* 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
206 lines
5.8 KiB
Go
206 lines
5.8 KiB
Go
package gemini
|
|
|
|
import (
|
|
"bytes"
|
|
"errors"
|
|
"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"
|
|
relayconstant "github.com/QuantumNous/new-api/relay/constant"
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
"github.com/QuantumNous/new-api/relaykit/types"
|
|
"github.com/gin-gonic/gin"
|
|
"github.com/stretchr/testify/assert"
|
|
"github.com/stretchr/testify/require"
|
|
)
|
|
|
|
func TestGeminiResponsesHandlerReturnsOpenAIResponsesJSON(t *testing.T) {
|
|
gin.SetMode(gin.TestMode)
|
|
recorder := httptest.NewRecorder()
|
|
c, _ := gin.CreateTestContext(recorder)
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1/responses", nil)
|
|
c.Set(common.RequestIdKey, "gemini-responses-test")
|
|
|
|
info := newGeminiResponsesRelayInfo(false)
|
|
payload := dto.GeminiChatResponse{
|
|
Candidates: []dto.GeminiChatCandidate{
|
|
{
|
|
Content: dto.GeminiChatContent{
|
|
Role: "model",
|
|
Parts: []dto.GeminiPart{
|
|
{Text: "hello"},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
UsageMetadata: dto.GeminiUsageMetadata{
|
|
PromptTokenCount: 2,
|
|
CandidatesTokenCount: 3,
|
|
TotalTokenCount: 5,
|
|
},
|
|
}
|
|
body, err := common.Marshal(payload)
|
|
require.NoError(t, err)
|
|
|
|
usage, newAPIError := GeminiResponsesHandler(c, info, &http.Response{
|
|
Body: io.NopCloser(bytes.NewReader(body)),
|
|
})
|
|
require.Nil(t, newAPIError)
|
|
require.NotNil(t, usage)
|
|
assert.Equal(t, 2, usage.PromptTokens)
|
|
assert.Equal(t, 3, usage.CompletionTokens)
|
|
|
|
got := recorder.Body.String()
|
|
assert.Contains(t, got, `"object":"response"`)
|
|
assert.Contains(t, got, `"status":"completed"`)
|
|
assert.Contains(t, got, `"type":"output_text"`)
|
|
assert.Contains(t, got, `"text":"hello"`)
|
|
assert.Contains(t, got, `"input_tokens":2`)
|
|
assert.Contains(t, got, `"output_tokens":3`)
|
|
assert.NotContains(t, got, `"choices"`)
|
|
assert.NotContains(t, got, `"candidates"`)
|
|
}
|
|
|
|
func TestGeminiResponsesHandlerClosesBodyOnReadError(t *testing.T) {
|
|
gin.SetMode(gin.TestMode)
|
|
recorder := httptest.NewRecorder()
|
|
c, _ := gin.CreateTestContext(recorder)
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1/responses", nil)
|
|
c.Set(common.RequestIdKey, "gemini-responses-read-error-test")
|
|
|
|
body := &failingReadCloser{}
|
|
usage, newAPIError := GeminiResponsesHandler(c, newGeminiResponsesRelayInfo(false), &http.Response{Body: body})
|
|
|
|
require.Nil(t, usage)
|
|
require.NotNil(t, newAPIError)
|
|
assert.True(t, body.closed)
|
|
}
|
|
|
|
func TestGeminiResponsesStreamHandlerReturnsOpenAIResponsesSSE(t *testing.T) {
|
|
gin.SetMode(gin.TestMode)
|
|
recorder := httptest.NewRecorder()
|
|
c, _ := gin.CreateTestContext(recorder)
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1/responses", nil)
|
|
c.Set(common.RequestIdKey, "gemini-responses-stream-test")
|
|
|
|
oldStreamingTimeout := constant.StreamingTimeout
|
|
constant.StreamingTimeout = 300
|
|
t.Cleanup(func() { constant.StreamingTimeout = oldStreamingTimeout })
|
|
|
|
info := newGeminiResponsesRelayInfo(true)
|
|
first := dto.GeminiChatResponse{
|
|
Candidates: []dto.GeminiChatCandidate{
|
|
{
|
|
Content: dto.GeminiChatContent{
|
|
Role: "model",
|
|
Parts: []dto.GeminiPart{
|
|
{Text: "hello"},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
UsageMetadata: dto.GeminiUsageMetadata{
|
|
PromptTokenCount: 2,
|
|
CandidatesTokenCount: 3,
|
|
TotalTokenCount: 5,
|
|
},
|
|
}
|
|
stop := "STOP"
|
|
final := dto.GeminiChatResponse{
|
|
Candidates: []dto.GeminiChatCandidate{
|
|
{
|
|
FinishReason: &stop,
|
|
Content: dto.GeminiChatContent{
|
|
Role: "model",
|
|
Parts: []dto.GeminiPart{{Text: ""}},
|
|
},
|
|
},
|
|
},
|
|
UsageMetadata: dto.GeminiUsageMetadata{
|
|
PromptTokenCount: 2,
|
|
CandidatesTokenCount: 3,
|
|
TotalTokenCount: 5,
|
|
},
|
|
}
|
|
firstData, err := common.Marshal(first)
|
|
require.NoError(t, err)
|
|
finalData, err := common.Marshal(final)
|
|
require.NoError(t, err)
|
|
streamBody := strings.Join([]string{
|
|
"data: " + string(firstData),
|
|
"",
|
|
"data: " + string(finalData),
|
|
"",
|
|
"data: [DONE]",
|
|
"",
|
|
}, "\n")
|
|
|
|
usage, newAPIError := GeminiResponsesStreamHandler(c, info, &http.Response{
|
|
Body: io.NopCloser(strings.NewReader(streamBody)),
|
|
})
|
|
require.Nil(t, newAPIError)
|
|
require.NotNil(t, usage)
|
|
assert.Equal(t, 5, usage.TotalTokens)
|
|
|
|
got := recorder.Body.String()
|
|
assert.Equal(t, "text/event-stream", recorder.Header().Get("Content-Type"))
|
|
assert.Contains(t, got, `event: response.created`)
|
|
assert.Contains(t, got, `event: response.output_text.delta`)
|
|
assert.Contains(t, got, `"delta":"hello"`)
|
|
assert.Contains(t, got, `event: response.completed`)
|
|
assert.Contains(t, got, `"input_tokens":2`)
|
|
assert.Contains(t, got, `"output_tokens":3`)
|
|
assert.NotContains(t, got, `"choices"`)
|
|
assert.NotContains(t, got, `"candidates"`)
|
|
requireOrderedGeminiResponsesSubstrings(t, got,
|
|
`event: response.created`,
|
|
`event: response.output_item.added`,
|
|
`event: response.output_text.delta`,
|
|
`event: response.output_text.done`,
|
|
`event: response.completed`,
|
|
)
|
|
}
|
|
|
|
func newGeminiResponsesRelayInfo(isStream bool) *relaycommon.RelayInfo {
|
|
return &relaycommon.RelayInfo{
|
|
IsStream: isStream,
|
|
RelayMode: relayconstant.RelayModeResponses,
|
|
RelayFormat: types.RelayFormatOpenAIResponses,
|
|
RequestURLPath: "/v1/responses",
|
|
DisablePing: true,
|
|
OriginModelName: "gemini-test",
|
|
ChannelMeta: &relaycommon.ChannelMeta{
|
|
UpstreamModelName: "gemini-test",
|
|
},
|
|
}
|
|
}
|
|
|
|
type failingReadCloser struct {
|
|
closed bool
|
|
}
|
|
|
|
func (r *failingReadCloser) Read([]byte) (int, error) {
|
|
return 0, errors.New("read failed")
|
|
}
|
|
|
|
func (r *failingReadCloser) Close() error {
|
|
r.closed = true
|
|
return nil
|
|
}
|
|
|
|
func requireOrderedGeminiResponsesSubstrings(t *testing.T, s string, parts ...string) {
|
|
t.Helper()
|
|
offset := 0
|
|
for _, part := range parts {
|
|
idx := strings.Index(s[offset:], part)
|
|
require.NotEqualf(t, -1, idx, "missing %q after byte offset %d", part, offset)
|
|
offset += idx + len(part)
|
|
}
|
|
}
|