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.
126 lines
3.6 KiB
Python
126 lines
3.6 KiB
Python
"""Tests for tools/slash_confirm.py — the generic slash-command confirmation primitive.
|
|
|
|
Covers register/resolve/clear lifecycle, stale-entry behavior, confirm_id
|
|
mismatch, handler exceptions, and async resolution.
|
|
"""
|
|
|
|
import asyncio
|
|
import time
|
|
|
|
import pytest
|
|
|
|
from tools import slash_confirm
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _clean_pending():
|
|
"""Every test gets a clean primitive state."""
|
|
slash_confirm._pending.clear()
|
|
yield
|
|
slash_confirm._pending.clear()
|
|
|
|
|
|
class TestRegisterAndGetPending:
|
|
def test_register_stores_entry(self):
|
|
async def handler(choice):
|
|
return f"got {choice}"
|
|
|
|
slash_confirm.register("sess1", "cid1", "reload-mcp", handler)
|
|
|
|
pending = slash_confirm.get_pending("sess1")
|
|
assert pending is not None
|
|
assert pending["confirm_id"] == "cid1"
|
|
assert pending["command"] == "reload-mcp"
|
|
assert pending["handler"] is handler
|
|
assert "created_at" in pending
|
|
|
|
|
|
def test_get_pending_returns_copy_not_reference(self):
|
|
async def h(choice):
|
|
return "x"
|
|
|
|
slash_confirm.register("sess1", "cid1", "cmd", h)
|
|
|
|
p1 = slash_confirm.get_pending("sess1")
|
|
p1["command"] = "mutated"
|
|
|
|
p2 = slash_confirm.get_pending("sess1")
|
|
assert p2["command"] == "cmd"
|
|
|
|
|
|
class TestResolve:
|
|
@pytest.mark.asyncio
|
|
async def test_resolve_runs_handler_and_pops_entry(self):
|
|
calls = []
|
|
|
|
async def handler(choice):
|
|
calls.append(choice)
|
|
return f"resolved {choice}"
|
|
|
|
slash_confirm.register("sess1", "cid1", "reload-mcp", handler)
|
|
|
|
result = await slash_confirm.resolve("sess1", "cid1", "once")
|
|
assert result == "resolved once"
|
|
assert calls == ["once"]
|
|
|
|
# Entry should be popped.
|
|
assert slash_confirm.get_pending("sess1") is None
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_resolve_no_pending_returns_none(self):
|
|
result = await slash_confirm.resolve("sess1", "cid1", "once")
|
|
assert result is None
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_resolve_double_click_only_runs_handler_once(self):
|
|
calls = []
|
|
|
|
async def handler(choice):
|
|
calls.append(choice)
|
|
return "ran"
|
|
|
|
slash_confirm.register("sess1", "cid1", "cmd", handler)
|
|
|
|
# Simulate two near-simultaneous button clicks.
|
|
r1, r2 = await asyncio.gather(
|
|
slash_confirm.resolve("sess1", "cid1", "once"),
|
|
slash_confirm.resolve("sess1", "cid1", "once"),
|
|
)
|
|
# Exactly one should have run the handler.
|
|
assert calls == ["once"]
|
|
assert (r1 == "ran") ^ (r2 == "ran")
|
|
|
|
|
|
class TestClear:
|
|
def test_clear_removes_entry(self):
|
|
async def h(c):
|
|
return "x"
|
|
|
|
slash_confirm.register("sess1", "cid1", "cmd", h)
|
|
assert slash_confirm.get_pending("sess1") is not None
|
|
|
|
slash_confirm.clear("sess1")
|
|
assert slash_confirm.get_pending("sess1") is None
|
|
|
|
def test_clear_missing_is_noop(self):
|
|
# Should not raise.
|
|
slash_confirm.clear("nobody")
|
|
|
|
|
|
class TestClearIfStale:
|
|
def test_clears_stale_entry(self):
|
|
async def h(c):
|
|
return "x"
|
|
|
|
slash_confirm.register("sess1", "cid1", "cmd", h)
|
|
slash_confirm._pending["sess1"]["created_at"] = time.time() - 10000
|
|
|
|
cleared = slash_confirm.clear_if_stale("sess1", timeout=300)
|
|
assert cleared is True
|
|
assert slash_confirm.get_pending("sess1") is None
|
|
|
|
|
|
def test_returns_false_for_missing_entry(self):
|
|
cleared = slash_confirm.clear_if_stale("nobody")
|
|
assert cleared is False
|