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.
77 lines
2.8 KiB
Python
77 lines
2.8 KiB
Python
"""TelegramAdapter.send_draft MarkdownV2 formatting parity.
|
|
|
|
Bot API 9.5 ``sendMessageDraft`` powers the animated streaming preview in
|
|
DMs. The regular ``send`` path renders with MarkdownV2, so the draft must
|
|
too — otherwise the live preview streams as raw text and the final
|
|
``sendMessage`` snaps into formatted output, producing a jarring visual
|
|
shift at the end of the response (reported by an external user, May 2026).
|
|
|
|
These tests pin:
|
|
1. The happy path passes ``parse_mode=MARKDOWN_V2`` with format_message'd
|
|
text (formatting parity with the final message).
|
|
2. A MarkdownV2 BadRequest triggers a single plain-text retry rather than
|
|
killing draft streaming for the whole response.
|
|
3. A non-BadRequest failure propagates so the caller falls back to edit.
|
|
"""
|
|
import sys
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
|
|
import pytest
|
|
|
|
from gateway.config import PlatformConfig
|
|
|
|
|
|
def _ensure_telegram_mock():
|
|
if "telegram" in sys.modules and hasattr(sys.modules["telegram"], "__file__"):
|
|
return
|
|
mod = MagicMock()
|
|
mod.error.NetworkError = type("NetworkError", (OSError,), {})
|
|
mod.error.TimedOut = type("TimedOut", (OSError,), {})
|
|
mod.error.BadRequest = type("BadRequest", (Exception,), {})
|
|
for name in ("telegram", "telegram.ext", "telegram.constants", "telegram.request"):
|
|
sys.modules.setdefault(name, mod)
|
|
sys.modules.setdefault("telegram.error", mod.error)
|
|
|
|
|
|
_ensure_telegram_mock()
|
|
|
|
import plugins.platforms.telegram.adapter as tg_mod # noqa: E402
|
|
from plugins.platforms.telegram.adapter import TelegramAdapter # noqa: E402
|
|
|
|
|
|
def _make_adapter() -> TelegramAdapter:
|
|
adapter = TelegramAdapter(PlatformConfig(enabled=True, token="***"))
|
|
adapter._bot = MagicMock()
|
|
adapter._bot.send_message_draft = AsyncMock(return_value=True)
|
|
return adapter
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_send_draft_falls_back_to_plain_text_on_markdownv2_error():
|
|
"""A MarkdownV2 BadRequest retries once as plain text (no parse_mode),
|
|
instead of aborting draft streaming for the whole response."""
|
|
adapter = _make_adapter()
|
|
adapter.format_message = lambda content: f"FMT::{content}"
|
|
|
|
# Resolve the BadRequest type the adapter checks via _is_bad_request_error.
|
|
from telegram.error import BadRequest # type: ignore
|
|
calls = []
|
|
|
|
async def _draft(**kwargs):
|
|
calls.append(kwargs)
|
|
if "parse_mode" in kwargs:
|
|
raise BadRequest("can't parse entities")
|
|
return True
|
|
|
|
adapter._bot.send_message_draft = AsyncMock(side_effect=_draft)
|
|
|
|
result = await adapter.send_draft("123", 9, "weird _text")
|
|
|
|
assert result.success is True
|
|
# First attempt: MarkdownV2; second attempt: plain text, no parse_mode.
|
|
assert len(calls) == 2
|
|
assert "parse_mode" in calls[0]
|
|
assert "parse_mode" not in calls[1]
|
|
assert calls[1]["text"] == "weird _text" # raw, unformatted
|
|
|
|
|