"""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.

Phase 97 adaptation: the catalog is the DRILL-DOWN TREE the agent's
``ls`` walks — the top level lists the sources (this fixture's single
indexed-only source, ``docs``), then one folder link per path segment;
the flat all-documents table no longer renders. The asserted rows,
links, and stat cards are UNCHANGED in intent — the drill is the only
change (every row here is nested under a folder). The empty-state test
now pins the zero-SOURCES state (a registered 0-document source renders
its row instead) — for that state to be reachable at all, this suite
runs its OWN module app (the conftest leak-guard pattern) with
``BOR_GIT_SOURCES`` forced empty: the session app would inherit an
operator's local ``.env`` fallback source, which would leak a
0-document top-level row into the tree.
"""
from __future__ import annotations

import asyncio
import json
import os
import subprocess
import sys
from collections.abc import Iterator
from pathlib import Path
from threading import Thread
from typing import Any

import pytest
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
from e2e.conftest import (
    ADMIN_PASSWORD,
    SESSION_SECRET,
    USE_REAL_LLM,
    _wait_http,
)

REPO = Path(__file__).resolve().parents[2]
FIXTURES = REPO / "tests" / "fixtures" / "docs"

# Phase 79 (task 04, full inventory): the conftest session app owns its
# port in a combined run — this module app binds its own port instead
# (a same-port second uvicorn dies on bind and would drive the wrong
# server). Env-overridable.
APP_PORT = int(os.environ.get("E2E_APP_PORT_IMPORTDOCS", "8140"))
APP_URL = f"http://127.0.0.1:{APP_PORT}"


@pytest.fixture(scope="module")
def app_server(mock_llm: int) -> Iterator[str]:
    """The real app under test — per-module env (the conftest pattern):
    the leak guards force the code defaults, and ``BOR_GIT_SOURCES`` is
    forced EMPTY (phase 97 — the registered sources now render as
    top-level rows: the operator's ``.env`` fallback source would leak
    a 0-document source into the tree and break the empty-state test's
    zero-SOURCES state). The session app is never started in this
    isolated run, so no port clash."""
    env = dict(os.environ)
    env.pop("DEBUGPY", None)
    env["BOR_ENVIRONMENT"] = "e2e"
    env["BOR_STATIC_DIR"] = str(REPO / "frontend")
    env["BOR_LLM_BASE_URL"] = (
        "https://aipi.reeseapps.com/v1"
        if USE_REAL_LLM
        else f"http://127.0.0.1:{mock_llm}/v1"
    )
    # Mock-calibrated threshold (conftest pattern).
    env["BOR_RELEVANCE_THRESHOLD"] = "0.30"
    # Phase 67: instant retry waits + the code-default budget.
    env["BOR_LLM_RETRY_DELAY"] = "0"
    env["BOR_LLM_RETRIES"] = str(Settings.model_fields["llm_retries"].default)
    env.setdefault(
        "BOR_DATABASE_URL",
        "postgresql+psycopg://reese:reese@localhost:5432/brain_of_reese",
    )
    # Phase 16: admin auth must be set or create_app() refuses to boot.
    env["BOR_ADMIN_PASSWORD"] = ADMIN_PASSWORD
    env["BOR_SESSION_SECRET"] = SESSION_SECRET
    # Phase 97: the registry is this suite's own concern (see the
    # fixture docstring) — the env fallback is git-only, empty here.
    env["BOR_GIT_SOURCES"] = ""
    # Leak guards (conftest pattern): an operator's local (gitignored)
    # .env cannot leak corpus-specific settings into the app under test.
    env["BOR_DOCS_REPO"] = ""
    env["BOR_SUGGESTIONS"] = json.dumps(
        Settings.model_fields["suggestions"].default
    )
    env["BOR_INPUT_PLACEHOLDER"] = Settings.model_fields["input_placeholder"].default
    env["BOR_FOOTER_TEXT"] = Settings.model_fields["footer_text"].default
    proc = subprocess.Popen(
        [sys.executable, "-m", "uvicorn", "app.main:app",
         "--host", "127.0.0.1", "--port", str(APP_PORT), "--log-level", "warning"],
        cwd=REPO,
        env=env,
    )
    try:
        _wait_http(f"{APP_URL}/api/health")
        yield APP_URL
    finally:
        proc.terminate()
        try:
            proc.wait(timeout=10)
        except subprocess.TimeoutExpired:
            proc.kill()


@pytest.fixture(scope="module")
def app_url(app_server: str) -> str:
    return app_server

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.

    Phase 97: the registry (``git_sources``) and the stored folder
    descriptions (``folder_summaries``) are truncated too — they now
    RENDER in the RAG view (top-level source rows + descriptions), so a
    leftover row from another suite would show up as a 0-document
    source and break the empty-state test's zero-SOURCES state."""
    with SessionLocal() as db:
        db.execute(
            text("TRUNCATE chunks, documents, query_log, git_sources, folder_summaries")
        )
        db.commit()
    if not seed:
        return None
    return _run_in_thread(_import_fixtures(mock_port))


# ---------------------------------------------------------------------------
# Phase 97: the catalog is the drill-down tree the agent's `ls` walks —
# the top level lists the SOURCES (this fixture's single indexed-only
# source: `docs`, the fixtures dir's basename — import_sources seeded it
# with no registry row), then one folder link per path segment. The
# flat all-documents table is gone; the drill is the only change (the
# asserted rows/links are the same).
# ---------------------------------------------------------------------------


SOURCE_NAME = "docs"  # the fixtures dir's basename (the indexed-only source)


def _drill(page: Page, *names: str) -> None:
    """Drill one level at a time (client-side — no fetch, no URL
    change): each name is the EXACT text of the source/folder link at
    the current level (the test_kb_tree house pattern)."""
    for name in names:
        page.click(f'#folders-tbody a.folder-link:text-is("{name}")')


def _go_top(page: Page) -> None:
    """Back to the top level (the sources list): the breadcrumb's
    top-level link (hidden AT the top — call between drills only)."""
    page.locator("#kb-crumb a.kb-crumb-link").first.click()


def _wait_top_level(page: Page) -> None:
    """The tree's single fetch settled: the source row is rendered
    (the catalog-rendered signal — the top-level file table is always
    hidden, so it is no longer a usable one)."""
    page.locator("#folders-tbody .folder-link").first.wait_for(state="visible")


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()

    _wait_top_level(page)
    # Phase 97: every row is nested under a folder — drill source →
    # folder(s) per path before asserting (the flat 13-row tbody no
    # longer exists; the stat cards above hold the KB total).
    for i, row_path in enumerate(EXPECTED_ROWS):
        if i > 0:
            _go_top(page)
        _drill(page, SOURCE_NAME, *row_path.rsplit("/", 1)[0].split("/"))
        expect(page.locator("#docs-tbody tr", has_text=row_path)).to_have_count(1)
    # The hidden junk was never indexed (A9 scope) — scoped to the
    # level where it WOULD appear: no `.hidden` file row at the source
    # level AND no `.hidden` folder row there either (the stat cards
    # pin the 13 total, so the junk is counted nowhere).
    _go_top(page)
    _drill(page, SOURCE_NAME)
    expect(page.locator("#docs-tbody tr", has_text=".hidden")).to_have_count(0)
    expect(page.locator("#folders-tbody .folder-link", has_text=".hidden")).to_have_count(0)
    # The path column carries the full path for hover (ellipsis is visual only).
    _drill(page, "homelab")
    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
    # Phase 97: the top level lists the sources (the file table is
    # hidden there) — wait for the source row, then drill to a file
    # level (docs → homelab) for the file table's layout asserts.
    _wait_top_level(page)
    _drill(page, SOURCE_NAME, "homelab")
    page.locator("#docs-tbody tr").first.wait_for(state="visible")

    # Phase 76 (task 02): the shell carries BOTH views' .table-wrap —
    # scope to the RAG view. Phase 97: the RAG view carries TWO
    # .table-wraps (#folders-wrap + the file table's) — :has() targets
    # the file table's (the one these layout pins were written for).
    wrap = page.locator("#view-rag .table-wrap:has(#docs-table)")
    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
        _wait_top_level(mobile)
        _drill(mobile, SOURCE_NAME, "homelab")
        mobile.locator("#docs-tbody tr").first.wait_for(state="visible")
        # Phase 97: target the FILE table's wrap explicitly (a bare
        # .table-wrap query would hit #folders-wrap first now).
        scroll_width, client_width = mobile.evaluate(
            "() => { const el = document.querySelector('#docs-table').parentElement;"
            " 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"
    )
    # Phase 97: BOTH catalog tables ship in the RAG view — the empty
    # state hides both (the original single-wrap pin, extended).
    expect(page.locator("#view-rag .table-wrap:has(#docs-table)")).to_be_hidden()
    expect(page.locator("#folders-wrap")).to_be_hidden()
    expect(page.locator("#stat-docs")).to_have_text("0")
    expect(page.locator("#stat-chunks")).to_have_text("0")