steve
96c612e707
Add provider/llamaswap, a tailored provider for llama-swap (the model-swapping
proxy over llama.cpp / stable-diffusion.cpp). Its chat path delegates to
provider/openai at {base}/v1 — no duplicated wire client (ADR-0007) — with
legacy max_tokens, a Bearer no-key placeholder for keyless local instances, and
a timeout-free client so cold model swaps rely on context deadlines. The
"tailored" surface is concrete management methods (ListModels / Running /
Unload) that don't belong on the canonical llm.Provider interface. The
llama-swap:// DSN scheme builds an http base URL (local-first); a no-URL
built-in errors clearly on use, mirroring foreman.
Add imagegen, a new canonical text-to-image interface separate from llm
(Request/Result/Model/Provider; Image = llm.ImagePart so generated images feed
straight back into chat). First backend is llama-swap via OpenAI
/v1/images/generations (b64_json, bytes-only). Re-exported from the root. v1 is
txt2img only.
Hermetic httptest coverage for chat delegation, management endpoints, image
decode, and scheme wiring. ADR-0015 + ADR-0016, README support matrix +
image-gen section, CLAUDE.md package map, and progress.md updated in the same
commit.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
43 lines
1.1 KiB
Go
43 lines
1.1 KiB
Go
package imagegen
|
|
|
|
import (
|
|
"testing"
|
|
|
|
"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
|
|
)
|
|
|
|
func TestRequestApply(t *testing.T) {
|
|
base := Request{Prompt: "a red bicycle"}
|
|
got := base.Apply(WithN(3), WithSize("1024x1024"))
|
|
|
|
if got.Prompt != "a red bicycle" {
|
|
t.Errorf("Prompt = %q, want %q", got.Prompt, "a red bicycle")
|
|
}
|
|
if got.N != 3 {
|
|
t.Errorf("N = %d, want 3", got.N)
|
|
}
|
|
if got.Size != "1024x1024" {
|
|
t.Errorf("Size = %q, want %q", got.Size, "1024x1024")
|
|
}
|
|
|
|
// Apply must not mutate the receiver (options apply to a copy).
|
|
if base.N != 0 || base.Size != "" {
|
|
t.Errorf("base mutated: %+v", base)
|
|
}
|
|
}
|
|
|
|
func TestApplyModelOptions(t *testing.T) {
|
|
// No options yet; just verify it returns a usable zero config.
|
|
_ = ApplyModelOptions(nil)
|
|
}
|
|
|
|
// TestImageIsImagePart pins the alias so generated images stay interchangeable
|
|
// with chat content.
|
|
func TestImageIsImagePart(t *testing.T) {
|
|
var img Image = llm.ImagePart{MIME: "image/png", Data: []byte{0x89, 'P', 'N', 'G'}}
|
|
var part llm.Part = img // must satisfy llm.Part for use in messages
|
|
if _, ok := part.(llm.ImagePart); !ok {
|
|
t.Fatalf("Image does not round-trip as llm.ImagePart")
|
|
}
|
|
}
|