[DOCS] `claude agents` image-paste docs omit peek-panel reply input behavior

Documentation Type

Missing documentation (feature not documented)

Documentation Location

https://code.claude.com/docs/en/agent-view

Section/Topic

"Peek and reply" plus "From agent view" in the agent view guide

Current Documentation

The agent view page currently says:

Type a reply in the peek panel and press Enter to send it to that session. When the session is asking a multiple-choice question, the peek panel shows the options and you can press a number key to pick one. For other blocked sessions, press Tab to fill the input with a suggested reply you can edit before sending. Prefix a reply with ! to send a Bash command instead. From v2.1.145, with voice dictation enabled, hold or tap your push-to-talk key while the reply input is focused to dictate a reply instead of typing it. The same works in the dispatch input at the bottom of agent view.

Later, the same page says:

Paste an image into the prompt to include a screenshot or diagram with the task.

What's Wrong or Missing?

The page only documents pasted images for the dispatch prompt, not for the blocked-session reply input in the peek panel.

In v2.1.162, the changelog says claude agents fixed Ctrl+V image paste in both the dispatch input and the session reply box, and that using the paste shortcut with no image now shows a hint instead of silently doing nothing.

That leaves two documentation gaps on the agent view page:

A. The reply-input section does not mention image paste

The "Peek and reply" section explains typed replies, number-key answers, Tab suggestions, Bash replies, and voice dictation, but it does not say that the reply input also accepts pasted clipboard images.

B. The page does not describe the no-image feedback

The only image-paste sentence is about adding a screenshot to the dispatch prompt. It does not tell readers that if they press the image-paste shortcut without an image on the clipboard, agent view now shows a hint instead of failing silently.

Suggested Improvement

Update the agent view guide so image-paste behavior is documented for both input surfaces.

For example:

• In "Peek and reply," add that the reply input accepts clipboard images with the same image-paste shortcut used elsewhere in Claude Code.
• In "From agent view," clarify that the dispatch prompt and the peek-panel reply input both support pasted screenshots/diagrams.
• Add a short note that if no image is available on the clipboard, Claude Code shows a hint instead of attaching anything.

If the docs want to avoid repeating platform-specific shortcuts, link to the shared keyboard shortcut reference for the exact bindings.

Impact

Medium - Makes feature difficult to understand

Additional Context

Affected Pages:

| Page | Line(s) | Context |
|------|---------|---------|
| https://code.claude.com/docs/en/agent-view | 165-167 | Reply-input docs cover typing, number keys, Tab, Bash, and voice dictation, but not image paste |
| https://code.claude.com/docs/en/agent-view | 245 | The dispatch section is the only place that mentions pasted images |
| https://code.claude.com/docs/en/changelog | 30 | v2.1.162 says Ctrl+V image paste works in both the dispatch input and the session reply box, and no-image paste now shows a hint |

Total scope: 2 documentation pages affected

Version context: This gap matters for the v2.1.162 release entry: "Fixed claude agents Ctrl+V image paste doing nothing in the dispatch input and the session reply box; pasting with no image now shows a hint"