open-swe/tests/test_stale_sandbox_creating.py
Johannes du Plessis da20e57bcc
fix: refresh sandbox GitHub proxy token before mid-run expiry (#1496)
* fix: refresh sandbox GitHub proxy token before mid-run expiry

GitHub App installation tokens expire after exactly 1 hour. The LangSmith
sandbox proxy was configured once at run start with a snapshot of that
token, so runs longer than ~1h hit 401s on every gh/git call. Record the
proxy token's expiry per thread and add a before-model hook that
re-configures the proxy with a fresh token when it nears expiry.

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>

* fix: preserve repo-scoped proxy token on mid-run refresh

Reviewer runs mint a repository-scoped installation token. Record the
repo scope per thread alongside the expiry so the before-model refresh
re-mints a token with the same scope instead of an installation-wide
token, avoiding privilege expansion on long reviewer runs.

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>

* fix: update passthrough stub for github_proxy_repositories param

---------

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-11 10:59:21 -07:00

101 lines
3.9 KiB
Python

from unittest.mock import AsyncMock, MagicMock, patch
import pytest
from agent.server import (
SANDBOX_BACKENDS,
SANDBOX_CREATING,
SANDBOX_CREATION_TIMEOUT,
ensure_sandbox_for_thread,
)
@pytest.mark.asyncio
async def test_stale_sandbox_creating_without_cached_backend_resets_and_creates() -> None:
thread_id = "thread-stale-creating"
SANDBOX_BACKENDS.clear()
sandbox_backend = MagicMock()
sandbox_backend.id = "sandbox-new"
stale_at = 0.0 # epoch 0 → far older than the timeout
thread = {"metadata": {"sandbox_id": SANDBOX_CREATING, "sandbox_creating_at": stale_at}}
with (
patch(
"agent.server.get_sandbox_id_from_metadata",
new_callable=AsyncMock,
return_value=SANDBOX_CREATING,
),
patch("agent.server.client.threads.get", new_callable=AsyncMock, return_value=thread),
patch("agent.server._create_sandbox_with_proxy", new_callable=AsyncMock) as create_sandbox,
patch("agent.server._configure_git_identity", new_callable=AsyncMock),
patch("agent.server.client.threads.update", new_callable=AsyncMock) as update_thread,
):
create_sandbox.return_value = sandbox_backend
result = await ensure_sandbox_for_thread(thread_id)
assert result.id == "sandbox-new"
create_sandbox.assert_awaited_once()
# Stale sentinel reset (id + timestamp cleared), then fresh creation claims it.
assert update_thread.await_args_list[0].kwargs == {
"thread_id": thread_id,
"metadata": {"sandbox_id": None, "sandbox_creating_at": None},
}
assert update_thread.await_args_list[1].kwargs["metadata"]["sandbox_id"] == SANDBOX_CREATING
assert update_thread.await_args_list[2].kwargs == {
"thread_id": thread_id,
"metadata": {"sandbox_id": "sandbox-new"},
}
SANDBOX_BACKENDS.clear()
@pytest.mark.asyncio
async def test_fresh_sandbox_creating_waits_for_other_worker() -> None:
"""A recent sentinel from another worker must be waited on, not overwritten."""
thread_id = "thread-concurrent-creating"
SANDBOX_BACKENDS.clear()
existing_backend = MagicMock()
existing_backend.id = "sandbox-existing"
import time
fresh_at = time.time() # well within the timeout
threads = [
{"metadata": {"sandbox_id": SANDBOX_CREATING, "sandbox_creating_at": fresh_at}},
{"metadata": {"sandbox_id": "sandbox-existing", "sandbox_creating_at": fresh_at}},
]
async def passthrough(
sb, _thread_id, _github_proxy_token=None, _github_proxy_repositories=None
):
return sb
with (
patch(
"agent.server.get_sandbox_id_from_metadata",
new_callable=AsyncMock,
return_value=SANDBOX_CREATING,
),
patch("agent.server.client.threads.get", new_callable=AsyncMock, side_effect=threads),
patch("agent.server.asyncio.sleep", new_callable=AsyncMock),
patch("agent.server.create_sandbox", return_value=existing_backend) as connect_sandbox,
patch("agent.server._create_sandbox_with_proxy", new_callable=AsyncMock) as create_sandbox,
patch("agent.server.check_or_recreate_sandbox", side_effect=passthrough),
patch("agent.server._refresh_github_proxy_or_recreate", side_effect=passthrough),
patch("agent.server._configure_git_identity", new_callable=AsyncMock),
patch("agent.server.client.threads.update", new_callable=AsyncMock) as update_thread,
):
result = await ensure_sandbox_for_thread(thread_id)
assert result.id == "sandbox-existing"
# Connected to the worker's sandbox; no second sandbox was created.
connect_sandbox.assert_called_once_with("sandbox-existing")
create_sandbox.assert_not_awaited()
# The fresh sentinel was never reset.
for call in update_thread.await_args_list:
assert call.kwargs["metadata"] != {"sandbox_id": None, "sandbox_creating_at": None}
assert SANDBOX_CREATION_TIMEOUT > 0
SANDBOX_BACKENDS.clear()