FabledScribe/src/scribe/services/record_batch.py

"""Create several records at once, so they can cite each other without guessing ids.

Why this exists is in services/record_refs.py (#4016): a session that needs
records to reference one another used to create them one by one and predict
the ids of the ones not yet made — and any concurrent create, from any session
or any user, took those numbers.

Here the whole batch is ONE transaction: insert every record, flush so the
sequence assigns the real ids, rewrite each `{{ref:N}}` with the id and title
it names, commit. Other sessions keep creating throughout and cannot interfere
— the sequence never hands out the same number twice, so another session's
insert just takes a different one. The ids a batch receives are therefore NOT
guaranteed consecutive, and nothing here needs them to be: the placeholders
are filled with whatever ids came back. Forcing consecutive ids would take a
table lock that stalls every user's writes; nobody needs that.

All or nothing: a bad placeholder, an invalid status, or a failure mid-insert
leaves no partial batch behind — which is also why there are no "reserved"
stub records to clean up after a session that dies.
"""
from __future__ import annotations

from dataclasses import dataclass, field

from sqlalchemy import select

from scribe.models import async_session
from scribe.models.milestone import Milestone
from scribe.models.note import Note
from scribe.services import access as access_svc
from scribe.services import notes as notes_svc
from scribe.services import systems as systems_svc
from scribe.services.record_refs import placeholder_keys, resolve_placeholders

# A batch is a plan's steps or a handful of linked records, and every item runs
# the near-duplicate gate (an embedding search) before the transaction. 50 is
# far past any real plan and keeps one call from becoming a bulk import, which
# is a different job with a different door.
MAX_BATCH = 50


@dataclass
class BatchItem:
    """One record in a batch. `is_task` False makes it a plain note."""

    title: str
    body: str = ""
    is_task: bool = True
    status: str = "todo"
    priority: str | None = None
    task_kind: str = "work"
    tags: list[str] = field(default_factory=list)
    system_ids: list[int] = field(default_factory=list)


@dataclass
class BatchMilestone:
    """The milestone start_planning creates in the same transaction as its steps."""

    title: str
    body: str
    description: str | None = None


def check_batch(items: list[BatchItem], milestone: BatchMilestone | None = None) -> None:
    """Refuse a batch that cannot be written in full, before any write.

    Every placeholder must name something the batch will actually create;
    otherwise the rewrite has nothing to put there, and the alternatives —
    leaving `{{ref:9}}` in a stored body, or dropping it — both store a
    reference that points nowhere.
    """
    if not items and milestone is None:
        raise ValueError("a batch needs at least one record")
    if len(items) > MAX_BATCH:
        raise ValueError(f"a batch holds at most {MAX_BATCH} records; got {len(items)}")
    for i, item in enumerate(items, start=1):
        if not (item.title or "").strip():
            raise ValueError(f"record {i} has no title")
    valid = {str(i) for i in range(1, len(items) + 1)}
    if milestone is not None:
        valid.add("milestone")
    texts = [item.body for item in items] + ([milestone.body] if milestone else [])
    unknown = placeholder_keys(*texts) - valid
    if unknown:
        named = ", ".join("{{ref:%s}}" % k for k in sorted(unknown))
        raise ValueError(
            f"{named} names no record in this batch. {{{{ref:N}}}} is the Nth "
            f"record listed (1 to {len(items)})"
            + (", and {{ref:milestone}} is the milestone being created." if milestone else ".")
        )


async def create_batch(
    user_id: int,
    items: list[BatchItem],
    *,
    project_id: int | None = None,
    milestone_id: int | None = None,
    milestone: BatchMilestone | None = None,
) -> tuple[Milestone | None, list[Note]]:
    """Create `items` (and optionally a new milestone they belong to) atomically.

    `milestone_id` files the items under an EXISTING milestone the caller owns;
    `milestone` creates a new one alongside them and files them there. Passing
    both is refused. Returns (the new milestone or None, the notes in input
    order). Near-duplicate gating is the door's job, exactly as for a single
    create.
    """
    if milestone is not None and milestone_id:
        raise ValueError("pass milestone_id (an existing milestone) or a new milestone, not both")
    check_batch(items, milestone)

    if milestone_id:
        async with async_session() as session:
            existing = (await session.execute(
                select(Milestone).where(
                    Milestone.id == milestone_id, Milestone.deleted_at.is_(None),
                )
            )).scalars().first()
        if existing is None:
            raise ValueError(f"milestone {milestone_id} not found")
        if project_id and project_id != existing.project_id:
            raise ValueError(
                f"milestone {milestone_id} belongs to project {existing.project_id}, not {project_id}"
            )
        project_id = existing.project_id
    if milestone is not None and not project_id:
        raise ValueError("a new milestone needs a project_id")
    # Share-aware (rule 78): a collaborator with write access to a shared
    # project may plan in it; a bare owner filter would refuse them.
    if project_id and not await access_svc.can_write_project(user_id, project_id):
        raise ValueError(f"project {project_id} not found")

    async with async_session() as session:
        # Validate every record before adding any: build_note raises on a bad
        # status/priority, and raising here writes nothing.
        notes = [
            notes_svc.build_note(
                user_id,
                title=item.title,
                body=item.body,
                tags=item.tags,
                project_id=project_id,
                milestone_id=milestone_id,
                status=item.status if item.is_task else None,
                priority=item.priority if item.is_task else None,
                task_kind=notes_svc.minted_kind(item.task_kind) if item.is_task else "work",
            )
            for item in items
        ]

        new_ms = None
        if milestone is not None:
            new_ms = Milestone(
                user_id=user_id, project_id=project_id, title=milestone.title,
                description=milestone.description, body=milestone.body, status="active",
            )
            session.add(new_ms)
            await session.flush()
            for note in notes:
                note.milestone_id = new_ms.id

        session.add_all(notes)
        # The flush is where the sequence assigns ids. Nothing is visible to
        # any other session until the commit below, and if anything between
        # here and there raises, the context manager rolls it all back.
        await session.flush()

        refs = {str(i): f'#{n.id} "{n.title}"' for i, n in enumerate(notes, start=1)}
        if new_ms is not None:
            refs["milestone"] = f'milestone {new_ms.id} "{new_ms.title}"'
            new_ms.body = resolve_placeholders(new_ms.body, refs)
        for note in notes:
            note.body = resolve_placeholders(note.body, refs)

        await session.commit()
        for note in notes:
            await session.refresh(note)
        if new_ms is not None:
            await session.refresh(new_ms)

    # After the commit, as a single create does: embedding and System tags are
    # enrichment on records that now exist, and a failure in either must not
    # un-create them.
    for note, item in zip(notes, items):
        notes_svc.embed_note(note)
        if item.system_ids:
            await systems_svc.set_record_systems(user_id, note.id, item.system_ids)
    if project_id is not None:
        await notes_svc._maybe_reactivate_project(project_id)

    return new_ms, notes