test(perception): add strict TDD suite for autonomous ad marker learning and verification

tests/unit/test_autonomous_ad_learning.py

@@ -0,0 +1,49 @@
+import pytest
+import os
+import json
+from GramAddict.core.utils import is_ad, learn_ad_marker, get_learned_ad_markers
+
+@pytest.fixture(autouse=True)
+def clean_ad_markers():
+    # Clean up any existing learned markers file before and after tests
+    file_path = os.path.join(os.getcwd(), "learned_ad_markers.json")
+    if os.path.exists(file_path):
+        os.remove(file_path)
+    import GramAddict.core.utils
+    GramAddict.core.utils._LEARNED_AD_MARKERS_CACHE = None
+    yield
+    if os.path.exists(file_path):
+        os.remove(file_path)
+    GramAddict.core.utils._LEARNED_AD_MARKERS_CACHE = None
+
+def test_learn_ad_marker_validates_against_xml():
+    xml_dump = """<?xml version="1.0" encoding="utf-8"?>
+    <hierarchy>
+        <node class="android.widget.TextView" text="Sponsorisé" resource-id="com.instagram.android:id/some_id" content-desc=""/>
+    </hierarchy>
+    """
+    
+    # Attempt to learn a hallucinated marker
+    learn_ad_marker("Hallucination", xml_dump)
+    assert "hallucination" not in get_learned_ad_markers()
+    
+    # Attempt to learn an actual marker present in XML
+    learn_ad_marker("Sponsorisé", xml_dump)
+    assert "sponsorisé" in get_learned_ad_markers()
+
+def test_is_ad_uses_learned_markers():
+    xml_dump = """<?xml version="1.0" encoding="utf-8"?>
+    <hierarchy>
+        <node class="android.widget.TextView" text="Sponsorisé" resource-id="com.instagram.android:id/some_id" content-desc=""/>
+        <node resource-id="row_feed_photo_profile_name" text="someone" />
+    </hierarchy>
+    """
+    
+    # Initially, it shouldn't recognize "Sponsorisé" because it's not in the hardcoded list
+    assert is_ad(xml_dump) is False
+    
+    # Learn the new marker
+    learn_ad_marker("Sponsorisé", xml_dump)
+    
+    # Now, is_ad should return True immediately without VLM
+    assert is_ad(xml_dump) is True