From 014a5b712d4cdc352b68e2510e11d0a372fd4a3d Mon Sep 17 00:00:00 2001
From: teknium1 <teknium1@gmail.com>
Date: Thu, 5 Mar 2026 20:35:33 -0800
Subject: [PATCH] fix: prevent duplicate gateway instances from running
 simultaneously

start_gateway() now checks for an existing running instance via PID file
before starting. If another gateway is already running under the same
HERMES_HOME, it refuses to start with a clear error message directing the
user to 'hermes gateway restart' or 'hermes gateway stop'.

Also fixes gateway/status.py to respect the HERMES_HOME env var instead of
hardcoding ~/.hermes. This scopes the PID file per HERMES_HOME directory,
which lays the groundwork for future multi-profile support where distinct
HERMES_HOME directories can run concurrent gateway instances independently.
---
 gateway/run.py    | 21 ++++++++++++++++++++
 gateway/status.py | 50 ++++++++++++++++++++++++++++++++++-------------
 2 files changed, 57 insertions(+), 14 deletions(-)

diff --git a/gateway/run.py b/gateway/run.py
index 2ed9ed8c2..3af04f1ea 100644
--- a/gateway/run.py
+++ b/gateway/run.py
@@ -2389,6 +2389,27 @@ async def start_gateway(config: Optional[GatewayConfig] = None) -> bool:
     Returns True if the gateway ran successfully, False if it failed to start.
     A False return causes a non-zero exit code so systemd can auto-restart.
     """
+    # ── Duplicate-instance guard ──────────────────────────────────────
+    # Prevent two gateways from running under the same HERMES_HOME.
+    # The PID file is scoped to HERMES_HOME, so future multi-profile
+    # setups (each profile using a distinct HERMES_HOME) will naturally
+    # allow concurrent instances without tripping this guard.
+    from gateway.status import get_running_pid
+    existing_pid = get_running_pid()
+    if existing_pid is not None and existing_pid != os.getpid():
+        hermes_home = os.getenv("HERMES_HOME", "~/.hermes")
+        logger.error(
+            "Another gateway instance is already running (PID %d, HERMES_HOME=%s). "
+            "Use 'hermes gateway restart' to replace it, or 'hermes gateway stop' first.",
+            existing_pid, hermes_home,
+        )
+        print(
+            f"\n❌ Gateway already running (PID {existing_pid}).\n"
+            f"   Use 'hermes gateway restart' to replace it,\n"
+            f"   or 'hermes gateway stop' to kill it first.\n"
+        )
+        return False
+
     # Configure rotating file log so gateway output is persisted for debugging
     log_dir = _hermes_home / 'logs'
     log_dir.mkdir(parents=True, exist_ok=True)
diff --git a/gateway/status.py b/gateway/status.py
index f28adc880..78d71947f 100644
--- a/gateway/status.py
+++ b/gateway/status.py
@@ -3,37 +3,59 @@ Gateway runtime status helpers.
 
 Provides PID-file based detection of whether the gateway daemon is running,
 used by send_message's check_fn to gate availability in the CLI.
+
+The PID file lives at ``{HERMES_HOME}/gateway.pid``.  HERMES_HOME defaults to
+``~/.hermes`` but can be overridden via the environment variable.  This means
+separate HERMES_HOME directories naturally get separate PID files — a property
+that will be useful when we add named profiles (multiple agents running
+concurrently under distinct configurations).
 """
 
 import os
 from pathlib import Path
+from typing import Optional
 
-_PID_FILE = Path.home() / ".hermes" / "gateway.pid"
+
+def _get_pid_path() -> Path:
+    """Return the path to the gateway PID file, respecting HERMES_HOME."""
+    home = Path(os.getenv("HERMES_HOME", Path.home() / ".hermes"))
+    return home / "gateway.pid"
 
 
 def write_pid_file() -> None:
     """Write the current process PID to the gateway PID file."""
-    _PID_FILE.parent.mkdir(parents=True, exist_ok=True)
-    _PID_FILE.write_text(str(os.getpid()))
+    pid_path = _get_pid_path()
+    pid_path.parent.mkdir(parents=True, exist_ok=True)
+    pid_path.write_text(str(os.getpid()))
 
 
 def remove_pid_file() -> None:
     """Remove the gateway PID file if it exists."""
     try:
-        _PID_FILE.unlink(missing_ok=True)
+        _get_pid_path().unlink(missing_ok=True)
     except Exception:
         pass
 
 
+def get_running_pid() -> Optional[int]:
+    """Return the PID of a running gateway instance, or ``None``.
+
+    Checks the PID file and verifies the process is actually alive.
+    Cleans up stale PID files automatically.
+    """
+    pid_path = _get_pid_path()
+    if not pid_path.exists():
+        return None
+    try:
+        pid = int(pid_path.read_text().strip())
+        os.kill(pid, 0)  # signal 0 = existence check, no actual signal sent
+        return pid
+    except (ValueError, ProcessLookupError, PermissionError):
+        # Stale PID file — process is gone
+        remove_pid_file()
+        return None
+
+
 def is_gateway_running() -> bool:
     """Check if the gateway daemon is currently running."""
-    if not _PID_FILE.exists():
-        return False
-    try:
-        pid = int(_PID_FILE.read_text().strip())
-        os.kill(pid, 0)  # signal 0 = existence check, no actual signal sent
-        return True
-    except (ValueError, ProcessLookupError, PermissionError):
-        # Stale PID file -- process is gone
-        remove_pid_file()
-        return False
+    return get_running_pid() is not None