feat(admin): one-click sources sync — admin-only button triggers git clone/pull + re-import + KB overview refresh with polled live status

tests/e2e/test_sync_button.py

@@ -0,0 +1,283 @@
+"""Phase 32 E2E (Playwright): the admin-only "Sync sources" button.
+
+Story: ``.agent/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).
+
+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,
+    APP_PORT,
+    SESSION_SECRET,
+    USE_REAL_LLM,
+    _wait_http,
+)
+
+REPO = Path(__file__).resolve().parents[2]
+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:
+        db.execute(text("TRUNCATE chunks, documents, query_log, kb_overview"))
+        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)
+
+
+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) → "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()
+    expect(page.locator("#sync-label")).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.
+    expect(page.locator("#sync-result")).to_have_text("1 added")
+
+    # The REAL clone was imported: the fixture path is in the Sources
+    # table (the sentinel lives inside it).
+    expect(page.locator("#docs-tbody tr", has_text=FIXTURE_DOC)).to_have_count(1)
+
+    # 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-label")).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.
+    expect(page.locator("#sync-result")).to_have_text("0 added · 1 unchanged")
+    # The doc survived the prune re-import (its file is still in the repo).
+    expect(page.locator("#docs-tbody tr", has_text=FIXTURE_DOC)).to_have_count(1)
+
+
+# --- 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

tests/integration/test_sync_api.py

@@ -0,0 +1,379 @@
+"""Integration: the admin sources-sync API (phase 32, task 01).
+
+Covers the in-process sync runner end to end over HTTP: anonymous 403s
+on both endpoints; admin idle → 202 → ``success`` with the full
+ImportSummary detail; 409 on a double trigger while a run is in flight;
+``GitSyncError`` → ``failed`` with the failing repo named and **zero**
+import attempts; empty ``BOR_GIT_SOURCES`` → ``failed`` loudly; an
+embedding failure → ``failed`` with any credentials masked; the import
+always runs with ``prune=True``; and the phase-31 overview trigger is
+change-gated (no ``lite`` call on an unchanged KB).
+
+The git / import / overview layers are monkeypatched in ``app.api.sync``
+(same fake style as ``test_import_docs_git.py``) — no real git, no real
+DB, no LLM: the runner's state machine and HTTP surface are under test.
+
+The admin client is used **as a context manager** on purpose: the
+background sync task lives on the app's event loop, so the loop must
+survive across requests — exactly how the app runs under uvicorn.
+(A TestClient without the context manager starts a fresh loop per
+request and would cancel the task on request exit.)
+"""
+from __future__ import annotations
+
+import asyncio
+import time
+from collections.abc import Iterator
+from datetime import datetime
+from pathlib import Path
+
+import pytest
+from fastapi.testclient import TestClient
+from sqlalchemy.orm import Session
+
+from app.api import sync as sync_api
+from app.config import Settings
+from app.main import app as fastapi_app
+from app.rag.importer import ImportSummary
+from app.rag.llm import EmbeddingError, LLMClient
+from scripts.git_sync import GitSyncError
+from tests.conftest import ADMIN_PASSWORD
+
+
+@pytest.fixture(autouse=True)
+def _fresh_sync_state() -> Iterator[None]:
+    """The module-level status object + task are process-global: reset them
+    around every test (both before — a previous test's terminal state
+    would leak into the idle assertion — and after)."""
+    sync_api._status = sync_api.SyncStatus()
+    sync_api._task = None
+    yield
+    sync_api._status = sync_api.SyncStatus()
+    sync_api._task = None
+
+
+@pytest.fixture()
+def sync_client() -> Iterator[TestClient]:
+    """Context-managed TestClient — one app event loop across requests
+    (the background task must survive between the POST and the polls)."""
+    with TestClient(fastapi_app) as client:
+        yield client
+
+
+def _settings(git_sources: str = "", sources_dir: str = "~/bor-sources") -> Settings:
+    """Fresh settings (no .env file); explicit kwargs beat any env leaks."""
+    return Settings(_env_file=None, git_sources=git_sources, sources_dir=sources_dir)  # pyright: ignore[reportCallIssue]
+
+
+def _login(client: TestClient) -> None:
+    r = client.post("/api/login", json={"password": ADMIN_PASSWORD})
+    assert r.status_code == 204, f"admin login failed: {r.status_code} {r.text}"
+
+
+def _poll(client: TestClient, want: str, timeout: float = 5.0) -> dict:
+    """Poll ``GET /api/sync/status`` until ``state == want`` (terminal).
+
+    Any state other than ``running`` before the deadline fails loudly —
+    an unexpected ``failed`` must never be masked by the wait.
+    """
+    deadline = time.monotonic() + timeout
+    while time.monotonic() < deadline:
+        body = client.get("/api/sync/status").json()
+        if body["state"] == want:
+            return body
+        assert body["state"] == "running", (
+            f"unexpected state {body['state']!r} while waiting for {want!r}: {body}"
+        )
+        time.sleep(0.05)
+    raise AssertionError(f"sync did not reach {want!r} within {timeout}s")
+
+
+class FakeImportSources:
+    """Records every ``import_sources`` call; returns a canned summary."""
+
+    def __init__(self, summary: ImportSummary, delay: float = 0.0) -> None:
+        self.summary = summary
+        self.delay = delay
+        self.sources: list[list[Path]] = []
+        self.llms: list[LLMClient] = []
+        self.prune_flags: list[bool] = []
+
+    async def __call__(
+        self,
+        sources: list[Path],
+        llm: LLMClient,
+        *,
+        prune: bool = False,
+        limit: int | None = None,
+        session: Session | None = None,
+    ) -> ImportSummary:
+        self.sources.append(list(sources))
+        self.llms.append(llm)
+        self.prune_flags.append(prune)
+        if self.delay:
+            await asyncio.sleep(self.delay)
+        return self.summary
+
+
+class FakeOverview:
+    """Records every ``regenerate_overview`` call; canned result."""
+
+    def __init__(self, ok: bool = True) -> None:
+        self.ok = ok
+        self.llms: list[LLMClient] = []
+
+    async def __call__(self, llm: LLMClient, session: Session | None = None) -> bool:
+        self.llms.append(llm)
+        return self.ok
+
+
+def _fake_clone() -> tuple[list[tuple[str, Path]], object]:
+    """A ``clone_or_pull`` that materialises a checkout with one .md file."""
+    calls: list[tuple[str, Path]] = []
+
+    def fake_clone_or_pull(url: str, dest: Path | str) -> Path:
+        dest = Path(dest)
+        dest.mkdir(parents=True, exist_ok=True)
+        (dest / "notes.md").write_text(f"# {dest.name}\ncontent for the KB\n", encoding="utf-8")
+        calls.append((url, dest))
+        return dest
+
+    return calls, fake_clone_or_pull
+
+
+# --- anonymous -------------------------------------------------------------
+
+
+def test_anonymous_gets_403_on_both_endpoints(client: TestClient) -> None:
+    r = client.get("/api/sync/status")
+    assert r.status_code == 403
+    assert r.json() == {"detail": "admin only"}
+    r = client.post("/api/sync")
+    assert r.status_code == 403
+    assert r.json() == {"detail": "admin only"}
+
+
+# --- admin: success --------------------------------------------------------
+
+
+def test_admin_sync_success_reports_full_detail(
+    sync_client: TestClient, monkeypatch: pytest.MonkeyPatch, tmp_path: Path
+) -> None:
+    repo_url = f"file://{tmp_path / 'repo.git'}"
+    monkeypatch.setattr(
+        sync_api,
+        "get_settings",
+        lambda: _settings(git_sources=repo_url, sources_dir=str(tmp_path / "bor")),
+    )
+    clone_calls, fake_clone = _fake_clone()
+    monkeypatch.setattr(sync_api, "clone_or_pull", fake_clone)
+    summary = ImportSummary(
+        files=5, added=1, updated=2, unchanged=2, pruned=3, errors=0,
+        chunks=11, embed_batches=4, summaries=1, summary_errors=0,
+    )
+    fake_import = FakeImportSources(summary)
+    monkeypatch.setattr(sync_api, "import_sources", fake_import)
+    fake_overview = FakeOverview(ok=True)
+    monkeypatch.setattr(sync_api, "regenerate_overview", fake_overview)
+
+    _login(sync_client)
+    assert sync_client.get("/api/sync/status").json() == {
+        "state": "idle",
+        "started_at": None,
+        "finished_at": None,
+        "detail": {},
+        "error": None,
+    }
+
+    r = sync_client.post("/api/sync")
+    assert r.status_code == 202
+    assert r.json() == {"detail": "sync started"}
+
+    body = _poll(sync_client, "success")
+    assert body["error"] is None
+    # ISO-8601 timestamps round-trip; finished after started.
+    started = datetime.fromisoformat(body["started_at"])
+    finished = datetime.fromisoformat(body["finished_at"])
+    assert finished >= started
+    # Every ImportSummary field + the overview flag, verbatim.
+    assert body["detail"] == {
+        "files": 5, "added": 1, "updated": 2, "unchanged": 2, "pruned": 3,
+        "errors": 0, "chunks": 11, "summaries": 1, "summary_errors": 0,
+        "overview": True,
+    }
+    # Git: the configured repo was cloned into BOR_SOURCES_DIR/<repo-name>/.
+    assert clone_calls == [(repo_url, tmp_path / "bor" / "repo")]
+    # Import: exactly the checkouts, with prune=True (the button is the
+    # canonical "mirror the repos" action) and a real LLMClient.
+    assert fake_import.sources == [[tmp_path / "bor" / "repo"]]
+    assert fake_import.prune_flags == [True]
+    assert len(fake_import.llms) == 1
+    assert isinstance(fake_import.llms[0], LLMClient)
+    # Overview: refreshed (added + updated > 0) with the same client.
+    assert fake_overview.llms == [fake_import.llms[0]]
+
+
+def test_unchanged_kb_skips_overview_refresh(
+    sync_client: TestClient, monkeypatch: pytest.MonkeyPatch, tmp_path: Path
+) -> None:
+    """Phase-31 trigger is change-gated: added + updated == 0 → no ``lite`` call."""
+    repo_url = f"file://{tmp_path / 'repo.git'}"
+    monkeypatch.setattr(
+        sync_api,
+        "get_settings",
+        lambda: _settings(git_sources=repo_url, sources_dir=str(tmp_path / "bor")),
+    )
+    _, fake_clone = _fake_clone()
+    monkeypatch.setattr(sync_api, "clone_or_pull", fake_clone)
+    summary = ImportSummary(files=7, added=0, updated=0, unchanged=7, pruned=0)
+    fake_import = FakeImportSources(summary)
+    monkeypatch.setattr(sync_api, "import_sources", fake_import)
+    fake_overview = FakeOverview(ok=True)
+    monkeypatch.setattr(sync_api, "regenerate_overview", fake_overview)
+
+    _login(sync_client)
+    assert sync_client.post("/api/sync").status_code == 202
+    body = _poll(sync_client, "success")
+
+    assert body["detail"]["overview"] is False
+    assert fake_overview.llms == []  # no wasted model call
+    assert len(fake_import.llms) == 1  # the import itself ran
+
+
+# --- admin: concurrency ----------------------------------------------------
+
+
+def test_double_trigger_while_running_returns_409(
+    sync_client: TestClient, monkeypatch: pytest.MonkeyPatch, tmp_path: Path
+) -> None:
+    repo_url = f"file://{tmp_path / 'repo.git'}"
+    monkeypatch.setattr(
+        sync_api,
+        "get_settings",
+        lambda: _settings(git_sources=repo_url, sources_dir=str(tmp_path / "bor")),
+    )
+    _, fake_clone = _fake_clone()
+    monkeypatch.setattr(sync_api, "clone_or_pull", fake_clone)
+    # The in-flight run takes a while (asyncio.sleep) so the second POST
+    # lands while it is still running.
+    fake_import = FakeImportSources(ImportSummary(files=1, added=1), delay=0.5)
+    monkeypatch.setattr(sync_api, "import_sources", fake_import)
+    monkeypatch.setattr(sync_api, "regenerate_overview", FakeOverview(ok=True))
+
+    _login(sync_client)
+    assert sync_client.post("/api/sync").status_code == 202
+
+    r = sync_client.post("/api/sync")  # second trigger while running
+    assert r.status_code == 409
+    assert r.json() == {"detail": "a sync is already running"}
+
+    body = sync_client.get("/api/sync/status").json()
+    assert body["state"] == "running"
+    assert body["started_at"] is not None
+    assert body["finished_at"] is None
+    assert body["error"] is None
+
+    # The (single) run completes; the import ran exactly once.
+    _poll(sync_client, "success")
+    assert len(fake_import.sources) == 1
+
+
+# --- admin: failures -------------------------------------------------------
+
+
+def test_git_failure_marks_failed_and_skips_import(
+    sync_client: TestClient, monkeypatch: pytest.MonkeyPatch, tmp_path: Path
+) -> None:
+    repo_url = f"file://{tmp_path / 'bad.git'}"
+    monkeypatch.setattr(
+        sync_api,
+        "get_settings",
+        lambda: _settings(git_sources=repo_url, sources_dir=str(tmp_path / "bor")),
+    )
+
+    def failing_clone(url: str, dest: Path | str) -> Path:
+        raise GitSyncError(
+            f"git clone --depth 1 {url} failed (exit 128): "
+            "fatal: repository not found"
+        )
+
+    monkeypatch.setattr(sync_api, "clone_or_pull", failing_clone)
+    fake_import = FakeImportSources(ImportSummary())
+    monkeypatch.setattr(sync_api, "import_sources", fake_import)
+    fake_overview = FakeOverview(ok=True)
+    monkeypatch.setattr(sync_api, "regenerate_overview", fake_overview)
+
+    _login(sync_client)
+    assert sync_client.post("/api/sync").status_code == 202
+
+    body = _poll(sync_client, "failed")
+    assert "bad.git" in body["error"]  # the failing repo is named
+    assert "fatal: repository not found" in body["error"]
+    assert body["detail"] == {}
+    assert body["finished_at"] is not None
+    assert fake_import.sources == []  # no partial import
+    assert fake_overview.llms == []
+
+    # A failed run leaves the system restartable: a new POST is accepted.
+    assert sync_client.post("/api/sync").status_code == 202
+    _poll(sync_client, "failed")
+
+
+def test_no_git_sources_configured_fails_loudly(
+    sync_client: TestClient, monkeypatch: pytest.MonkeyPatch, tmp_path: Path
+) -> None:
+    monkeypatch.setattr(
+        sync_api,
+        "get_settings",
+        # Whitespace-only is just as unconfigured as empty.
+        lambda: _settings(git_sources=" , ", sources_dir=str(tmp_path / "bor")),
+    )
+    clone_calls, fake_clone = _fake_clone()
+    monkeypatch.setattr(sync_api, "clone_or_pull", fake_clone)
+    fake_import = FakeImportSources(ImportSummary())
+    monkeypatch.setattr(sync_api, "import_sources", fake_import)
+
+    _login(sync_client)
+    assert sync_client.post("/api/sync").status_code == 202
+
+    body = _poll(sync_client, "failed")
+    assert body["error"] == "no git sources configured (BOR_GIT_SOURCES)"
+    assert clone_calls == []  # git is never touched
+    assert fake_import.sources == []
+
+
+def test_import_error_is_reported_with_credentials_masked(
+    sync_client: TestClient, monkeypatch: pytest.MonkeyPatch, tmp_path: Path
+) -> None:
+    repo_url = f"file://{tmp_path / 'repo.git'}"
+    monkeypatch.setattr(
+        sync_api,
+        "get_settings",
+        lambda: _settings(git_sources=repo_url, sources_dir=str(tmp_path / "bor")),
+    )
+    _, fake_clone = _fake_clone()
+    monkeypatch.setattr(sync_api, "clone_or_pull", fake_clone)
+
+    async def failing_import(
+        sources: list[Path],
+        llm: LLMClient,
+        *,
+        prune: bool = False,
+        limit: int | None = None,
+        session: Session | None = None,
+    ) -> ImportSummary:
+        raise EmbeddingError(
+            "embeddings request to https://user:secret@aipi.reeseapps.com/v1 "
+            "failed: connection refused"
+        )
+
+    monkeypatch.setattr(sync_api, "import_sources", failing_import)
+    monkeypatch.setattr(sync_api, "regenerate_overview", FakeOverview(ok=True))
+
+    _login(sync_client)
+    assert sync_client.post("/api/sync").status_code == 202
+
+    body = _poll(sync_client, "failed")
+    assert "*****@aipi.reeseapps.com" in body["error"]  # credentials masked
+    assert "user:secret" not in body["error"]
+    assert "connection refused" in body["error"]  # the reason survives

tests/unit/test_sync_button.py

@@ -0,0 +1,325 @@
+"""Unit: the admin "Sync sources" button contract (phase 32, task 02).
+
+The browser behavior is E2E-covered (tests/e2e/test_sync_button.py,
+task 03); here we pin the source-level wiring — the anonymous-safe
+ship-hidden button markup, the header.js admin reveal on the SAME
+cached whoami (no extra fetch), the sources.js sync state machine
+(2 s poll, 202 start / 409 adoption / 403 hide, terminal labels,
+the aria-live result, the single-poll-loop guard, no client-side hard
+timeout), the §7.4 never-stale CSS (spin + reduced-motion opt-out,
+disabled state, 44px floor, contrast pair) — so a silent regression is
+caught without a browser.
+"""
+from __future__ import annotations
+
+import re
+from pathlib import Path
+
+FRONTEND = Path(__file__).resolve().parents[2] / "frontend"
+ASSETS = FRONTEND / "assets"
+
+HEADER_JS = ASSETS / "header.js"
+SOURCES_JS = ASSETS / "sources.js"
+STYLES_CSS = ASSETS / "styles.css"
+SOURCES_HTML = FRONTEND / "sources.html"
+
+
+def _text(path: Path) -> str:
+    assert path.is_file(), f"missing frontend file: {path}"
+    return path.read_text(encoding="utf-8")
+
+
+def _body(js: str, fn_name: str) -> str:
+    """The source of the first top-level `function <fn_name>` in js."""
+    fn = js.find(f"function {fn_name}")
+    assert fn != -1, f"{fn_name} must be defined"
+    return js[fn : js.find("\n}", fn)]
+
+
+# ---------- sources.html: anonymous-safe ship-hidden markup ----------
+
+
+def test_sync_button_ships_hidden_and_labeled() -> None:
+    """#sync-btn SHIPS with the hidden attribute (anonymous-safe —
+    header.js reveals it for the admin), is a real <button type=
+    "button">, and carries aria-label="Sync sources" so the accessible
+    name stays stable across the label states."""
+    tag = re.search(r"<button[^>]*id=\"sync-btn\"[^>]*>", _text(SOURCES_HTML))
+    assert tag, "sources.html must carry the #sync-btn button"
+    attrs = tag.group(0)
+    assert 'class="sync-btn"' in attrs
+    assert 'type="button"' in attrs
+    assert re.search(r"\bhidden\b", attrs), "#sync-btn must ship hidden"
+    assert 'aria-label="Sync sources"' in attrs
+
+
+def test_sync_button_has_icon_and_label_span() -> None:
+    """The button body is a refresh-cycle svg (aria-hidden — decorative,
+    the spin is the visible running state) + the #sync-label span with
+    the idle text, so the label can be swapped by sources.js."""
+    text = _text(SOURCES_HTML)
+    btn = text[text.find('id="sync-btn"') : text.find("</button>", text.find('id="sync-btn"'))]
+    assert re.search(r'<svg[^>]*class="sync-icon"[^>]*aria-hidden="true"', btn)
+    assert 'id="sync-label"' in btn
+    assert re.search(r'<span[^>]*id="sync-label"[^>]*>Sync sources</span>', btn)
+
+
+def test_sync_result_is_the_aria_live_announcer() -> None:
+    """#sync-result sits right after the button and is a polite live
+    region (role="status" + aria-live="polite") — the last-result /
+    counts announcement for screen readers."""
+    text = _text(SOURCES_HTML)
+    tag = re.search(r'<span[^>]*id="sync-result"[^>]*>', text)
+    assert tag, "sources.html must carry the #sync-result announcer"
+    attrs = tag.group(0)
+    assert 'role="status"' in attrs
+    assert 'aria-live="polite"' in attrs
+    assert text.find('id="sync-result"') > text.find("</button>", text.find('id="sync-btn"'))
+
+
+def test_sync_error_banner_is_a_hidden_alert() -> None:
+    """The failure banner uses the chat error-banner markup style
+    (kb-banner + is-error) and role="alert", shipping hidden —
+    sources.js un-hides it with the error text on a failed run."""
+    text = _text(SOURCES_HTML)
+    tag = re.search(r'<div[^>]*id="sync-error-banner"[^>]*>', text)
+    assert tag, "sources.html must carry the #sync-error-banner"
+    attrs = tag.group(0)
+    assert "kb-banner" in attrs and "is-error" in attrs
+    assert 'role="alert"' in attrs
+    assert re.search(r"\bhidden\b", attrs)
+    assert 'id="sync-error-text"' in text
+    # The banner lives in the page content, not the 64px header bar.
+    assert text.find('id="sync-error-banner"') > text.find('<main id="main"')
+
+
+def test_page_sub_copy_mentions_the_button() -> None:
+    """The page-sub copy still points at the import CLI and now names
+    the header button as the one-click alternative (task 02 step 1)."""
+    sub = re.search(r'<p class="page-sub">(.*?)</p>', _text(SOURCES_HTML), re.DOTALL)
+    assert sub, "sources.html must keep the .page-sub copy"
+    assert "Re-run the import" in sub.group(1)
+    assert "Sync sources" in sub.group(1)
+    assert "header" in sub.group(1)
+
+
+def test_sources_page_stays_cdn_free() -> None:
+    """No-CDN rule (PLAN §7.3, A11): the new button markup adds no
+    external references — same-origin assets only (the integration
+    test_index_html_served_locally re-checks this on the served page)."""
+    text = _text(SOURCES_HTML)
+    assert 'src="https://' not in text
+    assert 'href="https://' not in text
+
+
+# ---------- header.js: the admin reveal ----------
+
+
+def test_header_reveals_sync_btn_on_the_admin_branch() -> None:
+    """initSharedHeader reveals #sync-btn in the SAME admin branch as
+    #nav-sources (querySelector + hidden = !admin) — one cached whoami,
+    no extra whoami call; anonymous users never leave the hidden
+    default."""
+    js = _text(HEADER_JS)
+    fn = js.find("function initSharedHeader")
+    assert fn != -1
+    body = js[fn : js.find("\n}", fn)]
+    assert 'querySelector("#sync-btn")' in body, "#sync-btn must join the admin reveal"
+    assert "syncBtn.hidden = !admin" in body
+    # The reveal must not introduce a second whoami call site.
+    assert js.count('fetch("/api/whoami")') == 1
+
+
+# ---------- sources.js: the sync state machine ----------
+
+
+def test_sources_js_calls_the_sync_api() -> None:
+    """The click posts to POST /api/sync and the poll loop GETs
+    /api/sync/status — both through the same-origin API (A10)."""
+    js = _text(SOURCES_JS)
+    assert 'fetch("/api/sync", { method: "POST" })' in js
+    assert 'fetch("/api/sync/status")' in js
+
+
+def test_sources_js_polls_every_2000ms() -> None:
+    """The feedback loop is a 2000 ms poll of the status endpoint,
+    re-scheduled one tick at a time (setTimeout, not setInterval — an
+    in-flight fetch can never overlap the next tick)."""
+    js = _text(SOURCES_JS)
+    assert "SYNC_POLL_MS = 2000" in js
+    assert "setTimeout(tick, SYNC_POLL_MS)" in js
+    assert "setInterval" not in js
+
+
+def test_sources_js_adopts_409_and_starts_on_202() -> None:
+    """202 (started) and 409 (a run started elsewhere — e.g. a second
+    tab) both enter the running state and start polling: the UI never
+    starts a second run, it adopts the in-flight one."""
+    js = _text(SOURCES_JS)
+    assert "r.status === 202 || r.status === 409" in js
+    idx = js.find("r.status === 202 || r.status === 409")
+    branch = js[idx : idx + 200]
+    assert "enterRunningState()" in branch
+    assert "startSyncPolling()" in branch
+
+
+def test_sources_js_hides_the_button_on_403() -> None:
+    """A 403 anywhere (POST or poll) is treated as not-admin: the
+    button hides — defense in depth behind header.js's whoami reveal."""
+    js = _text(SOURCES_JS)
+    for occurrence in re.finditer(r"r\.status === 403", js):
+        window = js[occurrence.start() : occurrence.start() + 400]
+        assert "syncBtn.hidden = true" in window, "every 403 branch must hide the button"
+    assert len(re.findall(r"r\.status === 403", js)) >= 3, (
+        "POST, the status poll, and the load re-attach must all handle 403"
+    )
+
+
+def test_sources_js_running_state_is_never_stale() -> None:
+    """Entering the running state disables the button, sets aria-busy,
+    spins the icon, and swaps the label to 'Syncing…' (the §7.4
+    feedback while the poll waits)."""
+    js = _text(SOURCES_JS)
+    fn = js.find("function enterRunningState")
+    assert fn != -1
+    body = js[fn : js.find("\n}", fn)]
+    assert "syncBtn.disabled = true" in body
+    assert 'syncBtn.setAttribute("aria-busy", "true")' in body
+    assert "syncIcon.classList.add(\"is-spinning\")" in body
+    assert '"Syncing…"' in body
+
+
+def test_sources_js_terminal_states() -> None:
+    """Terminal rendering: success → enabled + 'Synced HH:MM' (local
+    time of finished_at) + the last-result counts ('added' always
+    announced, zero terms omitted — a no-op re-sync reads '0 added ·
+    1 unchanged', never an empty live region) + a live catalog refresh
+    (the KB just changed — never a stale table); failed → enabled +
+    retry-ready 'Sync sources' label + the role='alert' banner with
+    the error; the result is cleared on a failure."""
+    js = _text(SOURCES_JS)
+
+    success = _body(js, "applySyncSuccess")
+    assert '"Synced"' in success and "fmtSyncTime(status.finished_at)" in success
+    assert "fmtSyncResult(status.detail)" in success
+    # A successful sync just changed the KB: the catalog re-fetches live
+    # (table / stats / empty state never sit stale under "Synced").
+    assert "loadDocs()" in success
+
+    failure = _body(js, "applySyncFailure")
+    assert 'settleSyncButton("Sync sources")' in failure  # retry-ready
+    assert "showSyncError(status.error)" in failure
+
+    result = _body(js, "fmtSyncResult")
+    # "added" is the always-announced headline term; "unchanged" covers
+    # the no-op case ("0 added · 1 unchanged"); updated/pruned are
+    # zero-omitted.
+    assert "added" in result and "unchanged" in result
+    assert " · " in result
+    assert "> 0" in result, "zero terms must be omitted"
+
+    time = _body(js, "fmtSyncTime")
+    assert "getHours()" in time and "getMinutes()" in time, "local HH:MM of finished_at"
+
+
+def test_sources_js_settles_the_button_on_terminal() -> None:
+    """settleSyncButton re-enables the control, drops aria-busy, and
+    un-spins the icon — the button can never sit disabled after a run
+    reaches a terminal state (failed included: retry-ready)."""
+    js = _text(SOURCES_JS)
+    fn = js.find("function settleSyncButton")
+    assert fn != -1
+    body = js[fn : js.find("\n}", fn)]
+    assert "syncBtn.disabled = false" in body
+    assert 'syncBtn.removeAttribute("aria-busy")' in body
+    assert "syncIcon.classList.remove(\"is-spinning\")" in body
+
+
+def test_sources_js_never_starts_a_second_poll_loop() -> None:
+    """startSyncPolling is guarded by the module-level timer: a 409
+    adoption, a reload re-attach, or a stray call can never run two
+    poll loops at once (phase completion criterion)."""
+    js = _text(SOURCES_JS)
+    fn = js.find("function startSyncPolling")
+    assert fn != -1
+    head = js[fn : js.find("const tick", fn)]
+    assert re.search(r"if\s*\(\s*syncPollTimer\s*!==\s*null\s*\)\s*return", head), (
+        "the single-loop guard must be the first statement"
+    )
+    assert "clearTimeout(syncPollTimer)" in _body(js, "stopSyncPolling")
+
+
+def test_sources_js_has_no_client_side_hard_timeout() -> None:
+    """Phase locked decision: a sync can legitimately run for minutes,
+    so there is NO client-side hard timeout — the 2 s poll is the
+    feedback loop and the server state is authoritative (the 120 s
+    LLM-turn guard must not leak into the sync path)."""
+    js = _text(SOURCES_JS)
+    assert "TURN_TIMEOUT" not in js
+    assert "120" not in js[js.find("Phase 32") :], (
+        "no turn-timeout constant in the sync section"
+    )
+
+
+def test_sources_js_reattaches_on_load() -> None:
+    """initSyncButton (run from the IIFE on the admin path, after
+    initSharedHeader) fetches the status once and re-enters the running
+    state on 'running' (reload mid-sync) or renders the last result on
+    a terminal state; the click binding wires startSync to the button."""
+    js = _text(SOURCES_JS)
+    fn = js.find("function initSyncButton")
+    assert fn != -1
+    body = js[fn : js.find("\n}\n", fn)]
+    assert 'fetch("/api/sync/status")' in body
+    assert 'status.state === "running"' in body
+    assert 'status.state === "success"' in body
+    assert 'status.state === "failed"' in body
+    assert "syncBtn.addEventListener(\"click\", startSync)" in js
+    # The IIFE runs it on the admin path only (after the whoami gate).
+    iife = js[js.find("(async () => {") :]
+    admin_idx = iife.find("await isAdmin()")
+    init_idx = iife.find("initSyncButton();")
+    assert -1 < admin_idx < init_idx, "re-attach must run only for the admin"
+
+
+# ---------- styles.css: the §7.4 states ----------
+
+
+def test_sync_button_css_ghost_pill_and_disabled_state() -> None:
+    """.sync-btn is the same ghost pill as .new-chat-btn (contrast pair
+    ink-soft on surface ≈6.9:1 ≥ 4.5:1), with a ≥44px touch floor and a
+    :disabled state (never stale — the busy look is visible)."""
+    css = _text(STYLES_CSS)
+    block = re.search(r"\.sync-btn\s*\{([^}]*)\}", css)
+    assert block, "styles.css must define .sync-btn"
+    body = block.group(1)
+    assert "min-height: 44px" in body
+    assert "color: var(--ink-soft)" in body
+    assert "border-radius: 999px" in body
+    disabled = re.search(r"\.sync-btn:disabled\s*\{([^}]*)\}", css)
+    assert disabled, ".sync-btn:disabled must be styled"
+    assert "cursor: wait" in disabled.group(1)
+
+
+def test_sync_icon_spins_and_respects_reduced_motion() -> None:
+    """The running state spins the refresh icon on the shared spin
+    keyframes (1s linear infinite), and prefers-reduced-motion stills
+    it — the existing opt-out pattern."""
+    css = _text(STYLES_CSS)
+    spin = re.search(r"\.sync-btn \.sync-icon\.is-spinning\s*\{([^}]*)\}", css)
+    assert spin, "the .is-spinning state must be styled"
+    assert "animation: spin 1s linear infinite" in spin.group(1)
+    spinner = r"\.sync-btn \.sync-icon\.is-spinning\s*\{([^}]*)\}"
+    reduced = re.search(r"@media \(prefers-reduced-motion: reduce\)\s*\{\s*" + spinner, css)
+    assert reduced, "the spin must opt out under prefers-reduced-motion"
+    assert "animation: none" in reduced.group(1)
+    assert "@keyframes spin" in css, "the spin keyframes are shared (pre-existing)"
+
+
+def test_sync_result_is_styled() -> None:
+    """#sync-result (the aria-live last-result line) is styled in the
+    theme tokens — soft ink, small mono, no wrap in the header bar."""
+    css = _text(STYLES_CSS)
+    block = re.search(r"\.sync-result\s*\{([^}]*)\}", css)
+    assert block, "styles.css must define .sync-result"
+    assert "var(--ink-soft)" in block.group(1)