fix: protect server config from truncation and recover from Discord guilds

- Save servers_config.json atomically via temp file + fsync + rename
- Keep .bak backup and auto-restore when main config is empty/corrupt
- Add /servers/recover endpoint for manual recovery
- Auto-recover basic server configs on startup when config is empty but bot is in guilds

bot/bot.py

@@ -163,6 +163,42 @@ async def on_ready():
     # Start server-specific schedulers (includes DM mood rotation)
     server_manager.start_all_schedulers(globals.client)
     
+    # Auto-recover server config if it was lost/corrupted (e.g., disk full)
+    if not server_manager.servers and globals.client.guilds:
+        logger.warning("⚠️ Server config is empty but bot is in guilds — attempting auto-recovery")
+        recovered = 0
+        for guild in globals.client.guilds:
+            text_channels = [ch for ch in guild.text_channels if ch.permissions_for(guild.me).send_messages]
+            if not text_channels:
+                text_channels = guild.text_channels
+            if not text_channels:
+                continue
+            preferred = None
+            for ch in text_channels:
+                if ch.name.lower() in ("general", "chat", "main", "lounge", "general-chat"):
+                    preferred = ch
+                    break
+            channel = preferred or text_channels[0]
+            try:
+                server_manager.add_server(
+                    guild_id=guild.id,
+                    guild_name=guild.name,
+                    autonomous_channel_id=channel.id,
+                    autonomous_channel_name=f"#{channel.name}",
+                    bedtime_channel_ids=[channel.id],
+                    enabled_features={"autonomous", "bedtime", "monday_video"}
+                )
+                recovered += 1
+                logger.info(f"🔄 Auto-recovered server: {guild.name} (ID: {guild.id}) → #{channel.name}")
+            except Exception as e:
+                logger.error(f"Failed to auto-recover server {guild.name}: {e}")
+        if recovered > 0:
+            logger.info(f"✅ Auto-recovered {recovered} server(s) — restarting schedulers")
+            server_manager.stop_all_schedulers()
+            server_manager.start_all_schedulers(globals.client)
+        else:
+            logger.warning("Auto-recovery found no recoverable servers")
+    
     # Start the global scheduler for other tasks
     globals.scheduler.start()
 

bot/routes/servers.py

@@ -136,3 +136,96 @@ def repair_server_config():
         return {"status": "ok", "message": "Server configuration repaired and saved"}
     except Exception as e:
         return JSONResponse(status_code=500, content={"status": "error", "message": f"Failed to repair configuration: {e}"})
+
+
+@router.post("/servers/recover")
+def recover_servers_from_discord():
+    """Auto-discover servers from Discord guilds and create config entries.
+    
+    Use this when servers_config.json is lost/corrupted and you need to
+    quickly restore basic server configurations. Each discovered guild gets
+    a placeholder config using the first available text channel as the
+    autonomous channel. You can then adjust channels via the dashboard.
+    """
+    if not globals.client or not globals.client.is_ready():
+        return JSONResponse(status_code=503, content={
+            "status": "error",
+            "message": "Discord client not ready — bot must be connected"
+        })
+
+    if not globals.client.guilds:
+        return JSONResponse(status_code=404, content={
+            "status": "error",
+            "message": "Bot is not in any Discord guilds"
+        })
+
+    recovered = []
+    skipped = []
+    failed = []
+
+    for guild in globals.client.guilds:
+        guild_id = guild.id
+        guild_name = guild.name
+
+        # Skip if already configured
+        if server_manager.get_server_config(guild_id):
+            skipped.append({"guild_id": str(guild_id), "guild_name": guild_name, "reason": "Already configured"})
+            continue
+
+        # Find the first text channel (prefer one named "general" or "chat")
+        text_channels = [ch for ch in guild.text_channels if ch.permissions_for(guild.me).send_messages]
+        if not text_channels:
+            # Try any text channel even without send permissions
+            text_channels = guild.text_channels
+
+        if not text_channels:
+            failed.append({"guild_id": str(guild_id), "guild_name": guild_name, "reason": "No text channels found"})
+            continue
+
+        # Prefer "general" or "chat" channel, otherwise use the first one
+        preferred = None
+        for ch in text_channels:
+            if ch.name.lower() in ("general", "chat", "main", "lounge", "general-chat"):
+                preferred = ch
+                break
+        channel = preferred or text_channels[0]
+
+        try:
+            success = server_manager.add_server(
+                guild_id=guild_id,
+                guild_name=guild_name,
+                autonomous_channel_id=channel.id,
+                autonomous_channel_name=f"#{channel.name}",
+                bedtime_channel_ids=[channel.id],
+                enabled_features={"autonomous", "bedtime", "monday_video"}
+            )
+            if success:
+                recovered.append({
+                    "guild_id": str(guild_id),
+                    "guild_name": guild_name,
+                    "autonomous_channel": f"#{channel.name} ({channel.id})"
+                })
+                logger.info(f"Recovered server config: {guild_name} (ID: {guild_id}) → #{channel.name}")
+            else:
+                failed.append({"guild_id": str(guild_id), "guild_name": guild_name, "reason": "add_server returned False"})
+        except Exception as e:
+            failed.append({"guild_id": str(guild_id), "guild_name": guild_name, "reason": str(e)})
+            logger.error(f"Failed to recover server {guild_name}: {e}")
+
+    # Restart schedulers if we recovered any servers
+    if recovered:
+        try:
+            server_manager.stop_all_schedulers()
+            server_manager.start_all_schedulers(globals.client)
+        except Exception as e:
+            logger.error(f"Failed to restart schedulers after recovery: {e}")
+
+    return {
+        "status": "ok",
+        "recovered": recovered,
+        "skipped": skipped,
+        "failed": failed,
+        "total_guilds": len(globals.client.guilds),
+        "note": "Recovered servers use the first text channel as autonomous channel. "
+                "Use the Servers tab to adjust channel settings."
+    }

bot/server_manager.py

@@ -79,23 +79,60 @@ class ServerManager:
         self.load_config()
     
     def load_config(self):
-        """Load server configurations from file"""
+        """Load server configurations from file.
-        if os.path.exists(self.config_file):
+        
-            try:
+        If the main file is missing, empty, or corrupt, falls back to the
-                with open(self.config_file, "r", encoding="utf-8") as f:
+        .bak backup file automatically.
-                    data = json.load(f)
+        """
-                    for guild_id_str, server_data in data.items():
+        loaded = self._try_load_file(self.config_file)
-                        guild_id = int(guild_id_str)
+        
-                        self.servers[guild_id] = ServerConfig.from_dict(server_data)
+        if not loaded:
-                        logger.info(f"Loaded config for server: {server_data['guild_name']} (ID: {guild_id})")
+            # Try backup file
-                
+            bak_file = self.config_file + ".bak"
-                # After loading, check if we need to repair the config
+            if os.path.exists(bak_file):
-                self.repair_config()
+                logger.warning(f"Main config is empty/corrupt, trying backup: {bak_file}")
-            except Exception as e:
+                loaded = self._try_load_file(bak_file)
-                logger.error(f"Failed to load server config: {e}")
+                if loaded:
-                logger.info("Starting with zero servers — add servers via the API or dashboard")
+                    # Restore main config from backup
-        else:
+                    logger.info("Successfully restored server config from backup")
-            logger.info("No servers_config.json found — starting with zero servers")
+                    self.save_config()
+        
+        if not loaded:
+            logger.info("No valid servers_config.json found — starting with zero servers")
+        
+        # After loading, check if we need to repair the config
+        self.repair_config()
+    
+    def _try_load_file(self, filepath: str) -> bool:
+        """Try to load server config from a file. Returns True if any servers loaded."""
+        if not os.path.exists(filepath):
+            return False
+        
+        # Check for empty file
+        if os.path.getsize(filepath) == 0:
+            logger.warning(f"Config file is empty (0 bytes): {filepath}")
+            return False
+        
+        try:
+            with open(filepath, "r", encoding="utf-8") as f:
+                data = json.load(f)
+            
+            if not data or not isinstance(data, dict):
+                logger.warning(f"Config file has invalid structure: {filepath}")
+                return False
+            
+            for guild_id_str, server_data in data.items():
+                guild_id = int(guild_id_str)
+                self.servers[guild_id] = ServerConfig.from_dict(server_data)
+                logger.info(f"Loaded config for server: {server_data.get('guild_name', 'Unknown')} (ID: {guild_id})")
+            
+            return len(self.servers) > 0
+        except json.JSONDecodeError as e:
+            logger.error(f"Failed to parse server config from {filepath}: {e}")
+            return False
+        except Exception as e:
+            logger.error(f"Failed to load server config from {filepath}: {e}")
+            return False
     
     def repair_config(self):
         """Repair corrupted configuration data and save it back"""
@@ -122,7 +159,11 @@ class ServerManager:
             logger.error(f"Failed to repair config: {e}")
     
     def save_config(self):
-        """Save server configurations to file"""
+        """Save server configurations to file (atomic write with backup).
+        
+        Uses write-to-temp-then-rename to prevent file corruption if the
+        filesystem runs out of space mid-write. Also keeps a .bak backup.
+        """
         try:
             os.makedirs(os.path.dirname(self.config_file), exist_ok=True)
             config_data = {}
@@ -134,10 +175,42 @@ class ServerManager:
                     server_dict['enabled_features'] = list(server_dict['enabled_features'])
                 config_data[str(guild_id)] = server_dict
             
-            with open(self.config_file, "w", encoding="utf-8") as f:
+            serialized = json.dumps(config_data, indent=2)
-                json.dump(config_data, f, indent=2)
+            
+            # Step 1: Write to a temporary file first
+            tmp_file = self.config_file + ".tmp"
+            with open(tmp_file, "w", encoding="utf-8") as f:
+                f.write(serialized)
+                f.flush()
+                os.fsync(f.fileno())  # Ensure data is written to disk
+            
+            # Step 2: Keep a .bak copy of the current valid config (if any)
+            bak_file = self.config_file + ".bak"
+            if os.path.exists(self.config_file) and os.path.getsize(self.config_file) > 0:
+                try:
+                    os.replace(self.config_file, bak_file)
+                except OSError as e:
+                    logger.warning(f"Could not create backup of server config: {e}")
+            
+            # Step 3: Atomically rename temp file to the real config file
+            os.replace(tmp_file, self.config_file)
+            
+            # Step 4: Write a second backup copy (paranoid double-backup)
+            try:
+                with open(bak_file, "w", encoding="utf-8") as f:
+                    f.write(serialized)
+            except OSError:
+                pass  # Backup is best-effort
+                
         except Exception as e:
             logger.error(f"Failed to save server config: {e}")
+            # Clean up temp file if something went wrong
+            tmp_file = self.config_file + ".tmp"
+            if os.path.exists(tmp_file):
+                try:
+                    os.remove(tmp_file)
+                except OSError:
+                    pass
     
     def add_server(self, guild_id: int, guild_name: str, autonomous_channel_id: int, 
                    autonomous_channel_name: str, bedtime_channel_ids: List[int] = None,