mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 20:53:15 +00:00
Some checks are pending
CI / Lint (push) Waiting to run
CI / Format check (push) Waiting to run
CI / Unit tests (push) Waiting to run
CI / Playwright E2E (push) Waiting to run
CI / Docker build smoke (push) Waiting to run
CI / Triage ledger up to date (push) Waiting to run
CI / ui bun.lock in sync (push) Waiting to run
* feat: port plan-review & workflow-approval UX (#135)
Port six upstream commits onto dev:
- c03a6be7 (already ported): keep plan guidance high-level
- 546042a4: add workflow approval UI with diff preview, approval URLs,
web review links, and polling for approval status during active runs
- 216cf181: remove workflow token elevation; approved pushes pass
through directly without proxy token rewriting
- 3dbc0282: preserve plan redirects after login by accepting relative
same-origin redirect_to values and rejecting blocked paths
- bb104d93: submit plan comments with cmd+enter
- 90cb6caa: terse Slack replies, shared content via save_plan outside
plan mode (PLAN_STATUS_SHARED), reject shared-content mutations
Refs: #135
* feat: port durable dispatch hardening and startup latency improvements
Port five upstream PRs onto dev:
- #1621 / #1658: durable dispatch with loopback webhook defense,
create_durable_run helper, _config_with_prepare_run_id, degradation
to None for relative/loopback completion webhook URLs
- #1696: run-level completion webhook deduplication (replace
claim-then-post with post-then-flag per run_id), DeferredErrorModel
for graph-factory resilience, ToolRetryMiddleware for task subagents,
TimeoutWrapupMiddleware for all three graphs
- #1697: lazy-load __init__.py for agent.middleware, agent.tools,
agent.dashboard (PEP 562); defer heavy imports (exa_py in web_search,
agent.webapp in request_pr_review, deepagents in sandbox.py); add
ttl_cache.py with stale-while-revalidate for tool loaders
Refs: #137
* fix: restore login page render and clear CI lint/format
The plan-review port removed the authRedirectUrl import from login.tsx
but left its call site, crashing the login page at runtime (blank page,
no 'Sign in to open-swe'). Pass the relative path straight to loginUrl,
matching the plan route and the backend relative-redirect handling.
Also drop an unused os import in the guard test and reformat
workflow_push_guard.py to satisfy ruff.
* fix: restore RepairOrphaned middleware export and repoint model fake to deferred_model boundary
* fix: restore RepairOrphanedToolCallsMiddleware, fix E2E model-fake patch, drop dead ttl_cache
- Re-add RepairOrphanedToolCallsMiddleware to the lazy middleware __init__
(_MIDDLEWARE_MODULES, __all__, TYPE_CHECKING) so agent.reviewer can import it.
- Reroute E2E model patching to deferred_model.make_model so make_model_or_defer
(used by all three graph factories) returns the scripted fake instead of
building a real model with fake credentials.
- Drop unused agent/utils/ttl_cache.py — no agent module imports it.
- Fix import ordering in agent/reviewer.py and agent/analyzer.py (ruff I001).
- Format tests/test_dispatch.py.
* fix: claim-then-post run-level failure dedup; stop permanent suppression
---------
Co-authored-by: amoussa1229 <166072409+amoussa1229@users.noreply.github.com>
Co-authored-by: Adam Moussa <adam@seahavenind.com>
124 lines
4 KiB
Python
124 lines
4 KiB
Python
from __future__ import annotations
|
|
|
|
import importlib
|
|
from typing import Any
|
|
|
|
import pytest
|
|
|
|
dispatch = importlib.import_module("agent.dispatch")
|
|
|
|
_ABSOLUTE = "https://open-swe-v3-abc.us.langgraph.app/webhooks/run-complete"
|
|
|
|
|
|
def test_is_loopback_webhook_relative() -> None:
|
|
assert dispatch._is_loopback_webhook("/webhooks/run-complete") is True
|
|
|
|
|
|
def test_is_loopback_webhook_localhost() -> None:
|
|
assert dispatch._is_loopback_webhook("http://localhost:2024/webhooks/run-complete") is True
|
|
assert dispatch._is_loopback_webhook("http://127.0.0.1:8000/webhooks/run-complete") is True
|
|
|
|
|
|
def test_is_loopback_webhook_absolute() -> None:
|
|
assert dispatch._is_loopback_webhook(_ABSOLUTE) is False
|
|
|
|
|
|
def test_resolve_no_secret_attaches_nothing() -> None:
|
|
assert dispatch._resolve_completion_webhook_url(_ABSOLUTE, None) is None
|
|
assert dispatch._resolve_completion_webhook_url(_ABSOLUTE, "") is None
|
|
|
|
|
|
def test_resolve_relative_url_degrades_to_none() -> None:
|
|
# Secret set but a loopback URL would 422 every run — attach nothing instead.
|
|
assert dispatch._resolve_completion_webhook_url("/webhooks/run-complete", "s3cret") is None
|
|
|
|
|
|
def test_resolve_localhost_url_degrades_to_none() -> None:
|
|
assert dispatch._resolve_completion_webhook_url("http://localhost/x", "s3cret") is None
|
|
|
|
|
|
def test_resolve_absolute_url_appends_token() -> None:
|
|
assert (
|
|
dispatch._resolve_completion_webhook_url(_ABSOLUTE, "s3cret") == f"{_ABSOLUTE}?token=s3cret"
|
|
)
|
|
|
|
|
|
def test_resolve_absolute_url_with_existing_query_left_as_is() -> None:
|
|
url = f"{_ABSOLUTE}?token=preset"
|
|
assert dispatch._resolve_completion_webhook_url(url, "s3cret") == url
|
|
|
|
|
|
class _FakeRuns:
|
|
def __init__(self) -> None:
|
|
self.created: list[dict[str, Any]] = []
|
|
|
|
async def create(self, thread_id: str, assistant_id: str, **kwargs: Any) -> dict[str, str]:
|
|
self.created.append({"thread_id": thread_id, "assistant_id": assistant_id, **kwargs})
|
|
return {"run_id": "run-1"}
|
|
|
|
|
|
class _FakeClient:
|
|
def __init__(self) -> None:
|
|
self.runs = _FakeRuns()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_create_durable_run_applies_defaults(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
client = _FakeClient()
|
|
monkeypatch.setattr(dispatch, "COMPLETION_WEBHOOK_URL", "https://app/webhooks/run-complete")
|
|
|
|
run = await dispatch.create_durable_run(
|
|
"thread-1",
|
|
"agent",
|
|
input={"messages": [{"role": "user", "content": "hi"}]},
|
|
source="test",
|
|
config={"configurable": {"thread_id": "thread-1"}, "metadata": {"kind": "test"}},
|
|
client=client,
|
|
)
|
|
|
|
assert run == {"run_id": "run-1"}
|
|
created = client.runs.created[0]
|
|
assert created["durability"] == "sync"
|
|
assert created["multitask_strategy"] == "interrupt"
|
|
assert created["if_not_exists"] == "create"
|
|
assert created["webhook"] == "https://app/webhooks/run-complete"
|
|
assert created["config"]["metadata"] == {"kind": "test"}
|
|
assert created["config"]["configurable"]["thread_id"] == "thread-1"
|
|
assert isinstance(created["config"]["configurable"]["prepare_run_id"], str)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_create_durable_run_no_webhook_when_none(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
client = _FakeClient()
|
|
monkeypatch.setattr(dispatch, "COMPLETION_WEBHOOK_URL", None)
|
|
|
|
await dispatch.create_durable_run(
|
|
"thread-1",
|
|
"agent",
|
|
input={"messages": []},
|
|
source="test",
|
|
client=client,
|
|
)
|
|
|
|
created = client.runs.created[0]
|
|
assert "webhook" not in created
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_dispatch_agent_run_preserves_multitask_strategy(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
client = _FakeClient()
|
|
monkeypatch.setattr(dispatch, "COMPLETION_WEBHOOK_URL", None)
|
|
|
|
await dispatch.dispatch_agent_run(
|
|
"thread-1",
|
|
"hi",
|
|
{"key": "val"},
|
|
source="test",
|
|
client=client,
|
|
multitask_strategy="reject",
|
|
)
|
|
|
|
created = client.runs.created[0]
|
|
assert created["multitask_strategy"] == "reject"
|