iop/apps/edge/internal/openai/gemini_handler_test.go
toki 3d53c28ae1 fix(edge): Gemini caller 모델 경로를 분리한다
엄격한 route 식별자 규칙을 유지하면서 공식 caller의 URL-encoded 표시 모델 이름은 별도 bounded 규칙으로 수용해 Gemini ingress의 잘못된 400을 제거한다.
2026-08-13 23:28:51 +09:00

395 lines
18 KiB
Go

package openai
import (
"encoding/json"
"fmt"
"net/http"
"net/http/httptest"
"strings"
"testing"
"go.uber.org/zap"
"go.uber.org/zap/zaptest/observer"
edgeservice "iop/apps/edge/internal/service"
"iop/packages/go/config"
iop "iop/proto/gen/iop"
)
func TestGeminiIngressAuthenticatesAndStreamsThroughChatRoute(t *testing.T) {
fake := &fakeRunService{events: bufferedRunEvents(
&iop.RunEvent{Type: "delta", Delta: "hello"},
&iop.RunEvent{Type: "complete", Usage: &iop.Usage{InputTokens: 3, OutputTokens: 2}, Metadata: map[string]string{"finish_reason": "length"}},
)}
srv := NewServer(config.EdgeOpenAIConf{BearerToken: "iop-principal", Adapter: "ollama", Target: "provider-model"}, fake, nil)
body := `{
"systemInstruction":{"role":"user","parts":[{"text":"be concise"}]},
"contents":[{"role":"user","parts":[{"text":"say hello"}]}],
"generationConfig":{"candidateCount":1,"maxOutputTokens":16,"temperature":0.2,"topK":8,"topP":0.9,"thinkingConfig":{"includeThoughts":true,"thinkingBudget":-1}}
}`
req := httptest.NewRequest(http.MethodPost, "/gemini/gemini-direct/v1beta/models/gemini-3.6-flash:streamGenerateContent?alt=sse", strings.NewReader(body))
req.Header.Set("X-Goog-Api-Key", "iop-principal")
w := httptest.NewRecorder()
srv.routes().ServeHTTP(w, req)
if w.Code != http.StatusOK || w.Header().Get("Content-Type") != "text/event-stream" {
t.Fatalf("status/header: %d %q body=%s", w.Code, w.Header().Get("Content-Type"), w.Body.String())
}
if fake.req.ModelGroupKey != "gemini-direct" || fake.req.Target != "provider-model" {
t.Fatalf("route bypassed Chat admission: %+v", fake.req)
}
if !strings.Contains(fake.req.Prompt, "system: be concise") || !strings.Contains(fake.req.Prompt, "user: say hello") {
t.Fatalf("prompt conversion mismatch: %q", fake.req.Prompt)
}
options := fake.req.Input["options"].(map[string]any)
if options["max_tokens"] != 16 {
t.Fatalf("generation config mismatch: input=%+v", fake.req.Input)
}
if _, exists := options["top_k"]; exists {
t.Fatalf("deprecated Gemini sampling option reached Chat upstream: input=%+v", fake.req.Input)
}
response := w.Body.String()
for _, want := range []string{`"text":"hello"`, `"finishReason":"MAX_TOKENS"`} {
if !strings.Contains(response, want) {
t.Fatalf("missing %s in %s", want, response)
}
}
if strings.Contains(response, "iop-principal") {
t.Fatal("principal token leaked to response")
}
}
func TestGeminiStreamPathAcceptsOfficialCallerModelLabel(t *testing.T) {
req := httptest.NewRequest(
http.MethodPost,
"/gemini/gemini-direct/v1beta/models/Gemini%203.6%20Flash:streamGenerateContent?alt=sse",
nil,
)
routeID, callerModel, err := parseGeminiStreamPath(req)
if err != nil {
t.Fatalf("parseGeminiStreamPath: %v", err)
}
if routeID != "gemini-direct" || callerModel != "Gemini 3.6 Flash" {
t.Fatalf("path = %q/%q", routeID, callerModel)
}
for _, path := range []string{
"/gemini/gemini-direct/v1beta/models/%20Gemini:streamGenerateContent?alt=sse",
"/gemini/gemini-direct/v1beta/models/Gemini%20:streamGenerateContent?alt=sse",
} {
bad := httptest.NewRequest(http.MethodPost, path, nil)
if _, _, err := parseGeminiStreamPath(bad); err == nil {
t.Fatalf("expected invalid caller model path: %s", path)
}
}
}
func TestGeminiIngressRejectsAuthenticationAndShapeBeforeDispatch(t *testing.T) {
base := `{"contents":[{"role":"user","parts":[{"text":"hi"}]}]}`
for _, tc := range []struct {
name, path, body, bearer, key string
status int
}{
{"missing key", "/gemini/r/v1beta/models/gemini-3.6-flash:streamGenerateContent?alt=sse", base, "", "", 401},
{"conflicting auth", "/gemini/r/v1beta/models/gemini-3.6-flash:streamGenerateContent?alt=sse", base, "Bearer other", "iop-principal", 401},
{"wrong query", "/gemini/r/v1beta/models/gemini-3.6-flash:streamGenerateContent", base, "", "iop-principal", 400},
{"duplicate member", "/gemini/r/v1beta/models/gemini-3.6-flash:streamGenerateContent?alt=sse", `{"contents":[],"contents":[]}`, "", "iop-principal", 400},
{"two candidates", "/gemini/r/v1beta/models/gemini-3.6-flash:streamGenerateContent?alt=sse", `{"contents":[{"role":"user","parts":[{"text":"hi"}]}],"generationConfig":{"candidateCount":2}}`, "", "iop-principal", 400},
{"invalid thinking budget", "/gemini/r/v1beta/models/gemini-3.6-flash:streamGenerateContent?alt=sse", `{"contents":[{"role":"user","parts":[{"text":"hi"}]}],"generationConfig":{"thinkingConfig":{"thinkingBudget":-2}}}`, "", "iop-principal", 400},
} {
t.Run(tc.name, func(t *testing.T) {
fake := &fakeRunService{}
srv := NewServer(config.EdgeOpenAIConf{BearerToken: "iop-principal", Adapter: "ollama"}, fake, nil)
req := httptest.NewRequest(http.MethodPost, tc.path, strings.NewReader(tc.body))
if tc.bearer != "" {
req.Header.Set("Authorization", tc.bearer)
}
if tc.key != "" {
req.Header.Set("X-Goog-Api-Key", tc.key)
}
w := httptest.NewRecorder()
srv.routes().ServeHTTP(w, req)
if w.Code != tc.status {
t.Fatalf("status=%d body=%s", w.Code, w.Body.String())
}
var failure geminiErrorResponse
if json.Unmarshal(w.Body.Bytes(), &failure) != nil || failure.Error.Code != tc.status {
t.Fatalf("not a Gemini error: %s", w.Body.String())
}
if fake.req.ModelGroupKey != "" {
t.Fatalf("unexpected dispatch: %+v", fake.req)
}
})
}
}
func TestGeminiRequestBridgePreservesToolsAndThoughtSignature(t *testing.T) {
body := []byte(`{
"contents":[
{"role":"model","parts":[{"text":"thinking","thought":true},{"functionCall":{"name":"lookup","args":{"q":"x"}},"thoughtSignature":"opaque"}]},
{"role":"user","parts":[{"functionResponse":{"name":"lookup","response":{"value":1}}}]},
{"role":"user","parts":[{"text":"continue"}]}
],
"tools":[{"functionDeclarations":[{"name":"lookup","description":"find","parametersJsonSchema":{"type":"object"}}]}],
"toolConfig":{"functionCallingConfig":{"mode":"ANY"}}
}`)
converted, err := prepareGeminiChatBridge(body, "preset-gemini-hybrid")
if err != nil {
t.Fatal(err)
}
text := string(converted)
for _, want := range []string{`"model":"preset-gemini-hybrid"`, `"reasoning_content":"thinking"`, `"thought_signature":"opaque"`, `"tool_call_id":"gemini_call_0_1"`, `"tool_choice":"required"`} {
if !strings.Contains(text, want) {
t.Fatalf("missing %s in %s", want, text)
}
}
if strings.Contains(text, `"tool_name"`) {
t.Fatalf("nonstandard tool result field reached Chat bridge: %s", text)
}
}
func TestGeminiRequestBridgeMatchesExplicitToolCallIDsOutOfOrder(t *testing.T) {
converted, err := prepareGeminiChatBridge([]byte(`{
"contents":[
{"role":"model","parts":[
{"functionCall":{"id":"call_first","name":"lookup","args":{"q":"first"}}},
{"functionCall":{"id":"call_second","name":"lookup","args":{"q":"second"}}}
]},
{"role":"user","parts":[
{"functionResponse":{"id":"call_second","name":"lookup","response":{"value":2}}},
{"functionResponse":{"id":"call_first","name":"lookup","response":{"value":1}}}
]}
]
}`), "gemini-route")
if err != nil {
t.Fatal(err)
}
var body struct {
Messages []map[string]any `json:"messages"`
}
if err := json.Unmarshal(converted, &body); err != nil {
t.Fatal(err)
}
if len(body.Messages) != 3 {
t.Fatalf("messages=%+v", body.Messages)
}
if body.Messages[1]["tool_call_id"] != "call_second" || body.Messages[2]["tool_call_id"] != "call_first" {
t.Fatalf("explicit response order was not preserved: %+v", body.Messages)
}
for _, message := range body.Messages[1:] {
if _, exists := message["tool_name"]; exists {
t.Fatalf("nonstandard tool_name field survived: %+v", message)
}
}
}
func TestGeminiRequestBridgeKeepsIDLessFIFOCompatibility(t *testing.T) {
converted, err := prepareGeminiChatBridge([]byte(`{
"contents":[
{"role":"model","parts":[
{"functionCall":{"name":"lookup","args":{"q":"first"}}},
{"functionCall":{"name":"lookup","args":{"q":"second"}}}
]},
{"role":"user","parts":[
{"functionResponse":{"name":"lookup","response":{"value":1}}},
{"functionResponse":{"name":"lookup","response":{"value":2}}}
]}
]
}`), "gemini-route")
if err != nil {
t.Fatal(err)
}
var body struct {
Messages []map[string]any `json:"messages"`
}
if err := json.Unmarshal(converted, &body); err != nil {
t.Fatal(err)
}
if len(body.Messages) != 3 || body.Messages[1]["tool_call_id"] != "gemini_call_0_0" || body.Messages[2]["tool_call_id"] != "gemini_call_0_1" {
t.Fatalf("ID-less FIFO changed: %+v", body.Messages)
}
}
func TestGeminiRequestBridgeRejectsInvalidToolCallIdentity(t *testing.T) {
for _, tc := range []struct {
name string
body string
}{
{
name: "duplicate id",
body: `{"contents":[{"role":"model","parts":[{"functionCall":{"id":"call_1","name":"a","args":{}}},{"functionCall":{"id":"call_1","name":"b","args":{}}}]}]}`,
},
{
name: "mismatched name",
body: `{"contents":[{"role":"model","parts":[{"functionCall":{"id":"call_1","name":"a","args":{}}}]},{"role":"user","parts":[{"functionResponse":{"id":"call_1","name":"b","response":{}}}]}]}`,
},
{
name: "missing response id for explicit call",
body: `{"contents":[{"role":"model","parts":[{"functionCall":{"id":"call_1","name":"a","args":{}}}]},{"role":"user","parts":[{"functionResponse":{"name":"a","response":{}}}]}]}`,
},
{
name: "invalid id",
body: `{"contents":[{"role":"model","parts":[{"functionCall":{"id":"call id","name":"a","args":{}}}]}]}`,
},
} {
t.Run(tc.name, func(t *testing.T) {
if _, err := prepareGeminiChatBridge([]byte(tc.body), "gemini-route"); err == nil {
t.Fatal("invalid identity must fail")
}
})
}
}
func TestGeminiRequestBridgeUsesProviderNativeThinkingEnvelope(t *testing.T) {
converted, err := prepareGeminiChatBridge([]byte(`{
"contents":[{"role":"user","parts":[{"text":"hello"}]}],
"generationConfig":{"temperature":1,"topK":50,"topP":1,"thinkingConfig":{"includeThoughts":true,"thinkingBudget":-1}}
}`), "gemini-3.6-flash")
if err != nil {
t.Fatal(err)
}
var body map[string]any
if json.Unmarshal(converted, &body) != nil {
t.Fatal("converted body is invalid")
}
for _, forbidden := range []string{"temperature", "top_k", "top_p", "think", "include_reasoning", "thinking_token_budget"} {
if _, exists := body[forbidden]; exists {
t.Fatalf("unsupported field %q in converted body: %s", forbidden, converted)
}
}
extra := body["extra_body"].(map[string]any)
google := extra["google"].(map[string]any)
thinking := google["thinking_config"].(map[string]any)
if thinking["include_thoughts"] != true || thinking["thinking_budget"] != float64(-1) {
t.Fatalf("thinking envelope mismatch: %+v", thinking)
}
}
func TestGeminiRequestBridgeAcceptsOfficialAgyPlannerStructuredOutput(t *testing.T) {
converted, err := prepareGeminiChatBridge([]byte(`{
"contents":[{"role":"user","parts":[{"text":"plan"}]}],
"generationConfig":{
"responseMimeType":"application/json",
"responseJsonSchema":{"type":"OBJECT","properties":{"steps":{"type":"ARRAY"}},"required":["steps"]}
},
"tools":[{"functionDeclarations":[{
"name":"read_file","parameters":{"type":"OBJECT","properties":{"path":{"type":"STRING"}}},
"responseJsonSchema":{"type":"object"}
}]}]
}`), "gemini-3.6-flash")
if err != nil {
t.Fatal(err)
}
var body map[string]any
if json.Unmarshal(converted, &body) != nil {
t.Fatal("converted body is invalid")
}
format := body["response_format"].(map[string]any)
jsonSchema := format["json_schema"].(map[string]any)
schema := jsonSchema["schema"].(map[string]any)
if format["type"] != "json_schema" || jsonSchema["name"] != "agy_response" || jsonSchema["strict"] != true || schema["type"] != "object" {
t.Fatalf("structured output mismatch: %+v", format)
}
tools := body["tools"].([]any)
function := tools[0].(map[string]any)["function"].(map[string]any)
if function["name"] != "read_file" {
t.Fatalf("function conversion mismatch: %+v", function)
}
}
func TestGeminiRequestBridgeRejectsConflictingStructuredSchemas(t *testing.T) {
for _, body := range []string{
`{"contents":[{"role":"user","parts":[{"text":"x"}]}],"generationConfig":{"responseMimeType":"application/json","responseSchema":{"type":"object"},"responseJsonSchema":{"type":"object"}}}`,
`{"contents":[{"role":"user","parts":[{"text":"x"}]}],"tools":[{"functionDeclarations":[{"name":"f","parameters":{"type":"object"},"parametersJsonSchema":{"type":"object"}}]}]}`,
} {
if _, err := prepareGeminiChatBridge([]byte(body), "gemini-3.6-flash"); err == nil {
t.Fatal("conflicting schema alternatives must fail")
}
}
}
func TestGeminiStreamBridgeEmitsBoundedToolOnce(t *testing.T) {
w := httptest.NewRecorder()
stream := newGeminiBridgeStream(w, "gemini-3.6-flash")
input := "data: {\"choices\":[{\"delta\":{\"tool_calls\":[{\"index\":0,\"id\":\"call_provider_1\",\"function\":{\"name\":\"lookup\",\"arguments\":\"{\\\"q\\\":\"}}]}}]}\n\n" +
"data: {\"choices\":[{\"delta\":{\"tool_calls\":[{\"index\":0,\"function\":{\"arguments\":\"\\\"x\\\"}\"}}]},\"finish_reason\":\"tool_calls\"}]}\n\n" +
"data: [DONE]\n\n"
if err := stream.Feed([]byte(input)); err != nil {
t.Fatal(err)
}
if strings.Count(w.Body.String(), `"functionCall"`) != 1 || !strings.Contains(w.Body.String(), `"finishReason":"STOP"`) {
t.Fatalf("tool terminal mismatch: %s", w.Body.String())
}
if !strings.Contains(w.Body.String(), `"id":"call_provider_1"`) {
t.Fatalf("provider tool call id was not preserved: %s", w.Body.String())
}
usageWriter := httptest.NewRecorder()
usageStream := newGeminiBridgeStream(usageWriter, "m")
if err := usageStream.Feed([]byte("data: {\"usage\":{\"prompt_tokens\":3,\"completion_tokens\":2,\"total_tokens\":5,\"prompt_tokens_details\":{\"cached_tokens\":1},\"completion_tokens_details\":{\"reasoning_tokens\":1}}}\n\ndata: [DONE]\n\n")); err != nil {
t.Fatal(err)
}
for _, want := range []string{`"promptTokenCount":3`, `"candidatesTokenCount":2`, `"cachedContentTokenCount":1`, `"thoughtsTokenCount":1`, `"totalTokenCount":5`} {
if !strings.Contains(usageWriter.Body.String(), want) {
t.Fatalf("missing usage %s in %s", want, usageWriter.Body.String())
}
}
oversize := newGeminiBridgeStream(httptest.NewRecorder(), "m")
state := &geminiBridgeToolState{name: "lookup"}
state.arguments.WriteString(strings.Repeat("x", geminiToolArgumentLimit))
oversize.tools[0] = state
chunk := `data: {"choices":[{"delta":{"tool_calls":[{"index":0,"function":{"arguments":"x"}}]}}]}` + "\n\n"
if err := oversize.Feed([]byte(chunk)); err == nil {
t.Fatal("oversize tool arguments must fail")
}
}
func TestGeminiRejectionObservationIsClassificationOnly(t *testing.T) {
core, observed := observer.New(zap.InfoLevel)
secret := "secret-fixture-must-not-be-logged"
authServer := NewServer(config.EdgeOpenAIConf{BearerToken: "principal"}, &fakeRunService{}, zap.New(core))
authReq := httptest.NewRequest(http.MethodPost, "/gemini/r/v1beta/models/m:streamGenerateContent?alt=sse", strings.NewReader(`{"contents":[{"role":"user","parts":[{"text":"`+secret+`"}]}]}`))
authServer.routes().ServeHTTP(httptest.NewRecorder(), authReq)
managedServer := managedCredentialMigrationServer(t, &providerFakeRunService{})
managedServer.logger = zap.New(core)
managedReq := httptest.NewRequest(http.MethodPost, "/gemini/public-route/v1beta/models/m:streamGenerateContent?alt=sse", strings.NewReader(`{"contents":[{"role":"user","parts":[{"text":"hello"}]}]}`))
managedReq.Header.Set("X-Goog-Api-Key", "managed-iop-token")
managedReq.Header.Set(legacyProviderCredentialHeader, secret)
managedServer.routes().ServeHTTP(httptest.NewRecorder(), managedReq)
candidate := anthropicTestCandidate(t, "openai")
candidate.ActualModel = "served-chat"
providerBody := []byte(`{"error":{"message":"` + secret + `"}}`)
fake := &providerFakeRunService{
poolDispatchPath: string(edgeservice.ProviderPoolPathTunnel),
poolSelectedCandidate: candidate,
tunnelFrames: anthropicTunnelFrames(http.StatusBadRequest, "application/json", providerBody),
}
providerServer := NewServer(config.EdgeOpenAIConf{BearerToken: "principal"}, fake, zap.New(core))
providerServer.SetModelCatalog([]config.ModelCatalogEntry{{ID: "r", Providers: map[string]string{"chat": "served-chat"}}})
providerReq := httptest.NewRequest(http.MethodPost, "/gemini/r/v1beta/models/m:streamGenerateContent?alt=sse", strings.NewReader(`{"contents":[{"role":"user","parts":[{"text":"hello"}]}]}`))
providerReq.Header.Set("X-Goog-Api-Key", "principal")
providerServer.routes().ServeHTTP(httptest.NewRecorder(), providerReq)
localFailureServer := NewServer(config.EdgeOpenAIConf{BearerToken: "principal", Adapter: "ollama", Target: "provider-model"}, &fakeRunService{submitErrAfter: 1}, zap.New(core))
localFailureReq := httptest.NewRequest(http.MethodPost, "/gemini/r/v1beta/models/m:streamGenerateContent?alt=sse", strings.NewReader(`{"contents":[{"role":"user","parts":[{"text":"`+secret+`"}]}]}`))
localFailureReq.Header.Set("X-Goog-Api-Key", "principal")
localFailureServer.routes().ServeHTTP(httptest.NewRecorder(), localFailureReq)
entries := observed.FilterMessage(geminiRejectionLogMessage).All()
if len(entries) != 3 {
t.Fatalf("rejection observations=%d logs=%+v", len(entries), observed.All())
}
wantClasses := []string{string(geminiRejectionPreIngress), string(geminiRejectionPreIngress), string(geminiRejectionProviderHTTP)}
wantStatuses := []int64{http.StatusUnauthorized, http.StatusBadRequest, http.StatusBadRequest}
for index, entry := range entries {
context := entry.ContextMap()
if len(context) != 4 || context["surface"] != "gemini" || context["bridge"] != "chat" || context["rejection_class"] != wantClasses[index] || context["http_status"] != wantStatuses[index] {
t.Fatalf("unsafe or incomplete observation: %+v", context)
}
if strings.Contains(fmt.Sprint(context), secret) {
t.Fatalf("secret leaked to observation: %+v", context)
}
}
}