docs(computer-use): document requesting the actual screenshot on chat surfaces

Follow-up to PR #90183 — computer_use now saves a bounded shareable copy of
image captures, so attachment-capable surfaces (Telegram, Discord, Desktop)
can deliver the real screenshot when the user asks. Documents the behavior,
the 20-file cache bound, and the no-automatic-send rule.
This commit is contained in:
Teknium
2026-08-19 22:59:30 -07:00
parent 8436e0d142
commit dbbd8937ae
@@ -284,6 +284,23 @@ the model substitutes the platform's idiomatic shortcut and app name):
During all of this, your cursor stays wherever you left it and the email
app never comes to front.
## Receiving the actual screenshot
Screenshots taken during computer control are normally internal — they exist
so the model can see the screen, and the agent replies in text. But every
image capture also saves a bounded, shareable copy under Hermes' image cache
and reports its path, so on attachment-capable surfaces (Telegram, Discord,
Desktop, and other gateway platforms) you can simply ask:
> *"Send me a screenshot of my screen."*
and the agent delivers the real image as a native attachment, not just a
description. On the CLI there is no attachment channel, so the agent gives
you the saved file's path instead.
Only the 20 most recent capture files are kept, and screenshots are never
sent automatically — only when you ask for one.
## Provider compatibility
| Provider | Vision? | Works? | Notes |