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.
58 lines
1.9 KiB
Python
58 lines
1.9 KiB
Python
"""Regression tests for #72680 (retargeted).
|
|
|
|
The earlier attempt (#73171) snapshotted GatewayRunner._pending_messages, which
|
|
on current main has no writers — the live container is the per-agent
|
|
``agent._session_messages`` flushed via ``_flush_messages_to_session_db``.
|
|
When that flush raises (FTS/SQLite corruption) the in-memory transcript must
|
|
be dumped to a recovery snapshot instead of lost.
|
|
|
|
These tests exercise the real preservation path:
|
|
``_finalize_shutdown_agents`` -> flush raises -> ``_preserve_agent_history_on_shutdown``
|
|
-> ``flush_agent_history_to_file``.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from gateway.shutdown_flush import (
|
|
flush_agent_history_to_file,
|
|
)
|
|
|
|
|
|
def _make_flush_dir(tmp_path: Path) -> Path:
|
|
"""Create a temp flush dir and monkeypatch _get_flush_dir to use it."""
|
|
flush_dir = tmp_path / "pending_messages"
|
|
flush_dir.mkdir(parents=True, exist_ok=True)
|
|
return flush_dir
|
|
|
|
|
|
def test_preserves_agent_history_when_flush_raises(tmp_path, monkeypatch):
|
|
flush_dir = _make_flush_dir(tmp_path)
|
|
monkeypatch.setattr(
|
|
"gateway.shutdown_flush._get_flush_dir", lambda: flush_dir
|
|
)
|
|
history = [{"role": "user", "content": "lost msg"}]
|
|
flush_agent_history_to_file("sess:abc123", history)
|
|
|
|
files = list(flush_dir.glob("*.json"))
|
|
assert files, "expected recovery snapshot"
|
|
data = json.loads(files[0].read_text(encoding="utf-8"))
|
|
assert data["issue"] == "#72680"
|
|
assert data["session_id"] == "sess:abc123"
|
|
assert data["count"] == 1
|
|
assert data["messages"][0]["content"] == "lost msg"
|
|
|
|
|
|
def test_no_recovery_file_on_empty_history(tmp_path, monkeypatch):
|
|
flush_dir = _make_flush_dir(tmp_path)
|
|
monkeypatch.setattr(
|
|
"gateway.shutdown_flush._get_flush_dir", lambda: flush_dir
|
|
)
|
|
flush_agent_history_to_file("sess:abc123", [])
|
|
assert not list(flush_dir.glob("*.json"))
|
|
|
|
|