feat(navigation): add structural identity and transitions for NOTIFICATIONS trap

2026-05-05 13:05:46 +02:00
parent 5ca5777c4b
commit b626dc6488
7 changed files with 104 additions and 7 deletions
--- a/GramAddict/core/perception/screen_identity.py
+++ b/GramAddict/core/perception/screen_identity.py
@@ -23,6 +23,7 @@ class ScreenType(Enum):
    COMMENTS = "comments"
    MODAL = "modal"
    FOREIGN_APP = "foreign_app"
+    NOTIFICATIONS = "notifications"
    UNKNOWN = "unknown"


@@ -94,7 +95,14 @@ class ScreenIdentity:
                resource_ids.add(short_id)

                # Track which tab is selected
-                if selected and short_id in ("feed_tab", "search_tab", "clips_tab", "profile_tab", "direct_tab"):
+                if selected and short_id in (
+                    "feed_tab",
+                    "search_tab",
+                    "clips_tab",
+                    "profile_tab",
+                    "direct_tab",
+                    "news_tab",
+                ):
                    selected_tab = short_id

            if text:
@@ -180,7 +188,15 @@ class ScreenIdentity:
        # Structural detection is O(1), zero LLM calls, and cannot be fooled.
        # EXCEPTION: If Qdrant has explicitly learned this screen as NORMAL (via LLM unlearning),
        # we skip the structural check to prevent false-positive infinite loops.
-        creation_flow_markers = ("quick_capture", "gallery_cancel_button", "creation_flow", "reel_camera")
+        creation_flow_markers = (
+            "quick_capture",
+            "gallery_cancel_button",
+            "creation_flow",
+            "reel_camera",
+            "gallery_grid_item_thumbnail",
+            "camera_cancel_button",
+            "next_button_textview",
+        )
        browser_markers = ("ig_browser_text_title", "ig_browser_close_button", "ig_chrome_subsection")
        if not is_normal_override and any(marker in ids_str for marker in creation_flow_markers):
            logger.info("🛡️ [ScreenIdentity] Content-creation overlay detected → MODAL")
@@ -239,6 +255,11 @@ class ScreenIdentity:
        if any(marker in ids for marker in STORY_MARKERS):
            return ScreenType.STORY_VIEW

+        # Notifications / Activity structural markers
+        NOTIFICATIONS_MARKERS = ("row_newsfeed_text", "newsfeed_tab", "newsfeed_user_imageview")
+        if any(marker in ids for marker in NOTIFICATIONS_MARKERS) or selected_tab == "news_tab":
+            return ScreenType.NOTIFICATIONS
+
        # DM thread detection — Structural markers (header and input fields)
        if "direct_thread_header" in ids or "direct_text_input" in ids or "message_composer_container" in ids:
            return ScreenType.DM_THREAD
@@ -357,6 +378,7 @@ class ScreenIdentity:
            "clips_tab": "tap reels tab",
            "profile_tab": "tap profile tab",
            "direct_tab": "tap messages tab",
+            "news_tab": "tap activity heart icon notifications",
        }
        for tab_id, action in tab_map.items():
            if tab_id in resource_ids:
--- a/GramAddict/core/screen_topology.py
+++ b/GramAddict/core/screen_topology.py
@@ -33,6 +33,7 @@ class ScreenTopology:
            "tap profile tab": ScreenType.OWN_PROFILE,
            "tap reels tab": ScreenType.REELS_FEED,
            "tap messages tab": ScreenType.DM_INBOX,
+            "tap activity heart icon notifications": ScreenType.NOTIFICATIONS,
            "tap story ring avatar": ScreenType.STORY_VIEW,
        },
        ScreenType.EXPLORE_GRID: {
@@ -84,6 +85,12 @@ class ScreenTopology:
            "tap home tab": ScreenType.HOME_FEED,
            # NOTE: 'press back' intentionally omitted — destination is non-deterministic
        },
+        ScreenType.NOTIFICATIONS: {
+            "tap home tab": ScreenType.HOME_FEED,
+            "press back": ScreenType.HOME_FEED,
+            "tap profile tab": ScreenType.OWN_PROFILE,
+            "tap explore tab": ScreenType.EXPLORE_GRID,
+        },
        ScreenType.UNKNOWN: {
            "tap home tab": ScreenType.HOME_FEED,
        },
@@ -110,6 +117,7 @@ class ScreenTopology:
        "open user profile": ScreenType.OTHER_PROFILE,
        "open search": ScreenType.SEARCH_RESULTS,
        "view comments": ScreenType.COMMENTS,
+        "open notifications": ScreenType.NOTIFICATIONS,
    }

    @classmethod
--- a/GramAddict/core/telepathic_engine.py
+++ b/GramAddict/core/telepathic_engine.py
@@ -253,9 +253,12 @@ class TelepathicEngine:
        # ZERO-TRUST: NO LOCALIZED STRINGS.
        res_id = (node.resource_id or "").lower()

-        # Avoid clicking on audio/trending/camera elements unless explicitly requested
-        if any(trap in res_id for trap in ["album_art", "use_in_camera", "trending", "audio"]):
-            if not any(word in intent for word in ["audio", "trending", "camera"]):
+        # Avoid clicking on audio/trending/camera/creation elements unless explicitly requested
+        if any(
+            trap in res_id
+            for trap in ["album_art", "use_in_camera", "trending", "audio", "creation", "camera", "gallery"]
+        ):
+            if not any(word in intent for word in ["audio", "trending", "camera", "create", "gallery"]):
                return False

        # Avoid clicking share, save, menu, options unless explicitly requested
--- a/tests/tdd/test_context_gate_matrix.py
+++ b/tests/tdd/test_context_gate_matrix.py
@@ -141,6 +141,7 @@ class TestScreenTopologyBackTransitions:
                    ScreenType.FOLLOW_LIST,
                    ScreenType.STORY_VIEW,
                    ScreenType.COMMENTS,
+                    ScreenType.NOTIFICATIONS,
                ):
                    # These are "leaf" screens with a deterministic parent — OK to keep
                    continue
--- a/tests/tdd/test_gallery_trap_guard.py
+++ b/tests/tdd/test_gallery_trap_guard.py
@@ -0,0 +1,39 @@
+from GramAddict.core.perception.screen_identity import ScreenIdentity, ScreenType
+
+
+def test_gallery_screen_is_modal():
+    """
+    Test that the Gallery/New Post screen is correctly identified as a MODAL,
+    preventing it from being hallucinated as POST_DETAIL or HOME_FEED.
+    """
+    xml_dump = """<?xml version='1.0' encoding='UTF-8' standalone='yes' ?>
+<hierarchy rotation="0">
+  <node index="0" text="" resource-id="" class="android.widget.FrameLayout" package="com.instagram.android" bounds="[0,0][1080,2400]">
+    <node index="0" text="New post" resource-id="" class="android.widget.TextView" bounds="[0,0][100,100]" />
+    <node index="1" text="" resource-id="com.instagram.android:id/gallery_grid_item_thumbnail" class="android.widget.Button" content-desc="Selected media number 1 Photo thumbnail created on 3 May 2026 10:30" bounds="[0,100][500,600]" />
+    <node index="2" text="" resource-id="com.instagram.android:id/next_button_textview" class="android.widget.Button" content-desc="Next" bounds="[900,0][1080,100]" />
+  </node>
+</hierarchy>
+"""
+    identity = ScreenIdentity("bot_user")
+    result = identity.identify(xml_dump)
+
+    assert result["screen_type"] == ScreenType.MODAL
+
+
+def test_camera_screen_is_modal():
+    """
+    Test that the Camera creation screen is correctly identified as a MODAL.
+    """
+    xml_dump = """<?xml version='1.0' encoding='UTF-8' standalone='yes' ?>
+<hierarchy rotation="0">
+  <node index="0" text="" resource-id="" class="android.widget.FrameLayout" package="com.instagram.android" bounds="[0,0][1080,2400]">
+    <node index="0" text="" resource-id="com.instagram.android:id/camera_cancel_button" class="android.widget.ImageView" bounds="[0,0][100,100]" />
+    <node index="1" text="" resource-id="com.instagram.android:id/quick_capture" class="android.widget.FrameLayout" bounds="[0,100][1080,2400]" />
+  </node>
+</hierarchy>
+"""
+    identity = ScreenIdentity("bot_user")
+    result = identity.identify(xml_dump)
+
+    assert result["screen_type"] == ScreenType.MODAL
--- a/tests/tdd/test_notifications_screen.py
+++ b/tests/tdd/test_notifications_screen.py
@@ -0,0 +1,22 @@
+from GramAddict.core.perception.screen_identity import ScreenIdentity, ScreenType
+
+
+def test_notifications_screen_identification():
+    """
+    Test that the Notifications/Activity screen is correctly identified,
+    preventing it from being hallucinated as POST_DETAIL.
+    """
+    xml_dump = """<?xml version='1.0' encoding='UTF-8' standalone='yes' ?>
+<hierarchy rotation="0">
+  <node index="0" text="" resource-id="" class="android.widget.FrameLayout" package="com.instagram.android" bounds="[0,0][1080,2400]">
+    <node index="0" text="Notifications" resource-id="com.instagram.android:id/action_bar_title" class="android.widget.TextView" bounds="[0,0][1080,100]" />
+    <node index="1" text="User liked your photo." resource-id="com.instagram.android:id/row_newsfeed_text" class="android.widget.TextView" bounds="[100,100][1000,200]" />
+    <node index="2" text="" resource-id="com.instagram.android:id/newsfeed_tab" selected="true" class="android.widget.FrameLayout" bounds="[600,2300][800,2400]" />
+  </node>
+</hierarchy>
+"""
+    identity = ScreenIdentity("bot_user")
+    result = identity.identify(xml_dump)
+
+    assert result["screen_type"] == ScreenType.NOTIFICATIONS
+    assert "tap home tab" in result["available_actions"] or "press back" in result["available_actions"]
--- a/tests/tdd/test_obstacle_keyboard.py
+++ b/tests/tdd/test_obstacle_keyboard.py
@@ -28,7 +28,8 @@ def test_sae_detects_obstacle_keyboard():
    xml_with_keyboard = """<?xml version='1.0' encoding='UTF-8' standalone='yes' ?>
    <hierarchy rotation="0">
      <node index="0" package="com.instagram.android" resource-id="" text="" content-desc="" />
-      <node index="1" package="com.google.android.inputmethod.latin" resource-id="com.google.android.inputmethod.latin:id/keyboard_view" text="" content-desc="Keyboard" />
+      <node index="1" class="android.widget.EditText" focused="true" />
+      <node index="2" package="com.google.android.inputmethod.latin" resource-id="com.google.android.inputmethod.latin:id/keyboard_view" text="" content-desc="Keyboard" />
    </hierarchy>
    """

@@ -45,7 +46,8 @@ def test_obstacle_guard_dismisses_keyboard():
    xml_with_keyboard = """<?xml version='1.0' encoding='UTF-8' standalone='yes' ?>
    <hierarchy rotation="0">
      <node index="0" package="com.instagram.android" resource-id="" text="" content-desc="" />
-      <node index="1" package="com.google.android.inputmethod.latin" resource-id="com.google.android.inputmethod.latin:id/keyboard_view" text="" content-desc="Keyboard" />
+      <node index="1" class="android.widget.EditText" focused="true" />
+      <node index="2" package="com.google.android.inputmethod.latin" resource-id="com.google.android.inputmethod.latin:id/keyboard_view" text="" content-desc="Keyboard" />
    </hierarchy>
    """