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.
73 lines
2.3 KiB
Python
73 lines
2.3 KiB
Python
"""Regression tests for issue #47237.
|
|
|
|
When the gateway persists a user message after a transient provider
|
|
failure (429/timeout/auth error), subsequent retries of the same
|
|
Telegram message must not stack duplicate user turns in the transcript.
|
|
The dedupe guard checks has_platform_message_id before persisting.
|
|
"""
|
|
|
|
from gateway.session import SessionStore
|
|
from hermes_state import SessionDB
|
|
|
|
|
|
class TestHasPlatformMessageId:
|
|
"""SessionDB.has_platform_message_id and SessionStore wrapper."""
|
|
|
|
def _make_db(self, tmp_path):
|
|
db = SessionDB(tmp_path / "state.db")
|
|
db.create_session("s1", "cli")
|
|
return db
|
|
|
|
|
|
def test_returns_false_for_different_session(self, tmp_path):
|
|
db = self._make_db(tmp_path)
|
|
db.create_session("s2", "cli")
|
|
db.append_message(
|
|
session_id="s1",
|
|
role="user",
|
|
content="hello",
|
|
platform_message_id="msg-123",
|
|
)
|
|
assert not db.has_platform_message_id("s2", "msg-123")
|
|
|
|
|
|
def test_session_store_wrapper_proxies_to_db(self, tmp_path):
|
|
db = self._make_db(tmp_path)
|
|
db.append_message(
|
|
session_id="s1",
|
|
role="user",
|
|
content="hello",
|
|
platform_message_id="msg-456",
|
|
)
|
|
store = SessionStore.__new__(SessionStore)
|
|
store._db = db
|
|
assert store.has_platform_message_id("s1", "msg-456")
|
|
assert not store.has_platform_message_id("s1", "msg-000")
|
|
|
|
|
|
class TestDedupeOnTransientFailure:
|
|
"""The gateway's transient-failure path must not persist duplicates."""
|
|
|
|
@staticmethod
|
|
def _make_db(tmp_path):
|
|
db = SessionDB(tmp_path / "state.db")
|
|
db.create_session("s1", "cli")
|
|
return db
|
|
|
|
def test_duplicate_message_id_skipped(self, tmp_path):
|
|
"""When has_platform_message_id returns True, the append is skipped."""
|
|
db = self._make_db(tmp_path)
|
|
db.append_message(
|
|
session_id="s1",
|
|
role="user",
|
|
content="hello",
|
|
platform_message_id="msg-789",
|
|
)
|
|
store = SessionStore.__new__(SessionStore)
|
|
store._db = db
|
|
|
|
# Simulate a second attempt to persist the same message
|
|
assert store.has_platform_message_id("s1", "msg-789")
|
|
# The gateway code checks this before calling append_to_transcript,
|
|
# so the second append should never fire.
|
|
|