mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 09:13:14 +00:00
* fix: reset stale sandbox creation sentinel Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com> * fix: treat SANDBOX_CREATING as a timestamped cross-process lock Only reset the sentinel when proven stale (older than the creation timeout); otherwise wait for the worker that holds the lock so a concurrent run does not create a duplicate sandbox. * feat(analyzer): outcomes dataset + bootstrap/continual split via skills Rename the review_style_analyzer graph to `analyzer` and split it into two modes, plus capture reviewer finding outcomes for continual learning. - Outcomes dataset: upsert resolved-by-commit (positive), dismissed (false positive), and GitHub/Slack thumbs findings into a single LangSmith dataset (openswe-reviewer-outcomes), keyed deterministically per finding+source. Emit points wired into update_finding, resolve_finding_thread, and the GitHub/Slack reaction handlers. - Two playbooks delivered as deepagents skills (bootstrap-repo-analysis, continual-learning), served as virtual files via a CompositeBackend /skills/ route + StateBackend (seeded into the run files channel at invoke time, never written to the sandbox). Mode is set by the launcher; continual runs fall back to the GitHub App installation token. - Split launcher into start_bootstrap_analysis + start_continual_run; register a per-repo nightly continual-learning cron when bootstrap completes. - New read_finding_outcomes tool feeds confirmed/dismissed findings back to the continual playbook. Tests for outcome label mapping, skills helper, and cron idempotency. * fix(analyzer): anchor continual cron runs to a real thread_id The nightly continual-learning cron is threadless, and get_analyzer early-returns an empty agent when configurable.thread_id is missing — so every cron-launched run no-op'd before reading outcomes or saving a refined prompt. Include the repo's deterministic analyzer thread_id in the continual run configurable so the run executes; the threadless run carries no message history, so nightly runs don't accumulate context. * refactor(analyzer): move cron lifecycle calls out of the review-styles store Drop the inline `analyzer_cron` imports from review_styles.py (added only to dodge a circular import) by relocating the cron-trigger calls to the layer above the store: registration to the save_review_style tool (after a prompt is saved) and removal to the dashboard delete route. review_styles.py is now a pure store again with top-level imports only. * refactor: hoist reviewer_outcomes imports to module level Move the two inline emit_finding_status_outcome imports introduced in this PR (update_finding, resolve_finding_thread) to top-level imports. reviewer_outcomes only depends on langsmith, so there is no circular import to avoid. --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
99 lines
3.3 KiB
Python
99 lines
3.3 KiB
Python
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
|
|
import pytest
|
|
|
|
from agent.dashboard import analyzer_cron
|
|
|
|
|
|
class _FakeCrons:
|
|
def __init__(self) -> None:
|
|
self.created: list[dict[str, Any]] = []
|
|
self.deleted: list[str] = []
|
|
|
|
async def create(self, assistant_id: str, **kwargs: Any) -> dict[str, Any]:
|
|
self.created.append({"assistant_id": assistant_id, **kwargs})
|
|
return {"cron_id": "cron_123"}
|
|
|
|
async def delete(self, cron_id: str) -> None:
|
|
self.deleted.append(cron_id)
|
|
|
|
|
|
class _FakeClient:
|
|
def __init__(self) -> None:
|
|
self.crons = _FakeCrons()
|
|
|
|
|
|
@pytest.fixture
|
|
def fake_client(monkeypatch) -> _FakeClient: # noqa: ANN001
|
|
client = _FakeClient()
|
|
monkeypatch.setattr(analyzer_cron, "_client", lambda: client)
|
|
return client
|
|
|
|
|
|
def _patch_record(monkeypatch, record: dict[str, Any] | None) -> dict[str, Any]: # noqa: ANN001
|
|
updates: dict[str, Any] = {}
|
|
|
|
async def fake_get(full_name: str) -> dict[str, Any] | None:
|
|
return record
|
|
|
|
async def fake_update(full_name: str, patch: dict[str, Any]) -> dict[str, Any]:
|
|
updates.update(patch)
|
|
return {**(record or {}), **patch}
|
|
|
|
monkeypatch.setattr(analyzer_cron, "get_review_style", fake_get)
|
|
monkeypatch.setattr(analyzer_cron, "update_review_style", fake_update)
|
|
return updates
|
|
|
|
|
|
async def test_ensure_continual_cron_creates_and_stores(monkeypatch, fake_client) -> None: # noqa: ANN001
|
|
updates = _patch_record(monkeypatch, {"full_name": "o/r", "continual_cron_id": None})
|
|
|
|
cron_id = await analyzer_cron.ensure_continual_cron("o/r")
|
|
|
|
assert cron_id == "cron_123"
|
|
assert len(fake_client.crons.created) == 1
|
|
created = fake_client.crons.created[0]
|
|
assert created["assistant_id"] == "analyzer"
|
|
assert created["config"]["configurable"]["analyzer_mode"] == "continual"
|
|
# Must carry an explicit thread_id, else get_analyzer early-returns an empty
|
|
# agent and the nightly run no-ops.
|
|
assert created["config"]["configurable"].get("thread_id")
|
|
assert "/continual-learning/SKILL.md" in created["input"]["files"]
|
|
assert updates["continual_cron_id"] == "cron_123"
|
|
|
|
|
|
async def test_ensure_continual_cron_idempotent(monkeypatch, fake_client) -> None: # noqa: ANN001
|
|
_patch_record(monkeypatch, {"full_name": "o/r", "continual_cron_id": "existing"})
|
|
|
|
cron_id = await analyzer_cron.ensure_continual_cron("o/r")
|
|
|
|
assert cron_id == "existing"
|
|
assert fake_client.crons.created == []
|
|
|
|
|
|
async def test_remove_continual_cron(monkeypatch, fake_client) -> None: # noqa: ANN001
|
|
updates = _patch_record(monkeypatch, {"full_name": "o/r", "continual_cron_id": "cron_123"})
|
|
|
|
await analyzer_cron.remove_continual_cron("o/r")
|
|
|
|
assert fake_client.crons.deleted == ["cron_123"]
|
|
assert updates["continual_cron_id"] is None
|
|
|
|
|
|
async def test_remove_continual_cron_noop_when_absent(monkeypatch, fake_client) -> None: # noqa: ANN001
|
|
_patch_record(monkeypatch, {"full_name": "o/r", "continual_cron_id": None})
|
|
|
|
await analyzer_cron.remove_continual_cron("o/r")
|
|
|
|
assert fake_client.crons.deleted == []
|
|
|
|
|
|
def test_daily_schedule_is_stable_and_in_window() -> None:
|
|
sched = analyzer_cron._daily_schedule("o/r")
|
|
sched2 = analyzer_cron._daily_schedule("o/r")
|
|
assert sched == sched2
|
|
minute, hour, *_ = sched.split()
|
|
assert 0 <= int(minute) <= 59
|
|
assert 5 <= int(hour) <= 8
|