feat: configurable tool pricing, Sub2API channel, and alpha search billing

Add admin-configurable tool-call prices with cross-provider surcharge settlement, Sub2API channel support, /v1/alpha/search relay, and usage-log surcharge UI.
2026-09-11 14:41:21 +00:00 · 2026-07-26 20:05:15 +08:00
parent 3e1e728279
commit 2d23cdf291
65 changed files with 3210 additions and 431 deletions
@@ -342,6 +342,7 @@ var streamSupportedChannels = map[int]bool{
 	constant.ChannelTypeMiniMax:        true,
 	constant.ChannelTypeSiliconFlow:    true,
 	constant.ChannelTypeAdvancedCustom: true,
+	constant.ChannelTypeSub2API:        true,
 	constant.ChannelTypeTencent:        true,
 }

@@ -576,6 +577,11 @@ func GenRelayInfo(c *gin.Context, relayFormat types.RelayFormat, request dto.Req
 			return GenRelayInfoResponsesCompaction(c, request), nil
 		}
 		return nil, errors.New("request is not a OpenAIResponsesCompactionRequest")
+	case types.RelayFormatOpenAIAlphaSearch:
+		if request, ok := request.(*dto.AlphaSearchRequest); ok {
+			return GenRelayInfoAlphaSearch(c, request), nil
+		}
+		return nil, errors.New("request is not a AlphaSearchRequest")
 	case types.RelayFormatTask:
 		info = genBaseRelayInfo(c, nil)
 		info.TaskRelayInfo = &TaskRelayInfo{}
@@ -650,6 +656,23 @@ func GenRelayInfoResponsesCompaction(c *gin.Context, request *dto.OpenAIResponse
 	return info
 }

+func GenRelayInfoAlphaSearch(c *gin.Context, request *dto.AlphaSearchRequest) *RelayInfo {
+	info := genBaseRelayInfo(c, request)
+	if info.RelayMode == relayconstant.RelayModeUnknown {
+		info.RelayMode = relayconstant.RelayModeAlphaSearch
+	}
+	info.RelayFormat = types.RelayFormatOpenAIAlphaSearch
+	info.ResponsesUsageInfo = &ResponsesUsageInfo{
+		BuiltInTools: map[string]*BuildInToolInfo{
+			dto.BuildInToolWebSearchPreview: {
+				ToolName:  dto.BuildInToolWebSearchPreview,
+				CallCount: 0,
+			},
+		},
+	}
+	return info
+}
+
 //func (info *RelayInfo) SetPromptTokens(promptTokens int) {
 //	info.promptTokens = promptTokens
 //}
@@ -0,0 +1,194 @@
+package common
+
+import (
+	"crypto/sha256"
+	"encoding/hex"
+	"fmt"
+	"strings"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/setting/operation_setting"
+)
+
+var reservedBillableToolNames = map[string]struct{}{
+	dto.BuildInToolWebSearchPreview: {},
+	dto.BuildInToolWebSearch:        {},
+	dto.BuildInToolFileSearch:       {},
+	dto.BuildInToolGoogleSearch:     {},
+	dto.BuildInToolImageGeneration:  {},
+}
+
+// CountBillableToolCall is the single entry point for per-call tool billing counts.
+// Built-in call types always count; custom function/tool_use names only count when priced.
+func (info *RelayInfo) CountBillableToolCall(itemType string, functionName string) {
+	if info == nil {
+		return
+	}
+	if info.ResponsesUsageInfo == nil {
+		info.ResponsesUsageInfo = &ResponsesUsageInfo{
+			BuiltInTools: make(map[string]*BuildInToolInfo),
+		}
+	}
+	if info.ResponsesUsageInfo.BuiltInTools == nil {
+		info.ResponsesUsageInfo.BuiltInTools = make(map[string]*BuildInToolInfo)
+	}
+
+	switch itemType {
+	case dto.BuildInCallWebSearchCall:
+		info.incrementBillableToolCall(resolveWebSearchToolName(info.ResponsesUsageInfo.BuiltInTools))
+	case dto.BuildInCallFileSearchCall:
+		info.incrementBillableToolCall(dto.BuildInToolFileSearch)
+	case dto.BuildInCallFunctionCall, dto.BuildInCallToolUse:
+		if functionName == "" {
+			return
+		}
+		if _, reserved := reservedBillableToolNames[functionName]; reserved {
+			return
+		}
+		if operation_setting.GetToolPriceForModel(functionName, info.OriginModelName) <= 0 {
+			return
+		}
+		info.incrementBillableToolCall(functionName)
+	}
+}
+
+func resolveWebSearchToolName(tools map[string]*BuildInToolInfo) string {
+	if _, ok := tools[dto.BuildInToolWebSearchPreview]; ok {
+		return dto.BuildInToolWebSearchPreview
+	}
+	if _, ok := tools[dto.BuildInToolWebSearch]; ok {
+		return dto.BuildInToolWebSearch
+	}
+	return dto.BuildInToolWebSearchPreview
+}
+
+func (info *RelayInfo) incrementBillableToolCall(name string) {
+	if existing, ok := info.ResponsesUsageInfo.BuiltInTools[name]; ok && existing != nil {
+		existing.CallCount++
+		return
+	}
+	info.ResponsesUsageInfo.BuiltInTools[name] = &BuildInToolInfo{
+		ToolName:  name,
+		CallCount: 1,
+	}
+}
+
+// ImageGenerationCallCounter counts completed Responses image_generation_call
+// outputs with stream-safe identity deduplication.
+type ImageGenerationCallCounter struct {
+	seen  map[string]struct{}
+	count int
+}
+
+// Observe records one completed final image output when billable.
+// outputIndex may be nil; when set and nonnegative it participates in dedup.
+func (c *ImageGenerationCallCounter) Observe(item *dto.ResponsesOutput, outputIndex *int) {
+	if c == nil || item == nil {
+		return
+	}
+	if item.Type != dto.ResponsesOutputTypeImageGenerationCall {
+		return
+	}
+	if strings.TrimSpace(item.Result) == "" {
+		return
+	}
+	switch strings.ToLower(strings.TrimSpace(item.Status)) {
+	case "failed", "cancelled", "canceled", "incomplete", "partial":
+		return
+	}
+
+	aliases := make([]string, 0, 4)
+	if item.ID != "" {
+		aliases = append(aliases, "id:"+item.ID)
+	}
+	if item.CallId != "" {
+		aliases = append(aliases, "call:"+item.CallId)
+	}
+	if outputIndex != nil && *outputIndex >= 0 {
+		aliases = append(aliases, fmt.Sprintf("index:%d", *outputIndex))
+	}
+	sum := sha256.Sum256([]byte(item.Result))
+	aliases = append(aliases, "result:"+hex.EncodeToString(sum[:]))
+
+	if c.seen == nil {
+		c.seen = make(map[string]struct{})
+	}
+	for _, alias := range aliases {
+		if _, ok := c.seen[alias]; ok {
+			return
+		}
+	}
+	for _, alias := range aliases {
+		c.seen[alias] = struct{}{}
+	}
+	c.count++
+}
+
+// Reset clears pending observations (used when a terminal response fails).
+func (c *ImageGenerationCallCounter) Reset() {
+	if c == nil {
+		return
+	}
+	c.seen = nil
+	c.count = 0
+}
+
+// Count returns the deduplicated completed image output count before commit capping.
+func (c *ImageGenerationCallCounter) Count() int {
+	if c == nil {
+		return 0
+	}
+	return c.count
+}
+
+// Commit writes the capped completed-output count into RelayInfo once.
+// Request tool declarations alone must not become billable calls.
+func (c *ImageGenerationCallCounter) Commit(info *RelayInfo) {
+	if info == nil {
+		return
+	}
+	if info.ResponsesUsageInfo == nil {
+		info.ResponsesUsageInfo = &ResponsesUsageInfo{
+			BuiltInTools: make(map[string]*BuildInToolInfo),
+		}
+	}
+	if info.ResponsesUsageInfo.BuiltInTools == nil {
+		info.ResponsesUsageInfo.BuiltInTools = make(map[string]*BuildInToolInfo)
+	}
+
+	count := 0
+	if c != nil {
+		count = c.count
+	}
+	if count > dto.MaxImageN {
+		count = dto.MaxImageN
+	}
+
+	if existing, ok := info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolImageGeneration]; ok && existing != nil {
+		existing.CallCount = count
+		return
+	}
+	info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolImageGeneration] = &BuildInToolInfo{
+		ToolName:  dto.BuildInToolImageGeneration,
+		CallCount: count,
+	}
+}
+
+// IsNonBillableResponsesStatus reports terminal response statuses that must not
+// bill pending image_generation observations.
+func IsNonBillableResponsesStatus(status []byte) bool {
+	if len(status) == 0 {
+		return false
+	}
+	var s string
+	if err := common.Unmarshal(status, &s); err != nil {
+		return false
+	}
+	switch strings.ToLower(strings.TrimSpace(s)) {
+	case "failed", "cancelled", "canceled", "incomplete":
+		return true
+	default:
+		return false
+	}
+}
@@ -0,0 +1,348 @@
+package common
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/setting/operation_setting"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestCountBillableToolCallWebSearchPrefersDeclaredWebSearch(t *testing.T) {
+	info := &RelayInfo{
+		OriginModelName: "gpt-5.1",
+		ResponsesUsageInfo: &ResponsesUsageInfo{
+			BuiltInTools: map[string]*BuildInToolInfo{
+				dto.BuildInToolWebSearch: {ToolName: dto.BuildInToolWebSearch, CallCount: 0},
+			},
+		},
+	}
+
+	info.CountBillableToolCall(dto.BuildInCallWebSearchCall, "")
+	require.Contains(t, info.ResponsesUsageInfo.BuiltInTools, dto.BuildInToolWebSearch)
+	assert.Equal(t, 1, info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolWebSearch].CallCount)
+	assert.NotContains(t, info.ResponsesUsageInfo.BuiltInTools, dto.BuildInToolWebSearchPreview)
+}
+
+func TestCountBillableToolCallWebSearchDefaultsToPreview(t *testing.T) {
+	info := &RelayInfo{OriginModelName: "gpt-5.1"}
+
+	info.CountBillableToolCall(dto.BuildInCallWebSearchCall, "")
+	require.NotNil(t, info.ResponsesUsageInfo)
+	require.Contains(t, info.ResponsesUsageInfo.BuiltInTools, dto.BuildInToolWebSearchPreview)
+	assert.Equal(t, 1, info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolWebSearchPreview].CallCount)
+}
+
+func TestCountBillableToolCallFunctionCallRequiresPrice(t *testing.T) {
+	operation_setting.SetToolPriceForTest("my_priced_fn", 5.0)
+	t.Cleanup(func() {
+		operation_setting.DeleteToolPriceForTest("my_priced_fn")
+	})
+
+	info := &RelayInfo{OriginModelName: "gpt-5.1"}
+	info.CountBillableToolCall(dto.BuildInCallFunctionCall, "my_priced_fn")
+	require.Contains(t, info.ResponsesUsageInfo.BuiltInTools, "my_priced_fn")
+	assert.Equal(t, 1, info.ResponsesUsageInfo.BuiltInTools["my_priced_fn"].CallCount)
+
+	info.CountBillableToolCall(dto.BuildInCallFunctionCall, "unpriced_fn")
+	assert.NotContains(t, info.ResponsesUsageInfo.BuiltInTools, "unpriced_fn")
+}
+
+func TestCountBillableToolCallFunctionCallSkipsReservedNames(t *testing.T) {
+	info := &RelayInfo{OriginModelName: "gpt-5.1"}
+
+	info.CountBillableToolCall(dto.BuildInCallFunctionCall, dto.BuildInToolWebSearchPreview)
+	info.CountBillableToolCall(dto.BuildInCallFunctionCall, dto.BuildInToolFileSearch)
+	info.CountBillableToolCall(dto.BuildInCallFunctionCall, dto.BuildInToolGoogleSearch)
+	info.CountBillableToolCall(dto.BuildInCallFunctionCall, dto.BuildInToolImageGeneration)
+
+	if info.ResponsesUsageInfo != nil {
+		assert.NotContains(t, info.ResponsesUsageInfo.BuiltInTools, dto.BuildInToolWebSearchPreview)
+		assert.NotContains(t, info.ResponsesUsageInfo.BuiltInTools, dto.BuildInToolFileSearch)
+		assert.NotContains(t, info.ResponsesUsageInfo.BuiltInTools, dto.BuildInToolGoogleSearch)
+		assert.NotContains(t, info.ResponsesUsageInfo.BuiltInTools, dto.BuildInToolImageGeneration)
+	}
+}
+
+func TestImageGenerationCallCounterCompletedOutputs(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name      string
+		observe   func(c *ImageGenerationCallCounter)
+		wantCount int
+	}{
+		{
+			name: "one final result",
+			observe: func(c *ImageGenerationCallCounter) {
+				idx := 0
+				c.Observe(&dto.ResponsesOutput{
+					Type:   dto.ResponsesOutputTypeImageGenerationCall,
+					ID:     "img_1",
+					Status: "completed",
+					Result: "base64-a",
+				}, &idx)
+			},
+			wantCount: 1,
+		},
+		{
+			name: "two distinct finals",
+			observe: func(c *ImageGenerationCallCounter) {
+				idx0, idx1 := 0, 1
+				c.Observe(&dto.ResponsesOutput{
+					Type:   dto.ResponsesOutputTypeImageGenerationCall,
+					ID:     "img_1",
+					Result: "base64-a",
+				}, &idx0)
+				c.Observe(&dto.ResponsesOutput{
+					Type:   dto.ResponsesOutputTypeImageGenerationCall,
+					ID:     "img_2",
+					Result: "base64-b",
+				}, &idx1)
+			},
+			wantCount: 2,
+		},
+		{
+			name: "empty result",
+			observe: func(c *ImageGenerationCallCounter) {
+				idx := 0
+				c.Observe(&dto.ResponsesOutput{
+					Type:   dto.ResponsesOutputTypeImageGenerationCall,
+					ID:     "img_1",
+					Result: "   ",
+				}, &idx)
+			},
+			wantCount: 0,
+		},
+		{
+			name: "failed status",
+			observe: func(c *ImageGenerationCallCounter) {
+				idx := 0
+				c.Observe(&dto.ResponsesOutput{
+					Type:   dto.ResponsesOutputTypeImageGenerationCall,
+					ID:     "img_1",
+					Status: "failed",
+					Result: "base64-a",
+				}, &idx)
+			},
+			wantCount: 0,
+		},
+		{
+			name: "incomplete status",
+			observe: func(c *ImageGenerationCallCounter) {
+				idx := 0
+				c.Observe(&dto.ResponsesOutput{
+					Type:   dto.ResponsesOutputTypeImageGenerationCall,
+					ID:     "img_1",
+					Status: "incomplete",
+					Result: "base64-a",
+				}, &idx)
+			},
+			wantCount: 0,
+		},
+		{
+			name: "cancelled status",
+			observe: func(c *ImageGenerationCallCounter) {
+				idx := 0
+				c.Observe(&dto.ResponsesOutput{
+					Type:   dto.ResponsesOutputTypeImageGenerationCall,
+					ID:     "img_1",
+					Status: "cancelled",
+					Result: "base64-a",
+				}, &idx)
+			},
+			wantCount: 0,
+		},
+		{
+			name: "canceled status",
+			observe: func(c *ImageGenerationCallCounter) {
+				idx := 0
+				c.Observe(&dto.ResponsesOutput{
+					Type:   dto.ResponsesOutputTypeImageGenerationCall,
+					ID:     "img_1",
+					Status: "canceled",
+					Result: "base64-a",
+				}, &idx)
+			},
+			wantCount: 0,
+		},
+		{
+			name: "partial status",
+			observe: func(c *ImageGenerationCallCounter) {
+				idx := 0
+				c.Observe(&dto.ResponsesOutput{
+					Type:   dto.ResponsesOutputTypeImageGenerationCall,
+					ID:     "img_1",
+					Status: "partial",
+					Result: "partial-bytes",
+				}, &idx)
+			},
+			wantCount: 0,
+		},
+		{
+			name: "id dedup",
+			observe: func(c *ImageGenerationCallCounter) {
+				idx0, idx1 := 0, 1
+				c.Observe(&dto.ResponsesOutput{
+					Type:   dto.ResponsesOutputTypeImageGenerationCall,
+					ID:     "img_1",
+					CallId: "call_a",
+					Result: "base64-a",
+				}, &idx0)
+				c.Observe(&dto.ResponsesOutput{
+					Type:   dto.ResponsesOutputTypeImageGenerationCall,
+					ID:     "img_1",
+					CallId: "call_b",
+					Result: "base64-b",
+				}, &idx1)
+			},
+			wantCount: 1,
+		},
+		{
+			name: "index dedup",
+			observe: func(c *ImageGenerationCallCounter) {
+				idx := 0
+				c.Observe(&dto.ResponsesOutput{
+					Type:   dto.ResponsesOutputTypeImageGenerationCall,
+					ID:     "img_1",
+					Result: "base64-a",
+				}, &idx)
+				c.Observe(&dto.ResponsesOutput{
+					Type:   dto.ResponsesOutputTypeImageGenerationCall,
+					ID:     "img_2",
+					Result: "base64-b",
+				}, &idx)
+			},
+			wantCount: 1,
+		},
+		{
+			name: "result hash dedup",
+			observe: func(c *ImageGenerationCallCounter) {
+				idx0, idx1 := 0, 1
+				c.Observe(&dto.ResponsesOutput{
+					Type:   dto.ResponsesOutputTypeImageGenerationCall,
+					Result: "same-bytes",
+				}, &idx0)
+				c.Observe(&dto.ResponsesOutput{
+					Type:   dto.ResponsesOutputTypeImageGenerationCall,
+					Result: "same-bytes",
+				}, &idx1)
+			},
+			wantCount: 1,
+		},
+		{
+			name: "output_item.done plus completed dedup",
+			observe: func(c *ImageGenerationCallCounter) {
+				idx := 0
+				item := &dto.ResponsesOutput{
+					Type:   dto.ResponsesOutputTypeImageGenerationCall,
+					ID:     "img_1",
+					CallId: "call_1",
+					Status: "completed",
+					Result: "base64-a",
+				}
+				c.Observe(item, &idx)
+				c.Observe(item, &idx)
+			},
+			wantCount: 1,
+		},
+		{
+			name: "output_item.done plus incomplete equals zero",
+			observe: func(c *ImageGenerationCallCounter) {
+				idx := 0
+				c.Observe(&dto.ResponsesOutput{
+					Type:   dto.ResponsesOutputTypeImageGenerationCall,
+					ID:     "img_1",
+					Status: "completed",
+					Result: "base64-a",
+				}, &idx)
+				c.Reset()
+			},
+			wantCount: 0,
+		},
+		{
+			name: "partial event equals zero",
+			observe: func(c *ImageGenerationCallCounter) {
+				idx := 0
+				c.Observe(&dto.ResponsesOutput{
+					Type:   "image_generation_call.partial_image",
+					ID:     "img_1",
+					Result: "partial-bytes",
+				}, &idx)
+			},
+			wantCount: 0,
+		},
+		{
+			name: "in_progress with final result counts",
+			observe: func(c *ImageGenerationCallCounter) {
+				idx := 0
+				c.Observe(&dto.ResponsesOutput{
+					Type:   dto.ResponsesOutputTypeImageGenerationCall,
+					ID:     "img_1",
+					Status: "in_progress",
+					Result: "base64-a",
+				}, &idx)
+			},
+			wantCount: 1,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+			counter := &ImageGenerationCallCounter{}
+			tt.observe(counter)
+			assert.Equal(t, tt.wantCount, counter.Count())
+		})
+	}
+}
+
+func TestImageGenerationCallCounterCommitCapsAtMaxImageN(t *testing.T) {
+	t.Parallel()
+
+	counter := &ImageGenerationCallCounter{}
+	for i := 0; i < dto.MaxImageN+3; i++ {
+		idx := i
+		counter.Observe(&dto.ResponsesOutput{
+			Type:   dto.ResponsesOutputTypeImageGenerationCall,
+			ID:     "img_" + strings.Repeat("a", i+1),
+			Result: "result-" + strings.Repeat("b", i+1),
+		}, &idx)
+	}
+	require.Equal(t, dto.MaxImageN+3, counter.Count())
+
+	info := &RelayInfo{}
+	counter.Commit(info)
+	require.Contains(t, info.ResponsesUsageInfo.BuiltInTools, dto.BuildInToolImageGeneration)
+	assert.Equal(t, dto.MaxImageN, info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolImageGeneration].CallCount)
+}
+
+func TestImageGenerationCallCounterCommitDoesNotBillDeclarationsAlone(t *testing.T) {
+	t.Parallel()
+
+	info := &RelayInfo{
+		ResponsesUsageInfo: &ResponsesUsageInfo{
+			BuiltInTools: map[string]*BuildInToolInfo{
+				dto.BuildInToolImageGeneration: {
+					ToolName:  dto.BuildInToolImageGeneration,
+					CallCount: 0,
+				},
+			},
+		},
+	}
+	(&ImageGenerationCallCounter{}).Commit(info)
+	assert.Equal(t, 0, info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolImageGeneration].CallCount)
+}
+
+func TestIsNonBillableResponsesStatus(t *testing.T) {
+	t.Parallel()
+
+	assert.True(t, IsNonBillableResponsesStatus([]byte(`"failed"`)))
+	assert.True(t, IsNonBillableResponsesStatus([]byte(`"incomplete"`)))
+	assert.True(t, IsNonBillableResponsesStatus([]byte(`"cancelled"`)))
+	assert.True(t, IsNonBillableResponsesStatus([]byte(`"canceled"`)))
+	assert.False(t, IsNonBillableResponsesStatus([]byte(`"completed"`)))
+	assert.False(t, IsNonBillableResponsesStatus(nil))
+}