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.
66 lines
2.5 KiB
Python
66 lines
2.5 KiB
Python
"""Tests for the experimental CapabilityDescriptor (relay Phase 0, Task 0.2)."""
|
|
|
|
from gateway.relay.descriptor import CONTRACT_VERSION, CapabilityDescriptor
|
|
|
|
|
|
def _telegram_descriptor(**overrides) -> CapabilityDescriptor:
|
|
base = dict(
|
|
contract_version=CONTRACT_VERSION,
|
|
platform="telegram",
|
|
label="Telegram",
|
|
max_message_length=4096,
|
|
supports_draft_streaming=False,
|
|
supports_edit=True,
|
|
supports_threads=True,
|
|
markdown_dialect="markdown_v2",
|
|
len_unit="utf16",
|
|
emoji="\u2708\ufe0f",
|
|
platform_hint="You are on Telegram.",
|
|
pii_safe=False,
|
|
)
|
|
base.update(overrides)
|
|
return CapabilityDescriptor(**base)
|
|
|
|
|
|
def test_descriptor_is_frozen():
|
|
d = _telegram_descriptor()
|
|
try:
|
|
d.max_message_length = 1 # type: ignore[misc]
|
|
except Exception as exc: # FrozenInstanceError
|
|
assert "cannot assign" in str(exc) or "frozen" in str(exc).lower()
|
|
else: # pragma: no cover
|
|
raise AssertionError("descriptor should be immutable (frozen)")
|
|
|
|
|
|
def test_module_is_marked_experimental():
|
|
import gateway.relay.descriptor as m
|
|
|
|
assert "EXPERIMENTAL" in (m.__doc__ or "")
|
|
|
|
|
|
# ─────────────── supported_ops (op-level capability discovery, Phase 1) ───────────────
|
|
|
|
|
|
def test_supports_op_legacy_connector_assumes_legacy_set():
|
|
"""An empty supported_ops means the connector predates op discovery: the
|
|
legacy four ops are assumed supported (old connectors keep working), while
|
|
NEW ops are not (discovery semantics — never probe by trying)."""
|
|
d = _telegram_descriptor() # no supported_ops
|
|
for op in ("send", "edit", "typing", "follow_up"):
|
|
assert d.supports_op(op) is True, op
|
|
assert d.supports_op("get_chat_info") is False
|
|
|
|
|
|
def test_from_json_normalizes_malformed_supported_ops():
|
|
"""Non-list shapes and non-string members degrade to the legacy fallback
|
|
(empty tuple), never raise — malformed input can't break the handshake."""
|
|
base = (
|
|
'{"contract_version": 1, "platform": "x", "label": "X", '
|
|
'"max_message_length": 2000, "supports_draft_streaming": false, '
|
|
'"supports_edit": true, "supports_threads": false, '
|
|
'"markdown_dialect": "plain", "len_unit": "chars", '
|
|
)
|
|
d = CapabilityDescriptor.from_json(base + '"supported_ops": "send"}')
|
|
assert d.supported_ops == ()
|
|
d = CapabilityDescriptor.from_json(base + '"supported_ops": ["send", 7, null, ""]}')
|
|
assert d.supported_ops == ("send",)
|