fix: session stability improvements

- Fix docker client initialization bug in app.py (context manager was closing client)
- Add restart_session() method to preserve session IDs during container restarts
- Add 60-second startup grace period before health checking new sessions
- Fix _stop_container and _get_container_info to use docker_service API consistently
- Disable mDNS in Dockerfile to prevent Bonjour service name conflicts
- Remove old container before restart to free port bindings

session-manager/session_manager.py

@@ -367,6 +367,86 @@ class SessionManager:
     async def list_sessions(self) -> List[SessionData]:
         return list(self.sessions.values())
 
+    async def restart_session(self, session_id: str) -> Optional[SessionData]:
+        """Restart a session's container while preserving the session ID.
+        
+        Unlike create_session(), this reuses the existing session data
+        and only creates a new container, maintaining session ID continuity.
+        This method removes the old container to free up the port.
+        """
+        session = await self.get_session(session_id)
+        if not session:
+            logger.error(
+                "Cannot restart session: not found",
+                extra={"session_id": session_id},
+            )
+            return None
+        
+        old_container_id = session.container_id
+        logger.info(
+            "Restarting session container",
+            extra={"session_id": session_id, "old_container_id": old_container_id},
+        )
+        
+        # Stop and remove old container to free up the port
+        if old_container_id and self.docker_service:
+            try:
+                logger.info(
+                    "Stopping old container for restart",
+                    extra={"session_id": session_id, "container_id": old_container_id},
+                )
+                await self.docker_service.stop_container(old_container_id)
+            except Exception as e:
+                logger.warning(
+                    "Failed to stop old container (may already be stopped)",
+                    extra={"session_id": session_id, "container_id": old_container_id, "error": str(e)},
+                )
+            
+            try:
+                logger.info(
+                    "Removing old container for restart",
+                    extra={"session_id": session_id, "container_id": old_container_id},
+                )
+                await self.docker_service.remove_container(old_container_id, force=True)
+            except Exception as e:
+                logger.warning(
+                    "Failed to remove old container",
+                    extra={"session_id": session_id, "container_id": old_container_id, "error": str(e)},
+                )
+        
+        # Generate new container name for the restart
+        new_container_name = f"opencode-{session_id}-{uuid.uuid4().hex[:8]}"
+        session.container_name = new_container_name
+        session.container_id = None  # Clear old container_id
+        session.status = "starting"
+        
+        # Update session in store before starting container
+        self.sessions[session_id] = session
+        
+        if USE_DATABASE_STORAGE:
+            try:
+                await SessionModel.update_session(
+                    session_id,
+                    {
+                        "container_name": new_container_name,
+                        "container_id": None,
+                        "status": "starting",
+                    },
+                )
+            except Exception as e:
+                logger.error(
+                    "Failed to update session in database during restart",
+                    extra={"session_id": session_id, "error": str(e)},
+                )
+        
+        # Start new container for this session
+        if USE_ASYNC_DOCKER:
+            asyncio.create_task(self._start_container_async(session))
+        else:
+            asyncio.create_task(self._start_container_sync(session))
+        
+        return session
+
     async def list_containers_async(self, all: bool = False) -> List:
         return await self.docker_service.list_containers(all=all)