The best way to control Claude Code, Codex and more from any computer or phone
Mirrored from https://github.com/Camo67/t3code.git
Synced Nov 21, 03:37 UTC
| 1 | # Activity log |
| 2 | |
| 3 | On web and desktop, consecutive tool calls appear as an expandable summary. Open it to inspect |
| 4 | commands, tool inputs, status, and exit codes. Expand a tool call to see its output. A running |
| 5 | command's output updates live, and long output shows only its most recent part. Use **Open diff** on |
| 6 | a file change to review its contents. |
| 7 | |
| 8 | T3 Orchestrator summaries describe the actions taken, such as **Ran 2 commands and sent messages |
| 9 | to 3 threads**. Repeated messages to the same destinations show both counts: **Sent 5 messages to |
| 10 | 2 threads**. Thread creation counts the threads returned by the tool, including batches. |
| 11 | |
| 12 | Groups with many kinds of activity show up to two specific action categories and a count of the |
| 13 | remaining actions. Commands, file changes, and orchestration changes take priority over reads and |
| 14 | status checks. Expand the group for the full list. |
| 15 | |
| 16 | Failed calls do not count as successful messages or creations. Waiting on a thread does not mean |
| 17 | it finished, and an interrupt or cancellation request does not mean the thread stopped. When tool |
| 18 | details are unavailable, summaries use a broader description instead of guessing how many threads |
| 19 | were 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 |
| 25 | from the conversation. **Hide successful** shows a call while it runs and keeps |
| 26 | it 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 |
| 28 | and the agent's last reply, which appears when the turn ends. If you steer while the agent is |
| 29 | answering, the answer it finished before reading your steer stays too. On web and desktop, Find |
| 30 | shows the in-between messages while it is open. Approvals, questions, and errors always show. The |
| 31 | setting applies to this browser or device only. |
| 32 | |
| 33 | ## Screen reader announcements |
| 34 | |
| 35 | On web and desktop, a screen reader hears the open thread's turn as it runs. **Screen reader |
| 36 | announcements** in **Settings → Chat** sets how much. **Status only** says when a turn starts, |
| 37 | needs your approval or input, and ends. **Status and messages** also reads each message the agent |
| 38 | writes and then keeps working after, once that message is complete. A very long message is cut |
| 39 | short. 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 |
| 41 | are spaced out, so a quick step can be skipped for a newer one. |
| 42 | The 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 | |
| 45 | To hear the open thread and what it's doing when you switch to T3 Code, turn on **Screen reader |
| 46 | window 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 |
| 48 | screen reader says them first. When the turn ends, only the status goes away. |
| 49 | Anyone who can see your taskbar, window switcher, or shared screen sees it too, and time trackers |
| 50 | that group by window title count each status separately. |