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.
69 lines
2.5 KiB
Python
69 lines
2.5 KiB
Python
"""Regression tests for /retry replacement semantics."""
|
|
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
|
|
import pytest
|
|
|
|
from gateway.config import GatewayConfig
|
|
from gateway.platforms.base import MessageEvent, MessageType
|
|
from gateway.run import GatewayRunner
|
|
from gateway.session import SessionStore
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_gateway_retry_replaces_last_user_turn_in_transcript(tmp_path, monkeypatch):
|
|
# Pin DEFAULT_DB_PATH so SessionDB() doesn't write to the real ~/.hermes/state.db.
|
|
# (Module-level constant snapshot, see test_load_transcript_db_only.)
|
|
import hermes_state
|
|
monkeypatch.setattr(hermes_state, "DEFAULT_DB_PATH", tmp_path / "state.db")
|
|
|
|
config = GatewayConfig()
|
|
store = SessionStore(sessions_dir=tmp_path, config=config)
|
|
|
|
session_id = "retry_session"
|
|
store._db.create_session(session_id=session_id, source="test")
|
|
for msg in [
|
|
{"role": "session_meta", "tools": []},
|
|
{"role": "user", "content": "first question"},
|
|
{"role": "assistant", "content": "first answer"},
|
|
{"role": "user", "content": "retry me"},
|
|
{"role": "assistant", "content": "old answer"},
|
|
]:
|
|
store.append_to_transcript(session_id, msg)
|
|
|
|
gw = GatewayRunner.__new__(GatewayRunner)
|
|
gw.config = config
|
|
gw.session_store = store
|
|
|
|
session_entry = MagicMock(session_id=session_id)
|
|
session_entry.last_prompt_tokens = 111
|
|
gw.session_store.get_or_create_session = MagicMock(return_value=session_entry)
|
|
|
|
async def fake_handle_message(event):
|
|
assert event.text == "retry me"
|
|
transcript_before = store.load_transcript(session_id)
|
|
assert [m.get("content") for m in transcript_before if m.get("role") == "user"] == [
|
|
"first question"
|
|
]
|
|
store.append_to_transcript(session_id, {"role": "user", "content": event.text})
|
|
store.append_to_transcript(session_id, {"role": "assistant", "content": "new answer"})
|
|
return "new answer"
|
|
|
|
gw._handle_message = AsyncMock(side_effect=fake_handle_message)
|
|
|
|
result = await gw._handle_retry_command(
|
|
MessageEvent(text="/retry", message_type=MessageType.TEXT, source=MagicMock())
|
|
)
|
|
|
|
assert result == "new answer"
|
|
transcript_after = store.load_transcript(session_id)
|
|
assert [m.get("content") for m in transcript_after if m.get("role") == "user"] == [
|
|
"first question",
|
|
"retry me",
|
|
]
|
|
assert [m.get("content") for m in transcript_after if m.get("role") == "assistant"] == [
|
|
"first answer",
|
|
"new answer",
|
|
]
|
|
|
|
|