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

"""Unit tests: SQLAlchemy models register the pgvector schema on the metadata.

Importing :mod:`app.models` is what Alembic's ``env.py`` and the runtime rely
on; these tests lock the table/column contract (PLAN §5) without a live DB.
"""
from __future__ import annotations

from pgvector.sqlalchemy import Vector
from sqlalchemy import TextClause, UniqueConstraint
from sqlalchemy.sql.schema import DefaultClause

import app.models  # noqa: F401  (import registers all tables on Base.metadata)
from app.db import Base


def test_all_tables_registered() -> None:
    tables = Base.metadata.tables
    assert "documents" in tables
    assert "chunks" in tables
    assert "query_log" in tables


def test_chunks_embedding_is_vector_768() -> None:
    chunks = Base.metadata.tables["chunks"]
    col = chunks.c["embedding"]
    assert isinstance(col.type, Vector)
    assert col.type.dim == 768
    # Embeddings are two-phase: inserted first, embedded later.
    assert col.nullable is True


def test_chunks_reference_documents_cascade() -> None:
    chunks = Base.metadata.tables["chunks"]
    fkc = list(chunks.foreign_key_constraints)[0]
    assert fkc.elements[0].column.table.name == "documents"
    assert fkc.ondelete == "CASCADE"


def test_documents_unique_source_path() -> None:
    documents = Base.metadata.tables["documents"]
    uq = [
        c
        for c in documents.constraints
        if isinstance(c, UniqueConstraint)
        and {col.name for col in c.columns} == {"source", "path"}
    ]
    assert uq, "documents must be unique on (source, path) — the upsert key"


def test_doc_drafts_token_is_unique_not_null() -> None:
    """Phase 59: the draft's URL credential — an unguessable uuid4,
    UNIQUE + NOT NULL (no "un-drafted" state, unlike the NULLable
    ``saved_chats.share_token``)."""
    drafts = Base.metadata.tables["doc_drafts"]
    token = drafts.c["token"]
    assert token.nullable is False, "doc_drafts.token must be NOT NULL"
    uq = [
        c
        for c in drafts.constraints
        if isinstance(c, UniqueConstraint)
        and {col.name for col in c.columns} == {"token"}
    ]
    assert uq, "doc_drafts must be unique on (token) — the URL credential"


def test_git_sources_ignore_paths_column_contract() -> None:
    """Phase 89: every source row carries its ignore list — JSONB, NOT
    NULL, server default ``'[]'`` (a pre-phase-89 row reads ``[]``, so
    every existing source imports exactly as before)."""
    sources = Base.metadata.tables["git_sources"]
    assert "ignore_paths" in sources.c, (
        "git_sources must have the ignore_paths column (phase 89)"
    )
    col = sources.c["ignore_paths"]
    assert col.nullable is False, "git_sources.ignore_paths must be NOT NULL"
    sd = col.server_default
    assert isinstance(sd, DefaultClause), "ignore_paths needs a server default"
    assert isinstance(sd.arg, TextClause), (
        "the server default must be the literal SQL text '[]'"
    )
    assert sd.arg.text == "'[]'", "ignore_paths server default must be '[]'"


def test_git_source_python_default_empty_list() -> None:
    """A freshly constructed row (no DB) resolves to an empty ignore
    list via the Python-side default (``default=list``) — the ORM
    INSERT-time default, so an ORM insert that omits the column inserts
    ``[]`` rather than NULL (the server default ``'[]'`` independently
    covers non-ORM inserts)."""
    from app.models import GitSource

    row = GitSource(url="https://example.com/r.git", kind="git")
    col = row.__table__.c["ignore_paths"]
    assert col.default is not None, (
        "ignore_paths needs a Python-side (INSERT-time) default"
    )
    # Invoked with the (unused) execution context at INSERT time — a
    # freshly constructed row that omits the kwarg stores [] rather
    # than NULL (the real-DB behaviour is pinned against the dev DB
    # by the git-sources API integration tests).
    assert col.default.arg(None) == [], "the default must resolve to []"


def test_doc_drafts_column_contract() -> None:
    """Phase 59: the editable triple (title/path/body) + status +
    timestamps are NOT NULL; ``branch`` / ``commit_sha`` are NULL
    until the push endpoint records them."""
    drafts = Base.metadata.tables["doc_drafts"]
    assert set(drafts.c.keys()) == {
        "id", "token", "title", "path", "body", "status",
        "branch", "commit_sha", "created_at", "updated_at",
    }
    for name in ("title", "path", "body", "status", "created_at", "updated_at"):
        assert drafts.c[name].nullable is False, f"{name} must be NOT NULL"
    for name in ("branch", "commit_sha"):
        assert drafts.c[name].nullable is True, f"{name} must be NULL until pushed"
    assert drafts.c["status"].default is not None, "status needs an ORM default (draft)"
    assert drafts.c["token"].default is not None, "token needs an ORM default (uuid4)"