From 125e5ef0899d4c60ec84ac720192ba05007ea7e1 Mon Sep 17 00:00:00 2001
From: Teknium <teknium1@gmail.com>
Date: Tue, 7 Apr 2026 14:05:25 -0700
Subject: [PATCH] fix: extend caption substring fix to all platforms

Move _merge_caption helper from TelegramAdapter to BasePlatformAdapter
so all adapters inherit it. Fix the same substring-containment bug in:
- gateway/platforms/base.py (photo burst merging)
- gateway/run.py (priority photo follow-up merging)
- gateway/platforms/feishu.py (media batch merging)

The original fix only covered telegram.py. The same bug existed in base.py
and run.py (pure substring check) and feishu.py (list membership without
whitespace normalization).
---
 gateway/platforms/base.py     | 21 +++++++++++++++++----
 gateway/platforms/feishu.py   |  5 +----
 gateway/platforms/telegram.py | 16 ----------------
 gateway/run.py                |  5 +----
 4 files changed, 19 insertions(+), 28 deletions(-)

diff --git a/gateway/platforms/base.py b/gateway/platforms/base.py
index a1fef589a..551c0e86a 100644
--- a/gateway/platforms/base.py
+++ b/gateway/platforms/base.py
@@ -1105,6 +1105,22 @@ class BasePlatformAdapter(ABC):
             logger.error("[%s] Fallback send also failed: %s", self.name, fallback_result.error)
         return fallback_result
 
+    @staticmethod
+    def _merge_caption(existing_text: Optional[str], new_text: str) -> str:
+        """Merge a new caption into existing text, avoiding duplicates.
+
+        Uses line-by-line exact match (not substring) to prevent false positives
+        where a shorter caption is silently dropped because it appears as a
+        substring of a longer one (e.g. "Meeting" inside "Meeting agenda").
+        Whitespace is normalised for comparison.
+        """
+        if not existing_text:
+            return new_text
+        existing_captions = [c.strip() for c in existing_text.split("\n\n")]
+        if new_text.strip() not in existing_captions:
+            return f"{existing_text}\n\n{new_text}".strip()
+        return existing_text
+
     async def handle_message(self, event: MessageEvent) -> None:
         """
         Process an incoming message.
@@ -1164,10 +1180,7 @@ class BasePlatformAdapter(ABC):
                     existing.media_urls.extend(event.media_urls)
                     existing.media_types.extend(event.media_types)
                     if event.text:
-                        if not existing.text:
-                            existing.text = event.text
-                        elif event.text not in existing.text:
-                            existing.text = f"{existing.text}\n\n{event.text}".strip()
+                        existing.text = self._merge_caption(existing.text, event.text)
                 else:
                     self._pending_messages[session_key] = event
                 return  # Don't interrupt now - will run after current task completes
diff --git a/gateway/platforms/feishu.py b/gateway/platforms/feishu.py
index fce22a970..7b20bc19a 100644
--- a/gateway/platforms/feishu.py
+++ b/gateway/platforms/feishu.py
@@ -2065,10 +2065,7 @@ class FeishuAdapter(BasePlatformAdapter):
         existing.media_urls.extend(event.media_urls)
         existing.media_types.extend(event.media_types)
         if event.text:
-            if not existing.text:
-                existing.text = event.text
-            elif event.text not in existing.text.split("\n\n"):
-                existing.text = f"{existing.text}\n\n{event.text}"
+            existing.text = self._merge_caption(existing.text, event.text)
         existing.timestamp = event.timestamp
         if event.message_id:
             existing.message_id = event.message_id
diff --git a/gateway/platforms/telegram.py b/gateway/platforms/telegram.py
index 3fa114986..f72c31e1c 100644
--- a/gateway/platforms/telegram.py
+++ b/gateway/platforms/telegram.py
@@ -2213,22 +2213,6 @@ class TelegramAdapter(BasePlatformAdapter):
             if self._pending_photo_batch_tasks.get(batch_key) is current_task:
                 self._pending_photo_batch_tasks.pop(batch_key, None)
 
-    @staticmethod
-    def _merge_caption(existing_text: Optional[str], new_text: str) -> str:
-        """Merge a new caption into existing text, avoiding duplicates.
-
-        Uses line-by-line exact match (not substring) to prevent false positives
-        where a shorter caption is silently dropped because it appears as a
-        substring of a longer one (e.g. "Meeting" inside "Meeting agenda").
-        Whitespace is normalised for comparison.
-        """
-        if not existing_text:
-            return new_text
-        existing_captions = [c.strip() for c in existing_text.split("\n\n")]
-        if new_text.strip() not in existing_captions:
-            return f"{existing_text}\n\n{new_text}".strip()
-        return existing_text
-
     def _enqueue_photo_event(self, batch_key: str, event: MessageEvent) -> None:
         """Merge photo events into a pending batch and schedule flush."""
         existing = self._pending_photo_batches.get(batch_key)
diff --git a/gateway/run.py b/gateway/run.py
index df7df7db7..81c7d55f1 100644
--- a/gateway/run.py
+++ b/gateway/run.py
@@ -1987,10 +1987,7 @@ class GatewayRunner:
                             existing.media_urls.extend(event.media_urls)
                             existing.media_types.extend(event.media_types)
                             if event.text:
-                                if not existing.text:
-                                    existing.text = event.text
-                                elif event.text not in existing.text:
-                                    existing.text = f"{existing.text}\n\n{event.text}".strip()
+                                existing.text = BasePlatformAdapter._merge_caption(existing.text, event.text)
                         else:
                             adapter._pending_messages[_quick_key] = event
                     else: