mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-10-01 06:13:15 +00:00
a8c7af4192
* test(open-swe): add Playwright E2E for the Slack → PR → web handoff Local, secrets-free end-to-end suite that drives the full happy path through mock Slack/GitHub control panels and the real dashboard UI. Only the LLM and external SaaS HTTP boundaries (GitHub/Slack APIs, OAuth token mint) are faked — the real process_slack_mention, get_agent, deepagents loop, tools, middleware, and dashboard authorization all run under `langgraph dev` with a scripted fake chat model and a local temp-dir sandbox. - full_flow: a Slack mention runs the agent, which implements a change in the sandbox, opens a PR against a fake GitHub remote, and replies with the PR link in the same thread. - dashboard: clicking the bot's real "Open in Web" link loads the built ui/ app (served same-origin); the thread owner can continue the conversation, while a different user sees the same thread read-only (no composer). Wired into Agent CI as a `Playwright E2E` job that runs on pull requests. * fix(open-swe): serve E2E UI assets via explicit route; pin Playwright The dashboard E2E served the built ui/ SPA's /assets via app.mount(StaticFiles), but LangGraph's custom-app loader serves APIRoutes and drops sub-app Mounts, so /assets 404'd under `langgraph dev` in CI — the React app never booted and the composer/transcript never rendered. Serve assets via an explicit route instead. Also pin @playwright/test to the latest (1.61.0) for reproducible runs, and make the owner composer assertion tolerant of either hydration state. * test(open-swe): record Playwright trace + video on every E2E run Capture a replayable trace (DOM snapshots, network, console, source) and a screen recording for every test, not just retries, plus a screenshot on failure. The CI job already uploads playwright-report/ and test-results/, so each run now has a downloadable replay; documented how to open it.
72 lines
2.7 KiB
Python
72 lines
2.7 KiB
Python
"""Boundary monkeypatches: fake the LLM and the external SaaS endpoints.
|
|
|
|
Everything patched here is an *external boundary*, not agent logic:
|
|
- the LLM (model factory) -> scripted fake
|
|
- GitHub App token mint + GitHub REST base URL -> dummy token + fake GitHub
|
|
- Slack API base URL -> fake Slack
|
|
- the api.github.com/user identity lookup -> offline (falls back to config)
|
|
|
|
Applied at import of both the graph entrypoint and the HTTP harness (same dev
|
|
process), so it runs before the first run regardless of import order. Idempotent.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import e2e_env # noqa: F401 (sets env before any agent import)
|
|
|
|
_applied = False
|
|
|
|
|
|
def apply() -> None:
|
|
global _applied
|
|
if _applied:
|
|
return
|
|
|
|
import importlib
|
|
|
|
from agent import server
|
|
from agent.utils import auth, authorship
|
|
from agent.utils import slack as slack_utils
|
|
|
|
# NB: ``from agent.tools import open_pull_request`` returns the re-exported
|
|
# *function* (the tools package __init__ shadows the submodule), so patch the
|
|
# actual module object by name instead.
|
|
opr = importlib.import_module("agent.tools.open_pull_request")
|
|
|
|
from e2e_env import FAKE_GITHUB_API, FAKE_SLACK_API
|
|
from fake_llm import FakeScriptedChatModel, build_script
|
|
|
|
def _fake_make_model(model_id: str, **kwargs: object): # noqa: ARG001
|
|
return FakeScriptedChatModel(script=build_script())
|
|
|
|
server.make_model = _fake_make_model
|
|
|
|
async def _dummy_install_token_with_expiry() -> tuple[str, str | None]:
|
|
return "dummy-installation-token", None
|
|
|
|
async def _dummy_install_token() -> str:
|
|
return "dummy-installation-token"
|
|
|
|
auth.get_github_app_installation_token_with_expiry = _dummy_install_token_with_expiry
|
|
opr.get_github_app_installation_token = _dummy_install_token
|
|
|
|
# Point the real PR/Slack code at the in-process fakes.
|
|
opr.GITHUB_API = FAKE_GITHUB_API
|
|
slack_utils.SLACK_API_BASE_URL = FAKE_SLACK_API
|
|
|
|
# Keep the triggering-user identity lookup offline; the real fallback to
|
|
# config-derived identity (Slack name/email) still runs.
|
|
authorship._identity_from_github_token = lambda _token: None # noqa: SLF001
|
|
|
|
# OAuth-token store is an external credential boundary. Stub it so a web
|
|
# follow-up (dashboard run.start) and PR-as-user resolution have a token;
|
|
# the real ownership/authorization checks still run.
|
|
from agent.dashboard import profiles, thread_api
|
|
|
|
async def _dummy_user_token(login: str, **_kwargs: object) -> str: # noqa: ARG001
|
|
return "dummy-user-oauth-token"
|
|
|
|
profiles.get_valid_access_token = _dummy_user_token
|
|
thread_api.get_valid_access_token = _dummy_user_token
|
|
|
|
_applied = True
|