fix(media): drop oldest images on over-count instead of refusing the request
media.Normalize refused (ErrUnsupported) when a request carried more images than
the target's MaxImagesPerReq, on the theory that a failover chain would try a
roomier target. In practice the chain's targets share the same cap — an agent loop
that accumulates a preview image per iteration (e.g. scaddy's write_scad) blows
past the cap, EVERY target rejects ("9 images, target allows at most 8"), and the
run dies. Observed live on ollama-cloud (cap 8).
Now: over-count keeps the most-recent MaxImagesPerReq images and replaces each
older one with a short text placeholder ("[earlier image omitted to fit this
model's per-request image limit]"), preserving each message's turn structure and
telling the model an image was elided. The most-recent images are the relevant
ones in an iterative run. Copy-on-write; the input request is never mutated. The
per-model threshold stays configurable via Capabilities.MaxImagesPerReq (0 still
means no image support); SupportsImages / MIME / byte-budget / dimension behavior
is unchanged, and the provider-side count backstop remains.
Test: TestNormalizeTooManyImages_DropsOldest — 3 images, cap 2 → 2 kept (the most
recent), 1 placeholder, no error, oldest dropped, input unmutated.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
This commit is contained in:
+41
-9
@@ -149,18 +149,50 @@ func TestNormalizeImagesUnsupported(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestNormalizeTooManyImages(t *testing.T) {
|
||||
img := llm.Image("image/png", encPNG(t, gradient(4, 4)))
|
||||
func TestNormalizeTooManyImages_DropsOldest(t *testing.T) {
|
||||
// 3 distinguishable images across 2 messages; cap = 2. Overflow no longer
|
||||
// errors — the OLDEST image is replaced with a placeholder and the most-recent
|
||||
// two (the relevant ones in an iterative run) are kept.
|
||||
a := llm.Image("image/png", encPNG(t, gradient(2, 2))).(llm.ImagePart)
|
||||
b := llm.Image("image/png", encPNG(t, gradient(4, 4))).(llm.ImagePart)
|
||||
c := llm.Image("image/png", encPNG(t, gradient(8, 8))).(llm.ImagePart)
|
||||
req := llm.Request{Messages: []llm.Message{
|
||||
llm.UserParts(img, img),
|
||||
llm.UserParts(img),
|
||||
llm.UserParts(a, b),
|
||||
llm.UserParts(c),
|
||||
}}
|
||||
_, err := Normalize(req, llm.Capabilities{MaxImagesPerReq: 2})
|
||||
if !errors.Is(err, llm.ErrUnsupported) {
|
||||
t.Fatalf("err = %v, want ErrUnsupported", err)
|
||||
caps := llm.Capabilities{MaxImagesPerReq: 2, MaxImageDimension: 64, MaxImageBytes: 1 << 20, AllowedImageMIME: []string{"image/png"}}
|
||||
out, err := Normalize(req, caps)
|
||||
if err != nil {
|
||||
t.Fatalf("drop-oldest overflow should not error: %v", err)
|
||||
}
|
||||
if !strings.Contains(err.Error(), "3 images") || !strings.Contains(err.Error(), "at most 2") {
|
||||
t.Errorf("err message %q lacks the counts", err)
|
||||
var imgs []llm.ImagePart
|
||||
placeholders := 0
|
||||
for _, m := range out.Messages {
|
||||
for _, p := range m.Parts {
|
||||
switch v := p.(type) {
|
||||
case llm.ImagePart:
|
||||
imgs = append(imgs, v)
|
||||
case llm.TextPart:
|
||||
if strings.Contains(v.Text, "omitted") {
|
||||
placeholders++
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
if len(imgs) != 2 {
|
||||
t.Fatalf("kept %d images, want 2 (the cap)", len(imgs))
|
||||
}
|
||||
if placeholders != 1 {
|
||||
t.Errorf("placeholders = %d, want 1 for the dropped oldest image", placeholders)
|
||||
}
|
||||
for _, im := range imgs {
|
||||
if bytes.Equal(im.Data, a.Data) {
|
||||
t.Errorf("oldest image was kept; the most-recent two should survive")
|
||||
}
|
||||
}
|
||||
// The input request must be untouched (copy-on-write).
|
||||
if len(req.Messages[0].Parts) != 2 {
|
||||
t.Errorf("input request was mutated: %+v", req.Messages[0].Parts)
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user