let5see/clawdbot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: emit tool outputs for full verbose

Browse Source
This commit is contained in:
Peter Steinberger
2026-01-17 05:40:21 +00:00
parent 99dd428862
commit 68d35be383
3 changed files with 16 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/tools/thinking.md
View File

@@ -39,7 +39,7 @@ read_when:
- Inline directive affects only that message; session/global defaults apply otherwise.
- Send `/verbose` (or `/verbose:`) with no argument to see the current verbose level.
- When verbose is on, agents that emit structured tool results (Pi, other JSON agents) send each tool call back as its own metadata-only message, prefixed with `<emoji> <tool-name>: <arg>` when available (path/command). These tool summaries are sent as soon as each tool starts (separate bubbles), not as streaming deltas.
- When verbose is `full`, exec/process tool outputs are also forwarded after completion (separate bubble, truncated to a safe length). If you toggle `/verbose on|full|off` while a run is in-flight, subsequent tool bubbles honor the new setting.
- When verbose is `full`, tool outputs are also forwarded after completion (separate bubble, truncated to a safe length). If you toggle `/verbose on|full|off` while a run is in-flight, subsequent tool bubbles honor the new setting.
## Reasoning visibility (/reasoning)
- Levels: `on|off|stream`.