Merge branch 'router-for-me:main' into main

Fixed incorrect function signature call to `NewBaseAPIHandlers`

config.example.yaml

@@ -39,6 +39,9 @@ api-keys:
 # Enable debug logging
 debug: false
 
+# When true, disable high-overhead HTTP middleware features to reduce per-request memory usage under high concurrency.
+commercial-mode: false
+
 # Open OAuth URLs in incognito/private browser mode.
 # Useful when you want to login with a different account without logging out from your current session.
 # Default: false (but Kiro auth defaults to true for multi-account support)

internal/api/server.go

@@ -209,13 +209,15 @@ func NewServer(cfg *config.Config, authManager *auth.Manager, accessManager *sdk
 	// Resolve logs directory relative to the configuration file directory.
 	var requestLogger logging.RequestLogger
 	var toggle func(bool)
-	if optionState.requestLoggerFactory != nil {
-		requestLogger = optionState.requestLoggerFactory(cfg, configFilePath)
-	}
-	if requestLogger != nil {
-		engine.Use(middleware.RequestLoggingMiddleware(requestLogger))
-		if setter, ok := requestLogger.(interface{ SetEnabled(bool) }); ok {
-			toggle = setter.SetEnabled
+	if !cfg.CommercialMode {
+		if optionState.requestLoggerFactory != nil {
+			requestLogger = optionState.requestLoggerFactory(cfg, configFilePath)
+		}
+		if requestLogger != nil {
+			engine.Use(middleware.RequestLoggingMiddleware(requestLogger))
+			if setter, ok := requestLogger.(interface{ SetEnabled(bool) }); ok {
+				toggle = setter.SetEnabled
+			}
 		}
 	}
 

internal/config/config.go

@@ -39,6 +39,9 @@ type Config struct {
 	// Debug enables or disables debug-level logging and other debug features.
 	Debug bool `yaml:"debug" json:"debug"`
 
+	// CommercialMode disables high-overhead HTTP middleware features to minimize per-request memory usage.
+	CommercialMode bool `yaml:"commercial-mode" json:"commercial-mode"`
+
 	// LoggingToFile controls whether application logs are written to rotating files or stdout.
 	LoggingToFile bool `yaml:"logging-to-file" json:"logging-to-file"`
 

internal/translator/antigravity/claude/antigravity_claude_response.go

@@ -271,11 +271,11 @@ func ConvertAntigravityResponseToClaude(_ context.Context, _ string, originalReq
 
 	if usageResult := gjson.GetBytes(rawJSON, "response.usageMetadata"); usageResult.Exists() {
 		params.HasUsageMetadata = true
-		params.PromptTokenCount = usageResult.Get("promptTokenCount").Int()
+		params.CachedTokenCount = usageResult.Get("cachedContentTokenCount").Int()
+		params.PromptTokenCount = usageResult.Get("promptTokenCount").Int() - params.CachedTokenCount
 		params.CandidatesTokenCount = usageResult.Get("candidatesTokenCount").Int()
 		params.ThoughtsTokenCount = usageResult.Get("thoughtsTokenCount").Int()
 		params.TotalTokenCount = usageResult.Get("totalTokenCount").Int()
-		params.CachedTokenCount = usageResult.Get("cachedContentTokenCount").Int()
 		if params.CandidatesTokenCount == 0 && params.TotalTokenCount > 0 {
 			params.CandidatesTokenCount = params.TotalTokenCount - params.PromptTokenCount - params.ThoughtsTokenCount
 			if params.CandidatesTokenCount < 0 {

internal/translator/antigravity/openai/chat-completions/antigravity_openai_request.go

@@ -249,8 +249,28 @@ func ConvertOpenAIRequestToAntigravity(modelName string, inputRawJSON []byte, _
 				p := 0
 				if content.Type == gjson.String {
 					node, _ = sjson.SetBytes(node, "parts.-1.text", content.String())
-					out, _ = sjson.SetRawBytes(out, "request.contents.-1", node)
 					p++
+				} else if content.IsArray() {
+					// Assistant multimodal content (e.g. text + image) -> single model content with parts
+					for _, item := range content.Array() {
+						switch item.Get("type").String() {
+						case "text":
+							p++
+						case "image_url":
+							// If the assistant returned an inline data URL, preserve it for history fidelity.
+							imageURL := item.Get("image_url.url").String()
+							if len(imageURL) > 5 { // expect data:...
+								pieces := strings.SplitN(imageURL[5:], ";", 2)
+								if len(pieces) == 2 && len(pieces[1]) > 7 {
+									mime := pieces[0]
+									data := pieces[1][7:]
+									node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".inlineData.mime_type", mime)
+									node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".inlineData.data", data)
+									p++
+								}
+							}
+						}
+					}
 				}
 
 				// Tool calls -> single model content with functionCall parts
@@ -305,6 +325,8 @@ func ConvertOpenAIRequestToAntigravity(modelName string, inputRawJSON []byte, _
 					if pp > 0 {
 						out, _ = sjson.SetRawBytes(out, "request.contents.-1", toolNode)
 					}
+				} else {
+					out, _ = sjson.SetRawBytes(out, "request.contents.-1", node)
 				}
 			}
 		}

internal/translator/antigravity/openai/chat-completions/antigravity_openai_response.go

@@ -87,15 +87,15 @@ func ConvertAntigravityResponseToOpenAI(_ context.Context, _ string, originalReq
 
 	// Extract and set usage metadata (token counts).
 	if usageResult := gjson.GetBytes(rawJSON, "response.usageMetadata"); usageResult.Exists() {
+		cachedTokenCount := usageResult.Get("cachedContentTokenCount").Int()
 		if candidatesTokenCountResult := usageResult.Get("candidatesTokenCount"); candidatesTokenCountResult.Exists() {
 			template, _ = sjson.Set(template, "usage.completion_tokens", candidatesTokenCountResult.Int())
 		}
 		if totalTokenCountResult := usageResult.Get("totalTokenCount"); totalTokenCountResult.Exists() {
 			template, _ = sjson.Set(template, "usage.total_tokens", totalTokenCountResult.Int())
 		}
-		promptTokenCount := usageResult.Get("promptTokenCount").Int()
+		promptTokenCount := usageResult.Get("promptTokenCount").Int() - cachedTokenCount
 		thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").Int()
-		cachedTokenCount := usageResult.Get("cachedContentTokenCount").Int()
 		template, _ = sjson.Set(template, "usage.prompt_tokens", promptTokenCount+thoughtsTokenCount)
 		if thoughtsTokenCount > 0 {
 			template, _ = sjson.Set(template, "usage.completion_tokens_details.reasoning_tokens", thoughtsTokenCount)
@@ -181,12 +181,14 @@ func ConvertAntigravityResponseToOpenAI(_ context.Context, _ string, originalReq
 					mimeType = "image/png"
 				}
 				imageURL := fmt.Sprintf("data:%s;base64,%s", mimeType, data)
-				imagePayload := `{"image_url":{"url":""},"type":"image_url"}`
-				imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
 				imagesResult := gjson.Get(template, "choices.0.delta.images")
 				if !imagesResult.Exists() || !imagesResult.IsArray() {
 					template, _ = sjson.SetRaw(template, "choices.0.delta.images", `[]`)
 				}
+				imageIndex := len(gjson.Get(template, "choices.0.delta.images").Array())
+				imagePayload := `{"type":"image_url","image_url":{"url":""}}`
+				imagePayload, _ = sjson.Set(imagePayload, "index", imageIndex)
+				imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
 				template, _ = sjson.Set(template, "choices.0.delta.role", "assistant")
 				template, _ = sjson.SetRaw(template, "choices.0.delta.images.-1", imagePayload)
 			}

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

@@ -218,8 +218,29 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
 				if content.Type == gjson.String {
 					// Assistant text -> single model content
 					node, _ = sjson.SetBytes(node, "parts.-1.text", content.String())
-					out, _ = sjson.SetRawBytes(out, "request.contents.-1", node)
 					p++
+				} else if content.IsArray() {
+					// Assistant multimodal content (e.g. text + image) -> single model content with parts
+					for _, item := range content.Array() {
+						switch item.Get("type").String() {
+						case "text":
+							node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".text", item.Get("text").String())
+							p++
+						case "image_url":
+							// If the assistant returned an inline data URL, preserve it for history fidelity.
+							imageURL := item.Get("image_url.url").String()
+							if len(imageURL) > 5 { // expect data:...
+								pieces := strings.SplitN(imageURL[5:], ";", 2)
+								if len(pieces) == 2 && len(pieces[1]) > 7 {
+									mime := pieces[0]
+									data := pieces[1][7:]
+									node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".inlineData.mime_type", mime)
+									node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".inlineData.data", data)
+									p++
+								}
+							}
+						}
+					}
 				}
 
 				// Tool calls -> single model content with functionCall parts
@@ -260,6 +281,8 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
 					if pp > 0 {
 						out, _ = sjson.SetRawBytes(out, "request.contents.-1", toolNode)
 					}
+				} else {
+					out, _ = sjson.SetRawBytes(out, "request.contents.-1", node)
 				}
 			}
 		}

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

@@ -170,12 +170,14 @@ func ConvertCliResponseToOpenAI(_ context.Context, _ string, originalRequestRawJ
 					mimeType = "image/png"
 				}
 				imageURL := fmt.Sprintf("data:%s;base64,%s", mimeType, data)
-				imagePayload := `{"image_url":{"url":""},"type":"image_url"}`
-				imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
 				imagesResult := gjson.Get(template, "choices.0.delta.images")
 				if !imagesResult.Exists() || !imagesResult.IsArray() {
 					template, _ = sjson.SetRaw(template, "choices.0.delta.images", `[]`)
 				}
+				imageIndex := len(gjson.Get(template, "choices.0.delta.images").Array())
+				imagePayload := `{"type":"image_url","image_url":{"url":""}}`
+				imagePayload, _ = sjson.Set(imagePayload, "index", imageIndex)
+				imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
 				template, _ = sjson.Set(template, "choices.0.delta.role", "assistant")
 				template, _ = sjson.SetRaw(template, "choices.0.delta.images.-1", imagePayload)
 			}

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

@@ -233,18 +233,15 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 			} else if role == "assistant" {
 				node := []byte(`{"role":"model","parts":[]}`)
 				p := 0
-
 				if content.Type == gjson.String {
 					// Assistant text -> single model content
 					node, _ = sjson.SetBytes(node, "parts.-1.text", content.String())
-					out, _ = sjson.SetRawBytes(out, "contents.-1", node)
 					p++
 				} else if content.IsArray() {
 					// Assistant multimodal content (e.g. text + image) -> single model content with parts
 					for _, item := range content.Array() {
 						switch item.Get("type").String() {
 						case "text":
-							node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".text", item.Get("text").String())
 							p++
 						case "image_url":
 							// If the assistant returned an inline data URL, preserve it for history fidelity.
@@ -261,7 +258,6 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 							}
 						}
 					}
-					out, _ = sjson.SetRawBytes(out, "contents.-1", node)
 				}
 
 				// Tool calls -> single model content with functionCall parts
@@ -302,6 +298,8 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 					if pp > 0 {
 						out, _ = sjson.SetRawBytes(out, "contents.-1", toolNode)
 					}
+				} else {
+					out, _ = sjson.SetRawBytes(out, "contents.-1", node)
 				}
 			}
 		}

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

@@ -89,15 +89,15 @@ func ConvertGeminiResponseToOpenAI(_ context.Context, _ string, originalRequestR
 
 	// Extract and set usage metadata (token counts).
 	if usageResult := gjson.GetBytes(rawJSON, "usageMetadata"); usageResult.Exists() {
+		cachedTokenCount := usageResult.Get("cachedContentTokenCount").Int()
 		if candidatesTokenCountResult := usageResult.Get("candidatesTokenCount"); candidatesTokenCountResult.Exists() {
 			template, _ = sjson.Set(template, "usage.completion_tokens", candidatesTokenCountResult.Int())
 		}
 		if totalTokenCountResult := usageResult.Get("totalTokenCount"); totalTokenCountResult.Exists() {
 			template, _ = sjson.Set(template, "usage.total_tokens", totalTokenCountResult.Int())
 		}
-		promptTokenCount := usageResult.Get("promptTokenCount").Int()
+		promptTokenCount := usageResult.Get("promptTokenCount").Int() - cachedTokenCount
 		thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").Int()
-		cachedTokenCount := usageResult.Get("cachedContentTokenCount").Int()
 		template, _ = sjson.Set(template, "usage.prompt_tokens", promptTokenCount+thoughtsTokenCount)
 		if thoughtsTokenCount > 0 {
 			template, _ = sjson.Set(template, "usage.completion_tokens_details.reasoning_tokens", thoughtsTokenCount)
@@ -182,12 +182,14 @@ func ConvertGeminiResponseToOpenAI(_ context.Context, _ string, originalRequestR
 					mimeType = "image/png"
 				}
 				imageURL := fmt.Sprintf("data:%s;base64,%s", mimeType, data)
-				imagePayload := `{"image_url":{"url":""},"type":"image_url"}`
-				imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
 				imagesResult := gjson.Get(template, "choices.0.delta.images")
 				if !imagesResult.Exists() || !imagesResult.IsArray() {
 					template, _ = sjson.SetRaw(template, "choices.0.delta.images", `[]`)
 				}
+				imageIndex := len(gjson.Get(template, "choices.0.delta.images").Array())
+				imagePayload := `{"type":"image_url","image_url":{"url":""}}`
+				imagePayload, _ = sjson.Set(imagePayload, "index", imageIndex)
+				imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
 				template, _ = sjson.Set(template, "choices.0.delta.role", "assistant")
 				template, _ = sjson.SetRaw(template, "choices.0.delta.images.-1", imagePayload)
 			}
@@ -316,12 +318,14 @@ func ConvertGeminiResponseToOpenAINonStream(_ context.Context, _ string, origina
 					mimeType = "image/png"
 				}
 				imageURL := fmt.Sprintf("data:%s;base64,%s", mimeType, data)
-				imagePayload := `{"image_url":{"url":""},"type":"image_url"}`
-				imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
 				imagesResult := gjson.Get(template, "choices.0.message.images")
 				if !imagesResult.Exists() || !imagesResult.IsArray() {
 					template, _ = sjson.SetRaw(template, "choices.0.message.images", `[]`)
 				}
+				imageIndex := len(gjson.Get(template, "choices.0.message.images").Array())
+				imagePayload := `{"type":"image_url","image_url":{"url":""}}`
+				imagePayload, _ = sjson.Set(imagePayload, "index", imageIndex)
+				imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
 				template, _ = sjson.Set(template, "choices.0.message.role", "assistant")
 				template, _ = sjson.SetRaw(template, "choices.0.message.images.-1", imagePayload)
 			}

sdk/api/handlers/handlers_stream_bootstrap_test.go

@@ -99,7 +99,7 @@ func TestExecuteStreamWithAuthManager_RetriesBeforeFirstByte(t *testing.T) {
 		Streaming: sdkconfig.StreamingConfig{
 			BootstrapRetries: &bootstrapRetries,
 		},
-	}, manager, nil)
+	}, manager)
 	dataChan, errChan := handler.ExecuteStreamWithAuthManager(context.Background(), "openai", "test-model", []byte(`{"model":"test-model"}`), "")
 	if dataChan == nil || errChan == nil {
 		t.Fatalf("expected non-nil channels")