brain-of-reese/tests/integration/test_sync_api.py

"""Integration: the admin sources-sync API (phase 32, task 01; phase 35,
task 03 re-points the URL resolution at the shared resolver; phase 38,
task 03 adds the local kind).

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 on *both* origins (no git rows, no local rows,
no env URLs) → ``failed`` loudly (``no sources configured
(git or local)``); 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).

Phase 38 (local kind): local-only, git-only, and mixed syncs over a
**host temp local dir** (the app server runs on the same host) — the
mixed run goes through the **real** ``import_sources`` (deterministic
in-process ``FakeEmbedder``, no network), so the local file verifiably
lands in the KB via ``GET /api/docs`` and union pruning holds (a file
deleted out of the local dir is pruned on the next sync while the git
doc survives); a local directory missing at sync time → ``failed`` with
``local source missing: <path>`` and **zero** import attempts.

Phase 35: the runner resolves the sources through
:func:`app.rag.git_sources.effective_sources` — the **real** resolver
against the **real** ``git_sources`` table (truncated around every
test), so DB-over-env and the env fallback go through the actual
indirection; the env list is driven by a fresh ``Settings`` on the
resolver's module (the dev ``.env`` never leaks in).

Phase 41: the pre-sync model probe (``check_models``) — a dead model
endpoint fails the run **before any clone** (the model-naming error
lands in the ``failed`` state verbatim; the sanitizer is a no-op for
it); the probe runs before ``effective_sources``; a real probe against
a stubbed dead ``LLMClient`` names the embed model **and** masks the
credentials wrapped from the endpoint URL. Where the runner keeps a
real ``LLMClient`` the probe is stubbed (:func:`_stub_probe`) so no
test ever hits the network; the ``_real_llm`` tests get a passing
probe from ``FakeEmbedder.embed_one``/``chat``.

Phase 53 (task 02): the sources-version bump — a sync whose import
changed the KB (added + updated + pruned > 0) advances the single-row
``sources_meta`` counter exactly once (the new generation lands in the
``/api/sync/status`` detail as ``sources_version``); an unchanged
re-sync never bumps (the detail still reports the current generation),
and every failure path (git error, model down) never bumps. The
counter is pinned to the migration-0010 seed (0) around every test by
:func:`_reset_sources_version`.

The git / import / overview layers are monkeypatched in ``app.api.sync``
(same fake style as ``test_import_docs_git.py``) — no real git, 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 logging
import time
from collections.abc import Callable, Iterator
from datetime import UTC, datetime
from pathlib import Path
from typing import Any

import pytest
from fastapi.testclient import TestClient
from sqlalchemy import text
from sqlalchemy.orm import Session

from app.api import sync as sync_api
from app.config import Settings
from app.db import SessionLocal, db_available
from app.main import app as fastapi_app
from app.models import GitSource
from app.rag import git_sources as git_sources_resolver
from app.rag.importer import ImportSummary
from app.rag.llm import EmbeddingError, LLMClient, ModelUnavailableError
from app.rag.sources_meta import current_sources_version
from scripts.git_sync import GitSyncError
from tests.conftest import ADMIN_PASSWORD
from tests.fakes import FakeEmbedder


@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(autouse=True)
def clean_git_sources(db: Session) -> Iterator[None]:
    """Phase 35: the runner resolves through the real ``git_sources``
    table — global state, truncated around every test (the ``db``
    fixture skips the file when Postgres is down)."""
    db.execute(text("TRUNCATE git_sources"))
    db.commit()
    yield
    db.execute(text("TRUNCATE git_sources"))
    db.commit()


@pytest.fixture(autouse=True)
def _reset_sources_version() -> Iterator[None]:
    """Phase 53: the sources version counter is global mutable state —
    pin it to the migration-0010 seed (0) around every sync test so the
    bump assertions start from a known generation (own session: the
    runner bumps through its own short-lived ``SessionLocal``).
    Skips like the ``db`` fixture when Postgres is down."""
    if not db_available():
        pytest.skip("Postgres not reachable — run `podman compose up -d db` first")
    session = SessionLocal()
    try:
        session.execute(text("UPDATE sources_meta SET version = 0 WHERE id = 1"))
        session.commit()
        yield
    finally:
        session.execute(text("UPDATE sources_meta SET version = 0 WHERE id = 1"))
        session.commit()
        session.close()


@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(sources_dir: str = "~/bor-sources") -> Settings:
    """Fresh settings (no .env file); explicit kwargs beat any env leaks.

    (The ``git_sources`` kwarg is gone with phase 35 — the runner reads
    the URLs from the resolver, not from its own settings; the env list
    is stubbed on the resolver's module via :func:`_stub_env`.)
    """
    return Settings(_env_file=None, sources_dir=sources_dir)  # pyright: ignore[reportCallIssue]


def _stub_env(monkeypatch: pytest.MonkeyPatch, git_sources: str = "") -> None:
    """The resolver's env fallback, driven by a fresh ``Settings`` (the
    dev ``.env`` never leaks in — the task-02 pattern)."""
    monkeypatch.setattr(
        git_sources_resolver,
        "get_settings",
        lambda: Settings(_env_file=None, git_sources=git_sources),  # pyright: ignore[reportCallIssue]
    )


def _seed(db: Session, url: str) -> None:
    db.add(GitSource(url=url))
    db.commit()


def _seed_local(db: Session, path: Path) -> None:
    """A ``kind=local`` row as the phase-38 API stores it: the expanded
    absolute path in both ``path`` and the NOT-NULL ``url`` column."""
    db.add(GitSource(url=str(path), kind="local", path=str(path)))
    db.commit()


@pytest.fixture()
def clean_documents(db: Session) -> Iterator[None]:
    """The real-import tests write ``documents``/``chunks`` (the canonical
    KB state) — global, truncated around every such test."""
    db.execute(text("TRUNCATE chunks, documents"))
    db.commit()
    yield
    db.execute(text("TRUNCATE chunks, documents"))
    db.commit()


def _real_llm(monkeypatch: pytest.MonkeyPatch) -> None:
    """The pipeline's ``LLMClient`` becomes the deterministic in-process
    ``FakeEmbedder`` (real import, no network). ``FakeEmbedder``
    implements ``embed_one`` + ``chat``, so the phase-41 probe passes
    against it without a stub."""
    monkeypatch.setattr(sync_api, "LLMClient", lambda: FakeEmbedder())


def _stub_probe(monkeypatch: pytest.MonkeyPatch) -> list[Any]:
    """Stub the phase-41 model probe (a real ``LLMClient`` in the runner
    would hit the network). Returns the clients the probe received, so
    tests can assert the probe and the import share one client."""
    seen: list[Any] = []

    async def fake_check_models(llm: LLMClient) -> None:
        seen.append(llm)

    monkeypatch.setattr(sync_api, "check_models", fake_check_models)
    return seen


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] = []
        # Phase 64 (task 02): the progress hook the runner passes (a live
        # closure while wired, None if the wiring regresses).
        self.progress_hooks: list[object] = []
        # Phase 89: the per-root ignore map the runner builds from the
        # rows' ``ignore_paths`` (keyed by the root string the importer
        # sees; two rows sharing a root string get the union).
        self.ignore_maps: list[dict[str, list[str]]] = []

    async def __call__(
        self,
        sources: list[Path],
        llm: LLMClient,
        *,
        prune: bool = False,
        limit: int | None = None,
        session: Session | None = None,
        progress: Callable[[str, str, int, int], None] | None = None,
        ignore_by_root: dict[str, list[str]] | None = None,
    ) -> ImportSummary:
        self.sources.append(list(sources))
        self.llms.append(llm)
        self.prune_flags.append(prune)
        self.progress_hooks.append(progress)
        self.ignore_maps.append(ignore_by_root or {})
        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, db: Session, tmp_path: Path
) -> None:
    repo_url = f"file://{tmp_path / 'repo.git'}"
    _seed(db, repo_url)  # the phase-35 resolver picks the DB row up
    _stub_env(monkeypatch)  # env must not matter once the table has a row
    monkeypatch.setattr(
        sync_api,
        "get_settings",
        lambda: _settings(sources_dir=str(tmp_path / "bor")),
    )
    clone_calls, fake_clone = _fake_clone()
    monkeypatch.setattr(sync_api, "clone_or_pull", fake_clone)
    probe_seen = _stub_probe(monkeypatch)  # real LLMClient — probe stubbed
    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,
        # Phase 64 (task 02): the per-file progress keys — null/0/0 idle.
        "current_file": None,
        "files_done": 0,
        "files_total": 0,
    }

    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,
        "sources_version": 1,  # phase 53: changed KB → exactly one bump (0 → 1)
    }
    # The bump committed: the counter advanced exactly once, not twice.
    assert current_sources_version(db) == 1
    # 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)
    # Phase 64 (task 02): the runner wires the per-file progress hook
    # (the live closure the status endpoint reads while the import runs).
    assert len(fake_import.progress_hooks) == 1
    assert callable(fake_import.progress_hooks[0])
    # Overview: refreshed (added + updated > 0) with the same client.
    assert fake_overview.llms == [fake_import.llms[0]]
    # Phase 41: the probe ran first and got the very client the import
    # and the overview reuse.
    assert probe_seen == [fake_import.llms[0]]


def test_unchanged_kb_skips_overview_refresh(
    sync_client: TestClient, monkeypatch: pytest.MonkeyPatch, db: Session, tmp_path: Path
) -> None:
    """Phase-31 trigger is change-gated: added + updated == 0 → no ``lite`` call."""
    repo_url = f"file://{tmp_path / 'repo.git'}"
    _seed(db, repo_url)
    _stub_env(monkeypatch)
    monkeypatch.setattr(
        sync_api,
        "get_settings",
        lambda: _settings(sources_dir=str(tmp_path / "bor")),
    )
    _, fake_clone = _fake_clone()
    monkeypatch.setattr(sync_api, "clone_or_pull", fake_clone)
    _stub_probe(monkeypatch)
    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
    # Phase 53: an unchanged re-sync never bumps — the detail reports
    # the current (unadvanced) generation.
    assert body["detail"]["sources_version"] == 0
    assert current_sources_version(db) == 0


# --- admin: concurrency ----------------------------------------------------


def test_double_trigger_while_running_returns_409(
    sync_client: TestClient, monkeypatch: pytest.MonkeyPatch, db: Session, tmp_path: Path
) -> None:
    repo_url = f"file://{tmp_path / 'repo.git'}"
    _seed(db, repo_url)
    _stub_env(monkeypatch)
    monkeypatch.setattr(
        sync_api,
        "get_settings",
        lambda: _settings(sources_dir=str(tmp_path / "bor")),
    )
    _, fake_clone = _fake_clone()
    monkeypatch.setattr(sync_api, "clone_or_pull", fake_clone)
    _stub_probe(monkeypatch)
    # 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, db: Session, tmp_path: Path
) -> None:
    repo_url = f"file://{tmp_path / 'bad.git'}"
    _seed(db, repo_url)
    _stub_env(monkeypatch)
    monkeypatch.setattr(
        sync_api,
        "get_settings",
        lambda: _settings(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)
    _stub_probe(monkeypatch)
    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 == []
    # Phase 53: a FAILED sync never bumps — the version is untouched.
    assert current_sources_version(db) == 0

    # 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_sources_configured_fails_loudly(
    sync_client: TestClient, monkeypatch: pytest.MonkeyPatch, tmp_path: Path
) -> None:
    """Both origins empty — no git rows, no local rows, no env URLs
    (the truncate fixture + a blank env) → the fail-loud error
    (phase 38: git-only message retired)."""
    # Whitespace-only is just as unconfigured as empty.
    _stub_env(monkeypatch, " , ")
    monkeypatch.setattr(
        sync_api,
        "get_settings",
        lambda: _settings(sources_dir=str(tmp_path / "bor")),
    )
    clone_calls, fake_clone = _fake_clone()
    monkeypatch.setattr(sync_api, "clone_or_pull", fake_clone)
    _stub_probe(monkeypatch)
    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 sources configured (git or local)"
    assert clone_calls == []  # git is never touched
    assert fake_import.sources == []


def test_db_rows_win_over_env(
    sync_client: TestClient,
    monkeypatch: pytest.MonkeyPatch,
    db: Session,
    tmp_path: Path,
    caplog: pytest.LogCaptureFixture,
) -> None:
    """Phase 35: a stored row beats ``BOR_GIT_SOURCES`` — only the DB URL
    is cloned, and the started log names the origin."""
    db_url = "https://db.example.com/managed.git"
    _seed(db, db_url)
    _stub_env(monkeypatch, "https://env.example.com/ignored.git")
    monkeypatch.setattr(
        sync_api,
        "get_settings",
        lambda: _settings(sources_dir=str(tmp_path / "bor")),
    )
    clone_calls, fake_clone = _fake_clone()
    monkeypatch.setattr(sync_api, "clone_or_pull", fake_clone)
    _stub_probe(monkeypatch)
    fake_import = FakeImportSources(ImportSummary(files=1, added=1))
    monkeypatch.setattr(sync_api, "import_sources", fake_import)
    monkeypatch.setattr(sync_api, "regenerate_overview", FakeOverview(ok=True))

    _login(sync_client)
    with caplog.at_level(logging.INFO, logger="app.api.sync"):
        assert sync_client.post("/api/sync").status_code == 202
        body = _poll(sync_client, "success")

    assert clone_calls == [(db_url, tmp_path / "bor" / "managed")]
    assert fake_import.sources == [[tmp_path / "bor" / "managed"]]
    assert "env.example.com" not in str(body)  # the env URL never reaches the UI
    assert any("sync: started repos=1 origin=db" in r.getMessage() for r in caplog.records)


def test_env_fallback_when_table_empty(
    sync_client: TestClient,
    monkeypatch: pytest.MonkeyPatch,
    tmp_path: Path,
    caplog: pytest.LogCaptureFixture,
) -> None:
    """Phase 35: with the table empty (the truncate fixture), the
    ``BOR_GIT_SOURCES`` list is what gets cloned — origin ``env``."""
    env_url = "https://env.example.com/fallback.git"
    _stub_env(monkeypatch, env_url)
    monkeypatch.setattr(
        sync_api,
        "get_settings",
        lambda: _settings(sources_dir=str(tmp_path / "bor")),
    )
    clone_calls, fake_clone = _fake_clone()
    monkeypatch.setattr(sync_api, "clone_or_pull", fake_clone)
    _stub_probe(monkeypatch)
    fake_import = FakeImportSources(ImportSummary(files=1, added=1))
    monkeypatch.setattr(sync_api, "import_sources", fake_import)
    monkeypatch.setattr(sync_api, "regenerate_overview", FakeOverview(ok=True))

    _login(sync_client)
    with caplog.at_level(logging.INFO, logger="app.api.sync"):
        assert sync_client.post("/api/sync").status_code == 202
        _poll(sync_client, "success")

    assert clone_calls == [(env_url, tmp_path / "bor" / "fallback")]
    assert any("sync: started repos=1 origin=env" in r.getMessage() for r in caplog.records)


# --- phase 38: the local kind (real import, host temp dirs) ---------------


def test_local_only_sync_imports_dir(
    sync_client: TestClient,
    monkeypatch: pytest.MonkeyPatch,
    db: Session,
    tmp_path: Path,
    clean_documents: None,
) -> None:
    """Local-only config: the host temp dir (one fixture ``.md``) is
    walked directly — no clone at all — and the file lands in the KB
    (``GET /api/docs`` as admin)."""
    local_dir = tmp_path / "LocalDocs"
    local_dir.mkdir()
    (local_dir / "notes.md").write_text("# Local Notes\nthe local fixture\n", encoding="utf-8")
    _seed_local(db, local_dir)
    _stub_env(monkeypatch)  # env must not matter once the table has a row
    monkeypatch.setattr(
        sync_api,
        "get_settings",
        lambda: _settings(sources_dir=str(tmp_path / "bor")),
    )
    clone_calls, fake_clone = _fake_clone()
    monkeypatch.setattr(sync_api, "clone_or_pull", fake_clone)
    _real_llm(monkeypatch)  # real import_sources, deterministic embeddings

    _login(sync_client)
    assert sync_client.post("/api/sync").status_code == 202
    body = _poll(sync_client, "success")

    assert clone_calls == []  # nothing to clone — local is walked directly
    assert body["detail"]["added"] == 1
    assert body["detail"]["errors"] == 0
    # The local file is in the KB, sourced by the directory's basename.
    docs = sync_client.get("/api/docs").json()["documents"]
    assert [(d["source"], d["path"]) for d in docs] == [("LocalDocs", "notes.md")]


def test_mixed_git_local_sync_imports_both_and_prunes_union(
    sync_client: TestClient,
    monkeypatch: pytest.MonkeyPatch,
    db: Session,
    tmp_path: Path,
    caplog: pytest.LogCaptureFixture,
    clean_documents: None,
) -> None:
    """Mixed config: the git row is cloned, the local dir walked, and
    both are imported in one run over the single combined list. The
    started log carries the kind counts; a file deleted out of the
    local dir is pruned on the next sync (union prune) while the git
    doc survives."""
    repo_url = f"file://{tmp_path / 'repo.git'}"
    _seed(db, repo_url)
    local_dir = tmp_path / "LocalDocs"
    local_dir.mkdir()
    (local_dir / "a.md").write_text("# A\nfirst local file\n", encoding="utf-8")
    (local_dir / "b.md").write_text("# B\nsecond local file\n", encoding="utf-8")
    _seed_local(db, local_dir)
    _stub_env(monkeypatch)
    monkeypatch.setattr(
        sync_api,
        "get_settings",
        lambda: _settings(sources_dir=str(tmp_path / "bor")),
    )
    clone_calls, fake_clone = _fake_clone()
    monkeypatch.setattr(sync_api, "clone_or_pull", fake_clone)
    _real_llm(monkeypatch)

    _login(sync_client)
    with caplog.at_level(logging.INFO, logger="app.api.sync"):
        assert sync_client.post("/api/sync").status_code == 202
        body = _poll(sync_client, "success")

    # Git cloned into BOR_SOURCES_DIR, local dir walked in row order.
    assert clone_calls == [(repo_url, tmp_path / "bor" / "repo")]
    assert body["detail"]["added"] == 3
    assert any(
        "sync: started repos=2 origin=db git=1 local=1" in r.getMessage() for r in caplog.records
    )
    docs = {(d["source"], d["path"]) for d in sync_client.get("/api/docs").json()["documents"]}
    assert docs == {("repo", "notes.md"), ("LocalDocs", "a.md"), ("LocalDocs", "b.md")}

    # Union prune: delete one local file → the next sync prunes exactly
    # it; the git doc (and the surviving local file) stay.
    (local_dir / "b.md").unlink()
    assert sync_client.post("/api/sync").status_code == 202
    body = _poll(sync_client, "success")
    assert body["detail"]["pruned"] == 1
    assert body["detail"]["added"] == 0
    docs = {(d["source"], d["path"]) for d in sync_client.get("/api/docs").json()["documents"]}
    assert docs == {("repo", "notes.md"), ("LocalDocs", "a.md")}


def test_missing_local_dir_fails_loudly_and_imports_nothing(
    sync_client: TestClient, monkeypatch: pytest.MonkeyPatch, db: Session, tmp_path: Path
) -> None:
    """A local row whose directory is gone at sync time (moved/deleted
    since add-time) → ``failed`` naming the path, **zero** import
    attempts — the git row before it in row order was still cloned
    (per-row walk; a clone is not an import)."""
    repo_url = f"file://{tmp_path / 'repo.git'}"
    missing = tmp_path / "Gone"
    db.add(
        GitSource(url=repo_url, kind="git", added_at=datetime(2026, 1, 1, tzinfo=UTC))
    )
    db.add(
        GitSource(url=str(missing), kind="local", path=str(missing),
                  added_at=datetime(2026, 1, 2, tzinfo=UTC))
    )
    db.commit()
    _stub_env(monkeypatch)
    monkeypatch.setattr(
        sync_api,
        "get_settings",
        lambda: _settings(sources_dir=str(tmp_path / "bor")),
    )
    clone_calls, fake_clone = _fake_clone()
    monkeypatch.setattr(sync_api, "clone_or_pull", fake_clone)
    _stub_probe(monkeypatch)
    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 f"local source missing: {missing}" in body["error"]  # the path is named
    assert body["detail"] == {}
    assert clone_calls == [(repo_url, tmp_path / "bor" / "repo")]  # git row walked first
    assert fake_import.sources == []  # no partial import
    assert fake_overview.llms == []


def test_import_error_is_reported_with_credentials_masked(
    sync_client: TestClient, monkeypatch: pytest.MonkeyPatch, db: Session, tmp_path: Path
) -> None:
    repo_url = f"file://{tmp_path / 'repo.git'}"
    _seed(db, repo_url)
    _stub_env(monkeypatch)
    monkeypatch.setattr(
        sync_api,
        "get_settings",
        lambda: _settings(sources_dir=str(tmp_path / "bor")),
    )
    _, fake_clone = _fake_clone()
    monkeypatch.setattr(sync_api, "clone_or_pull", fake_clone)
    _stub_probe(monkeypatch)

    async def failing_import(
        sources: list[Path],
        llm: LLMClient,
        *,
        prune: bool = False,
        limit: int | None = None,
        session: Session | None = None,
        progress: Callable[[str, str, int, int], None] | None = None,
        ignore_by_root: dict[str, list[str]] | 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


# --- phase 41: model probe (fail fast before any clone) --------------------


class _DeadEmbedder:
    """Probe fake whose embedding call dies like a dead endpoint — with a
    credential-bearing URL in the wrapped error (the sanitizer must
    mask it). ``chat`` is recorded: it must never be reached."""

    def __init__(self) -> None:
        self.settings = Settings(_env_file=None)  # pyright: ignore[reportCallIssue]
        self.embed_batches = 0
        self.chat_calls: list[list[dict[str, str]]] = []

    async def embed_one(self, text: str) -> list[float]:
        raise EmbeddingError(
            "embeddings request to https://user:secret@aipi.reeseapps.com/v1 "
            "failed: connection refused"
        )

    async def chat(self, messages: list[dict[str, str]], model: str | None = None) -> str:
        self.chat_calls.append(list(messages))
        return "pong"


def test_model_down_fails_fast_before_any_clone(
    sync_client: TestClient, monkeypatch: pytest.MonkeyPatch, db: Session, tmp_path: Path
) -> None:
    """A dead model endpoint fails the run **before any clone**: the
    model-naming error lands in the ``failed`` state verbatim (the
    sanitizer is a no-op for it), and clone + import never run."""
    repo_url = f"file://{tmp_path / 'repo.git'}"
    _seed(db, repo_url)
    _stub_env(monkeypatch)
    monkeypatch.setattr(
        sync_api,
        "get_settings",
        lambda: _settings(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)
    message = (
        "The embedding model ('embed') is not available — "
        "check the model endpoint and retry."
    )

    async def dead_probe(llm: LLMClient) -> None:
        raise ModelUnavailableError(message)

    monkeypatch.setattr(sync_api, "check_models", dead_probe)

    _login(sync_client)
    assert sync_client.post("/api/sync").status_code == 202

    body = _poll(sync_client, "failed")
    assert body["error"] == message  # the model is named, verbatim
    # The sanitizer must leave the model-naming message untouched.
    assert sync_api._sanitize_error(body["error"]) == body["error"]
    assert body["detail"] == {}
    assert clone_calls == []  # fail fast: before any clone
    assert fake_import.sources == []  # and before any import
    # Phase 53: a FAILED sync (model down) never bumps.
    assert current_sources_version(db) == 0


def test_probe_names_dead_embed_model_and_masks_credentials(
    sync_client: TestClient, monkeypatch: pytest.MonkeyPatch, db: Session, tmp_path: Path
) -> None:
    """The **real** probe against a stubbed dead client: the error names
    the embedding model, and the credentials wrapped from the endpoint
    URL are masked by the sync sanitizer (the reason survives)."""
    repo_url = f"file://{tmp_path / 'repo.git'}"
    _seed(db, repo_url)
    _stub_env(monkeypatch)
    monkeypatch.setattr(
        sync_api,
        "get_settings",
        lambda: _settings(sources_dir=str(tmp_path / "bor")),
    )
    dead = _DeadEmbedder()
    monkeypatch.setattr(sync_api, "LLMClient", lambda: dead)
    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 "The embedding model ('embed') is not available" in body["error"]
    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
    assert dead.chat_calls == []  # embed died first — chat never probed
    assert clone_calls == []
    assert fake_import.sources == []


def test_probe_runs_before_source_resolution(
    sync_client: TestClient, monkeypatch: pytest.MonkeyPatch, tmp_path: Path
) -> None:
    """Ordering: the probe is the **first** pipeline step — it runs
    before ``effective_sources`` (and, transitively, before any
    clone)."""
    order: list[str] = []

    async def spy_probe(llm: LLMClient) -> None:
        order.append("probe")

    def spy_effective_sources(session: Session) -> tuple[list[GitSource], str]:
        order.append("effective_sources")
        raise GitSyncError("short-circuit after the ordering spy")

    monkeypatch.setattr(sync_api, "check_models", spy_probe)
    monkeypatch.setattr(sync_api, "effective_sources", spy_effective_sources)
    monkeypatch.setattr(
        sync_api,
        "get_settings",
        lambda: _settings(sources_dir=str(tmp_path / "bor")),
    )
    clone_calls, fake_clone = _fake_clone()
    monkeypatch.setattr(sync_api, "clone_or_pull", fake_clone)

    _login(sync_client)
    assert sync_client.post("/api/sync").status_code == 202
    body = _poll(sync_client, "failed")

    assert order == ["probe", "effective_sources"]
    assert clone_calls == []
    assert "short-circuit" in body["error"]  # the spy aborted the run


# --- phase 89: per-row ignore lists ------------------------------------------


def test_local_row_ignore_paths_excluded_from_sync(
    sync_client: TestClient,
    monkeypatch: pytest.MonkeyPatch,
    db: Session,
    tmp_path: Path,
    clean_documents: None,
) -> None:
    """Phase 89: a local row carrying ``ignore_paths`` — the button
    sync skips every matching file: the ignored file never lands in the
    KB (no document row — hence no embedding, no summary), and the
    success detail's ``files``/``added`` counts exclude it, while the
    kept file imports as usual."""
    local_dir = tmp_path / "LocalDocs"
    local_dir.mkdir()
    (local_dir / "keep.md").write_text("# Keep\nin scope\n", encoding="utf-8")
    (local_dir / "ignore").mkdir()
    (local_dir / "ignore" / "secret.md").write_text("# Secret\nignored\n",
                                                    encoding="utf-8")
    db.add(
        GitSource(
            url=str(local_dir), kind="local", path=str(local_dir),
            ignore_paths=["ignore/"],  # any spelling — the importer normalizes
        )
    )
    db.commit()
    _stub_env(monkeypatch)
    monkeypatch.setattr(
        sync_api,
        "get_settings",
        lambda: _settings(sources_dir=str(tmp_path / "bor")),
    )
    _real_llm(monkeypatch)  # real import_sources, deterministic embeddings

    _login(sync_client)
    assert sync_client.post("/api/sync").status_code == 202
    body = _poll(sync_client, "success")

    # The ignored file is not counted: only keep.md was walked.
    assert body["detail"]["files"] == 1
    assert body["detail"]["added"] == 1
    assert body["detail"]["errors"] == 0
    # The KB holds exactly the kept file — ignore/secret.md is absent.
    docs = [(d["source"], d["path"]) for d in sync_client.get("/api/docs").json()["documents"]]
    assert docs == [("LocalDocs", "keep.md")]


def test_sync_builds_ignore_map_by_root_string_with_union(
    sync_client: TestClient,
    monkeypatch: pytest.MonkeyPatch,
    db: Session,
    tmp_path: Path,
) -> None:
    """Phase 89 wiring (fake import): the runner keys the map by the
    SAME root string the importer sees, and two rows sharing that root
    string (the sibling/repo-name edge — ``…/shared`` and
    ``…/shared.git`` clone into the same checkout dir) get the UNION
    of their lists, in row order; a row with an empty list contributes
    nothing."""
    url_a = f"file://{tmp_path / 'shared'}"
    url_b = f"{url_a}.git"  # same repo name → same checkout dir
    # Distinct added_at: the resolver orders by (added_at, id) — a
    # same-timestamp pair would tie-break on the random uuid.
    db.add(GitSource(url=url_a, kind="git", ignore_paths=["a/"],
                     added_at=datetime(2026, 1, 1, tzinfo=UTC)))
    db.add(GitSource(url=url_b, kind="git", ignore_paths=["b"],
                     added_at=datetime(2026, 1, 2, tzinfo=UTC)))
    db.commit()
    _stub_env(monkeypatch)
    monkeypatch.setattr(
        sync_api,
        "get_settings",
        lambda: _settings(sources_dir=str(tmp_path / "bor")),
    )
    _, fake_clone = _fake_clone()
    monkeypatch.setattr(sync_api, "clone_or_pull", fake_clone)
    _stub_probe(monkeypatch)
    fake_import = FakeImportSources(ImportSummary(files=1, added=1))
    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
    _poll(sync_client, "success")

    shared = str(tmp_path / "bor" / "shared")
    # Both rows resolve to the SAME checkout (the collision itself) and
    # the map holds their union, keyed by that one root string.
    assert fake_import.sources == [[tmp_path / "bor" / "shared", tmp_path / "bor" / "shared"]]
    assert fake_import.ignore_maps == [{shared: ["a/", "b"]}]


def test_sync_without_ignore_lists_passes_empty_map(
    sync_client: TestClient,
    monkeypatch: pytest.MonkeyPatch,
    db: Session,
    tmp_path: Path,
) -> None:
    """Phase 89 regression: rows without a list → the runner passes an
    EMPTY map (the importer's byte-identical pre-phase-89 behavior)."""
    local_dir = tmp_path / "LocalDocs"
    local_dir.mkdir()
    (local_dir / "notes.md").write_text("# Notes\nplain row\n", encoding="utf-8")
    _seed_local(db, local_dir)  # no ignore_paths → []
    _stub_env(monkeypatch)
    monkeypatch.setattr(
        sync_api,
        "get_settings",
        lambda: _settings(sources_dir=str(tmp_path / "bor")),
    )
    _stub_probe(monkeypatch)
    fake_import = FakeImportSources(ImportSummary(files=1, added=1))
    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
    _poll(sync_client, "success")

    assert fake_import.sources == [[local_dir]]
    assert fake_import.ignore_maps == [{}]  # no row carried a list