fix: add gateway coverage for session boundary hooks, move test to tests/cli/

- Fire on_session_finalize and on_session_reset in gateway _handle_reset_command()
- Fire on_session_finalize during gateway stop() for each active agent
- Move CLI test from tests/ root to tests/cli/ (matches recent restructure)
- Add 5 gateway tests covering reset hooks, ordering, shutdown, and error handling
- Place on_session_reset after new session is guaranteed to exist (covers
  the get_or_create_session fallback path)

gateway/run.py

@@ -1481,6 +1481,14 @@ class GatewayRunner:
                 logger.debug("Interrupted running agent for session %s during shutdown", session_key[:20])
             except Exception as e:
                 logger.debug("Failed interrupting agent during shutdown: %s", e)
+            # Fire plugin on_session_finalize hook before memory shutdown
+            try:
+                from hermes_cli.plugins import invoke_hook as _invoke_hook
+                _invoke_hook("on_session_finalize",
+                             session_id=getattr(agent, 'session_id', None),
+                             platform="gateway")
+            except Exception:
+                pass
             # Shut down memory provider at actual session boundary
             try:
                 if hasattr(agent, 'shutdown_memory_provider'):
@@ -3274,6 +3282,15 @@ class GatewayRunner:
         # the configured default instead of the previously switched model.
         self._session_model_overrides.pop(session_key, None)
 
+        # Fire plugin on_session_finalize hook (session boundary)
+        try:
+            from hermes_cli.plugins import invoke_hook as _invoke_hook
+            _old_sid = old_entry.session_id if old_entry else None
+            _invoke_hook("on_session_finalize", session_id=_old_sid,
+                         platform=source.platform.value if source.platform else "")
+        except Exception:
+            pass
+
         # Emit session:end hook (session is ending)
         await self.hooks.emit("session:end", {
             "platform": source.platform.value if source.platform else "",
@@ -3287,7 +3304,7 @@ class GatewayRunner:
             "user_id": source.user_id,
             "session_key": session_key,
         })
-        
+
         # Resolve session config info to surface to the user
         try:
             session_info = self._format_session_info()
@@ -3298,9 +3315,18 @@ class GatewayRunner:
             header = "✨ Session reset! Starting fresh."
         else:
             # No existing session, just create one
-            self.session_store.get_or_create_session(source, force_new=True)
+            new_entry = self.session_store.get_or_create_session(source, force_new=True)
             header = "✨ New session started!"
 
+        # Fire plugin on_session_reset hook (new session guaranteed to exist)
+        try:
+            from hermes_cli.plugins import invoke_hook as _invoke_hook
+            _new_sid = new_entry.session_id if new_entry else None
+            _invoke_hook("on_session_reset", session_id=_new_sid,
+                         platform=source.platform.value if source.platform else "")
+        except Exception:
+            pass
+
         if session_info:
             return f"{header}\n\n{session_info}"
         return header

tests/gateway/test_session_boundary_hooks.py

@@ -0,0 +1,158 @@
+"""Tests that on_session_finalize and on_session_reset plugin hooks fire in the gateway."""
+from datetime import datetime
+from types import SimpleNamespace
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import pytest
+
+from gateway.config import GatewayConfig, Platform, PlatformConfig
+from gateway.platforms.base import MessageEvent
+from gateway.session import SessionEntry, SessionSource, build_session_key
+
+
+def _make_source() -> SessionSource:
+    return SessionSource(
+        platform=Platform.TELEGRAM,
+        user_id="u1",
+        chat_id="c1",
+        user_name="tester",
+        chat_type="dm",
+    )
+
+
+def _make_event(text: str) -> MessageEvent:
+    return MessageEvent(text=text, source=_make_source(), message_id="m1")
+
+
+def _make_runner():
+    from gateway.run import GatewayRunner
+
+    runner = object.__new__(GatewayRunner)
+    runner.config = GatewayConfig(
+        platforms={Platform.TELEGRAM: PlatformConfig(enabled=True, token="***")}
+    )
+    adapter = MagicMock()
+    adapter.send = AsyncMock()
+    runner.adapters = {Platform.TELEGRAM: adapter}
+    runner._voice_mode = {}
+    runner.hooks = SimpleNamespace(emit=AsyncMock(), loaded_hooks=False)
+    runner._session_model_overrides = {}
+    runner._pending_model_notes = {}
+    runner._background_tasks = set()
+
+    session_key = build_session_key(_make_source())
+    session_entry = SessionEntry(
+        session_key=session_key,
+        session_id="sess-old",
+        created_at=datetime.now(),
+        updated_at=datetime.now(),
+        platform=Platform.TELEGRAM,
+        chat_type="dm",
+    )
+    new_session_entry = SessionEntry(
+        session_key=session_key,
+        session_id="sess-new",
+        created_at=datetime.now(),
+        updated_at=datetime.now(),
+        platform=Platform.TELEGRAM,
+        chat_type="dm",
+    )
+    runner.session_store = MagicMock()
+    runner.session_store.get_or_create_session.return_value = new_session_entry
+    runner.session_store.reset_session.return_value = new_session_entry
+    runner.session_store._entries = {session_key: session_entry}
+    runner.session_store._generate_session_key.return_value = session_key
+    runner._running_agents = {}
+    runner._pending_messages = {}
+    runner._pending_approvals = {}
+    runner._session_db = None
+    runner._agent_cache_lock = None
+    runner._is_user_authorized = lambda _source: True
+    runner._format_session_info = lambda: ""
+
+    return runner
+
+
+@pytest.mark.asyncio
+@patch("hermes_cli.plugins.invoke_hook")
+async def test_reset_fires_finalize_hook(mock_invoke_hook):
+    """/new must fire on_session_finalize with the OLD session id."""
+    runner = _make_runner()
+
+    await runner._handle_reset_command(_make_event("/new"))
+
+    mock_invoke_hook.assert_any_call(
+        "on_session_finalize", session_id="sess-old", platform="telegram"
+    )
+
+
+@pytest.mark.asyncio
+@patch("hermes_cli.plugins.invoke_hook")
+async def test_reset_fires_reset_hook(mock_invoke_hook):
+    """/new must fire on_session_reset with the NEW session id."""
+    runner = _make_runner()
+
+    await runner._handle_reset_command(_make_event("/new"))
+
+    mock_invoke_hook.assert_any_call(
+        "on_session_reset", session_id="sess-new", platform="telegram"
+    )
+
+
+@pytest.mark.asyncio
+@patch("hermes_cli.plugins.invoke_hook")
+async def test_finalize_before_reset(mock_invoke_hook):
+    """on_session_finalize must fire before on_session_reset."""
+    runner = _make_runner()
+
+    await runner._handle_reset_command(_make_event("/new"))
+
+    calls = [c for c in mock_invoke_hook.call_args_list
+             if c[0][0] in ("on_session_finalize", "on_session_reset")]
+    hook_names = [c[0][0] for c in calls]
+    assert hook_names == ["on_session_finalize", "on_session_reset"]
+
+
+@pytest.mark.asyncio
+@patch("hermes_cli.plugins.invoke_hook")
+async def test_shutdown_fires_finalize_for_active_agents(mock_invoke_hook):
+    """Gateway stop() must fire on_session_finalize for each active agent."""
+    from gateway.run import GatewayRunner
+
+    runner = object.__new__(GatewayRunner)
+    runner._running = True
+    runner._background_tasks = set()
+    runner._pending_messages = {}
+    runner._pending_approvals = {}
+    runner._shutdown_event = MagicMock()
+    runner.adapters = {}
+    runner._exit_reason = "test"
+
+    agent1 = MagicMock()
+    agent1.session_id = "sess-a"
+    agent2 = MagicMock()
+    agent2.session_id = "sess-b"
+    runner._running_agents = {"key-a": agent1, "key-b": agent2}
+
+    with patch("gateway.status.remove_pid_file"), \
+         patch("gateway.status.write_runtime_status"):
+        await runner.stop()
+
+    finalize_calls = [
+        c for c in mock_invoke_hook.call_args_list
+        if c[0][0] == "on_session_finalize"
+    ]
+    session_ids = {c[1]["session_id"] for c in finalize_calls}
+    assert session_ids == {"sess-a", "sess-b"}
+
+
+@pytest.mark.asyncio
+@patch("hermes_cli.plugins.invoke_hook", side_effect=Exception("boom"))
+async def test_hook_error_does_not_break_reset(mock_invoke_hook):
+    """Plugin hook errors must not prevent /new from completing."""
+    runner = _make_runner()
+
+    result = await runner._handle_reset_command(_make_event("/new"))
+
+    # Should still return a success message despite hook errors
+    assert "Session reset" in result or "New session" in result