mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +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.
226 lines
6.8 KiB
Python
226 lines
6.8 KiB
Python
"""Tests for hermes_cli.kanban_diagnostics — rule-engine that produces
|
|
structured distress signals (diagnostics) for kanban tasks.
|
|
|
|
These tests exercise each rule in isolation using minimal in-memory
|
|
task/event/run fixtures (no DB) plus a few integration-style cases
|
|
that round-trip through the real kanban_db to make sure the rule
|
|
engine works on sqlite3.Row objects as well as dataclasses.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import time
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from hermes_cli import kanban_db as kb
|
|
from hermes_cli import kanban_diagnostics as kd
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Fixtures
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
@pytest.fixture
|
|
def kanban_home(tmp_path, monkeypatch):
|
|
home = tmp_path / ".hermes"
|
|
home.mkdir()
|
|
monkeypatch.setenv("HERMES_HOME", str(home))
|
|
monkeypatch.setattr(Path, "home", lambda: tmp_path)
|
|
kb.init_db()
|
|
return home
|
|
|
|
|
|
def _task(**overrides):
|
|
base = {
|
|
"id": "t_demo00",
|
|
"title": "demo task",
|
|
"assignee": "demo",
|
|
"status": "ready",
|
|
"consecutive_failures": 0,
|
|
"last_failure_error": None,
|
|
}
|
|
base.update(overrides)
|
|
return base
|
|
|
|
|
|
def _event(kind, ts=None, **payload):
|
|
return {
|
|
"kind": kind,
|
|
"created_at": int(ts if ts is not None else time.time()),
|
|
"payload": payload or None,
|
|
}
|
|
|
|
|
|
def _run(outcome="completed", run_id=1, error=None):
|
|
return {
|
|
"id": run_id,
|
|
"outcome": outcome,
|
|
"error": error,
|
|
}
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Each rule — positive + negative + clearing
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_stuck_in_blocked_fires_past_threshold():
|
|
now = int(time.time())
|
|
task = _task(status="blocked")
|
|
events = [
|
|
_event("blocked", ts=now - 3600 * 48, reason="needs approval"),
|
|
]
|
|
diags = kd.compute_task_diagnostics(
|
|
task, events, [], now=now,
|
|
)
|
|
assert len(diags) == 1
|
|
d = diags[0]
|
|
assert d.kind == "stuck_in_blocked"
|
|
assert d.severity == "warning"
|
|
assert d.data["age_hours"] >= 48
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_repeated_crashes_truncates_huge_tracebacks():
|
|
"""Full Python tracebacks can be tens of KB. The title stays one
|
|
line (≤160 chars); the detail caps at 500 chars + ellipsis so the
|
|
card doesn't explode visually."""
|
|
huge = "Traceback (most recent call last):\n" + (" File\n" * 500)
|
|
task = _task(status="ready")
|
|
runs = [
|
|
_run(outcome="crashed", run_id=1, error=huge),
|
|
_run(outcome="crashed", run_id=2, error=huge),
|
|
]
|
|
diags = kd.compute_task_diagnostics(task, [], runs)
|
|
d = diags[0]
|
|
# Title only the first line, capped.
|
|
assert "\n" not in d.title
|
|
assert len(d.title) < 250
|
|
# Detail contains the snippet with ellipsis.
|
|
assert d.detail.endswith("…") or len(d.detail) < 700
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Severity sorting
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Integration — runs through real kanban_db so sqlite.Row fields work
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def test_engine_works_on_sqlite_row_objects(kanban_home):
|
|
"""Regression: the rule functions must handle sqlite3.Row (which
|
|
supports mapping access but not attribute access and isn't a dict)
|
|
as well as dataclass Task / plain dict. The API layer passes Row
|
|
objects directly.
|
|
"""
|
|
conn = kb.connect()
|
|
try:
|
|
parent = kb.create_task(conn, title="p", assignee="w")
|
|
real = kb.create_task(conn, title="r", assignee="x", created_by="w")
|
|
with pytest.raises(kb.HallucinatedCardsError):
|
|
kb.complete_task(
|
|
conn, parent,
|
|
summary="with phantom", created_cards=[real, "t_deadbeef1"],
|
|
)
|
|
# Pull Row objects the way the API helper does.
|
|
row = conn.execute(
|
|
"SELECT * FROM tasks WHERE id = ?", (parent,),
|
|
).fetchone()
|
|
events = list(conn.execute(
|
|
"SELECT * FROM task_events WHERE task_id = ? ORDER BY id",
|
|
(parent,),
|
|
).fetchall())
|
|
runs = list(conn.execute(
|
|
"SELECT * FROM task_runs WHERE task_id = ? ORDER BY id",
|
|
(parent,),
|
|
).fetchall())
|
|
diags = kd.compute_task_diagnostics(row, events, runs)
|
|
assert len(diags) == 1
|
|
assert diags[0].kind == "hallucinated_cards"
|
|
assert "t_deadbeef1" in diags[0].data["phantom_ids"]
|
|
finally:
|
|
conn.close()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Error-tolerance: a broken rule shouldn't 500 the whole compute call
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# stranded_in_ready
|
|
#
|
|
# Surfaces ready tasks that nobody has claimed within the threshold.
|
|
# Identity-agnostic by design: catches typo'd assignees, deleted profiles,
|
|
# down external worker pools, and misconfigured dispatchers in one rule.
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def test_stranded_in_ready_fires_when_age_exceeds_threshold():
|
|
"""Default threshold = 30 min. A ready task promoted 45 min ago
|
|
with no claim should fire as a warning."""
|
|
now = 100_000
|
|
task = _task(status="ready", assignee="demo", claim_lock=None)
|
|
# 45 min = 2700s, threshold = 1800s.
|
|
events = [_event("created", ts=now - 45 * 60)]
|
|
diags = kd.compute_task_diagnostics(task, events, [], now=now)
|
|
stranded = [d for d in diags if d.kind == "stranded_in_ready"]
|
|
assert len(stranded) == 1
|
|
assert stranded[0].severity == "warning"
|
|
assert stranded[0].data["age_seconds"] == 45 * 60
|
|
assert stranded[0].data["assignee"] == "demo"
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# triage_aux_unavailable rule — auto-decompose aware
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def _triage_task():
|
|
return _task(id="t_triage1", status="triage")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_severity_at_or_above_uses_threshold_semantics():
|
|
assert kd.severity_at_or_above("warning", "warning") is True
|
|
assert kd.severity_at_or_above("error", "warning") is True
|
|
assert kd.severity_at_or_above("critical", "warning") is True
|
|
assert kd.severity_at_or_above("critical", "error") is True
|
|
assert kd.severity_at_or_above("warning", "error") is False
|
|
assert kd.severity_at_or_above("error", "critical") is False
|
|
assert kd.severity_at_or_above("mystery", "warning") is False
|
|
assert kd.severity_at_or_above("warning", None) is True
|