mmintel/instagram-bot
1
0
Fork 0
Code Issues Pull Requests 4 Actions Packages Projects Releases Wiki Activity

feat: enforce zero-maintenance autonomous navigation by purging hardcoded string searches and localized translations; harden VLM perception via robust JSON fallback; fix OTHER_PROFILE topological routing

Browse Source
This commit is contained in:
Marc Mintel
2026-05-03 23:28:00 +02:00
parent 4b645c6fb2
commit c641204a6b
19 changed files with 455 additions and 166 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
GramAddict/core/behaviors/darwin_dwell.py
View File

@@ -40,7 +40,15 @@ class DarwinDwellPlugin(BehaviorPlugin):
logger.info("🐢 [DarwinDwell] Executing organic dwell behaviors...")
darwin.execute_micro_wobble(ctx.device)
res_score = ctx.shared_state.get("res_score", 1.0)
darwin.execute_proof_of_resonance(ctx.device, res_score)
darwin.execute_proof_of_resonance(
ctx.device,
res_score,
nav_graph=ctx.cognitive_stack.get("nav_graph"),
configs=ctx.configs,
resonance_oracle=ctx.cognitive_stack.get("oracle"),
username=ctx.username,
context_xml=ctx.context_xml or ctx.device.dump_hierarchy(),
)
else:
logger.info("🐢 [DarwinDwell] Darwin engine missing. Falling back to static sleep.")
sleep(2.5 * ctx.sleep_mod)

9
GramAddict/core/behaviors/repost.py
View File

@@ -50,8 +50,11 @@ class RepostPlugin(BehaviorPlugin):
nav_graph = QNavGraph(ctx.device)
if nav_graph.do("share to story"):
logger.info(f"📤 [Repost] Shared post by @{ctx.username} to story ✓")
return BehaviorResult(executed=True, interactions=1)
# We must click the send post button first
if nav_graph.do("tap send post button"):
# A modal should appear, now click add to story
if nav_graph.do("tap add to story"):
logger.info(f"📤 [Repost] Shared post by @{ctx.username} to story ✓")
return BehaviorResult(executed=True, interactions=1)
return BehaviorResult(executed=False)

15
GramAddict/core/darwin_engine.py
View File

@@ -84,7 +84,6 @@ class DarwinEngine(QdrantBase):
resonance: float,
text_length: int = 0,
nav_graph=None,
zero_engine=None,
configs=None,
resonance_oracle=None,
username=None,
@@ -142,12 +141,22 @@ class DarwinEngine(QdrantBase):
cy = h // 2
dur_ms = int(random.uniform(200, 500))
device.shell(f"input swipe {int(cx)} {int(cy)} {int(cx + noise_x)} {int(cy + slip_distance)} {dur_ms}")
# Use physics-based injector instead of algorithmic 'input swipe'
body = PhysicsBody.get_session_instance(device)
injector = SendEventInjector.get_instance(device)
start_pt = (int(cx), int(cy))
end_pt = (int(cx + noise_x), int(cy + slip_distance))
points = BezierGesture.scroll_curve(start_pt, end_pt, body, n_points=5)
timing = BezierGesture.compute_sigmoid_timing(len(points), dur_ms)
injector.inject_gesture(points, timing, touch_major=body.get_touch_major())
time.sleep(random.uniform(0.5, 1.2))
# 4. Comment depth simulation (probabilistic & resonance-correlated)
if profile["comment_read_dwell"] > 1.0 and resonance > 0.4 and random.random() < 0.3:
if nav_graph and zero_engine:
if nav_graph:
if not self._has_comments(context_xml):
logger.debug(" -> 🚫 [Darwin Engine] Skipping comment depth simulation (Post has 0 comments).")
else:

20
GramAddict/core/goap.py
View File

@@ -176,11 +176,21 @@ class GoalExecutor:
if last_action and last_screen_type:
self.action_failures[(last_screen_type, last_action)] = (
self.action_failures.get((last_screen_type, last_action), 0) + MAX_RETRIES
) # Instantly mask it
self.planner.knowledge.learn_trap(last_screen_type, last_action, f"caused_obstacle_{obstacle_name}")
logger.warning(
f"🛡️ [SAE Feedback] Action '{last_action}' caused an obstacle. Masking aggressively and learned trap."
)
) # Instantly mask it for this session
from GramAddict.core.screen_topology import ScreenTopology
if ScreenTopology.is_structural_action(last_screen_type, last_action):
logger.warning(
f"🛡️ [SAE Feedback] Structural action '{last_action}' caused an obstacle. "
f"Masking for this session. (Never burned permanently)"
)
else:
logger.warning(
f"🛡️ [SAE Feedback] Content action '{last_action}' caused an obstacle. "
f"Masking for this session to break loop, but preventing permanent Qdrant poisoning."
)
# We specifically DO NOT call self.planner.knowledge.learn_trap here anymore!
# Burning dynamic actions like "tap follow button" permanently destroys the bot's capabilities across sessions.
if not self._get_sae().ensure_clear_screen():
if screen_type == ScreenType.FOREIGN_APP:

39
GramAddict/core/perception/action_memory.py
View File

@@ -1,6 +1,5 @@
import json
import logging
import re
from typing import Any, Dict, Optional
from GramAddict.core.perception.spatial_parser import SpatialNode
@@ -23,8 +22,8 @@ def _parse_yes_no(response: str) -> Optional[bool]:
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,
# If it is valid JSON but we couldn't definitively find YES/NO,
# do NOT fall through to text matching
return None
except Exception:
@@ -169,19 +168,33 @@ class ActionMemory:
logger.warning(f"⚠️ [ActionMemory] Still on grid after trying to '{intent}'. Verification FAIL.")
return False # Still on grid, definitely failed
# Specific check for opening a profile
if "profile" in intent_lower or "author" in intent_lower or "username" in intent_lower:
if "profile_header_container" in post_xml_lower:
logger.info("✅ [ActionMemory] Structural check confirmed profile navigation success.")
return True
else:
logger.warning(
f"⚠️ [ActionMemory] Profile header NOT found after trying to '{intent}'. Verification FAIL."
)
return False
# Specific check for navigating to Home Feed
if "home feed" in intent_lower or "home tab" in intent_lower:
if "main_feed_action_bar" in post_xml_lower:
logger.info("✅ [ActionMemory] Structural check confirmed Home Feed navigation success.")
return True
# Specific check for navigating to Explore Feed
if "explore feed" in intent_lower or "explore tab" in intent_lower or "search" in intent_lower:
if "explore_action_bar" in post_xml_lower or "action_bar_search_edit_text" in post_xml_lower:
logger.info("✅ [ActionMemory] Structural check confirmed Explore Feed navigation success.")
return True
state_toggles = ["like", "save", "follow", "heart"]
is_toggle = any(t in intent_lower for t in state_toggles)
# ── State-Specific Structural Verification ──
# If it was a follow, the resulting XML MUST contain "Following", "Requested", "Abonniert" or "Angefragt"
if "follow" in intent_lower:
FOLLOW_SUCCESS_MARKERS = ["following", "requested", "abonniert", "angefragt", "gefolgt"]
if any(m in post_xml_lower for m in FOLLOW_SUCCESS_MARKERS):
logger.info("✅ [ActionMemory] Structural check confirmed follow success.")
return True
else:
logger.warning("⚠️ [ActionMemory] Follow success markers NOT found in post-click XML.")
# We don't return False immediately because it might take a second to update
# ── VLM Verification Fallback ──
# If we are highly confident (e.g. pulled from Qdrant memory), bypass heavy VLM
if device and confidence < 0.95:

83
GramAddict/core/perception/intent_resolver.py
View File

@@ -228,17 +228,15 @@ class IntentResolver:
rid = (node.resource_id or "").lower()
desc = (node.content_desc or "").lower()
text = (node.text or "").lower()
if (
"send" in rid
or "composer_button" in rid
or "send" in desc
or "absenden" in desc
or text in ["send", "absenden"]
):
if "send" in rid or "composer_button" in rid:
logger.info(f"🎯 [Structural Fast-Path] Found send button: {rid or desc or text}")
return node
if "post author username" in intent_lower or "tap post username" in intent_lower:
for node in candidates:
if "row_feed_photo_profile_imageview" in (node.resource_id or "").lower():
logger.info(f"🎯 [Structural Fast-Path] Found post author avatar image: {node.content_desc}")
return node
for node in candidates:
if "row_feed_photo_profile_name" in (node.resource_id or "").lower():
logger.info(f"🎯 [Structural Fast-Path] Found post author username text: {node.text}")
@@ -271,6 +269,47 @@ class IntentResolver:
logger.info(f"🎯 [Structural Fast-Path] Found comment button: {node.resource_id}")
return node
if "like" in intent_lower and ("button" in intent_lower or "post" in intent_lower):
for node in candidates:
rid = (node.resource_id or "").lower()
if "row_feed_button_like" in rid:
logger.info(f"🎯 [Structural Fast-Path] Found like button: {rid}")
return node
if ("send" in intent_lower or "share" in intent_lower) and "post" in intent_lower and "button" in intent_lower:
for node in candidates:
rid = (node.resource_id or "").lower()
desc = (node.content_desc or "").lower()
if "row_feed_button_share" in rid or "send post" in desc:
logger.info(f"🎯 [Structural Fast-Path] Found send/share post button: {rid or desc}")
return node
if "add to story" in intent_lower:
# We skip structural fast-path for 'add to story' since it relies heavily on language/text strings
# and let the VLM figure it out or rely on purely visual indicators.
pass
if "share" in intent_lower and ("button" in intent_lower or "post" in intent_lower):
for node in candidates:
rid = (node.resource_id or "").lower()
if "row_feed_button_share" in rid:
logger.info(f"🎯 [Structural Fast-Path] Found share button: {rid}")
return node
if "save" in intent_lower and ("button" in intent_lower or "post" in intent_lower):
for node in candidates:
rid = (node.resource_id or "").lower()
if "row_feed_button_save" in rid:
logger.info(f"🎯 [Structural Fast-Path] Found save button: {rid}")
return node
if "follow" in intent_lower and "button" in intent_lower:
for node in candidates:
rid = (node.resource_id or "").lower()
if "profile_header_follow_button" in rid or "inline_follow_button" in rid:
logger.info(f"🎯 [Structural Fast-Path] Found follow/following button: {rid}")
return node
if "first post" in intent_lower or "first item" in intent_lower or "first search result" in intent_lower:
for node in candidates:
rid = (node.resource_id or "").lower()
@@ -289,23 +328,29 @@ class IntentResolver:
# Ignore the user's explicit "Add to story" ring
if "add to story" not in desc and "your story" not in text:
story_nodes.append(node)
if story_nodes:
# Sort horizontally (left-to-right)
story_nodes.sort(key=lambda n: n.x1)
# Check if this is the home feed story tray (avatar_image_view without 'highlight' in desc)
is_highlight = any("highlight" in (n.content_desc or "").lower() for n in story_nodes)
if "avatar_image_view" in (story_nodes[0].resource_id or "").lower() and not is_highlight:
if len(story_nodes) > 1:
logger.info(f"🎯 [Structural Fast-Path] Found {len(story_nodes)} story rings. Skipping own profile. Picking second: '{story_nodes[1].content_desc}'")
logger.info(
f"🎯 [Structural Fast-Path] Found {len(story_nodes)} story rings. Skipping own profile. Picking second: '{story_nodes[1].content_desc}'"
)
return story_nodes[1]
else:
logger.warning("🎯 [Structural Fast-Path] Only 1 story ring found on feed (likely own profile). Skipping to avoid modal trap.")
logger.warning(
"🎯 [Structural Fast-Path] Only 1 story ring found on feed (likely own profile). Skipping to avoid modal trap."
)
return None
else:
# Profile header or other single-story views
logger.info(f"🎯 [Structural Fast-Path] Found story ring avatar: {story_nodes[0].resource_id} (desc: '{story_nodes[0].content_desc}')")
logger.info(
f"🎯 [Structural Fast-Path] Found story ring avatar: {story_nodes[0].resource_id} (desc: '{story_nodes[0].content_desc}')"
)
return story_nodes[0]
# --- Navigation Tab Fast-Paths ---
@@ -337,13 +382,21 @@ class IntentResolver:
quotes = re.findall(r"['\"](.*?)['\"]", intent_description)
if quotes:
target_text = quotes[0].lower()
pattern = r"\b" + re.escape(target_text) + r"\b"
# Only use the exact target string (no manual localized translation dictionaries!)
localized_targets = [target_text]
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)
# Check if any of the localized targets match
for loc_target in localized_targets:
pattern = r"\b" + re.escape(loc_target) + r"\b"
if re.search(pattern, n_text) or re.search(pattern, n_desc):
semantic_candidates.append(node)
break # Found a match, no need to check other localized targets
if semantic_candidates:
if len(semantic_candidates) == 1:

22
GramAddict/core/perception/screen_identity.py
View File

@@ -170,7 +170,7 @@ class ScreenIdentity:
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)
is_normal_override = (cached_type_str == "NORMAL")
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.
@@ -185,8 +185,16 @@ class ScreenIdentity:
if "unified_follow_list_tab_layout" in ids or "follow_list_container" in ids:
return ScreenType.FOLLOW_LIST
if "profile_header_container" in ids:
if selected_tab == "profile_tab":
# Profile structural markers
PROFILE_MARKERS = (
"profile_header_container",
"row_profile_header_imageview",
"profile_tabs_container",
"profile_header_name",
)
if any(marker in ids for marker in PROFILE_MARKERS):
own_profile_texts = ("edit profile", "share profile", "profil bearbeiten", "profil teilen")
if selected_tab == "profile_tab" or any(m in desc_lower or m in text_lower for m in own_profile_texts):
return ScreenType.OWN_PROFILE
return ScreenType.OTHER_PROFILE
@@ -252,7 +260,9 @@ class ScreenIdentity:
# 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.")
logger.warning(
f"⚠️ [ScreenIdentity] Rejecting cached {cached_type.name} due to missing structural markers."
)
else:
return cached_type
except KeyError:
@@ -304,7 +314,9 @@ class ScreenIdentity:
# 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.")
logger.warning(
f"⚠️ [ScreenIdentity] Rejecting VLM hallucinated {t.name} due to missing structural markers."
)
return ScreenType.UNKNOWN
if signature and self.screen_memory:

15
GramAddict/core/perception/semantic_evaluator.py
View File

@@ -123,8 +123,7 @@ class SemanticEvaluator:
{{
"should_like": true/false,
"should_comment": true/false,
"is_ad": true/false,
"reasoning": "brief explanation"
"is_ad": true/false
}}
"""
response = self._query_vlm(prompt, screenshot_b64)
@@ -133,7 +132,17 @@ class SemanticEvaluator:
json_str = response.split("```json")[1].split("```")[0].strip()
else:
json_str = response.strip()
return json.loads(json_str)
try:
return json.loads(json_str)
except json.JSONDecodeError:
# Try to close potential unclosed JSON strings
if not json_str.endswith("}"):
json_str += "}"
try:
return json.loads(json_str)
except json.JSONDecodeError:
pass
logger.warning(f"👁️ [Vision Core] VLM returned malformed JSON: {response}")
except Exception as e:
logger.warning(f"Failed to evaluate post vibe: {e}")
return None

23
GramAddict/core/q_nav_graph.py
View File

@@ -121,34 +121,11 @@ class QNavGraph:
GOAP-powered action execution.
Replaces _execute_transition() for post interactions.
Screen-aware: refuses to attempt actions that don't exist on the current screen.
Usage:
nav_graph.do("like this post") # instead of _execute_transition("tap_like_button")
nav_graph.do("follow this user") # instead of _execute_transition("tap_follow_button")
nav_graph.do("tap first grid item") # instead of _execute_transition("tap_explore_grid_item")
"""
# ── Screen sanity check: is this action possible here? ──
screen = self.goap.perceive()
available = screen.get("available_actions", [])
screen_type = screen["screen_type"]
# Map goal to the action that should be available
action_checks = {
"like": ["tap like button"],
"comment": ["tap comment button"],
"share": ["tap share button"],
"follow": ["tap follow button", "tap following button"],
}
for keyword, required_actions in action_checks.items():
if keyword in goal.lower():
# If ANY of the required actions are available, it's valid
if not any(req in available for req in required_actions):
logger.warning(
f"🚫 [GOAP] Cannot '{goal}' on {screen_type.value} "
f"({required_actions} not available on this screen)"
)
return False
return self.goap._execute_action(goal)

25
GramAddict/core/resonance_engine.py
View File

@@ -1,5 +1,6 @@
import logging
import math
import random
from typing import Optional
from colorama import Fore
@@ -334,11 +335,31 @@ class ResonanceEngine:
is_ui_junk = (
val.lower().startswith("go to")
or val.lower().startswith("tap to")
or val.lower().startswith("gehe zu")
or val.lower().startswith("tippe auf")
or "actions for this post" in val.lower()
or "aktionen für diesen beitrag" in val.lower()
)
blocked_exact = [
"reply",
"antworten",
"like",
"gefällt mir",
"view replies",
"antworten ansehen",
"see translation",
"übersetzung anzeigen",
"hide replies",
"antworten verbergen",
"view all comments",
"alle kommentare ansehen",
"send",
"absenden",
]
if val and len(val) > 2 and is_comment_node and not is_ui_junk:
if val.lower() not in ["reply", "like", "view replies", "see translation", "hide replies"]:
if val.lower() not in blocked_exact:
raw_comments.append(val)
except Exception as e:
logger.error(f"🧠 [Comment Learning] Failed to parse XML: {e}")
@@ -393,7 +414,7 @@ class ResonanceEngine:
logger.debug(f"DEBUG CONDENSER RAW: {response_text}")
# Parse json gracefully
if type(response_text) is str:
if isinstance(response_text, str):
clean_json = response_text.strip()
if clean_json.startswith("```json"):
clean_json = clean_json[7:]

6
GramAddict/core/screen_topology.py
View File

@@ -62,7 +62,13 @@ class ScreenTopology:
"press back": ScreenType.HOME_FEED,
},
ScreenType.OTHER_PROFILE: {
"press back": ScreenType.HOME_FEED,
},
ScreenType.POST_DETAIL: {
"tap home tab": ScreenType.HOME_FEED,
"tap explore tab": ScreenType.EXPLORE_GRID,
"tap profile tab": ScreenType.OWN_PROFILE,
"tap reels tab": ScreenType.REELS_FEED,
},
ScreenType.UNKNOWN: {
"tap home tab": ScreenType.HOME_FEED,

18
GramAddict/core/situational_awareness.py
View File

@@ -761,6 +761,24 @@ class SituationalAwarenessEngine:
logger.warning(f"🔍 [SAE] Obstacle detected: {situation.value} (attempt {attempt + 1}/{max_attempts})")
# ── O(1) Fast-Path for Foreign Apps ──
if situation == SituationType.OBSTACLE_FOREIGN_APP:
logger.warning("⚡ [SAE Fast-Path] Foreign App detected. Bypassing LLM and killing immediately.")
action = EscapeAction("kill_foreign_apps", reason="O(1) fast-path to eliminate foreign app")
self._execute_escape(action)
# Check if we recovered
post_xml = self.device.dump_hierarchy()
if self.perceive(post_xml) == SituationType.NORMAL:
logger.info("✅ [SAE Fast-Path] Foreign App cleared successfully!")
self._consecutive_failures = 0
return True
# If we didn't recover, log it and let the loop continue
logger.warning("⚠️ [SAE Fast-Path] kill_foreign_apps did not return to NORMAL. Retrying...")
self._consecutive_failures += 1
continue
# ── COMPRESS for memory lookup ──
compressed = self._compress_xml(xml_dump)

14
GramAddict/core/unfollow_engine.py
View File

@@ -65,6 +65,20 @@ def _run_zero_latency_unfollow_loop(
try:
xml_dump = device.dump_hierarchy()
# ── Perimeter Guard: Verify we're still inside Instagram ──
if xml_dump:
import re
unfollow_packages = set(re.findall(r'package="([^"]+)"', xml_dump))
unfollow_app_id = getattr(device, "app_id", "com.instagram.android")
if unfollow_packages and unfollow_app_id not in unfollow_packages:
logger.error(
f"🚨 [UnfollowLoop] FOREIGN APP DETECTED! Packages: {unfollow_packages}. Aborting loop."
)
device.press("back")
random_sleep(1.0, 1.5)
return "CONTEXT_LOST"
# Autonomously identify user rows via Semantic Extraction
telepathic = cognitive_stack.get("telepathic")
nodes = []