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.
109 lines
3.8 KiB
Python
109 lines
3.8 KiB
Python
"""
|
|
Tests for Slack inbound mention humanization + bot identity grounding.
|
|
|
|
Slack delivers user mentions as opaque IDs (``<@U123>``). Passing those to the
|
|
agent raw leaves it unable to tell one participant from another — or from
|
|
itself — so it can misread a mention of a human as a self-mention and reply to
|
|
messages addressed to that person (the reported "bot thinks it's @someone-else"
|
|
bug). Two cooperating fixes:
|
|
|
|
* ``_humanize_user_mentions`` rewrites ``<@UID>`` → ``@DisplayName`` (the
|
|
Slack equivalent of Discord's ``clean_content``).
|
|
* ``_build_identity_prompt`` returns an ephemeral system-prompt line naming
|
|
the bot's own Slack handle so the agent has a positive "that's me" anchor.
|
|
"""
|
|
|
|
import sys
|
|
from unittest.mock import MagicMock
|
|
|
|
import pytest
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Mock slack-bolt if not installed (same pattern as test_slack_mention.py)
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def _ensure_slack_mock():
|
|
if "slack_bolt" in sys.modules and hasattr(sys.modules["slack_bolt"], "__file__"):
|
|
return
|
|
|
|
slack_bolt = MagicMock()
|
|
slack_bolt.async_app.AsyncApp = MagicMock
|
|
slack_bolt.adapter.socket_mode.async_handler.AsyncSocketModeHandler = MagicMock
|
|
|
|
slack_sdk = MagicMock()
|
|
slack_sdk.web.async_client.AsyncWebClient = MagicMock
|
|
|
|
for name, mod in [
|
|
("slack_bolt", slack_bolt),
|
|
("slack_bolt.async_app", slack_bolt.async_app),
|
|
("slack_bolt.adapter", slack_bolt.adapter),
|
|
("slack_bolt.adapter.socket_mode", slack_bolt.adapter.socket_mode),
|
|
("slack_bolt.adapter.socket_mode.async_handler",
|
|
slack_bolt.adapter.socket_mode.async_handler),
|
|
("slack_sdk", slack_sdk),
|
|
("slack_sdk.web", slack_sdk.web),
|
|
("slack_sdk.web.async_client", slack_sdk.web.async_client),
|
|
]:
|
|
sys.modules.setdefault(name, mod)
|
|
sys.modules.setdefault("aiohttp", MagicMock())
|
|
|
|
|
|
_ensure_slack_mock()
|
|
|
|
import plugins.platforms.slack.adapter as _slack_mod # noqa: E402
|
|
_slack_mod.SLACK_AVAILABLE = True
|
|
|
|
from plugins.platforms.slack.adapter import SlackAdapter # noqa: E402
|
|
|
|
|
|
def _make_adapter():
|
|
# object.__new__ skips __init__ (heavy setup) — established slack-test pattern.
|
|
return object.__new__(SlackAdapter)
|
|
|
|
|
|
def _adapter_with_names(names):
|
|
"""Adapter whose _resolve_user_name returns from a fixed UID→name map."""
|
|
adapter = _make_adapter()
|
|
|
|
async def _resolve(user_id, chat_id="", team_id=""):
|
|
return names.get(user_id, user_id)
|
|
|
|
adapter._resolve_user_name = _resolve # type: ignore[assignment]
|
|
return adapter
|
|
|
|
|
|
# ----- _humanize_user_mentions -------------------------------------------------
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_humanizes_multiple_distinct_mentions():
|
|
adapter = _adapter_with_names(
|
|
{"U07ALICE": "Alice Example", "U07BOB": "Bob Example"}
|
|
)
|
|
out = await adapter._humanize_user_mentions(
|
|
"hey <@U07ALICE> and <@U07BOB>", chat_id="C1"
|
|
)
|
|
assert out == "hey @Alice Example and @Bob Example"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_handles_labelled_mention_form():
|
|
# Slack sometimes sends <@UID|handle>; only the ID drives resolution.
|
|
adapter = _adapter_with_names({"U07ALICE": "Alice Example"})
|
|
out = await adapter._humanize_user_mentions("<@U07ALICE|alice> hi", chat_id="C1")
|
|
assert out == "@Alice Example hi"
|
|
|
|
|
|
# ----- _build_identity_prompt --------------------------------------------------
|
|
|
|
def test_identity_prompt_names_the_bot():
|
|
adapter = _make_adapter()
|
|
adapter._bot_display_name = "TestBot"
|
|
adapter._team_bot_names = {}
|
|
prompt = adapter._build_identity_prompt(team_id="T1")
|
|
assert "@TestBot" in prompt
|
|
# Must instruct that another participant's mention is not a self-mention.
|
|
assert "not a mention of you" in prompt
|
|
|
|
|