mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 12:43:16 +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.
83 lines
3.1 KiB
Python
83 lines
3.1 KiB
Python
"""Shared environment + constants for the full-flow E2E.
|
|
|
|
Imported FIRST by both the agent graph entrypoint and the HTTP harness, before
|
|
any ``agent.*`` module — several webapp/auth/slack constants are read into module
|
|
globals at import time, so the env must be set beforehand.
|
|
|
|
Everything here only configures *boundaries* (which sandbox, which fake API
|
|
URLs, where git writes its global config). The agent code itself is unchanged.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
from pathlib import Path
|
|
|
|
REPO_ROOT = Path(__file__).resolve().parents[2]
|
|
TMP = Path(os.environ.setdefault("E2E_TMP", str(Path(__file__).parent / ".e2e-tmp")))
|
|
|
|
# Demo repo the fake GitHub serves and the agent operates on.
|
|
OWNER = "fakeorg"
|
|
REPO = "demo"
|
|
BASE_BRANCH = "main"
|
|
FEATURE_BRANCH = "add-greet"
|
|
PR_TITLE = "Add greet() helper"
|
|
FEATURE_FILE = "greet.py"
|
|
|
|
# Fixed Slack identifiers so the mock UI and assertions are deterministic.
|
|
BOT_USER_ID = "U0BOT"
|
|
BOT_USERNAME = "open-swe"
|
|
DEMO_CHANNEL = "C_DEMO"
|
|
HUMAN_USER = "U_HUMAN"
|
|
|
|
PORT = os.environ.setdefault("E2E_PORT", "2024")
|
|
BASE_URL = os.environ.setdefault("E2E_BASE", f"http://127.0.0.1:{PORT}")
|
|
|
|
_GH_DIR = TMP / "github"
|
|
_WORK_DIR = TMP / "work"
|
|
BARE_REMOTE = _GH_DIR / f"{OWNER}__{REPO}.git"
|
|
|
|
_DEFAULTS = {
|
|
# Sandbox: real local provider, rooted in a throwaway temp dir.
|
|
"SANDBOX_TYPE": "local",
|
|
"LOCAL_SANDBOX_ROOT_DIR": str(_WORK_DIR),
|
|
# Keep git's --global writes (bot identity) out of the user's ~/.gitconfig.
|
|
"GIT_CONFIG_GLOBAL": str(TMP / "gitconfig-global"),
|
|
"GIT_CONFIG_SYSTEM": "/dev/null",
|
|
# Path the scripted agent clones from (a local bare repo = "fake GitHub").
|
|
"E2E_REMOTE": str(BARE_REMOTE),
|
|
# Webhook signing + bot identity.
|
|
"GITHUB_WEBHOOK_SECRET": "test-github-secret",
|
|
"SLACK_SIGNING_SECRET": "test-slack-secret",
|
|
"SLACK_BOT_TOKEN": "xoxb-test-token",
|
|
"SLACK_BOT_USER_ID": BOT_USER_ID,
|
|
"SLACK_BOT_USERNAME": BOT_USERNAME,
|
|
# Slack runs resolve the repo from this when the channel/thread carry none.
|
|
"DEFAULT_REPO_OWNER": OWNER,
|
|
"DEFAULT_REPO_NAME": REPO,
|
|
# Bot-token-only mode: lets Slack runs proceed without a per-user OAuth token.
|
|
"LANGSMITH_API_KEY_PROD": "test-bot-mode",
|
|
# SDK client target (same dev server).
|
|
"LANGGRAPH_URL": BASE_URL,
|
|
# Dashboard: the "Open in Web" link target + session-cookie signing. Use
|
|
# 127.0.0.1 (not localhost) so the local-dev LLM-key check stays skipped.
|
|
"DASHBOARD_BASE_URL": BASE_URL,
|
|
"DASHBOARD_API_BASE_URL": BASE_URL,
|
|
"DASHBOARD_ALLOWED_ORIGINS": BASE_URL,
|
|
"DASHBOARD_JWT_SECRET": "test-dashboard-jwt-secret",
|
|
}
|
|
|
|
# The Slack run's triggering user (fake users.info returns this email) — the
|
|
# thread owner. A session with this email may continue the thread on the web.
|
|
SAME_USER = {"login": "dev-user", "email": "dev@example.com"}
|
|
# Any other logged-in user: can view the thread read-only, cannot post.
|
|
OTHER_USER = {"login": "someone-else", "email": "someone@example.com"}
|
|
|
|
for _k, _v in _DEFAULTS.items():
|
|
os.environ.setdefault(_k, _v)
|
|
|
|
for _d in (TMP, _GH_DIR, _WORK_DIR):
|
|
_d.mkdir(parents=True, exist_ok=True)
|
|
|
|
FAKE_GITHUB_API = f"{BASE_URL}/fake-gh"
|
|
FAKE_SLACK_API = f"{BASE_URL}/fake-slack"
|