fix: fall back on model support errors during auth rotation

2026-03-18 12:43:45 -04:00
parent db63f9b5d6
commit 5135c22cd6
3 changed files with 287 additions and 43 deletions
@@ -1627,53 +1627,60 @@ func (m *Manager) MarkResult(ctx context.Context, result Result) {
 				}

 				statusCode := statusCodeFromResult(result.Error)
-				switch statusCode {
-				case 401:
-					next := now.Add(30 * time.Minute)
-					state.NextRetryAfter = next
-					suspendReason = "unauthorized"
-					shouldSuspendModel = true
-				case 402, 403:
-					next := now.Add(30 * time.Minute)
-					state.NextRetryAfter = next
-					suspendReason = "payment_required"
-					shouldSuspendModel = true
-				case 404:
+				if isModelSupportResultError(result.Error) {
 					next := now.Add(12 * time.Hour)
 					state.NextRetryAfter = next
-					suspendReason = "not_found"
+					suspendReason = "model_not_supported"
 					shouldSuspendModel = true
-				case 429:
-					var next time.Time
-					backoffLevel := state.Quota.BackoffLevel
-					if result.RetryAfter != nil {
-						next = now.Add(*result.RetryAfter)
-					} else {
-						cooldown, nextLevel := nextQuotaCooldown(backoffLevel, quotaCooldownDisabledForAuth(auth))
-						if cooldown > 0 {
-							next = now.Add(cooldown)
-						}
-						backoffLevel = nextLevel
-					}
-					state.NextRetryAfter = next
-					state.Quota = QuotaState{
-						Exceeded:      true,
-						Reason:        "quota",
-						NextRecoverAt: next,
-						BackoffLevel:  backoffLevel,
-					}
-					suspendReason = "quota"
-					shouldSuspendModel = true
-					setModelQuota = true
-				case 408, 500, 502, 503, 504:
-					if quotaCooldownDisabledForAuth(auth) {
-						state.NextRetryAfter = time.Time{}
-					} else {
-						next := now.Add(1 * time.Minute)
+				} else {
+					switch statusCode {
+					case 401:
+						next := now.Add(30 * time.Minute)
 						state.NextRetryAfter = next
+						suspendReason = "unauthorized"
+						shouldSuspendModel = true
+					case 402, 403:
+						next := now.Add(30 * time.Minute)
+						state.NextRetryAfter = next
+						suspendReason = "payment_required"
+						shouldSuspendModel = true
+					case 404:
+						next := now.Add(12 * time.Hour)
+						state.NextRetryAfter = next
+						suspendReason = "not_found"
+						shouldSuspendModel = true
+					case 429:
+						var next time.Time
+						backoffLevel := state.Quota.BackoffLevel
+						if result.RetryAfter != nil {
+							next = now.Add(*result.RetryAfter)
+						} else {
+							cooldown, nextLevel := nextQuotaCooldown(backoffLevel, quotaCooldownDisabledForAuth(auth))
+							if cooldown > 0 {
+								next = now.Add(cooldown)
+							}
+							backoffLevel = nextLevel
+						}
+						state.NextRetryAfter = next
+						state.Quota = QuotaState{
+							Exceeded:      true,
+							Reason:        "quota",
+							NextRecoverAt: next,
+							BackoffLevel:  backoffLevel,
+						}
+						suspendReason = "quota"
+						shouldSuspendModel = true
+						setModelQuota = true
+					case 408, 500, 502, 503, 504:
+						if quotaCooldownDisabledForAuth(auth) {
+							state.NextRetryAfter = time.Time{}
+						} else {
+							next := now.Add(1 * time.Minute)
+							state.NextRetryAfter = next
+						}
+					default:
+						state.NextRetryAfter = time.Time{}
 					}
-				default:
-					state.NextRetryAfter = time.Time{}
 				}

 				auth.Status = StatusError
@@ -1883,14 +1890,65 @@ func statusCodeFromResult(err *Error) int {
 	return err.StatusCode()
 }

+func isModelSupportErrorMessage(message string) bool {
+	lower := strings.ToLower(strings.TrimSpace(message))
+	if lower == "" {
+		return false
+	}
+	patterns := [...]string{
+		"model_not_supported",
+		"requested model is not supported",
+		"requested model is unsupported",
+		"requested model is unavailable",
+		"model is not supported",
+		"model not supported",
+		"unsupported model",
+		"model unavailable",
+		"not available for your plan",
+		"not available for your account",
+	}
+	for _, pattern := range patterns {
+		if strings.Contains(lower, pattern) {
+			return true
+		}
+	}
+	return false
+}
+
+func isModelSupportError(err error) bool {
+	if err == nil {
+		return false
+	}
+	status := statusCodeFromError(err)
+	if status != http.StatusBadRequest && status != http.StatusUnprocessableEntity {
+		return false
+	}
+	return isModelSupportErrorMessage(err.Error())
+}
+
+func isModelSupportResultError(err *Error) bool {
+	if err == nil {
+		return false
+	}
+	status := statusCodeFromResult(err)
+	if status != http.StatusBadRequest && status != http.StatusUnprocessableEntity {
+		return false
+	}
+	return isModelSupportErrorMessage(err.Message)
+}
+
 // isRequestInvalidError returns true if the error represents a client request
 // error that should not be retried. Specifically, it treats 400 responses with
 // "invalid_request_error" and all 422 responses as request-shape failures,
-// where switching auths or pooled upstream models will not help.
+// where switching auths or pooled upstream models will not help. Model-support
+// errors are excluded so routing can fall through to another auth or upstream.
 func isRequestInvalidError(err error) bool {
 	if err == nil {
 		return false
 	}
+	if isModelSupportError(err) {
+		return false
+	}
 	status := statusCodeFromError(err)
 	switch status {
 	case http.StatusBadRequest: