Files
hermes-agent/tests/gateway/test_unknown_command.py
kshitijk4poor ab2f4602de refactor: MessageEvent to gateway/platforms/event.py; ElicitationHandler takes a call_context thunk
Breaks the two import cycles that forced Protocol stand-ins in the F821 sweep, so the two
sites now name the real types.

gateway/platforms/event.py (new leaf): MessageType, ProcessingOutcome, MessageEvent moved
out of base.py verbatim. Their only dependency is gateway.session.SessionSource; base.py
imported helpers.py at module level, so helpers could not name MessageEvent. Now
TextBatchAggregator is typed by the real MessageEvent. 249 importers repointed
(`from gateway.platforms.base import` -> `.event`, preserving each import's layout);
gateway.platforms.__init__ re-exports from .event. The three revert-scheduled PLUGIN-COMPAT
pointers that named these symbols (gateway.slash_commands → MessageType, dingtalk → MessageType,
photon → ProcessingOutcome) and their COMPAT_MANIFEST rows now target gateway.platforms.event.
Docs updated: ADDING_A_PLATFORM.md, adding-platform-adapters.md (en + zh-Hans).

tools/mcp_tool_sampling.py: ElicitationHandler no longer holds a back-reference to its
MCPServerTask (mcp_tool imports sampling, so the task type cannot be named there). It only
ever read owner._pending_call_context, so it takes `call_context: Callable[[], Context | None]`
and MCPServerTask passes `lambda: self._pending_call_context`. The consent call is one
`functools.partial`, run directly or inside the captured Context.

ty on the 11 touched production files vs origin/main: 0 new diagnostics, 14 resolved.
(The one `source: SessionSource = None` diagnostic moves with the class; typing it Optional
exposes ~60 unguarded call sites — separate follow-up.)

Tests: tests/gateway + tests/plugins + tests/tools + touched files, 18,235 passed; the 31
failures reproduce identically on origin/main (macOS /private/tmp, systemd socket,
long-path fixtures, live-service tests).
2026-09-07 22:47:33 +05:30

228 lines
7.5 KiB
Python

"""Tests for gateway warning when an unrecognized /command is dispatched.
Without this warning, unknown slash commands get forwarded to the LLM as plain
text, which often leads to silent failure (e.g. the model inventing a bogus
delegate_task call instead of telling the user the command doesn't exist).
"""
from datetime import datetime
from types import SimpleNamespace
from unittest.mock import AsyncMock, MagicMock
import pytest
from gateway.config import GatewayConfig, Platform, PlatformConfig
from gateway.platforms.event import MessageEvent, MessageType
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_voice_event(text: str = "voice_message_1.ogg") -> MessageEvent:
source = _make_source()
return MessageEvent(
text=text,
message_type=MessageType.VOICE,
source=source,
message_id="m1",
media_urls=["/tmp/voice_message_1.ogg"],
media_types=["audio/ogg"],
)
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(),
emit_collect=AsyncMock(return_value=[]),
loaded_hooks=False,
)
session_entry = SessionEntry(
session_key=build_session_key(_make_source()),
session_id="sess-1",
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 = session_entry
runner.session_store.load_transcript.return_value = []
runner.session_store.has_any_sessions.return_value = True
runner.session_store.append_to_transcript = MagicMock()
runner.session_store.rewrite_transcript = MagicMock()
runner.session_store.update_session = MagicMock()
runner._running_agents = {}
runner._pending_messages = {}
runner._pending_approvals = {}
runner._session_db = None
runner._reasoning_config = None
runner._provider_routing = {}
runner._fallback_model = None
runner._show_reasoning = False
runner._is_user_authorized = lambda _source: True
runner._set_session_env = lambda _context: None
runner._should_send_voice_reply = lambda *_args, **_kwargs: False
runner._send_voice_reply = AsyncMock()
runner._capture_gateway_honcho_if_configured = lambda *args, **kwargs: None
runner._emit_gateway_run_progress = AsyncMock()
return runner
@pytest.mark.asyncio
async def test_unknown_slash_command_returns_guidance(monkeypatch):
"""A genuinely unknown /foobar should return user-facing guidance, not
silently drop through to the LLM."""
import gateway.run as gateway_run
runner = _make_runner()
# If the LLM were called, this would fail: the guard must short-circuit
# before _run_agent is invoked.
runner._run_agent = AsyncMock(
side_effect=AssertionError(
"unknown slash command leaked through to the agent"
)
)
monkeypatch.setattr(
gateway_run, "_resolve_runtime_agent_kwargs", lambda: {"api_key": "***"}
)
result = await runner._handle_message(_make_event("/definitely-not-a-command"))
assert result is not None
assert "Unknown command" in result
assert "/definitely-not-a-command" in result
assert "/commands" in result
runner._run_agent.assert_not_called()
@pytest.mark.asyncio
async def test_known_slash_command_not_flagged_as_unknown(monkeypatch):
"""A real built-in like /status must NOT hit the unknown-command guard."""
runner = _make_runner()
# Make _handle_status_command exist via the normal path by running a real
# dispatch. If the guard fires, the return string will mention "Unknown".
runner._running_agents[build_session_key(_make_source())] = MagicMock()
result = await runner._handle_message(_make_event("/status"))
assert result is not None
assert "Unknown command" not in result
@pytest.mark.asyncio
async def test_egress_slash_command_reports_proxy_status(monkeypatch):
runner = _make_runner()
monkeypatch.setattr(
"hermes_cli.proxy_cli.format_status_text",
lambda: "Egress proxy status\nEnabled: no",
)
result = await runner._handle_message(_make_event("/egress"))
assert result is not None
assert "Egress proxy status" in result
assert "Unknown command" not in result
@pytest.mark.asyncio
async def test_underscored_alias_for_hyphenated_builtin_not_flagged(monkeypatch):
"""Telegram autocomplete sends /reload_mcp for the /reload-mcp built-in.
That must NOT be flagged as unknown."""
import gateway.run as gateway_run
runner = _make_runner()
# Prevent real MCP work; we only care that the unknown guard doesn't fire.
async def _noop_reload(*_a, **_kw):
return "mcp reloaded"
runner._handle_reload_mcp_command = _noop_reload # type: ignore[attr-defined]
monkeypatch.setattr(
gateway_run, "_resolve_runtime_agent_kwargs", lambda: {"api_key": "***"}
)
result = await runner._handle_message(_make_event("/reload_mcp"))
# Whatever /reload_mcp returns, it must not be the unknown-command guard.
if result is not None:
assert "Unknown command" not in result
# ------------------------------------------------------------------
# command:<name> decision hook — deny / handled / rewrite
# ------------------------------------------------------------------
@pytest.mark.asyncio
async def test_command_hook_rewrite_routes_to_plugin(monkeypatch):
"""A rewrite decision should re-resolve the command and route to the new one."""
import gateway.run as gateway_run
runner = _make_runner()
runner._run_agent = AsyncMock(
side_effect=AssertionError("rewritten command leaked to the agent")
)
call_log = []
async def _emit_collect(event_type, ctx):
call_log.append(event_type)
if event_type == "command:status":
return [
{
"decision": "rewrite",
"command_name": "metricas",
"raw_args": "dias:7",
}
]
return []
runner.hooks.emit_collect = AsyncMock(side_effect=_emit_collect)
monkeypatch.setattr(
gateway_run, "_resolve_runtime_agent_kwargs", lambda: {"api_key": "***"}
)
from hermes_cli import plugins as _plugins_mod
monkeypatch.setattr(
_plugins_mod,
"get_plugin_commands",
lambda: {"metricas": {"description": "Metrics", "args_hint": "dias:7"}},
)
monkeypatch.setattr(
_plugins_mod,
"get_plugin_command_handler",
lambda name: (lambda args: f"metrics {args}") if name == "metricas" else None,
)
result = await runner._handle_message(_make_event("/status"))
assert result == "metrics dias:7"
# First emit_collect fires on the original command; after rewrite the
# dispatcher does NOT re-fire for the new command (one decision per turn).
assert call_log == ["command:status"]