agent: rewrite view_image to emit Image leaves

view_image now reads the file, grabs dimensions via imagesize (no full
decode), and pushes a user-role branch containing a NodeBody::Image
leaf straight into the conversation. The tool_result is just a short
acknowledgment — the actual pixels ride in the Image leaf for the API
layer to extract into multi_modal_data.

Drops the capture_tmux_pane path, which had no business living under
"vision" (tmux text capture belongs in bash or a dedicated tool, and
this one just returned rendered text anyway).

Co-Authored-By: Proof of Concept <poc@bcachefs.org>
This commit is contained in:
Kent Overstreet 2026-04-16 18:06:25 -04:00
parent 0bf71b9110
commit 91106deaa1
4 changed files with 48 additions and 72 deletions

View file

@ -68,6 +68,7 @@ hyper-util = { version = "0.1", features = ["tokio"], default-features = false }
http-body-util = "0.1"
bytes = "1"
base64 = "0.22"
imagesize = "0.14"
rustls = "0.23"
tokio-rustls = "0.26"