mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
39975613b1
Second, deeper pass over tools/gateway/hermes_cli plus first pass over the trees wave 1 missed (acp, acp_adapter, skills, computer_use, docker, dashboard, conformance, monitoring, secret_sources, hermes_state, providers). Same rubric as wave 1 (AGENTS.md test policy); security, alternation/caching invariants, issue-number regressions, and E2E kept. Real test-quality fixes found and rooted out along the way: - tests/tools/test_command_guards.py made real auxiliary-LLM HTTPS calls (DEFAULT_CONFIG smart-approval leaked in) — pinned approval mode=manual via autouse fixture: 17.4s → 0.4s. - test_model_switch_custom_providers.py / test_user_providers_model_switch.py silently probed live provider catalogs (~2s/test) — stubbed cached_provider_model_ids/provider_model_ids/fetch_api_models. - test_telegram_noise_filter.py: 15-platform copy-paste matrix over shared gateway.run logic → 3 representative platforms (55s → 3.9s). - test_gateway_shutdown.py: stop()'s 5s interrupt-deadline loop spun on MagicMock agents — interrupt.side_effect now clears _running_agents (22s → 1.0s). - test_gateway_inactivity_timeout.py poll-harness timings shrunk 3-5x (24s → 1.1s); test_mcp_stability.py backoff/SIGTERM-grace sleeps patched (15.4s → 2.5s); test_async_delegation.py negative-drain wait 5s → 0.5s. - test_telegram_init_deadline.py: loop-block margin restored to 1.0s with rationale comment — the watchdog-dump assertion needs the loop blocked well past deadline+grace under parallel load (flaked once in the 40-worker verification run at a 0.2s margin). Verification: full hermetic suite via scripts/run_tests.sh — 2,438 files, 21,718 tests passed, 0 failed, 293.9s wall. Suite totals vs original baseline: 46,820 → 19,757 test functions (−57.8%), wall 583.5s → 293.9s (−50%), subprocess CPU 13,564s → 11,623s.
70 lines
2.4 KiB
Python
70 lines
2.4 KiB
Python
"""Tests for MCP list_* pagination (nextCursor draining).
|
|
|
|
The MCP spec allows servers to paginate ``tools/list``, ``resources/list``,
|
|
and ``prompts/list`` via an opaque ``nextCursor`` token. The Python SDK
|
|
fetches one page per call, so hermes must follow the cursor to see items
|
|
past page 1. Port of the invariant behind anomalyco/opencode#35439/#35500.
|
|
"""
|
|
|
|
import asyncio
|
|
from types import SimpleNamespace
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
|
|
from tools.mcp_tool import _MCP_LIST_MAX_PAGES, _paginate_full_list
|
|
|
|
|
|
def _tool(name):
|
|
t = MagicMock()
|
|
t.name = name
|
|
return t
|
|
|
|
|
|
class TestPaginateFullList:
|
|
def test_single_page_no_cursor(self):
|
|
"""A result without nextCursor returns just that page."""
|
|
list_method = AsyncMock(
|
|
return_value=SimpleNamespace(tools=[_tool("a"), _tool("b")])
|
|
)
|
|
items = asyncio.run(_paginate_full_list(list_method, "tools", "srv"))
|
|
assert [t.name for t in items] == ["a", "b"]
|
|
list_method.assert_called_once_with()
|
|
|
|
|
|
def test_runaway_cursor_capped(self):
|
|
"""A server that returns a cursor forever is bounded by the page cap."""
|
|
calls = {"n": 0}
|
|
|
|
async def evil_list(cursor=None):
|
|
calls["n"] += 1
|
|
return SimpleNamespace(
|
|
tools=[_tool(f"t{calls['n']}")], nextCursor=f"c{calls['n']}"
|
|
)
|
|
|
|
items = asyncio.run(_paginate_full_list(evil_list, "tools", "srv"))
|
|
assert calls["n"] == _MCP_LIST_MAX_PAGES
|
|
assert len(items) == _MCP_LIST_MAX_PAGES
|
|
|
|
|
|
class TestDiscoveryUsesPagination:
|
|
def test_discover_tools_drains_all_pages(self):
|
|
"""MCPServerTask._discover_tools registers tools from every page."""
|
|
from tools.mcp_tool import MCPServerTask
|
|
|
|
server = MCPServerTask("pag_srv")
|
|
server._config = {"command": "test"}
|
|
pages = {
|
|
None: SimpleNamespace(tools=[_tool("first")], nextCursor="page-2"),
|
|
"page-2": SimpleNamespace(tools=[_tool("second")]),
|
|
}
|
|
|
|
async def fake_list(cursor=None):
|
|
return pages[cursor]
|
|
|
|
server.session = MagicMock()
|
|
server.session.list_tools = fake_list
|
|
# capability gate: _advertises_tools() returns True when no
|
|
# capability info was captured (legacy fallback), so no override
|
|
# is needed here.
|
|
|
|
asyncio.run(server._discover_tools())
|
|
assert [t.name for t in server._tools] == ["first", "second"]
|