version 5.2.2

error_received() no longer sets _dead=True; it just closes the transport
so the existing retry loop in heartbeat_sender (hbc) and sendto (hbc_mini)
reopens the connection on the next interval. This allows hbc to recover
when it starts before network connectivity is established.

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

hbd/__init__.py

@@ -14,4 +14,4 @@ Install options:
 """
 
 __all__ = ["__version__"]
-__version__ = "5.2.0"
+__version__ = "5.2.2"

hbd/client/main.py

@@ -172,9 +172,8 @@ 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()
 
 

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/templates/alerts.html

@@ -439,7 +439,7 @@
                 <span class="alert-level ${level}">${alert.level}</span>
                 <a class="alert-hostname" href="/plugins#${alert.hostname}">${alert.hostname}</a>
               </div>
-              <div class="alert-metric">${alert.metric_path}</div>
+              <div class="alert-metric">${alert.metric_path.includes('.') ? alert.metric_path.slice(alert.metric_path.indexOf('.') + 1) : alert.metric_path}</div>
               <div class="alert-details">
                 <span>${valueText}</span>
                 <span class="alert-duration">Active for ${duration}</span>

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 for readability
+        short_path = metric_path.partition(".")[2] or metric_path
+
         # 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
@@ -1157,6 +1160,9 @@ 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 +1344,8 @@ class ThresholdChecker:
             
             # Format operator symbol
             op_symbol = threshold.operator.value
-            
+            short_path = metric_path.partition(".")[2] or metric_path
+
             # Time to re-notify
             if threshold_value is not None:
                 # Use display format string
@@ -1351,9 +1358,9 @@ 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"
+                message = f"REMINDER ({alert_state.level.name}): {host_name} - {short_path} = {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)"
+                message = f"REMINDER ({alert_state.level.name}): {host_name} - {short_path} = {value} (ongoing for {int(now - alert_state.since)}s)"
             
             from . import hbdclass
             host = hbdclass.Host.hosts.get(host_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]

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "hbd"
-version = "5.2.0"
+version = "5.2.2"
 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__ = "5.2.2"
 
 # ---------------------------------------------------------------------------
 # Protocol  (mirrors hbd/common/proto.py)
@@ -797,8 +797,7 @@ 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()