"""Systems become findable by meaning — the charter as an ANSWER (#4251).

A System's `description` is a charter: several hundred words saying what
belongs in that area and what does not. It is the answer to "where does this
go?", and there was no semantic path to it — `list_systems` enumerates and
`search(system_id=…)` uses a System as a FILTER over notes, so a System could
narrow a search and could never be the answer to one.

These pin the three halves: the document shape, the search's scoping and
best-chunk contract, and that a charter edited through any door is re-indexed.
"""
from unittest.mock import AsyncMock, MagicMock, patch

import pytest

from scribe.services import embeddings as emb
from scribe.services import systems as systems_svc
from tests.helpers import make_mock_session


def _system(system_id=3, name="Retrieval & recall", description="the charter"):
    s = MagicMock(id=system_id, project_id=2, description=description)
    s.name = name          # never via the constructor — see note #2833
    return s


# --- the document shape ------------------------------------------------------


def test_the_document_is_the_name_and_the_charter():
    assert emb.system_document("Retrieval", "what belongs here") == (
        "Retrieval", "what belongs here"
    )


def test_a_system_with_no_charter_yet_degrades_to_its_name():
    """It still embeds, just weakly. That is an argument for writing the
    charter, not for padding the document with whatever is to hand."""
    assert emb.system_document("Retrieval", None) == ("Retrieval", None)
    assert emb.system_document("Retrieval", "   ") == ("Retrieval", None)
    assert emb.chunk_document(*emb.system_document("Retrieval", None)) == ["Retrieval"]


def test_an_empty_system_produces_no_document_at_all():
    """Callers gate on falsiness to clear vectors rather than embed nothing."""
    assert emb.system_document("", "") == (None, None)
    assert emb.chunk_document(*emb.system_document("", "")) == []


# --- the search --------------------------------------------------------------


def _rows_ctx(rows):
    session = MagicMock()
    result = MagicMock()
    result.all.return_value = rows
    session.execute = AsyncMock(return_value=result)
    ctx = MagicMock()
    ctx.__aenter__ = AsyncMock(return_value=session)
    ctx.__aexit__ = AsyncMock(return_value=False)
    return session, ctx


@pytest.mark.asyncio
async def test_the_search_collapses_to_best_chunk_and_reports_which_one_won():
    """A charter is long, and a result shows its NAME — so the paragraph that
    actually decides where a record belongs has to come back with it, or the
    caller judges from two words that cannot say (#4243). Published from the
    start here rather than retrofitted, which is what #4251 asked for."""
    a, b = _system(3), _system(4, name="Data Model")
    rows = [
        (a, 0.10, 2, "retrieval telemetry belongs here"),
        (b, 0.22, 0, "the persistence layer"),
        (a, 0.40, 0, "a weaker paragraph of the same charter"),
    ]
    _session, ctx = _rows_ctx(rows)
    report: dict = {}
    with (
        patch.object(emb, "async_session", return_value=ctx),
        patch.object(emb, "get_embedding", AsyncMock(return_value=[0.0] * 384)),
        patch.object(emb, "can_read_project", AsyncMock(return_value=True)),
    ):
        out = await emb.semantic_search_systems(
            7, "where does telemetry go?",
            project_id=2, threshold=0.0, report=report,
        )

    assert [s.id for _score, s in out] == [3, 4]
    assert out[0][0] == 1.0 - 0.10          # the BEST chunk's score
    assert report["best_chunk"][3] == {
        "index": 2, "text": "retrieval telemetry belongs here",
    }


@pytest.mark.asyncio
async def test_a_project_the_caller_cannot_read_returns_nothing():
    """Rule 78 — the charter of a project someone was not given is not an
    answer to any question they are entitled to ask."""
    _session, ctx = _rows_ctx([])
    with (
        patch.object(emb, "async_session", return_value=ctx),
        patch.object(emb, "get_embedding", AsyncMock(return_value=[0.0] * 384)),
        patch.object(emb, "can_read_project", AsyncMock(return_value=False)),
    ):
        assert await emb.semantic_search_systems(7, "q", project_id=99) == []


@pytest.mark.asyncio
async def test_an_empty_query_never_reaches_the_embedder():
    with patch.object(emb, "get_embedding", AsyncMock()) as embed:
        assert await emb.semantic_search_systems(7, "   ") == []
    embed.assert_not_awaited()


@pytest.mark.asyncio
async def test_a_search_that_fails_returns_nothing_rather_than_raising():
    """A recall aid must never break the call it serves."""
    with patch.object(emb, "get_embedding", AsyncMock(side_effect=RuntimeError)):
        assert await emb.semantic_search_systems(7, "q") == []


# --- staying current ---------------------------------------------------------


@pytest.mark.asyncio
async def test_creating_a_system_indexes_its_charter():
    session = make_mock_session()
    with (
        patch.object(systems_svc, "async_session", return_value=session),
        patch.object(systems_svc.access, "can_write_project", AsyncMock(return_value=True)),
        patch.object(systems_svc, "embed_system") as embed,
    ):
        await systems_svc.create_system(7, 2, "Retrieval", description="the charter")
    embed.assert_called_once()


@pytest.mark.asyncio
async def test_editing_a_charter_re_indexes_it():
    """A charter edited and not re-indexed stays findable by what it used to
    say — the stale-vector case, and the one that matters most for a record
    whose whole job is to say where things belong now."""
    system = _system()
    session = make_mock_session()
    session.get = AsyncMock(return_value=system)
    system.deleted_at = None
    with (
        patch.object(systems_svc, "async_session", return_value=session),
        patch.object(systems_svc.access, "can_write_project", AsyncMock(return_value=True)),
        patch.object(systems_svc, "embed_system") as embed,
    ):
        await systems_svc.update_system(7, 3, description="a new charter")
    embed.assert_called_once_with(system)


def test_embedding_a_system_never_breaks_the_write_that_saved_it():
    """A System that saved must not fail on its index refresh. ValueError
    rather than RuntimeError deliberately: RuntimeError is also what "no
    running loop" raises, which is an ordinary sync caller and has its own
    branch — this has to land in the general swallow to prove it exists."""
    with patch(
        "scribe.services.embeddings.upsert_system_embedding",
        side_effect=ValueError("boom"),
    ):
        systems_svc.embed_system(_system())   # returns quietly, does not raise