Files
automaton/tests/test_dashboard_ui.py
T
Lap Tran bc7daf8590 Restore archived tasks, fix dashboard scroll-reset, bind ornith, add Playwright smoke test
- **Restore 82 completed tasks** from tasks/complete/ back to tasks/ top
  level (all <7 days old per the cleanup policy; premature bulk archive
  was fixed).
- **Dashboard: fix scroll-reset on auto-refresh** — renderBoard rebuilds
  the board via innerHTML every 2s, destroying each column-body's
  scrollTop. Now snapshots column-body scrollTop + board.scrollLeft +
  view.scrollTop before rebuild and restores after (matched by
  PHASE_GROUPS index).
- **Dashboard UI additions** (pre-existing unstaged work): approval
  section cards, transition buttons, inline artifact editor (textarea for
  writing missing SPEC/VERDICT/etc from the detail modal).
- **Bind ornith as Implement model** — config.md: Model explicit to
  omlx/Ornith-1.0-35B-4bit-mlx, context window 32768. Interactive
  autopilot already used ornith via opencode default; now explicit.
- **Fix cleanup stub** — automaton-cleanup.sh had a stale --project arg
  pointing at a pytest temp dir (test isolation leak). Rewired to point
  at ~/.automaton.
- **Fix plist-isolation test** — test asserted host plist doesn't exist,
  but a real install creates it. Now snapshots mtime before run, asserts
  unchanged after (only a write during the test counts as bleed).
- **New Playwright smoke test** (tests/test_dashboard_ui.py) — 2 tests:
  board renders tasks, column scroll survives auto-refresh tick.
  Verified the test fails without the scroll fix (scrollTop resets to 0).
  Skipped via importorskip when playwright is absent (main CI stays
  green).
- **Clarify SI loop scope in README** — new-project onboarding section
  documents the framework-scoped self-improvement loop and options
  (leave/pause/create project loop).
- **CHANGELOG** documents all changes including the known model-divergence
  gap (mde tasks marked complete but per-role model binding was never
  implemented).
2026-06-26 10:05:18 -04:00

115 lines
4.4 KiB
Python

"""Playwright browser smoke test for the dashboard UI.
Verifies the dashboard boots, renders tasks, and preserves column scroll
position across auto-refresh (the fix for the scroll-reset bug). Skipped
when playwright/chromium is not installed so the main suite stays green
in CI environments without a browser.
Run standalone:
python3 -m pytest tests/test_dashboard_ui.py -v
"""
from __future__ import annotations
import socket
import threading
import time
from http.server import HTTPServer
from pathlib import Path
import pytest
from automaton.dashboard.ui.app import DashboardHandler, DashboardApp
playwright = pytest.importorskip("playwright")
from playwright.sync_api import sync_playwright # noqa: E402
def _free_port() -> int:
s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
s.bind(("127.0.0.1", 0))
port = s.getsockname()[1]
s.close()
return port
def _make_done_tasks(project_root: Path, count: int) -> None:
tasks = project_root / ".automaton" / "tasks"
tasks.mkdir(parents=True, exist_ok=True)
for i in range(count):
d = tasks / f"done-task-{i:02d}"
d.mkdir(exist_ok=True)
(d / "SPEC.md").write_text(f"# Done task {i}\n" + ("line. " * 40) + "\n")
(d / ".state").write_text("complete\n")
@pytest.fixture
def dashboard_server(tmp_path: Path):
_make_done_tasks(tmp_path, 40)
app = DashboardApp(start_path=tmp_path)
assert app.initialize(), "dashboard failed to init"
port = _free_port()
DashboardHandler.config = app.config
DashboardHandler.project_root = app.project_root
DashboardHandler.scope = app.scope
server = HTTPServer(("127.0.0.1", port), DashboardHandler)
thread = threading.Thread(target=server.serve_forever, daemon=True)
thread.start()
base_url = f"http://127.0.0.1:{port}"
try:
yield base_url
finally:
server.shutdown()
server.server_close()
thread.join(timeout=5)
def _wait_for(predicate, timeout=10.0, interval=0.2):
deadline = time.time() + timeout
while time.time() < deadline:
if predicate():
return True
time.sleep(interval)
return False
class TestDashboardUI:
def test_board_renders_done_tasks(self, dashboard_server):
with sync_playwright() as p:
browser = p.chromium.launch()
page = browser.new_page()
page.goto(dashboard_server)
# Footer refresh counter increments once auto-refresh fires.
assert _wait_for(lambda: page.text_content("#refresh-count") not in (None, "0", ""))
# The Done (resolution) group contains our tasks.
cards = page.locator(".task-card")
assert _wait_for(lambda: cards.count() >= 40, timeout=15)
assert page.text_content("#done-tasks") == "40"
browser.close()
def test_refresh_preserves_column_scroll(self, dashboard_server):
"""The scroll-reset bug: re-render snapped a column's scrollTop to 0,
so users couldn't scroll the Done group down to review older tasks.
Verify the column-body scrollTop survives an auto-refresh tick."""
with sync_playwright() as p:
browser = p.chromium.launch()
# Wide viewport so columns fit and the Done column-body overflows
# vertically (rather than the board squeezing them horizontally).
page = browser.new_page(viewport={"width": 1400, "height": 500})
page.goto(dashboard_server)
assert _wait_for(lambda: page.locator(".task-card").count() >= 40, timeout=15)
# The Done (resolution) group is the last column.
bodies = page.locator(".column-body")
n = bodies.count()
done_body = bodies.nth(n - 1)
assert done_body.evaluate("el => el.scrollHeight > el.clientHeight")
# Scroll the column-body well past the top.
target = 400
done_body.evaluate("(el, y) => { el.scrollTop = y; }", target)
assert done_body.evaluate("el => el.scrollTop") == target
# Wait for an auto-refresh re-render (default interval 2s).
before = int(page.text_content("#refresh-count") or "0")
assert _wait_for(lambda: int(page.text_content("#refresh-count") or "0") > before, timeout=10)
# Scroll must survive the re-render (the bug fix).
assert done_body.evaluate("el => el.scrollTop") == target
browser.close()