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>

Cargo.lock

@@ -492,6 +492,7 @@ dependencies = [
  "http-body-util",
  "hyper",
  "hyper-util",
+ "imagesize",
  "json-five",
  "libc",
  "log",
@@ -1423,6 +1424,12 @@ dependencies = [
  "winapi-util",
 ]
 
+[[package]]
+name = "imagesize"
+version = "0.14.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09e54e57b4c48b40f7aec75635392b12b3421fa26fe8b4332e63138ed278459c"
+
 [[package]]
 name = "indexmap"
 version = "2.14.0"