mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +00:00
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.
56 lines
2 KiB
Python
56 lines
2 KiB
Python
"""Tests for pending follow-up extraction in recursive _run_agent calls.
|
|
|
|
When pending_event is None (Path B: pending comes from interrupt_message),
|
|
accessing pending_event.channel_prompt previously raised AttributeError.
|
|
This verifies the fix: channel_prompt is captured inside the
|
|
`if pending_event is not None:` block and falls back to None otherwise.
|
|
|
|
Also verifies that internal control interrupt reasons like "Stop requested"
|
|
do not get recycled into the pending-user-message follow-up path.
|
|
"""
|
|
|
|
from types import SimpleNamespace
|
|
|
|
from gateway.run import _is_control_interrupt_message
|
|
|
|
|
|
def _extract_channel_prompt(pending_event):
|
|
"""Reproduce the fixed logic from gateway/run.py.
|
|
|
|
Mirrors the variable-capture pattern used before the recursive
|
|
_run_agent call so we can test both paths without a full runner.
|
|
"""
|
|
next_channel_prompt = None
|
|
if pending_event is not None:
|
|
next_channel_prompt = getattr(pending_event, "channel_prompt", None)
|
|
return next_channel_prompt
|
|
|
|
|
|
def _extract_pending_text(interrupted, pending_event, interrupt_message):
|
|
"""Reproduce the fixed pending-text selection from gateway/run.py."""
|
|
if interrupted and pending_event is None and interrupt_message:
|
|
if _is_control_interrupt_message(interrupt_message):
|
|
return None
|
|
return interrupt_message
|
|
return None
|
|
|
|
|
|
class TestPendingEventNoneChannelPrompt:
|
|
"""Guard against AttributeError when pending_event is None."""
|
|
|
|
|
|
def test_pending_event_with_channel_prompt_passes_through(self):
|
|
"""Path A: pending_event present — channel_prompt is forwarded."""
|
|
event = SimpleNamespace(channel_prompt="You are a helpful bot.")
|
|
result = _extract_channel_prompt(event)
|
|
assert result == "You are a helpful bot."
|
|
|
|
|
|
class TestControlInterruptMessages:
|
|
"""Control interrupt reasons must not become follow-up user input."""
|
|
|
|
def test_stop_requested_is_not_treated_as_pending_user_message(self):
|
|
result = _extract_pending_text(True, None, "Stop requested")
|
|
assert result is None
|
|
|
|
|