brain-of-reese/tests/unit/test_importer.py

"""Unit tests: importer directory walk + sha256 delta logic + summaries.

The walk tests are pure filesystem (``tmp_path``); the delta and summary
tests run against the local compose Postgres (preferred — a real vector
table), skipping with clear instructions when the stack is not up.

Summaries (phase 30): non-markdown files get a ``lite``-model summary via
the fake's deterministic ``chat`` (``"Summary of <first token>"``); the
sentinel word ``SUMMARY-BLOWUP`` makes ``chat`` raise :class:`LLMError`
for the fail-soft path.
"""
from __future__ import annotations

import asyncio
import logging
from pathlib import Path

import pytest
from sqlalchemy import func, select

from app.config import Settings
from app.models import Chunk, Document
from app.rag.importer import (
    EXCLUDED_DIRS,
    ImportSummary,
    _store_summary,
    import_sources,
    iter_importable_files,
)
from app.rag.llm import EmbeddingError
from tests.fakes import FakeEmbedder

#: The original seven A9 formats as dotted suffixes (pre-phase-47 default
#: set). The phase-47 walk test uses the live config default
#: (``Settings().import_extension_set`` — now seventeen formats).
DEFAULT_EXTS = frozenset({".md", ".markdown", ".txt", ".yaml", ".yml", ".json", ".py"})


class _PoisonEmbedder(FakeEmbedder):
    """Fails (like a real endpoint) on any text containing 'poison'."""

    async def embed(self, texts: list[str]) -> list[list[float]]:
        if any("poison" in t for t in texts):
            raise EmbeddingError("embeddings endpoint refused the input (simulated)")
        return await super().embed(texts)


class _CapEmbedder(FakeEmbedder):
    """Simulates the endpoint's ~1024-token input cap at ~1.1 chars/token:
    any single text over 1000 chars is rejected (URL-dense worst case)."""

    async def embed(self, texts: list[str]) -> list[list[float]]:
        if any(len(t) > 1000 for t in texts):
            raise EmbeddingError(
                "a single 1100-char chunk exceeded the endpoint's per-request "
                "input token cap — lower BOR_CHUNK_TARGET_CHARS and re-import"
            )
        return await super().embed(texts)


def _cleanup_source(db, source: str) -> None:
    for doc in db.scalars(select(Document).where(Document.source == source)).all():
        db.delete(doc)
    db.commit()


def test_iter_importable_files_excludes_noncontent_dirs_and_hidden(tmp_path: Path) -> None:
    """Well-known non-content dirs, hidden (dot-) dirs/files, and non-A9
    extensions are all skipped; the A9 formats pass."""
    root = tmp_path / "proj"
    for d in (
        "notes/sub",
        ".venv/lib",
        "node_modules/x",
        ".git",
        "__pycache__",
        ".pytest_cache",
        "dist",
        "build",
        ".esphome/.espressif",  # vendored hidden cache — the real A9 case
    ):
        (root / d).mkdir(parents=True)
    files = {
        # content that must be found:
        "README.md": "readme",
        "notes/sub/deep.md": "deep",
        "compose.yaml": "services: {}",
        "legacy.YML": "a: b",  # case-insensitive suffix
        "notes/sub/agent.py": "x = 1",
        "config.json": "{}",
        "README.txt": "plain",
        "notes/sub/deep.markdown": "md2",
        # must be skipped:
        ".venv/lib/junk.md": "junk",
        "node_modules/x/j.md": "j",
        ".git/c.md": "g",
        "__pycache__/c.md": "p",
        ".pytest_cache/c.md": "pc",
        "dist/d.md": "d",
        "build/b.md": "b",
        ".esphome/.espressif/secret.md": "vendor",
        ".secret.md": "hidden file",  # dot-prefixed FILE, not just dir
        "notes/sub/notes.csv": "a,b",  # not an A9 format
        "notes/sub/file.md.bak": "x",
    }
    for rel, text in files.items():
        (root / rel).write_text(text)

    found = {p.relative_to(root).as_posix() for p in iter_importable_files(root, DEFAULT_EXTS)}
    assert found == {
        "README.md",
        "notes/sub/deep.md",
        "compose.yaml",
        "legacy.YML",
        "notes/sub/agent.py",
        "config.json",
        "README.txt",
        "notes/sub/deep.markdown",
    }


def test_iter_importable_files_missing_dir_yields_nothing(tmp_path: Path) -> None:
    assert iter_importable_files(tmp_path / "definitely-missing", DEFAULT_EXTS) == []


def test_iter_importable_files_walker_picks_up_new_formats_by_default(
    tmp_path: Path,
) -> None:
    """Phase 47 (A9 revised 2026-08-27): the ten new formats — the full
    quadlet family + j2 — walk under the *default* extension set (no env
    configuration needed), the original seven still walk (regression), and
    unknown/hidden-dir/excluded-dir filtering is unchanged for them."""
    root = tmp_path / "quadproj"
    (root / ".esphome").mkdir(parents=True)
    (root / "node_modules").mkdir()
    files = {
        # the ten new formats (A9 revised 2026-08-27):
        "web.container": "# RESE-QUADLET-SENTINEL-77aa\n[Container]\nImage=alpine\n",
        "lan.network": "[Network]\nDriver=bridge\n",
        "cache.volume": "[Volume]\nDriver=local\n",
        "alpine.image": "[Image]\nImages=alpine\n",
        "app.pod": "[Pod]\nPodName=app\n",
        "k3s.kube": "apiVersion: v1\nkind: Pod\n",
        "zram.swap": "[Swap]\nFile=/swapfile\n",
        "fedora.os": "[OS]\nImage=fedora\n",
        "edge.endpoint": "[Endpoint]\nPort=8080\n",
        "deploy.j2": "{% for s in services %}\n[{{ s }}]\n{% endfor %}\n",
        # the original seven — regression:
        "note.md": "# n\n",
        "note.markdown": "# m\n",
        "note.txt": "t\n",
        "cfg.yaml": "a: b\n",
        "cfg.yml": "a: b\n",
        "data.json": "{}\n",
        "agent.py": "x = 1\n",
        # must be skipped — filtering is unchanged for the new formats too:
        "mystery.xyz": "unknown extension",
        ".esphome/x.container": "hidden dir (new-format file)",
        "node_modules/y.container": "excluded dir (new-format file)",
    }
    for rel, text in files.items():
        (root / rel).write_text(text)
    # The live config default (Settings with no env override) — no
    # BOR_IMPORT_EXTENSIONS needed for the new formats to walk.
    exts = Settings(_env_file=None).import_extension_set  # pyright: ignore[reportCallIssue]
    found = {p.relative_to(root).as_posix() for p in iter_importable_files(root, exts)}
    assert found == {
        # all ten new formats:
        "web.container",
        "lan.network",
        "cache.volume",
        "alpine.image",
        "app.pod",
        "k3s.kube",
        "zram.swap",
        "fedora.os",
        "edge.endpoint",
        "deploy.j2",
        # …and the original seven:
        "note.md",
        "note.markdown",
        "note.txt",
        "cfg.yaml",
        "cfg.yml",
        "data.json",
        "agent.py",
    }


def test_iter_importable_files_respects_custom_extension_filter(tmp_path: Path) -> None:
    """A narrower filter (e.g. md only) excludes the other A9 formats."""
    root = tmp_path / "filtered"
    root.mkdir()
    (root / "a.md").write_text("a")
    (root / "b.yaml").write_text("a: b")
    (root / "c.py").write_text("x = 1")
    found = {p.name for p in iter_importable_files(root, frozenset([".md"]))}
    assert found == {"a.md"}


def test_excluded_dirs_match_plan_anchor_a9() -> None:
    assert {
        ".venv", "node_modules", ".git", "__pycache__", ".pytest_cache", "dist", "build"
    } == EXCLUDED_DIRS


def test_added_then_unchanged_then_updated_then_pruned(db, tmp_path: Path) -> None:
    root = tmp_path / "src"
    root.mkdir()
    (root / "a.md").write_text("# A\n\nalpha\n\n## Sub\n\nmore alpha\n")
    (root / "b.md").write_text("# B\n\nbeta\n")
    llm = FakeEmbedder()
    try:
        s1 = asyncio.run(import_sources([root], llm, session=db))
        assert (s1.files, s1.added, s1.unchanged, s1.updated, s1.pruned) == (2, 2, 0, 0, 0)
        # a.md has two sections (2 chunks), b.md one (1 chunk).
        assert s1.chunks == 3
        # Embeddings are stored with the configured dimension.
        n = db.scalar(
            select(func.count())
            .select_from(Chunk)
            .join(Document, Document.id == Chunk.document_id)
            .where(Document.source == root.name)
        )
        assert n == 3
        for c in db.scalars(
            select(Chunk)
            .join(Document, Document.id == Chunk.document_id)
            .where(Document.source == root.name)
        ).all():
            assert c.embedding is not None and len(c.embedding) == 768

        s2 = asyncio.run(import_sources([root], llm, session=db))
        assert s2.added == 0 and s2.unchanged == 2

        (root / "a.md").write_text("# A\n\nalpha CHANGED\n")
        s3 = asyncio.run(import_sources([root], llm, session=db))
        assert s3.updated == 1 and s3.unchanged == 1
        doc = db.scalar(
            select(Document).where(Document.source == root.name, Document.path == "a.md")
        )
        assert doc is not None and "CHANGED" in doc.content

        (root / "a.md").unlink()
        s4 = asyncio.run(import_sources([root], llm, session=db, prune=True))
        assert s4.pruned == 1
        assert db.scalar(
            select(Document).where(Document.source == root.name, Document.path == "a.md")
        ) is None
        # Chunks of the pruned document are gone (FK cascade).
        n_after = db.scalar(
            select(func.count())
            .select_from(Chunk)
            .join(Document, Document.id == Chunk.document_id)
            .where(Document.source == root.name)
        )
        assert n_after == 1
    finally:
        _cleanup_source(db, root.name)


def test_embedding_failure_is_logged_and_import_continues(db, tmp_path: Path) -> None:
    """A file the embedding endpoint refuses must not abort the whole KB:
    its rows are rolled back, the error is counted, and other files import."""
    root = tmp_path / "mixed"
    root.mkdir()
    (root / "bad.md").write_text("# Bad\n\npoison content that the endpoint refuses\n")
    (root / "good.md").write_text("# Good\n\nperfectly fine content\n")
    try:
        summary = asyncio.run(import_sources([root], _PoisonEmbedder(), session=db))
        assert summary.files == 2
        assert summary.errors == 1
        assert summary.added == 1  # only good.md
        # bad.md left no row and no orphan chunks behind (rolled back).
        assert db.scalar(
            select(Document).where(Document.source == root.name, Document.path == "bad.md")
        ) is None
        assert db.scalar(
            select(func.count())
            .select_from(Chunk)
            .join(Document, Document.id == Chunk.document_id)
            .where(Document.source == root.name, Document.path == "bad.md")
        ) == 0
        assert db.scalar(
            select(Document).where(Document.source == root.name, Document.path == "good.md")
        ) is not None
    finally:
        _cleanup_source(db, root.name)


def test_oversized_chunk_triggers_adaptive_rechunk(db, tmp_path: Path) -> None:
    """A URL-dense paragraph the endpoint rejects must be re-chunked smaller
    for that file only — the import still succeeds."""
    root = tmp_path / "dense"
    root.mkdir()
    # One ~1165-char paragraph: under the 1200-char hard cap, over the
    # simulated token cap. The retry at 600 chars must split it.
    para = "see https://example.com/" + "a" * 1100
    (root / "dense.md").write_text(f"# D\n\n{para}\n")
    try:
        summary = asyncio.run(import_sources([root], _CapEmbedder(), session=db))
        assert summary.errors == 0
        assert summary.added == 1
        doc = db.scalar(
            select(Document).where(Document.source == root.name, Document.path == "dense.md")
        )
        assert doc is not None
        assert len(doc.chunks) >= 2  # re-chunked smaller than the hard cap
        assert all(len(c.content) <= 1000 for c in doc.chunks)
        assert all(c.embedding is not None for c in doc.chunks)
        # The content survives the split.
        assert "".join(c.content for c in doc.chunks).count("a" * 500) >= 1
    finally:
        _cleanup_source(db, root.name)


def test_missing_source_dir_is_skipped(db, tmp_path: Path) -> None:
    llm = FakeEmbedder()
    summary = asyncio.run(import_sources([tmp_path / "missing"], llm, session=db))
    assert summary.files == 0 and summary.added == 0


def test_limit_caps_files_and_disables_prune(db, tmp_path: Path) -> None:
    root = tmp_path / "limited"
    root.mkdir()
    for name in ("a.md", "b.md", "c.md"):
        (root / name).write_text(f"# {name}\n\nbody {name}\n")
    llm = FakeEmbedder()
    try:
        summary = asyncio.run(import_sources([root], llm, limit=2, session=db, prune=True))
        assert summary.files == 2 and summary.added == 2
        # c.md was never walked, so it must NOT be pruned (prune disabled
        # under --limit) — and nothing else disappears either.
        assert summary.pruned == 0
        assert db.scalar(
            select(func.count()).select_from(Document).where(Document.source == root.name)
        ) == 2
    finally:
        _cleanup_source(db, root.name)


def test_limit_must_be_positive(db, tmp_path: Path) -> None:
    with pytest.raises(ValueError):
        asyncio.run(import_sources([tmp_path], FakeEmbedder(), limit=0, session=db))


def test_prune_is_scoped_to_the_given_sources(db, tmp_path: Path) -> None:
    src_x = tmp_path / "SourceX"
    src_y = tmp_path / "SourceY"
    src_x.mkdir()
    src_y.mkdir()
    (src_x / "x.md").write_text("# X\n\nx body\n")
    (src_y / "y.md").write_text("# Y\n\ny body\n")
    llm = FakeEmbedder()
    try:
        asyncio.run(import_sources([src_x, src_y], llm, session=db))
        # Re-import ONLY source Y (y.md removed) with prune: source X's doc
        # must survive — prune never touches sources not passed to this run.
        (src_y / "y.md").unlink()
        summary = asyncio.run(import_sources([src_y], llm, session=db, prune=True))
        assert summary.pruned == 1
        assert db.scalar(
            select(Document).where(Document.source == "SourceX", Document.path == "x.md")
        ) is not None
    finally:
        _cleanup_source(db, "SourceX")
        _cleanup_source(db, "SourceY")


def test_chunk_positions_and_titles(db, tmp_path: Path) -> None:
    root = tmp_path / "titled"
    root.mkdir()
    (root / "multi.md").write_text("# Real Title\n\n## One\n\na\n\n## Two\n\nb\n")
    (root / "noh1.md").write_text("## Only heading\n\nbody\n")
    llm = FakeEmbedder()
    try:
        asyncio.run(import_sources([root], llm, session=db))
        titles = {
            d.path: d.title
            for d in db.scalars(select(Document).where(Document.source == root.name)).all()
        }
        assert titles["multi.md"] == "Real Title"  # H1 wins
        assert titles["noh1.md"] == "noh1"  # …else the file stem
        doc = db.scalar(
            select(Document).where(Document.source == root.name, Document.path == "multi.md")
        )
        assert doc is not None
        positions = sorted(c.position for c in doc.chunks)
        assert positions == list(range(len(doc.chunks))) and len(doc.chunks) >= 2
    finally:
        _cleanup_source(db, root.name)


def test_multi_format_import_counts_per_format_and_titles_stem(db, tmp_path: Path) -> None:
    """A9 formats all import; the summary records per-format counts, and
    non-markdown titles come from the file stem (a ``#`` line is a comment
    there, not a heading)."""
    root = tmp_path / "multi"
    (root / "svc").mkdir(parents=True)
    (root / "guide.md").write_text("# Real Heading\n\nbody\n")
    (root / "svc" / "compose.yaml").write_text("# a comment\nservices:\n  gitlab: {}\n")
    (root / "svc" / "agent.py").write_text("# docstring-like comment\ndef ping():\n    return 1\n")
    (root / "inventory.json").write_text('{"hosts": []}\n')
    (root / "notes.txt").write_text("plain text notes\n")
    llm = FakeEmbedder()
    try:
        summary = asyncio.run(import_sources([root], llm, session=db))
        assert summary.files == 5
        assert summary.added == 5
        assert summary.formats == {"md": 1, "yaml": 1, "py": 1, "json": 1, "txt": 1}
        # PLAN §9 summary line: counts, highest first, ext:name pairs.
        assert summary.format_counts() == "json:1,md:1,py:1,txt:1,yaml:1"

        titles = {
            d.path: d.title
            for d in db.scalars(select(Document).where(Document.source == root.name)).all()
        }
        assert titles["guide.md"] == "Real Heading"  # markdown keeps the H1
        assert titles["svc/compose.yaml"] == "compose"  # …comment is not a heading
        assert titles["svc/agent.py"] == "agent"
        assert titles["inventory.json"] == "inventory"
        assert titles["notes.txt"] == "notes"
    finally:
        _cleanup_source(db, root.name)


def test_quadlet_and_j2_files_get_stem_titles_and_per_format_counts(
    db, tmp_path: Path
) -> None:
    """Phase 47: the ten new formats import like any other A9 format — the
    per-format counts land in the summary, every file yields content
    chunks, and a leading ``#`` line (a TOML comment in quadlet files, not
    a heading) never becomes the title: the file stem wins."""
    root = tmp_path / "quadsrc"
    (root / "quadlet").mkdir(parents=True)
    (root / "tpl").mkdir(parents=True)
    (root / "quadlet" / "web.container").write_text(
        "# RESE-QUADLET-SENTINEL-77aa\n\n[Container]\nImage=alpine\n"
    )
    (root / "quadlet" / "lan.network").write_text("# net\n[Network]\nDriver=bridge\n")
    (root / "quadlet" / "cache.volume").write_text("[Volume]\nDriver=local\n")
    (root / "quadlet" / "alpine.image").write_text("[Image]\nImages=alpine\n")
    (root / "quadlet" / "app.pod").write_text("[Pod]\nPodName=app\n")
    (root / "quadlet" / "k3s.kube").write_text("apiVersion: v1\nkind: Pod\n")
    (root / "quadlet" / "zram.swap").write_text("[Swap]\nFile=/swapfile\n")
    (root / "quadlet" / "fedora.os").write_text("[OS]\nImage=fedora\n")
    (root / "quadlet" / "edge.endpoint").write_text("[Endpoint]\nPort=8080\n")
    (root / "tpl" / "deploy.j2").write_text(
        "{% for s in services %}\n[{{ s }}]\nport = {{ s.port }}\n{% endfor %}\n"
    )
    llm = FakeEmbedder()
    try:
        summary = asyncio.run(import_sources([root], llm, session=db))
        assert summary.files == 10 and summary.added == 10
        assert summary.formats == {
            "container": 1, "network": 1, "volume": 1, "image": 1, "pod": 1,
            "kube": 1, "swap": 1, "os": 1, "endpoint": 1, "j2": 1,
        }
        docs = {
            d.path: d
            for d in db.scalars(select(Document).where(Document.source == root.name)).all()
        }
        titles = {p: d.title for p, d in docs.items()}
        assert titles == {
            # the ``#`` line is a comment in these formats — stem titles:
            "quadlet/web.container": "web",
            "quadlet/lan.network": "lan",
            "quadlet/cache.volume": "cache",
            "quadlet/alpine.image": "alpine",
            "quadlet/app.pod": "app",
            "quadlet/k3s.kube": "k3s",
            "quadlet/zram.swap": "zram",
            "quadlet/fedora.os": "fedora",
            "quadlet/edge.endpoint": "edge",
            "tpl/deploy.j2": "deploy",
        }
        for doc in docs.values():
            content = [c for c in doc.chunks if not c.is_summary]
            assert content  # every new-format file yields content chunks
            assert all(c.embedding is not None and len(c.embedding) == 768 for c in content)
    finally:
        _cleanup_source(db, root.name)


# ---------- phase 30: lite-model summaries for non-markdown files ----------


def test_non_markdown_file_gets_stored_and_indexed_summary(db, tmp_path: Path) -> None:
    """A ``.yaml`` file is summarized: ``documents.summary`` is set and one
    ``is_summary`` chunk (position −1, embedded) is indexed alongside the
    content chunks."""
    root = tmp_path / "sumsrc"
    root.mkdir()
    (root / "svc.yaml").write_text("alpha services:\n  gitlab:\n    port: 8929\n")
    llm = FakeEmbedder()
    try:
        summary = asyncio.run(import_sources([root], llm, session=db))
        assert summary.added == 1
        assert summary.summaries == 1
        assert summary.summary_errors == 0
        doc = db.scalar(
            select(Document).where(Document.source == root.name, Document.path == "svc.yaml")
        )
        assert doc is not None
        assert doc.summary is not None
        # Deterministic fake reply + the code-appended pointer line.
        assert doc.summary.startswith("Summary of alpha")
        assert doc.summary.endswith(f"Source: {root.name}/svc.yaml")
        schunks = [c for c in doc.chunks if c.is_summary]
        assert len(schunks) == 1
        assert schunks[0].position == -1
        assert schunks[0].content == doc.summary
        assert schunks[0].embedding is not None and len(schunks[0].embedding) == 768
        # Content chunks stay 0-based and are never flagged as summaries.
        content = [c for c in doc.chunks if not c.is_summary]
        assert sorted(c.position for c in content) == list(range(len(content)))
    finally:
        _cleanup_source(db, root.name)


def test_markdown_file_never_gets_summary(db, tmp_path: Path) -> None:
    """Markdown is already natural language: no summary, no ``is_summary``
    chunk, and the ``lite`` model is never called."""
    root = tmp_path / "mdsrc"
    root.mkdir()
    (root / "note.md").write_text("# Note\n\nmarkdown body\n")
    llm = FakeEmbedder()
    try:
        summary = asyncio.run(import_sources([root], llm, session=db))
        assert summary.added == 1
        assert summary.summaries == 0 and summary.summary_errors == 0
        assert llm.chat_calls == []  # the model was never asked
        doc = db.scalar(
            select(Document).where(Document.source == root.name, Document.path == "note.md")
        )
        assert doc is not None
        assert doc.summary is None
        assert doc.chunks and all(not c.is_summary for c in doc.chunks)
    finally:
        _cleanup_source(db, root.name)


def test_summary_failure_is_fail_soft(db, tmp_path: Path) -> None:
    """A ``lite``-model failure must never lose the document: the file is
    fully indexed (content chunks + embeddings), ``documents.summary`` stays
    NULL, and the failure is counted in ``summary_errors``."""
    root = tmp_path / "blowup"
    root.mkdir()
    (root / "bad.txt").write_text("SUMMARY-BLOWUP the lite model chokes on this\n")
    llm = FakeEmbedder()
    try:
        summary = asyncio.run(import_sources([root], llm, session=db))
        assert summary.errors == 0  # the document itself imported fine
        assert summary.added == 1
        assert summary.summaries == 0
        assert summary.summary_errors == 1
        doc = db.scalar(
            select(Document).where(Document.source == root.name, Document.path == "bad.txt")
        )
        assert doc is not None
        assert doc.summary is None
        assert len(doc.chunks) == 1
        assert doc.chunks[0].embedding is not None  # content chunk embedded
        assert all(not c.is_summary for c in doc.chunks)
    finally:
        _cleanup_source(db, root.name)


def test_summary_chunk_is_replaced_on_reimport(db, tmp_path: Path) -> None:
    """Re-importing a changed non-markdown file keeps exactly one
    ``is_summary`` chunk — the old one is gone, the new summary is stored
    and embedded, and the content chunks stay 0-based."""
    root = tmp_path / "repl"
    root.mkdir()
    path = root / "cfg.yaml"
    path.write_text("alpha settings:\n  host: one\n")
    llm = FakeEmbedder()
    try:
        asyncio.run(import_sources([root], llm, session=db))
        path.write_text("bravo settings:\n  host: two\n")
        summary = asyncio.run(import_sources([root], llm, session=db))
        assert summary.updated == 1
        assert summary.summaries == 1 and summary.summary_errors == 0
        doc = db.scalar(
            select(Document).where(Document.source == root.name, Document.path == "cfg.yaml")
        )
        assert doc is not None
        assert doc.summary is not None and doc.summary.startswith("Summary of bravo")
        schunks = [c for c in doc.chunks if c.is_summary]
        assert len(schunks) == 1  # the old one was deleted
        assert schunks[0].position == -1
        assert schunks[0].content == doc.summary
        assert schunks[0].embedding is not None
        assert "alpha" not in schunks[0].content  # no stale summary text
        assert sorted(c.position for c in doc.chunks if not c.is_summary) == [0]
    finally:
        _cleanup_source(db, root.name)


def test_store_summary_replaces_an_existing_summary_chunk(db, tmp_path: Path) -> None:
    """Replacement unit, driven directly: with a pre-existing
    ``is_summary`` chunk in place, ``_store_summary`` deletes the old one
    and leaves exactly one (new) summary chunk + updated
    ``documents.summary`` — the at-most-one-summary invariant."""
    root = tmp_path / "direct"
    root.mkdir()
    (root / "a.yaml").write_text("alpha x\n")
    llm = FakeEmbedder()
    try:
        asyncio.run(import_sources([root], llm, session=db))
        doc = db.scalar(
            select(Document).where(Document.source == root.name, Document.path == "a.yaml")
        )
        assert doc is not None and doc.summary is not None
        assert any(c.is_summary for c in doc.chunks)  # the first import's summary
        counters = ImportSummary()
        asyncio.run(
            _store_summary(
                session=db, doc=doc, source=root.name, rel="a.yaml",
                content=doc.content, llm=llm, summary=counters,
            )
        )
        assert counters.summaries == 1 and counters.summary_errors == 0
        schunks = [c for c in doc.chunks if c.is_summary]
        assert len(schunks) == 1  # the old one was deleted
        assert schunks[0].position == -1
        assert schunks[0].content == doc.summary
        assert schunks[0].embedding is not None
    finally:
        _cleanup_source(db, root.name)


def test_store_summary_fail_soft_leaves_document_untouched(db, tmp_path: Path) -> None:
    """A ``lite`` failure inside ``_store_summary`` rolls back only the
    summary rows: the previous summary (if any) and the document survive,
    and the failure is counted."""
    root = tmp_path / "directfail"
    root.mkdir()
    (root / "a.yaml").write_text("alpha x\n")
    llm = FakeEmbedder()
    try:
        asyncio.run(import_sources([root], llm, session=db))
        doc = db.scalar(
            select(Document).where(Document.source == root.name, Document.path == "a.yaml")
        )
        assert doc is not None and doc.summary is not None
        previous_summary = doc.summary
        (root / "a.yaml").write_text("SUMMARY-BLOWUP now the lite model fails\n")
        counters = ImportSummary()
        asyncio.run(
            _store_summary(
                session=db, doc=doc, source=root.name, rel="a.yaml",
                content="SUMMARY-BLOWUP now the lite model fails\n",
                llm=llm, summary=counters,
            )
        )
        assert counters.summaries == 0 and counters.summary_errors == 1
        assert doc.summary == previous_summary  # rolled back, not nulled
        schunks = [c for c in doc.chunks if c.is_summary]
        assert len(schunks) == 1  # the old one survived the rollback
        assert schunks[0].content == previous_summary
    finally:
        _cleanup_source(db, root.name)


def test_import_summary_log_line_includes_summary_counters(
    caplog: pytest.LogCaptureFixture,
) -> None:
    """PLAN §9 summary line: the phase-30 counters sit between
    ``embed_batches`` and ``formats``."""
    s = ImportSummary()
    s.files, s.added, s.chunks, s.embed_batches = 3, 3, 5, 4
    s.summaries, s.summary_errors = 2, 1
    s.formats = {"md": 1, "yaml": 2}
    with caplog.at_level(logging.INFO, logger="app.importer"):
        s.log()
    line = caplog.records[-1].getMessage()
    assert line == (
        "import: summary files=3 added=3 updated=0 unchanged=0 pruned=0 errors=0 "
        "chunks=5 embed_batches=4 summaries=2 summary_errors=1 formats=yaml:2,md:1"
    )


def test_prune_removes_files_now_excluded_by_format_filter(db, tmp_path: Path) -> None:
    """Previously-imported junk leaves the index: a file that no longer
    matches the A9 extension filter is pruned on the next ``prune=True`` run.
    This is how dot-dir READMEs imported before the scope fix get cleaned up."""
    root = tmp_path / "cleanup"
    root.mkdir()
    (root / "keep.md").write_text("# Keep\n\nkept\n")
    (root / "junk.md.bak").write_text("old junk that was once imported\n")
    llm = FakeEmbedder()
    try:
        # Seed: import both files as if they were valid at the time.
        (root / "junk.md").write_text("old junk that was once imported\n")
        (root / "junk.md.bak").unlink()
        asyncio.run(import_sources([root], llm, session=db))
        # Rename the junk out of the A9 formats, then prune.
        (root / "junk.md").rename(root / "junk.md.bak")
        summary = asyncio.run(import_sources([root], llm, session=db, prune=True))
        assert summary.pruned == 1
        assert summary.unchanged == 1  # keep.md survived
        assert db.scalar(
            select(Document).where(Document.source == root.name, Document.path == "junk.md")
        ) is None
        assert db.scalar(
            select(Document).where(Document.source == root.name, Document.path == "keep.md")
        ) is not None
    finally:
        _cleanup_source(db, root.name)