[DOCS] Deep links docs still describe launch warnings as above-input banners

Documentation Type

Incorrect/outdated documentation

Documentation Location

https://code.claude.com/docs/en/deep-links

Section/Topic

What a launched session shows

Current Documentation

The docs currently say:

A deep link never executes anything on its own. The link only chooses a directory and fills the prompt box. If you click a link from a page you do not trust, the prompt is still inert: nothing reaches the model until you read what was filled in and press Enter. When the session opens, a banner above the input shows that an external link launched it and which directory it selected. For prompts over 1,000 characters, the banner tells you to scroll and review the full text before pressing Enter, since long prompts can push instructions off screen.

What's Wrong or Missing?

Claude Code's v2.1.162 changelog says:

Launch-prompt warnings (deep link/pre-filled prompt) now stay pinned below the input until you act instead of scrolling away

The deep-links page still describes the launch warning with the older presentation. It says the warning is a banner above the input, but the v2.1.162 behavior is that the warning stays pinned below the input until the user acts.

That leaves two parts of the current guidance outdated:

A. The warning location is described differently from the released UI

Readers are told to expect an above-input banner, while the changelog says the warning now stays pinned below the input.

B. The persistence behavior is undocumented

The current page tells readers about the "scroll and review" warning for long pre-filled prompts, but it does not explain that the warning remains visible until they act instead of scrolling away.

Suggested Improvement

Update https://code.claude.com/docs/en/deep-links to match the v2.1.162 behavior.

For example, revise the launched-session description so it says the deep-link / pre-filled-prompt warning stays pinned below the input until the user acts, and keep the existing safety guidance that the prompt is not submitted automatically.

If the same pinned warning also applies to non-deep-link pre-filled prompts, add one sentence clarifying that the behavior is shared across both launch-prompt cases.

Impact

Medium - Makes feature difficult to understand

Additional Context

Affected Pages:

| Page | Line(s) | Context |
|------|---------|---------|
| https://code.claude.com/docs/en/deep-links | 43-45 | What a launched session shows still describes an above-input banner and omits the pinned-below-input behavior |

Total scope: 1 page affected

Version context: v2.1.162 changelog entry says launch-prompt warnings now stay pinned below the input until the user acts.