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.
89 lines
3 KiB
Python
89 lines
3 KiB
Python
"""Tests for structured send-error classification (SendResult.error_kind).
|
|
|
|
Covers the platform-neutral ``classify_send_error`` vocabulary in
|
|
``gateway/platforms/base.py`` and its wiring into the Telegram adapter's
|
|
``send()`` failure path, so consumers can branch on a typed category instead
|
|
of substring-matching the raw provider message.
|
|
"""
|
|
|
|
import pytest
|
|
|
|
from gateway.platforms.base import (
|
|
SEND_ERROR_KINDS,
|
|
SendResult,
|
|
classify_send_error,
|
|
)
|
|
|
|
|
|
class _FakeBadRequest(Exception):
|
|
"""Stand-in for a provider BadRequest carrying a message string."""
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,expected",
|
|
[
|
|
("Message_too_long", "too_long"),
|
|
("Bad Request: message is too long", "too_long"),
|
|
("Bad Request: can't parse entities: unsupported start tag", "bad_format"),
|
|
("Bad Request: can't find end of the entity", "bad_format"),
|
|
("Forbidden: bot was blocked by the user", "forbidden"),
|
|
("Forbidden: user is deactivated", "forbidden"),
|
|
("Bad Request: not enough rights to send text messages", "forbidden"),
|
|
("Bad Request: chat not found", "not_found"),
|
|
("Bad Request: message to edit not found", "not_found"),
|
|
("Too Many Requests: retry after 12", "rate_limited"),
|
|
("Flood control exceeded", "rate_limited"),
|
|
("ConnectError: connection refused", "transient"),
|
|
("ConnectTimeout", "transient"),
|
|
("some entirely novel provider message", "unknown"),
|
|
("", "unknown"),
|
|
],
|
|
)
|
|
def test_classify_send_error_text(text, expected):
|
|
assert classify_send_error(None, text) == expected
|
|
|
|
|
|
def test_every_classification_is_in_the_vocabulary():
|
|
samples = [
|
|
"message_too_long",
|
|
"can't parse entities",
|
|
"forbidden",
|
|
"chat not found",
|
|
"flood",
|
|
"connecterror",
|
|
"mystery",
|
|
"",
|
|
]
|
|
for s in samples:
|
|
assert classify_send_error(None, s) in SEND_ERROR_KINDS
|
|
|
|
|
|
def test_telegram_send_failure_populates_error_kind():
|
|
"""Telegram send() failures carry a typed error_kind alongside error."""
|
|
import asyncio
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
|
|
from gateway.config import PlatformConfig
|
|
from plugins.platforms.telegram.adapter import TelegramAdapter
|
|
|
|
cfg = PlatformConfig(enabled=True, token="fake-token", extra={})
|
|
adapter = TelegramAdapter(cfg)
|
|
|
|
# Minimal bot whose send_message raises a parse/entity rejection.
|
|
bot = MagicMock()
|
|
bot.send_message = AsyncMock(
|
|
side_effect=Exception("Bad Request: can't parse entities: bad tag")
|
|
)
|
|
bot.send_chat_action = AsyncMock()
|
|
# Force the legacy (non-rich) path and a connected bot.
|
|
adapter._bot = bot
|
|
adapter._rich_messages_enabled = False
|
|
|
|
result = asyncio.run(adapter.send("123", "<b>broken"))
|
|
assert result.success is False
|
|
# Telegram has a plain-text fallback for parse errors inside the send loop,
|
|
# so a raw parse failure that still escapes is classified for consumers.
|
|
assert result.error_kind in SEND_ERROR_KINDS
|
|
assert result.error_kind != "unknown" or result.error
|
|
|
|
|