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.
112 lines
4 KiB
Python
112 lines
4 KiB
Python
"""Tests for typed block reasons + the unblock-loop breaker.
|
|
|
|
Covers the built-in fix for the kanban "blocked loop" — a worker blocks a
|
|
task, a cron unblocks it, the worker re-blocks for the same reason, repeat
|
|
forever. The fix gives ``block_task`` a typed ``kind`` and a persistent
|
|
``block_recurrences`` counter:
|
|
|
|
* ``dependency`` blocks route to ``todo`` (parent-gated, auto-resumed) and
|
|
never enter the human ``blocked`` bucket a cron would keep unblocking.
|
|
* ``needs_input`` / ``capability`` / un-typed blocks land in ``blocked``;
|
|
each same-cause re-block after an unblock increments ``block_recurrences``,
|
|
and at ``BLOCK_RECURRENCE_LIMIT`` the task routes to ``triage`` for a human.
|
|
* ``unblock_task`` deliberately does NOT reset ``block_recurrences`` (the
|
|
amnesia that let the loop run unbounded).
|
|
* A successful ``complete_task`` resets the loop memory.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from hermes_cli import kanban_db as kb
|
|
|
|
|
|
@pytest.fixture
|
|
def kanban_home(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> Path:
|
|
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 _running_task(conn, title="t"):
|
|
"""Create a task and drive it to ``running`` so block_task can act."""
|
|
tid = kb.create_task(conn, title=title, assignee="worker")
|
|
with kb.write_txn(conn):
|
|
conn.execute("UPDATE tasks SET status='ready' WHERE id=?", (tid,))
|
|
claimed = kb.claim_task(conn, tid, claimer="worker")
|
|
assert claimed is not None
|
|
return tid
|
|
|
|
|
|
def _make_running_again(conn, tid):
|
|
with kb.write_txn(conn):
|
|
conn.execute("UPDATE tasks SET status='ready' WHERE id=?", (tid,))
|
|
assert kb.claim_task(conn, tid, claimer="worker") is not None
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Loop breaker
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_block_loop_detected_event_emitted(kanban_home: Path) -> None:
|
|
with kb.connect_closing() as conn:
|
|
tid = _running_task(conn)
|
|
kb.block_task(conn, tid, reason="x", kind="capability")
|
|
kb.unblock_task(conn, tid)
|
|
_make_running_again(conn, tid)
|
|
kb.block_task(conn, tid, reason="x", kind="capability")
|
|
events = [e for e in kb.list_events(conn, tid)
|
|
if e.kind == "block_loop_detected"]
|
|
assert events, "expected a block_loop_detected event"
|
|
payload = events[-1].payload or {}
|
|
assert payload.get("recurrences") == 2
|
|
assert payload.get("kind") == "capability"
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Dependency routing
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def test_dependency_then_parent_done_promotes(kanban_home: Path) -> None:
|
|
"""A dependency-parked child becomes ready once its parent completes."""
|
|
with kb.connect_closing() as conn:
|
|
parent = kb.create_task(conn, title="parent", assignee="worker")
|
|
child = _running_task(conn, title="child")
|
|
kb.link_tasks(conn, parent_id=parent, child_id=child)
|
|
kb.block_task(conn, child, reason="wait", kind="dependency")
|
|
assert kb.get_task(conn, child).status == "todo"
|
|
# Finish the parent, then let recompute_ready run.
|
|
with kb.write_txn(conn):
|
|
conn.execute("UPDATE tasks SET status='ready' WHERE id=?", (parent,))
|
|
kb.claim_task(conn, parent, claimer="worker")
|
|
kb.complete_task(conn, parent, result="done")
|
|
kb.recompute_ready(conn)
|
|
assert kb.get_task(conn, child).status == "ready"
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Completion resets loop memory
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Validation + back-compat
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|