diff --git a/agent_v0/server_v1/api_stream.py b/agent_v0/server_v1/api_stream.py
index 33f713d92..83bcf68e5 100644
--- a/agent_v0/server_v1/api_stream.py
+++ b/agent_v0/server_v1/api_stream.py
@@ -5230,8 +5230,10 @@ def _resolve_target_sync(
         # ---------------------------------------------------------------
         by_text_source = target_spec.get("by_text_source", "")
 
-        if by_text_strict and by_text_source in ("ocr", "vlm"):
-            # Texte visible (OCR ou lu par gemma4) → grounding VLM direct
+        has_window = bool(target_spec.get("window_capture", {}).get("rect"))
+
+        if by_text_strict and by_text_source in ("ocr", "vlm") and has_window:
+            # Texte visible DANS une fenêtre → grounding VLM sur fenêtre croppée
             grounding_result = _resolve_by_grounding(
                 screenshot_path=screenshot_path,
                 target_spec=target_spec,