (Mar 12, 2026):
> MESSAGES:MIDDLETRUNCATE:500 selects up to **500 MESSAGES**, not 500 tokens. It takes the first ~250 messages and last ~250 messages if there are more than 500 messages total.
>
> To truncate each message's content, you need to filter it via pipe: {{MESSAGES|middletruncate:500}} (truncates each message's content to 500 characters) or {{MESSAGES:MIDDLETRUNCATE:10|middletruncate:50}} (selects 10 messages, truncates each to 50 chars).
Thanks a lot. It works.
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 @cloudtuotuo on GitHub (Mar 12, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/22605
Check Existing Issues
Installation Method
Docker
Open WebUI Version
v0.8.10
Ollama Version (if applicable)
No response
Operating System
Ubuntu
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
Task message truncation doesn't work. OWU still passes over 500 tokens to AI model.
My Title Generation Prompt:
Chat history
<chat_history>
{{MESSAGES:MIDDLETRUNCATE:500}}
</chat_history>
Actual Behavior
Only pass 500 tokens to AI model.
Steps to Reproduce
Title Generation Prompt:
...
Chat history
<chat_history>
{{MESSAGES:MIDDLETRUNCATE:500}}
</chat_history>
Logs & Screenshots
There's no error info.
Additional Information
No response
@Classic298 commented on GitHub (Mar 12, 2026):
MESSAGES:MIDDLETRUNCATE:500 selects up to 500 MESSAGES, not 500 tokens. It takes the first ~250 messages and last ~250 messages if there are more than 500 messages total.
To truncate each message's content, you need to filter it via pipe: {{MESSAGES|middletruncate:500}} (truncates each message's content to 500 characters) or {{MESSAGES:MIDDLETRUNCATE:10|middletruncate:50}} (selects 10 messages, truncates each to 50 chars).
@cloudtuotuo commented on GitHub (Mar 12, 2026):
Thanks a lot. It works.