diff --git a/.github/workflows/strix.yml b/.github/workflows/strix.yml
index 73298c6e9..908696144 100644
--- a/.github/workflows/strix.yml
+++ b/.github/workflows/strix.yml
@@ -173,6 +173,7 @@ jobs:
           STRIX_MEMORY_COMPRESSOR_TIMEOUT: 10
           STRIX_TRANSIENT_RETRY_PER_MODEL: 2
           STRIX_TRANSIENT_RETRY_BACKOFF_SECONDS: 3
+          STRIX_FALLBACK_MODELS: ${{ secrets.STRIX_FALLBACK_MODELS || 'openai/gpt-5.4-fallback openai/gpt-5.4-turbo' }}
           STRIX_PROCESS_TIMEOUT_SECONDS: ${{ github.event_name == 'pull_request_target' && '1200' || '2400' }}
           STRIX_TOTAL_TIMEOUT_SECONDS: 4800
           STRIX_PR_SCOPE_MAX_FILES_PER_BATCH: 12
diff --git a/scripts/ci/strix_quick_gate.sh b/scripts/ci/strix_quick_gate.sh
index af02d58a3..ce49db4ca 100644
--- a/scripts/ci/strix_quick_gate.sh
+++ b/scripts/ci/strix_quick_gate.sh
@@ -2045,9 +2045,6 @@ is_llm_service_unavailable_error() {
 is_transient_same_model_retry_error() {
 	local model="${1-}"
 	if is_timeout_error; then
-		if [ -n "$model" ] && ! is_vertex_model "$model"; then
-			return 0
-		fi
 		return 1
 	fi
 	if is_llm_api_connection_error; then