mirror of
https://github.com/QuantumNous/new-api.git
synced 2026-09-11 14:41:21 +00:00
* 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
181 lines
7.4 KiB
Go
181 lines
7.4 KiB
Go
package openai
|
|
|
|
import (
|
|
"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/types"
|
|
"github.com/gin-gonic/gin"
|
|
"github.com/stretchr/testify/require"
|
|
)
|
|
|
|
func newResponsesChatTestContext(t *testing.T, body string, isStream bool) (*gin.Context, *httptest.ResponseRecorder, *http.Response, *relaycommon.RelayInfo) {
|
|
t.Helper()
|
|
|
|
recorder := httptest.NewRecorder()
|
|
c, _ := gin.CreateTestContext(recorder)
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
|
|
c.Set(common.RequestIdKey, "responses-test")
|
|
|
|
resp := &http.Response{
|
|
StatusCode: http.StatusOK,
|
|
Body: io.NopCloser(strings.NewReader(body)),
|
|
Header: http.Header{"Content-Type": []string{"text/event-stream"}},
|
|
}
|
|
info := &relaycommon.RelayInfo{
|
|
ChannelMeta: &relaycommon.ChannelMeta{UpstreamModelName: "gpt-test"},
|
|
IsStream: isStream,
|
|
RelayFormat: types.RelayFormatOpenAI,
|
|
ShouldIncludeUsage: true,
|
|
DisablePing: true,
|
|
}
|
|
return c, recorder, resp, info
|
|
}
|
|
|
|
func TestOaiResponsesToChatStreamHandlerConvertsSSEOrderAndUsage(t *testing.T) {
|
|
oldMode := gin.Mode()
|
|
gin.SetMode(gin.TestMode)
|
|
t.Cleanup(func() { gin.SetMode(oldMode) })
|
|
|
|
oldTimeout := constant.StreamingTimeout
|
|
constant.StreamingTimeout = 30
|
|
t.Cleanup(func() { constant.StreamingTimeout = oldTimeout })
|
|
|
|
body := strings.Join([]string{
|
|
`data: {"type":"response.created","response":{"id":"resp_1","model":"gpt-test","created_at":1710000000}}`,
|
|
`data: {"type":"response.output_text.delta","delta":"hello"}`,
|
|
`data: {"type":"response.output_item.added","output_index":1,"item":{"type":"function_call","id":"fc_1","call_id":"call_1","name":"lookup"}}`,
|
|
`data: {"type":"response.function_call_arguments.delta","output_index":1,"delta":"{\"q\":\"x\"}"}`,
|
|
`data: {"type":"response.completed","response":{"status":"completed","usage":{"input_tokens":2,"output_tokens":3,"total_tokens":5}}}`,
|
|
`data: [DONE]`,
|
|
``,
|
|
}, "\n")
|
|
|
|
c, recorder, resp, info := newResponsesChatTestContext(t, body, true)
|
|
|
|
usage, err := OaiResponsesToChatStreamHandler(c, info, resp)
|
|
require.Nil(t, err)
|
|
require.NotNil(t, usage)
|
|
require.Equal(t, 2, usage.PromptTokens)
|
|
require.Equal(t, 3, usage.CompletionTokens)
|
|
require.Equal(t, 5, usage.TotalTokens)
|
|
|
|
got := recorder.Body.String()
|
|
require.Equal(t, "text/event-stream", recorder.Header().Get("Content-Type"))
|
|
require.Contains(t, got, `"role":"assistant"`)
|
|
require.Contains(t, got, `"content":"hello"`)
|
|
require.Contains(t, got, `"name":"lookup"`)
|
|
require.Contains(t, got, `"arguments":"{\"q\":\"x\"}"`)
|
|
require.Contains(t, got, `"finish_reason":"tool_calls"`)
|
|
require.Contains(t, got, `"usage":{"prompt_tokens":2,"completion_tokens":3,"total_tokens":5`)
|
|
require.Contains(t, got, `data: [DONE]`)
|
|
requireOrderedSubstrings(t, got,
|
|
`"role":"assistant"`,
|
|
`"content":"hello"`,
|
|
`"name":"lookup"`,
|
|
`"arguments":"{\"q\":\"x\"}"`,
|
|
`"finish_reason":"tool_calls"`,
|
|
`"usage":{"prompt_tokens":2,"completion_tokens":3,"total_tokens":5`,
|
|
`data: [DONE]`,
|
|
)
|
|
}
|
|
|
|
func TestOaiResponsesToChatBufferedStreamHandlerReturnsJSONFromSSE(t *testing.T) {
|
|
oldMode := gin.Mode()
|
|
gin.SetMode(gin.TestMode)
|
|
t.Cleanup(func() { gin.SetMode(oldMode) })
|
|
|
|
body := strings.Join([]string{
|
|
`data: {"type":"response.output_text.delta","delta":"buffered text"}`,
|
|
`data: {"type":"response.output_item.added","output_index":0,"item":{"type":"function_call","id":"fc_1","call_id":"call_1","name":"lookup"}}`,
|
|
`data: {"type":"response.function_call_arguments.delta","output_index":0,"delta":"{\"q\":\"x\"}"}`,
|
|
`data: {"type":"response.done","response":{"model":"gpt-test","status":"completed","usage":{"input_tokens":1,"output_tokens":2,"total_tokens":3}}}`,
|
|
`data: [DONE]`,
|
|
``,
|
|
}, "\n")
|
|
|
|
c, recorder, resp, info := newResponsesChatTestContext(t, body, false)
|
|
|
|
usage, err := OaiResponsesToChatBufferedStreamHandler(c, info, resp)
|
|
require.Nil(t, err)
|
|
require.NotNil(t, usage)
|
|
require.Equal(t, 3, usage.TotalTokens)
|
|
|
|
got := recorder.Body.String()
|
|
require.NotContains(t, got, `data:`)
|
|
require.Contains(t, got, `"object":"chat.completion"`)
|
|
require.Contains(t, got, `"content":"buffered text"`)
|
|
require.Contains(t, got, `"name":"lookup"`)
|
|
require.Contains(t, got, `"arguments":"{\"q\":\"x\"}"`)
|
|
require.Contains(t, got, `"finish_reason":"tool_calls"`)
|
|
}
|
|
|
|
func TestOaiChatToResponsesStreamHandlerConvertsSSEOrderAndUsage(t *testing.T) {
|
|
oldMode := gin.Mode()
|
|
gin.SetMode(gin.TestMode)
|
|
t.Cleanup(func() { gin.SetMode(oldMode) })
|
|
|
|
oldTimeout := constant.StreamingTimeout
|
|
constant.StreamingTimeout = 30
|
|
t.Cleanup(func() { constant.StreamingTimeout = oldTimeout })
|
|
|
|
body := strings.Join([]string{
|
|
`data: {"id":"chatcmpl_1","object":"chat.completion.chunk","created":1710000000,"model":"gpt-test","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}`,
|
|
`data: {"id":"chatcmpl_1","object":"chat.completion.chunk","created":1710000000,"model":"gpt-test","choices":[{"index":0,"delta":{"content":"hello"},"finish_reason":null}]}`,
|
|
`data: {"id":"chatcmpl_1","object":"chat.completion.chunk","created":1710000000,"model":"gpt-test","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"id":"call_1","type":"function","function":{"name":"lookup"}}]},"finish_reason":null}]}`,
|
|
`data: {"id":"chatcmpl_1","object":"chat.completion.chunk","created":1710000000,"model":"gpt-test","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"q\":\"x\"}"}}]},"finish_reason":null}]}`,
|
|
`data: {"id":"chatcmpl_1","object":"chat.completion.chunk","created":1710000000,"model":"gpt-test","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}`,
|
|
`data: {"id":"chatcmpl_1","object":"chat.completion.chunk","created":1710000000,"model":"gpt-test","choices":[],"usage":{"prompt_tokens":2,"completion_tokens":3,"total_tokens":5}}`,
|
|
`data: [DONE]`,
|
|
``,
|
|
}, "\n")
|
|
|
|
c, recorder, resp, info := newResponsesChatTestContext(t, body, true)
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1/responses", nil)
|
|
|
|
usage, err := OaiChatToResponsesStreamHandler(c, info, resp)
|
|
require.Nil(t, err)
|
|
require.NotNil(t, usage)
|
|
require.Equal(t, 2, usage.PromptTokens)
|
|
require.Equal(t, 3, usage.CompletionTokens)
|
|
require.Equal(t, 5, usage.TotalTokens)
|
|
|
|
got := recorder.Body.String()
|
|
require.Equal(t, "text/event-stream", recorder.Header().Get("Content-Type"))
|
|
require.Contains(t, got, `event: response.created`)
|
|
require.Contains(t, got, `event: response.output_text.delta`)
|
|
require.Contains(t, got, `"delta":"hello"`)
|
|
require.Contains(t, got, `event: response.function_call_arguments.delta`)
|
|
require.Contains(t, got, `"delta":"{\"q\":\"x\"}"`)
|
|
require.Contains(t, got, `event: response.completed`)
|
|
require.Contains(t, got, `"input_tokens":2`)
|
|
require.Contains(t, got, `"output_tokens":3`)
|
|
requireOrderedSubstrings(t, got,
|
|
`event: response.created`,
|
|
`event: response.output_item.added`,
|
|
`event: response.output_text.delta`,
|
|
`event: response.output_item.added`,
|
|
`event: response.function_call_arguments.delta`,
|
|
`event: response.output_text.done`,
|
|
`event: response.function_call_arguments.done`,
|
|
`event: response.completed`,
|
|
)
|
|
}
|
|
|
|
func requireOrderedSubstrings(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)
|
|
}
|
|
}
|