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.
75 lines
2.6 KiB
Python
75 lines
2.6 KiB
Python
"""Tests for step_callback backward compatibility.
|
|
|
|
Verifies that the gateway's step_callback normalization keeps
|
|
``tool_names`` as a list of strings for backward-compatible hooks,
|
|
while also providing the enriched ``tools`` list with results.
|
|
"""
|
|
|
|
import asyncio
|
|
|
|
|
|
class TestStepCallbackNormalization:
|
|
"""The gateway's _step_callback_sync normalizes prev_tools from run_agent."""
|
|
|
|
def _extract_step_callback(self):
|
|
"""Build a minimal _step_callback_sync using the same logic as gateway/run.py.
|
|
|
|
We replicate the closure so we can test normalisation in isolation
|
|
without spinning up the full gateway.
|
|
"""
|
|
captured_events = []
|
|
|
|
class FakeHooks:
|
|
async def emit(self, event_type, data):
|
|
captured_events.append((event_type, data))
|
|
|
|
hooks_ref = FakeHooks()
|
|
loop = asyncio.new_event_loop()
|
|
|
|
def _step_callback_sync(iteration: int, prev_tools: list) -> None:
|
|
_names: list[str] = []
|
|
for _t in (prev_tools or []):
|
|
if isinstance(_t, dict):
|
|
_names.append(_t.get("name") or "")
|
|
else:
|
|
_names.append(str(_t))
|
|
asyncio.run_coroutine_threadsafe(
|
|
hooks_ref.emit("agent:step", {
|
|
"iteration": iteration,
|
|
"tool_names": _names,
|
|
"tools": prev_tools,
|
|
}),
|
|
loop,
|
|
)
|
|
|
|
return _step_callback_sync, captured_events, loop
|
|
|
|
def test_dict_prev_tools_produce_string_tool_names(self):
|
|
"""When prev_tools is list[dict], tool_names should be list[str]."""
|
|
cb, events, loop = self._extract_step_callback()
|
|
|
|
# Simulate the enriched format from run_agent.py
|
|
prev_tools = [
|
|
{"name": "terminal", "result": '{"output": "hello"}'},
|
|
{"name": "read_file", "result": '{"content": "..."}'},
|
|
]
|
|
|
|
try:
|
|
loop.run_until_complete(asyncio.sleep(0)) # prime the loop
|
|
import threading
|
|
t = threading.Thread(target=cb, args=(1, prev_tools))
|
|
t.start()
|
|
t.join(timeout=2)
|
|
loop.run_until_complete(asyncio.sleep(0.1))
|
|
finally:
|
|
loop.close()
|
|
|
|
assert len(events) == 1
|
|
_, data = events[0]
|
|
# tool_names must be strings for backward compat
|
|
assert data["tool_names"] == ["terminal", "read_file"]
|
|
assert all(isinstance(n, str) for n in data["tool_names"])
|
|
# tools should be the enriched dicts
|
|
assert data["tools"] == prev_tools
|
|
|
|
|