[DOCS] Extended thinking docs omit the amber spinner state during long thinking periods
Documentation Type
Missing documentation (feature not documented)
Documentation Location
https://code.claude.com/docs/en/model-config
Section/Topic
Extended thinking
Current Documentation
The docs currently say:
Extended thinking is the reasoning Claude emits before responding. On models that support adaptive reasoning, the effort level is the primary control for how much thinking happens; the settings below turn thinking on or off and control how it displays. Thinking output is collapsed by default. PressCtrl+Oto toggle verbose mode and see the reasoning as gray italic text. Interactive sessions on the Anthropic API receive redacted thinking blocks by default, so setshowThinkingSummaries: truein settings if you want the full summaries available when you expand.
What's Wrong or Missing?
Claude Code v2.1.141 added a long-wait thinking indicator where the spinner warms to amber after 10 seconds to show that Claude is still working.
The main Extended thinking docs explain how to enable thinking and how to inspect the reasoning output, but they do not explain this time-based spinner state or what the amber color means. When users hit a long thinking pause, there is no main-doc explanation that the amber spinner is an expected "still working" signal rather than an error or stuck state.
Suggested Improvement
Add a short note to the Extended thinking section describing the long-wait indicator introduced in v2.1.141, for example:
During long thinking periods, the spinner warms to amber after about 10 seconds to show Claude is still working. This color change is informational rather than an error state.
If this behavior is considered part of general spinner UX rather than thinking-specific UX, add the same explanation or a cross-reference in the spinner-related settings/theme docs.
Impact
Medium - Makes feature difficult to understand
Additional Context
Affected Pages:
| Page | Line(s) | Context |
|------|---------|---------|
| https://code.claude.com/docs/en/model-config | 225-235 | Extended thinking explains display behavior but not the amber long-wait state |
| https://code.claude.com/docs/en/settings | 235-237 | Spinner settings document tips and verbs, but not the amber "still working" signal |
| https://code.claude.com/docs/en/terminal-config | 177, 194, 249-252 | Theme tokens document spinner and warning colors without explaining the meaning of the amber state |
Total scope: 3 pages affected
Behavior change introduced in v2.1.141.
This issue has 2 comments on GitHub. Read the full discussion on GitHub ↗