From 5ca5777c4b91479950c3fd2503ed9c4017eb46e9 Mon Sep 17 00:00:00 2001
From: Marc Mintel <marc@mintel.me>
Date: Tue, 5 May 2026 12:32:34 +0200
Subject: [PATCH] feat(story_view): delegate next story segment resolution to
 TelepathicEngine/VLM instead of hardcoded coordinates

---
 GramAddict/core/behaviors/story_view.py | 39 ++++++++++++++++++++++---
 1 file changed, 35 insertions(+), 4 deletions(-)

diff --git a/GramAddict/core/behaviors/story_view.py b/GramAddict/core/behaviors/story_view.py
index 5c896e5..7e978e8 100644
--- a/GramAddict/core/behaviors/story_view.py
+++ b/GramAddict/core/behaviors/story_view.py
@@ -96,13 +96,44 @@ class StoryViewPlugin(BehaviorPlugin):
         for i in range(count):
             sleep(random.uniform(2.0, 5.0) * ctx.sleep_mod)
             if i < count - 1:
-                # Click top-right to avoid 'reply' input fields and most stickers
-                humanized_click(ctx.device, int(w * 0.85), int(h * 0.25), sleep_mod=ctx.sleep_mod)
-                # Atomic state validation after click
+                # Atomic state validation before click
                 xml_dump = ctx.device.dump_hierarchy()
                 if not xml_dump:
                     continue
-                packages = set(re.findall(r'package="([^"]+)"', xml_dump))
+
+                # Query VLM to find the interactive area for the next segment
+                intent = "tap right side of screen to view next story segment"
+                node = ctx.telepathic.find_best_node(xml_dump, intent, device=ctx.device, track=False)
+
+                if node:
+                    logger.debug(
+                        f"📸 [StoryView] VLM selected node '{node.resource_id or node.content_desc or 'unknown'}' for next segment."
+                    )
+                    # If VLM selects a large container (e.g. the entire screen or story viewer),
+                    # we must tap its right side, not its exact center, to avoid pausing the story.
+                    if getattr(node, "area", 0) > (w * h * 0.4):
+                        target_x = node.x1 + int((node.x2 - node.x1) * 0.85)
+                        target_y = node.y1 + int((node.y2 - node.y1) * 0.25)
+                        logger.debug(
+                            f"📸 [StoryView] Adjusting click to top-right quadrant of large container: ({target_x}, {target_y})"
+                        )
+                    else:
+                        target_x = node.center_x
+                        target_y = node.center_y
+
+                    humanized_click(ctx.device, target_x, target_y, sleep_mod=ctx.sleep_mod)
+                else:
+                    logger.warning(
+                        "📸 [StoryView] VLM could not resolve next story segment. Falling back to geometric safety quadrant."
+                    )
+                    # Click top-right to avoid 'reply' input fields and most stickers
+                    humanized_click(ctx.device, int(w * 0.85), int(h * 0.25), sleep_mod=ctx.sleep_mod)
+
+                # Verify we didn't leave Instagram
+                xml_dump_after = ctx.device.dump_hierarchy()
+                if not xml_dump_after:
+                    continue
+                packages = set(re.findall(r'package="([^"]+)"', xml_dump_after))
                 app_id = getattr(ctx.device, "app_id", "com.instagram.android")
                 if packages and app_id not in packages:
                     logger.error(