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. Raw command output and tool-result bodies are not
5shown. Use **Open diff** on a file change to review its contents.
6
7T3 Orchestrator summaries describe the actions taken, such as **Ran 2 commands and sent messages
8to 3 threads**. Repeated messages to the same destinations show both counts: **Sent 5 messages to
92 threads**. Thread creation counts the threads returned by the tool, including batches.
10
11Groups with many kinds of activity show up to two specific action categories and a count of the
12remaining actions. Commands, file changes, and orchestration changes take priority over reads and
13status checks. Expand the group for the full list.
14
15Failed calls do not count as successful messages or creations. Waiting on a thread does not mean
16it finished, and an interrupt or cancellation request does not mean the thread stopped. When tool
17details are unavailable, summaries use a broader description instead of guessing how many threads
18were affected.
19
20## Script progress
21
22Node scripts using `@clo/lib/progress` show their live tasks above the composer
23when launched by Codex, Claude, Pi, Muse, an ACP agent, or the chat's terminal.
24Web and desktop show
25the nested task tree; mobile shows task counts. Command output stays available
26as usual. Progress remains visible when you reconnect to the chat remotely.
27
28Disconnected progress preserves the last reported values without claiming the
29command succeeded. The command's result determines whether it completed.
30
31Capture needs Node's synchronous module hooks and a separately loaded progress
32module. A progress library bundled into a script is not captured automatically.