Skip to content

feat: add daily token limit error handling and corresponding test #16

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
hcastc00 merged 1 commit into from
Oct 23, 2026
Merged

feat: add daily token limit error handling and corresponding test #16

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions apps/gateway/internal/adapters/metering/client.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -295,6 +295,9 @@ func userFacingMeteringError(method, path string, status int, envelope errorResp
if envelope.Error.Code == domain.ErrCodeInsufficientBalance {
wantStatus = http.StatusPaymentRequired
wantType = domain.ErrTypePermission
} else if envelope.Error.Code == domain.ErrCodeDailyTokenLimit {
wantStatus = http.StatusTooManyRequests
wantType = domain.ErrTypeRateLimit
}
}

Expand Down
19 changes: 19 additions & 0 deletions apps/gateway/internal/adapters/metering/client_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -263,3 +263,22 @@ func assertInternalMeteringError(t *testing.T, err error) {
t.Fatalf("metadata = %#v, want metering dependency", gatewayErr.Metadata)
}
}

func TestClientReserve_MapsDailyTokenLimitWithoutRetry(t *testing.T) {
var attempts atomic.Int32
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
attempts.Add(1)
w.WriteHeader(http.StatusTooManyRequests)
_, _ = w.Write([]byte(`{"error":{"type":"rate_limit_error","code":"daily_token_limit_exceeded","message":"Daily token quota reached"}}`))
}))
defer server.Close()
client := NewClient(server.URL, "token", time.Second)
_, err := client.Reserve(context.Background(), testAuth(), domain.EndpointChatCompletions, domain.GenerateRequest{PublicModelID: "model"}, testModel(), "gw-limit")
var gatewayErr *domain.GatewayError
if !errors.As(err, &gatewayErr) || gatewayErr.HTTPStatus != 429 || gatewayErr.Type != domain.ErrTypeRateLimit || gatewayErr.Code != domain.ErrCodeDailyTokenLimit {
t.Fatalf("got %#v, want daily quota 429", err)
}
if attempts.Load() != 1 {
t.Fatalf("quota error retried %d times", attempts.Load())
}
}
2 changes: 2 additions & 0 deletions pkg/domain/error.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@ const (
ErrTypePermission = "permission_error"
ErrTypeProvider = "provider_error"
ErrTypeInternal = "internal_error"
ErrTypeRateLimit = "rate_limit_error"
)

// Error codes as defined in the spec.
Expand All @@ -33,6 +34,7 @@ const (
ErrCodeInvalidField = "invalid_field"
ErrCodeUnknownField = "unknown_field"
ErrCodeInsufficientBalance = "insufficient_balance"
ErrCodeDailyTokenLimit = "daily_token_limit_exceeded"
ErrCodeClientCanceled = "client_canceled"
ErrCodeInternalError = "internal_error"
)
Expand Down
Loading