[DOCS] Extended thinking docs omit collapsed summary rendering behavior

Open 💬 1 comment Opened May 27, 2026 by coygeek

Documentation Type

Missing documentation (feature not documented)

Documentation Location

https://code.claude.com/docs/en/model-config#extended-thinking

Section/Topic

Extended thinking in model configuration, plus the showThinkingSummaries setting and the Ctrl+O transcript viewer references for interactive sessions

Current Documentation

The docs currently say:

Thinking output is collapsed by default. Press Ctrl+O to toggle verbose mode and see the reasoning as gray italic text. Interactive sessions on the Anthropic API receive redacted thinking blocks by default, so set showThinkingSummaries: true in settings if you want the full summaries available when you expand. You are charged for all thinking tokens generated, even when collapsed or redacted.

And the settings reference says:

Show extended thinking summaries in interactive sessions. When unset or false (default in interactive mode), thinking blocks are redacted by the API and shown as a collapsed stub. Redaction only changes what you see, not what the model generates: to reduce thinking spend, lower the budget or disable thinking instead.

What's Wrong or Missing?

The current docs explain that thinking is collapsed by default and that Ctrl+O shows the full reasoning, but they do not document the actual behavior of collapsed thinking summaries in interactive sessions.

As of v2.1.152, the changelog states that collapsed thinking summaries now:

stay readable for at least 3 seconds, render as markdown, and cap at 10 lines (Ctrl+O shows the full thinking)

That user-visible behavior is missing from the docs. A reader who enables showThinkingSummaries can tell that summaries exist, but not:

  1. that the collapsed preview is markdown-rendered rather than plain text
  2. that the collapsed preview is intentionally truncated to 10 lines
  3. that the preview remains visible briefly before collapsing, and Ctrl+O is the path to the full thinking content

Suggested Improvement

Add one short note in the Extended thinking section explaining how collapsed summaries behave in interactive sessions when summaries are available.

Suggested wording:

When thinking summaries are available in interactive sessions, the collapsed preview renders markdown, stays visible briefly so it can be read, and is truncated to 10 lines. Press Ctrl+O to view the full thinking transcript.

Also update the showThinkingSummaries setting description to clarify that enabling summaries affects the collapsed preview behavior, not just whether a generic collapsed stub appears.

Impact

Low - Minor confusion or inconvenience

Additional Context

Affected Pages:

| Page | Line(s) | Context |
|------|---------|---------|
| https://code.claude.com/docs/en/model-config | 227-238 | Extended thinking behavior and Ctrl+O explanation |
| https://code.claude.com/docs/en/settings | 240 | showThinkingSummaries setting description |
| https://code.claude.com/docs/en/interactive-mode | 32, 88-100 | Ctrl+O transcript viewer behavior in interactive sessions |

Cross-reference:

| Page | Context |
|------|---------|
| https://code.claude.com/docs/en/changelog | v2.1.152 release notes describe the collapsed-summary behavior that is not yet reflected in the docs |

Total scope: 3 documentation pages affected

Behavior introduced in v2.1.152.

View original on GitHub ↗

This issue has 1 comment on GitHub. Read the full discussion on GitHub ↗