fix: address gadfly review — filename sanitization, truncation guard, shared plumbing

- Transcribe: sanitize the caller-supplied multipart filename (CR/LF
  would inject Content-Disposition headers; upload metadata is
  untrusted), always send the required model/response_format fields,
  parse MIME parameters before extension matching, and give audio/opus
  its own .opus extension.
- doRaw: a response larger than maxResponseBytes is now an error, not a
  silent truncation.
- Shared plumbing: requireBaseURL() + newRequest() helpers replace the
  7x-duplicated guard/error string and the triplicated request
  building across doJSON/doRaw/Health.
- Health: non-2xx now returns *llm.APIError (package convention,
  programmatically distinguishable from transport failure) instead of
  a one-off unexported error type.
- Speak: reject negative Speed; speechMIME no longer accepts video/*
  Content-Types.
- image.go: Generate/Edit share one sdWire validate+map helper.

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01AXQxVhXBw8PwFAtsVrXSmj

provider/llamaswap/image.go

@@ -16,8 +16,8 @@ import (
 // served by llama-swap (routed to a stable-diffusion.cpp upstream). The id is
 // passed through verbatim and selects which upstream llama-swap loads.
 func (p *Provider) ImageModel(id string, opts ...imagegen.ModelOption) (imagegen.Model, error) {
-	if p.baseURL == "" {
-		return nil, fmt.Errorf("llama-swap provider %q: no base URL configured (set one via WithBaseURL or an LLM_* env DSN)", p.name)
+	if err := p.requireBaseURL(); err != nil {
+		return nil, err
 	}
 	_ = imagegen.ApplyModelOptions(opts)
 	return &imageModel{p: p, id: id}, nil
@@ -53,32 +53,39 @@ type txt2imgResponse struct {
 	Images []string `json:"images"`
 }
 
+// sdWire validates the generation knobs shared by Generate and Edit and
+// builds the common txt2img wire fields. verb labels validation errors.
+func (m *imageModel) sdWire(verb, prompt, negativePrompt, sampler, size string, seed *int64, steps *int, cfgScale *float64, n int) (txt2imgRequest, error) {
+	if strings.TrimSpace(prompt) == "" {
+		return txt2imgRequest{}, fmt.Errorf("%w: image %s requires a prompt", llm.ErrUnsupported, verb)
+	}
+	if n < 0 {
+		return txt2imgRequest{}, fmt.Errorf("%w: image count N must be >= 0, got %d", llm.ErrUnsupported, n)
+	}
+	width, height, err := parseSize(size)
+	if err != nil {
+		return txt2imgRequest{}, fmt.Errorf("%w: %v", llm.ErrUnsupported, err)
+	}
+	return txt2imgRequest{
+		Model:          m.id,
+		Prompt:         prompt,
+		NegativePrompt: negativePrompt,
+		Seed:           seed,
+		Steps:          steps,
+		CFGScale:       cfgScale,
+		Width:          width,
+		Height:         height,
+		SampleMethod:   sampler,
+		BatchCount:     n,
+	}, nil
+}
+
 // Generate implements imagegen.Model via POST {base}/sdapi/v1/txt2img.
 func (m *imageModel) Generate(ctx context.Context, req imagegen.Request, opts ...imagegen.Option) (*imagegen.Result, error) {
 	req = req.Apply(opts...)
-	if strings.TrimSpace(req.Prompt) == "" {
-		return nil, fmt.Errorf("%w: image generation requires a prompt", llm.ErrUnsupported)
-	}
-	if req.N < 0 {
-		return nil, fmt.Errorf("%w: image count N must be >= 0, got %d", llm.ErrUnsupported, req.N)
-	}
-
-	width, height, err := parseSize(req.Size)
+	wire, err := m.sdWire("generation", req.Prompt, req.NegativePrompt, req.Sampler, req.Size, req.Seed, req.Steps, req.CFGScale, req.N)
 	if err != nil {
-		return nil, fmt.Errorf("%w: %v", llm.ErrUnsupported, err)
-	}
-
-	wire := txt2imgRequest{
-		Model:          m.id,
-		Prompt:         req.Prompt,
-		NegativePrompt: req.NegativePrompt,
-		Seed:           req.Seed,
-		Steps:          req.Steps,
-		CFGScale:       req.CFGScale,
-		Width:          width,
-		Height:         height,
-		SampleMethod:   req.Sampler,
-		BatchCount:     req.N,
+		return nil, err
 	}
 
 	var resp txt2imgResponse
@@ -126,37 +133,18 @@ type img2imgRequest struct {
 // Edit implements imagegen.Editor via POST {base}/sdapi/v1/img2img.
 func (m *imageModel) Edit(ctx context.Context, req imagegen.EditRequest, opts ...imagegen.EditOption) (*imagegen.Result, error) {
 	req = req.Apply(opts...)
-	if strings.TrimSpace(req.Prompt) == "" {
-		return nil, fmt.Errorf("%w: image edit requires a prompt", llm.ErrUnsupported)
-	}
 	if len(req.Init.Data) == 0 {
 		return nil, fmt.Errorf("%w: image edit requires an init image", llm.ErrUnsupported)
 	}
-	if req.N < 0 {
-		return nil, fmt.Errorf("%w: image count N must be >= 0, got %d", llm.ErrUnsupported, req.N)
-	}
 	if req.Strength != nil && (*req.Strength < 0 || *req.Strength > 1) {
 		return nil, fmt.Errorf("%w: edit strength must be in [0,1], got %g", llm.ErrUnsupported, *req.Strength)
 	}
-
-	width, height, err := parseSize(req.Size)
+	base, err := m.sdWire("edit", req.Prompt, req.NegativePrompt, req.Sampler, req.Size, req.Seed, req.Steps, req.CFGScale, req.N)
 	if err != nil {
-		return nil, fmt.Errorf("%w: %v", llm.ErrUnsupported, err)
+		return nil, err
 	}
-
 	wire := img2imgRequest{
-		txt2imgRequest: txt2imgRequest{
-			Model:          m.id,
-			Prompt:         req.Prompt,
-			NegativePrompt: req.NegativePrompt,
-			Seed:           req.Seed,
-			Steps:          req.Steps,
-			CFGScale:       req.CFGScale,
-			Width:          width,
-			Height:         height,
-			SampleMethod:   req.Sampler,
-			BatchCount:     req.N,
-		},
+		txt2imgRequest:    base,
 		InitImages:        []string{base64.StdEncoding.EncodeToString(req.Init.Data)},
 		DenoisingStrength: req.Strength,
 	}