open-swe/tests/test_reconcile_sweep.py
Johannes du Plessis 209132d355
refactor: durable interrupt dispatch + completion webhook (#1621)
* wip(rebuild): core reliability spine

- remove PR-babysitting (ci_autofix + ci_monitor graph + webhook wiring)
- dispatch core: agent/dispatch.py with multitask_strategy=interrupt +
  durability=sync + completion webhook; reroute all webhook + plan triggers;
  drop the racy in-process lock + is_thread_active busy-check
- completion webhook: agent/completion.py + /webhooks/run-complete loopback
  route for failure/timeout replies (idempotent)

Co-authored-by: open-swe[bot]

* feat(rebuild): async tools, reconcile, shared http timeouts, assembly tuning

Parallel batch on top of the reliability spine:
- async-ify all 24 tools (drop asyncio.run; requests->httpx); re-implement the
  http_request/fetch_url SSRF + DNS-rebinding defense httpx-natively and harden
  the IP check to 'not is_global' (+ IPv4-mapped unwrap)
- reconcile.py: stale pending-run sweep (threads.search -> per-thread runs.list
  -> cancel_many), wired into the scheduler graph via task='reconcile'
- shared DEFAULT_HTTP_TIMEOUT (agent/utils/http.py) on every bare
  httpx.AsyncClient() across utils/dashboard/webapp/middleware
- run budget: MODEL_CALL_RECURSION_LIMIT 5000->250
- fix stale OpenAI->Anthropic fallback id (claude-opus-4-5 -> 4-8)
- drop redundant custom repair middleware (deepagents auto-adds PatchToolCalls)
- confirm tool-result eviction + summarization auto-wired via backend
- slim system prompt ~8% (full harness-profile rewrite deferred)

Co-authored-by: open-swe[bot]

* feat(rebuild): harness-profile prompt + split webhooks out of webapp

- prompt.py: own the system prompt via a registered harness profile
  (OPEN_SWE_SHARED_BASE, kept neutral so the read-only reviewer/analyzer that
  share it stay safe), registered across all 4 providers; per-thread values
  stay in construct_system_prompt. Assembled main-agent prompt ~6.8k -> ~3.1k
  tokens (~55% smaller); de-duped PR/commit/suite/force-push guidance; dropped
  ALL-CAPS markers.
- webapp.py 3325 -> 1890 LOC: moved 14 per-source handlers into
  agent/webhooks/{linear,slack,github}.py; webapp re-exports them for the
  routes + tests; moved handlers reach shared helpers via the webapp namespace
  to preserve the test suite's monkeypatch targets.

Full suite: 1168 passing, lint clean.

Co-authored-by: open-swe[bot]

* Restore MODEL_CALL_RECURSION_LIMIT to 5000 for long-running tasks

Reverts the 250 cap from the run-budget change — long-running tasks legitimately
need many model calls. The notify_step_limit_reached safety net still fires if a
run does hit the cap, so runs end with a signal either way.

Co-authored-by: open-swe[bot]

* fix: address PR review (auth, SSRF, interrupted status, redirect headers)

- completion.py: drop `interrupted` from failure statuses — with
  multitask_strategy=interrupt a follow-up ends the prior run as interrupted,
  which is healthy, not a failure to report. [open-swe]
- /webhooks/run-complete: shared-secret auth — dispatch appends ?token= when
  RUN_COMPLETE_WEBHOOK_SECRET is set; route verifies via hmac.compare_digest.
  [corridor-security]
- SSRF: extract the URL validator to agent/utils/url_safety.py and apply it
  before server-side image fetches in multimodal.fetch_image_block.
  [corridor-security]
- http_request: preserve caller headers/extensions across redirect hops instead
  of dropping them on the first hop. [open-swe]

Co-authored-by: open-swe[bot]

* chore: remove REBUILD_PLAN.md (planning doc, not needed in the repo)

Co-authored-by: open-swe[bot]

* fix: fail closed on run-complete webhook auth when secret unset

Corridor follow-up: verify_run_complete_token returns False (not True) when
RUN_COMPLETE_WEBHOOK_SECRET is unset, so the public route is never
unauthenticated. Logs a startup warning when the secret is absent, and dispatch
skips registering the webhook when there's no secret (no rejected callbacks).

Co-authored-by: open-swe[bot]

---------

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-26 13:48:38 -07:00

158 lines
5.5 KiB
Python

from __future__ import annotations
from datetime import UTC, datetime, timedelta
from typing import Any
from unittest.mock import AsyncMock
import pytest
from agent import reconcile
def _run(run_id: str, thread_id: str, age_seconds: float) -> dict[str, Any]:
created = datetime.now(UTC) - timedelta(seconds=age_seconds)
return {
"run_id": run_id,
"thread_id": thread_id,
"status": "pending",
"created_at": created.isoformat(),
}
class _FakeThreads:
def __init__(self, pages: list[list[dict[str, Any]]]) -> None:
self._pages = pages
self.search_calls: list[dict[str, Any]] = []
async def search(self, **kwargs: Any) -> list[dict[str, Any]]:
self.search_calls.append(kwargs)
offset = kwargs.get("offset", 0)
limit = kwargs.get("limit", 100)
index = offset // limit if limit else 0
if index < len(self._pages):
return self._pages[index]
return []
class _FakeRuns:
def __init__(self, runs_by_thread: dict[str, Any]) -> None:
self._runs_by_thread = runs_by_thread
self.cancel_many = AsyncMock(return_value=None)
self.list_calls: list[tuple[str, dict[str, Any]]] = []
async def list(self, thread_id: str, **kwargs: Any) -> list[dict[str, Any]]:
self.list_calls.append((thread_id, kwargs))
value = self._runs_by_thread.get(thread_id, [])
if isinstance(value, Exception):
raise value
return value
class _FakeClient:
def __init__(self, threads: _FakeThreads, runs: _FakeRuns) -> None:
self.threads = threads
self.runs = runs
def _patch(monkeypatch: pytest.MonkeyPatch, client: _FakeClient) -> None:
monkeypatch.setattr(reconcile, "langgraph_client", lambda: client)
@pytest.mark.asyncio
async def test_cancels_only_stale_pending_runs(monkeypatch: pytest.MonkeyPatch) -> None:
threads = _FakeThreads([[{"thread_id": "t1"}]])
runs = _FakeRuns(
{
"t1": [
_run("old1", "t1", age_seconds=4000),
_run("fresh1", "t1", age_seconds=60),
_run("old2", "t1", age_seconds=10000),
]
}
)
_patch(monkeypatch, _FakeClient(threads, runs))
counts = await reconcile.reconcile_stale_runs(max_age_seconds=1800)
assert counts == {"threads_checked": 1, "stale_runs": 2, "cancelled": 2}
runs.cancel_many.assert_awaited_once()
kwargs = runs.cancel_many.await_args.kwargs
assert kwargs["thread_id"] == "t1"
assert sorted(kwargs["run_ids"]) == ["old1", "old2"]
@pytest.mark.asyncio
async def test_no_stale_runs_means_no_cancel(monkeypatch: pytest.MonkeyPatch) -> None:
threads = _FakeThreads([[{"thread_id": "t1"}]])
runs = _FakeRuns({"t1": [_run("fresh1", "t1", age_seconds=30)]})
_patch(monkeypatch, _FakeClient(threads, runs))
counts = await reconcile.reconcile_stale_runs(max_age_seconds=1800)
assert counts == {"threads_checked": 1, "stale_runs": 0, "cancelled": 0}
runs.cancel_many.assert_not_awaited()
@pytest.mark.asyncio
async def test_bad_thread_does_not_abort_sweep(monkeypatch: pytest.MonkeyPatch) -> None:
threads = _FakeThreads([[{"thread_id": "bad"}, {"thread_id": "good"}]])
runs = _FakeRuns(
{
"bad": RuntimeError("runs.list exploded"),
"good": [_run("old1", "good", age_seconds=5000)],
}
)
_patch(monkeypatch, _FakeClient(threads, runs))
counts = await reconcile.reconcile_stale_runs(max_age_seconds=1800)
# Both threads counted; the good thread is still reconciled despite the bad one.
assert counts == {"threads_checked": 2, "stale_runs": 1, "cancelled": 1}
runs.cancel_many.assert_awaited_once()
assert runs.cancel_many.await_args.kwargs["thread_id"] == "good"
assert runs.cancel_many.await_args.kwargs["run_ids"] == ["old1"]
@pytest.mark.asyncio
async def test_paginates_busy_threads(monkeypatch: pytest.MonkeyPatch) -> None:
full_page = [{"thread_id": f"t{i}"} for i in range(reconcile._SEARCH_PAGE_SIZE)]
second_page = [{"thread_id": "tail"}]
threads = _FakeThreads([full_page, second_page])
runs_by_thread: dict[str, Any] = {t["thread_id"]: [] for t in full_page}
runs_by_thread["tail"] = [_run("old", "tail", age_seconds=9000)]
runs = _FakeRuns(runs_by_thread)
_patch(monkeypatch, _FakeClient(threads, runs))
counts = await reconcile.reconcile_stale_runs(max_age_seconds=1800)
assert counts["threads_checked"] == reconcile._SEARCH_PAGE_SIZE + 1
assert counts["cancelled"] == 1
# Two search calls: first full page triggers a second page fetch.
assert len(threads.search_calls) == 2
assert threads.search_calls[0]["offset"] == 0
assert threads.search_calls[1]["offset"] == reconcile._SEARCH_PAGE_SIZE
assert threads.search_calls[0]["status"] == "busy"
@pytest.mark.asyncio
async def test_unparseable_created_at_is_skipped(monkeypatch: pytest.MonkeyPatch) -> None:
threads = _FakeThreads([[{"thread_id": "t1"}]])
runs = _FakeRuns(
{
"t1": [
{
"run_id": "bad",
"thread_id": "t1",
"status": "pending",
"created_at": "not-a-date",
},
_run("old", "t1", age_seconds=5000),
]
}
)
_patch(monkeypatch, _FakeClient(threads, runs))
counts = await reconcile.reconcile_stale_runs(max_age_seconds=1800)
assert counts == {"threads_checked": 1, "stale_runs": 1, "cancelled": 1}
assert runs.cancel_many.await_args.kwargs["run_ids"] == ["old"]