Files
new-api/relay/channel/openai/chat_via_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

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)
}
}