openclaw - 💡(How to fix) Fix [Bug]: Thinking level displayed inconsistently almost everywhere; XHIGH support for models should be enhanced. [1 participants]

Official PRs (…)
ON THIS PAGE

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…
GitHub stats
openclaw/openclaw#59416Fetched 2026-04-08 02:24:05
View on GitHub
Comments
0
Participants
1
Timeline
2
Reactions
0
Author
Participants
Timeline (top)
labeled ×2

/think, /status, TUI status bar and WebUI selection box displayed thinking levels are inconsistent, leading to actually unknown current thinking level. xhigh support for multiple able models are still not yet planned.

Root Cause

/think, /status, TUI status bar and WebUI selection box displayed thinking levels are inconsistent, leading to actually unknown current thinking level. xhigh support for multiple able models are still not yet planned.

RAW_BUFFERClick to expand / collapse

Bug type

Behavior bug (incorrect output/state without crash)

Beta release blocker

No

Summary

/think, /status, TUI status bar and WebUI selection box displayed thinking levels are inconsistent, leading to actually unknown current thinking level. xhigh support for multiple able models are still not yet planned.

Steps to reproduce

  1. Start OpenClaw 2026.4.1. Model using a currently non-xhigh-able (e.g. github-copilot/gpt-5.4-mini, which SHOULD BE ADDED). xhigh being set as thinkingDefault for some items to reproduce.
  2. Uses /think, /status and look at the values displayed at TUI and WebUI for thinking levels for the session.

Expected behavior

  1. Display of thinking level should be consistent. Allowed options as well.
  2. Add xhigh support for multiple github-copilot models immediately as being frequently suggested by issues and PRs.

Actual behavior

  1. /think displays low no matter what is set as thinkingDefault, even when setting default to high, as long as the session's override thinking level is not being set (non-inherit).
  2. /status and TUI status bar displays xhigh even the model does not support xhigh
  3. WebUI selection box allows xhigh for all models.

OpenClaw version

2026.4.1

Operating system

Windows 11

Install method

npm global

Model

github-copilot/gpt-5.4-mini, github-copilot/gpt-5-mini

Provider / routing chain

openclaw -> github copilot api

extent analysis

TL;DR

The inconsistency in thinking levels displayed by /think, /status, TUI status bar, and WebUI selection box can be addressed by ensuring that the thinkingDefault setting is correctly applied and that xhigh support is properly handled for models that do not support it.

Guidance

  • Verify that the thinkingDefault setting is being correctly set and applied to the session, as the current behavior suggests it is not being inherited.
  • Check the model's capabilities to ensure that xhigh is only displayed as an option when the model actually supports it, to prevent inconsistent displays.
  • Review the code handling the display of thinking levels in /think, /status, TUI, and WebUI to ensure consistency in how the levels are determined and displayed.
  • Consider adding a check to prevent the display of xhigh in the WebUI selection box for models that do not support it, to match the expected behavior.

Example

No specific code snippet can be provided without more context, but ensuring that model capabilities are checked before displaying options could involve a conditional statement, such as if (model.supportsXHigh) { displayXHighOption(); }.

Notes

The issue seems to stem from inconsistencies in how thinking levels are determined and displayed across different interfaces and models. Ensuring that the thinkingDefault is correctly applied and that model capabilities are properly checked can help resolve the issue.

Recommendation

Apply a workaround to correctly handle xhigh support for models and ensure consistent display of thinking levels, as upgrading to a fixed version is not mentioned as an option in the provided issue. This involves modifying the display logic to match the model's capabilities and the session's settings.

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

  1. Display of thinking level should be consistent. Allowed options as well.
  2. Add xhigh support for multiple github-copilot models immediately as being frequently suggested by issues and PRs.

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]: Thinking level displayed inconsistently almost everywhere; XHIGH support for models should be enhanced. [1 participants]