Files
hermes-agent/tests/gateway/test_telegram_conflict.py
Teknium 75fcbc44ce feat(telegram): auto-discover fallback IPs via DoH when api.telegram.org is unreachable (#3376)
* feat(telegram): auto-discover fallback IPs via DoH when api.telegram.org is unreachable

On some networks (university, corporate), api.telegram.org resolves to a
valid Telegram IP that is unreachable due to routing/firewall rules. A
different IP in the same Telegram-owned 149.154.160.0/20 block works fine.

This adds automatic fallback IP discovery at connect time:
1. Query Google and Cloudflare DNS-over-HTTPS for api.telegram.org A records
2. Exclude the system-DNS IP (the unreachable one), use the rest as fallbacks
3. If DoH is also blocked, fall back to a seed list (149.154.167.220)
4. TelegramFallbackTransport tries primary first, sticks to whichever works

No configuration needed — works automatically. TELEGRAM_FALLBACK_IPS env var
still available as manual override. Zero impact on healthy networks (primary
path succeeds on first attempt, fallback never exercised).

No new dependencies (uses httpx already in deps + stdlib socket).

* fix: share transport instance and downgrade seed fallback log to info

- Use single TelegramFallbackTransport shared between request and
  get_updates_request so sticky IP is shared across polling and API calls
- Keep separate HTTPXRequest instances (different timeout settings)
- Downgrade "using seed fallback IPs" from warning to info to avoid
  noisy logs on healthy networks

* fix: add telegram.request mock and discovery fixture to remaining test files

The original PR missed test_dm_topics.py and
test_telegram_network_reconnect.py — both need the telegram.request
mock module. The reconnect test also needs _no_auto_discovery since
_handle_polling_network_error calls connect() which now invokes
discover_fallback_ips().

---------

Co-authored-by: Mohan Qiao <Gavin-Qiao@users.noreply.github.com>
2026-03-27 04:03:13 -07:00

250 lines
8.1 KiB
Python

import asyncio
import sys
from types import SimpleNamespace
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
telegram_mod = MagicMock()
telegram_mod.ext.ContextTypes.DEFAULT_TYPE = type(None)
telegram_mod.constants.ParseMode.MARKDOWN_V2 = "MarkdownV2"
telegram_mod.constants.ChatType.GROUP = "group"
telegram_mod.constants.ChatType.SUPERGROUP = "supergroup"
telegram_mod.constants.ChatType.CHANNEL = "channel"
telegram_mod.constants.ChatType.PRIVATE = "private"
for name in ("telegram", "telegram.ext", "telegram.constants", "telegram.request"):
sys.modules.setdefault(name, telegram_mod)
_ensure_telegram_mock()
from gateway.platforms.telegram import TelegramAdapter # noqa: E402
@pytest.fixture(autouse=True)
def _no_auto_discovery(monkeypatch):
"""Disable DoH auto-discovery so connect() uses the plain builder chain."""
async def _noop():
return []
monkeypatch.setattr("gateway.platforms.telegram.discover_fallback_ips", _noop)
@pytest.mark.asyncio
async def test_connect_rejects_same_host_token_lock(monkeypatch):
adapter = TelegramAdapter(PlatformConfig(enabled=True, token="secret-token"))
monkeypatch.setattr(
"gateway.status.acquire_scoped_lock",
lambda scope, identity, metadata=None: (False, {"pid": 4242}),
)
ok = await adapter.connect()
assert ok is False
assert adapter.fatal_error_code == "telegram_token_lock"
assert adapter.has_fatal_error is True
assert "already using this Telegram bot token" in adapter.fatal_error_message
@pytest.mark.asyncio
async def test_polling_conflict_retries_before_fatal(monkeypatch):
"""A single 409 should trigger a retry, not an immediate fatal error."""
adapter = TelegramAdapter(PlatformConfig(enabled=True, token="***"))
fatal_handler = AsyncMock()
adapter.set_fatal_error_handler(fatal_handler)
monkeypatch.setattr(
"gateway.status.acquire_scoped_lock",
lambda scope, identity, metadata=None: (True, None),
)
monkeypatch.setattr(
"gateway.status.release_scoped_lock",
lambda scope, identity: None,
)
captured = {}
async def fake_start_polling(**kwargs):
captured["error_callback"] = kwargs["error_callback"]
updater = SimpleNamespace(
start_polling=AsyncMock(side_effect=fake_start_polling),
stop=AsyncMock(),
running=True,
)
bot = SimpleNamespace(set_my_commands=AsyncMock())
app = SimpleNamespace(
bot=bot,
updater=updater,
add_handler=MagicMock(),
initialize=AsyncMock(),
start=AsyncMock(),
)
builder = MagicMock()
builder.token.return_value = builder
builder.build.return_value = app
monkeypatch.setattr("gateway.platforms.telegram.Application", SimpleNamespace(builder=MagicMock(return_value=builder)))
# Speed up retries for testing
monkeypatch.setattr("asyncio.sleep", AsyncMock())
ok = await adapter.connect()
assert ok is True
assert callable(captured["error_callback"])
conflict = type("Conflict", (Exception,), {})
# First conflict: should retry, NOT be fatal
captured["error_callback"](conflict("Conflict: terminated by other getUpdates request"))
await asyncio.sleep(0)
await asyncio.sleep(0)
# Give the scheduled task a chance to run
for _ in range(10):
await asyncio.sleep(0)
assert adapter.has_fatal_error is False, "First conflict should not be fatal"
assert adapter._polling_conflict_count == 0, "Count should reset after successful retry"
@pytest.mark.asyncio
async def test_polling_conflict_becomes_fatal_after_retries(monkeypatch):
"""After exhausting retries, the conflict should become fatal."""
adapter = TelegramAdapter(PlatformConfig(enabled=True, token="***"))
fatal_handler = AsyncMock()
adapter.set_fatal_error_handler(fatal_handler)
monkeypatch.setattr(
"gateway.status.acquire_scoped_lock",
lambda scope, identity, metadata=None: (True, None),
)
monkeypatch.setattr(
"gateway.status.release_scoped_lock",
lambda scope, identity: None,
)
captured = {}
async def fake_start_polling(**kwargs):
captured["error_callback"] = kwargs["error_callback"]
# Make start_polling fail on retries to exhaust retries
call_count = {"n": 0}
async def failing_start_polling(**kwargs):
call_count["n"] += 1
if call_count["n"] == 1:
# First call (initial connect) succeeds
captured["error_callback"] = kwargs["error_callback"]
else:
# Retry calls fail
raise Exception("Connection refused")
updater = SimpleNamespace(
start_polling=AsyncMock(side_effect=failing_start_polling),
stop=AsyncMock(),
running=True,
)
bot = SimpleNamespace(set_my_commands=AsyncMock())
app = SimpleNamespace(
bot=bot,
updater=updater,
add_handler=MagicMock(),
initialize=AsyncMock(),
start=AsyncMock(),
)
builder = MagicMock()
builder.token.return_value = builder
builder.build.return_value = app
monkeypatch.setattr("gateway.platforms.telegram.Application", SimpleNamespace(builder=MagicMock(return_value=builder)))
# Speed up retries for testing
monkeypatch.setattr("asyncio.sleep", AsyncMock())
ok = await adapter.connect()
assert ok is True
conflict = type("Conflict", (Exception,), {})
# Directly call _handle_polling_conflict to avoid event-loop scheduling
# complexity. Each call simulates one 409 from Telegram.
for i in range(4):
await adapter._handle_polling_conflict(
conflict("Conflict: terminated by other getUpdates request")
)
# After 3 failed retries (count 1-3 each enter the retry branch but
# start_polling raises), the 4th conflict pushes count to 4 which
# exceeds MAX_CONFLICT_RETRIES (3), entering the fatal branch.
assert adapter.fatal_error_code == "telegram_polling_conflict", (
f"Expected fatal after 4 conflicts, got code={adapter.fatal_error_code}, "
f"count={adapter._polling_conflict_count}"
)
assert adapter.has_fatal_error is True
fatal_handler.assert_awaited_once()
@pytest.mark.asyncio
async def test_connect_marks_retryable_fatal_error_for_startup_network_failure(monkeypatch):
adapter = TelegramAdapter(PlatformConfig(enabled=True, token="***"))
monkeypatch.setattr(
"gateway.status.acquire_scoped_lock",
lambda scope, identity, metadata=None: (True, None),
)
monkeypatch.setattr(
"gateway.status.release_scoped_lock",
lambda scope, identity: None,
)
builder = MagicMock()
builder.token.return_value = builder
app = SimpleNamespace(
bot=SimpleNamespace(),
updater=SimpleNamespace(),
add_handler=MagicMock(),
initialize=AsyncMock(side_effect=RuntimeError("Temporary failure in name resolution")),
start=AsyncMock(),
)
builder.build.return_value = app
monkeypatch.setattr("gateway.platforms.telegram.Application", SimpleNamespace(builder=MagicMock(return_value=builder)))
ok = await adapter.connect()
assert ok is False
assert adapter.fatal_error_code == "telegram_connect_error"
assert adapter.fatal_error_retryable is True
assert "Temporary failure in name resolution" in adapter.fatal_error_message
@pytest.mark.asyncio
async def test_disconnect_skips_inactive_updater_and_app(monkeypatch):
adapter = TelegramAdapter(PlatformConfig(enabled=True, token="***"))
updater = SimpleNamespace(running=False, stop=AsyncMock())
app = SimpleNamespace(
updater=updater,
running=False,
stop=AsyncMock(),
shutdown=AsyncMock(),
)
adapter._app = app
warning = MagicMock()
monkeypatch.setattr("gateway.platforms.telegram.logger.warning", warning)
await adapter.disconnect()
updater.stop.assert_not_awaited()
app.stop.assert_not_awaited()
app.shutdown.assert_awaited_once()
warning.assert_not_called()