BCAI/easyai-ai-gateway
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat: add Responses API compatibility

Browse Source
This commit is contained in:
wangbo
2026-07-10 23:33:15 +08:00
parent b7351f3b9b
commit 8847d973a8
24 changed files with 5922 additions and 169 deletions
Download Patch File Download Diff File Expand all files Collapse all files
apps/api/internal/runner/service.go
+57 -7
View File
@@ -93,6 +93,7 @@ func (s *Service) execute(ctx context.Context, task store.GatewayTask, user *aut
return Result{}, err
}
body := normalizeRequest(task.Kind, restoredRequest)
responseExecution := responseExecutionContext{}
modelType := modelTypeFromKind(task.Kind, body)
if err := s.store.MarkTaskRunning(ctx, task.ID, modelType, s.slimTaskRequestSnapshot(task, body)); err != nil {
return Result{}, err
@@ -145,6 +146,18 @@ func (s *Service) execute(ctx context.Context, task store.GatewayTask, user *aut
return Result{}, err
}
}
if task.Kind == "responses" {
responseExecution, err = s.prepareResponseExecution(ctx, task, body)
if err != nil {
code, message := responseExecutionFailure(err)
s.recordFailedAttempt(ctx, failedAttemptRecord{Task: task, Body: body, AttemptNo: task.AttemptCount + 1, Code: code, Cause: err, Simulated: task.RunMode == "simulation", Scope: "response_chain", Reason: code, ModelType: modelType})
failed, finishErr := s.failTask(ctx, task.ID, code, message, task.RunMode == "simulation", err)
if finishErr != nil {
return Result{}, finishErr
}
return Result{Task: failed, Output: failed.Result}, err
}
}
runnerPolicy, err := s.store.GetActiveRunnerPolicy(ctx)
if err != nil {
return Result{}, err
@@ -156,6 +169,9 @@ func (s *Service) execute(ctx context.Context, task store.GatewayTask, user *aut
CacheAffinityPolicy: runnerPolicy.CacheAffinityPolicy,
})
if err != nil {
if task.Kind == "responses" && responseExecution.PreviousChain != nil {
err = responseChainUnavailableError()
}
s.recordFailedAttempt(ctx, failedAttemptRecord{
Task: task,
Body: body,
@@ -214,6 +230,18 @@ func (s *Service) execute(ctx context.Context, task store.GatewayTask, user *aut
}
return Result{Task: failed, Output: failed.Result}, err
}
if task.Kind == "responses" {
candidates, err = prepareResponseCandidates(candidates, responseExecution)
if err != nil {
code, message := responseExecutionFailure(err)
s.recordFailedAttempt(ctx, failedAttemptRecord{Task: task, Body: body, AttemptNo: task.AttemptCount + 1, Code: code, Cause: err, Simulated: task.RunMode == "simulation", Scope: "response_protocol", Reason: code, ModelType: modelType})
failed, finishErr := s.failTask(ctx, task.ID, code, message, task.RunMode == "simulation", err)
if finishErr != nil {
return Result{}, finishErr
}
return Result{Task: failed, Output: failed.Result}, err
}
}
firstCandidateBody := body
normalizedModelType := modelType
attemptNo := task.AttemptCount
@@ -325,7 +353,7 @@ candidatesLoop:
break candidatesLoop
}
candidateBody := preprocessing.Body
response, err := s.runCandidate(ctx, task, user, candidateBody, preprocessing.Log, candidate, nextAttemptNo, onDelta, singleSourceProtected, runnerPolicy.CacheAffinityPolicy, cacheAffinityKeys.Record)
response, err := s.runCandidate(ctx, task, user, candidateBody, preprocessing.Log, candidate, nextAttemptNo, onDelta, responseExecution, singleSourceProtected, runnerPolicy.CacheAffinityPolicy, cacheAffinityKeys.Record)
if err == nil {
attemptNo = nextAttemptNo
billings := s.billings(ctx, user, task.Kind, candidateBody, candidate, response, isSimulation(task, candidate))
@@ -536,7 +564,7 @@ candidatesLoop:
return Result{Task: failed, Output: failed.Result}, lastErr
}
func (s *Service) runCandidate(ctx context.Context, task store.GatewayTask, user *auth.User, body map[string]any, preprocessing parameterPreprocessingLog, candidate store.RuntimeModelCandidate, attemptNo int, onDelta clients.StreamDelta, singleSourceProtected bool, cacheAffinityPolicy map[string]any, cacheAffinityRecordKeys []string) (clients.Response, error) {
func (s *Service) runCandidate(ctx context.Context, task store.GatewayTask, user *auth.User, body map[string]any, preprocessing parameterPreprocessingLog, candidate store.RuntimeModelCandidate, attemptNo int, onDelta clients.StreamDelta, responseExecution responseExecutionContext, singleSourceProtected bool, cacheAffinityPolicy map[string]any, cacheAffinityRecordKeys []string) (clients.Response, error) {
simulated := isSimulation(task, candidate)
baseAttemptMetrics := mergeMetrics(attemptMetrics(candidate, attemptNo, simulated), parameterPreprocessingMetrics(preprocessing))
reservations := s.rateLimitReservations(ctx, user, candidate, body)
@@ -628,6 +656,12 @@ func (s *Service) runCandidate(ctx context.Context, task store.GatewayTask, user
return clients.Response{}, err
}
callStartedAt := time.Now()
publicResponseID := ""
publicPreviousResponseID := ""
if task.Kind == "responses" && candidate.ResponseProtocol == clients.ProtocolOpenAIChatCompletions {
publicResponseID = responseExecution.PublicResponseID
publicPreviousResponseID = responseExecution.PublicPreviousResponseID
}
response, err := client.Run(ctx, clients.Request{
Kind: task.Kind,
ModelType: candidate.ModelType,
@@ -643,8 +677,13 @@ func (s *Service) runCandidate(ctx context.Context, task store.GatewayTask, user
}
return s.store.SetTaskRemoteTask(context.WithoutCancel(ctx), task.ID, attemptID, remoteTaskID, payload)
},
Stream: boolFromMap(providerBody, "stream"),
StreamDelta: onDelta,
Stream: boolFromMap(providerBody, "stream"),
StreamDelta: onDelta,
UpstreamProtocol: candidate.ResponseProtocol,
PublicResponseID: publicResponseID,
PublicPreviousResponseID: publicPreviousResponseID,
UpstreamPreviousResponseID: responseExecution.UpstreamPreviousResponseID,
PreviousResponseTurns: responseExecution.PreviousTurns,
})
callFinishedAt := time.Now()
if response.ResponseStartedAt.IsZero() {
@@ -715,6 +754,20 @@ func (s *Service) runCandidate(ctx context.Context, task store.GatewayTask, user
return clients.Response{}, err
}
response.Result = uploadedResult
if task.Kind == "responses" {
response.UpstreamProtocol = candidate.ResponseProtocol
response.ParentResponseID = responseExecution.PublicPreviousResponseID
response.ResponseChainDepth = responseExecution.ChainDepth
if candidate.ResponseProtocol == clients.ProtocolOpenAIChatCompletions {
response.Result["id"] = responseExecution.PublicResponseID
response.PublicResponseID = responseExecution.PublicResponseID
} else {
response.PublicResponseID = strings.TrimSpace(stringFromAny(response.Result["id"]))
}
if err := s.persistResponseChain(ctx, task, body, candidate, responseExecution, response); err != nil {
return clients.Response{}, fmt.Errorf("persist response chain: %w", err)
}
}
if task.Kind == "voice.clone" {
voice, err := s.persistVoiceCloneResult(ctx, task, user, candidate, attemptID, body, response.Result)
if err != nil {
@@ -1283,9 +1336,6 @@ func loadAvoidanceFallbackDecision(err error) failoverDecision {
func normalizeRequest(kind string, body map[string]any) map[string]any {
out := cloneMap(body)
if kind == "responses" && out["messages"] == nil && out["input"] != nil {
out["messages"] = []any{map[string]any{"role": "user", "content": out["input"]}}
}
return out
}