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

"""Phase 32 E2E (Playwright): the admin-only "Sync sources" button.

Story: ``.agents/user_stories/admin-sync-button.md``
Run in isolation (DB must be up: ``podman compose up -d db``; git on
PATH — a documented environment prerequisite, phase 28):

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

The story gate runs the **real** sync path end to end — a real
``git clone`` of a local ``file://`` fixture repo (deterministic, no
network), a real import against the mock LLM, a real KB-overview
regeneration — plus the admin-only visibility and the full button
lifecycle (§7.4: "Syncing…" → "Synced HH:MM" + counts, the idempotent
second run, the 409 double trigger). Phase 149 (task 01): the
RUNNING-state pins (the 202's "Syncing…") ride the detail box
(``#sync-progress`` — the running label left the pill; the button is
the spinner), while every SETTLED pin (the idle "Sync sources", the
"Synced HH:MM" label + counts line) is unchanged.

Per-module app env (the E2E conftest pattern, module-scoped): this
story's app boots with ``BOR_GIT_SOURCES=file://<fixture repo>`` and
its own ``BOR_SOURCES_DIR`` — the session app (no git sources) is
never started in this isolated run, so no port clash.

Test → story mapping (Playwright Mapping Rule):
1. ``test_anonymous_sees_no_button`` → AC 1 + 3 (hidden button, 403s)
2. ``test_admin_sync_lifecycle`` → AC 2 + 4 (full lifecycle + idempotent
   second run + the fresh ``kb_overview`` row)
3. ``test_double_trigger_409`` → AC 2 (one sync at a time)
"""
from __future__ import annotations

import os
import re
import subprocess
import sys
import time
from collections.abc import Iterator
from pathlib import Path
from typing import Any

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

from app.db import SessionLocal
from app.models import KbOverview
from e2e.auth_helpers import login
from e2e.conftest import (
    ADMIN_PASSWORD,
    SESSION_SECRET,
    USE_REAL_LLM,
    _wait_http,
)
from e2e.sync_helpers import counts_line

REPO = Path(__file__).resolve().parents[2]

# 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_SYNCBTN", "8132"))
APP_URL = f"http://127.0.0.1:{APP_PORT}"

#: The unique sentinel inside the fixture doc (task 03 step 1) — its
#: import into the Sources table proves the REAL clone was indexed.
SENTINEL = "RESE-SYNC-SENTINEL-9b2c"
FIXTURE_DOC = "notes/sync-fixture.md"

#: "Synced HH:MM" — the local-time last-result label (sources.js's
#: fmtSyncTime), any hour/minute.
SYNCED_LABEL = re.compile(r"Synced \d{1,2}:\d{2}")

#: Real git clone + embed against the mock LLM — generous budget
#: (task 03: the sync can legitimately take a while, no client timeout).
SYNC_TIMEOUT_MS = 60_000


def _git(cwd: Path, *args: str) -> None:
    """Run git in *cwd*; a non-zero exit fails the fixture loudly."""
    proc = subprocess.run(["git", *args], cwd=cwd, capture_output=True, text=True)
    if proc.returncode != 0:
        raise AssertionError(f"git {' '.join(args)} failed: {proc.stderr.strip()}")


@pytest.fixture(scope="module")
def sync_git_repo(tmp_path_factory: pytest.TempPathFactory) -> Path:
    """A real one-commit git repo the sync must clone (task 03 step 1).

    ``tmp_path`` is function-scoped while the module-scoped app fixture
    needs the repo for the module's lifetime, so it is built under
    ``tmp_path_factory`` (the same pytest-managed temp area, module-safe)
    via real ``git`` subprocess calls.
    """
    root = tmp_path_factory.mktemp("sync_git")
    repo = root / "homelab-notes"
    (repo / "notes").mkdir(parents=True)
    (repo / "notes" / "sync-fixture.md").write_text(
        "# Sync fixture note\n"
        "\n"
        "One small note that exists only to prove the admin sync button\n"
        "end to end: a real git clone, a real import, a real KB overview\n"
        "regeneration.\n"
        "\n"
        f"Marker: {SENTINEL}\n",
        encoding="utf-8",
    )
    _git(repo, "init", "-q")
    _git(repo, "add", "-A")
    _git(
        repo,
        "-c", "user.email=e@x", "-c", "user.name=t",
        "-c", "commit.gpgsign=false",  # the fixture commit never signs
        "commit", "-qm", "one",
    )
    assert (repo / ".git").is_dir()
    return repo


@pytest.fixture(scope="module")
def app_server(mock_llm: int, sync_git_repo: Path) -> Iterator[str]:
    """The real app under test — per-module env: the sync's subject is a
    real ``file://`` git source with its own checkout dir (the conftest
    session app boots without ``BOR_GIT_SOURCES`` and is never started
    in this isolated run)."""
    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) — keeps every story
    # suite's deterministic gate behavior; production default stays 0.62.
    env["BOR_RELEVANCE_THRESHOLD"] = "0.30"
    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 32: the sync button's subject — one real local repo.
    env["BOR_GIT_SOURCES"] = f"file://{sync_git_repo}"
    env["BOR_SOURCES_DIR"] = str(sync_git_repo.parent / "checkouts")
    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


def _truncate_kb() -> None:
    """Fresh KB per test (the E2E isolation pattern): the sync's counts
    and the ``kb_overview`` row must be the sync's own doing."""
    with SessionLocal() as db:
        # git_sources too: the shared Postgres may carry leftover
        # registry rows from other suites, and effective_sources prefers
        # the DB list over this app's BOR_GIT_SOURCES env fallback.
        db.execute(text("TRUNCATE chunks, documents, query_log, kb_overview, git_sources"))
        db.commit()


@pytest.fixture(autouse=True)
def _clean_kb(db_ready: None) -> Iterator[None]:
    _truncate_kb()
    yield


def _overview_row() -> KbOverview | None:
    with SessionLocal() as db:
        return db.get(KbOverview, 1)


# The git fixture repo's directory name — the source name the import
# records for it (the repo_name basename rule, phase 28).
GIT_SOURCE_NAME = "homelab-notes"


def _go_top(page: Page) -> None:
    """Back to the top level (no-op when already there — the
    breadcrumb is hidden at the top)."""
    if not page.locator("#kb-crumb").is_hidden():
        page.locator("#kb-crumb a.kb-crumb-link").first.click()


def _expect_fixture_row(page: Page) -> None:
    """The REAL clone was imported — the fixture path is listed. Phase
    97: the catalog is the drill-down tree, so drill source → folder
    ``notes`` first (the flat all-docs row is the same row, one level
    deeper)."""
    _go_top(page)
    page.click(f'#folders-tbody a.folder-link:text-is("{GIT_SOURCE_NAME}")')
    page.click('#folders-tbody a.folder-link:text-is("notes")')
    expect(page.locator("#docs-tbody tr", has_text=FIXTURE_DOC)).to_have_count(1)


def _wait_sync_done(page: Page, app_url: str, timeout_s: float = 60.0) -> dict[str, Any]:
    """Poll the (cookie-authenticated) status endpoint until the run
    reaches a terminal state — exactly what the UI's 2 s poll loop
    observes."""
    deadline = time.monotonic() + timeout_s
    body: dict[str, Any] = {}
    while time.monotonic() < deadline:
        r = page.request.get(f"{app_url}/api/sync/status")
        assert r.status == 200
        body = r.json()
        if body["state"] in ("success", "failed"):
            return body
        time.sleep(0.5)
    raise AssertionError(f"sync did not reach a terminal state: {body}")


# --- 1. Anonymous: no button, locked endpoints ----------------------------


def test_anonymous_sees_no_button(page: Page, app_url: str, db_ready: None) -> None:
    """AC 1 + 3 — anonymous: ``#sync-btn`` never leaves ``hidden`` (the
    whoami reveal is admin-only, so for a logged-out visitor it is
    absent from the *revealed* DOM) and both sync endpoints answer
    403 — the admin-only surface (A10 extended, phase 16 pattern)."""
    page.goto(f"{app_url}/sources.html")
    expect(page.locator("#sync-btn")).to_be_hidden()
    # The same whoami gate that hides the button also hides the admin
    # nav link and shows the catalog sign-in gate.
    expect(page.locator("#nav-sources")).to_be_hidden()
    expect(page.locator("#sources-gate")).to_be_visible()
    assert page.request.get(f"{app_url}/api/sync/status").status == 403
    assert page.request.post(f"{app_url}/api/sync").status == 403


# --- 2. Admin: the full lifecycle against the real sync path --------------


def test_admin_sync_lifecycle(page: Page, app_url: str, db_ready: None) -> None:
    """AC 2 + 4 — click → "Syncing…" (disabled; phase 149: the
    running label is in the detail box — the button is the spinner)
    → "Synced HH:MM" + the counts, against the REAL pipeline (git
    clone of the ``file://`` fixture → import with prune → KB overview
    regeneration, mock LLM). Then the idempotent second run:
    fast-forward pull + sha256 hash skip → "0 added · 1 unchanged"."""
    login(page, app_url)  # lands on /sources.html (the button's home)

    btn = page.locator("#sync-btn")
    expect(btn).to_be_visible()
    expect(page.locator("#sync-label")).to_have_text("Sync sources")

    # --- run 1: clone + import + overview --------------------------------
    btn.click()
    expect(btn).to_be_disabled()
    # Phase 149 (task 01): the running detail rides the box under the
    # button row (the button is the spinner) — the 202's bare label.
    expect(page.locator("#sync-progress")).to_have_text("Syncing…")
    expect(page.locator("#sync-label")).to_have_text(SYNCED_LABEL, timeout=SYNC_TIMEOUT_MS)
    expect(btn).to_be_enabled()  # never stale — re-enabled at the terminal state
    # The fixture doc (one A9-format file) is the only change — the
    # settle's counts line rides the box (phase 150: the box is the
    # sole sync text surface).
    expect(page.locator("#sync-progress-text")).to_have_text(counts_line("1 added"))

    # The REAL clone was imported: the fixture path is in the Sources
    # table (the sentinel lives inside it) — via the drill-down tree
    # (phase 97).
    _expect_fixture_row(page)

    # Phase-31 regeneration ran (the import changed the KB): the single
    # kb_overview row is fresh and non-empty (DB check — truncated
    # before this test, so it is the sync's own doing).
    row = _overview_row()
    assert row is not None and row.content.strip(), (
        "kb_overview must be regenerated by a successful, KB-changing sync"
    )

    # --- run 2: idempotent pull + hash skip -------------------------------
    btn.click()
    expect(btn).to_be_disabled()
    expect(page.locator("#sync-progress")).to_have_text("Syncing…")
    expect(page.locator("#sync-label")).to_have_text(SYNCED_LABEL, timeout=SYNC_TIMEOUT_MS)
    expect(btn).to_be_enabled()
    # Nothing re-embedded (sha256 delta) — the no-op run announces the
    # unchanged count instead of an empty live region (the box keeps
    # its result line — phase 150).
    expect(page.locator("#sync-progress-text")).to_have_text(counts_line("0 added · 1 unchanged"))
    # The doc survived the prune re-import (its file is still in the
    # repo) — via the drill-down tree (phase 97).
    _expect_fixture_row(page)


# --- 3. Concurrency: one sync at a time ------------------------------------


def test_double_trigger_409(page: Page, app_url: str, db_ready: None) -> None:
    """AC 2 — a second trigger while a run is in flight gets 409
    ("a sync is already running"); the UI adopts the in-flight run
    instead of starting a second one. The E2E path adds that the REAL
    run behind the 409 still completes (the adopted run is the one and
    only run)."""
    login(page, app_url)

    first = page.request.post(f"{app_url}/api/sync")
    assert first.status == 202, first.text
    second = page.request.post(f"{app_url}/api/sync")
    assert second.status == 409, second.text
    assert second.json()["detail"] == "a sync is already running"

    # The adopted (single) run still completes successfully.
    body = _wait_sync_done(page, app_url)
    assert body["state"] == "success", body
    assert body["detail"]["added"] == 1  # the fixture doc, fresh after the truncate