brain-of-reese/tests/e2e/test_document_viewer.py

"""Phase 26 E2E (Playwright): documents open in the almost-fullscreen
modal — not in a new page.

Story: ``.agents/user_stories/document-modal.md``
Run in isolation (DB must be up: ``podman compose up -d db``):

    uv run pytest tests/e2e/test_document_viewer.py -v --no-cov

Seeding reuses the real importer against ``tests/fixtures/docs/`` with the
deterministic mock embeddings (same harness as the phase-10 suite — only
the assertions changed: chips/row links now open the SAME-PAGE modal,
no ``expect_popup``).

Test → story mapping (Playwright Mapping Rule):
1. ``test_source_chip_opens_modal`` — chat chip → modal opens in-page
   (NO new tab, URL unchanged), title + ``.doc-md`` content + meta row.
2. ``test_sources_row_opens_modal`` — Sources path link → modal, yaml in
   ``<pre.doc-raw>``, mono font, URL unchanged.
3. ``test_modal_closes_on_button_escape_and_backdrop`` — close via
   ``#doc-modal-close``, via backdrop click, via ``Escape``.
4. ``test_modal_focus_and_a11y`` — ``role="dialog"`` + ``aria-modal``,
   focus inside the panel on open, close button has an ``aria-label``.
5. ``test_modal_xss_safe`` — hostile md document opened through the modal
   renders as escaped text; no dialog fires.
6. ``test_standalone_page_still_works`` — the dedicated ``/document.html``
   page keeps its phase-10 contract (title/content/badges, not-found,
   dark theme, no-CDN, a11y frame, the 72rem-container md column —
   phase 100: ≈1112px at the 1280px fixture viewport, the container's
   inner content).
7. ``test_modal_theme_and_no_cdn`` — dark page background, the panel on
   the Phase-08 surface colour, every asset same-origin or ``data:``.
"""
from __future__ import annotations

import asyncio
import re
from datetime import UTC, datetime
from pathlib import Path
from threading import Thread
from typing import Any

from playwright.sync_api import Page, expect
from sqlalchemy import text

from app.config import Settings
from app.db import SessionLocal
from app.models import Document
from app.rag.importer import ImportSummary, import_sources
from app.rag.llm import LLMClient
from e2e.auth_helpers import login

REPO = Path(__file__).resolve().parents[2]
FIXTURES = REPO / "tests" / "fixtures" / "docs"
QUESTION = "How is my Kubernetes cluster set up?"


async def _import_fixtures(mock_port: int) -> ImportSummary:
    kwargs: dict[str, Any] = {"_env_file": None, "llm_base_url": f"http://127.0.0.1:{mock_port}/v1"}
    settings = Settings(**kwargs)  # pyright: ignore[reportCallIssue]
    return await import_sources([FIXTURES], LLMClient(settings))


def _run_in_thread(coro: Any) -> Any:
    """Run a coroutine on a worker thread.

    Playwright's sync API keeps an asyncio loop running on the test thread,
    so ``asyncio.run`` cannot be called directly from a test body.
    """
    box: dict[str, Any] = {}

    def runner() -> None:
        try:
            box["value"] = asyncio.run(coro)
        except BaseException as e:  # noqa: BLE001 — re-raised on the test thread
            box["error"] = e

    t = Thread(target=runner)
    t.start()
    t.join()
    if "error" in box:
        raise box["error"]
    return box["value"]


def _reset_db(mock_port: int, seed: bool) -> ImportSummary | None:
    """Truncate the KB (and query log), then optionally re-import fixtures."""
    with SessionLocal() as db:
        db.execute(text("TRUNCATE chunks, documents, query_log"))
        db.commit()
    if not seed:
        return None
    return _run_in_thread(_import_fixtures(mock_port))


def _ask_for_chip(page: Page, app_url: str) -> Any:
    """Drive one chat turn and return the kubernetes.md source chip."""
    login(page, app_url, next="/")  # phase 79: chat is require_user-gated
    page.fill("#message-input", QUESTION)
    page.click("#send-btn")
    chip = page.locator(".msg.brain .source-chip", has_text="kubernetes.md")
    expect(chip).to_have_count(1, timeout=30_000)
    return chip


def _assert_closed(page: Page) -> None:
    """The modal is fully closed: the hidden attribute is back and the
    overlay is gone from view."""
    expect(page.locator("#doc-modal")).to_have_attribute("hidden", "")
    expect(page.locator(".doc-modal")).not_to_be_visible()


def _drill(page: Page, *names: str) -> None:
    """Phase 97: the catalog is the drill-down tree the agent's `ls`
    sees — click through the source/folder rows (exact name match,
    one per name) to the level that holds the asserted file. The drill
    is the only change from the flat-table era; the row itself is
    unchanged."""
    for name in names:
        page.click(f'#folders-tbody a.folder-link:text-is("{name}")')


# ---------------------------------------------------------------------------
# 1. Chat source chip → SAME-PAGE modal (no new tab)
# ---------------------------------------------------------------------------


def test_source_chip_opens_modal(
    page: Page, app_url: str, mock_llm: int, db_ready: None
) -> None:
    _reset_db(mock_llm, seed=True)
    page.set_default_timeout(30_000)
    chip = _ask_for_chip(page, app_url)
    # The encoded viewer URL stays as the no-JS / context-menu escape
    # hatch — but phase 26 removed target=_blank: the left click is
    # intercepted and opens the modal in place.
    expect(chip.first).to_have_attribute(
        "href", "/document.html?source=docs&path=homelab%2Fkubernetes.md&back=%2F"
    )
    expect(chip.first).not_to_have_attribute("target")

    before = len(page.context.pages)
    chip.first.click()
    # No new tab: the click must not have spawned a page.
    assert len(page.context.pages) == before, "clicking a chip must not open a new tab"

    # The almost-fullscreen modal becomes visible (hidden attribute gone).
    expect(page.locator("#doc-modal")).not_to_have_attribute("hidden")
    expect(page.locator(".doc-modal")).to_be_visible()
    # "Almost-fullscreen": the panel is min(1100px, 96vw) × 92vh, centered
    # (at a 1280px viewport the 1100px cap wins over 96vw = 1228.8px).
    box = page.locator("#doc-modal-panel").bounding_box()
    assert box is not None, "modal panel not rendered"
    expected_w = min(1100, 0.96 * 1280)
    expected_h = 0.92 * 800
    assert abs(box["width"] - expected_w) < 2, f"panel width {box['width']} (want ~{expected_w})"
    assert abs(box["height"] - expected_h) < 2, f"panel height {box['height']} (want ~{expected_h})"

    # Same content the /document.html page renders: title, markdown in
    # the centered .doc-md column (the modal's content target is
    # #doc-modal-content — the modal variant of the page's #doc-content).
    expect(page.locator("#doc-modal-title")).to_have_text("Kubernetes Homelab Cluster")
    expect(page.locator("#doc-modal-content .doc-md")).to_have_count(1)
    expect(page.locator("#doc-modal-content")).to_contain_text("Talos Linux on three nodes")
    # Meta row mirrors the viewer: source · format · mono path · indexed · chunks.
    expect(page.locator("#doc-modal-meta .doc-source-badge")).to_have_text("docs")
    expect(page.locator("#doc-modal-meta .format-badge")).to_have_text("md")
    expect(page.locator("#doc-modal-meta .doc-path")).to_have_text("homelab/kubernetes.md")
    expect(page.locator("#doc-modal-meta .doc-indexed")).to_contain_text("Indexed")
    assert re.fullmatch(
        r"\d+ chunks?", page.locator("#doc-modal-meta .doc-chunks").inner_text()
    )

    # Still the chat page: no navigation happened.
    assert page.url == app_url + "/", f"navigated away: {page.url}"


# ---------------------------------------------------------------------------
# 2. Sources table path link → same-page modal (yaml → raw pre)
# ---------------------------------------------------------------------------


def test_sources_row_opens_modal(
    page: Page, app_url: str, mock_llm: int, db_ready: None
) -> None:
    _reset_db(mock_llm, seed=True)
    login(page, app_url)  # phase 16: the Sources catalog is admin-only
    # Phase 97: the row lives at its folder level (docs → homelab →
    # container_gitlab) — the drill is the only change.
    _drill(page, "docs", "homelab", "container_gitlab")
    row = page.locator("#docs-tbody tr", has_text="gitlab-compose.yaml")
    expect(row).to_have_count(1)
    link = row.locator("td:nth-child(2) a.doc-link")
    expect(link).to_have_count(1)
    # Encoded URL kept as the escape hatch (slashes come out as %2F);
    # no target=_blank any more.
    expect(link).to_have_attribute(
        "href",
        "/document.html?source=docs&path=homelab%2Fcontainer_gitlab%2Fgitlab-compose.yaml",
    )
    expect(link).not_to_have_attribute("target")
    expect(link).to_have_attribute("title", "homelab/container_gitlab/gitlab-compose.yaml")

    before = len(page.context.pages)
    link.click()
    assert len(page.context.pages) == before, "clicking a row link must not open a new tab"

    expect(page.locator(".doc-modal")).to_be_visible()
    expect(page.locator("#doc-modal-title")).to_have_text("gitlab-compose")
    expect(page.locator("#doc-modal-meta .format-badge")).to_have_text("yaml")
    # Non-markdown formats render as escaped monospace text in a pre.
    pre = page.locator("#doc-modal-content pre.doc-raw")
    expect(pre).to_have_count(1)
    expect(pre).to_contain_text("gitlab/gitlab-ce:17.2.1-ce.0")
    font = pre.evaluate("el => getComputedStyle(el).fontFamily")
    assert "mono" in font

    # Still on the Sources page: no navigation happened.
    assert page.url == app_url + "/sources.html", f"navigated away: {page.url}"


# ---------------------------------------------------------------------------
# 3. Close on button, backdrop, and Escape
# ---------------------------------------------------------------------------


def test_modal_closes_on_button_escape_and_backdrop(
    page: Page, app_url: str, mock_llm: int, db_ready: None
) -> None:
    _reset_db(mock_llm, seed=True)
    page.set_default_timeout(30_000)
    chip = _ask_for_chip(page, app_url)

    def open_and_loaded() -> None:
        chip.first.click()
        expect(page.locator("#doc-modal-title")).to_have_text("Kubernetes Homelab Cluster")

    # 1) The close button.
    open_and_loaded()
    page.click("#doc-modal-close")
    _assert_closed(page)

    # 2) The backdrop — a point outside the centered 96vw × 92vh panel
    #    (panel starts at 4vh from the top / 2vw from the edge).
    open_and_loaded()
    page.locator("#doc-modal-backdrop").click(position={"x": 5, "y": 5})
    _assert_closed(page)

    # 3) Escape — the capture is document-level, so it works from any
    #    focus position inside (or outside) the panel.
    open_and_loaded()
    page.keyboard.press("Escape")
    _assert_closed(page)

    # After closing, the page behind is untouched: chat is still there.
    assert page.url == app_url + "/"
    expect(page.locator("#composer")).to_be_visible()


# ---------------------------------------------------------------------------
# 4. Focus management + dialog a11y frame
# ---------------------------------------------------------------------------


def test_modal_focus_and_a11y(
    page: Page, app_url: str, mock_llm: int, db_ready: None
) -> None:
    _reset_db(mock_llm, seed=True)
    page.set_default_timeout(30_000)
    chip = _ask_for_chip(page, app_url)

    chip.first.click()
    expect(page.locator("#doc-modal-title")).to_have_text("Kubernetes Homelab Cluster")

    # The panel is a proper modal dialog, labelled by its title.
    panel = page.locator("#doc-modal-panel")
    expect(panel).to_have_attribute("role", "dialog")
    expect(panel).to_have_attribute("aria-modal", "true")
    expect(panel).to_have_attribute("aria-labelledby", "doc-modal-title")

    # On open, focus moves into the dialog's content target.
    focus_id = page.evaluate("() => document.activeElement && document.activeElement.id")
    assert focus_id == "doc-modal-content", f"focus {focus_id!r} did not move into the modal"

    # The close control carries an accessible name (icon-only button).
    expect(page.locator("#doc-modal-close")).to_have_attribute("aria-label", "Close document")

    # The "Full page" escape hatch is rebuilt to the same encoded viewer
    # URL (no back param — the dedicated page's own default applies).
    expect(page.locator("#doc-modal-open")).to_be_visible()
    expect(page.locator("#doc-modal-open")).to_have_attribute(
        "href", "/document.html?source=docs&path=homelab%2Fkubernetes.md"
    )

    # Closing returns focus to the triggering control.
    page.keyboard.press("Escape")
    _assert_closed(page)
    focus_id = page.evaluate("() => document.activeElement && document.activeElement.className")
    assert "source-chip" in (focus_id or ""), f"focus {focus_id!r} did not return to the chip"


# ---------------------------------------------------------------------------
# 5. Modal rendering stays XSS-safe (hostile md, opened via the modal)
# ---------------------------------------------------------------------------


def test_modal_xss_safe(
    page: Page, app_url: str, mock_llm: int, db_ready: None
) -> None:
    _reset_db(mock_llm, seed=True)
    # A document whose content carries a hostile <script> line. The viewer
    # is database-only, so it can be seeded straight into the KB.
    with SessionLocal() as db:
        db.add(
            Document(
                source="docs",
                path="notes/xss-fixture.md",
                full_path="/tmp/xss-fixture.md",
                title="Xss Fixture",
                content="# Xss Fixture\n\n<script>alert(1)</script>\n\nXSS-FIXTURE-MARKER",
                content_hash="c" * 64,
                indexed_at=datetime.now(UTC),
            )
        )
        db.commit()

    dialogs: list[str] = []

    def _catch_dialog(d) -> None:  # a fired dialog == executed script
        dialogs.append(d.message)
        d.dismiss()

    page.on("dialog", _catch_dialog)

    # The Sources table lists every indexed document — the admin entry
    # point into the modal for a doc the chat never cited.
    login(page, app_url)
    # Phase 97: the seeded doc's row lives at the notes/ level — the
    # drill is the only change.
    _drill(page, "docs", "notes")
    row = page.locator("#docs-tbody tr", has_text="xss-fixture.md")
    expect(row).to_have_count(1)
    row.locator("td:nth-child(2) a.doc-link").click()

    expect(page.locator(".doc-modal")).to_be_visible()
    expect(page.locator("#doc-modal-title")).to_have_text("Xss Fixture")
    # The tag shows up as VISIBLE, ESCAPED text — rendered, never executed.
    expect(page.locator("#doc-modal-content")).to_contain_text("<script>alert(1)</script>")
    expect(page.locator("#doc-modal-content")).to_contain_text("XSS-FIXTURE-MARKER")
    assert page.locator("#doc-modal-content script").count() == 0, "hostile script became live HTML"
    assert dialogs == [], f"dialog fired — script executed: {dialogs}"


# ---------------------------------------------------------------------------
# 6. The dedicated /document.html page keeps its phase-10 contract
# ---------------------------------------------------------------------------


def test_standalone_page_still_works(
    page: Page, app_url: str, mock_llm: int, db_ready: None
) -> None:
    _reset_db(mock_llm, seed=True)
    # Phase 79: the viewer content is gated — the signed-in session sees
    # the phase-10 contract unchanged (the not-found cards below come
    # from the 404 / missing-params paths, not the auth gate).
    login(page, app_url, next="/")
    errors: list[str] = []
    page.on("pageerror", lambda e: errors.append(str(e)))

    # Direct link renders exactly as before (phase 10): title, meta row,
    # markdown in the centered column.
    page.goto(f"{app_url}/document.html?source=docs&path=homelab%2Fkubernetes.md")
    expect(page.locator("#doc-title")).to_have_text("Kubernetes Homelab Cluster")
    expect(page.locator("#doc-meta .doc-source-badge")).to_have_text("docs")
    expect(page.locator("#doc-meta .format-badge")).to_have_text("md")
    expect(page.locator("#doc-content .doc-md")).to_have_count(1)
    expect(page.locator("#doc-content")).to_contain_text("Talos Linux on three nodes")

    # Not-found state: an unknown pair AND missing params — no console
    # crash, the designed card with the Sources link.
    page.goto(f"{app_url}/document.html?source=docs&path=definitely/not/here.md")
    expect(page.locator("#doc-title")).to_have_text("Document not found")
    card = page.locator("#doc-not-found")
    expect(card).to_be_visible()
    expect(card).to_contain_text("Document not found")
    expect(card.locator("a.doc-open-sources")).to_have_attribute("href", "/sources.html")
    expect(page.locator("#doc-content")).to_be_empty()
    page.goto(f"{app_url}/document.html")
    expect(page.locator("#doc-not-found")).to_be_visible()

    # Dark theme + all assets local + a11y frame + capped md column.
    page.goto(f"{app_url}/document.html?source=docs&path=homelab%2Fkubernetes.md")
    expect(page.locator("#doc-content .doc-md")).not_to_be_empty()
    bg = page.evaluate("() => getComputedStyle(document.documentElement).backgroundColor")
    assert bg == "rgb(15, 10, 10)", "the dark-red rebrand canvas (#0f0a0a)"

    refs = page.evaluate(
        """() => [...document.querySelectorAll("script[src], link[href]")]
            .map((el) => el.src || el.href)"""
    )
    assert refs, "expected local asset references on /document.html"
    for ref in refs:
        assert ref.startswith(app_url) or ref.startswith("data:"), f"non-local: {ref}"

    expect(page.locator("header.doc-header")).to_have_count(1)
    expect(page.locator("main#main")).to_have_count(1)
    expect(page.locator("footer.app-footer")).to_have_count(1)
    expect(page.locator(".skip-link")).to_have_count(1)
    expect(page.locator(".doc-shell")).to_have_attribute("aria-live", "polite")
    assert page.evaluate("() => document.activeElement && document.activeElement.id") == "main"

    # Markdown column: the 72rem container's inner content (phase 100 —
    # the 46rem cap and its wide-desktop doubling are retired): at the
    # 1280px fixture viewport the container is 1152px border-box, so
    # .doc-md (width:100% inside it) measures 1152 − 2×1.25rem = 1112px.
    box = page.locator("#doc-content .doc-md").bounding_box()
    assert box is not None, "the standalone .doc-md column is not rendered"
    assert abs(box["width"] - 1112) <= 4, (
        f"the standalone .doc-md column is {box['width']:.0f}px, "
        f"want 1112px (the 72rem container's inner content) ±4px"
    )

    assert errors == [], f"console crashes: {errors}"


# ---------------------------------------------------------------------------
# 7. Modal theme + no CDN on the touched page
# ---------------------------------------------------------------------------


def test_modal_theme_and_no_cdn(
    page: Page, app_url: str, mock_llm: int, db_ready: None
) -> None:
    _reset_db(mock_llm, seed=True)
    page.set_default_timeout(30_000)
    chip = _ask_for_chip(page, app_url)
    chip.first.click()
    expect(page.locator("#doc-modal-title")).to_have_text("Kubernetes Homelab Cluster")
    expect(page.locator("#doc-modal-content .doc-md")).not_to_be_empty()

    # Dark theme (phase 08, dark-red rebrand 2026-08-28): the page
    # background is untouched, and the modal panel sits on the --surface
    # colour (#1a0f0f).
    bg = page.evaluate("() => getComputedStyle(document.documentElement).backgroundColor")
    assert bg == "rgb(15, 10, 10)"
    surface = page.evaluate(
        "() => getComputedStyle(document.querySelector('.doc-modal-panel')).backgroundColor"
    )
    assert surface == "rgb(26, 15, 15)", f"panel not on the --surface colour: {surface}"

    # No-CDN: every script/link reference on the chat page (the touched
    # page) is same-origin or a data: URI — the modal adds no assets.
    refs = page.evaluate(
        """() => [...document.querySelectorAll("script[src], link[href]")]
            .map((el) => el.src || el.href)"""
    )
    assert refs, "expected local asset references on the chat page"
    for ref in refs:
        assert ref.startswith(app_url) or ref.startswith("data:"), f"non-local: {ref}"