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

"""Phase 10 E2E (Playwright): the clickable document viewer.

Story: ``.agent/user_stories/document-viewer.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 pattern as the earlier story suites).

Test → story mapping (Playwright Mapping Rule):
1. ``test_source_chip_opens_document``       — chip → NEW TAB → viewer with
   title + known content string + format badge.
2. ``test_sources_row_links_to_viewer``      — Sources path link (yaml
   fixture) → viewer with raw content in a ``pre``.
3. ``test_markdown_renders_and_stays_xss_safe`` — md fixture containing
   ``<script>alert(1)</script>`` renders as visible escaped text (no
   execution).
4. ``test_missing_doc_shows_not_found``      — unknown doc → not-found
   state + Sources link; no console crash.
5. ``test_viewer_theme_and_no_cdn``          — dark theme + every
   ``script[src]`` / ``link[href]`` local or ``data:`` + a11y frame.
"""
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

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))


# ---------------------------------------------------------------------------
# 1. Chat source chip → new tab → full document
# ---------------------------------------------------------------------------


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

    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)
    # New-tab contract: same-origin viewer URL, all query values encoded
    # (the path's slashes come out as %2F — exactly why encoding matters),
    # plus back=/ (phase 13) so the viewer's back button returns to chat.
    expect(chip.first).to_have_attribute(
        "href", "/document.html?source=docs&path=homelab%2Fkubernetes.md&back=%2F"
    )
    expect(chip.first).to_have_attribute("target", "_blank")
    expect(chip.first).to_have_attribute("rel", "noopener")

    with page.expect_popup() as popup_info:
        chip.first.click()
    viewer = popup_info.value
    expect(viewer).to_have_url(
        re.compile(
            re.escape(
                f"{app_url}/document.html?source=docs&path=homelab%2Fkubernetes.md&back=%2F"
            )
        )
    )
    expect(viewer.locator("#doc-title")).to_have_text("Kubernetes Homelab Cluster")
    # Meta row: source badge · format badge · mono path · indexed · chunks.
    expect(viewer.locator("#doc-meta .doc-source-badge")).to_have_text("docs")
    expect(viewer.locator("#doc-meta .format-badge")).to_have_text("md")
    expect(viewer.locator("#doc-meta .doc-path")).to_have_text("homelab/kubernetes.md")
    expect(viewer.locator("#doc-meta .doc-indexed")).to_contain_text("Indexed")
    assert re.fullmatch(r"\d+ chunks?", viewer.locator("#doc-meta .doc-chunks").inner_text())
    # Full document, rendered markdown in the centered column (not a pre).
    expect(viewer.locator("#doc-content .doc-md")).to_have_count(1)
    expect(viewer.locator("#doc-content")).to_contain_text("Talos Linux on three nodes")


# ---------------------------------------------------------------------------
# 2. Sources table path link → viewer (yaml → raw pre)
# ---------------------------------------------------------------------------


def test_sources_row_links_to_viewer(
    page: Page, app_url: str, mock_llm: int, db_ready: None
) -> None:
    _reset_db(mock_llm, seed=True)
    page.goto(f"{app_url}/sources.html")

    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: the slashes in the path value come out as %2F.
    expect(link).to_have_attribute(
        "href",
        "/document.html?source=docs&path=homelab%2Fcontainer_gitlab%2Fgitlab-compose.yaml",
    )
    expect(link).to_have_attribute("target", "_blank")
    expect(link).to_have_attribute("rel", "noopener")
    expect(link).to_have_attribute("title", "homelab/container_gitlab/gitlab-compose.yaml")

    with page.expect_popup() as popup_info:
        link.click()
    viewer = popup_info.value
    expect(viewer.locator("#doc-title")).to_have_text("gitlab-compose")
    expect(viewer.locator("#doc-meta .format-badge")).to_have_text("yaml")
    # Non-markdown formats render as escaped monospace text in a pre.
    pre = viewer.locator("#doc-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


# ---------------------------------------------------------------------------
# 3. Markdown renders through the shared renderer and stays XSS-safe
# ---------------------------------------------------------------------------


def test_markdown_renders_and_stays_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)
    page.goto(f"{app_url}/document.html?source=docs&path=notes%2Fxss-fixture.md")

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


# ---------------------------------------------------------------------------
# 4. Missing document → designed not-found state, no console crash
# ---------------------------------------------------------------------------


def test_missing_doc_shows_not_found(
    page: Page, app_url: str, mock_llm: int, db_ready: None
) -> None:
    _reset_db(mock_llm, seed=True)
    errors: list[str] = []
    page.on("pageerror", lambda e: errors.append(str(e)))

    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()

    # Missing params → the same designed state (no fetch, no crash).
    page.goto(f"{app_url}/document.html")
    expect(page.locator("#doc-not-found")).to_be_visible()

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


# ---------------------------------------------------------------------------
# 5. Dark theme + all assets local + a11y frame
# ---------------------------------------------------------------------------


def test_viewer_theme_and_no_cdn(page: Page, app_url: str, mock_llm: int, db_ready: None) -> None:
    _reset_db(mock_llm, seed=True)
    page.goto(f"{app_url}/document.html?source=docs&path=homelab%2Fkubernetes.md")
    expect(page.locator("#doc-content .doc-md")).not_to_be_empty()

    # Dark theme inherited from phase 08 (same sampling as that story).
    bg = page.evaluate("() => getComputedStyle(document.documentElement).backgroundColor")
    assert bg == "rgb(10, 14, 23)"

    # No-CDN: every script/link reference is same-origin or a data: URI.
    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}"

    # A11y frame: landmarks, skip link, aria-live around the load→content
    # swap, and focus moved to main on load.
    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 centered and capped at 46rem (736px at 16px root).
    box = page.locator("#doc-content .doc-md").bounding_box()
    assert box is not None and box["width"] <= 736 + 1