FabledScribe/src/scribe/services/task_logs.py

"""Task work log service."""
import logging
from datetime import datetime, timezone

from sqlalchemy import func, select

from scribe.models import async_session
from scribe.models.task_log import TaskLog
from scribe.models.note import Note, TaskStatus
from scribe.services.access import can_read_note, can_write_note, readable_notes_clause
from scribe.services.task_claims import stamp_claim

logger = logging.getLogger(__name__)

_UNSET = object()


async def _refresh_task_document(session, task_id: int) -> None:
    """Re-embed the task whose work log just changed (#4251).

    A task's embedded document carries its logs, so a log written and not
    indexed is #4241's half-surface wearing different clothes: the entry is
    readable and unfindable, and the next session rebuilds what this one ruled
    out. Create, edit and delete all go through here — an edited log that keeps
    matching its old wording is the stale-vector problem `upsert_note_embedding`
    already refuses to leave behind for a body.

    Loads the NOTE rather than synthesising one. `embed_note` reads
    `title`, `body` and the OWNER's `user_id` off what it is handed, so a
    stand-in row would index the logs under an empty title — throwing away the
    per-chunk topical anchor that makes any of this discriminative — and file
    the vectors under the wrong user.

    Failure is swallowed the way `embed_note`'s own is: a log that saved must
    not fail on its index refresh. The startup backfill is the backstop.
    """
    from scribe.services.notes import embed_note

    try:
        result = await session.execute(select(Note).where(Note.id == task_id))
        note = result.scalars().first()
        if note is not None:
            embed_note(note)
    except Exception:  # noqa: BLE001 - indexing never breaks a write
        logger.exception("embedding refresh failed for task %s", task_id)


async def create_log(
    user_id: int,
    task_id: int,
    content: str,
    duration_minutes: int | None = None,
) -> TaskLog:
    # Whoever may WRITE the task may log on it (rule #78) — a collaborator on a
    # shared project included. This used to be a bare owner filter, which
    # refused exactly the person a shared task exists for.
    if not await can_write_note(user_id, task_id):
        raise ValueError(f"Task {task_id} not found")
    async with async_session() as session:
        result = await session.execute(select(Note).where(Note.id == task_id))
        task = result.scalars().first()
        if task is None:
            raise ValueError(f"Task {task_id} not found")
        # Logging IS working the task, so it stamps the claim (milestone 381) —
        # unless the work is over: a retrospective note on a closed task is not
        # a session picking it up.
        if task.status not in (TaskStatus.done.value, TaskStatus.cancelled.value):
            stamp_claim(task, user_id)
        log = TaskLog(
            task_id=task_id,
            user_id=user_id,
            content=content,
            duration_minutes=duration_minutes,
        )
        session.add(log)
        await session.commit()
        await session.refresh(log)
        await _refresh_task_document(session, task_id)
        return log


async def list_logs(user_id: int, task_id: int) -> list[TaskLog]:
    async with async_session() as session:
        result = await session.execute(
            select(TaskLog)
            .where(TaskLog.task_id == task_id, TaskLog.user_id == user_id)
            .order_by(TaskLog.created_at.asc())
        )
        return list(result.scalars().all())


async def logs_for_task(
    user_id: int, task_id: int, limit: int = 0
) -> list[TaskLog]:
    """Every work log on a task, NEWEST FIRST, whoever wrote it.

    Two differences from `list_logs`, both deliberate:

    1. Scoped by who may read the TASK, not by who wrote each entry. A work
       log belongs to the task, and on a shared task the owner's record is
       exactly what a collaborator needs — `list_logs`' `TaskLog.user_id ==
       user_id` returns them an empty list, which reads as "no work has been
       done" rather than "not yours". The permission question is asked of the
       note through `can_read_note` (rule #78), so this is not an unscoped
       read with the check left to the caller.
    2. Newest first, because the question a reader asks of a work log is
       "where does this actually stand", and the answer is the last entry.
       `list_logs` stays ascending — the web UI renders a narrative.

    `limit` of 0 means all of them. An unreadable or missing task returns []
    the same way an empty one does: a work log is not a channel for proving a
    record exists.
    """
    if not await can_read_note(user_id, task_id):
        return []
    async with async_session() as session:
        stmt = (
            select(TaskLog)
            .where(TaskLog.task_id == task_id)
            .order_by(TaskLog.created_at.desc(), TaskLog.id.desc())
        )
        if limit > 0:
            stmt = stmt.limit(limit)
        result = await session.execute(stmt)
        return list(result.scalars().all())


async def count_logs_for_task(user_id: int, task_id: int) -> int:
    """How many work logs a task carries. Same scoping as logs_for_task."""
    if not await can_read_note(user_id, task_id):
        return 0
    async with async_session() as session:
        result = await session.execute(
            select(func.count(TaskLog.id)).where(TaskLog.task_id == task_id)
        )
        return int(result.scalar() or 0)


async def log_counts_for_tasks(
    user_id: int, task_ids: list[int]
) -> dict[int, int]:
    """Log counts for a whole page of tasks in ONE query.

    A per-row lookup would be N+1 by construction — and so would a per-row
    `can_read_note` — which is the reason a list surface would otherwise keep
    omitting this and leave a reader to guess which rows carry a record. So
    the permission is expressed as set membership with
    `readable_notes_clause` and folded into the same statement, the pattern
    that function exists for.

    Tasks with no logs are absent from the mapping; callers zero-fill, so
    "none" reads as a count rather than a missing key.
    """
    ids = [int(t) for t in task_ids if t]
    if not ids:
        return {}
    async with async_session() as session:
        result = await session.execute(
            select(TaskLog.task_id, func.count(TaskLog.id))
            .join(Note, Note.id == TaskLog.task_id)
            .where(TaskLog.task_id.in_(ids), readable_notes_clause(user_id))
            .group_by(TaskLog.task_id)
        )
        return {int(tid): int(n) for tid, n in result.all()}


async def update_log(
    user_id: int,
    log_id: int,
    content: str | None = None,
    duration_minutes: object = _UNSET,
) -> TaskLog | None:
    async with async_session() as session:
        result = await session.execute(
            select(TaskLog).where(TaskLog.id == log_id, TaskLog.user_id == user_id)
        )
        log = result.scalars().first()
        if log is None:
            return None
        if content is not None:
            log.content = content
        if duration_minutes is not _UNSET:
            log.duration_minutes = duration_minutes  # type: ignore[assignment]
        log.updated_at = datetime.now(timezone.utc)
        await session.commit()
        await session.refresh(log)
        await _refresh_task_document(session, log.task_id)
        return log


async def delete_log(user_id: int, log_id: int) -> bool:
    async with async_session() as session:
        result = await session.execute(
            select(TaskLog).where(TaskLog.id == log_id, TaskLog.user_id == user_id)
        )
        log = result.scalars().first()
        if log is None:
            return False
        task_id = log.task_id
        await session.delete(log)
        await session.commit()
        await _refresh_task_document(session, task_id)
        return True