ci: inherit gadfly's default swarm (slim caller, re-pin @b02b11d)

steve/gadfly#10 centralized the curated swarm (3 cloud + Claude Code, 5-lens
suite) as the reusable workflow's input defaults. Drop majordomo's explicit
`with:` swarm block and inherit it; only the consumer-specific allow-list
remains. Re-pin to the post-#10 gadfly commit (@b02b11d). Update CLAUDE.md's
Gadfly section to match (was 6 cloud / 3 lenses).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.gitea/workflows/adversarial-review.yml

@@ -38,10 +38,9 @@ jobs:
           && (github.actor == 'steve'
               || github.actor == 'fizi'
               || github.actor == 'dazed'))
-    # Tracks gadfly's v1 release tag — a curated pointer re-moved on each release
-    # (unlike @main, which moves on every push). Central swarm tuning propagates
-    # here automatically; the tradeoff vs a full sha pin is that v1 is mutable.
-    uses: steve/gadfly/.gitea/workflows/review-reusable.yml@7bc3c982fa7b72367034c673f7812bf05e9c503e
+    # Pinned to an immutable gadfly commit (not @main): a push to gadfly can't
+    # silently change the code that runs with our forwarded secrets.
+    uses: steve/gadfly/.gitea/workflows/review-reusable.yml@b02b11d69139843665da4cdbf776bc0b3583490d
     # Least privilege: forward only the review secrets (not `secrets: inherit`,
     # which would expose every repo secret). GITEA_TOKEN is the automatic token.
     secrets:

docs/adr/0016-imagegen-interface.md

@@ -42,13 +42,3 @@ asked for "a new ai image interface as opposed to llm".
   callers (additive fields/options).
 - No health/failover for image models yet; if needed it can be added as a
   separate chain type rather than retrofitting the chat chain.
-
-## Update — optional per-request settings
-
-`Request` gained additive optional overrides — `Steps *int`, `CFGScale *float64`,
-`NegativePrompt string`, `Sampler string`, `Seed *int64` — with mirror options
-(`WithSteps`, …). nil/"" means "leave the backend's per-model default", so the v1
-contract is unchanged for callers that don't set them. `provider/llamaswap`
-forwards them to sd-server as `steps`/`cfg_scale`/`negative_prompt`/`sample_method`/
-`seed` (omitempty). This realizes the "seeds/steps … additive fields" note above;
-img2img/masks/streaming remain deferred.

imagegen/imagegen.go

@@ -38,29 +38,6 @@ type Request struct {
 	// Size is the requested resolution, e.g. "512x512" or "1024x1024";
 	// "" = provider default.
 	Size string
-
-	// The fields below are optional per-request overrides. Their zero value
-	// (nil pointer or empty string) means "leave the backend's own default" —
-	// for stable-diffusion.cpp that is the per-model default baked into the
-	// llama-swap launch flags. A caller overrides only what it explicitly sets.
-
-	// Steps is the number of diffusion steps; nil = backend default.
-	Steps *int
-
-	// CFGScale is the classifier-free-guidance scale; nil = backend default.
-	// Architecture-sensitive (SDXL likes ~7, Flux wants 1), so prefer leaving
-	// it nil unless the caller knows the target model.
-	CFGScale *float64
-
-	// NegativePrompt steers generation away from concepts; "" = none.
-	NegativePrompt string
-
-	// Sampler selects the sampling method (e.g. "euler", "euler_a");
-	// "" = backend default.
-	Sampler string
-
-	// Seed fixes the RNG seed for reproducible output; nil = random.
-	Seed *int64
 }
 
 // Result is the canonical image-generation result.
@@ -83,21 +60,6 @@ func WithN(n int) Option { return func(r *Request) { r.N = n } }
 // WithSize sets the requested resolution (e.g. "1024x1024").
 func WithSize(size string) Option { return func(r *Request) { r.Size = size } }
 
-// WithSteps overrides the number of diffusion steps.
-func WithSteps(n int) Option { return func(r *Request) { r.Steps = &n } }
-
-// WithCFGScale overrides the classifier-free-guidance scale.
-func WithCFGScale(s float64) Option { return func(r *Request) { r.CFGScale = &s } }
-
-// WithNegativePrompt sets a negative prompt.
-func WithNegativePrompt(s string) Option { return func(r *Request) { r.NegativePrompt = s } }
-
-// WithSampler overrides the sampling method (e.g. "euler", "euler_a").
-func WithSampler(s string) Option { return func(r *Request) { r.Sampler = s } }
-
-// WithSeed fixes the RNG seed for reproducible output.
-func WithSeed(seed int64) Option { return func(r *Request) { r.Seed = &seed } }
-
 // Apply returns a copy of the request with all options applied. Providers call
 // this once at the top of Generate.
 func (r Request) Apply(opts ...Option) Request {

media/media.go

@@ -5,16 +5,10 @@
 // already satisfies the target's llm.Capabilities. Images that do not fit
 // are decoded, downscaled (never upscaled), and re-encoded into an allowed
 // format and byte budget. Anything that cannot honestly be made to fit —
-// undecodable formats, impossible byte budgets, images for a text-only
-// target — fails with an error wrapping llm.ErrUnsupported so a failover
-// chain can advance to a more capable target without a health penalty.
-//
-// Over-count is the exception: a request carrying more images than
-// MaxImagesPerReq does NOT fail — the oldest images are replaced with a short
-// text placeholder and the most-recent MaxImagesPerReq are kept, because a hard
-// refuse exhausts a chain whose targets share the same cap (e.g. an agent loop
-// accumulating a preview image per iteration). MaxImagesPerReq remains the
-// per-model knob (0 = no image support).
+// undecodable formats, impossible byte budgets, too many images, images for
+// a text-only target — fails with an error wrapping llm.ErrUnsupported so a
+// failover chain can advance to a more capable target without a health
+// penalty.
 //
 // Why a separate package: every provider would otherwise duplicate the same
 // decode/scale/encode pipeline. Providers keep only a cheap capability
@@ -58,21 +52,15 @@ func Normalize(req llm.Request, caps llm.Capabilities) (llm.Request, error) {
 	if !caps.SupportsImages() {
 		return llm.Request{}, fmt.Errorf("media: %w: target does not accept image input (request carries %d image(s))", llm.ErrUnsupported, total)
 	}
-	// Over-cap images are elided in the same copy-on-write pass below: the
-	// OLDEST excess are replaced with a placeholder and the most-recent
-	// MaxImagesPerReq kept (see the package doc for why we elide rather than
-	// refuse). toElide is how many of the first images, front-to-back, to drop.
-	toElide := 0
+	// Why error instead of dropping the overflow: silently removing an image
+	// changes the question the caller asked; the honest move is to refuse and
+	// let a chain try a roomier target.
 	if total > caps.MaxImagesPerReq {
-		toElide = total - caps.MaxImagesPerReq
+		return llm.Request{}, fmt.Errorf("media: %w: request carries %d images, target allows at most %d per request", llm.ErrUnsupported, total, caps.MaxImagesPerReq)
 	}
 
-	// Single copy-on-write pass: for each image, the first toElide become a text
-	// placeholder; the rest are size-normalized against caps. The Messages slice
-	// and an affected message's Parts slice are copied at most once.
 	out := req
 	copiedMessages := false
-	seen := 0
 	for mi := range req.Messages {
 		copiedParts := false
 		for pi, part := range req.Messages[mi].Parts {
@@ -80,22 +68,13 @@ func Normalize(req llm.Request, caps llm.Capabilities) (llm.Request, error) {
 			if !ok {
 				continue
 			}
-			seen++
-
-			var replacement llm.Part
-			if seen <= toElide {
-				replacement = llm.Text(imageOverflowPlaceholder)
-			} else {
-				norm, changed, err := normalizeImage(ip, caps)
-				if err != nil {
-					return llm.Request{}, fmt.Errorf("media: message %d, part %d: %w", mi, pi, err)
-				}
-				if !changed {
-					continue
-				}
-				replacement = norm
+			norm, changed, err := normalizeImage(ip, caps)
+			if err != nil {
+				return llm.Request{}, fmt.Errorf("media: message %d, part %d: %w", mi, pi, err)
+			}
+			if !changed {
+				continue
 			}
-
 			if !copiedMessages {
 				out.Messages = make([]llm.Message, len(req.Messages))
 				copy(out.Messages, req.Messages)
@@ -107,17 +86,12 @@ func Normalize(req llm.Request, caps llm.Capabilities) (llm.Request, error) {
 				out.Messages[mi].Parts = parts
 				copiedParts = true
 			}
-			out.Messages[mi].Parts[pi] = replacement
+			out.Messages[mi].Parts[pi] = norm
 		}
 	}
 	return out, nil
 }
 
-// imageOverflowPlaceholder replaces an image elided to fit a target's
-// per-request image cap. It keeps the message turn intact and tells the model
-// an earlier image was omitted rather than silently changing the conversation.
-const imageOverflowPlaceholder = "[earlier image omitted to fit this model's per-request image limit]"
-
 // Info reports an image part's sniffed format ("jpeg", "png", "gif", or
 // "webp") and pixel dimensions. It is a cheap metadata read — the pixels are
 // never decoded. webp is recognized by signature but not decodable with the

media/media_test.go

@@ -149,48 +149,18 @@ func TestNormalizeImagesUnsupported(t *testing.T) {
 	}
 }
 
-func TestNormalizeOverCount(t *testing.T) {
-	// 3 distinguishable images across 2 messages; cap = 2. Over-count 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, in order.
-	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)
+func TestNormalizeTooManyImages(t *testing.T) {
+	img := llm.Image("image/png", encPNG(t, gradient(4, 4)))
 	req := llm.Request{Messages: []llm.Message{
-		llm.UserParts(a, b),
-		llm.UserParts(c),
+		llm.UserParts(img, img),
+		llm.UserParts(img),
 	}}
-	caps := llm.Capabilities{MaxImagesPerReq: 2, MaxImageDimension: 64, MaxImageBytes: 1 << 20, AllowedImageMIME: []string{"image/png"}}
-	out, err := Normalize(req, caps)
-	if err != nil {
-		t.Fatalf("over-count should not error: %v", err)
+	_, err := Normalize(req, llm.Capabilities{MaxImagesPerReq: 2})
+	if !errors.Is(err, llm.ErrUnsupported) {
+		t.Fatalf("err = %v, want ErrUnsupported", 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 v.Text == imageOverflowPlaceholder {
-					placeholders++
-				}
-			}
-		}
-	}
-	// The exact survivors are the most-recent two, in order: b then c (a elided).
-	if len(imgs) != 2 || !bytes.Equal(imgs[0].Data, b.Data) || !bytes.Equal(imgs[1].Data, c.Data) {
-		t.Fatalf("kept %d images; want exactly [b, c] (the most-recent two)", len(imgs))
-	}
-	if placeholders != 1 {
-		t.Errorf("placeholders = %d, want 1 for the elided oldest image", placeholders)
-	}
-	// Input request untouched (copy-on-write): the first part is still image a,
-	// not a placeholder — a len check alone wouldn't catch in-place substitution.
-	first, ok := req.Messages[0].Parts[0].(llm.ImagePart)
-	if !ok || !bytes.Equal(first.Data, a.Data) {
-		t.Errorf("input request was mutated; first part = %+v", req.Messages[0].Parts[0])
+	if !strings.Contains(err.Error(), "3 images") || !strings.Contains(err.Error(), "at most 2") {
+		t.Errorf("err message %q lacks the counts", err)
 	}
 }
 

provider/llamaswap/image.go

@@ -27,23 +27,14 @@ type imageModel struct {
 	id string
 }
 
-// imageRequest is the OpenAI /v1/images/generations request shape, plus the
-// stable-diffusion.cpp extras llama-swap forwards to sd-server. We always
-// request b64_json so the bytes come back inline (no second fetch). The
-// optional fields are pointers/omitempty so an unset value is omitted entirely
-// and sd-server falls back to the model's own default (a field name a given
-// sd-server build doesn't recognize is simply ignored — harmless).
+// imageRequest is the OpenAI /v1/images/generations request shape. We always
+// request b64_json so the bytes come back inline (no second fetch).
 type imageRequest struct {
-	Model          string   `json:"model"`
-	Prompt         string   `json:"prompt"`
-	N              int      `json:"n,omitempty"`
-	Size           string   `json:"size,omitempty"`
-	ResponseFormat string   `json:"response_format"`
-	Steps          *int     `json:"steps,omitempty"`
-	CFGScale       *float64 `json:"cfg_scale,omitempty"`
-	NegativePrompt string   `json:"negative_prompt,omitempty"`
-	SampleMethod   string   `json:"sample_method,omitempty"`
-	Seed           *int64   `json:"seed,omitempty"`
+	Model          string `json:"model"`
+	Prompt         string `json:"prompt"`
+	N              int    `json:"n,omitempty"`
+	Size           string `json:"size,omitempty"`
+	ResponseFormat string `json:"response_format"`
 }
 
 type imageResponse struct {
@@ -70,11 +61,6 @@ func (m *imageModel) Generate(ctx context.Context, req imagegen.Request, opts ..
 		N:              req.N,
 		Size:           req.Size,
 		ResponseFormat: "b64_json",
-		Steps:          req.Steps,
-		CFGScale:       req.CFGScale,
-		NegativePrompt: req.NegativePrompt,
-		SampleMethod:   req.Sampler,
-		Seed:           req.Seed,
 	}
 
 	var resp imageResponse

provider/llamaswap/llamaswap_test.go

@@ -201,48 +201,6 @@ func TestImageGenerate(t *testing.T) {
 	}
 }
 
-func TestImageGenerateSettings(t *testing.T) {
-	var gotBody map[string]any
-	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		_ = json.NewDecoder(r.Body).Decode(&gotBody)
-		_, _ = w.Write([]byte(`{"created":1,"data":[{"b64_json":"` + onePixelPNG + `"}]}`))
-	}))
-	defer srv.Close()
-
-	p := New(WithBaseURL(srv.URL), WithHTTPClient(srv.Client()))
-	im, _ := p.ImageModel("sd")
-
-	// Unset overrides must be omitted entirely so sd-server keeps its own
-	// per-model defaults.
-	if _, err := im.Generate(context.Background(), imagegen.Request{Prompt: "x"}); err != nil {
-		t.Fatalf("Generate: %v", err)
-	}
-	for _, k := range []string{"steps", "cfg_scale", "negative_prompt", "sample_method", "seed"} {
-		if v, ok := gotBody[k]; ok {
-			t.Errorf("unset request sent %q = %v, want omitted", k, v)
-		}
-	}
-
-	// Set overrides are forwarded with the sd-server-friendly field names.
-	gotBody = nil
-	_, err := im.Generate(context.Background(), imagegen.Request{Prompt: "x"},
-		imagegen.WithSteps(8),
-		imagegen.WithCFGScale(3.5),
-		imagegen.WithNegativePrompt("blurry"),
-		imagegen.WithSampler("euler"),
-		imagegen.WithSeed(42),
-	)
-	if err != nil {
-		t.Fatalf("Generate: %v", err)
-	}
-	want := map[string]any{"steps": float64(8), "cfg_scale": 3.5, "negative_prompt": "blurry", "sample_method": "euler", "seed": float64(42)}
-	for k, w := range want {
-		if gotBody[k] != w {
-			t.Errorf("%s = %v, want %v", k, gotBody[k], w)
-		}
-	}
-}
-
 func TestImageGenerateEmptyPrompt(t *testing.T) {
 	p := New(WithBaseURL("http://example.invalid"))
 	im, _ := p.ImageModel("sd")