fix(model): 支持不设置推理强度

internal/backend/agent/model/openai_stream_test.go

@@ -63,6 +63,79 @@ func TestOpenAIResponsesRequestsReasoningSummary(t *testing.T) {
 	assertOpenAIEventKindCount(t, events, ModelEventKindTextDelta, 1)
 }
 
+func TestOpenAIResponsesOmitsReasoningWhenEffortBlank(t *testing.T) {
+	var requestBody map[string]any
+	server := httptest.NewServer(http.HandlerFunc(func(writer http.ResponseWriter, request *http.Request) {
+		if err := json.NewDecoder(request.Body).Decode(&requestBody); err != nil {
+			http.Error(writer, err.Error(), http.StatusBadRequest)
+			return
+		}
+		writer.Header().Set("Content-Type", "text/event-stream")
+		_, _ = fmt.Fprint(writer, "data: {\"type\":\"response.completed\",\"response\":{\"id\":\"resp-1\",\"model\":\"grok-composer-2.5-fast\",\"status\":\"completed\",\"output_text\":\"done\"}}\n\n")
+		_, _ = fmt.Fprint(writer, "data: [DONE]\n\n")
+	}))
+	defer server.Close()
+
+	adapter := &OpenAIAdapter{client: server.Client()}
+	err := adapter.Stream(context.Background(), StreamRequest{
+		RequestID:       "request-1",
+		RunID:           "run-1",
+		ModelCallID:     "model-call-1",
+		BaseURL:         server.URL,
+		APIKey:          "test-key",
+		ProviderModelID: "grok-composer-2.5-fast",
+		OpenAIEndpoint:  "/v1/responses",
+		Messages:        []Message{{Role: "user", Content: "hello"}},
+		MaxTokens:       128,
+	}, func(ModelEvent) error { return nil })
+	if err != nil {
+		t.Fatalf("stream failed: %v", err)
+	}
+
+	if _, exists := requestBody["reasoning"]; exists {
+		t.Fatalf("reasoning should be omitted when effort is blank: %#v", requestBody["reasoning"])
+	}
+	if _, exists := requestBody["reasoning_effort"]; exists {
+		t.Fatalf("reasoning_effort should be omitted when effort is blank: %#v", requestBody["reasoning_effort"])
+	}
+}
+
+func TestOpenAIChatCompletionsOmitsReasoningWhenEffortBlank(t *testing.T) {
+	var requestBody map[string]any
+	server := httptest.NewServer(http.HandlerFunc(func(writer http.ResponseWriter, request *http.Request) {
+		if err := json.NewDecoder(request.Body).Decode(&requestBody); err != nil {
+			http.Error(writer, err.Error(), http.StatusBadRequest)
+			return
+		}
+		writer.Header().Set("Content-Type", "text/event-stream")
+		_, _ = fmt.Fprint(writer, "data: {\"model\":\"grok-composer-2.5-fast\",\"choices\":[{\"delta\":{\"content\":\"done\"},\"finish_reason\":\"stop\"}]}\n\n")
+		_, _ = fmt.Fprint(writer, "data: [DONE]\n\n")
+	}))
+	defer server.Close()
+
+	adapter := &OpenAIAdapter{client: server.Client()}
+	err := adapter.Stream(context.Background(), StreamRequest{
+		RequestID:       "request-1",
+		RunID:           "run-1",
+		ModelCallID:     "model-call-1",
+		BaseURL:         server.URL,
+		APIKey:          "test-key",
+		ProviderModelID: "grok-composer-2.5-fast",
+		OpenAIEndpoint:  "/v1/chat/completions",
+		Messages:        []Message{{Role: "user", Content: "hello"}},
+		MaxTokens:       128,
+	}, func(ModelEvent) error { return nil })
+	if err != nil {
+		t.Fatalf("stream failed: %v", err)
+	}
+
+	for _, field := range []string{"reasoning_effort", "reasoning", "include"} {
+		if value, exists := requestBody[field]; exists {
+			t.Fatalf("%s should be omitted when effort is blank: %#v", field, value)
+		}
+	}
+}
+
 func TestOpenAIChatCompletionsIgnoresBlankFinishReason(t *testing.T) {
 	server := httptest.NewServer(http.HandlerFunc(func(writer http.ResponseWriter, request *http.Request) {
 		writer.Header().Set("Content-Type", "text/event-stream")

internal/backend/agent/model/router_test.go

@@ -1,10 +1,64 @@
 package modeladapter
 
 import (
+	"context"
 	"reflect"
 	"testing"
+	"time"
+
+	legacyruntime "cursor/internal/runtime"
 )
 
+type recordingModelAdapter struct {
+	request StreamRequest
+}
+
+func (adapter *recordingModelAdapter) Stream(_ context.Context, req StreamRequest, _ func(ModelEvent) error) error {
+	adapter.request = req
+	return nil
+}
+
+type staticChannelResolver struct {
+	channel *legacyruntime.ResolvedChannel
+}
+
+func (resolver staticChannelResolver) SelectChannelForModel(context.Context, string) (*legacyruntime.ResolvedChannel, error) {
+	return resolver.channel, nil
+}
+
+func (staticChannelResolver) ProviderStreamIdleTimeout(context.Context) time.Duration {
+	return time.Second
+}
+
+func TestRouterRuntimeDisabledClearsReasoningEffort(t *testing.T) {
+	openAI := &recordingModelAdapter{}
+	router := &Router{
+		openai: openAI,
+		resolver: staticChannelResolver{channel: &legacyruntime.ResolvedChannel{
+			ID:              "channel-a",
+			Provider:        "openai",
+			Model:           "grok-composer-2.5-fast",
+			ReasoningEffort: "medium",
+		}},
+	}
+	requestKnobs := map[string]any{"reasoning_effort": "medium"}
+
+	err := router.Stream(context.Background(), StreamRequest{
+		ModelID:        "channel-a",
+		ThinkingEffort: "disabled",
+		RequestKnobs:   requestKnobs,
+	}, func(ModelEvent) error { return nil })
+	if err != nil {
+		t.Fatalf("Stream returned error: %v", err)
+	}
+	if got := openAI.request.ReasoningEffort; got != "" {
+		t.Fatalf("ReasoningEffort = %q, want blank", got)
+	}
+	if _, exists := openAI.request.RequestKnobs["reasoning_effort"]; exists {
+		t.Fatalf("reasoning_effort knob should be removed: %#v", openAI.request.RequestKnobs)
+	}
+}
+
 func TestSanitizeProviderMessagesMergesLegacyAssistantTextAndToolCallTurnsIdempotently(t *testing.T) {
 	input := []Message{
 		{

internal/backend/server/config/types.go

@@ -141,8 +141,8 @@ func NormalizeModelAdapterConfigs(input []ModelAdapterConfig) ([]ModelAdapterCon
 			return nil, errors.New("模型适配器 tooltipData 不能为空")
 		case next.ModelID == "":
 			return nil, errors.New("模型适配器 modelID 不能为空")
-		case next.Type == "openai" && next.ReasoningEffort == "":
-			return nil, errors.New("模型适配器 reasoningEffort 仅支持 low、medium、high、xhigh、max")
+		case next.Type == "openai" && !isSupportedReasoningEffort(next.ReasoningEffort):
+			return nil, errors.New("模型适配器 reasoningEffort 仅支持空值、low、medium、high、xhigh、max")
 		case next.Type == "openai" && next.OpenAIEndpoint == "":
 			return nil, errors.New("模型适配器 openAIEndpoint 仅支持 /v1/responses、/v1/chat/completions 或 /custom（自定义路径）")
 		case next.Type == "openai" && next.OpenAIExtraParamsEnabled:
@@ -224,13 +224,15 @@ func validateHeadersJSON(value string) error {
 }
 
 func normalizeReasoningEffort(value string) string {
-	switch strings.ToLower(strings.TrimSpace(value)) {
-	case "", "medium":
-		return "medium"
-	case "low", "high", "xhigh", "max":
-		return strings.ToLower(strings.TrimSpace(value))
+	return strings.ToLower(strings.TrimSpace(value))
+}
+
+func isSupportedReasoningEffort(value string) bool {
+	switch value {
+	case "", "low", "medium", "high", "xhigh", "max":
+		return true
 	default:
-		return ""
+		return false
 	}
 }
 

internal/backend/server/config/types_test.go

@@ -58,3 +58,25 @@ func TestNormalizeModelAdapterConfigsUsesStableExplicitSort(t *testing.T) {
 		}
 	}
 }
+
+func TestNormalizeModelAdapterConfigsAllowsBlankReasoningEffort(t *testing.T) {
+	adapter := testModelAdapter("non-reasoning-model", 1)
+	adapter.ReasoningEffort = ""
+
+	adapters, err := NormalizeModelAdapterConfigs([]ModelAdapterConfig{adapter})
+	if err != nil {
+		t.Fatalf("NormalizeModelAdapterConfigs returned error: %v", err)
+	}
+	if got := adapters[0].ReasoningEffort; got != "" {
+		t.Fatalf("ReasoningEffort = %q, want blank", got)
+	}
+}
+
+func TestNormalizeModelAdapterConfigsRejectsUnknownReasoningEffort(t *testing.T) {
+	adapter := testModelAdapter("invalid-reasoning-effort", 1)
+	adapter.ReasoningEffort = "unsupported"
+
+	if _, err := NormalizeModelAdapterConfigs([]ModelAdapterConfig{adapter}); err == nil {
+		t.Fatal("NormalizeModelAdapterConfigs should reject an unknown reasoning effort")
+	}
+}

internal/backend/server/upstream/mocks.go

@@ -835,7 +835,7 @@ func defaultThinkingEffortForAdapter(adapter legacyruntime.ModelAdapterConfig) s
 	if strings.EqualFold(strings.TrimSpace(adapter.Type), "anthropic") {
 		return normalizeAvailableModelThinkingEffort(adapter.AnthropicThinkingEffort, true, "xhigh")
 	}
-	return normalizeAvailableModelThinkingEffort(adapter.ReasoningEffort, true, "medium")
+	return normalizeAvailableModelThinkingEffort(adapter.ReasoningEffort, true, "disabled")
 }
 
 func normalizeAvailableModelThinkingEffort(raw string, allowMax bool, fallback string) string {

internal/backend/server/upstream/mocks_test.go

@@ -28,6 +28,40 @@ func TestBuildCLIModelDetailsPreservesChannelMetadata(t *testing.T) {
 	}
 }
 
+func TestDefaultThinkingEffortForOpenAIAdapterUsesDisabledWhenUnset(t *testing.T) {
+	adapter := legacyruntime.ModelAdapterConfig{Type: "openai", ReasoningEffort: ""}
+
+	if got := defaultThinkingEffortForAdapter(adapter); got != "disabled" {
+		t.Fatalf("default thinking effort = %q, want disabled", got)
+	}
+}
+
+func TestBuildAvailableModelEntriesUsesDisabledVariantWhenReasoningEffortUnset(t *testing.T) {
+	entries := buildAvailableModelEntries([]legacyruntime.ModelAdapterConfig{{
+		ID:          "channel-a",
+		DisplayName: "Model A",
+		ModelID:     "model-a",
+		Type:        "openai",
+	}})
+	if len(entries) != 1 {
+		t.Fatalf("entry count = %d, want 1", len(entries))
+	}
+
+	variants, ok := entries[0]["variants"].([]map[string]any)
+	if !ok {
+		t.Fatalf("variants type = %T, want []map[string]any", entries[0]["variants"])
+	}
+	if len(variants) == 0 {
+		t.Fatal("variants should not be empty")
+	}
+	if got := variants[0]["variantStringRepresentation"]; got != "channel-a:disabled" {
+		t.Fatalf("first variant representation = %#v, want channel-a:disabled", got)
+	}
+	if got := variants[0]["isDefaultNonMaxConfig"]; got != true {
+		t.Fatalf("disabled variant default flag = %#v, want true", got)
+	}
+}
+
 func TestEncodeCLIModelsUsesAgentModelDetailsWireFormat(t *testing.T) {
 	payload := map[string]any{"models": buildCLIModelDetails([]legacyruntime.ModelAdapterConfig{{ID: "channel-a", DisplayName: "Model A", APIKey: "provider-secret", BaseURL: "https://provider.example/v1"}})}
 	encoded, err := encodeMockProto("aiserver.v1.GetUsableModelsResponse", payload)

internal/client/model_adapter_benchmark.go

@@ -950,6 +950,8 @@ func normalizeModelAdapterTestType(value string) string {
 
 func normalizeModelAdapterTestReasoning(value string) string {
 	switch strings.ToLower(strings.TrimSpace(value)) {
+	case "":
+		return ""
 	case "low", "medium", "high", "xhigh", "max":
 		return strings.ToLower(strings.TrimSpace(value))
 	default:

internal/client/model_adapter_benchmark_test.go

@@ -0,0 +1,15 @@
+package client
+
+import (
+	"testing"
+
+	serverconfig "cursor/internal/backend/server/config"
+)
+
+func TestNormalizeModelAdapterTestProviderReasoningPreservesBlank(t *testing.T) {
+	adapter := serverconfig.ModelAdapterConfig{Type: "openai", ReasoningEffort: ""}
+
+	if got := normalizeModelAdapterTestProviderReasoning(adapter); got != "" {
+		t.Fatalf("reasoning effort = %q, want blank", got)
+	}
+}

internal/runtime/local_runtime.go

@@ -141,8 +141,8 @@ func NormalizeModelAdapterConfigs(input []ModelAdapterConfig) ([]ModelAdapterCon
 			return nil, errors.New("模型适配器 tooltipData 不能为空")
 		case next.ModelID == "":
 			return nil, errors.New("模型适配器 modelID 不能为空")
-		case next.Type == "openai" && next.ReasoningEffort == "":
-			return nil, errors.New("模型适配器 reasoningEffort 仅支持 low、medium、high、xhigh、max")
+		case next.Type == "openai" && !isSupportedReasoningEffort(next.ReasoningEffort):
+			return nil, errors.New("模型适配器 reasoningEffort 仅支持空值、low、medium、high、xhigh、max")
 		case next.Type == "openai" && next.OpenAIEndpoint == "":
 			return nil, errors.New("模型适配器 openAIEndpoint 仅支持 /v1/responses 或 /v1/chat/completions")
 		case next.Type == "openai" && next.OpenAIExtraParamsEnabled:
@@ -224,13 +224,15 @@ func validateHeadersJSON(value string) error {
 }
 
 func normalizeReasoningEffort(value string) string {
-	switch strings.ToLower(strings.TrimSpace(value)) {
-	case "", "medium":
-		return "medium"
-	case "low", "high", "xhigh", "max":
-		return strings.ToLower(strings.TrimSpace(value))
+	return strings.ToLower(strings.TrimSpace(value))
+}
+
+func isSupportedReasoningEffort(value string) bool {
+	switch value {
+	case "", "low", "medium", "high", "xhigh", "max":
+		return true
 	default:
-		return ""
+		return false
 	}
 }
 

internal/runtime/local_runtime_test.go

@@ -0,0 +1,32 @@
+package runtime
+
+import "testing"
+
+func testRuntimeModelAdapter(reasoningEffort string) ModelAdapterConfig {
+	return ModelAdapterConfig{
+		DisplayName:     "non-reasoning-model",
+		Type:            "openai",
+		BaseURL:         "https://api.example.com/v1",
+		APIKey:          "test-key",
+		TooltipData:     "non-reasoning-model",
+		ModelID:         "non-reasoning-model",
+		ReasoningEffort: reasoningEffort,
+		OpenAIEndpoint:  "/v1/responses",
+	}
+}
+
+func TestNormalizeModelAdapterConfigsAllowsBlankReasoningEffort(t *testing.T) {
+	adapters, err := NormalizeModelAdapterConfigs([]ModelAdapterConfig{testRuntimeModelAdapter("")})
+	if err != nil {
+		t.Fatalf("NormalizeModelAdapterConfigs returned error: %v", err)
+	}
+	if got := adapters[0].ReasoningEffort; got != "" {
+		t.Fatalf("ReasoningEffort = %q, want blank", got)
+	}
+}
+
+func TestNormalizeModelAdapterConfigsRejectsUnknownReasoningEffort(t *testing.T) {
+	if _, err := NormalizeModelAdapterConfigs([]ModelAdapterConfig{testRuntimeModelAdapter("unsupported")}); err == nil {
+		t.Fatal("NormalizeModelAdapterConfigs should reject an unknown reasoning effort")
+	}
+}