mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +00:00
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.
49 lines
1.9 KiB
Python
49 lines
1.9 KiB
Python
import time
|
|
|
|
import hermes_state
|
|
from hermes_state import SessionDB
|
|
|
|
|
|
def test_export_candidates_via_prune_filters_ended_old_sessions(tmp_path, monkeypatch):
|
|
db = SessionDB(db_path=tmp_path / "state.db")
|
|
monkeypatch.setattr(hermes_state.time, "time", lambda: 2_000_000.0)
|
|
try:
|
|
db.create_session("old_cli", source="cli")
|
|
db.end_session("old_cli", "done")
|
|
db._conn.execute("UPDATE sessions SET started_at=?, ended_at=? WHERE id=?", (1_000_000.0, 1_000_010.0, "old_cli"))
|
|
|
|
db.create_session("new_cli", source="cli")
|
|
db.end_session("new_cli", "done")
|
|
db._conn.execute("UPDATE sessions SET started_at=?, ended_at=? WHERE id=?", (1_990_000.0, 1_990_010.0, "new_cli"))
|
|
|
|
db.create_session("old_active", source="cli")
|
|
db._conn.execute("UPDATE sessions SET started_at=? WHERE id=?", (1_000_000.0, "old_active"))
|
|
db._conn.commit()
|
|
|
|
# Export uses the shared prune/archive candidate selection.
|
|
candidates = db.list_prune_candidates(
|
|
started_before=2_000_000.0 - 5 * 86400, archived=None
|
|
)
|
|
assert [c["id"] for c in candidates] == ["old_cli"]
|
|
finally:
|
|
db.close()
|
|
|
|
|
|
|
|
|
|
def test_get_compression_lineage_returns_only_compression_chain(tmp_path):
|
|
db = SessionDB(db_path=tmp_path / "state.db")
|
|
try:
|
|
db.create_session("root", source="cli")
|
|
db.end_session("root", "compression")
|
|
db.create_session("child", source="cli", parent_session_id="root")
|
|
db.end_session("child", "compression")
|
|
db.create_session("tip", source="cli", parent_session_id="child")
|
|
db.create_session("branch", source="cli", parent_session_id="root", model_config={"_branched_from": "root"})
|
|
|
|
assert db.get_compression_lineage("tip") == ["root", "child", "tip"]
|
|
assert db.get_compression_lineage("branch") == ["branch"]
|
|
finally:
|
|
db.close()
|
|
|
|
|