"""Sync the YNAB budget into the local Postgres mirror. YNAB has no event feed, but every budget response carries a ``server_knowledge`` counter; passing it back as ``last_knowledge_of_server`` returns only entities changed since then. The first sync downloads the whole budget, later syncs are deltas, and a full resync runs once a day as a safety net (deltas can't express things like month rollovers). Each sync diffs incoming entities against the mirror and appends what changed to ``ynab_changes``, which is the only history of edits we get. """ import asyncio import logging import os import time from dataclasses import dataclass from datetime import date, datetime, timedelta, timezone from decimal import Decimal from typing import Any, Callable from tortoise.models import Model from tortoise.transactions import in_transaction from utils.ynab_service import YNABService from .models import ( YnabAccount, YnabCategory, YnabCategoryGroup, YnabChange, YnabMonth, YnabMonthCategory, YnabPayee, YnabSubtransaction, YnabSyncState, YnabTransaction, ) logger = logging.getLogger(__name__) FULL_RESYNC_INTERVAL = timedelta(hours=24) # After a failed sync, tools answer from the mirror without retrying YNAB FAILURE_BACKOFF_SECONDS = 60 # Cap on rows passed to a single ``id IN (...)`` lookup LOOKUP_CHUNK = 2000 _sync_lock = asyncio.Lock() _last_failure = float("-inf") def ynab_configured() -> bool: return bool(os.getenv("YNAB_ACCESS_TOKEN")) # YNAB accepts these in place of a budget id; they can point at different # budgets over time, so the mirror resolves them once and keeps the real id BUDGET_ID_ALIASES = ("last-used", "default") def _configured_budget_id() -> str | None: """YNAB_BUDGET_ID if it names a specific budget, else None.""" budget_id = os.getenv("YNAB_BUDGET_ID", "").strip() return None if budget_id in ("", *BUDGET_ID_ALIASES) else budget_id def _money(milliunits: int | None) -> Decimal | None: return None if milliunits is None else Decimal(milliunits).scaleb(-3) def _date(value: str | None) -> date | None: return date.fromisoformat(value) if value else None def _datetime(value: str | None) -> datetime | None: if not value: return None return datetime.fromisoformat(value.replace("Z", "+00:00")) def _norm(value: Any) -> Any: """Normalize values so DB rows and freshly mapped rows compare equal.""" if isinstance(value, datetime) and value.tzinfo is None: return value.replace(tzinfo=timezone.utc) return value def _jsonable(value: Any) -> Any: if isinstance(value, Decimal): return float(value) if isinstance(value, (date, datetime)): return value.isoformat() return value def _map_account(a: dict) -> dict: return { "id": a["id"], "name": a["name"], "type": a["type"], "on_budget": a["on_budget"], "closed": a["closed"], "note": a.get("note"), "balance": _money(a["balance"]), "cleared_balance": _money(a["cleared_balance"]), "uncleared_balance": _money(a["uncleared_balance"]), "last_reconciled_at": _datetime(a.get("last_reconciled_at")), "deleted": a["deleted"], } def _map_payee(p: dict) -> dict: return { "id": p["id"], "name": p["name"], "transfer_account_id": p.get("transfer_account_id"), "deleted": p["deleted"], } def _map_category_group(g: dict) -> dict: return { "id": g["id"], "name": g["name"], "hidden": g["hidden"], "internal": g.get("internal") or False, "deleted": g["deleted"], } def _map_category(c: dict) -> dict: return { "id": c["id"], "category_group_id": c["category_group_id"], "name": c["name"], "hidden": c["hidden"], "internal": c.get("internal") or False, "note": c.get("note"), "goal_type": c.get("goal_type"), "goal_target": _money(c.get("goal_target")), "goal_target_month": _date(c.get("goal_target_month")), "deleted": c["deleted"], } def _map_month(m: dict) -> dict: return { "id": m["month"], "month": _date(m["month"]), "note": m.get("note"), "income": _money(m["income"]), "budgeted": _money(m["budgeted"]), "activity": _money(m["activity"]), "to_be_budgeted": _money(m["to_be_budgeted"]), "age_of_money": m.get("age_of_money"), "deleted": m["deleted"], } def _map_month_category(c: dict) -> dict: return { "id": f"{c['month']}:{c['id']}", "month": _date(c["month"]), "category_id": c["id"], "budgeted": _money(c["budgeted"]), "activity": _money(c["activity"]), "balance": _money(c["balance"]), "deleted": c["deleted"], } def _map_transaction(t: dict) -> dict: return { "id": t["id"], "date": _date(t["date"]), "amount": _money(t["amount"]), "memo": t.get("memo"), "cleared": t["cleared"], "approved": t["approved"], "flag_color": t.get("flag_color"), "account_id": t["account_id"], "payee_id": t.get("payee_id"), "category_id": t.get("category_id"), "transfer_account_id": t.get("transfer_account_id"), "import_payee_name": t.get("import_payee_name"), "deleted": t["deleted"], } def _map_subtransaction(s: dict) -> dict: return { "id": s["id"], "transaction_id": s["transaction_id"], "amount": _money(s["amount"]), "memo": s.get("memo"), "payee_id": s.get("payee_id"), "category_id": s.get("category_id"), "transfer_account_id": s.get("transfer_account_id"), "deleted": s["deleted"], } # Filled in from payees/categories/accounts after each sync, not from YNAB DENORMALIZED_FIELDS = ("account_name", "payee_name", "category_name") @dataclass class EntitySpec: entity_type: str model: type[Model] mapper: Callable[[dict], dict] # Fields worth recording in the change log. Derived fields (balances, # activity) change with every transaction and would drown out real edits. logged_fields: tuple[str, ...] def _fields(model: type[Model], exclude: tuple[str, ...] = ()) -> tuple[str, ...]: return tuple(f for f in model._meta.fields_map if f != "id" and f not in exclude) SPECS = { "accounts": EntitySpec( "account", YnabAccount, _map_account, ("name", "type", "on_budget", "closed", "note", "deleted"), ), "payees": EntitySpec("payee", YnabPayee, _map_payee, ("name", "deleted")), "category_groups": EntitySpec( "category_group", YnabCategoryGroup, _map_category_group, ("name", "hidden", "deleted"), ), "categories": EntitySpec( "category", YnabCategory, _map_category, _fields(YnabCategory) ), "months": EntitySpec("month", YnabMonth, _map_month, ("note",)), "month_categories": EntitySpec( "month_category", YnabMonthCategory, _map_month_category, ("budgeted",) ), "transactions": EntitySpec( "transaction", YnabTransaction, _map_transaction, _fields(YnabTransaction, exclude=DENORMALIZED_FIELDS), ), "subtransactions": EntitySpec( "subtransaction", YnabSubtransaction, _map_subtransaction, _fields(YnabSubtransaction), ), } def _budget_entities(budget: dict) -> dict[str, list[dict]]: """Split a budget payload into raw entity lists keyed like ``SPECS``.""" month_categories = [ {**c, "month": m["month"]} for m in budget.get("months") or [] for c in m.get("categories") or [] ] return { "accounts": budget.get("accounts") or [], "payees": budget.get("payees") or [], "category_groups": budget.get("category_groups") or [], "categories": budget.get("categories") or [], "months": budget.get("months") or [], "month_categories": month_categories, "transactions": budget.get("transactions") or [], "subtransactions": budget.get("subtransactions") or [], } # Id fields that reference a named entity (account, payee, category, group); # the change log records these by name NAMED_ID_FIELDS = ( "account_id", "payee_id", "category_id", "category_group_id", "transfer_account_id", ) class _Labeler: """Resolves ids to names for change log labels and diffs.""" def __init__(self, names: dict[str, str]): self.names = names def name(self, entity_id: str | None) -> str | None: return None if entity_id is None else self.names.get(entity_id, entity_id) def __call__(self, entity_type: str, row: dict) -> str: if entity_type == "transaction": payee = self.name(row.get("payee_id")) or row.get("import_payee_name") or "" return f"{row['date']} {payee} {row['amount']:+.2f}" if entity_type == "subtransaction": category = self.name(row.get("category_id")) or "" return f"split line {category} {row['amount']:+.2f}" if entity_type == "month_category": return f"{self.name(row['category_id'])} {row['month']:%Y-%m}" if entity_type == "month": return row["id"][:7] return row.get("name") or row["id"] def diff_entry(self, field: str, old: Any, new: Any) -> tuple[str, list]: """Log e.g. ``category_id`` changes as ``category`` names, not ids.""" if field in NAMED_ID_FIELDS: return field.removesuffix("_id"), [self.name(old), self.name(new)] return field, [_jsonable(old), _jsonable(new)] async def _load_names(conn) -> dict[str, str]: names: dict[str, str] = {} for model in (YnabAccount, YnabPayee, YnabCategory, YnabCategoryGroup): for row in await model.all().using_db(conn).values("id", "name"): names[row["id"]] = row["name"] return names async def _fetch_existing(spec: EntitySpec, ids: list[str], conn, fields) -> dict: existing: dict[str, dict] = {} for i in range(0, len(ids), LOOKUP_CHUNK): rows = ( await spec.model.filter(id__in=ids[i : i + LOOKUP_CHUNK]) .using_db(conn) .values("id", *fields) ) existing.update({row["id"]: row for row in rows}) return existing async def _apply( spec: EntitySpec, raw_rows: list[dict], conn, server_knowledge: int, log_changes: bool, labeler: _Labeler, complete: bool = False, ) -> int: """Upsert rows that differ from the mirror; return how many changed. ``complete`` means ``raw_rows`` is every live entity of this type (a full download). Full downloads omit deleted entities, so mirror rows missing from it are marked deleted here; otherwise deletions that happened right before a full sync would never reach the mirror. """ incoming = {row["id"]: row for row in map(spec.mapper, raw_rows)} # Only YNAB-sourced columns; denormalized names are filled in afterwards field_names = tuple(f for f in _fields(spec.model) if f not in DENORMALIZED_FIELDS) existing = await _fetch_existing(spec, list(incoming), conn, field_names) to_write: list[Model] = [] changes: list[YnabChange] = [] def log(entity_id: str, action: str, diff: dict, row: dict) -> None: changes.append( YnabChange( server_knowledge=server_knowledge, entity_type=spec.entity_type, entity_id=entity_id, action=action, label=labeler(spec.entity_type, row)[:500], changes=diff, ) ) for entity_id, new in incoming.items(): old = existing.get(entity_id) if old is not None and all(_norm(old[f]) == _norm(new[f]) for f in field_names): continue to_write.append(spec.model(**new)) if not log_changes or not spec.logged_fields: continue if old is None: # Created and deleted between two syncs: nothing worth logging if new.get("deleted"): continue diff = dict( labeler.diff_entry(f, None, new[f]) for f in spec.logged_fields if new[f] is not None ) # e.g. a month rollover creates every category's month row with # nothing assigned; that's not an edit anyone made if not any(values[1] for values in diff.values()): continue log(entity_id, "created", diff, new) else: diff = dict( labeler.diff_entry(f, old[f], new[f]) for f in spec.logged_fields if _norm(old[f]) != _norm(new[f]) ) if diff: deleted = diff.get("deleted") == [False, True] log(entity_id, "deleted" if deleted else "updated", diff, new) removed = 0 if complete: live_ids = ( await spec.model.filter(deleted=False) .using_db(conn) .values_list("id", flat=True) ) missing = [i for i in live_ids if i not in incoming] if missing: if log_changes and "deleted" in spec.logged_fields: gone = await _fetch_existing(spec, missing, conn, field_names) for entity_id, row in gone.items(): log(entity_id, "deleted", {"deleted": [False, True]}, row) for i in range(0, len(missing), LOOKUP_CHUNK): removed += ( await spec.model.filter(id__in=missing[i : i + LOOKUP_CHUNK]) .using_db(conn) .update(deleted=True) ) if to_write: await spec.model.bulk_create( to_write, batch_size=500, on_conflict=["id"], update_fields=list(field_names), using_db=conn, ) if changes: await YnabChange.bulk_create(changes, batch_size=500, using_db=conn) return len(to_write) + removed DENORMALIZE_SQL = ( """UPDATE ynab_transactions AS t SET payee_name = p.name FROM ynab_payees p WHERE t.payee_id = p.id AND t.payee_name IS DISTINCT FROM p.name""", """UPDATE ynab_transactions AS t SET category_name = c.name FROM ynab_categories c WHERE t.category_id = c.id AND t.category_name IS DISTINCT FROM c.name""", """UPDATE ynab_transactions AS t SET account_name = a.name FROM ynab_accounts a WHERE t.account_id = a.id AND t.account_name IS DISTINCT FROM a.name""", """UPDATE ynab_transactions SET payee_name = NULL WHERE payee_id IS NULL AND payee_name IS NOT NULL""", """UPDATE ynab_transactions SET category_name = NULL WHERE category_id IS NULL AND category_name IS NOT NULL""", ) # Entity types whose changes can affect the denormalized name columns NAME_SOURCES = ("accounts", "payees", "categories", "transactions") REFERENCE_KEYS = ("accounts", "payees", "category_groups", "categories") DATA_KEYS = ("months", "month_categories", "transactions", "subtransactions") async def apply_budget( budget: dict, server_knowledge: int, conn, log_changes: bool, full: bool = False, ) -> dict[str, int]: """Write a full or delta budget payload into the mirror. With ``full``, entity types present in the payload are treated as complete and anything missing from them is marked deleted. """ entities = _budget_entities(budget) present = {key for key in SPECS if budget.get(key) is not None} if budget.get("months") is not None: present.add("month_categories") labeler = _Labeler({}) if log_changes and any(entities.values()): labeler.names = await _load_names(conn) counts: dict[str, int] = {} for key in REFERENCE_KEYS + DATA_KEYS: counts[key] = await _apply( SPECS[key], entities[key], conn, server_knowledge, log_changes, labeler, complete=full and key in present, ) if key in REFERENCE_KEYS: # Later labels (e.g. a new payee on a new transaction) need these labeler.names.update({row["id"]: row["name"] for row in entities[key]}) if any(counts[key] for key in NAME_SOURCES): for sql in DENORMALIZE_SQL: await conn.execute_query(sql) return counts async def _current_state() -> YnabSyncState | None: """The sync state for the mirrored budget. The mirror holds a single budget, keyed by its real YNAB id. With ``YNAB_BUDGET_ID`` unset or an alias, the first sync resolves "last-used" and the mirror stays pinned to that budget, so switching budgets in YNAB can't mix two budgets' rows. """ configured = _configured_budget_id() states = await YnabSyncState.all().order_by("budget_id") ids = [s.budget_id for s in states] if len(ids) > 1 or (configured and ids and ids[0] != configured): raise ValueError( f"YNAB mirror holds budget(s) {', '.join(ids)} but YNAB_BUDGET_ID " f"is {configured or 'unset'}; clear the ynab_* tables to switch budgets" ) return states[0] if states else None def _backing_off() -> bool: return time.monotonic() - _last_failure < FAILURE_BACKOFF_SECONDS def _is_fresh(state: YnabSyncState | None, max_age_seconds: int) -> bool: return ( state is not None and state.last_synced_at is not None and datetime.now(timezone.utc) - _norm(state.last_synced_at) <= timedelta(seconds=max_age_seconds) ) async def sync_ynab(full: bool = False, max_age_seconds: int | None = None) -> dict: """Sync YNAB into Postgres. Returns per-entity counts of changed rows. ``max_age_seconds`` (on-demand syncs from tools) skips the sync if the mirror is already that fresh or YNAB failed recently. Both are checked under the lock, so parallel tool calls share one sync or one failure. The YNAB request runs before the DB transaction. An asyncio lock serializes syncs in this process; a Postgres advisory lock plus a server_knowledge check discards a payload if the other blue/green container synced in the meantime. """ global _last_failure async with _sync_lock: state = await _current_state() if max_age_seconds is not None and ( _is_fresh(state, max_age_seconds) or _backing_off() ): return {"skipped": True} now = datetime.now(timezone.utc) base_knowledge = state.server_knowledge if state else None first_sync = base_knowledge is None full = ( full or first_sync or state.last_full_sync_at is None or now - _norm(state.last_full_sync_at) > FULL_RESYNC_INTERVAL ) budget_id = state.budget_id if state else _configured_budget_id() budget_id = budget_id or "last-used" try: data = await YNABService().fetch_budget( budget_id, None if full else base_knowledge ) budget = data["budget"] knowledge = data["server_knowledge"] if state is not None and budget["id"] != state.budget_id: raise ValueError( f"YNAB returned budget {budget['id']} for {state.budget_id}" ) async with in_transaction() as conn: await conn.execute_query( "SELECT pg_advisory_xact_lock(hashtext('ynab_sync'))" ) latest = await YnabSyncState.get_or_none( budget_id=budget["id"] ).using_db(conn) if (latest.server_knowledge if latest else None) != base_knowledge: logger.info("YNAB sync skipped: mirror changed during fetch") return {"skipped": True} counts = await apply_budget( budget, knowledge, conn, log_changes=not first_sync, full=full ) await YnabSyncState.update_or_create( budget_id=budget["id"], defaults={ "budget_name": budget.get("name"), "server_knowledge": knowledge, "last_synced_at": now, "last_error": None, **({"last_full_sync_at": now} if full else {}), }, using_db=conn, ) except Exception as e: _last_failure = time.monotonic() if state is not None: await YnabSyncState.filter(budget_id=state.budget_id).update( last_error=f"{type(e).__name__}: {e}"[:2000] ) raise changed = {k: v for k, v in counts.items() if v} if changed: logger.info(f"YNAB {'full' if full else 'delta'} sync @{knowledge}: {changed}") return {"full": full, "server_knowledge": knowledge, "changed": changed} async def ensure_fresh(max_age_seconds: int = 120) -> YnabSyncState | None: """Sync if the mirror is older than ``max_age_seconds``. Used by agent tools before answering. A failed sync is logged and the (possibly stale) mirror is used anyway, and YNAB isn't retried for ``FAILURE_BACKOFF_SECONDS``. Returns None only if the mirror has never been populated. """ state = await _current_state() if not _is_fresh(state, max_age_seconds) and not _backing_off(): try: await sync_ynab(max_age_seconds=max_age_seconds) except Exception: logger.exception("YNAB sync failed; answering from existing mirror") state = await _current_state() if state is None or state.server_knowledge is None: return None return state async def ynab_sync_loop() -> None: """Background task: delta-sync YNAB every ``YNAB_SYNC_INTERVAL`` seconds.""" # Below ensure_fresh's 120s window, so tool calls rarely sync inline. interval = int(os.getenv("YNAB_SYNC_INTERVAL", "90")) logger.info(f"YNAB sync loop started (interval={interval}s)") while True: try: await sync_ynab() except Exception: logger.exception("YNAB sync error") await asyncio.sleep(interval)