Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix [Bug]: WebChat truncation despite settings

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

WebChat / ControlUI truncate prompts and AI responses, even when all settings related to truncation are on max values, while original prompts and AI responses are kept in trajectory files untruncated.

Root Cause

WebChat / ControlUI truncate prompts and AI responses, even when all settings related to truncation are on max values, while original prompts and AI responses are kept in trajectory files untruncated.

Code Example

Attached in additional information (screenshot)
RAW_BUFFERClick to expand / collapse

Bug type

Behavior bug (incorrect output/state without crash)

Beta release blocker

No

Summary

WebChat / ControlUI truncate prompts and AI responses, even when all settings related to truncation are on max values, while original prompts and AI responses are kept in trajectory files untruncated.

Steps to reproduce

  1. Start OpenClaw 2026.5.19
  2. Ask agent about couple of things, so prompt can be longs (attach some code, documentation etc.). Also ask things that you think require long answer.
  3. See if these messages are truncated or not (with ...(truncated)...).

Expected behavior

In 2026.5.19, in WebChat/ControlUI there are original, full prompts and responses.

Actual behavior

Truncated messages with ...(truncated)...

OpenClaw version

2026.5.19

Operating system

Linux Mint 22.3

Install method

npm global / installer (both affected)

Model

openai/gpt-5.4-nano

Provider / routing chain

OpenClaw->OpenAI API->OpenClaw

Additional provider/model setup details

I tested OpenClaw with GPT 5.4 mini and nano.

I attach openclaw.json config.

Logs, screenshots, and evidence

Attached in additional information (screenshot)

Impact and severity

Affected: All users when using WebChat on 2026.5.19 (also older 2026.5.12 version) Severity: Annoying and makes OpenClaw unusable for long tasks and automations. Frequency: Always Consequence: Missed messages, no answer for questions

Additional information

Full prompts and responses are kept untruncated in trajectory files, so this is not provider/model limit.

It would be lovely to see "read more" button or something like this or even ability to globally disabling truncation in WebChat.

<img width="1910" height="88" alt="Image" src="https://github.com/user-attachments/assets/286071a5-1d67-497a-8b2c-9709cb34d12d" /> <img width="1172" height="460" alt="Image" src="https://github.com/user-attachments/assets/05dce915-853d-4455-9411-1a020da53cd1" />

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

FAQ

Expected behavior

In 2026.5.19, in WebChat/ControlUI there are original, full prompts and responses.

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

openclaw - 💡(How to fix) Fix [Bug]: WebChat truncation despite settings