fix(gateway): /stop and /new bypass Level 1 active-session guard

The base adapter's Level 1 guard intercepted ALL messages while an
agent was running, including /stop and /new. These commands were queued
as pending messages instead of being dispatched to the gateway runner's
Level 2 handler. When the agent eventually stopped (via the interrupt
mechanism), the command text leaked into the conversation as a user
message — the model would receive '/stop' as input and respond to it.

Fix: Add /stop, /new, and /reset to the bypass set in base.py alongside
/approve, /deny, and /status. Consolidate the three separate bypass
blocks into one. Commands in the bypass set are dispatched inline to the
gateway runner, where Level 2 handles them correctly (hard-kill for
/stop, session reset for /new).

Also add a safety net in _run_agent's pending-message processing: if the
pending text resolves to a known slash command, discard it instead of
passing it to the agent. This catches edge cases where command text
leaks through the interrupt_message fallback.

Refs: #5244

gateway/platforms/base.py

@@ -1103,16 +1103,20 @@ class BasePlatformAdapter(ABC):
         
         # Check if there's already an active handler for this session
         if session_key in self._active_sessions:
-            # /approve and /deny must bypass the active-session guard.
-            # The agent thread is blocked on threading.Event.wait() inside
-            # tools/approval.py — queuing these commands creates a deadlock:
-            # the agent waits for approval, approval waits for agent to finish.
-            # Dispatch directly to the message handler without touching session
-            # lifecycle (no competing background task, no session guard removal).
+            # Certain commands must bypass the active-session guard and be
+            # dispatched directly to the gateway runner.  Without this, they
+            # are queued as pending messages and either:
+            #   - leak into the conversation as user text (/stop, /new), or
+            #   - deadlock (/approve, /deny — agent is blocked on Event.wait)
+            #
+            # Dispatch inline: call the message handler directly and send the
+            # response.  Do NOT use _process_message_background — it manages
+            # session lifecycle and its cleanup races with the running task
+            # (see PR #4926).
             cmd = event.get_command()
-            if cmd in ("approve", "deny"):
+            if cmd in ("approve", "deny", "status", "stop", "new", "reset"):
                 logger.debug(
-                    "[%s] Approval command '/%s' bypassing active-session guard for %s",
+                    "[%s] Command '/%s' bypassing active-session guard for %s",
                     self.name, cmd, session_key,
                 )
                 try:
@@ -1126,29 +1130,7 @@ class BasePlatformAdapter(ABC):
                             metadata=_thread_meta,
                         )
                 except Exception as e:
-                    logger.error("[%s] Approval dispatch failed: %s", self.name, e, exc_info=True)
-                return
-
-            # /status must also bypass the active-session guard so it always
-            # returns a system-generated response instead of being queued as
-            # user text and passed to the agent (#5046).
-            if cmd == "status":
-                logger.debug(
-                    "[%s] Status command bypassing active-session guard for %s",
-                    self.name, session_key,
-                )
-                try:
-                    _thread_meta = {"thread_id": event.source.thread_id} if event.source.thread_id else None
-                    response = await self._message_handler(event)
-                    if response:
-                        await self._send_with_retry(
-                            chat_id=event.source.chat_id,
-                            content=response,
-                            reply_to=event.message_id,
-                            metadata=_thread_meta,
-                        )
-                except Exception as e:
-                    logger.error("[%s] Status dispatch failed: %s", self.name, e, exc_info=True)
+                    logger.error("[%s] Command '/%s' dispatch failed: %s", self.name, cmd, e, exc_info=True)
                 return
 
             # Special case: photo bursts/albums frequently arrive as multiple near-

gateway/run.py

@@ -7021,6 +7021,27 @@ class GatewayRunner:
                     if pending:
                         logger.debug("Processing queued message after agent completion: '%s...'", pending[:40])
             
+            # Safety net: if the pending text is a slash command (e.g. "/stop",
+            # "/new"), discard it — commands should never be passed to the agent
+            # as user input.  The primary fix is in base.py (commands bypass the
+            # active-session guard), but this catches edge cases where command
+            # text leaks through the interrupt_message fallback.
+            if pending and pending.strip().startswith("/"):
+                _pending_parts = pending.strip().split(None, 1)
+                _pending_cmd_word = _pending_parts[0][1:].lower() if _pending_parts else ""
+                if _pending_cmd_word:
+                    try:
+                        from hermes_cli.commands import resolve_command as _rc_pending
+                        if _rc_pending(_pending_cmd_word):
+                            logger.info(
+                                "Discarding command '/%s' from pending queue — "
+                                "commands must not be passed as agent input",
+                                _pending_cmd_word,
+                            )
+                            pending = None
+                    except Exception:
+                        pass
+
             if pending:
                 logger.debug("Processing pending message: '%s...'", pending[:40])