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

"""Phase 02 E2E (Playwright): the Sources page reflects the imported KB.

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

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

Seeding runs the real import function in-process against
``tests/fixtures/docs/`` with the deterministic mock embeddings — it is a
fixture, not the subject of the tests.

Phase 16 adaptation: the Sources catalog is admin-only — every test
performs the real form login (``e2e.auth_helpers.login``) first.
"""
from __future__ import annotations

import asyncio
from pathlib import Path
from threading import Thread
from typing import Any

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

from app.config import Settings
from app.db import SessionLocal
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"

EXPECTED_ROWS = (
    "homelab/kubernetes.md",
    "homelab/backups.md",
    "deployments/new-service.md",
    "homelab/container_gitlab/gitlab.md",
    "homelab/container_gitlab/gitlab-compose.yaml",
    "homelab/networking/static-dns.json",
    "homelab/scripts/uptime_probe.py",
    "homelab/ssh/ssh_aliases.txt",
    "homelab/tables.md",  # phase 44: the markdown-tables fixture
    # phase 47 (A9 revised 2026-08-27): quadlet family + jinja fixtures
    "homelab/quadlet/compose.container",
    "homelab/quadlet/lan.network",
    "homelab/quadlet/cache.volume",
    "homelab/templates/deploy.j2",
)


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 test_sources_page_lists_indexed_docs(
    page: Page, app_url: str, mock_llm: int, db_ready: None
) -> None:
    summary = _reset_db(mock_llm, seed=True)
    # Thirteen A9-format files are imported (phase 44 added
    # homelab/tables.md, phase 47 added the quadlet + j2 fixtures);
    # .hidden/junk.md is out of scope (A9 revised — hidden path components
    # are never walked).
    assert summary is not None and summary.added == 13
    assert summary.formats == {
        "md": 5, "yaml": 1, "json": 1, "py": 1, "txt": 1,
        "container": 1, "network": 1, "volume": 1, "j2": 1,  # phase 47
    }

    login(page, app_url)  # phase 16: the catalog is admin-only
    expect(page.locator("#stat-docs")).to_have_text("13")
    # Phase 30: non-markdown fixtures each gained one ``is_summary`` chunk,
    # so the Sources total is content chunks + summary chunks.
    expect(page.locator("#stat-chunks")).to_have_text(
        str(summary.chunks + summary.summaries)
    )
    expect(page.locator("#stat-last")).not_to_have_text("–")
    expect(page.locator("#sources-empty")).to_be_hidden()

    for row_path in EXPECTED_ROWS:
        expect(page.locator("#docs-tbody tr", has_text=row_path)).to_have_count(1)
    # The hidden junk was never indexed (A9 scope).
    expect(page.locator("#docs-tbody tr", has_text=".hidden")).to_have_count(0)
    # The path column carries the full path for hover (ellipsis is visual only).
    expect(page.locator("#docs-tbody tr", has_text="homelab/kubernetes.md")
           .get_by_role("cell").nth(1)).to_have_attribute("title", "homelab/kubernetes.md")


def test_sources_table_layout(
    page: Page, browser: Browser, app_url: str, mock_llm: int, db_ready: None
) -> None:
    _reset_db(mock_llm, seed=True)
    login(page, app_url)  # phase 16: the catalog is admin-only
    page.locator("#docs-tbody tr").first.wait_for(state="visible")

    wrap = page.locator(".table-wrap")
    expect(wrap).to_be_visible()
    expect(wrap).to_have_attribute("role", "region")
    expect(wrap).to_have_attribute("tabindex", "0")
    expect(page.locator("#docs-table caption")).to_have_count(1)

    # Full-width table: the wrapper uses (well) ≥80% of the 72rem container.
    wrap_box = wrap.bounding_box()
    shell_box = page.locator(".sources-shell").bounding_box()
    assert wrap_box is not None and shell_box is not None
    assert wrap_box["width"] >= 0.80 * shell_box["width"]

    # Mobile (375px): the table keeps its 640px min-width → the wrapper
    # scrolls horizontally instead of squeezing into a hairline.
    mobile = browser.new_page(viewport={"width": 375, "height": 812})
    try:
        login(mobile, app_url)  # phase 16: the catalog is admin-only
        mobile.locator("#docs-tbody tr").first.wait_for(state="visible")
        scroll_width, client_width = mobile.evaluate(
            "() => { const el = document.querySelector('.table-wrap');"
            " return [el.scrollWidth, el.clientWidth]; }"
        )
        assert scroll_width > client_width
    finally:
        mobile.close()


def test_empty_state_when_no_docs(page: Page, app_url: str, mock_llm: int, db_ready: None) -> None:
    _reset_db(mock_llm, seed=False)

    login(page, app_url)  # phase 16: the (empty-state) catalog is admin-only
    expect(page.locator("#sources-empty")).to_be_visible()
    expect(page.locator("#sources-empty")).to_contain_text("Nothing indexed yet")
    expect(page.locator("#sources-empty code")).to_have_text(
        "uv run python -m scripts.import_docs"
    )
    expect(page.locator(".table-wrap")).to_be_hidden()
    expect(page.locator("#stat-docs")).to_have_text("0")
    expect(page.locator("#stat-chunks")).to_have_text("0")