fix(gemini): map responseModalities to uppercase IMAGE/TEXT

Author: hkfires

internal/runtime/executor/gemini_cli_executor.go

@@ -703,7 +703,7 @@ func fixGeminiCLIImageAspectRatio(modelName string, rawJSON []byte) []byte {
 					}
 
 					rawJSON, _ = sjson.SetRawBytes(rawJSON, "request.contents.0.parts", []byte(newPartsJson))
-					rawJSON, _ = sjson.SetRawBytes(rawJSON, "request.generationConfig.responseModalities", []byte(`["Image", "Text"]`))
+					rawJSON, _ = sjson.SetRawBytes(rawJSON, "request.generationConfig.responseModalities", []byte(`["IMAGE", "TEXT"]`))
 				}
 			}
 			rawJSON, _ = sjson.DeleteBytes(rawJSON, "request.generationConfig.imageConfig")

internal/translator/gemini-cli/openai/chat-completions/gemini-cli_openai_request.go

@@ -66,15 +66,15 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
 	}
 
 	// Map OpenAI modalities -> Gemini CLI request.generationConfig.responseModalities
-	// e.g. "modalities": ["image", "text"] -> ["Image", "Text"]
+	// e.g. "modalities": ["image", "text"] -> ["IMAGE", "TEXT"]
 	if mods := gjson.GetBytes(rawJSON, "modalities"); mods.Exists() && mods.IsArray() {
 		var responseMods []string
 		for _, m := range mods.Array() {
 			switch strings.ToLower(m.String()) {
 			case "text":
-				responseMods = append(responseMods, "Text")
+				responseMods = append(responseMods, "TEXT")
 			case "image":
-				responseMods = append(responseMods, "Image")
+				responseMods = append(responseMods, "IMAGE")
 			}
 		}
 		if len(responseMods) > 0 {

internal/translator/gemini/openai/chat-completions/gemini_openai_request.go

@@ -66,15 +66,15 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 	}
 
 	// Map OpenAI modalities -> Gemini generationConfig.responseModalities
-	// e.g. "modalities": ["image", "text"] -> ["Image", "Text"]
+	// e.g. "modalities": ["image", "text"] -> ["IMAGE", "TEXT"]
 	if mods := gjson.GetBytes(rawJSON, "modalities"); mods.Exists() && mods.IsArray() {
 		var responseMods []string
 		for _, m := range mods.Array() {
 			switch strings.ToLower(m.String()) {
 			case "text":
-				responseMods = append(responseMods, "Text")
+				responseMods = append(responseMods, "TEXT")
 			case "image":
-				responseMods = append(responseMods, "Image")
+				responseMods = append(responseMods, "IMAGE")
 			}
 		}
 		if len(responseMods) > 0 {