buildUserMessage replaces the unconditional NewUserText wrap inside
SubmitWithOptions. When the active model advertises Vision and the
input contains [Image: /path] markers, the markers are inlined as
ImageContent blocks carrying the file bytes; otherwise the input is
passed through as a single text block (legacy behavior preserved
for subprocess CLIs that auto-ingest paths, e.g. gemini-cli).
image_input.go:
- imageMarkerRe extracts each [Image: ...] occurrence.
- Per marker: validates absolute path, file (not dir), size cap of
10 MiB, image/* media type via http.DetectContentType.
- On any validation failure, the marker is left as literal text and
a warning is recorded — the turn still proceeds.
Routing: latestUserHasImages drives task.RequiresVision in both the
primary stream attempt and the retryOnTransient path, so failover
arms also respect the vision requirement.
Tests cover: no markers (single text block), single image
(bytes captured into Image.Data, MediaType set), missing file
(literal fallback + warning), relative path rejection, oversized
rejection, non-image file rejection, multiple images interleaved
with text.
