Files
hermes-agent/tests/gateway/test_session_boundary_security_state.py
T
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

216 lines
8.1 KiB
Python

from hermes_state import AsyncSessionDB
"""Regression tests for approval-state cleanup on session boundaries."""
from datetime import datetime
from unittest.mock import MagicMock
import pytest
from gateway.config import Platform
from gateway.platforms.event import MessageEvent
from gateway.session import SessionEntry, SessionSource, build_session_key
from tools import approval as approval_mod
from tools import slash_confirm as slash_confirm_mod
from tools.approval import approve_session, enable_session_yolo, is_approved, is_session_yolo_enabled
from tools.approval_gateway_wait import _ApprovalEntry
@pytest.fixture(autouse=True)
def _clear_approval_state():
approval_mod._gateway_queues.clear()
approval_mod._gateway_notify_cbs.clear()
approval_mod._session_approved.clear()
approval_mod._session_yolo.clear()
approval_mod._permanent_approved.clear()
approval_mod._pending.clear()
slash_confirm_mod._pending.clear()
yield
approval_mod._gateway_queues.clear()
approval_mod._gateway_notify_cbs.clear()
approval_mod._session_approved.clear()
approval_mod._session_yolo.clear()
approval_mod._permanent_approved.clear()
approval_mod._pending.clear()
slash_confirm_mod._pending.clear()
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_entry(session_id: str, source: SessionSource | None = None) -> SessionEntry:
source = source or _make_source()
return SessionEntry(
session_key=build_session_key(source),
session_id=session_id,
created_at=datetime.now(),
updated_at=datetime.now(),
origin=source,
platform=source.platform,
chat_type=source.chat_type,
)
def _make_resume_runner():
from gateway.run import GatewayRunner
source = _make_source()
session_key = build_session_key(source)
current_entry = _make_entry("current-session", source)
resumed_entry = _make_entry("resumed-session", source)
runner = object.__new__(GatewayRunner)
runner.adapters = {}
runner._background_tasks = set()
runner._running_agents = {}
runner._running_agents_ts = {}
runner._busy_ack_ts = {}
runner._pending_approvals = {}
runner._update_prompt_pending = {}
runner._agent_cache_lock = None
runner.session_store = MagicMock()
runner.session_store.get_or_create_session.return_value = current_entry
runner.session_store.switch_session.return_value = resumed_entry
runner.session_store.load_transcript.return_value = []
runner._session_db = AsyncSessionDB(MagicMock())
runner._session_db._db.resolve_session_by_title.return_value = "resumed-session"
runner._session_db._db.get_session_title.return_value = "Resumed Work"
# The resumed session is live and shares the caller's origin, so the
# /resume IDOR guard authorizes it (this test covers the post-resume
# security-state clearing, not the ownership check).
runner._gateway_session_origin_for_id = lambda sid: source
return runner, session_key
def _make_branch_runner():
from gateway.run import GatewayRunner
source = _make_source()
session_key = build_session_key(source)
current_entry = _make_entry("current-session", source)
branched_entry = _make_entry("branched-session", source)
runner = object.__new__(GatewayRunner)
runner.adapters = {}
runner.config = {}
runner._running_agents = {}
runner._running_agents_ts = {}
runner._busy_ack_ts = {}
runner._pending_approvals = {}
runner._update_prompt_pending = {}
runner._agent_cache_lock = None
runner.session_store = MagicMock()
runner.session_store.get_or_create_session.return_value = current_entry
runner.session_store.load_transcript.return_value = [
{"role": "user", "content": "hello"},
{"role": "assistant", "content": "world"},
]
runner.session_store.switch_session.return_value = branched_entry
runner._session_db = AsyncSessionDB(MagicMock())
runner._session_db._db.get_session_title.return_value = "Current Work"
runner._session_db._db.get_next_title_in_lineage.return_value = "Current Work #2"
return runner, session_key
def test_clear_session_boundary_security_state_is_scoped():
"""The helper must wipe only the target session's approval/yolo state.
Also exercises the /new reset path indirectly: /new calls this helper,
so if the helper is scoped correctly, /new's clearing is correct too.
"""
from gateway.run import GatewayRunner
runner = object.__new__(GatewayRunner)
runner._pending_approvals = {}
runner._update_prompt_pending = {}
runner._pending_skills_reload_notes = {}
source = _make_source()
session_key = build_session_key(source)
other_key = "agent:main:telegram:dm:other-chat"
approve_session(session_key, "recursive delete")
approve_session(other_key, "recursive delete")
enable_session_yolo(session_key)
enable_session_yolo(other_key)
runner._pending_approvals[session_key] = {"command": "rm -rf /tmp/demo"}
runner._pending_approvals[other_key] = {"command": "rm -rf /tmp/other"}
runner._update_prompt_pending[session_key] = True
runner._update_prompt_pending[other_key] = True
runner._pending_skills_reload_notes[session_key] = (
"[USER INITIATED SKILLS RELOAD: target]"
)
runner._pending_skills_reload_notes[other_key] = (
"[USER INITIATED SKILLS RELOAD: other]"
)
async def _target_handler(choice):
return f"target:{choice}"
async def _other_handler(choice):
return f"other:{choice}"
slash_confirm_mod.register(session_key, "confirm-target", "reload-mcp", _target_handler)
slash_confirm_mod.register(other_key, "confirm-other", "reload-mcp", _other_handler)
runner._clear_session_boundary_security_state(session_key)
# Target session cleared
assert is_approved(session_key, "recursive delete") is False
assert is_session_yolo_enabled(session_key) is False
assert session_key not in runner._pending_approvals
assert session_key not in runner._update_prompt_pending
assert session_key not in runner._pending_skills_reload_notes
assert slash_confirm_mod.get_pending(session_key) is None
# Other session untouched
assert is_approved(other_key, "recursive delete") is True
assert is_session_yolo_enabled(other_key) is True
assert other_key in runner._pending_approvals
assert other_key in runner._update_prompt_pending
assert other_key in runner._pending_skills_reload_notes
assert slash_confirm_mod.get_pending(other_key) is not None
# Empty session_key is a no-op
runner._clear_session_boundary_security_state("")
assert is_approved(other_key, "recursive delete") is True
assert other_key in runner._update_prompt_pending
assert other_key in runner._pending_skills_reload_notes
assert slash_confirm_mod.get_pending(other_key) is not None
def test_clear_session_boundary_security_state_wakes_blocked_approvals():
"""Boundary cleanup must cancel blocked approval waiters immediately."""
from gateway.run import GatewayRunner
runner = object.__new__(GatewayRunner)
runner._pending_approvals = {}
runner._update_prompt_pending = {}
source = _make_source()
session_key = build_session_key(source)
other_key = "agent:main:telegram:dm:other-chat"
target_entry = _ApprovalEntry({"command": "rm -rf /tmp/demo"})
other_entry = _ApprovalEntry({"command": "rm -rf /tmp/other"})
approval_mod._gateway_queues[session_key] = [target_entry]
approval_mod._gateway_queues[other_key] = [other_entry]
runner._clear_session_boundary_security_state(session_key)
assert target_entry.event.is_set()
assert target_entry.result == "deny"
assert other_entry.event.is_set() is False
assert other_entry.result is None
assert session_key not in approval_mod._gateway_queues
assert other_key in approval_mod._gateway_queues