feat: async subprocess in nagios_runner with stderr capture and signal handling

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

hbd/client/plugins/nagios_runner.py

@@ -21,8 +21,9 @@ nagios_runner:
 ```
 """
 
+import asyncio
+import os
 import re
-import subprocess
 from typing import Any, Dict, List, Optional, Tuple
 
 from hbd.client.plugin import MonitorPlugin
@@ -76,7 +77,6 @@ class NagiosRunnerPlugin(MonitorPlugin):
         # Extract configuration
         self.commands: List[Dict[str, str]] = config.get("commands", []) if config else []
         self.timeout: int = config.get("timeout", 30) if config else 30
-        self.shell: bool = config.get("shell", True) if config else True
         self.interval = config.get("interval", 300) if config else 300
     
     async def initialize(self) -> bool:
@@ -135,7 +135,7 @@ class NagiosRunnerPlugin(MonitorPlugin):
                     for metric_name, metric_value in perfdata.items():
                         results[f"{name}_{metric_name}"] = metric_value
                 
-                self.logger.debug(
+                self.logger.info(
                     f"Executed {name}: {STATUS_NAMES.get(status_code, 'UNKNOWN')} - {output[:50]}"
                 )
                 
@@ -157,46 +157,49 @@ class NagiosRunnerPlugin(MonitorPlugin):
         self,
         command: str
     ) -> Tuple[int, str, Dict[str, Any]]:
-        """Execute a Nagios plugin and parse its output.
+        """Execute a Nagios plugin and parse its output."""
-        
-        Args:
-            command: Command string to execute
-            
-        Returns:
-            Tuple of (status_code, output_message, performance_data_dict)
-        """
         try:
-            # Run command
+            proc = await asyncio.create_subprocess_shell(
-            result = subprocess.run(
                 command,
-                shell=self.shell,
+                stdout=asyncio.subprocess.PIPE,
-                capture_output=True,
+                stderr=asyncio.subprocess.PIPE,
-                timeout=self.timeout,
-                text=True
             )
-            
+            try:
-            status_code = result.returncode
+                stdout_bytes, stderr_bytes = await asyncio.wait_for(
-            output = result.stdout.strip()
+                    proc.communicate(), timeout=self.timeout
-            
+                )
-            # Nagios plugins can return codes > 3, treat as UNKNOWN
+            except asyncio.TimeoutError:
+                proc.kill()
+                await proc.communicate()
+                self.logger.error(f"Command timed out: {command}")
+                return NAGIOS_UNKNOWN, f"Command timed out after {self.timeout}s", {}
+
+            status_code = proc.returncode
+
+            if status_code < 0:
+                return NAGIOS_UNKNOWN, f"Process killed by signal {-status_code}", {}
+
             if status_code > 3:
                 status_code = NAGIOS_UNKNOWN
-            
+
-            # Parse performance data
+            stdout = stdout_bytes.decode(errors="replace").strip()
-            perfdata = self._parse_perfdata(output)
+            stderr = stderr_bytes.decode(errors="replace").strip()
-            
+
-            # Extract just the status message (before the pipe if present)
+            # Parse perfdata from stdout before mixing in stderr
-            if '|' in output:
+            perfdata = self._parse_perfdata(stdout)
-                output_msg = output.split('|')[0].strip()
+
+            # Build status message
+            status_part = stdout.split('|')[0].strip() if '|' in stdout else stdout
+
+            if not stdout and stderr:
+                output_msg = stderr
+            elif stdout and stderr:
+                output_msg = f"{status_part} [stderr: {stderr}]"
             else:
-                output_msg = output
+                output_msg = status_part
-            
+
             return status_code, output_msg, perfdata
-            
+
-        except subprocess.TimeoutExpired:
-            self.logger.error(f"Command timed out: {command}")
-            return NAGIOS_UNKNOWN, f"Command timed out after {self.timeout}s", {}
-        
         except Exception as e:
             self.logger.error(f"Error executing command: {e}")
             return NAGIOS_UNKNOWN, f"Execution error: {str(e)}", {}

tests/test_nagios_runner.py

@@ -20,3 +20,43 @@ def test_no_commands_sets_skip_reason():
     assert result is False
     assert plugin.skip_reason is not None
     assert "nagios_runner.commands" in plugin.skip_reason
+
+
+def test_stderr_used_when_stdout_empty(tmp_path):
+    script = tmp_path / "check_err.sh"
+    script.write_text("#!/bin/sh\necho 'error from stderr' >&2\nexit 2\n")
+    script.chmod(script.stat().st_mode | stat.S_IEXEC)
+
+    config = {"commands": [{"name": "t", "command": str(script)}], "timeout": 5}
+    plugin = NagiosRunnerPlugin(config=config)
+    asyncio.run(plugin.initialize())
+    data = asyncio.run(plugin._collect_metrics())
+
+    assert "error from stderr" in data["t_output"]
+    assert data["t_status_code"] == NAGIOS_CRITICAL
+
+
+def test_stderr_appended_when_both_present(tmp_path):
+    script = tmp_path / "check_both.sh"
+    script.write_text("#!/bin/sh\necho 'OK - all good'\necho 'extra detail' >&2\nexit 0\n")
+    script.chmod(script.stat().st_mode | stat.S_IEXEC)
+
+    config = {"commands": [{"name": "t", "command": str(script)}], "timeout": 5}
+    plugin = NagiosRunnerPlugin(config=config)
+    asyncio.run(plugin.initialize())
+    data = asyncio.run(plugin._collect_metrics())
+
+    assert "OK - all good" in data["t_output"]
+    assert "extra detail" in data["t_output"]
+    assert data["t_status_code"] == NAGIOS_OK
+
+
+def test_negative_returncode_maps_to_unknown():
+    # kill -9 $$ kills the shell itself; asyncio sees returncode -9
+    config = {"commands": [{"name": "t", "command": "kill -9 $$"}], "timeout": 5}
+    plugin = NagiosRunnerPlugin(config=config)
+    asyncio.run(plugin.initialize())
+    data = asyncio.run(plugin._collect_metrics())
+
+    assert data["t_status_code"] == NAGIOS_UNKNOWN
+    assert "signal" in data["t_output"].lower()