Skip to content

armgit / strix

Public Imported from GitHub
0

Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.

fix: stop gracefully with resume hint on persistent RateLimitError (#261) (#593)

Rome Thorstenson777005a42b8e
diff --git a/strix/core/runner.py b/strix/core/runner.py
index 82e653d9..90becf87 100644
--- a/strix/core/runner.py
+++ b/strix/core/runner.py
@@ -11,6 +11,7 @@ from typing import TYPE_CHECKING, Any
from agents import RunConfig
from agents.sandbox import SandboxRunConfig
+from openai import RateLimitError
from strix.agents.factory import build_strix_agent, make_child_factory
from strix.config import load_settings
@@ -308,6 +309,19 @@ async def run_strix_scan(
with contextlib.suppress(Exception):
await coordinator.set_status(root_id, "stopped")
return None
+ except RateLimitError as exc:
+ logger.warning(
+ "Scan %s stopped: persistent rate limit from the LLM provider (%s). "
+ "Resume with 'strix --resume %s' once the limit clears.",
+ scan_id,
+ exc,
+ scan_id,
+ )
+ if root_id is not None:
+ await coordinator.cancel_descendants(root_id)
+ with contextlib.suppress(Exception):
+ await coordinator.set_status(root_id, "stopped")
+ return None
except BaseException:
logger.exception("Strix scan %s failed", scan_id)
if root_id is not None:
diff --git a/tests/test_runner_rate_limit.py b/tests/test_runner_rate_limit.py
new file mode 100644
index 00000000..ed28d250
--- /dev/null
+++ b/tests/test_runner_rate_limit.py
@@ -0,0 +1,84 @@
+"""Tests for graceful handling of persistent RateLimitError in run_strix_scan."""
+
+from __future__ import annotations
+
+import logging
+import types
+from typing import Any
+
+import httpx
+import pytest
+from openai import RateLimitError
+
+import strix.tools.notes.tools as notes_tools
+import strix.tools.todo.tools as todo_tools
+from strix.core import runner
+from strix.core.agents import AgentCoordinator
+
+
+def _make_rate_limit_error() -> RateLimitError:
+ request = httpx.Request("POST", "https://api.openai.com/v1/responses")
+ response = httpx.Response(status_code=429, request=request)
+ return RateLimitError("rate limited", response=response, body=None)
+
+
+async def test_persistent_rate_limit_stops_gracefully(
+ monkeypatch: pytest.MonkeyPatch, tmp_path: Any, caplog: pytest.LogCaptureFixture
+) -> None:
+ """A persistent RateLimitError stops the scan (root -> 'stopped') without raising."""
+ monkeypatch.setattr(runner, "run_dir_for", lambda _scan_id: tmp_path)
+ monkeypatch.setattr(runner, "runtime_state_dir", lambda _run_dir: tmp_path)
+ monkeypatch.setattr(runner, "setup_scan_logging", lambda _run_dir: lambda: None)
+ monkeypatch.setattr(runner, "set_scan_id", lambda _scan_id: None)
+
+ settings = types.SimpleNamespace(
+ llm=types.SimpleNamespace(model="openai/gpt-4o", reasoning_effort="high")
+ )
+ monkeypatch.setattr(runner, "load_settings", lambda: settings)
+ monkeypatch.setattr(runner, "configure_sdk_model_defaults", lambda _settings: None)
+ monkeypatch.setattr(
+ runner, "uses_chat_completions_tool_schema", lambda _model, _settings: False
+ )
+
+ monkeypatch.setattr(todo_tools, "hydrate_todos_from_disk", lambda _state_dir: None)
+ monkeypatch.setattr(notes_tools, "hydrate_notes_from_disk", lambda _state_dir: None)
+
+ async def _create_or_reuse(*_args: Any, **_kwargs: Any) -> dict[str, Any]:
+ return {"client": object(), "session": object(), "caido_client": None}
+
+ async def _cleanup(*_args: Any, **_kwargs: Any) -> None:
+ return None
+
+ monkeypatch.setattr(runner.session_manager, "create_or_reuse", _create_or_reuse)
+ monkeypatch.setattr(runner.session_manager, "cleanup", _cleanup)
+
+ monkeypatch.setattr(runner, "build_root_task", lambda _scan_config: "task")
+ monkeypatch.setattr(runner, "build_scope_context", lambda _scan_config: "")
+ monkeypatch.setattr(runner, "make_model_settings", lambda *_args, **_kwargs: object())
+ monkeypatch.setattr(runner, "build_strix_agent", lambda **_kwargs: object())
+ monkeypatch.setattr(runner, "make_child_factory", lambda **_kwargs: lambda **_k: object())
+ monkeypatch.setattr(runner, "open_agent_session", lambda _root_id, _db: object())
+
+ async def _raise_rate_limit(*_args: Any, **_kwargs: Any) -> None:
+ raise _make_rate_limit_error()
+
+ monkeypatch.setattr(runner, "run_agent_loop", _raise_rate_limit)
+
+ coordinator = AgentCoordinator()
+
+ with caplog.at_level(logging.WARNING):
+ result = await runner.run_strix_scan(
+ scan_config={"targets": [], "scan_mode": "deep"},
+ scan_id="scan-test",
+ image="img",
+ coordinator=coordinator,
+ )
+
+ assert result is None
+ root_ids = [aid for aid, parent in coordinator.parent_of.items() if parent is None]
+ assert len(root_ids) == 1
+ assert coordinator.statuses[root_ids[0]] == "stopped"
+ # the resume hint must carry the real scan id, not a literal placeholder
+ assert "strix --resume scan-test" in caplog.text
+ assert "<run_name>" not in caplog.text