LLeMbas/src/lembas/services/library/memories.py

"""Memory: short facts, in front of the model on every turn.

The whole design follows from being injected rather than searched.

* Each record is **capped short**, because every one of them costs tokens on
  every request forever. A tool that writes an essay gets it trimmed and is
  told so, rather than the write failing -- the model can then decide to put
  the long version in a note.
* There is a **budget** for the block as a whole. Past it the oldest are left
  out rather than the request growing without limit; the user can see the whole
  list in their settings and prune it.
* There is **no search tool**. Searching something the model is already looking
  at is a round trip for nothing.
* They are **not shareable**. A record about a person is not content to hand
  round, and nobody asked to share their memories with a group.
"""

from __future__ import annotations

import logging

from sqlalchemy import func, select
from sqlalchemy.orm import Session as DBSession

from lembas.db.models import AUTHOR_MODEL, AUTHOR_USER, Memory, User

log = logging.getLogger(__name__)

# One fact, not a paragraph. Long enough for "prefers metric units and a 24-hour
# clock", short enough that fifty of them are still affordable.
MAX_MEMORY_CHARS = 400

# Ceiling on the injected block. Reached, the oldest records drop out of the
# prompt -- they are still listed in settings, so nothing disappears silently.
MAX_TOTAL_CHARS = 4000

# A hard stop on how many can exist, so an enthusiastic model cannot fill a
# database with variations on one fact.
MAX_RECORDS = 200


def all_for(db: DBSession, user: User | None) -> list[Memory]:
    if user is None:
        return []
    return list(
        db.scalars(
            select(Memory).where(Memory.owner_id == user.id).order_by(Memory.created_at)
        )
    )


def get(db: DBSession, memory_id: str, user: User | None) -> Memory | None:
    memory = db.get(Memory, memory_id)
    if memory is None or user is None or memory.owner_id != user.id:
        return None
    return memory


def add(db: DBSession, *, owner: User, content: str, author: str = AUTHOR_MODEL) -> Memory:
    """Record a fact. Raises ValueError when there is no room or nothing to say."""
    content = " ".join((content or "").split())
    if not content:
        raise ValueError("A memory cannot be empty.")

    count = db.scalar(
        select(func.count()).select_from(Memory).where(Memory.owner_id == owner.id)
    )
    if (count or 0) >= MAX_RECORDS:
        raise ValueError(
            f"There are already {MAX_RECORDS} memories. Remove one first, or put "
            f"this in a note instead."
        )

    memory = Memory(
        owner_id=owner.id,
        content=content[:MAX_MEMORY_CHARS],
        author=author if author in (AUTHOR_USER, AUTHOR_MODEL) else AUTHOR_MODEL,
    )
    db.add(memory)
    db.commit()
    return memory


def update(db: DBSession, memory: Memory, content: str) -> Memory:
    content = " ".join((content or "").split())
    if not content:
        raise ValueError("A memory cannot be empty.")
    memory.content = content[:MAX_MEMORY_CHARS]
    db.commit()
    return memory


def delete(db: DBSession, memory: Memory) -> None:
    db.delete(memory)
    db.commit()


def block(db: DBSession, user: User | None) -> str:
    """The memories as they appear in the prompt, within the budget.

    Oldest first, and truncation drops the *newest* -- a fact that has survived
    a long time is more likely to be a standing preference than something said
    once this morning.
    """
    records = all_for(db, user)
    if not records:
        return ""

    lines: list[str] = []
    total = 0
    for memory in records:
        line = f"- {memory.content}"
        if total + len(line) > MAX_TOTAL_CHARS:
            lines.append(f"- (…{len(records) - len(lines)} more, see your settings)")
            break
        lines.append(line)
        total += len(line)

    return "\n".join(lines)