mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
[F045] rate-limit: loud activate-failure log + in-memory orphan-probe fallback
The in-verb i_am_blocked(rate_limited) path wrapped RateLimitStateTracker.activate in a bare contextlib.suppress. A silent activate failure stranded the fleet: agents were parked in _waiting_records but the provider never entered the tracker, so the tracker-driven _sweep_rate_limit_probes never probed it and no _on_probe_success ever resumed them — parked agents stuck in WAITING_LONG. Fix: (1) replace the bare suppress with a try/except that logs an error event naming the provider + affected agents; (2) in _sweep_rate_limit_probes, after probing the tracker-listed set, scan _waiting_records for any rate_limit_lifted provider the loop did NOT cover and probe it via the time-expiry fallback (empty state -> probe now) so _on_probe_success resumes the parked agents. The fallback reads only local memory, so it still resumes when Redis was down at park time (list_rate_limited_providers failure now falls through to the orphan scan instead of returning early).
This commit is contained in:
@@ -6337,6 +6337,17 @@ Start by:
|
||||
- **Failure**: increment probe_failures; if the count reaches 10 and
|
||||
we haven't already sent a CEO notification for this episode, send
|
||||
one now.
|
||||
|
||||
F045: the loop is tracker-driven, but an ``activate()`` failure in the
|
||||
in-verb ``i_am_blocked(rate_limited)`` path (or a Redis hiccup) can
|
||||
leave agents parked in ``_waiting_records`` for a provider the tracker
|
||||
never learned about — so the tracker-listed loop above never probes it
|
||||
and the parked agents strand in WAITING_LONG forever. After probing the
|
||||
tracker-listed set, scan the in-memory records for any
|
||||
``rate_limit_lifted`` provider the loop did NOT cover and probe it via
|
||||
the time-expiry fallback (empty state → ``_too_early_to_probe`` returns
|
||||
False → probe now) so ``_on_probe_success`` can resume them. The
|
||||
fallback reads only local memory, so it works even when Redis is down.
|
||||
"""
|
||||
from roboco.services.gateway.rate_limit_tracker import RateLimitStateTracker
|
||||
|
||||
@@ -6344,9 +6355,11 @@ Start by:
|
||||
providers = await RateLimitStateTracker.list_rate_limited_providers()
|
||||
except Exception as e:
|
||||
logger.warning("Failed to list rate-limited providers", error=str(e))
|
||||
return
|
||||
providers = []
|
||||
|
||||
probed_providers: set[str] = set()
|
||||
for provider, state in providers:
|
||||
probed_providers.add(provider)
|
||||
try:
|
||||
await self._probe_one_provider(provider, state)
|
||||
except Exception as e:
|
||||
@@ -6356,6 +6369,28 @@ Start by:
|
||||
error=str(e),
|
||||
)
|
||||
|
||||
# F045 orphan fallback: resume agents parked for a provider the
|
||||
# tracker-listed loop above did not cover (activate failed silently or
|
||||
# Redis was down at park time). Empty state => probe immediately; on
|
||||
# success ``_on_probe_success`` clears the tracker (self-healing) and
|
||||
# resumes the parked agents.
|
||||
orphan_providers: set[str] = set()
|
||||
for record in self._waiting_records.values():
|
||||
if record.waiting_for != "rate_limit_lifted":
|
||||
continue
|
||||
prov = record.context.get("provider")
|
||||
if prov and prov not in probed_providers:
|
||||
orphan_providers.add(prov)
|
||||
for provider in orphan_providers:
|
||||
try:
|
||||
await self._probe_one_provider(provider, {})
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
"Unhandled error probing orphaned rate-limited provider",
|
||||
provider=provider,
|
||||
error=str(e),
|
||||
)
|
||||
|
||||
def _make_tracker(self, provider: str) -> Any:
|
||||
"""Return a RateLimitStateTracker for *provider*.
|
||||
|
||||
|
||||
@@ -2941,8 +2941,19 @@ class Choreographer:
|
||||
# calls can gate new spawns for this provider. Skipped when the
|
||||
# provider is "unknown" (orchestrator not wired or not tracking the
|
||||
# agent) to avoid polluting the tracker with meaningless keys.
|
||||
#
|
||||
# F045: an activate() failure is logged loudly, NOT bare-suppressed.
|
||||
# The probe-resume loop is tracker-driven — it iterates
|
||||
# ``list_rate_limited_providers()`` — so a silent activate failure here
|
||||
# leaves every parked agent in ``_waiting_records`` with a provider the
|
||||
# tracker never learned about, and no probe ever runs to resume them
|
||||
# (the stranded-fleet blind spot). The orchestrator's
|
||||
# ``_sweep_rate_limit_probes`` has an in-memory ``_waiting_records``
|
||||
# fallback that resumes them when the provider recovers even without
|
||||
# tracker state; this error log makes the condition visible to
|
||||
# operators either way.
|
||||
if provider != "unknown":
|
||||
with contextlib.suppress(Exception):
|
||||
try:
|
||||
from roboco.services.gateway.rate_limit_tracker import (
|
||||
RateLimitStateTracker,
|
||||
)
|
||||
@@ -2951,6 +2962,14 @@ class Choreographer:
|
||||
retry_after=retry_after_seconds,
|
||||
affected_agents=affected_agents,
|
||||
)
|
||||
except Exception as exc:
|
||||
logger.error(
|
||||
"rate_limit_tracker.activate failed; parked agents rely on"
|
||||
" the in-memory probe fallback to resume",
|
||||
provider=provider,
|
||||
affected_agents=affected_agents,
|
||||
error=str(exc),
|
||||
)
|
||||
|
||||
bus = self.stream_bus
|
||||
if bus is not None:
|
||||
|
||||
@@ -20,6 +20,7 @@ from uuid import uuid4
|
||||
|
||||
from roboco.models.events import EventType
|
||||
from roboco.services.gateway.choreographer import Choreographer, ChoreographerDeps
|
||||
from structlog.testing import capture_logs
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Helpers
|
||||
@@ -505,3 +506,31 @@ class TestRateLimitTrackerActivateOnParking:
|
||||
|
||||
assert env.error is None
|
||||
assert env.status == "in_progress"
|
||||
|
||||
async def test_activate_failure_is_logged_not_silent(self) -> None:
|
||||
"""F045: an activate() failure must be logged loudly, not bare-suppressed.
|
||||
|
||||
The probe-resume loop is tracker-driven, so a silent activate failure
|
||||
strands every parked agent in WAITING_LONG with no probe ever running.
|
||||
A loud error log makes the stranded-fleet condition visible to
|
||||
operators (and pairs with the orchestrator's in-memory fallback sweep).
|
||||
"""
|
||||
agent_id = uuid4()
|
||||
task_id = uuid4()
|
||||
orch = _make_orchestrator(active_agents=["be-dev-1"], provider=_PROVIDER)
|
||||
deps = _make_deps(agent_id, task_id, orchestrator=orch)
|
||||
c = Choreographer(deps)
|
||||
|
||||
mock_tracker = AsyncMock()
|
||||
mock_tracker.activate = AsyncMock(side_effect=RuntimeError("redis down"))
|
||||
mock_tracker_cls = MagicMock(return_value=mock_tracker)
|
||||
|
||||
with patch(_TRACKER_PATCH, mock_tracker_cls), capture_logs() as logs:
|
||||
env = await c.i_am_blocked(agent_id, task_id, "rate_limited")
|
||||
|
||||
assert env.error is None
|
||||
assert any(
|
||||
"activate" in str(e.get("event", "")).lower()
|
||||
and e.get("log_level") == "error"
|
||||
for e in logs
|
||||
), f"expected an error log about activate failure; got {logs!r}"
|
||||
|
||||
@@ -414,6 +414,93 @@ class TestCEONotificationThreshold:
|
||||
notify_mock.assert_awaited_once()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Tests: orphan-provider fallback (F045)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestOrphanProviderFallback:
|
||||
"""F045: an activate() failure in the in-verb ``i_am_blocked(rate_limited)``
|
||||
path leaves agents parked in ``_waiting_records`` but the provider never
|
||||
makes it into the tracker — so the tracker-driven loop never probes it and
|
||||
the parked agents strand in WAITING_LONG forever. The sweep must scan the
|
||||
in-memory records for any ``rate_limit_lifted`` provider the tracker-listed
|
||||
set did NOT cover and probe it via the time-expiry fallback so
|
||||
``_on_probe_success`` can resume them.
|
||||
"""
|
||||
|
||||
async def test_orphan_parked_agent_resumed_when_tracker_lacks_provider(
|
||||
self,
|
||||
) -> None:
|
||||
orch = _make_orchestrator()
|
||||
provider = "anthropic"
|
||||
agent = "be-dev-1"
|
||||
orch._waiting_records = {agent: _waiting_record(agent, provider)}
|
||||
|
||||
tracker_mock = _make_tracker_mock()
|
||||
resolve_mock = AsyncMock(return_value=None)
|
||||
|
||||
with (
|
||||
patch.object(orch, "resolve_wait", new=resolve_mock),
|
||||
patch.object(orch, "_make_tracker", return_value=tracker_mock),
|
||||
patch.object(orch, "_do_probe", new=AsyncMock(return_value=True)),
|
||||
patch.object(
|
||||
RateLimitStateTracker,
|
||||
"list_rate_limited_providers",
|
||||
new=AsyncMock(return_value=[]),
|
||||
),
|
||||
patch("roboco.events.get_event_bus") as mock_bus_fn,
|
||||
):
|
||||
bus_mock = AsyncMock()
|
||||
bus_mock.publish = AsyncMock()
|
||||
mock_bus_fn.return_value = bus_mock
|
||||
|
||||
await orch._sweep_rate_limit_probes()
|
||||
|
||||
# The orphan provider was probed and the parked agent resumed.
|
||||
assert resolve_mock.await_count == 1
|
||||
assert resolve_mock.call_args.args[0] == agent
|
||||
|
||||
async def test_orphan_skipped_when_tracker_already_covers_provider(
|
||||
self,
|
||||
) -> None:
|
||||
"""A provider the tracker lists must NOT be double-probed via the fallback."""
|
||||
orch = _make_orchestrator()
|
||||
provider = "anthropic"
|
||||
agent = "be-dev-1"
|
||||
orch._waiting_records = {agent: _waiting_record(agent, provider)}
|
||||
|
||||
tracker_mock = _make_tracker_mock()
|
||||
resolve_mock = AsyncMock(return_value=None)
|
||||
state = _make_active_state(provider, retry_after=None)
|
||||
|
||||
probe_calls: list[str] = []
|
||||
|
||||
async def fake_do_probe(p: str) -> bool:
|
||||
probe_calls.append(p)
|
||||
return True
|
||||
|
||||
with (
|
||||
patch.object(orch, "resolve_wait", new=resolve_mock),
|
||||
patch.object(orch, "_make_tracker", return_value=tracker_mock),
|
||||
patch.object(orch, "_do_probe", new=fake_do_probe),
|
||||
patch.object(
|
||||
RateLimitStateTracker,
|
||||
"list_rate_limited_providers",
|
||||
new=AsyncMock(return_value=[(provider, state)]),
|
||||
),
|
||||
patch("roboco.events.get_event_bus") as mock_bus_fn,
|
||||
):
|
||||
bus_mock = AsyncMock()
|
||||
bus_mock.publish = AsyncMock()
|
||||
mock_bus_fn.return_value = bus_mock
|
||||
|
||||
await orch._sweep_rate_limit_probes()
|
||||
|
||||
# Probed exactly once (via the tracker-listed path), not twice.
|
||||
assert probe_calls == [provider]
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Tests: list_rate_limited_providers
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
Reference in New Issue
Block a user