Hardened E2E integrity, purged synthetic mocks, and implemented proactive device discovery.
This commit is contained in:
@@ -36,15 +36,38 @@ def create_device(device_id, app_id, args=None):
|
||||
try:
|
||||
return DeviceFacade(device_id, app_id, args)
|
||||
except Exception as e:
|
||||
str(e)
|
||||
err_msg = str(e)
|
||||
err_type = str(type(e))
|
||||
if (
|
||||
"ConnectError" in err_type
|
||||
or "ConnectionRefusedError" in err_type
|
||||
or "ConnectionError" in err_type
|
||||
or "Timeout" in err_type
|
||||
if any(
|
||||
keyword in err_type or keyword in err_msg
|
||||
for keyword in ["ConnectError", "ConnectionRefused", "ConnectionError", "Timeout"]
|
||||
):
|
||||
logger.error(f"⚠️ [ADB ConnectError] Could not connect to device '{device_id}'.")
|
||||
|
||||
# Proactive Discovery
|
||||
try:
|
||||
import subprocess
|
||||
|
||||
result = subprocess.run(["adb", "devices"], capture_output=True, text=True, timeout=2)
|
||||
lines = [
|
||||
line.strip()
|
||||
for line in result.stdout.split("\n")
|
||||
if line.strip() and not line.startswith("List of devices")
|
||||
]
|
||||
devices = [line.split("\t")[0] for line in lines if "device" in line]
|
||||
|
||||
if devices:
|
||||
logger.info("🔍 Proactive Discovery: I found the following devices connected:")
|
||||
for d in devices:
|
||||
if d.split(":")[0] == device_id.split(":")[0]:
|
||||
logger.info(f" 👉 {d} (MATCHING IP - Is this the same device with a different port?)")
|
||||
else:
|
||||
logger.info(f" - {d}")
|
||||
else:
|
||||
logger.warning("🔍 Proactive Discovery: No ADB devices found. Is your phone authorized?")
|
||||
except Exception as discovery_err:
|
||||
logger.debug(f"Proactive discovery failed: {discovery_err}")
|
||||
|
||||
logger.error("👉 Please verify:")
|
||||
logger.error(" 1. Your phone is connected via USB or Wi-Fi.")
|
||||
logger.error(" 2. 'USB Debugging' is enabled in Developer Options.")
|
||||
@@ -359,6 +382,8 @@ class DeviceFacade:
|
||||
from io import BytesIO
|
||||
|
||||
img = self.deviceV2.screenshot()
|
||||
if img is None:
|
||||
return None
|
||||
buffered = BytesIO()
|
||||
img.save(buffered, format="JPEG", quality=70) # Compressed for target latency
|
||||
return base64.b64encode(buffered.getvalue()).decode("utf-8")
|
||||
|
||||
@@ -73,7 +73,7 @@ class ActionMemory:
|
||||
|
||||
logger.info(
|
||||
f"✅ [ActionMemory] Confirming success for '{ctx['intent']}'. Boosting confidence.",
|
||||
extra={"color": "\x1b[32m"}
|
||||
extra={"color": "\x1b[32m"},
|
||||
)
|
||||
|
||||
# Store or boost in Qdrant
|
||||
@@ -99,8 +99,7 @@ class ActionMemory:
|
||||
return
|
||||
|
||||
logger.warning(
|
||||
f"❌ [ActionMemory] Click failed for '{ctx['intent']}'. Applying penalty.",
|
||||
extra={"color": "\x1b[31m"}
|
||||
f"❌ [ActionMemory] Click failed for '{ctx['intent']}'. Applying penalty.", extra={"color": "\x1b[31m"}
|
||||
)
|
||||
|
||||
try:
|
||||
@@ -121,9 +120,17 @@ class ActionMemory:
|
||||
|
||||
# Specific check for opening a post (from explore/profile grid)
|
||||
if "view a post" in intent_lower or "first image" in intent_lower or "grid item" in intent_lower:
|
||||
if "row_feed_photo_imageview" in post_xml_lower or "row_feed_button_like" in post_xml_lower or "clips_viewer_view_pager" in post_xml_lower:
|
||||
if (
|
||||
"row_feed_photo_imageview" in post_xml_lower
|
||||
or "row_feed_button_like" in post_xml_lower
|
||||
or "clips_viewer_view_pager" in post_xml_lower
|
||||
):
|
||||
return True
|
||||
if "explore_action_bar" in post_xml_lower and "row_feed_button_like" not in post_xml_lower and "clips_viewer" not in post_xml_lower:
|
||||
if (
|
||||
"explore_action_bar" in post_xml_lower
|
||||
and "row_feed_button_like" not in post_xml_lower
|
||||
and "clips_viewer" not in post_xml_lower
|
||||
):
|
||||
return None # Still on grid, inconclusive
|
||||
|
||||
state_toggles = ["like", "save", "follow", "heart"]
|
||||
@@ -178,6 +185,8 @@ class ActionMemory:
|
||||
|
||||
try:
|
||||
screenshot = device.get_screenshot_b64()
|
||||
if not screenshot:
|
||||
raise ValueError("No screenshot available from device")
|
||||
response = evaluator._query_vlm(prompt, screenshot)
|
||||
|
||||
if response and "yes" in response.lower() and "no" not in response.lower():
|
||||
@@ -202,7 +211,9 @@ class ActionMemory:
|
||||
return False
|
||||
|
||||
# Fallback to structural delta
|
||||
logger.info(f"DEBUG: len(pre_click_xml)={len(pre_click_xml)} len(post_click_xml)={len(post_click_xml)}")
|
||||
diff = abs(len(pre_click_xml) - len(post_click_xml))
|
||||
logger.info(f"DEBUG: diff={diff}")
|
||||
|
||||
if is_toggle:
|
||||
if diff > 1000:
|
||||
@@ -222,7 +233,13 @@ class ActionMemory:
|
||||
from GramAddict.core.screen_topology import ScreenTopology
|
||||
|
||||
# We don't have screen type here, so we just check if it's in the HD Map keys
|
||||
logger.info(f"DEBUG: intent is '{intent}'")
|
||||
logger.info(
|
||||
f"DEBUG: TRANSITIONS keys are: {[list(t.keys()) for t in ScreenTopology.TRANSITIONS.values()]}"
|
||||
)
|
||||
is_standard = any(intent in transitions for transitions in ScreenTopology.TRANSITIONS.values())
|
||||
logger.info(f"DEBUG: is_standard={is_standard}")
|
||||
|
||||
if is_standard:
|
||||
logger.debug(
|
||||
f"🧠 [ActionMemory] Structural change detected for known navigation '{intent}'. Verification PASS."
|
||||
|
||||
@@ -53,13 +53,47 @@ class IntentResolver:
|
||||
if intent_lower in abstract_goals:
|
||||
return None
|
||||
|
||||
# --- Semantic Match Guard ---
|
||||
# If the intent explicitly quotes a target (e.g., "tap 'New Message'"),
|
||||
# we strictly filter candidates to those whose text or content_desc contains the quote.
|
||||
import re
|
||||
|
||||
quotes = re.findall(r"['\"](.*?)['\"]", intent_description)
|
||||
if quotes:
|
||||
target_text = quotes[0].lower()
|
||||
pattern = r"\b" + re.escape(target_text) + r"\b"
|
||||
semantic_candidates = []
|
||||
for node in candidates:
|
||||
n_text = (node.text or "").lower()
|
||||
n_desc = (node.content_desc or "").lower()
|
||||
if re.search(pattern, n_text) or re.search(pattern, n_desc):
|
||||
semantic_candidates.append(node)
|
||||
|
||||
if semantic_candidates:
|
||||
if len(semantic_candidates) == 1:
|
||||
logger.info(f"🎯 [Semantic Guard] Exact match found for '{target_text}', skipping VLM.")
|
||||
return semantic_candidates[0]
|
||||
else:
|
||||
logger.info(
|
||||
f"🎯 [Semantic Guard] {len(semantic_candidates)} matches found for '{target_text}'. Reducing candidates for VLM."
|
||||
)
|
||||
candidates = semantic_candidates
|
||||
else:
|
||||
logger.warning(
|
||||
f"⚠️ [Semantic Guard] No candidates found containing '{target_text}'. Returning None to prevent hallucination."
|
||||
)
|
||||
return None
|
||||
|
||||
# ── PRIMARY PATH: Visual Discovery ──
|
||||
# If we have a device, the VLM SEES the screen and decides.
|
||||
if device is not None and (
|
||||
hasattr(device, "screenshot") or hasattr(getattr(device, "deviceV2", None), "screenshot")
|
||||
):
|
||||
logger.info("📸 Device screenshot capability detected. Enforcing visual discovery.")
|
||||
return self._visual_discovery(intent_description, candidates, device)
|
||||
visual_res = self._visual_discovery(intent_description, candidates, device)
|
||||
if visual_res is not None:
|
||||
return visual_res
|
||||
logger.warning("👁️ [IntentResolver] Visual discovery yielded None. Falling back to text-based resolution.")
|
||||
|
||||
# --- Strict VLM Hallucination Guard (Text-only Fallback) ---
|
||||
# For known structural targets that the text-based VLM frequently hallucinates when they are missing,
|
||||
@@ -254,37 +288,6 @@ class IntentResolver:
|
||||
logger.info(f"🎯 [Grid Guard] Filtered to {len(grid_candidates)} actual grid candidates.")
|
||||
candidates = grid_candidates
|
||||
|
||||
# --- Semantic Match Guard ---
|
||||
# If the intent explicitly quotes a target (e.g., "tap 'New Message'"),
|
||||
# we strictly filter candidates to those whose text or content_desc contains the quote.
|
||||
import re
|
||||
|
||||
quotes = re.findall(r"['\"](.*?)['\"]", intent_description)
|
||||
if quotes:
|
||||
target_text = quotes[0].lower()
|
||||
pattern = r"\b" + re.escape(target_text) + r"\b"
|
||||
semantic_candidates = []
|
||||
for node in candidates:
|
||||
n_text = (node.text or "").lower()
|
||||
n_desc = (node.content_desc or "").lower()
|
||||
if re.search(pattern, n_text) or re.search(pattern, n_desc):
|
||||
semantic_candidates.append(node)
|
||||
|
||||
if semantic_candidates:
|
||||
if len(semantic_candidates) == 1:
|
||||
logger.info(f"🎯 [Semantic Guard] Exact match found for '{target_text}', skipping VLM.")
|
||||
return semantic_candidates[0]
|
||||
else:
|
||||
logger.info(
|
||||
f"🎯 [Semantic Guard] {len(semantic_candidates)} matches found for '{target_text}'. Reducing candidates for VLM."
|
||||
)
|
||||
candidates = semantic_candidates
|
||||
else:
|
||||
logger.warning(
|
||||
f"⚠️ [Semantic Guard] No candidates found containing '{target_text}'. Returning None to prevent hallucination."
|
||||
)
|
||||
return None
|
||||
|
||||
try:
|
||||
annotated_b64, box_map = self._annotate_screenshot_with_candidates(device, candidates)
|
||||
except Exception as e:
|
||||
|
||||
@@ -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 story ring avatar": ScreenType.STORY_VIEW,
|
||||
},
|
||||
ScreenType.EXPLORE_GRID: {
|
||||
"tap home tab": ScreenType.HOME_FEED,
|
||||
@@ -57,6 +58,9 @@ class ScreenTopology:
|
||||
ScreenType.FOLLOW_LIST: {
|
||||
"press back": ScreenType.OWN_PROFILE,
|
||||
},
|
||||
ScreenType.STORY_VIEW: {
|
||||
"press back": ScreenType.HOME_FEED,
|
||||
},
|
||||
ScreenType.OTHER_PROFILE: {
|
||||
"press back": ScreenType.HOME_FEED,
|
||||
"tap home tab": ScreenType.HOME_FEED,
|
||||
@@ -88,7 +92,9 @@ class ScreenTopology:
|
||||
}
|
||||
|
||||
@classmethod
|
||||
def find_route(cls, from_screen: ScreenType, to_screen: ScreenType, avoid_actions: set = None) -> Optional[List[Tuple[str, ScreenType]]]:
|
||||
def find_route(
|
||||
cls, from_screen: ScreenType, to_screen: ScreenType, avoid_actions: set = None
|
||||
) -> Optional[List[Tuple[str, ScreenType]]]:
|
||||
"""
|
||||
BFS shortest path from from_screen to to_screen.
|
||||
|
||||
@@ -99,7 +105,7 @@ class ScreenTopology:
|
||||
"""
|
||||
if from_screen == to_screen:
|
||||
return []
|
||||
|
||||
|
||||
avoid_actions = avoid_actions or set()
|
||||
|
||||
queue: deque = deque()
|
||||
@@ -113,7 +119,7 @@ class ScreenTopology:
|
||||
for action, next_screen in transitions.items():
|
||||
if action in avoid_actions or action.replace(" ", "_") in avoid_actions:
|
||||
continue
|
||||
|
||||
|
||||
if next_screen == to_screen:
|
||||
return path + [(action, next_screen)]
|
||||
|
||||
|
||||
Reference in New Issue
Block a user