AI web starter: bands, review split pane, approve gate, server stub (checkpoint)

React + Vite + Tailwind starter with the no-AI shell, band legend, review
split pane with drafts and verify, and a server stub that refuses approval
while flagged fields are unverified. Band self-check and AI page check.
Both page checks share one Chromium via tests/conftest.py.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

tests/conftest.py

@@ -0,0 +1,12 @@
+"""Shared by both page checks: one headless Chromium for the whole run
+(Playwright's sync API allows only one instance per process)."""
+import pytest
+from playwright.sync_api import sync_playwright
+
+
+@pytest.fixture(scope="session")
+def browser():
+    with sync_playwright() as p:
+        b = p.chromium.launch()
+        yield b
+        b.close()

tests/page_check/conftest.py

@@ -11,7 +11,6 @@ import re
 from pathlib import Path
 
 import pytest
-from playwright.sync_api import sync_playwright
 
 ROOT = Path(__file__).resolve().parents[2]
 TEMPLATE = ROOT / "rpa-dashboard-no-ai" / "templates" / "dashboard.html"
@@ -44,14 +43,6 @@ def page_url(tmp_path_factory):
     return out.as_uri()
 
 
-@pytest.fixture(scope="session")
-def browser():
-    with sync_playwright() as p:
-        b = p.chromium.launch()
-        yield b
-        b.close()
-
-
 @pytest.fixture(params=list(MODES))
 def page(request, browser, page_url):
     width, height, dark = MODES[request.param]

tests/page_check_ai/conftest.py

@@ -0,0 +1,128 @@
+"""Seam 1 page check for the AI web dashboard (React + Vite), served by its server stub.
+
+Page under test: set PAGE_CHECK_AI_DIR to a generated dashboard folder (the one with
+package.json, index.html and server_stub.py). Without it, the AI web starter template
+is filled with TEST_FILL and built in a cache folder. Either way the folder is built
+with npm, and its server_stub.py runs in this process, so tests can set run and
+review state directly through the `stub` fixture.
+
+Contract envelopes go in through window.__pyMsg, as in the no-AI check. Each action
+the page POSTs to {API_BASE}/<slot> is recorded in window.__calls as [slot, ...args].
+Every page test runs in light, dark and narrow mode.
+"""
+import hashlib
+import importlib.util
+import json
+import os
+import re
+import shutil
+import subprocess
+import sys
+import tempfile
+import threading
+from pathlib import Path
+
+import pytest
+
+ROOT = Path(__file__).resolve().parents[2]
+TEMPLATE = ROOT / "rpa-dashboard-ai" / "templates" / "web"
+TEST_FILL = {
+    "APP_NAME": "Test Extractor",
+    "APP_SUBTITLE": "Page check",
+    "LOGO_SRC": "",
+    "API_BASE": "/api",
+    "STEPS_JSON": json.dumps(["Initializing", "Login", "Process items", "Completed"]),
+    "REPORT_COLUMNS_JSON": json.dumps([{"key": "item", "label": "Item"}, {"key": "status", "label": "Status"}]),
+}
+RECORD_ACTIONS = """
+window.__calls = [];
+const realFetch = window.fetch;
+window.fetch = (url, opts = {}) => {
+  const m = String(url).match(/\\/api\\/([a-z-]+)$/);
+  if (m && opts.method === 'POST') window.__calls.push([m[1].replace(/-/g, '_'), ...JSON.parse(opts.body || '[]')]);
+  return realFetch(url, opts);
+};
+"""
+MODES = {"light": (1280, 820, False), "dark": (1280, 820, True), "narrow": (800, 900, False)}
+SKIP_COPY = shutil.ignore_patterns("node_modules", "dist", "__pycache__")
+
+
+@pytest.fixture(scope="session")
+def site():
+    """The dashboard folder under test: server_stub.py, index.html and the sources."""
+    if os.environ.get("PAGE_CHECK_AI_DIR"):
+        return Path(os.environ["PAGE_CHECK_AI_DIR"]).resolve()
+    pkg = (TEMPLATE / "package.json").read_bytes() + (TEMPLATE / "package-lock.json").read_bytes()
+    out = Path(tempfile.gettempdir()) / f"rpa-dashboard-ai-web-{hashlib.sha1(pkg).hexdigest()[:10]}"
+    shutil.rmtree(out / "src", ignore_errors=True)  # node_modules is kept between runs
+    shutil.copytree(TEMPLATE, out, dirs_exist_ok=True, ignore=SKIP_COPY)
+    index = out / "index.html"
+    index.write_text(re.sub(r"\{\{(\w+)\}\}", lambda m: TEST_FILL[m[1]], index.read_text(encoding="utf-8")),
+                     encoding="utf-8")
+    return out
+
+
+@pytest.fixture(scope="session")
+def built(site):
+    npm = shutil.which("npm") or pytest.skip("npm not on PATH")
+    if not (site / "node_modules").exists():
+        subprocess.run([npm, "ci" if (site / "package-lock.json").exists() else "install"], cwd=site, check=True)
+    r = subprocess.run([npm, "run", "build"], cwd=site, capture_output=True, text=True)
+    assert r.returncode == 0, r.stdout + r.stderr
+    return site
+
+
+@pytest.fixture(scope="session")
+def stub_module(site):
+    sys.path.insert(0, str(site))  # the stub imports bands.py from its own folder
+    spec = importlib.util.spec_from_file_location("server_stub", site / "server_stub.py")
+    mod = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(mod)
+    return mod
+
+
+@pytest.fixture(scope="session")
+def server(stub_module):
+    srv = stub_module.make_server("127.0.0.1", 0)
+    threading.Thread(target=srv.serve_forever, daemon=True).start()
+    yield f"http://127.0.0.1:{srv.server_address[1]}"
+    srv.shutdown()
+
+
+@pytest.fixture
+def stub(stub_module, server):
+    """The running stub, reset to its sample data. Tests change stub.RUNS / stub.ROWS directly."""
+    stub_module.reset()
+    return stub_module
+
+
+@pytest.fixture(scope="session")
+def page_url(built, server):
+    return server + "/"
+
+
+@pytest.fixture(params=list(MODES))
+def page(request, browser, page_url, stub):
+    width, height, dark = MODES[request.param]
+    ctx = browser.new_context(viewport={"width": width, "height": height})
+    ctx.add_init_script(RECORD_ACTIONS)
+    pg = ctx.new_page()
+    pg.set_default_timeout(5000)
+    errors = []
+    pg.on("pageerror", lambda e: errors.append(e))
+    pg.goto(page_url)
+    assert not errors, f"page script errors: {errors}"
+    if dark:
+        push_to(pg, "apply_dark", {"on": True})
+    yield pg
+    ctx.close()
+
+
+def push_to(pg, event, data):
+    pg.evaluate("([event, data]) => window.__pyMsg(JSON.stringify({event, data}))", [event, data])
+
+
+@pytest.fixture
+def push(page):
+    """push(event, data): send one contract envelope to the page, as the bot would."""
+    return lambda event, data: push_to(page, event, data)

tests/page_check_ai/test_ai_review.py

@@ -0,0 +1,140 @@
+"""AI contract cases: confidence bands, review drafts, the approve gate and run progress.
+
+Run and review state is set on the server stub (the page's backend); what the page
+shows is asserted through the browser. See rpa-dashboard-ai/templates/contract.md.
+"""
+import json
+import re
+import urllib.error
+import urllib.request
+
+from playwright.sync_api import expect
+
+# (field, value, word scores, mandatory) -> the band each one must land in
+FIELDS = [
+    ("Invoice number", "INV-2207", [1.0], True),            # green
+    ("Vendor", "Northwind Traders", [0.99, 0.97], True),    # green
+    ("Invoice date", "2026-10-02", [0.93], True),           # amber
+    ("Total", "1,284.50", [0.98, 0.71], True),              # red: worst word wins
+    ("Due date", "", [1.0], True),                           # blank mandatory
+    ("PO number", "PO-118", [], False),                      # unscored
+]
+EXPECTED = {"green": ["Invoice number", "Vendor"], "amber": ["Invoice date"], "red": ["Total"],
+            "blank": ["Due date"], "unscored": ["PO number"]}
+FLAGGED = 4  # everything but green
+
+
+def api(server, method, path, body=None):
+    req = urllib.request.Request(server + "/api" + path, method=method,
+                                 data=None if body is None else json.dumps(body).encode(),
+                                 headers={"Content-Type": "application/json"})
+    try:
+        with urllib.request.urlopen(req) as r:
+            return r.status, json.loads(r.read())
+    except urllib.error.HTTPError as e:
+        return e.code, json.loads(e.read())
+
+
+def test_server_refuses_approval_while_flagged_fields_are_unverified(stub, server):
+    """The gate lives on the server: no request from any page can skip it."""
+    stub.put_run("job-gate", "gate.pdf", FIELDS)
+    status, body = api(server, "POST", "/runs/job-gate/approve")
+    assert status == 409 and str(FLAGGED) in body["detail"]
+
+    _, rows = api(server, "GET", "/runs/job-gate/review")
+    first_flagged = next(r for r in rows["rows"] if r["band"] != "green")
+    api(server, "PATCH", f"/review/{first_flagged['row_id']}", {"verified": True})
+    status, body = api(server, "POST", "/runs/job-gate/approve")
+    assert status == 409 and str(FLAGGED - 1) in body["detail"]
+
+    api(server, "POST", "/runs/job-gate/verify-remaining")
+    status, _ = api(server, "POST", "/runs/job-gate/approve")
+    assert status == 200
+    assert api(server, "GET", "/runs/job-gate")[1]["approved"] is True
+
+
+def open_review(page, job_id):
+    page.get_by_role("navigation").get_by_role("button", name="Review", exact=True).click()
+    page.get_by_label("Document", exact=True).select_option(job_id)
+
+
+def fields_list(page):
+    return page.get_by_role("list", name="Extracted fields").get_by_role("listitem")
+
+
+LEGEND = {"green": "Clean", "amber": "Check", "red": "Review", "blank": "Missing", "unscored": "Unscored"}
+
+
+def test_band_counts_and_legend_match(page, stub):
+    stub.put_run("job-t", "bands.pdf", FIELDS)
+    open_review(page, "job-t")
+    legend = page.get_by_role("list", name="Confidence bands").get_by_role("listitem")
+    expect(legend).to_have_count(len(LEGEND))
+    for i, (band, word) in enumerate(LEGEND.items()):
+        expect(legend.nth(i)).to_have_text(re.compile(rf"^\s*{word}\b.*· {len(EXPECTED[band])}\s*$"))
+    expect(page.get_by_text(re.compile("print clarity, not correctness", re.I))).to_be_visible()
+
+
+def test_band_filters_show_the_right_rows(page, stub):
+    stub.put_run("job-t", "bands.pdf", FIELDS)
+    open_review(page, "job-t")
+    expect(fields_list(page)).to_have_count(len(FIELDS))
+    filters = page.get_by_role("group", name="Filter by band")
+    for name, band in [("Red", "red"), ("Amber", "amber"), ("Missing", "blank"), ("Unscored", "unscored")]:
+        filters.get_by_role("button", name=name, exact=True).click()
+        expect(fields_list(page)).to_have_count(len(EXPECTED[band]))
+        for field in EXPECTED[band]:
+            expect(page.get_by_role("textbox", name=field, exact=True)).to_be_visible()
+    filters.get_by_role("button", name="All", exact=True).click()
+    expect(fields_list(page)).to_have_count(len(FIELDS))
+
+
+def row(stub, job_id, field):
+    return next(r for r in stub.ROWS[job_id] if r["field"] == field)
+
+
+def test_draft_edit_is_not_saved_until_save(page, stub):
+    stub.put_run("job-t", "bands.pdf", FIELDS)
+    open_review(page, "job-t")
+    box = page.get_by_role("textbox", name="Vendor", exact=True)
+    box.fill("Northwind Traders Ltd")
+    expect(page.get_by_text("1 unsaved change", exact=True)).to_be_visible()
+    assert row(stub, "job-t", "Vendor")["corrected_value"] is None
+
+    asked = []
+    page.once("dialog", lambda d: (asked.append(d.message), d.dismiss()))
+    page.get_by_role("navigation").get_by_role("button", name="Report", exact=True).click()
+    expect(box).to_have_value("Northwind Traders Ltd")  # leaving was refused, the draft is still there
+    assert asked and "unsaved" in asked[0].lower()
+
+    page.get_by_role("button", name="Save", exact=True).click()
+    expect(page.get_by_text("1 unsaved change", exact=True)).to_be_hidden()
+    saved = row(stub, "job-t", "Vendor")
+    assert saved["corrected_value"] == "Northwind Traders Ltd" and saved["verified"] is True
+
+
+def test_approve_stays_blocked_while_rows_are_unverified(page, stub):
+    stub.put_run("job-t", "bands.pdf", FIELDS)
+    open_review(page, "job-t")
+    page.get_by_role("button", name="Verify Total", exact=True).click()
+    expect(page.get_by_role("button", name="Verify Total", exact=True)).to_have_attribute("aria-pressed", "true")
+    page.get_by_role("button", name="Approve", exact=True).click()
+    expect(page.get_by_role("alert")).to_contain_text(f"{FLAGGED - 1} flagged")
+    assert stub.RUNS["job-t"]["approved"] is False
+
+    page.get_by_role("button", name="Verify remaining", exact=True).click()
+    page.get_by_role("button", name="Approve", exact=True).click()
+    expect(page.get_by_text("✓ Approved", exact=True)).to_be_visible()
+    expect(page.get_by_role("alert")).to_be_hidden()
+    assert stub.RUNS["job-t"]["approved"] is True
+
+
+def test_page_x_of_y_updates_while_running(page, stub):
+    stub.put_run("job-busy", "busy.pdf", FIELDS, status="running", pages_done=1, pages_total=4)
+    open_review(page, "job-busy")
+    expect(page.get_by_text("page 1 of 4", exact=True)).to_be_visible()
+    stub.RUNS["job-busy"]["pages_done"] = 3
+    expect(page.get_by_text("page 3 of 4", exact=True)).to_be_visible()
+    stub.RUNS["job-busy"].update(status="done", pages_done=4)
+    expect(fields_list(page)).to_have_count(len(FIELDS))
+    expect(page.get_by_text(re.compile(r"^page \d+ of \d+$"))).to_be_hidden()

tests/page_check_ai/test_ai_shared.py

@@ -0,0 +1,19 @@
+"""Everything from the no-AI page: the no-AI contract cases, run unchanged against the AI page.
+
+They use this folder's `page` and `push` fixtures, so they check the React page.
+"""
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "page_check"))
+
+from test_contract import (  # noqa: E402,F401
+    test_dark_toggle_flips_theme,
+    test_donut_and_legend_match_batch_states,
+    test_kpi_counts_match_batch_states,
+    test_log_lines_show_their_type,
+    test_no_bot_page_runs_on_sample_data,
+    test_plain_browser_first_open_shows_sample_data,
+    test_report_search_filters_rows_and_shows_bucket_pill,
+    test_step_list_follows_step_label,
+)

tests/test_bands.py

@@ -0,0 +1,41 @@
+"""Confidence bands: thresholds, the worst-word rule and the blank-mandatory flag (spec: Banding)."""
+import importlib.util
+from pathlib import Path
+
+BANDS = Path(__file__).resolve().parents[1] / "rpa-dashboard-ai" / "templates" / "web" / "bands.py"
+spec = importlib.util.spec_from_file_location("bands", BANDS)
+bands = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(bands)
+
+
+def test_thresholds():
+    assert bands.band_of(1.0) == "green"
+    assert bands.band_of(0.95) == "green"
+    assert bands.band_of(0.9499) == "amber"
+    assert bands.band_of(0.90) == "amber"
+    assert bands.band_of(0.8999) == "red"
+    assert bands.band_of(0.0) == "red"
+
+
+def test_field_takes_its_worst_word():
+    assert bands.field_band([0.99, 0.97, 0.98], "ACME Office Supply") == "green"
+    assert bands.field_band([0.99, 0.93, 0.98], "ACME Office Supply") == "amber"
+    assert bands.field_band([0.99, 0.97, 0.62], "ACME Office Supply") == "red"
+
+
+def test_blank_mandatory_field_is_always_flagged():
+    assert bands.field_band([1.0], "", mandatory=True) == "blank"
+    assert bands.field_band([], "   ", mandatory=True) == "blank"
+    assert bands.field_band(None, None, mandatory=True) == "blank"
+    assert bands.needs_review("blank")
+    # An optional blank is graded like any other field.
+    assert bands.field_band([1.0], "", mandatory=False) == "green"
+
+
+def test_no_scores_means_unscored():
+    assert bands.field_band([], "INV-1001") == "unscored"
+
+
+def test_only_green_skips_review():
+    assert not bands.needs_review("green")
+    assert all(bands.needs_review(b) for b in ["amber", "red", "blank", "unscored"])