version 5.2.4

- When os_info arrives with no owner field, apply default_owner from server config
- Stop applying default_owner unconditionally in get_host_access (now deferred to os_info handling)
- os_info plugin logs debug message when injecting owner from client config

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

README.md

@@ -507,6 +507,9 @@ hbc --boot your-server.example.com
 
 # Verbose output
 hbc -v your-server.example.com
+
+# Send 'boot' and 'shutdown' messages on start and exit 
+hbc -b your-server.example.com
 ```
 
 You can also run it via the module entrypoint:

docs/PLUGIN_DEVELOPMENT.md

@@ -8,6 +8,7 @@ This guide explains how to create custom plugins for the Heartbeat monitoring sy
 - [Plugin Types](#plugin-types)
 - [Creating a Plugin](#creating-a-plugin)
 - [Plugin Lifecycle](#plugin-lifecycle)
+- [Server-initiated InfoPlugin refresh](#server-initiated-infoplugin-refresh)
 - [Configuration](#configuration)
 - [Best Practices](#best-practices)
 - [Examples](#examples)
@@ -250,6 +251,28 @@ Understanding the plugin lifecycle helps you implement plugins correctly:
    └─> Plugin releases resources, closes connections
 ```
 
+## Server-initiated InfoPlugin refresh
+
+When a heartbeat packet arrives from a host the server has no plugin data for (e.g. after a server restart), the server sets `request_update = 1` in the ACK reply. The client detects this flag and immediately re-runs all InfoPlugins — clearing their cached results first — then resends the data as PLG messages.
+
+This means InfoPlugin data will always reach the server as soon as possible without requiring a client restart. No action is needed from plugin authors: the framework handles cache invalidation and re-collection automatically.
+
+The lifecycle for this case looks like:
+
+```
+Server restarts, host reconnects
+   └─> hbd receives HTB with no existing plugin_data for host
+   └─> hbd sets request_update=1 in ACK
+
+Client receives ACK
+   └─> Detects request_update flag
+   └─> Clears _cache on every registered InfoPlugin
+   └─> Calls collect() on each InfoPlugin
+   └─> Sends fresh PLG messages to server
+```
+
+If you write an `InfoPlugin` with side effects in `_collect_info()` (opening connections, writing files, etc.), be aware it may be called more than once per client session when this mechanism triggers.
+
 ## Configuration
 
 ### Plugin-Specific Configuration

docs/USERS.md

@@ -46,6 +46,24 @@ default_owner: andreas            # owns hosts with no explicit owner
                                   # falls back to the first admin user if omitted
 ```
 
+### Client-declared host ownership
+
+A host can declare its own owner directly in the hbc or hbc_mini client configuration. This is useful for hosts that are not listed in the server config, or during initial setup before a server-side config entry has been created.
+
+**`~/.hbc.yaml`** (hbc):
+```yaml
+owner: andreas
+```
+
+**`~/.hbc.json`** (hbc_mini):
+```json
+{ "owner": "andreas" }
+```
+
+When set, the value is included in the `os_info` plugin data sent to the server. The server applies it as `host.owner` the first time `os_info` arrives, provided no owner has been configured server-side for that host. Server-configured ownership always takes precedence.
+
+---
+
 ### Assigning roles to hosts
 
 ```yaml

hbd/__init__.py

@@ -14,4 +14,4 @@ Install options:
 """
 
 __all__ = ["__version__"]
-__version__ = "5.2.0"
+__version__ = "5.2.4"

hbd/client/config.py

@@ -15,12 +15,15 @@ CLIENT_DEFAULTS = {
     # Network settings
     "hb_port": 50003,          # Port where hbd servers listen
     "interval": 10,             # Heartbeat interval in seconds
-    
+
+    # Host identity
+    "owner": None,             # Optional username to set as this host's owner on the server
+
     # Runtime flags
     "foreground": False,
     "verbose": False,
     "debug": 0,
-    
+
     # Plugin configuration
     "plugins": {},              # Per-plugin configuration
     "thresholds": {},           # Threshold configuration for monitoring

hbd/client/main.py

@@ -21,6 +21,7 @@ from typing import Dict, List, Optional
 # Import protocol and config
 from .config import load_config
 from ..common.proto import dicttos, stodict
+from .. import __version__
 
 # Import plugin system
 from .plugin import PluginRegistry, PluginLoader, InfoPlugin, MonitorPlugin
@@ -58,6 +59,7 @@ class AsyncConnection:
         self._dead = False
         self._ever_opened = False
         self._open_fail_count = 0   # consecutive failures before first success
+        self.request_info_event: asyncio.Event = asyncio.Event()
 
         self.logger = logging.getLogger(f"hbc.conn.{addr}")
 
@@ -137,6 +139,9 @@ class AsyncConnection:
         
         self.ackcount += 1
         self.logger.debug(f"ACK received, RTT: {rtt:.1f}ms")
+        if msg.get("request_update"):
+            self.logger.info("server requested plugin info refresh")
+            self.request_info_event.set()
 
 
 class HeartbeatProtocol(asyncio.DatagramProtocol):
@@ -172,9 +177,8 @@ class HeartbeatProtocol(asyncio.DatagramProtocol):
             self.logger.error(f"Error processing datagram: {e}", exc_info=True)
     
     def error_received(self, exc):
-        """Handle protocol errors."""
-        self.logger.warning(f"Protocol error on {self.connection.addr}: {exc} — dropping connection")
-        self.connection._dead = True
+        """Handle protocol errors — close transport so the heartbeat sender retries."""
+        self.logger.warning(f"Protocol error on {self.connection.addr}: {exc} — will retry")
         self.connection.close()
 
 
@@ -338,15 +342,35 @@ async def heartbeat_sender(conn: AsyncConnection, interval: int):
             raise
 
 
+async def _info_plugin_refresh_loop(conn: AsyncConnection, info_plugins: List):
+    """Wait for server requests to re-send InfoPlugin data."""
+    logger = logging.getLogger("hbc.plugins")
+    while running:
+        await conn.request_info_event.wait()
+        if not running:
+            break
+        conn.request_info_event.clear()
+        logger.info("refreshing InfoPlugins on server request")
+        for plugin in info_plugins:
+            plugin._cache = None
+            try:
+                data = await plugin.collect()
+                if data:
+                    await conn.sendto({"plugin": plugin.name, **data}, "PLG")
+                    logger.info(f"Resent {plugin.name} data")
+            except Exception as e:
+                logger.error(f"Error re-collecting {plugin.name}: {e}", exc_info=True)
+
+
 async def plugin_collector(conn: AsyncConnection, registry: PluginRegistry):
     """Collect and send plugin data.
-    
+
     Args:
         conn: Connection to send on
         registry: Plugin registry
     """
     logger = logging.getLogger("hbc.plugins")
-    
+
     # Collect InfoPlugins once at startup
     info_plugins = registry.get_by_type(InfoPlugin)
     for plugin in info_plugins:
@@ -359,34 +383,31 @@ async def plugin_collector(conn: AsyncConnection, registry: PluginRegistry):
                 logger.info(f"Sent {plugin.name} data")
         except Exception as e:
             logger.error(f"Error collecting {plugin.name}: {e}", exc_info=True)
-    
+
     # Schedule MonitorPlugins
     # Group plugins by interval
     from collections import defaultdict
     by_interval = defaultdict(list)
-    
+
     monitor_plugins = registry.get_by_type(MonitorPlugin)
     for plugin in monitor_plugins:
         by_interval[plugin.interval].append(plugin)
-    
-    # Create tasks for each interval
-    tasks = []
+
+    # Create tasks for each interval; always include the info-refresh watcher
+    tasks = [asyncio.create_task(_info_plugin_refresh_loop(conn, info_plugins))]
     for interval, plugins in by_interval.items():
-        task = asyncio.create_task(
+        tasks.append(asyncio.create_task(
             plugin_collector_interval(conn, plugins, interval)
-        )
-        tasks.append(task)
-    
-    # Wait for all tasks
-    if tasks:
-        try:
-            await asyncio.gather(*tasks, return_exceptions=True)
-        except asyncio.CancelledError:
-            logger.debug("Plugin collector cancelled, cancelling sub-tasks")
-            for task in tasks:
-                if not task.done():
-                    task.cancel()
-            raise
+        ))
+
+    try:
+        await asyncio.gather(*tasks, return_exceptions=True)
+    except asyncio.CancelledError:
+        logger.debug("Plugin collector cancelled, cancelling sub-tasks")
+        for task in tasks:
+            if not task.done():
+                task.cancel()
+        raise
 
 
 async def plugin_collector_interval(
@@ -464,7 +485,7 @@ async def cleanup(connections: List[AsyncConnection]):
     logger.info("Cleaning up connections")
     
     target = next((c for c in connections if c.transport), connections[0] if connections else None)
-    if target:
+    if target and send_shutdown:
         try:
             await target.sendto({"shutdown": 1, "acks": target.ackcount})
         except Exception as e:
@@ -478,7 +499,7 @@ async def cleanup(connections: List[AsyncConnection]):
 
 async def async_main(args, config):
     """Async main function."""
-    global running, shutdown_event, active_tasks
+    global running, shutdown_event, active_tasks, send_shutdown 
     
     # Create shutdown event
     shutdown_event = asyncio.Event()
@@ -495,8 +516,7 @@ async def async_main(args, config):
     hb_port = config.get("hb_port", PORT)
     interval = config.get("interval", INTERVAL)
     
-    logger.info(f"Starting hbc for {iam} -> {hb_hosts}")
-    logger.info(f"Port: {hb_port}, Interval: {interval}s")
+    logger.info(f"hbc {__version__} on {iam} -> {hb_hosts} port={hb_port}, interval={interval}s")
     
     # Create connections
     connections = []
@@ -526,10 +546,13 @@ async def async_main(args, config):
     logger.info(f"Created {len(connections)} connections")
     
     # Send boot/message if requested
+    send_shutdown = False
     if args.boot or args.message:
         boot_msg = {}
         if args.boot:
             boot_msg["boot"] = 1
+            args.boot = False  # Clear boot flag so we don't send it again in main loop
+            send_shutdown = True
         if args.message:
             boot_msg["service"] = "service"
             boot_msg["msg"] = args.message

hbd/client/plugin.py

@@ -364,7 +364,10 @@ class PluginLoader:
                     
                     # Instantiate plugin with config — check plugins subdict first,
                     # then top-level keys (e.g. nagios_runner: ... at root of config).
-                    plugin_instance_config = plugins_subconfig.get(obj.name) or raw_config.get(obj.name, {})
+                    plugin_instance_config = dict(plugins_subconfig.get(obj.name) or raw_config.get(obj.name) or {})
+                    # Propagate top-level owner so os_info (and any future plugin) can report it.
+                    if "owner" in raw_config and "owner" not in plugin_instance_config:
+                        plugin_instance_config["owner"] = raw_config["owner"]
                     plugin = obj(config=plugin_instance_config)
                     
                     # Initialize plugin

hbd/client/plugins/os_info.py

@@ -62,6 +62,9 @@ class OSInfoPlugin(InfoPlugin):
                 "hbc_version": hbc_version,
                 "hbc_type": "full",
             }
+            if self.config.get("owner"):
+                self.logger.debug(f"Adding owner from config: {self.config['owner']}")
+                data["owner"] = self.config["owner"]
             
             # Add Linux-specific distribution info
             if platform.system() == "Linux":

hbd/client/plugins/ping_monitor.py

@@ -13,12 +13,8 @@ plugins:
     count: 3              # ICMP packets per ping run (default 3)
     timeout: 5            # seconds before a host is considered unreachable (default 5)
     hosts:
-      8.8.8.8:
-        warning: 20.0     # ms
-        critical: 100.0   # ms
-      192.168.1.1:
-        warning: 5.0
-        critical: 20.0
+      - 8.8.8.8
+      - 192.168.1.1
 ```
 
 Reported metrics per host (metric key uses the hostname with dots/colons replaced

hbd/server/config.py

@@ -309,7 +309,7 @@ def get_host_access(config, hostname) -> dict:
     """
     host_cfg = get_host_config(config, hostname)
 
-    owner = host_cfg.get("owner") or get_default_owner(config)
+    owner = host_cfg.get("owner") # or get_default_owner(config)
 
     managers = host_cfg.get("managers", [])
     if isinstance(managers, str):

hbd/server/main.py

@@ -475,6 +475,8 @@ def run(config, config_path=None):
     if config.get("debug", 0) > 0:
         log_level = logging.DEBUG
     logging.basicConfig(level=log_level)
+    if not config.get("debug", 0):
+        logging.getLogger("aiohttp.access").propagate = False
     load_pickled_hosts(config, hbdclass)
 
     notify_mod.initlog(logfile=config.get("logfile", "messages.log"))

hbd/server/notify.py

@@ -106,11 +106,18 @@ def closelog():
 
 def eventlog(host, lvl, m, service=None):
     ts = time.time()
+    msg = {
+        "ts": ts,
+        "host": host or None,
+        "level": lvl,
+        "service": service,
+        "message": m,
+    }
+    data.msgs.append(msg)
     s = f"{time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(ts))} {lvl} "
     if host:
         s += f"{host} "
     s += m
-    data.msgs.append(s)
     logger.info(s)
     if logf:
         try:
@@ -118,7 +125,7 @@ def eventlog(host, lvl, m, service=None):
             logf.flush()
         except Exception as e:
             logger.warning("failed to write to logfile: %s", e)
-    msg_to_websockets("message", s)
+    msg_to_websockets("message", msg)
 
 
 # ---------------------------------------------------------------------------
@@ -209,7 +216,7 @@ def _send_mattermost(channel_cfg: dict, notif: Notification) -> bool:
         return False
     text = f"**{notif.title}**\n{notif.body}"
     if notif.url:
-        text += f"\n[Plugin metrics]({notif.url})"
+        text += f"\n[Plugin metrics] {notif.url}"
     ses = {"url": host, "scheme": "http", "basepath": "/api/v4", "port": 8065}
     mm = Driver(ses)
     payload: dict = {"text": text, "channel": channel, "username": channel_cfg.get("username", "hbd")}

hbd/server/templates/alerts.html

@@ -184,9 +184,9 @@
     }
 
     .alert-metric {
-      color: #666;
-      font-family: 'Courier New', monospace;
-      font-size: 0.9em;
+      color: #0066cc;
+      font-size: 1.1em;
+      font-weight: normal;
     }
 
     .alert-details {
@@ -438,8 +438,8 @@
               <div class="alert-header">
                 <span class="alert-level ${level}">${alert.level}</span>
                 <a class="alert-hostname" href="/plugins#${alert.hostname}">${alert.hostname}</a>
+                <span class="alert-metric">${(alert.metric_path.includes('.') ? alert.metric_path.slice(alert.metric_path.indexOf('.') + 1) : alert.metric_path).replace(/_status_code$/, '')}</span>
               </div>
-              <div class="alert-metric">${alert.metric_path}</div>
               <div class="alert-details">
                 <span>${valueText}</span>
                 <span class="alert-duration">Active for ${duration}</span>

hbd/server/templates/head.html

@@ -214,7 +214,7 @@
         ctx.restore();
       }
 
-      hand((m + s / 60) / 60 * Math.PI * 2 - Math.PI / 2,
+      hand((sFrac >= 58.5 ? m + 1 : m) / 60 * Math.PI * 2 - Math.PI / 2,
            R * 0.88, -R * 0.12, SIZE * 0.027, '#222');           /* minute */
       hand((h + m / 60) / 12 * Math.PI * 2 - Math.PI / 2,
            R * 0.58, -R * 0.12, SIZE * 0.039, '#222');           /* hour   */

hbd/server/templates/live.html

@@ -183,11 +183,24 @@
       line-height: 1.0;
     }
 
-    #messages div {
+    #messages .log-entry {
       padding: 5px 0;
       border-bottom: 1px solid #f0f0f0;
+      display: flex;
+      gap: 0.5em;
+      align-items: baseline;
     }
 
+    .log-ts { color: #888; white-space: nowrap; }
+    .log-level { font-weight: bold; min-width: 6em; }
+    .log-host { font-weight: 600; }
+    .log-service { color: #888; }
+
+    .log-warning .log-level  { color: #b8860b; }
+    .log-critical .log-level { color: #c00; }
+    .log-recover .log-level  { color: #2a7a2a; }
+    .log-info .log-level     { color: #555; }
+
     /* Modal for connection status messages */
     .connection-modal {
       display: none;
@@ -460,7 +473,20 @@
             update_table(state.data);
           } else if (state.type == "message") {
             var msgs = document.getElementById("messages");
-            msgs.insertAdjacentHTML("afterbegin", "<div>" + state.data + "</div>");
+            var msg = state.data;
+            var _d = new Date(msg.ts * 1000);
+            function _p(n) { return n < 10 ? '0' + n : '' + n; }
+            var ts_str = _d.getFullYear() + '-' + _p(_d.getMonth()+1) + '-' + _p(_d.getDate())
+                       + ' ' + _p(_d.getHours()) + ':' + _p(_d.getMinutes()) + ':' + _p(_d.getSeconds());
+            var lvl = (msg.level || "INFO").toLowerCase();
+            var html = '<div class="log-entry log-' + lvl + '">';
+            html += '<span class="log-ts">' + ts_str + '</span>';
+            html += '<span class="log-level">' + (msg.level || "") + '</span>';
+            if (msg.host) html += '<span class="log-host">' + msg.host + '</span>';
+            if (msg.service) html += '<span class="log-service">' + msg.service + '</span>';
+            html += '<span class="log-msg">' + msg.message + '</span>';
+            html += '</div>';
+            msgs.insertAdjacentHTML("afterbegin", html);
           }
           cnt++;
         };

hbd/server/threshold.py

@@ -1043,7 +1043,10 @@ class ThresholdChecker:
         
         # Format operator symbol
         op_symbol = threshold.operator.value
-        
+
+        # Short metric label: strip the plugin-name prefix and _status_code suffix
+        short_path = (metric_path.partition(".")[2] or metric_path).removesuffix("_status_code")
+
         # Use a display-friendly value (inf is the sentinel for "overdue")
         import math
         display_value = "overdue" if isinstance(value, float) and math.isinf(value) else value
@@ -1065,25 +1068,25 @@ class ThresholdChecker:
 
         if new_level == AlertLevel.OK:
             lvl = "RECOVER"
-            message = f"{metric_path} = {display_value} ({old_level.name} -> OK)"
+            message = f"{short_path} = {display_value} ({old_level.name} -> OK)"
         elif new_level == AlertLevel.WARNING:
             lvl = "WARNING"
             if has_display:
-                message = f"{metric_path} = {display_value} {_fmt()}"
+                message = f"{short_path} = {display_value} {_fmt()}"
             else:
-                message = f"{metric_path} = {display_value}"
+                message = f"{short_path} = {display_value}"
         elif new_level == AlertLevel.CRITICAL:
             lvl = "CRITICAL"
             if has_display:
-                message = f"{metric_path} = {display_value} {_fmt()}"
+                message = f"{short_path} = {display_value} {_fmt()}"
             else:
-                message = f"{metric_path} = {display_value}"
+                message = f"{short_path} = {display_value}"
         else:
             lvl = "UNKNOWN"
             if has_display:
-                message = f"{metric_path} = {display_value} {_fmt()}"
+                message = f"{short_path} = {display_value} {_fmt()}"
             else:
-                message = f"{metric_path} = {display_value}"
+                message = f"{short_path} = {display_value}"
 
         # Formatted threshold info stored on AlertState for the UI
         formatted_threshold_msg = _fmt() if has_display and new_level != AlertLevel.OK else None
@@ -1106,11 +1109,16 @@ class ThresholdChecker:
         if host is not None and not host.watched:
             eventlog(host_name, lvl, message, service="threshold")
             return
+        short_path = (metric_path.partition(".")[2] or metric_path).removesuffix("_status_code")
+        title = f"[{lvl}] {host_name}  {short_path}"
+        # Strip the "metric = " prefix from message so body is just the value/detail
+        prefix = short_path + " = "
+        body = message[len(prefix):] if message.startswith(prefix) else message
         asyncio.get_event_loop().create_task(notify_mod.send_notification(
             host_name,
             notify_mod.Notification(
-                title=f"[{lvl}] {host_name}",
-                body=message,
+                title=title,
+                body=body,
                 level=lvl,
             ),
         ))
@@ -1157,6 +1165,9 @@ class ThresholdChecker:
         Returns:
             Formatted display string
         """
+        if not display_format:
+            display_format = "(threshold: {op_symbol} {threshold_value})" if threshold_value is not None else ""
+
         # Build format context with standard variables
         format_context = {
             'value': value,
@@ -1338,7 +1349,8 @@ class ThresholdChecker:
             
             # Format operator symbol
             op_symbol = threshold.operator.value
-            
+            short_path = (metric_path.partition(".")[2] or metric_path).removesuffix("_status_code")
+
             # Time to re-notify
             if threshold_value is not None:
                 # Use display format string
@@ -1351,18 +1363,19 @@ class ThresholdChecker:
                     check_name=check_name,
                     metric_name=metric_name,
                 )
-                message = f"REMINDER ({alert_state.level.name}): {host_name} - {metric_path} = {value} {threshold_info}, ongoing for {int(now - alert_state.since)}s"
+                body = f"{value} {threshold_info}, ongoing for {int(now - alert_state.since)}s"
             else:
-                message = f"REMINDER ({alert_state.level.name}): {host_name} - {metric_path} = {value} (ongoing for {int(now - alert_state.since)}s)"
-            
+                body = f"{value} (ongoing for {int(now - alert_state.since)}s)"
+            message = f"REMINDER ({alert_state.level.name}): {host_name} - {short_path} = {body}"
+
             from . import hbdclass
             host = hbdclass.Host.hosts.get(host_name)
             if host is None or host.watched:
                 asyncio.get_event_loop().create_task(notify_mod.send_notification(
                     host_name,
                     notify_mod.Notification(
-                        title=f"[REMINDER/{alert_state.level.name}] {host_name}",
-                        body=message,
+                        title=f"[REMINDER/{alert_state.level.name}] {host_name}  {short_path}",
+                        body=body,
                         level=alert_state.level.name,
                     ),
                 ))

hbd/server/udp.py

@@ -336,8 +336,7 @@ def handle_datagram(msg: dict, addr, transport, ctx: dict):
         # Apply user-access settings from config
         access = config_mod.get_host_access(cfg, uname)
         host.apply_access(access["owner"], access["managers"], access["monitors"])
-        if verbose:
-            print(("XX: New host, num now %s" % (len(hbdcls.Host.hosts))))
+        logger.info("New host signed on: %s (dyn=%s, access=%s)", uname, host.dyn, access)
         newh = True
     else:
         host = hbdcls.Host.hosts[uname]
@@ -351,8 +350,10 @@ def handle_datagram(msg: dict, addr, transport, ctx: dict):
 
     if msg.get("ID") == "HTB":
         host.doesack = msg.get("acks", -1)
-        # send ACK back
+        # send ACK back; ask client to resend plugin info when we have none yet
         rmsg = {"time": time.time()}
+        if not host.plugin_data:
+            rmsg["request_update"] = 1
         opkt = dicttos("ACK", rmsg)
         try:
             transport.sendto(opkt, addr)
@@ -369,6 +370,11 @@ def handle_datagram(msg: dict, addr, transport, ctx: dict):
                            if k not in ("ID", "plugin", "id", "name")}
             # Store plugin data with timestamp
             host.add_plugin_data(plugin_name, plugin_data, timestamp=now)
+
+            # If os_info reports an owner and none is configured server-side, apply it
+            if plugin_name == "os_info":
+                if not host.owner:
+                    host.owner = plugin_data.get("owner", config_mod.get_default_owner(cfg))
             if DEBUG > 1:
                 print(f"Stored plugin data for {uname}: {plugin_name}")
             

hbd/server/ws.py

@@ -85,11 +85,13 @@ async def handler(request):
             except Exception as e:
                 logger.error("Error sending initial hosts: %s", e)
 
-        # Send recent messages
+        # Send recent messages, filtered to hosts this user may see
         if data.msgs:
             try:
                 for m in data.msgs:
-                    await ws.send_str(json.dumps({"type": "message", "data": m}))
+                    host_name = m.get("host") if isinstance(m, dict) else None
+                    if not host_name or _user_can_see_host(user, host_name):
+                        await ws.send_str(json.dumps({"type": "message", "data": m}))
             except Exception as e:
                 logger.error("Error sending initial messages: %s", e)
 
@@ -128,6 +130,8 @@ def broadcast(typ: str, payload) -> bool:
     host_name: Optional[str] = None
     if typ in ("host", "plugin"):
         host_name = payload.get("raw_name") or payload.get("host") or payload.get("name")
+    elif typ == "message" and isinstance(payload, dict):
+        host_name = payload.get("host")
 
     jmsg = json.dumps({"type": typ, "data": payload})
 

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "hbd"
-version = "5.2.0"
+version = "5.2.4"
 description = "Heartbeat monitoring system — client (hbc) and server (hbd)"
 readme = "README.md"
 requires-python = ">=3.11"

scripts/hbc_mini.py

@@ -41,7 +41,7 @@ from pathlib import Path
 from typing import Any, Dict, List, Optional, Tuple
 
 # updated by scripts/bumpminor.sh
-__version__ = "5.2.0"
+__version__ = "5.2.4"
 
 # ---------------------------------------------------------------------------
 # Protocol  (mirrors hbd/common/proto.py)
@@ -114,6 +114,7 @@ def _stodict(data: bytes) -> Dict[str, Any]:
 _DEFAULTS: Dict[str, Any] = {
     "hb_port": 50003,
     "interval": 10,
+    "owner": None,
     "plugins": {},
 }
 
@@ -239,6 +240,8 @@ class OSInfoPlugin(InfoPlugin):
             "hbc_version": __version__,
             "hbc_type": "mini",
         }
+        if self.config.get("owner"):
+            data["owner"] = self.config["owner"]
         if platform.system() == "Linux":
             data.update(_linux_distro())
         elif platform.system() == "Darwin":
@@ -716,7 +719,9 @@ async def _load_plugins(cfg: Dict[str, Any]) -> List[Plugin]:
     plugins_cfg: Dict[str, Any] = cfg.get("plugins", {})
     loaded: List[Plugin] = []
     for cls in _ALL_PLUGIN_CLASSES:
-        plugin_cfg = plugins_cfg.get(cls.name) or cfg.get(cls.name, {})
+        plugin_cfg = dict(plugins_cfg.get(cls.name) or cfg.get(cls.name) or {})
+        if "owner" in cfg and "owner" not in plugin_cfg:
+            plugin_cfg["owner"] = cfg["owner"]
         plugin: Plugin = cls(config=plugin_cfg)
         try:
             ok = await plugin.initialize()
@@ -786,7 +791,7 @@ class _HeartbeatProtocol(asyncio.DatagramProtocol):
             msg_id = msg.get("ID")
             now = time.time()
             if msg_id == "ACK":
-                self._conn._handle_ack(now)
+                self._conn._handle_ack(msg, now)
             elif msg_id == "CMD":
                 asyncio.create_task(_handle_command(self._conn, msg))
             elif msg_id == "UPD":
@@ -797,8 +802,7 @@ class _HeartbeatProtocol(asyncio.DatagramProtocol):
             self._log.error("datagram error: %s", e)
 
     def error_received(self, exc):
-        self._log.warning("protocol error on %s: %s — dropping connection", self._conn.addr, exc)
-        self._conn._dead = True
+        self._log.warning("protocol error on %s: %s — will retry", self._conn.addr, exc)
         self._conn.close()
 
 
@@ -814,6 +818,7 @@ class AsyncConnection:
         self.rtts: List[float] = [0.0]
         self._transport: Optional[asyncio.DatagramTransport] = None
         self._dead = False
+        self._request_info: asyncio.Event = asyncio.Event()
         self._log = logging.getLogger(f"hbc.conn.{addr}")
 
     async def open(self) -> bool:
@@ -832,12 +837,14 @@ class AsyncConnection:
             self._transport.close()
             self._transport = None
 
-    def _handle_ack(self, now: float):
+    def _handle_ack(self, msg: Dict[str, Any], now: float):
         rtt = (now - self.lastsend) * 1000.0
         self.rtts.append(rtt)
         if len(self.rtts) > 10:
             self.rtts.pop(0)
         self.ackcount += 1
+        if msg.get("request_update"):
+            self._request_info.set()
 
     async def sendto(self, msg: Dict[str, Any], msg_id: str = "HTB"):
         if self._dead:
@@ -970,6 +977,19 @@ async def _run_monitor_group(conn: AsyncConnection, plugins: List[Plugin], inter
         await _sleep(interval)
 
 
+async def _info_refresh_loop(conn: AsyncConnection, info: List[Plugin]):
+    log = logging.getLogger("hbc.plugins")
+    while _running:
+        await conn._request_info.wait()
+        if not _running:
+            break
+        conn._request_info.clear()
+        log.info("refreshing InfoPlugins on server request")
+        for plugin in info:
+            plugin._cache = None
+        await _run_info_plugins(conn, info)
+
+
 async def _plugin_collector(conn: AsyncConnection, plugins: List[Plugin]):
     info = [p for p in plugins if isinstance(p, InfoPlugin)]
     monitor = [p for p in plugins if isinstance(p, MonitorPlugin)]
@@ -980,12 +1000,10 @@ async def _plugin_collector(conn: AsyncConnection, plugins: List[Plugin]):
     for p in monitor:
         by_interval[p.interval].append(p)
 
-    if by_interval:
-        await asyncio.gather(
-            *[asyncio.create_task(_run_monitor_group(conn, grp, iv))
-              for iv, grp in by_interval.items()],
-            return_exceptions=True,
-        )
+    tasks = [asyncio.create_task(_info_refresh_loop(conn, info))]
+    tasks += [asyncio.create_task(_run_monitor_group(conn, grp, iv))
+              for iv, grp in by_interval.items()]
+    await asyncio.gather(*tasks, return_exceptions=True)
 
 
 # ---------------------------------------------------------------------------
@@ -1029,7 +1047,7 @@ def _reconfigure_syslog(level: int):
 # ---------------------------------------------------------------------------
 
 async def _async_main(args, cfg: Dict[str, Any]) -> int:
-    global _running, _shutdown_event, _active_tasks
+    global _running, _shutdown_event, _active_tasks, send_shutdown
     _running = True
     _shutdown_event = asyncio.Event()
     _active_tasks = []
@@ -1039,7 +1057,7 @@ async def _async_main(args, cfg: Dict[str, Any]) -> int:
     port = cfg.get("hb_port", PORT)
     interval = cfg.get("interval", INTERVAL)
 
-    log.info("starting: %s -> %s port=%d interval=%ds", iam, args.hosts, port, interval)
+    log.info("hbc_mini %s on %s -> %s port=%d interval=%ds",__version__, iam, args.hosts, port, interval)
 
     connections: List[AsyncConnection] = []
     conn_id = 1
@@ -1060,10 +1078,13 @@ async def _async_main(args, cfg: Dict[str, Any]) -> int:
         return 1
 
     # Boot / one-shot message
+    send_shutdown = False
     if args.boot or args.message:
         bmsg: Dict[str, Any] = {"acks": 0}
         if args.boot:
             bmsg["boot"] = 1
+            args.boot = False  # don't repeat on restart
+            send_shutdown = True
         if args.message:
             bmsg["service"] = "service"
             bmsg["msg"] = args.message
@@ -1101,7 +1122,7 @@ async def _async_main(args, cfg: Dict[str, Any]) -> int:
 
     log.info("shutting down")
     target = next((c for c in connections if c._transport), connections[0] if connections else None)
-    if target:
+    if target and send_shutdown:
         try:
             await target.sendto({"shutdown": 1, "acks": target.ackcount})
         except Exception: