Files
new-api/relay/channel/gemini/relay_responses_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

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)
}
}