diff --git a/gateway/platforms/base.py b/gateway/platforms/base.py
index 21a806c1c8..16e7daf3b2 100644
--- a/gateway/platforms/base.py
+++ b/gateway/platforms/base.py
@@ -196,7 +196,7 @@ class BasePlatformAdapter(ABC):
         if not self._message_handler:
             return
         
-        # Start continuous typing indicator (refreshes every 4 seconds)
+        # Start continuous typing indicator (refreshes every 2 seconds)
         typing_task = asyncio.create_task(self._keep_typing(event.source.chat_id))
         
         try:
@@ -205,13 +205,27 @@ class BasePlatformAdapter(ABC):
             
             # Send response if any
             if response:
-                await self.send(
+                result = await self.send(
                     chat_id=event.source.chat_id,
                     content=response,
                     reply_to=event.message_id
                 )
+                
+                # Log send failures (don't raise - user already saw tool progress)
+                if not result.success:
+                    print(f"[{self.name}] Failed to send response: {result.error}")
+                    # Try sending without markdown as fallback
+                    fallback_result = await self.send(
+                        chat_id=event.source.chat_id,
+                        content=f"(Response formatting failed, plain text:)\n\n{response[:3500]}",
+                        reply_to=event.message_id
+                    )
+                    if not fallback_result.success:
+                        print(f"[{self.name}] Fallback send also failed: {fallback_result.error}")
         except Exception as e:
             print(f"[{self.name}] Error handling message: {e}")
+            import traceback
+            traceback.print_exc()
         finally:
             # Stop typing indicator
             typing_task.cancel()
diff --git a/gateway/platforms/telegram.py b/gateway/platforms/telegram.py
index ef46351c6a..10c67c96b9 100644
--- a/gateway/platforms/telegram.py
+++ b/gateway/platforms/telegram.py
@@ -142,13 +142,27 @@ class TelegramAdapter(BasePlatformAdapter):
             thread_id = metadata.get("thread_id") if metadata else None
             
             for i, chunk in enumerate(chunks):
-                msg = await self._bot.send_message(
-                    chat_id=int(chat_id),
-                    text=chunk,
-                    parse_mode=ParseMode.MARKDOWN,
-                    reply_to_message_id=int(reply_to) if reply_to and i == 0 else None,
-                    message_thread_id=int(thread_id) if thread_id else None,
-                )
+                # Try Markdown first, fall back to plain text if it fails
+                try:
+                    msg = await self._bot.send_message(
+                        chat_id=int(chat_id),
+                        text=chunk,
+                        parse_mode=ParseMode.MARKDOWN,
+                        reply_to_message_id=int(reply_to) if reply_to and i == 0 else None,
+                        message_thread_id=int(thread_id) if thread_id else None,
+                    )
+                except Exception as md_error:
+                    # Markdown parsing failed, try plain text
+                    if "parse" in str(md_error).lower() or "markdown" in str(md_error).lower():
+                        msg = await self._bot.send_message(
+                            chat_id=int(chat_id),
+                            text=chunk,
+                            parse_mode=None,  # Plain text
+                            reply_to_message_id=int(reply_to) if reply_to and i == 0 else None,
+                            message_thread_id=int(thread_id) if thread_id else None,
+                        )
+                    else:
+                        raise  # Re-raise if not a parse error
                 message_ids.append(str(msg.message_id))
             
             return SendResult(
diff --git a/gateway/run.py b/gateway/run.py
index b2159e28e1..b10f4cf54e 100644
--- a/gateway/run.py
+++ b/gateway/run.py
@@ -446,11 +446,16 @@ class GatewayRunner:
                 tool_progress_callback=progress_callback if tool_progress_enabled else None,
             )
             
-            # If we have history, we need to restore it
-            # For now, we pass the message directly
-            # TODO: Implement proper history restoration
+            # Convert transcript history to agent format
+            # Transcript has timestamps; agent expects {"role": ..., "content": ...}
+            agent_history = []
+            for msg in history:
+                role = msg.get("role")
+                content = msg.get("content")
+                if role and content:
+                    agent_history.append({"role": role, "content": content})
             
-            result = agent.run_conversation(message)
+            result = agent.run_conversation(message, conversation_history=agent_history)
             
             # Return final response, or a message if something went wrong
             final_response = result.get("final_response")
diff --git a/run_agent.py b/run_agent.py
index 502e6f60f7..72541f6bdb 100644
--- a/run_agent.py
+++ b/run_agent.py
@@ -1272,9 +1272,16 @@ class AIAgent:
             return
         
         try:
-            # Convert to trajectory format (reuse existing method)
-            # Use empty string as user_query since it's embedded in messages
-            trajectory = self._convert_to_trajectory_format(messages, "", True)
+            # Extract the first user message for the trajectory format
+            # The first message should be the user's initial query
+            first_user_query = ""
+            for msg in messages:
+                if msg.get("role") == "user":
+                    first_user_query = msg.get("content", "")
+                    break
+            
+            # Convert to trajectory format
+            trajectory = self._convert_to_trajectory_format(messages, first_user_query, True)
             
             # Build the session log entry
             entry = {