new-api/relay/channel/claude/relay_claude_test.go

package claude

import (
	"io"
	"net/http"
	"net/http/httptest"
	"strings"
	"testing"

	"github.com/QuantumNous/new-api/constant"
	"github.com/QuantumNous/new-api/dto"
	relaycommon "github.com/QuantumNous/new-api/relay/common"
	"github.com/QuantumNous/new-api/types"
	"github.com/gin-gonic/gin"
	"github.com/stretchr/testify/require"
)

func TestFormatClaudeResponseInfo_MessageStart(t *testing.T) {
	claudeInfo := &ClaudeResponseInfo{
		Usage: &dto.Usage{},
	}
	claudeResponse := &dto.ClaudeResponse{
		Type: "message_start",
		Message: &dto.ClaudeMediaMessage{
			Id:    "msg_123",
			Model: "claude-3-5-sonnet",
			Usage: &dto.ClaudeUsage{
				InputTokens:              100,
				OutputTokens:             1,
				CacheCreationInputTokens: 50,
				CacheReadInputTokens:     30,
			},
		},
	}

	ok := FormatClaudeResponseInfo(claudeResponse, nil, claudeInfo)
	if !ok {
		t.Fatal("expected true")
	}
	if claudeInfo.Usage.PromptTokens != 100 {
		t.Errorf("PromptTokens = %d, want 100", claudeInfo.Usage.PromptTokens)
	}
	if claudeInfo.Usage.PromptTokensDetails.CachedTokens != 30 {
		t.Errorf("CachedTokens = %d, want 30", claudeInfo.Usage.PromptTokensDetails.CachedTokens)
	}
	if claudeInfo.Usage.PromptTokensDetails.CachedCreationTokens != 50 {
		t.Errorf("CachedCreationTokens = %d, want 50", claudeInfo.Usage.PromptTokensDetails.CachedCreationTokens)
	}
	if claudeInfo.ResponseId != "msg_123" {
		t.Errorf("ResponseId = %s, want msg_123", claudeInfo.ResponseId)
	}
	if claudeInfo.Model != "claude-3-5-sonnet" {
		t.Errorf("Model = %s, want claude-3-5-sonnet", claudeInfo.Model)
	}
}

func TestFormatClaudeResponseInfo_MessageDelta_FullUsage(t *testing.T) {
	// message_start 先积累 usage
	claudeInfo := &ClaudeResponseInfo{
		Usage: &dto.Usage{
			PromptTokens: 100,
			PromptTokensDetails: dto.InputTokenDetails{
				CachedTokens:         30,
				CachedCreationTokens: 50,
			},
			CompletionTokens: 1,
		},
	}

	// message_delta 带完整 usage（原生 Anthropic 场景）
	claudeResponse := &dto.ClaudeResponse{
		Type: "message_delta",
		Usage: &dto.ClaudeUsage{
			InputTokens:              100,
			OutputTokens:             200,
			CacheCreationInputTokens: 50,
			CacheReadInputTokens:     30,
		},
	}

	ok := FormatClaudeResponseInfo(claudeResponse, nil, claudeInfo)
	if !ok {
		t.Fatal("expected true")
	}
	if claudeInfo.Usage.PromptTokens != 100 {
		t.Errorf("PromptTokens = %d, want 100", claudeInfo.Usage.PromptTokens)
	}
	if claudeInfo.Usage.CompletionTokens != 200 {
		t.Errorf("CompletionTokens = %d, want 200", claudeInfo.Usage.CompletionTokens)
	}
	if claudeInfo.Usage.TotalTokens != 300 {
		t.Errorf("TotalTokens = %d, want 300", claudeInfo.Usage.TotalTokens)
	}
	if !claudeInfo.Done {
		t.Error("expected Done = true")
	}
}

func TestFormatClaudeResponseInfo_MessageDelta_OnlyOutputTokens(t *testing.T) {
	// 模拟 Bedrock: message_start 已积累 usage
	claudeInfo := &ClaudeResponseInfo{
		Usage: &dto.Usage{
			PromptTokens: 100,
			PromptTokensDetails: dto.InputTokenDetails{
				CachedTokens:         30,
				CachedCreationTokens: 50,
			},
			CompletionTokens:            1,
			ClaudeCacheCreation5mTokens: 10,
			ClaudeCacheCreation1hTokens: 20,
		},
	}

	// Bedrock 的 message_delta 只有 output_tokens，缺少 input_tokens 和 cache 字段
	claudeResponse := &dto.ClaudeResponse{
		Type: "message_delta",
		Usage: &dto.ClaudeUsage{
			OutputTokens: 200,
			// InputTokens, CacheCreationInputTokens, CacheReadInputTokens 都是 0
		},
	}

	ok := FormatClaudeResponseInfo(claudeResponse, nil, claudeInfo)
	if !ok {
		t.Fatal("expected true")
	}
	// PromptTokens 应保持 message_start 的值（因为 message_delta 的 InputTokens=0，不更新）
	if claudeInfo.Usage.PromptTokens != 100 {
		t.Errorf("PromptTokens = %d, want 100", claudeInfo.Usage.PromptTokens)
	}
	if claudeInfo.Usage.CompletionTokens != 200 {
		t.Errorf("CompletionTokens = %d, want 200", claudeInfo.Usage.CompletionTokens)
	}
	if claudeInfo.Usage.TotalTokens != 300 {
		t.Errorf("TotalTokens = %d, want 300", claudeInfo.Usage.TotalTokens)
	}
	// cache 字段应保持 message_start 的值
	if claudeInfo.Usage.PromptTokensDetails.CachedTokens != 30 {
		t.Errorf("CachedTokens = %d, want 30", claudeInfo.Usage.PromptTokensDetails.CachedTokens)
	}
	if claudeInfo.Usage.PromptTokensDetails.CachedCreationTokens != 50 {
		t.Errorf("CachedCreationTokens = %d, want 50", claudeInfo.Usage.PromptTokensDetails.CachedCreationTokens)
	}
	if claudeInfo.Usage.ClaudeCacheCreation5mTokens != 10 {
		t.Errorf("ClaudeCacheCreation5mTokens = %d, want 10", claudeInfo.Usage.ClaudeCacheCreation5mTokens)
	}
	if claudeInfo.Usage.ClaudeCacheCreation1hTokens != 20 {
		t.Errorf("ClaudeCacheCreation1hTokens = %d, want 20", claudeInfo.Usage.ClaudeCacheCreation1hTokens)
	}
	if !claudeInfo.Done {
		t.Error("expected Done = true")
	}
}

func TestFormatClaudeResponseInfo_NilClaudeInfo(t *testing.T) {
	claudeResponse := &dto.ClaudeResponse{Type: "message_start"}
	ok := FormatClaudeResponseInfo(claudeResponse, nil, nil)
	if ok {
		t.Error("expected false for nil claudeInfo")
	}
}

func TestFormatClaudeResponseInfo_ContentBlockDelta(t *testing.T) {
	text := "hello"
	claudeInfo := &ClaudeResponseInfo{
		Usage:        &dto.Usage{},
		ResponseText: strings.Builder{},
	}
	claudeResponse := &dto.ClaudeResponse{
		Type: "content_block_delta",
		Delta: &dto.ClaudeMediaMessage{
			Text: &text,
		},
	}

	ok := FormatClaudeResponseInfo(claudeResponse, nil, claudeInfo)
	if !ok {
		t.Fatal("expected true")
	}
	if claudeInfo.ResponseText.String() != "hello" {
		t.Errorf("ResponseText = %q, want %q", claudeInfo.ResponseText.String(), "hello")
	}
}

func TestClaudeStreamHandlerReturnsErrorOnInitialErrorEvent(t *testing.T) {
	gin.SetMode(gin.TestMode)
	oldTimeout := constant.StreamingTimeout
	constant.StreamingTimeout = 30
	t.Cleanup(func() {
		constant.StreamingTimeout = oldTimeout
	})

	w := httptest.NewRecorder()
	c, _ := gin.CreateTestContext(w)
	c.Request = httptest.NewRequest(http.MethodPost, "/v1/messages", nil)

	errorEvent := `{"type":"error","error":{"type":"overloaded_error","message":"Overloaded"}}`
	resp := &http.Response{
		StatusCode: http.StatusOK,
		Body:       io.NopCloser(strings.NewReader("data: " + errorEvent + "\n\n")),
	}
	info := &relaycommon.RelayInfo{
		RelayFormat: types.RelayFormatClaude,
		ChannelMeta: &relaycommon.ChannelMeta{
			UpstreamModelName: "claude-test",
		},
	}

	usage, err := ClaudeStreamHandler(c, resp, info)
	require.Nil(t, usage)
	require.Error(t, err)
	require.Empty(t, w.Body.String())
}

func TestClaudeStreamHandlerDoesNotRetryAfterNormalStreamData(t *testing.T) {
	gin.SetMode(gin.TestMode)
	oldTimeout := constant.StreamingTimeout
	constant.StreamingTimeout = 30
	t.Cleanup(func() {
		constant.StreamingTimeout = oldTimeout
	})

	w := httptest.NewRecorder()
	c, _ := gin.CreateTestContext(w)
	c.Request = httptest.NewRequest(http.MethodPost, "/v1/messages", nil)

	normalEvent := `{"type":"message_start","message":{"id":"msg_test","model":"claude-test","usage":{"input_tokens":1,"output_tokens":1}}}`
	errorEvent := `{"type":"error","error":{"type":"overloaded_error","message":"Overloaded"}}`
	resp := &http.Response{
		StatusCode: http.StatusOK,
		Body:       io.NopCloser(strings.NewReader("data: " + normalEvent + "\n\ndata: " + errorEvent + "\n\n")),
	}
	info := &relaycommon.RelayInfo{
		RelayFormat: types.RelayFormatClaude,
		ChannelMeta: &relaycommon.ChannelMeta{
			UpstreamModelName: "claude-test",
		},
	}

	usage, err := ClaudeStreamHandler(c, resp, info)
	require.Nil(t, err)
	require.NotNil(t, usage)
	require.Contains(t, w.Body.String(), "message_start")
	require.NotContains(t, w.Body.String(), "overloaded_error")
}