1# Activity log
2
3On web and desktop, consecutive tool calls appear as an expandable summary. Open it to inspect
4commands, tool inputs, status, and exit codes. Expand a tool call to see its output. A running
5command's output updates live, and long output shows only its most recent part. Use **Open diff** on
6a file change to review its contents.
7
8T3 Orchestrator summaries describe the actions taken, such as **Ran 2 commands and sent messages
9to 3 threads**. Repeated messages to the same destinations show both counts: **Sent 5 messages to
102 threads**. Thread creation counts the threads returned by the tool, including batches.
11
12Groups with many kinds of activity show up to two specific action categories and a count of the
13remaining actions. Commands, file changes, and orchestration changes take priority over reads and
14status checks. Expand the group for the full list.
15
16Failed calls do not count as successful messages or creations. Waiting on a thread does not mean
17it finished, and an interrupt or cancellation request does not mean the thread stopped. When tool
18details are unavailable, summaries use a broader description instead of guessing how many threads
19were affected.
20
21## Hide tool calls
22
23**Tool calls in chat** in **Settings → Chat** (web and desktop) or **Settings → Appearance**
24(mobile) hides commands, file edits, searches, and MCP tool calls
25from the conversation. **Hide successful** shows a call while it runs and keeps
26it only if it fails. **Hide all** hides every call and shows **Thinking** while the agent works.
27**Zen** also hides the agent's in-between messages, so each turn shows your message
28and the agent's last reply, which appears when the turn ends. If you steer while the agent is
29answering, the answer it finished before reading your steer stays too. On web and desktop, Find
30shows the in-between messages while it is open. Approvals, questions, and errors always show. The
31setting applies to this browser or device only.
32
33## Screen reader announcements
34
35On web and desktop, a screen reader hears the open thread's turn as it runs. **Screen reader
36announcements** in **Settings → Chat** sets how much. **Status only** says when a turn starts,
37needs your approval or input, and ends. **Status and messages** also reads each message the agent
38writes and then keeps working after, once that message is complete. A very long message is cut
39short. The reply that closes the turn is not read, so you can read it yourself when you hear
40**Done**. **Everything** adds the step the agent is on, such as the command it is running. Steps
41are spaced out, so a quick step can be skipped for a newer one.
42The agent's reasoning text is never read. The setting follows the agent's real activity, whatever
43**Tool calls in chat** hides, and applies to this browser or device only.
44
45To hear the open thread and what it's doing when you switch to T3 Code, turn on **Screen reader
46window title** in the same section. The window title then starts with the thread's status
47(**Working**, **Needs approval**, or **Needs your input**) and its name, then the project, so a
48screen reader says them first. When the turn ends, only the status goes away.
49Anyone who can see your taskbar, window switcher, or shared screen sees it too, and time trackers
50that group by window title count each status separately.