[DOCS] Agent view docs omit voice dictation support in the peek-panel reply input

Documentation Type

Missing documentation (feature not documented)

Documentation Location

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

Section/Topic

"Peek and reply" / peek-panel reply input in agent view

Current Documentation

The current docs explain the peek panel reply flow, but not that voice dictation can be used there:

Select a row with the arrow keys and press Space to open the peek panel. It shows the session's most recent output, or the question it's waiting on, rather than the full transcript. Type a reply and press Enter to send it without leaving agent view.

Press Space on a selected row to open the peek panel. It shows what the session needs from you, its most recent output, and any pull requests it opened. Most of the time this is enough, and you never need to open the full transcript.

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.

The voice dictation docs also describe voice:pushToTalk generically, without mentioning the agent view reply input:

Speak your prompts instead of typing them in the Claude Code CLI. Your speech is transcribed live into the prompt input, so you can mix voice and typing in the same message.

The dictation key is bound to voice:pushToTalk in the Chat context and defaults to Space. The same binding controls both hold and tap modes.

What's Wrong or Missing?

Claude Code v2.1.145 fixed voice:pushToTalk not working in the agent view reply pane, which confirms that voice dictation is intended to work while replying from the peek panel.

That capability is not documented on the agent view page, and the voice dictation page does not call out agent view as a supported reply surface. As written, the docs make the peek panel reply flow look keyboard-only and make voice dictation sound limited to the main chat prompt.

This leaves a user-visible workflow undocumented: after opening the peek panel for a blocked session, users can reply with the same voice dictation feature instead of attaching to the full session and typing manually.

Suggested Improvement

Add a short note to the agent view "Peek and reply" section such as:

If /voice is enabled, the peek-panel reply input also supports voice dictation. Use your voice:pushToTalk binding while that input is focused to dictate a reply without attaching to the full session.

Add a matching cross-reference on the voice dictation page noting that voice input works in agent view's peek-panel reply field, not only in the main chat prompt.

Impact

Medium - Makes feature difficult to understand

Additional Context

Affected Pages:

| Page | Line(s) | Context |
|------|---------|---------|
| https://code.claude.com/docs/en/agent-view | 56-58, 153-155 | Describes opening the peek panel and typing a reply, but does not mention voice dictation in that reply input |

Cross-references:

| Page | Line(s) | Context |
|------|---------|---------|
| https://code.claude.com/docs/en/voice-dictation | 9, 129-147 | Describes voice dictation and voice:pushToTalk, but does not mention agent view's peek-panel reply field |
| https://code.claude.com/docs/en/keybindings | 311-315 | Documents voice:pushToTalk as a Chat-context action without connecting it to the agent view reply workflow |

Total scope: 1 primary page affected, with 2 related cross-reference pages