mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +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.
60 lines
2.3 KiB
Python
60 lines
2.3 KiB
Python
"""Tests for MessageDeduplicator TTL enforcement (#10306).
|
|
|
|
Previously, is_duplicate() returned True for any previously seen ID without
|
|
checking its age — expired entries were only purged when cache size exceeded
|
|
max_size. Normal workloads never overflowed, so messages stayed "duplicate"
|
|
forever.
|
|
|
|
The fix checks TTL at query time: if the entry's timestamp plus TTL is in
|
|
the past, the entry is treated as expired and the message is allowed through.
|
|
"""
|
|
|
|
import time
|
|
|
|
from gateway.platforms.helpers import MessageDeduplicator
|
|
|
|
|
|
class TestMessageDeduplicatorTTL:
|
|
"""TTL-based expiration must work regardless of cache size."""
|
|
|
|
def test_duplicate_within_ttl(self):
|
|
"""Same message within TTL window is duplicate."""
|
|
dedup = MessageDeduplicator(ttl_seconds=60)
|
|
assert dedup.is_duplicate("msg-1") is False
|
|
assert dedup.is_duplicate("msg-1") is True
|
|
|
|
def test_not_duplicate_after_ttl_expires(self):
|
|
"""Same message AFTER TTL expires should NOT be duplicate."""
|
|
dedup = MessageDeduplicator(ttl_seconds=5)
|
|
assert dedup.is_duplicate("msg-1") is False
|
|
|
|
# Fast-forward time past TTL
|
|
dedup._seen["msg-1"] = time.time() - 10 # 10s ago, TTL is 5s
|
|
assert dedup.is_duplicate("msg-1") is False, \
|
|
"Expired entry should not be treated as duplicate"
|
|
|
|
|
|
def test_contains_expires_stale_message_without_refreshing_it(self):
|
|
dedup = MessageDeduplicator(ttl_seconds=5)
|
|
dedup._seen["msg-1"] = time.time() - 10
|
|
|
|
assert dedup.contains("msg-1") is False
|
|
assert "msg-1" not in dedup._seen
|
|
|
|
def test_max_size_eviction_prunes_expired(self):
|
|
"""Cache pruning on overflow removes expired entries."""
|
|
dedup = MessageDeduplicator(max_size=5, ttl_seconds=60)
|
|
# Add 6 entries, with the first 3 expired
|
|
now = time.time()
|
|
for i in range(3):
|
|
dedup._seen[f"old-{i}"] = now - 120 # expired (2 min ago, TTL 60s)
|
|
for i in range(3):
|
|
dedup.is_duplicate(f"new-{i}")
|
|
# Now we have 6 entries. Next insert triggers pruning.
|
|
dedup.is_duplicate("trigger")
|
|
# The 3 expired entries should be gone, leaving 4 fresh ones
|
|
assert len(dedup._seen) == 4
|
|
assert "old-0" not in dedup._seen
|
|
assert "new-0" in dedup._seen
|
|
|
|
|