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.
56 lines
1.8 KiB
Python
56 lines
1.8 KiB
Python
"""Tests for SessionStore.rewind_session — the gateway /undo [N] primitive.
|
|
|
|
The gateway /undo backs up N user turns by soft-deleting the truncated rows
|
|
in state.db (active=0, kept for audit, hidden from re-prompts/search) via
|
|
SessionDB.rewind_to_message, rather than the old hard rewrite_transcript.
|
|
load_transcript returns only the active view. See issue #21910.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from hermes_state import SessionDB
|
|
from gateway.config import GatewayConfig
|
|
from gateway.session import SessionStore
|
|
|
|
|
|
@pytest.fixture()
|
|
def store(tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
|
monkeypatch.setattr(Path, "home", lambda: tmp_path)
|
|
db = SessionDB(db_path=tmp_path / "state.db")
|
|
s = SessionStore(sessions_dir=tmp_path / "sessions", config=GatewayConfig())
|
|
s._db = db # use the same DB instance the fixture seeds
|
|
return s
|
|
|
|
|
|
def _seed(store, sid, source="telegram", turns=3):
|
|
store._db.create_session(sid, source=source)
|
|
for i in range(1, turns + 1):
|
|
store._db.append_message(sid, "user", f"q{i}")
|
|
store._db.append_message(sid, "assistant", f"a{i}")
|
|
return sid
|
|
|
|
|
|
def test_rewind_default_one_turn(store):
|
|
sid = _seed(store, "gw-1")
|
|
res = store.rewind_session(sid)
|
|
assert res["turns_undone"] == 1
|
|
assert res["target_text"] == "q3"
|
|
assert res["rewound_count"] == 2 # q3 + a3
|
|
active = store.load_transcript(sid)
|
|
assert [m["role"] for m in active] == ["user", "assistant", "user", "assistant"]
|
|
|
|
|
|
def test_rewind_n_turns(store):
|
|
sid = _seed(store, "gw-2")
|
|
res = store.rewind_session(sid, 2)
|
|
assert res["turns_undone"] == 2
|
|
assert res["target_text"] == "q2"
|
|
assert res["rewound_count"] == 4 # q2,a2,q3,a3
|
|
assert len(store.load_transcript(sid)) == 2 # q1,a1
|
|
|
|
|