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.
87 lines
2.7 KiB
Python
87 lines
2.7 KiB
Python
"""Tests for gateway /compress --preview/--dry-run/--aggressive flags
|
|
(PR #3243 salvage).
|
|
|
|
The preview path must return a report WITHOUT building an agent or
|
|
touching the transcript; --aggressive must return an explanatory
|
|
message rather than being mis-parsed as a focus topic.
|
|
"""
|
|
|
|
from datetime import datetime
|
|
from unittest.mock import MagicMock
|
|
|
|
import pytest
|
|
|
|
from gateway.config import GatewayConfig, Platform, PlatformConfig
|
|
from gateway.platforms.base import MessageEvent
|
|
from gateway.session import SessionEntry, SessionSource, build_session_key
|
|
|
|
|
|
def _make_source() -> SessionSource:
|
|
return SessionSource(
|
|
platform=Platform.TELEGRAM,
|
|
user_id="u1",
|
|
chat_id="c1",
|
|
user_name="tester",
|
|
chat_type="dm",
|
|
)
|
|
|
|
|
|
def _make_event(text: str) -> MessageEvent:
|
|
return MessageEvent(text=text, source=_make_source(), message_id="m1")
|
|
|
|
|
|
def _make_history(n_pairs: int = 3) -> list[dict[str, str]]:
|
|
h: list[dict[str, str]] = []
|
|
for i in range(n_pairs):
|
|
h.append({"role": "user", "content": f"u{i}"})
|
|
h.append({"role": "assistant", "content": f"a{i}"})
|
|
return h
|
|
|
|
|
|
def _make_runner(history: list[dict[str, str]]):
|
|
from gateway.run import GatewayRunner
|
|
|
|
runner = object.__new__(GatewayRunner)
|
|
runner.config = GatewayConfig(
|
|
platforms={Platform.TELEGRAM: PlatformConfig(enabled=True, token="***")}
|
|
)
|
|
session_entry = SessionEntry(
|
|
session_key=build_session_key(_make_source()),
|
|
session_id="sess-1",
|
|
created_at=datetime.now(),
|
|
updated_at=datetime.now(),
|
|
platform=Platform.TELEGRAM,
|
|
chat_type="dm",
|
|
)
|
|
runner.session_store = MagicMock()
|
|
runner.session_store.get_or_create_session.return_value = session_entry
|
|
runner.session_store.load_transcript.return_value = history
|
|
runner.session_store.rewrite_transcript = MagicMock()
|
|
runner.session_store.update_session = MagicMock()
|
|
runner.session_store._save = MagicMock()
|
|
runner._session_db = None
|
|
return runner
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_preview_with_here_boundary():
|
|
runner = _make_runner(_make_history(4))
|
|
result = await runner._handle_compress_command(
|
|
_make_event("/compress --preview here 2")
|
|
)
|
|
assert "last 2 exchange" in result
|
|
assert "4 of 8" in result
|
|
runner.session_store.rewrite_transcript.assert_not_called()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_aggressive_dry_run_shows_preview_plus_note():
|
|
runner = _make_runner(_make_history(3))
|
|
result = await runner._handle_compress_command(
|
|
_make_event("/compress --aggressive --dry-run")
|
|
)
|
|
assert "no changes made" in result.lower()
|
|
assert "--aggressive is not supported" in result
|
|
runner.session_store.rewrite_transcript.assert_not_called()
|
|
|
|
|