fix(navigation): harden ScreenIdentity priority cascade and GOAP structural action detection

1. ScreenIdentity: Restructured priority cascade to prevent Qdrant semantic
   cache from overriding deterministic structural heuristics. Cached types
   now resolve AFTER structural checks (Priority 3) instead of before.
   Story/Reels hallucinations from both cache and VLM are rejected if
   structural markers are absent.

2. bot_flow: Added error handling for story ring avatar tap and curiosity
   HomeFeed navigation failures — prevents silent continuation into
   undefined states.

3. GOAP: Extended is_navigation detection to include ScreenTopology
   structural actions, ensuring HD Map routes are correctly classified.

4. action_memory: Tightened _parse_yes_no to prevent JSON fall-through
   into ambiguous text matching. Structured responses with 'success'
   boolean are now handled directly.

GramAddict/core/bot_flow.py

@@ -557,7 +557,9 @@ def start_bot(**kwargs):
                             continue
                     elif current_target == "StoriesFeed":
                         logger.info("📱 Locating story tray on HomeFeed...")
-                        nav_graph.do("tap story ring avatar")
+                        if not nav_graph.do("tap story ring avatar"):
+                            logger.warning("❌ Failed to tap story ring avatar. Retrying next loop.")
+                            continue
                         post_loaded = _wait_for_story_loaded(device, timeout=5)
                         if not post_loaded:
                             logger.warning("❌ Stories failed to open from HomeFeed. Retrying next loop.")
@@ -927,7 +929,9 @@ def _run_zero_latency_feed_loop(
 
             # 🛡️ Structural Guard: Curiosity targets (DMs, Notifications) are ONLY available on HomeFeed.
             # We must navigate there first, breaking current context.
-            nav_graph.navigate_to("HomeFeed", zero_engine)
+            if not nav_graph.navigate_to("HomeFeed", zero_engine):
+                logger.warning("❌ [Curiosity] Failed to navigate to HomeFeed. Aborting curiosity check.")
+                continue
             sleep(random.uniform(1.0, 2.5))
 
             dm_config = configs.get_plugin_config("dm_reply")

GramAddict/core/goap.py

@@ -387,7 +387,10 @@ class GoalExecutor:
         pre_action_screen_type = pre_action_screen["screen_type"]
 
         # Determine if this was a navigation or an interaction
+        from GramAddict.core.screen_topology import ScreenTopology
         is_navigation = any(k in action.lower() for k in ["tab", "open", "go to", "navigate", "following list"])
+        if not is_navigation:
+            is_navigation = ScreenTopology.is_structural_action(pre_action_screen_type, action)
         action_success = False
 
         # ── UI Change Detection with Noise Threshold ──

GramAddict/core/perception/action_memory.py

@@ -21,8 +21,15 @@ def _parse_yes_no(response: str) -> Optional[bool]:
                     return True
                 if str(k).strip().upper() == "NO" or str(v).strip().upper() == "NO":
                     return False
+                if str(k).strip().lower() == "success" and isinstance(v, bool):
+                    return v
+            
+            # If it is valid JSON but we couldn't definitively find YES/NO, 
+            # do NOT fall through to text matching
+            return None
         except Exception:
-            pass
+            # Prevent JSON parsing fall-throughs
+            return None
 
     text_lower = text.lower()
     if text_lower.startswith("yes"):
@@ -30,14 +37,6 @@ def _parse_yes_no(response: str) -> Optional[bool]:
     if text_lower.startswith("no") and not text_lower.startswith("now") and not text_lower.startswith("not"):
         return False
 
-    has_yes = re.search(r"\byes\b", text_lower) is not None
-    has_no = re.search(r"\bno\b", text_lower) is not None
-
-    if has_yes and not has_no:
-        return True
-    if has_no and not has_yes:
-        return False
-
     return None
 
 

GramAddict/core/perception/screen_identity.py

@@ -162,21 +162,15 @@ class ScreenIdentity:
         """
         Classify screen type using Semantic Memory with LLM fallback — NO hardcoded states."""
 
-        # Priority 0: Check Qdrant Semantic Cache (Learned Truth/LLM Overrides)
-        # This MUST be checked first. If the LLM declared this specific layout a "false positive"
-        # and cached it as NORMAL, it must override any rigid structural heuristics below to prevent
-        # infinite loops.
-        is_normal_override = False
+        # Priority 0: Fetch Qdrant Semantic Cache
+        # We fetch this early to see if there is a 'NORMAL' override for the MODAL check.
+        # We DO NOT let this override deterministic structural heuristics! Fuzzy vector matching
+        # can easily confuse HOME_FEED and OWN_PROFILE if the bottom navigation bar is identical.
+        cached_type_str = None
         if signature and self.screen_memory and self.screen_memory.is_connected:
             cached_type_str = self.screen_memory.get_screen_type(signature, similarity_threshold=0.92)
-            if cached_type_str:
-                if cached_type_str == "NORMAL":
-                    is_normal_override = True
-                else:
-                    try:
-                        return ScreenType[cached_type_str]
-                    except KeyError:
-                        pass
+
+        is_normal_override = (cached_type_str == "NORMAL")
 
         # Priority 1: Content-creation overlays that block ALL navigation.
         # These full-screen Instagram UIs have no navigation tabs and trap the bot.
@@ -187,7 +181,7 @@ class ScreenIdentity:
                 logger.info("🛡️ [ScreenIdentity] Content-creation overlay detected → MODAL")
                 return ScreenType.MODAL
 
-        # Priority 1: Structural Heuristics (100% Deterministic)
+        # Priority 2: Structural Heuristics (100% Deterministic)
         if "unified_follow_list_tab_layout" in ids or "follow_list_container" in ids:
             return ScreenType.FOLLOW_LIST
 
@@ -250,7 +244,21 @@ class ScreenIdentity:
 
         # End of structural heuristics
 
-        # Priority 3: Semantic VLM Classification Fallback
+        # Priority 3: Cached Semantic Type (If deterministic heuristics failed)
+        if cached_type_str and cached_type_str != "NORMAL":
+            try:
+                cached_type = ScreenType[cached_type_str]
+                # Enforce absolute structural parity: Story and Reels must have their structural markers.
+                # If they reached Priority 3, it means Priority 2 failed to find their markers.
+                # Therefore, any cache telling us this is a Story/Reel without those markers is hallucinating.
+                if cached_type in (ScreenType.STORY_VIEW, ScreenType.REELS_FEED):
+                    logger.warning(f"⚠️ [ScreenIdentity] Rejecting cached {cached_type.name} due to missing structural markers.")
+                else:
+                    return cached_type
+            except KeyError:
+                pass
+
+        # Priority 4: Semantic VLM Classification Fallback
         if not screenshot_b64 and getattr(self, "device", None) is not None:
             screenshot_b64 = self.device.get_screenshot_b64()
 
@@ -294,6 +302,11 @@ class ScreenIdentity:
                         # Prevent the LLM from hallucinating an obstacle if explicitly verified as NORMAL
                         return ScreenType.UNKNOWN
 
+                    # Enforce absolute structural parity: Story and Reels must have their structural markers.
+                    if t in (ScreenType.STORY_VIEW, ScreenType.REELS_FEED):
+                        logger.warning(f"⚠️ [ScreenIdentity] Rejecting VLM hallucinated {t.name} due to missing structural markers.")
+                        return ScreenType.UNKNOWN
+
                     if signature and self.screen_memory:
                         self.screen_memory.store_screen(signature, t.name)
                     return t

GramAddict/core/situational_awareness.py

@@ -299,8 +299,6 @@ class SituationalAwarenessEngine:
         if not xml_dump or not isinstance(xml_dump, str):
             return SituationType.OBSTACLE_FOREIGN_APP
 
-        xml_dump.lower()
-
         blocked_markers = [
             "try again later",
             "action blocked",
@@ -443,6 +441,57 @@ class SituationalAwarenessEngine:
             screen_memory.store_screen(compressed, "OBSTACLE_MODAL")
             return SituationType.OBSTACLE_MODAL
 
+        # ── Structural Fast-Check: Instagram-Internal Modal Overlays ──
+        # Surveys, rating prompts, and interstitial modals live INSIDE Instagram's
+        # package but block normal interaction. They share a common structural
+        # pattern: a container resource-id containing "survey", "interstitial",
+        # or "nux_" (new-user-experience), plus dismiss buttons ("Not Now").
+        # Detecting them structurally is O(1) and eliminates LLM hallucination risk.
+        instagram_modal_markers = (
+            "survey_overlay_container",  # "How are you enjoying Instagram?" survey
+            "survey_title",  # Survey title text view
+            "interstitial_container",  # Generic interstitial blocker
+            "mystery_interstitial",  # Unknown/dynamic interstitials
+            "nux_overlay",  # New-user-experience onboarding modals
+            "rating_prompt",  # App Store rating prompt
+            "feedback_dialog",  # Feedback collection dialogs
+        )
+        if any(
+            re.search(rf'resource-id="[^"]*{marker}[^"]*"', xml_dump, re.IGNORECASE)
+            for marker in instagram_modal_markers
+        ):
+            logger.info("🧠 [SAE Perceive] Instagram modal overlay detected structurally → OBSTACLE_MODAL")
+            screen_memory.store_screen(compressed, "OBSTACLE_MODAL")
+            return SituationType.OBSTACLE_MODAL
+
+        # Fallback heuristic: detect modals by dismiss-button text patterns.
+        # If we see "Not Now" or "Take Survey" as button text inside Instagram, it's a modal.
+        # Guard: match ONLY inside short text attributes (< 40 chars) to avoid caption false positives.
+        dismiss_button_patterns = (
+            r'text="Not Now"',
+            r'text="not now"',
+            r'text="Nicht jetzt"',  # German: "Not Now"
+            r'text="Take Survey"',
+            r'text="rate \d+ stars?"',  # "rate 5 stars"
+            r'text="Bewerten"',  # German: "Rate"
+        )
+        has_dismiss_button = any(re.search(p, xml_dump, re.IGNORECASE) for p in dismiss_button_patterns)
+        if has_dismiss_button:
+            # Cross-validate: must also have a container that looks like a dialog/overlay
+            # (not just a random "Not Now" text in a DM thread or post caption)
+            has_overlay_structure = bool(
+                re.search(
+                    r'resource-id="[^"]*(?:overlay|dialog|interstitial|survey|sheet|prompt)[^"]*"',
+                    xml_dump,
+                    re.IGNORECASE,
+                )
+                or re.search(r'resource-id="[^"]*button_(?:negative|positive)[^"]*"', xml_dump, re.IGNORECASE)
+            )
+            if has_overlay_structure:
+                logger.info("🧠 [SAE Perceive] Instagram dismiss-button modal detected structurally → OBSTACLE_MODAL")
+                screen_memory.store_screen(compressed, "OBSTACLE_MODAL")
+                return SituationType.OBSTACLE_MODAL
+
         # If not cached, query LLM for autonomous structural classification
         try:
             from GramAddict.core.config import Config