mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
* feat(conventions): standard schema models + effective-map merge * feat(orchestrator): park provider on persistent server overload (529/500) A 429 rate limit already parks a provider — queue its spawns, probe until it recovers — but a persistent 529/500/503 overload had no such break: the run died and the orchestrator crash-retried straight back into the overload, burning tokens in a respawn loop. Generalize the park to provider-unavailability. On a non-graceful Anthropic agent exit, match the API's overload markers (overloaded_error / internal_server_error / "API Error: 5xx") against the dead container's own output and park the provider with kind="overloaded"; the existing spawn gate already queues any parked provider, and the probe-resume loop revives the task when it recovers. Grok keeps its exit-75 path; both now route through one _park_provider_unavailable helper. Markers are kept specific so an agent that merely writes about HTTP 500/529 can't trip the break. Fix the recovery probe to require a 2xx: it treated any non-429 as recovered, so a probe that itself got a 529 would have resumed agents straight back into the overload — wrong for the new path and for a 429 that lifts into a 5xx. Gated by ROBOCO_OVERLOAD_BREAK_ENABLED (default on; off => crash-retry). --------- Co-authored-by: Renn F <rennf93@users.noreply.github.com>
195 lines
6.6 KiB
Python
195 lines
6.6 KiB
Python
"""Server-overload parking: break the 529/500 -> crash -> respawn cost loop.
|
|
|
|
A persistent overload (HTTP 529 / 500 / 503) from the model API kills the run;
|
|
the orchestrator parks the provider — the same break as a 429 rate limit —
|
|
instead of crash-retrying straight back into the overload. The probe-resume
|
|
loop revives the task when the provider recovers. These tests exercise the
|
|
decision points deterministically (logs + tracker + finalize stubbed).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from unittest.mock import AsyncMock
|
|
|
|
import pytest
|
|
from roboco.config import settings
|
|
from roboco.models.runtime import AgentInstance
|
|
from roboco.runtime.orchestrator import (
|
|
_OVERLOAD_RETRY_AFTER_S,
|
|
AgentOrchestrator,
|
|
AgentState,
|
|
)
|
|
|
|
_OVERLOAD_LOG = (
|
|
'API Error: 529 {"type":"error","error":{"type":"overloaded_error",'
|
|
'"message":"Overloaded"}}'
|
|
)
|
|
_CLEAN_LOG = "be-dev-1 finished editing src/app.py; all checks passed"
|
|
|
|
|
|
def _instance(provider_type: str | None = "anthropic") -> AgentInstance:
|
|
cfg = type(
|
|
"C",
|
|
(),
|
|
{"provider_type": provider_type, "model": "claude-x", "git_context": None},
|
|
)()
|
|
inst = AgentInstance(agent_id="be-dev-1", state=AgentState.ACTIVE, config=cfg)
|
|
inst.current_task_id = "task-1"
|
|
inst.container_id = "cid"
|
|
return inst
|
|
|
|
|
|
@pytest.fixture
|
|
def orch() -> AgentOrchestrator:
|
|
return AgentOrchestrator.__new__(AgentOrchestrator)
|
|
|
|
|
|
class _FakeTracker:
|
|
def __init__(self) -> None:
|
|
self.activated_with: dict[str, object] | None = None
|
|
|
|
async def activate(
|
|
self, *, retry_after: float, affected_agents: list[str], kind: str
|
|
) -> None:
|
|
self.activated_with = {
|
|
"retry_after": retry_after,
|
|
"affected_agents": affected_agents,
|
|
"kind": kind,
|
|
}
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# _provider_overload_park_target — the detection decision
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_detects_overload_marker_for_anthropic(
|
|
orch: AgentOrchestrator, monkeypatch: pytest.MonkeyPatch
|
|
) -> None:
|
|
monkeypatch.setattr(settings, "overload_break_enabled", True)
|
|
monkeypatch.setattr(
|
|
orch, "_tail_container_logs", AsyncMock(return_value=_OVERLOAD_LOG)
|
|
)
|
|
assert (
|
|
await orch._provider_overload_park_target("be-dev-1", _instance())
|
|
== "anthropic"
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_clean_output_is_not_overload(
|
|
orch: AgentOrchestrator, monkeypatch: pytest.MonkeyPatch
|
|
) -> None:
|
|
monkeypatch.setattr(settings, "overload_break_enabled", True)
|
|
monkeypatch.setattr(
|
|
orch, "_tail_container_logs", AsyncMock(return_value=_CLEAN_LOG)
|
|
)
|
|
assert await orch._provider_overload_park_target("be-dev-1", _instance()) is None
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_disabled_flag_never_parks(
|
|
orch: AgentOrchestrator, monkeypatch: pytest.MonkeyPatch
|
|
) -> None:
|
|
monkeypatch.setattr(settings, "overload_break_enabled", False)
|
|
tail = AsyncMock(return_value=_OVERLOAD_LOG)
|
|
monkeypatch.setattr(orch, "_tail_container_logs", tail)
|
|
assert await orch._provider_overload_park_target("be-dev-1", _instance()) is None
|
|
tail.assert_not_awaited() # short-circuits before reading logs
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_grok_provider_is_skipped(
|
|
orch: AgentOrchestrator, monkeypatch: pytest.MonkeyPatch
|
|
) -> None:
|
|
"""Grok has its own exit-75 detector; the log-marker path ignores it."""
|
|
monkeypatch.setattr(settings, "overload_break_enabled", True)
|
|
monkeypatch.setattr(
|
|
orch, "_tail_container_logs", AsyncMock(return_value=_OVERLOAD_LOG)
|
|
)
|
|
assert (
|
|
await orch._provider_overload_park_target("gk-dev-1", _instance("grok")) is None
|
|
)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# _park_provider_unavailable — the park action
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_park_offlines_and_activates_with_kind(
|
|
orch: AgentOrchestrator, monkeypatch: pytest.MonkeyPatch
|
|
) -> None:
|
|
inst = _instance()
|
|
inst.error_count = 2 # prior crashes — parking must NOT count one
|
|
tracker = _FakeTracker()
|
|
monkeypatch.setattr(orch, "_make_tracker", lambda _p: tracker)
|
|
monkeypatch.setattr(orch, "_finalize_spawn_session", AsyncMock())
|
|
|
|
await orch._park_provider_unavailable(
|
|
"be-dev-1", inst, provider="anthropic", retry_after=45.0, kind="overloaded"
|
|
)
|
|
|
|
assert inst.state == AgentState.OFFLINE
|
|
assert inst.container_id is None
|
|
assert inst.error_count == 0
|
|
assert tracker.activated_with == {
|
|
"retry_after": pytest.approx(45.0),
|
|
"affected_agents": ["be-dev-1"],
|
|
"kind": "overloaded",
|
|
}
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# _handle_stopped_container — overload short-circuits the crash-retry path
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_stopped_container_parks_on_overload(
|
|
orch: AgentOrchestrator, monkeypatch: pytest.MonkeyPatch
|
|
) -> None:
|
|
inst = _instance()
|
|
park = AsyncMock()
|
|
spawn = AsyncMock()
|
|
monkeypatch.setattr(orch, "_is_grok_rate_limit_exit", lambda _i, _e: False)
|
|
monkeypatch.setattr(
|
|
orch, "_provider_overload_park_target", AsyncMock(return_value="anthropic")
|
|
)
|
|
monkeypatch.setattr(orch, "_park_provider_unavailable", park)
|
|
monkeypatch.setattr(orch, "_finalize_spawn_session", AsyncMock())
|
|
monkeypatch.setattr(orch, "spawn_agent", spawn)
|
|
|
|
await orch._handle_stopped_container("be-dev-1", inst, exit_code=1)
|
|
|
|
park.assert_awaited_once_with(
|
|
"be-dev-1",
|
|
inst,
|
|
provider="anthropic",
|
|
retry_after=_OVERLOAD_RETRY_AFTER_S,
|
|
kind="overloaded",
|
|
)
|
|
spawn.assert_not_awaited() # the crash-retry path is short-circuited
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_stopped_container_crash_retries_when_not_overload(
|
|
orch: AgentOrchestrator, monkeypatch: pytest.MonkeyPatch
|
|
) -> None:
|
|
inst = _instance()
|
|
inst.error_count = 0
|
|
spawn = AsyncMock()
|
|
monkeypatch.setattr(orch, "_is_grok_rate_limit_exit", lambda _i, _e: False)
|
|
monkeypatch.setattr(
|
|
orch, "_provider_overload_park_target", AsyncMock(return_value=None)
|
|
)
|
|
monkeypatch.setattr(orch, "_finalize_spawn_session", AsyncMock())
|
|
monkeypatch.setattr(orch, "spawn_agent", spawn)
|
|
|
|
await orch._handle_stopped_container("be-dev-1", inst, exit_code=1)
|
|
|
|
# Not an overload → the normal crash-retry path runs.
|
|
spawn.assert_awaited_once()
|