test: add hallucination benchmark and enforce strict guard for structural targets

GramAddict/core/perception/intent_resolver.py

@@ -72,6 +72,16 @@ class IntentResolver:
         if intent_lower in abstract_goals:
             return None
 
+        # --- Strict VLM Hallucination Guard ---
+        # For known structural targets that the VLM frequently hallucinates when they are missing,
+        # we enforce a strict failure if they weren't caught by the structural fast paths.
+        if "following list" in intent_lower or "followers list" in intent_lower or "tap message button" in intent_lower:
+            logger.warning(
+                f"🛡️ [Hallucination Guard] Intent '{intent_description}' is a strict structural target. "
+                "Since it wasn't resolved by fast-paths, it is missing. Rejecting VLM fallback."
+            )
+            return None
+
         # ── PRIMARY PATH: Visual Discovery ──
         # If we have a device, the VLM SEES the screen and decides.
         if device: