Merge pull request #3991 from fengshao1227/fix/anthropic-usage-cache-creation-tokens

fix(apicompat): Responses↔Anthropic 转换补齐 cache_creation_input_tokens

backend/internal/pkg/apicompat/anthropic_to_responses_response.go

@@ -102,9 +102,10 @@ func AnthropicToResponsesResponse(resp *AnthropicResponse) *ResponsesResponse {
 		resp.Usage.CacheReadInputTokens +
 		resp.Usage.CacheCreationInputTokens
 	out.Usage = &ResponsesUsage{
-		InputTokens:  totalInputTokens,
-		OutputTokens: resp.Usage.OutputTokens,
-		TotalTokens:  totalInputTokens + resp.Usage.OutputTokens,
+		InputTokens:              totalInputTokens,
+		OutputTokens:             resp.Usage.OutputTokens,
+		TotalTokens:              totalInputTokens + resp.Usage.OutputTokens,
+		CacheCreationInputTokens: resp.Usage.CacheCreationInputTokens,
 	}
 	if resp.Usage.CacheReadInputTokens > 0 {
 		out.Usage.InputTokensDetails = &ResponsesInputTokensDetails{
@@ -497,9 +498,10 @@ func makeResponsesCompletedEvent(
 	// back to match OpenAI Responses semantics where input_tokens is the total.
 	totalInputTokens := state.InputTokens + state.CacheReadInputTokens + state.CacheCreationInputTokens
 	usage := &ResponsesUsage{
-		InputTokens:  totalInputTokens,
-		OutputTokens: state.OutputTokens,
-		TotalTokens:  totalInputTokens + state.OutputTokens,
+		InputTokens:              totalInputTokens,
+		OutputTokens:             state.OutputTokens,
+		TotalTokens:              totalInputTokens + state.OutputTokens,
+		CacheCreationInputTokens: state.CacheCreationInputTokens,
 	}
 	if state.CacheReadInputTokens > 0 {
 		usage.InputTokensDetails = &ResponsesInputTokensDetails{

backend/internal/pkg/apicompat/responses_anthropic_cache_creation_test.go

@@ -0,0 +1,99 @@
+package apicompat
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestAnthropicUsageFromResponsesUsage_CacheCreation(t *testing.T) {
+	usage := &ResponsesUsage{
+		InputTokens:              20,
+		OutputTokens:             5,
+		CacheCreationInputTokens: 6,
+		InputTokensDetails: &ResponsesInputTokensDetails{
+			CachedTokens: 4,
+		},
+	}
+
+	got := anthropicUsageFromResponsesUsage(usage)
+
+	assert.Equal(t, 10, got.InputTokens, "input = total(20) - cache_read(4) - cache_creation(6)")
+	assert.Equal(t, 5, got.OutputTokens)
+	assert.Equal(t, 4, got.CacheReadInputTokens)
+	assert.Equal(t, 6, got.CacheCreationInputTokens, "cache creation must be preserved")
+}
+
+func TestAnthropicUsageFromResponsesUsage_NoCacheCreation(t *testing.T) {
+	usage := &ResponsesUsage{
+		InputTokens:  10,
+		OutputTokens: 5,
+		InputTokensDetails: &ResponsesInputTokensDetails{
+			CachedTokens: 3,
+		},
+	}
+
+	got := anthropicUsageFromResponsesUsage(usage)
+
+	assert.Equal(t, 7, got.InputTokens)
+	assert.Equal(t, 3, got.CacheReadInputTokens)
+	assert.Equal(t, 0, got.CacheCreationInputTokens)
+}
+
+func TestResponsesEventToAnthropicEvents_StreamingCacheCreation(t *testing.T) {
+	state := NewResponsesEventToAnthropicState()
+	state.MessageStartSent = true
+
+	completedEvt := &ResponsesStreamEvent{
+		Type: "response.completed",
+		Response: &ResponsesResponse{
+			Status: "completed",
+			Usage: &ResponsesUsage{
+				InputTokens:              20,
+				OutputTokens:             5,
+				CacheCreationInputTokens: 6,
+				InputTokensDetails: &ResponsesInputTokensDetails{
+					CachedTokens: 4,
+				},
+			},
+		},
+	}
+
+	events := ResponsesEventToAnthropicEvents(completedEvt, state)
+
+	var deltaEvt *AnthropicStreamEvent
+	for i := range events {
+		if events[i].Type == "message_delta" {
+			deltaEvt = &events[i]
+			break
+		}
+	}
+	require.NotNil(t, deltaEvt, "should have message_delta event")
+	require.NotNil(t, deltaEvt.Usage)
+	assert.Equal(t, 6, deltaEvt.Usage.CacheCreationInputTokens, "streaming cache_creation must be preserved")
+	assert.Equal(t, 10, deltaEvt.Usage.InputTokens, "input = 20 - 4(read) - 6(creation)")
+	assert.Equal(t, 4, deltaEvt.Usage.CacheReadInputTokens)
+}
+
+func TestAnthropicToResponsesResponse_CacheCreation(t *testing.T) {
+	resp := AnthropicResponse{
+		ID:    "msg_test",
+		Type:  "message",
+		Role:  "assistant",
+		Model: "claude-opus-4-6",
+		Usage: AnthropicUsage{
+			InputTokens:              10,
+			OutputTokens:             5,
+			CacheReadInputTokens:     4,
+			CacheCreationInputTokens: 6,
+		},
+		StopReason: "end_turn",
+	}
+
+	out := AnthropicToResponsesResponse(&resp)
+
+	require.NotNil(t, out.Usage)
+	assert.Equal(t, 20, out.Usage.InputTokens, "total = input(10) + cache_read(4) + cache_creation(6)")
+	assert.Equal(t, 6, out.Usage.CacheCreationInputTokens, "cache creation must round-trip")
+}

backend/internal/pkg/apicompat/responses_to_anthropic.go

@@ -100,15 +100,16 @@ func anthropicUsageFromResponsesUsage(usage *ResponsesUsage) AnthropicUsage {
 		cachedTokens = usage.InputTokensDetails.CachedTokens
 	}
 
-	inputTokens := usage.InputTokens - cachedTokens
+	inputTokens := usage.InputTokens - cachedTokens - usage.CacheCreationInputTokens
 	if inputTokens < 0 {
 		inputTokens = 0
 	}
 
 	return AnthropicUsage{
-		InputTokens:          inputTokens,
-		OutputTokens:         usage.OutputTokens,
-		CacheReadInputTokens: cachedTokens,
+		InputTokens:              inputTokens,
+		OutputTokens:             usage.OutputTokens,
+		CacheReadInputTokens:     cachedTokens,
+		CacheCreationInputTokens: usage.CacheCreationInputTokens,
 	}
 }
 
@@ -181,9 +182,10 @@ type ResponsesEventToAnthropicState struct {
 	// OutputIndexToBlockIdx maps Responses output_index → Anthropic content block index.
 	OutputIndexToBlockIdx map[int]int
 
-	InputTokens          int
-	OutputTokens         int
-	CacheReadInputTokens int
+	InputTokens              int
+	OutputTokens             int
+	CacheReadInputTokens     int
+	CacheCreationInputTokens int
 
 	ResponseID string
 	Model      string
@@ -258,9 +260,10 @@ func FinalizeResponsesAnthropicStream(state *ResponsesEventToAnthropicState) []A
 				StopReason: stopReason,
 			},
 			Usage: &AnthropicUsage{
-				InputTokens:          state.InputTokens,
-				OutputTokens:         state.OutputTokens,
-				CacheReadInputTokens: state.CacheReadInputTokens,
+				InputTokens:              state.InputTokens,
+				OutputTokens:             state.OutputTokens,
+				CacheReadInputTokens:     state.CacheReadInputTokens,
+				CacheCreationInputTokens: state.CacheCreationInputTokens,
 			},
 		},
 		AnthropicStreamEvent{Type: "message_stop"},
@@ -578,6 +581,7 @@ func resToAnthHandleCompleted(evt *ResponsesStreamEvent, state *ResponsesEventTo
 		state.InputTokens = usage.InputTokens
 		state.OutputTokens = usage.OutputTokens
 		state.CacheReadInputTokens = usage.CacheReadInputTokens
+		state.CacheCreationInputTokens = usage.CacheCreationInputTokens
 	}
 	if evt.Response != nil {
 		if evt.Response.Usage != nil {
@@ -585,6 +589,7 @@ func resToAnthHandleCompleted(evt *ResponsesStreamEvent, state *ResponsesEventTo
 			state.InputTokens = usage.InputTokens
 			state.OutputTokens = usage.OutputTokens
 			state.CacheReadInputTokens = usage.CacheReadInputTokens
+			state.CacheCreationInputTokens = usage.CacheCreationInputTokens
 		}
 		switch evt.Response.Status {
 		case "incomplete":
@@ -605,9 +610,10 @@ func resToAnthHandleCompleted(evt *ResponsesStreamEvent, state *ResponsesEventTo
 				StopReason: stopReason,
 			},
 			Usage: &AnthropicUsage{
-				InputTokens:          state.InputTokens,
-				OutputTokens:         state.OutputTokens,
-				CacheReadInputTokens: state.CacheReadInputTokens,
+				InputTokens:              state.InputTokens,
+				OutputTokens:             state.OutputTokens,
+				CacheReadInputTokens:     state.CacheReadInputTokens,
+				CacheCreationInputTokens: state.CacheCreationInputTokens,
 			},
 		},
 		AnthropicStreamEvent{Type: "message_stop"},