[DOCS] Agent view docs omit background shell-command rows and completed-row behavior

Documentation Type

Missing documentation (feature not documented)

Documentation Location

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

Section/Topic

"Monitor sessions with agent view", especially row types, state transitions, and what opening a completed row does

Current Documentation

The current agent view docs describe the table as session-only UI:

Run claude agents to open agent view. It takes over the full terminal and lists every session grouped by state, with pinned sessions and the ones that need you at the top. Each row shows the session's name, current activity, and how long ago it last changed.

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.

Press Enter or → on a selected row to attach. Agent view is replaced by the full interactive session, exactly as if you had run claude in that directory.

Related docs acknowledge background shell commands elsewhere, but only as generic background tasks:

For long-running processes such as dev servers or watch builds, Claude can set run_in_background: true to start the command as a background task and continue working while it runs. List and stop background tasks with /tasks.

What's Wrong or Missing?

The v2.1.144 release notes fixed two user-visible agent view behaviors for shell-command rows: completed command rows could linger under Working, and pressing Enter on a completed row could re-run the command after its cached output expired.

The current docs never explain that background shell commands can appear as rows in agent view, how those rows transition from Working to Completed, or what reopening a completed command row is supposed to do. As written, agent-view reads as though every row is an attachable session, while background shell commands are documented only under /tasks.

Suggested Improvement

Add a short note to agent-view explaining that background shell commands can surface as rows, alongside session rows, and document their expected behavior.

For example:

Background shell commands may appear as rows in agent view while they are running. When they finish, they move to Completed instead of remaining under Working. Opening a completed command row should show the saved command result or task details; it should not start the command again just because the inline output preview has expired.

If /tasks is still the preferred place to inspect or stop those commands, cross-link that workflow explicitly from agent-view.

Impact

Medium - Makes feature difficult to understand

Additional Context

Affected Pages:

| Page | Line(s) | Context |
|------|---------|---------|
| https://code.claude.com/docs/en/agent-view | 73-81, 153-161 | Describes agent view rows as sessions and documents Space/Enter behavior, but not shell-command rows |
| https://code.claude.com/docs/en/tools-reference | 121 | Documents background Bash commands as tasks, without connecting them to agent view |
| https://code.claude.com/docs/en/commands | 117 | /tasks is listed as the command for background tasks, but does not clarify how this relates to agent view |

Total scope: 3 pages affected

Version context: This gap is about behavior fixed in Claude Code v2.1.144.