feat(api): add OpenAI compatibility for image models

- Introduced OpenAI-compatible image model support in the API, enabling integration through image generation and editing endpoints.
- Added registry type for OpenAIImageModelType to classify and validate compatibility.
- Implemented request handling for OpenAI-compatible image models, including JSON and multipart formats.
- Enhanced executor methods to support OpenAI-compatible image streaming and non-streaming requests.
- Included tests to validate model registration, streaming behavior, and multipart payload formatting.

internal/watcher/diff/model_hash_test.go

@@ -25,6 +25,17 @@ func TestComputeOpenAICompatModelsHash_Deterministic(t *testing.T) {
 	}
 }
 
+func TestComputeOpenAICompatModelsHash_IncludesImageFlag(t *testing.T) {
+	textModel := ComputeOpenAICompatModelsHash([]config.OpenAICompatibilityModel{{Name: "gpt-image", Alias: "image"}})
+	imageModel := ComputeOpenAICompatModelsHash([]config.OpenAICompatibilityModel{{Name: "gpt-image", Alias: "image", Image: true}})
+	if textModel == "" || imageModel == "" {
+		t.Fatal("hashes should not be empty")
+	}
+	if textModel == imageModel {
+		t.Fatal("hash should change when image flag changes")
+	}
+}
+
 func TestComputeOpenAICompatModelsHash_NormalizesAndDedups(t *testing.T) {
 	a := []config.OpenAICompatibilityModel{
 		{Name: "gpt-4", Alias: "gpt4"},