Merge pull request #2346 from pjpjq/codex/fix-codex-capacity-retry

fix(codex): Treat Codex capacity errors as retryable

internal/runtime/executor/codex_executor.go

@@ -685,13 +685,39 @@ func applyCodexHeaders(r *http.Request, auth *cliproxyauth.Auth, token string, s
 }
 
 func newCodexStatusErr(statusCode int, body []byte) statusErr {
-	err := statusErr{code: statusCode, msg: string(body)}
+	errCode := statusCode
-	if retryAfter := parseCodexRetryAfter(statusCode, body, time.Now()); retryAfter != nil {
+	if isCodexModelCapacityError(body) {
+		errCode = http.StatusTooManyRequests
+	}
+	err := statusErr{code: errCode, msg: string(body)}
+	if retryAfter := parseCodexRetryAfter(errCode, body, time.Now()); retryAfter != nil {
 		err.retryAfter = retryAfter
 	}
 	return err
 }
 
+func isCodexModelCapacityError(errorBody []byte) bool {
+	if len(errorBody) == 0 {
+		return false
+	}
+	candidates := []string{
+		gjson.GetBytes(errorBody, "error.message").String(),
+		gjson.GetBytes(errorBody, "message").String(),
+		string(errorBody),
+	}
+	for _, candidate := range candidates {
+		lower := strings.ToLower(strings.TrimSpace(candidate))
+		if lower == "" {
+			continue
+		}
+		if strings.Contains(lower, "selected model is at capacity") ||
+			strings.Contains(lower, "model is at capacity. please try a different model") {
+			return true
+		}
+	}
+	return false
+}
+
 func parseCodexRetryAfter(statusCode int, errorBody []byte, now time.Time) *time.Duration {
 	if statusCode != http.StatusTooManyRequests || len(errorBody) == 0 {
 		return nil

internal/runtime/executor/codex_executor_retry_test.go

@@ -60,6 +60,19 @@ func TestParseCodexRetryAfter(t *testing.T) {
 	})
 }
 
+func TestNewCodexStatusErrTreatsCapacityAsRetryableRateLimit(t *testing.T) {
+	body := []byte(`{"error":{"message":"Selected model is at capacity. Please try a different model."}}`)
+
+	err := newCodexStatusErr(http.StatusBadRequest, body)
+
+	if got := err.StatusCode(); got != http.StatusTooManyRequests {
+		t.Fatalf("status code = %d, want %d", got, http.StatusTooManyRequests)
+	}
+	if err.RetryAfter() != nil {
+		t.Fatalf("expected nil explicit retryAfter for capacity fallback, got %v", *err.RetryAfter())
+	}
+}
+
 func itoa(v int64) string {
 	return strconv.FormatInt(v, 10)
 }