* test(relayconvert): add golden snapshot matrix and relaykit boundary guard Phase 0 of the relaykit extraction plan: pin byte-level output of every registered (from,to) request/response/stream conversion route, and forbid kit-bound packages from growing host-only imports. * wip(relayconvert): drop gin.Context from converter signatures; add convmeta draft Phase 1 in progress: relayconvert now takes context.Context; host media resolver adapts gin.Context back at the service boundary. * refactor(relayconvert): decouple converters from RelayInfo, gin, and settings Phase 1 of the relaykit extraction plan: - converters now depend on convmeta.Meta (implemented by RelayInfo) instead of *relaycommon.RelayInfo; ClaudeConvertInfo and the format guesser move to convmeta with aliases left behind - host settings reach converters via a convmeta.Options snapshot built in RelayInfo.ConvOptions; no more model_setting/reasoning global reads inside the conversion layer - effort-suffix helpers move to service/relayconvert/reasoning (old package forwards); chat-to-responses upgrade policy moves to service (host routing logic, not conversion) - golden conversion matrix unchanged * test(relayconvert): tighten boundary — kit packages now free of gin/setting imports * refactor(dto): drop gin and logger dependencies Phase 2 (part 1): dto.Request.IsStream now takes *http.Request instead of *gin.Context (Gemini's impl reads query/path off the std request); dto's three logger calls become common.SysError. Boundary test allowlist is now empty — kit-bound packages import no gin/setting/logger/model. * refactor(kit): extract dependency-free kitutil; dto/types/relayconvert stop importing common Phase 2 of the relaykit extraction plan: - new service/relayconvert/kitutil holds the pure helpers the kit needs (JSON wrappers, pointer/string/uuid/timestamp utils, MaskSensitiveInfo, pluggable LogInfo/LogError hooks, Debug flag) - dto, types, and all relayconvert packages now use kitutil; their only remaining internal deps are dto/types/constant - common keeps every original symbol (MaskSensitiveInfo delegates to kitutil) so host code is untouched; main.go routes kit logging into common.SysLog/SysError and mirrors DebugEnabled - golden conversion matrix unchanged * refactor(kit): move EndpointType/FinishReason to types; OpenRouter dialect via Options Kit packages (dto/types/relayconvert/reasonmap) no longer import constant: - EndpointType and finish-reason values live in types; constant re-exports - the OpenRouter special-case in claude->openai request conversion reads Options.OpenRouterDialect, set by the host from the channel type; InitChannelMeta invalidates the cached snapshot on channel switch * refactor: extract relaykit submodule (dto/types/relayconvert/reasonmap) Phase 3 of the relaykit extraction plan: - new go module github.com/QuantumNous/new-api/relaykit containing dto (minus task family), types, relayconvert (with convmeta/kitutil/reasoning), and reasonmap; host consumes it via require + replace, go.work for dev - task-family dto (task/suno/midjourney/video) stays in the host dto package; dual-consumer host files alias it as taskdto - relaykit builds and tests standalone (GOWORK=off): no host imports, no gin, no DB, no settings - golden conversion matrix unchanged * build(docker): copy relaykit/go.mod before go mod download The local-replace submodule's go.mod must exist inside the build context for the main module graph to resolve. * fix: address relaykit extraction regressions * fix: address relaykit review regressions * docs: document Meta nil receiver contract * fix(relaykit): fail OpenAI→Claude conversion without max_tokens; reject negative default_max_tokens The Claude Messages API requires max_tokens (omitting it is a 400 "Field required"), but with a nil Options.Claude.DefaultMaxTokens hook the converters silently emitted a request the upstream is guaranteed to reject. Both OpenAI Chat and Responses → Claude conversions now return sharedclaude.ErrMissingMaxTokens when no path (client value, default hook, thinking-adapter floor) supplied one. Unreachable in the host, which always configures the hook. Host side, claude.default_max_tokens now rejects negative values at the option API before persisting — they would wrap into huge unsigned values during conversion. Zero stays allowed: the current API treats max_tokens: 0 as cache pre-warming. * fix: make Gemini safety settings read path race-free
268 lines
9.0 KiB
Go
268 lines
9.0 KiB
Go
package openai
|
|
|
|
import (
|
|
"bytes"
|
|
"io"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"strings"
|
|
"testing"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/constant"
|
|
relaycommon "github.com/QuantumNous/new-api/relay/common"
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
"github.com/QuantumNous/new-api/setting/operation_setting"
|
|
"github.com/gin-gonic/gin"
|
|
"github.com/stretchr/testify/assert"
|
|
"github.com/stretchr/testify/require"
|
|
)
|
|
|
|
func TestOaiResponsesHandlerCountsOutputCallsNotDeclarations(t *testing.T) {
|
|
gin.SetMode(gin.TestMode)
|
|
operation_setting.SetToolPriceForTest("priced_fn", 5.0)
|
|
t.Cleanup(func() {
|
|
operation_setting.DeleteToolPriceForTest("priced_fn")
|
|
})
|
|
|
|
body, err := common.Marshal(dto.OpenAIResponsesResponse{
|
|
Tools: []map[string]any{
|
|
{"type": "web_search_preview"},
|
|
{"type": "file_search"},
|
|
},
|
|
Output: []dto.ResponsesOutput{
|
|
{Type: dto.BuildInCallWebSearchCall},
|
|
{Type: dto.BuildInCallWebSearchCall},
|
|
{Type: dto.BuildInCallFunctionCall, Name: "priced_fn"},
|
|
{Type: dto.BuildInCallFunctionCall, Name: "unpriced_fn"},
|
|
},
|
|
Usage: &dto.Usage{InputTokens: 1, OutputTokens: 1, TotalTokens: 2},
|
|
})
|
|
require.NoError(t, err)
|
|
|
|
w := httptest.NewRecorder()
|
|
c, _ := gin.CreateTestContext(w)
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1/responses", nil)
|
|
|
|
info := &relaycommon.RelayInfo{
|
|
OriginModelName: "gpt-5.1",
|
|
ResponsesUsageInfo: &relaycommon.ResponsesUsageInfo{
|
|
BuiltInTools: map[string]*relaycommon.BuildInToolInfo{
|
|
dto.BuildInToolWebSearchPreview: {ToolName: dto.BuildInToolWebSearchPreview, CallCount: 0},
|
|
dto.BuildInToolFileSearch: {ToolName: dto.BuildInToolFileSearch, CallCount: 0},
|
|
},
|
|
},
|
|
}
|
|
resp := &http.Response{
|
|
StatusCode: http.StatusOK,
|
|
Body: io.NopCloser(bytes.NewReader(body)),
|
|
Header: http.Header{"Content-Type": []string{"application/json"}},
|
|
}
|
|
|
|
usage, apiErr := OaiResponsesHandler(c, info, resp)
|
|
require.Nil(t, apiErr)
|
|
require.NotNil(t, usage)
|
|
assert.Equal(t, 2, info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolWebSearchPreview].CallCount)
|
|
assert.Equal(t, 0, info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolFileSearch].CallCount)
|
|
require.Contains(t, info.ResponsesUsageInfo.BuiltInTools, "priced_fn")
|
|
assert.Equal(t, 1, info.ResponsesUsageInfo.BuiltInTools["priced_fn"].CallCount)
|
|
assert.NotContains(t, info.ResponsesUsageInfo.BuiltInTools, "unpriced_fn")
|
|
}
|
|
|
|
func TestOaiResponsesHandlerDeclaredToolsWithoutOutputCountZero(t *testing.T) {
|
|
gin.SetMode(gin.TestMode)
|
|
|
|
body, err := common.Marshal(dto.OpenAIResponsesResponse{
|
|
Tools: []map[string]any{
|
|
{"type": "web_search_preview"},
|
|
{"type": "file_search"},
|
|
},
|
|
Output: []dto.ResponsesOutput{
|
|
{Type: "message", Role: "assistant"},
|
|
},
|
|
Usage: &dto.Usage{InputTokens: 1, OutputTokens: 1, TotalTokens: 2},
|
|
})
|
|
require.NoError(t, err)
|
|
|
|
w := httptest.NewRecorder()
|
|
c, _ := gin.CreateTestContext(w)
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1/responses", nil)
|
|
|
|
info := &relaycommon.RelayInfo{
|
|
OriginModelName: "gpt-5.1",
|
|
ResponsesUsageInfo: &relaycommon.ResponsesUsageInfo{
|
|
BuiltInTools: map[string]*relaycommon.BuildInToolInfo{
|
|
dto.BuildInToolWebSearchPreview: {ToolName: dto.BuildInToolWebSearchPreview, CallCount: 0},
|
|
dto.BuildInToolFileSearch: {ToolName: dto.BuildInToolFileSearch, CallCount: 0},
|
|
},
|
|
},
|
|
}
|
|
resp := &http.Response{
|
|
StatusCode: http.StatusOK,
|
|
Body: io.NopCloser(bytes.NewReader(body)),
|
|
Header: http.Header{"Content-Type": []string{"application/json"}},
|
|
}
|
|
|
|
_, apiErr := OaiResponsesHandler(c, info, resp)
|
|
require.Nil(t, apiErr)
|
|
assert.Equal(t, 0, info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolWebSearchPreview].CallCount)
|
|
assert.Equal(t, 0, info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolFileSearch].CallCount)
|
|
}
|
|
|
|
func TestOaiResponsesHandlerCountsCompletedImageGenerationOutputs(t *testing.T) {
|
|
gin.SetMode(gin.TestMode)
|
|
|
|
body, err := common.Marshal(dto.OpenAIResponsesResponse{
|
|
Status: []byte(`"completed"`),
|
|
Output: []dto.ResponsesOutput{
|
|
{
|
|
Type: dto.ResponsesOutputTypeImageGenerationCall,
|
|
ID: "img_1",
|
|
Status: "completed",
|
|
Result: "base64-a",
|
|
},
|
|
{
|
|
Type: dto.ResponsesOutputTypeImageGenerationCall,
|
|
ID: "img_2",
|
|
Status: "completed",
|
|
Result: "base64-b",
|
|
},
|
|
{
|
|
Type: dto.ResponsesOutputTypeImageGenerationCall,
|
|
ID: "img_empty",
|
|
Status: "completed",
|
|
Result: "",
|
|
},
|
|
},
|
|
Usage: &dto.Usage{InputTokens: 1, OutputTokens: 1, TotalTokens: 2},
|
|
})
|
|
require.NoError(t, err)
|
|
|
|
w := httptest.NewRecorder()
|
|
c, _ := gin.CreateTestContext(w)
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1/responses", nil)
|
|
info := &relaycommon.RelayInfo{OriginModelName: "gpt-5.1"}
|
|
resp := &http.Response{
|
|
StatusCode: http.StatusOK,
|
|
Body: io.NopCloser(bytes.NewReader(body)),
|
|
Header: http.Header{"Content-Type": []string{"application/json"}},
|
|
}
|
|
|
|
_, apiErr := OaiResponsesHandler(c, info, resp)
|
|
require.Nil(t, apiErr)
|
|
require.Contains(t, info.ResponsesUsageInfo.BuiltInTools, dto.BuildInToolImageGeneration)
|
|
assert.Equal(t, 2, info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolImageGeneration].CallCount)
|
|
assert.False(t, c.GetBool("image_generation_call"))
|
|
}
|
|
|
|
func TestOaiResponsesHandlerIncompleteStatusCommitsZeroImageGeneration(t *testing.T) {
|
|
gin.SetMode(gin.TestMode)
|
|
|
|
body, err := common.Marshal(dto.OpenAIResponsesResponse{
|
|
Status: []byte(`"incomplete"`),
|
|
Output: []dto.ResponsesOutput{
|
|
{
|
|
Type: dto.ResponsesOutputTypeImageGenerationCall,
|
|
ID: "img_1",
|
|
Status: "completed",
|
|
Result: "base64-a",
|
|
},
|
|
},
|
|
Usage: &dto.Usage{InputTokens: 1, OutputTokens: 1, TotalTokens: 2},
|
|
})
|
|
require.NoError(t, err)
|
|
|
|
w := httptest.NewRecorder()
|
|
c, _ := gin.CreateTestContext(w)
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1/responses", nil)
|
|
info := &relaycommon.RelayInfo{
|
|
OriginModelName: "gpt-5.1",
|
|
ResponsesUsageInfo: &relaycommon.ResponsesUsageInfo{
|
|
BuiltInTools: map[string]*relaycommon.BuildInToolInfo{
|
|
dto.BuildInToolImageGeneration: {ToolName: dto.BuildInToolImageGeneration, CallCount: 0},
|
|
},
|
|
},
|
|
}
|
|
resp := &http.Response{
|
|
StatusCode: http.StatusOK,
|
|
Body: io.NopCloser(bytes.NewReader(body)),
|
|
Header: http.Header{"Content-Type": []string{"application/json"}},
|
|
}
|
|
|
|
_, apiErr := OaiResponsesHandler(c, info, resp)
|
|
require.Nil(t, apiErr)
|
|
assert.Equal(t, 0, info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolImageGeneration].CallCount)
|
|
}
|
|
|
|
func runResponsesImageBillingStream(t *testing.T, events ...string) *relaycommon.RelayInfo {
|
|
t.Helper()
|
|
gin.SetMode(gin.TestMode)
|
|
oldTimeout := constant.StreamingTimeout
|
|
constant.StreamingTimeout = 30
|
|
t.Cleanup(func() {
|
|
constant.StreamingTimeout = oldTimeout
|
|
})
|
|
|
|
var body strings.Builder
|
|
for _, event := range events {
|
|
body.WriteString("data: ")
|
|
body.WriteString(event)
|
|
body.WriteString("\n\n")
|
|
}
|
|
body.WriteString("data: [DONE]\n\n")
|
|
|
|
w := httptest.NewRecorder()
|
|
c, _ := gin.CreateTestContext(w)
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1/responses", nil)
|
|
c.Set(common.RequestIdKey, "responses-image-billing-test")
|
|
info := &relaycommon.RelayInfo{
|
|
OriginModelName: "gpt-5.1",
|
|
DisablePing: true,
|
|
ChannelMeta: &relaycommon.ChannelMeta{
|
|
UpstreamModelName: "gpt-5.1",
|
|
},
|
|
}
|
|
resp := &http.Response{
|
|
StatusCode: http.StatusOK,
|
|
Body: io.NopCloser(strings.NewReader(body.String())),
|
|
Header: http.Header{"Content-Type": []string{"text/event-stream"}},
|
|
}
|
|
|
|
_, apiErr := OaiResponsesStreamHandler(c, info, resp)
|
|
require.Nil(t, apiErr)
|
|
require.NotNil(t, info.ResponsesUsageInfo)
|
|
require.Contains(t, info.ResponsesUsageInfo.BuiltInTools, dto.BuildInToolImageGeneration)
|
|
return info
|
|
}
|
|
|
|
func TestOaiResponsesStreamHandlerDeduplicatesCompletedImageOutput(t *testing.T) {
|
|
item := `{"type":"image_generation_call","id":"img_1","call_id":"call_1","status":"completed","result":"base64-a"}`
|
|
info := runResponsesImageBillingStream(
|
|
t,
|
|
`{"type":"response.output_item.done","output_index":0,"item":`+item+`}`,
|
|
`{"type":"response.completed","response":{"status":"completed","output":[`+item+`],"usage":{"input_tokens":1,"output_tokens":1,"total_tokens":2}}}`,
|
|
)
|
|
|
|
assert.Equal(t, 1, info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolImageGeneration].CallCount)
|
|
}
|
|
|
|
func TestOaiResponsesStreamHandlerDiscardsImageOutputOnIncomplete(t *testing.T) {
|
|
info := runResponsesImageBillingStream(
|
|
t,
|
|
`{"type":"response.output_item.done","output_index":0,"item":{"type":"image_generation_call","id":"img_1","status":"completed","result":"base64-a"}}`,
|
|
`{"type":"response.incomplete","response":{"status":"incomplete"}}`,
|
|
)
|
|
|
|
assert.Equal(t, 0, info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolImageGeneration].CallCount)
|
|
}
|
|
|
|
func TestOaiResponsesStreamHandlerDoesNotCountPartialImageEvent(t *testing.T) {
|
|
info := runResponsesImageBillingStream(
|
|
t,
|
|
`{"type":"response.image_generation_call.partial_image","output_index":0,"partial_image_b64":"partial-bytes"}`,
|
|
`{"type":"response.completed","response":{"status":"completed","output":[]}}`,
|
|
)
|
|
|
|
assert.Equal(t, 0, info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolImageGeneration].CallCount)
|
|
}
|