Files
new-api/relay/channel/openai/relay_responses_billing_test.go
T
Calcium-Ion 86ac0f7745 refactor: extract protocol conversion layer into standalone relaykit module (#6369)
* 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
2026-07-27 15:56:21 +08:00

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)
}