FabledScribe/src/scribe/services/backup.py

import logging
from datetime import date, datetime, timezone

from sqlalchemy import or_, select

from scribe.models import async_session
from scribe.models.milestone import Milestone
from scribe.models.note import Note
from scribe.models.note_draft import NoteDraft
from scribe.models.note_supersession import NoteSupersession
from scribe.models.note_version import NoteVersion
from scribe.models.design_system import DesignSystem, DesignToken
from scribe.models.note_usage import NoteUsageEvent
from scribe.models.code_shape import CodeShape, CodeShapeEvent, CodeShapeUse
from scribe.models.project import Project
from scribe.models.repo_binding import RepoBinding
from scribe.models.rulebook import (
    Rule,
    Rulebook,
    RulebookTopic,
    project_rule_suppressions,
    project_rulebook_exclusions,
    project_rulebook_subscriptions,
    project_topic_suppressions,
)
from scribe.models.setting import Setting
from scribe.models.system import RecordSystem, System
from scribe.models.task_log import TaskLog
from scribe.models.user import User

logger = logging.getLogger(__name__)

# Backup format version. v3 (2026-06) added rulebooks/topics/rules + their
# project subscription/suppression join tables. v4 (2026-07) dropped events
# when the calendar surface was retired — old v3 events are skipped on restore.
# v5 (2026-08) added the six tables that had accumulated outside the backup
# entirely (#2293), and the coverage guard that stops the seventh.
# v6 (2026-08) added note_supersessions — and the guard did stop the seventh:
# the table shipped without a backup section and the coverage test failed the
# build, which is the whole reason that list was written.
# v7 (2026-08) added code_shapes — the shape ledger (#2787). Classifications
# are judgment data worth carrying; a restore keeps a judgment only when its
# snippet target survives the id re-mapping, else the row rejoins the todo.
# v8 (2026-08) added code_shape_events — the ledger's history (#2793): what
# was used where, when, and why is not recomputable, so it travels.
# v9 (2026-08) added code_shape_uses — the ledger's consumption edges (#2870):
# judgment-grade edges (agent/audit/import) are operator records; mechanical
# ones (reference/hook) travel too, cheaply, and the next refresh refreshes them.
# v10 (2026-08) added projects.inception + project_rulebook_exclusions
# (milestone 297): the WHY a project inherits what it does, and its opt-outs.
# Bump when the serialized schema changes.
BACKUP_VERSION = 10

# Every table this backup carries, by its REAL name. Paired with _NOT_INCLUDED
# below, these two lists must together account for the entire schema — which is
# what tests/test_services_backup.py asserts against Base.metadata.
#
# The point is the ABSENCE case. A new table gets a model and a migration, both
# of which fail loudly if wrong, and then silently never gets a backup section:
# no error, no warning, and a restore that reports success. Naming the coverage
# explicitly turns "someone forgot" into a failing test (#2293).
_BACKED_UP = [
    "users", "projects", "milestones", "notes", "task_logs", "note_drafts",
    "note_versions", "settings", "rulebooks", "rulebook_topics", "rules",
    "project_rulebook_subscriptions", "project_rule_suppressions",
    "project_topic_suppressions", "project_rulebook_exclusions",
    # v5 (2026-08): the five-year gap this list was written to stop.
    "systems", "record_systems", "design_systems", "design_tokens",
    "note_usage_events", "repo_bindings", "note_supersessions",
    # v7 (2026-08): the shape ledger (#2787); v8: its history (#2793).
    "code_shapes", "code_shape_events", "code_shape_uses",
]

# Tables intentionally NOT in the backup, surfaced in the payload so the gap is
# explicit rather than silent. ACL (groups/shares) is a coherent follow-up;
# note_embeddings are derived (regenerated from note bodies); api_keys are
# sensitive credentials; retrieval_logs is observational telemetry that nothing
# reads for correctness and that grows per query; the rest are
# transient/operational.
#
# REAL table names, deliberately. This list used to read "embeddings",
# "invitations", "password_resets" — none of which are tables — so it looked
# like coverage while naming nothing the schema could confirm.
_NOT_INCLUDED = [
    "groups", "group_memberships", "project_shares", "note_shares",
    "api_keys", "note_embeddings", "app_logs", "notifications",
    "invitation_tokens", "password_reset_tokens", "user_profiles",
    "retrieval_logs",
    # Sensitive credentials, same reasoning as api_keys: a backup that carries
    # forge tokens is a token-exfiltration file. Users re-add connections
    # after a restore; the per-project pin (projects.forge_connection_id) is
    # deliberately not exported either, so restored projects fall back to
    # keyring-by-host resolution — the documented unpinned behavior (#2778).
    "forge_connections",
]


def _dt(val: str | None) -> datetime:
    return datetime.fromisoformat(val) if val else datetime.now(timezone.utc)


def _d(val: str | None) -> date | None:
    return date.fromisoformat(val) if val else None


def _subscription_rows(rows) -> list[dict]:
    return [{"project_id": r.project_id, "rulebook_id": r.rulebook_id} for r in rows]


def _rule_suppression_rows(rows) -> list[dict]:
    return [{"project_id": r.project_id, "rule_id": r.rule_id} for r in rows]


def _topic_suppression_rows(rows) -> list[dict]:
    return [{"project_id": r.project_id, "topic_id": r.topic_id} for r in rows]


def _rulebook_exclusion_rows(rows) -> list[dict]:
    return [{"project_id": r.project_id, "rulebook_id": r.rulebook_id} for r in rows]


# The v5 sections. Pure row-builders like the join-table helpers above, for the
# same reason: CI has no database, so a serialiser that is a plain function is
# one that can actually be tested.

def _system_rows(rows) -> list[dict]:
    return [
        {
            "id": r.id, "user_id": r.user_id, "project_id": r.project_id,
            "name": r.name, "description": r.description, "color": r.color,
            "status": r.status, "order_index": r.order_index,
        }
        for r in rows
    ]


def _record_system_rows(rows) -> list[dict]:
    return [{"note_id": r.note_id, "system_id": r.system_id} for r in rows]


def _note_supersession_rows(rows) -> list[dict]:
    """Which record has overtaken which. Carried because it is a JUDGEMENT —
    someone decided this note replaced that one, and nothing in either note's
    text records the decision. Lose it and the corpus silently reverts to
    ranking stale material alongside current material."""
    return [
        {"superseder_id": r.superseder_id, "superseded_id": r.superseded_id}
        for r in rows
    ]


def _design_system_rows(rows) -> list[dict]:
    return [
        {
            "id": r.id, "owner_user_id": r.owner_user_id, "title": r.title,
            "description": r.description, "guidance": r.guidance,
            "parent_id": r.parent_id,
        }
        for r in rows
    ]


def _design_token_rows(rows) -> list[dict]:
    return [
        {
            "id": r.id, "design_system_id": r.design_system_id, "name": r.name,
            "value_by_mode": r.value_by_mode or {},
            "group_name": r.group_name, "purpose": r.purpose,
            "rationale": r.rationale, "supersedes": r.supersedes or [],
            "order_index": r.order_index,
        }
        for r in rows
    ]


def _usage_event_rows(rows) -> list[dict]:
    return [
        {
            "user_id": r.user_id, "note_id": r.note_id, "event": r.event,
            "source": r.source,
            "created_at": r.created_at.isoformat() if r.created_at else None,
        }
        for r in rows
    ]


def _code_shape_rows(rows) -> list[dict]:
    return [r.to_dict() for r in rows]


def _code_shape_event_rows(rows) -> list[dict]:
    return [r.to_dict() for r in rows]


def _code_shape_use_rows(rows) -> list[dict]:
    return [r.to_dict() for r in rows]


def _repo_binding_rows(rows) -> list[dict]:
    return [
        {"user_id": r.user_id, "project_id": r.project_id, "repo_key": r.repo_key}
        for r in rows
    ]


# Row builders for the sections both exporters carry. Pure, like the join-table
# helpers above; the full and per-user exports used to restate every one of
# these comprehensions side by side, and a column added to one and not the
# other is a backup that silently drops it (#2293's shape, one layer down).

def _user_rows(rows) -> list[dict]:
    return [
        {
            "id": u.id, "username": u.username, "email": u.email,
            "password_hash": u.password_hash, "oauth_sub": u.oauth_sub,
            "role": u.role, "session_version": u.session_version,
            "created_at": u.created_at.isoformat(),
        }
        for u in rows
    ]


def _project_rows(rows) -> list[dict]:
    return [
        {
            "id": p.id, "user_id": p.user_id, "title": p.title,
            "description": p.description, "goal": p.goal, "status": p.status,
            "color": p.color,
            "design_system_id": p.design_system_id,
            "inception": p.inception,
            "created_at": p.created_at.isoformat(),
            "updated_at": p.updated_at.isoformat(),
        }
        for p in rows
    ]


def _milestone_rows(rows) -> list[dict]:
    return [
        {
            "id": m.id, "user_id": m.user_id, "project_id": m.project_id,
            "title": m.title, "description": m.description, "status": m.status,
            "order_index": m.order_index,
            "created_at": m.created_at.isoformat(),
            "updated_at": m.updated_at.isoformat(),
        }
        for m in rows
    ]


def _note_rows(rows) -> list[dict]:
    return [
        {
            "id": n.id, "user_id": n.user_id, "title": n.title, "body": n.body,
            "tags": n.tags or [], "parent_id": n.parent_id,
            "project_id": n.project_id, "milestone_id": n.milestone_id,
            "status": n.status, "priority": n.priority,
            "due_date": n.due_date.isoformat() if n.due_date else None,
            "created_at": n.created_at.isoformat(),
            "updated_at": n.updated_at.isoformat(),
        }
        for n in rows
    ]


def _task_log_rows(rows) -> list[dict]:
    return [
        {
            "id": tl.id, "user_id": tl.user_id, "task_id": tl.task_id,
            "content": tl.content, "duration_minutes": tl.duration_minutes,
            "created_at": tl.created_at.isoformat(),
            "updated_at": tl.updated_at.isoformat(),
        }
        for tl in rows
    ]


def _note_draft_rows(rows) -> list[dict]:
    return [
        {
            "id": nd.id, "user_id": nd.user_id, "note_id": nd.note_id,
            "proposed_body": nd.proposed_body, "original_body": nd.original_body,
            "instruction": nd.instruction, "scope": nd.scope,
            "created_at": nd.created_at.isoformat(),
            "updated_at": nd.updated_at.isoformat(),
        }
        for nd in rows
    ]


def _note_version_rows(rows) -> list[dict]:
    return [
        {
            "id": nv.id, "user_id": nv.user_id, "note_id": nv.note_id,
            "title": nv.title, "body": nv.body, "tags": nv.tags or [],
            "pin_kind": nv.pin_kind, "pin_label": nv.pin_label,
            "created_at": nv.created_at.isoformat(),
        }
        for nv in rows
    ]


def _setting_rows(rows) -> list[dict]:
    return [{"user_id": s.user_id, "key": s.key, "value": s.value} for s in rows]


def _rulebook_rows(rows) -> list[dict]:
    return [
        {
            "id": rb.id, "owner_user_id": rb.owner_user_id, "title": rb.title,
            "description": rb.description, "always_on": rb.always_on,
            "created_at": rb.created_at.isoformat(),
            "updated_at": rb.updated_at.isoformat(),
        }
        for rb in rows
    ]


def _topic_rows(rows) -> list[dict]:
    return [
        {
            "id": t.id, "rulebook_id": t.rulebook_id, "title": t.title,
            "description": t.description, "order_index": t.order_index,
            "created_at": t.created_at.isoformat(),
            "updated_at": t.updated_at.isoformat(),
        }
        for t in rows
    ]


def _rule_rows(rows) -> list[dict]:
    return [
        {
            "id": r.id, "topic_id": r.topic_id, "project_id": r.project_id,
            "title": r.title, "statement": r.statement, "why": r.why,
            "how_to_apply": r.how_to_apply, "order_index": r.order_index,
            "created_at": r.created_at.isoformat(),
            "updated_at": r.updated_at.isoformat(),
        }
        for r in rows
    ]


# ---------------------------------------------------------------------------
# Export
# ---------------------------------------------------------------------------

async def export_full_backup() -> dict:
    """Export all data as a version-5 JSON backup."""
    async with async_session() as session:
        users = (await session.execute(select(User))).scalars().all()
        projects = (await session.execute(select(Project))).scalars().all()
        milestones = (await session.execute(select(Milestone))).scalars().all()
        notes = (await session.execute(select(Note))).scalars().all()
        task_logs = (await session.execute(select(TaskLog))).scalars().all()
        note_drafts = (await session.execute(select(NoteDraft))).scalars().all()
        note_versions = (await session.execute(
            select(NoteVersion).order_by(NoteVersion.note_id, NoteVersion.id)
        )).scalars().all()
        settings = (await session.execute(select(Setting))).scalars().all()
        systems = (await session.execute(select(System))).scalars().all()
        record_systems = (await session.execute(select(RecordSystem))).scalars().all()
        supersessions = (
            await session.execute(select(NoteSupersession))
        ).scalars().all()
        # Parent-first, so a restore can resolve parent_id as it goes rather
        # than needing a second pass — the self-FK is the only ordering
        # constraint in this payload.
        design_systems = (await session.execute(
            select(DesignSystem).order_by(DesignSystem.parent_id.nullsfirst(),
                                          DesignSystem.id)
        )).scalars().all()
        design_tokens = (await session.execute(select(DesignToken))).scalars().all()
        usage_events = (await session.execute(select(NoteUsageEvent))).scalars().all()
        repo_bindings = (await session.execute(select(RepoBinding))).scalars().all()
        code_shapes = (await session.execute(select(CodeShape))).scalars().all()
        code_shape_events = (await session.execute(
            select(CodeShapeEvent).order_by(CodeShapeEvent.at, CodeShapeEvent.id)
        )).scalars().all()
        code_shape_uses = (await session.execute(
            select(CodeShapeUse).order_by(CodeShapeUse.shape_id, CodeShapeUse.snippet_id)
        )).scalars().all()
        rulebooks = (await session.execute(select(Rulebook))).scalars().all()
        topics = (await session.execute(select(RulebookTopic))).scalars().all()
        rules = (await session.execute(select(Rule))).scalars().all()
        subscriptions = (await session.execute(
            select(project_rulebook_subscriptions)
        )).all()
        rule_suppressions = (await session.execute(
            select(project_rule_suppressions)
        )).all()
        topic_suppressions = (await session.execute(
            select(project_topic_suppressions)
        )).all()
        rulebook_exclusions = (await session.execute(
            select(project_rulebook_exclusions)
        )).all()

    return {
        "version": BACKUP_VERSION,
        "scope": "full",
        "exported_at": datetime.now(timezone.utc).isoformat(),
        "_security_notice": (
            "This backup contains hashed passwords. "
            "Store it securely and restrict access."
        ),
        "_not_included": _NOT_INCLUDED,
        "users": _user_rows(users),
        "projects": _project_rows(projects),
        "milestones": _milestone_rows(milestones),
        "notes": _note_rows(notes),
        "task_logs": _task_log_rows(task_logs),
        "note_drafts": _note_draft_rows(note_drafts),
        "note_versions": _note_version_rows(note_versions),
        "settings": _setting_rows(settings),
        "rulebooks": _rulebook_rows(rulebooks),
        "rulebook_topics": _topic_rows(topics),
        "rules": _rule_rows(rules),
        "rulebook_subscriptions": _subscription_rows(subscriptions),
        "rule_suppressions": _rule_suppression_rows(rule_suppressions),
        "topic_suppressions": _topic_suppression_rows(topic_suppressions),
        "rulebook_exclusions": _rulebook_exclusion_rows(rulebook_exclusions),
        "systems": _system_rows(systems),
        "record_systems": _record_system_rows(record_systems),
        "design_systems": _design_system_rows(design_systems),
        "design_tokens": _design_token_rows(design_tokens),
        "note_usage_events": _usage_event_rows(usage_events),
        "repo_bindings": _repo_binding_rows(repo_bindings),
        "note_supersessions": _note_supersession_rows(supersessions),
        "code_shapes": _code_shape_rows(code_shapes),
        "code_shape_events": _code_shape_event_rows(code_shape_events),
        "code_shape_uses": _code_shape_use_rows(code_shape_uses),
    }


async def export_user_backup(user_id: int) -> dict:
    """Export a single user's data as a version-5 JSON backup."""
    async with async_session() as session:
        user = await session.get(User, user_id)
        projects = (await session.execute(
            select(Project).where(Project.user_id == user_id)
        )).scalars().all()
        project_ids = [p.id for p in projects]
        milestones = (await session.execute(
            select(Milestone).where(Milestone.user_id == user_id)
        )).scalars().all()
        notes = (await session.execute(
            select(Note).where(Note.user_id == user_id)
        )).scalars().all()
        task_logs = (await session.execute(
            select(TaskLog).where(TaskLog.user_id == user_id)
        )).scalars().all()
        note_drafts = (await session.execute(
            select(NoteDraft).where(NoteDraft.user_id == user_id)
        )).scalars().all()
        note_versions = (await session.execute(
            select(NoteVersion).where(NoteVersion.user_id == user_id)
            .order_by(NoteVersion.note_id, NoteVersion.id)
        )).scalars().all()
        settings = (await session.execute(
            select(Setting).where(Setting.user_id == user_id)
        )).scalars().all()
        systems = (await session.execute(
            select(System).where(System.user_id == user_id)
        )).scalars().all()
        system_ids = [sy.id for sy in systems]
        note_ids = [n.id for n in notes]
        # Scoped by the user's SYSTEMS, not their notes: a shared note carrying
        # this user's system tag belongs in their backup, and a note of theirs
        # tagged with someone else's system does not — that row is the other
        # user's to keep.
        record_systems = (await session.execute(
            select(RecordSystem).where(RecordSystem.system_id.in_(system_ids))
        )).scalars().all() if system_ids else []
        # BOTH ends must be this user's notes. A claim spanning out to someone
        # else's record cannot be restored into a single-user import — the far
        # id would not be in the map — so carrying it would export a row that
        # silently vanishes on the way back in. Whole-instance backups have no
        # such problem and take every row.
        supersessions = (await session.execute(
            select(NoteSupersession).where(
                NoteSupersession.superseder_id.in_(note_ids),
                NoteSupersession.superseded_id.in_(note_ids),
            )
        )).scalars().all() if note_ids else []
        design_systems = (await session.execute(
            select(DesignSystem).where(DesignSystem.owner_user_id == user_id)
            .order_by(DesignSystem.parent_id.nullsfirst(), DesignSystem.id)
        )).scalars().all()
        ds_ids = [d.id for d in design_systems]
        design_tokens = (await session.execute(
            select(DesignToken).where(DesignToken.design_system_id.in_(ds_ids))
        )).scalars().all() if ds_ids else []
        usage_events = (await session.execute(
            select(NoteUsageEvent).where(NoteUsageEvent.note_id.in_(note_ids))
        )).scalars().all() if note_ids else []
        repo_bindings = (await session.execute(
            select(RepoBinding).where(RepoBinding.user_id == user_id)
        )).scalars().all()
        # The ledger has no user_id of its own — rows belong to the project
        # they account for, so a user's export carries their projects' rows.
        code_shapes = (await session.execute(
            select(CodeShape).where(CodeShape.project_id.in_(project_ids))
        )).scalars().all() if project_ids else []
        code_shape_events = (await session.execute(
            select(CodeShapeEvent).where(CodeShapeEvent.project_id.in_(project_ids))
            .order_by(CodeShapeEvent.at, CodeShapeEvent.id)
        )).scalars().all() if project_ids else []
        code_shape_uses = (await session.execute(
            select(CodeShapeUse).join(CodeShape, CodeShape.id == CodeShapeUse.shape_id)
            .where(CodeShape.project_id.in_(project_ids))
            .order_by(CodeShapeUse.shape_id, CodeShapeUse.snippet_id)
        )).scalars().all() if project_ids else []
        rulebooks = (await session.execute(
            select(Rulebook).where(Rulebook.owner_user_id == user_id)
        )).scalars().all()
        rulebook_ids = [rb.id for rb in rulebooks]
        topics = (await session.execute(
            select(RulebookTopic).where(RulebookTopic.rulebook_id.in_(rulebook_ids))
        )).scalars().all() if rulebook_ids else []
        topic_ids = [t.id for t in topics]
        # Rules owned by the user = rules in the user's topics OR project-rules
        # on the user's projects.
        rule_filters = []
        if topic_ids:
            rule_filters.append(Rule.topic_id.in_(topic_ids))
        if project_ids:
            rule_filters.append(Rule.project_id.in_(project_ids))
        rules = (await session.execute(
            select(Rule).where(or_(*rule_filters))
        )).scalars().all() if rule_filters else []
        if project_ids:
            subscriptions = (await session.execute(
                select(project_rulebook_subscriptions).where(
                    project_rulebook_subscriptions.c.project_id.in_(project_ids)
                )
            )).all()
            rule_suppressions = (await session.execute(
                select(project_rule_suppressions).where(
                    project_rule_suppressions.c.project_id.in_(project_ids)
                )
            )).all()
            topic_suppressions = (await session.execute(
                select(project_topic_suppressions).where(
                    project_topic_suppressions.c.project_id.in_(project_ids)
                )
            )).all()
            rulebook_exclusions = (await session.execute(
                select(project_rulebook_exclusions).where(
                    project_rulebook_exclusions.c.project_id.in_(project_ids)
                )
            )).all()
        else:
            subscriptions = rule_suppressions = topic_suppressions = rulebook_exclusions = []

    return {
        "version": BACKUP_VERSION,
        "scope": "user",
        "exported_at": datetime.now(timezone.utc).isoformat(),
        "_not_included": _NOT_INCLUDED,
        "user": {
            "id": user.id,
            "username": user.username,
            "email": user.email,
            "role": user.role,
            "created_at": user.created_at.isoformat(),
        } if user else None,
        "projects": _project_rows(projects),
        "milestones": _milestone_rows(milestones),
        "notes": _note_rows(notes),
        "task_logs": _task_log_rows(task_logs),
        "note_drafts": _note_draft_rows(note_drafts),
        "note_versions": _note_version_rows(note_versions),
        "settings": _setting_rows(settings),
        "rulebooks": _rulebook_rows(rulebooks),
        "rulebook_topics": _topic_rows(topics),
        "rules": _rule_rows(rules),
        "rulebook_subscriptions": _subscription_rows(subscriptions),
        "rule_suppressions": _rule_suppression_rows(rule_suppressions),
        "topic_suppressions": _topic_suppression_rows(topic_suppressions),
        "rulebook_exclusions": _rulebook_exclusion_rows(rulebook_exclusions),
        "systems": _system_rows(systems),
        "record_systems": _record_system_rows(record_systems),
        "design_systems": _design_system_rows(design_systems),
        "design_tokens": _design_token_rows(design_tokens),
        "note_usage_events": _usage_event_rows(usage_events),
        "repo_bindings": _repo_binding_rows(repo_bindings),
        "note_supersessions": _note_supersession_rows(supersessions),
        "code_shapes": _code_shape_rows(code_shapes),
        "code_shape_events": _code_shape_event_rows(code_shape_events),
        "code_shape_uses": _code_shape_use_rows(code_shape_uses),
    }


# ---------------------------------------------------------------------------
# Restore
# ---------------------------------------------------------------------------

async def restore_full_backup(data: dict) -> dict:
    """Restore from backup JSON. Dispatches by version."""
    version = data.get("version", 1)
    if version == 1:
        return await _restore_v1(data)
    # v2 and v3 share one path; v3-only sections are guarded by data.get so a
    # v2 payload (without them) restores cleanly.
    return await _restore_v2(data)


async def _restore_v1(data: dict) -> dict:
    """Restore legacy v1 backup (original format).

    Pre-pivot v1 backups included conversations + messages; those are
    skipped during restore now that the chat subsystem is gone.
    """
    stats = {"users": 0, "notes": 0, "settings": 0}

    async with async_session() as session:
        user_id_map: dict[int, int] = {}
        for u_data in data.get("users", []):
            old_id = u_data["id"]
            user = User(
                username=u_data["username"],
                email=u_data.get("email"),
                password_hash=u_data["password_hash"],
                role=u_data.get("role", "user"),
                created_at=_dt(u_data.get("created_at")),
            )
            session.add(user)
            await session.flush()
            user_id_map[old_id] = user.id
            stats["users"] += 1

        note_id_map: dict[int, int] = {}
        for n_data in data.get("notes", []):
            old_id = n_data.get("id")
            mapped_user_id = user_id_map.get(n_data.get("user_id", 0))
            if mapped_user_id is None:
                continue
            note = Note(
                user_id=mapped_user_id,
                title=n_data.get("title", ""),
                body=n_data.get("body", ""),
                tags=n_data.get("tags", []),
                parent_id=None,  # patched below
                status=n_data.get("status"),
                priority=n_data.get("priority"),
                due_date=_d(n_data.get("due_date")),
                created_at=_dt(n_data.get("created_at")),
                updated_at=_dt(n_data.get("updated_at")),
            )
            session.add(note)
            await session.flush()
            if old_id is not None:
                note_id_map[old_id] = note.id
            stats["notes"] += 1

        # Patch parent_id now that all notes have new IDs
        for n_data in data.get("notes", []):
            old_id = n_data.get("id")
            old_parent = n_data.get("parent_id")
            if old_id and old_parent and old_id in note_id_map and old_parent in note_id_map:
                note_row = await session.get(Note, note_id_map[old_id])
                if note_row:
                    note_row.parent_id = note_id_map[old_parent]

        for s_data in data.get("settings", []):
            mapped_user_id = user_id_map.get(s_data.get("user_id", 0))
            if mapped_user_id is None:
                continue
            session.add(Setting(user_id=mapped_user_id, key=s_data["key"], value=s_data.get("value", "")))
            stats["settings"] += 1

        await session.commit()

    logger.info("Restored v1 backup: %s", stats)
    return stats


async def _restore_v2(data: dict) -> dict:
    """Restore v2/v3 backup with full FK re-mapping.

    Conversations, push subscriptions, and (as of v4) events in older backups
    are silently skipped — those subsystems were removed. v3+ sections
    (rulebooks/topics/rules/join-tables) are guarded by data.get so a v2
    payload restores without them.
    """
    stats: dict[str, int] = {
        "users": 0, "projects": 0, "milestones": 0, "notes": 0,
        "task_logs": 0, "note_drafts": 0, "note_versions": 0,
        "settings": 0, "rulebooks": 0, "rulebook_topics": 0, "rules": 0,
        "rulebook_subscriptions": 0, "rule_suppressions": 0,
        "topic_suppressions": 0, "rulebook_exclusions": 0,
        "systems": 0, "record_systems": 0, "design_systems": 0,
        "design_tokens": 0, "note_usage_events": 0, "repo_bindings": 0,
        "note_supersessions": 0, "code_shapes": 0, "code_shape_events": 0,
        "code_shape_uses": 0,
    }

    async with async_session() as session:
        user_id_map: dict[int, int] = {}
        project_id_map: dict[int, int] = {}
        milestone_id_map: dict[int, int] = {}
        note_id_map: dict[int, int] = {}
        rulebook_id_map: dict[int, int] = {}
        topic_id_map: dict[int, int] = {}
        rule_id_map: dict[int, int] = {}

        # 1. Users
        for u_data in data.get("users", []):
            old_id = u_data["id"]
            user = User(
                username=u_data["username"],
                email=u_data.get("email"),
                password_hash=u_data.get("password_hash"),
                oauth_sub=u_data.get("oauth_sub"),
                role=u_data.get("role", "user"),
                session_version=u_data.get("session_version", 1),
                created_at=_dt(u_data.get("created_at")),
            )
            session.add(user)
            await session.flush()
            user_id_map[old_id] = user.id
            stats["users"] += 1

        # 2. Projects
        for p_data in data.get("projects", []):
            mapped_uid = user_id_map.get(p_data.get("user_id", 0))
            if mapped_uid is None:
                continue
            proj = Project(
                user_id=mapped_uid,
                title=p_data.get("title", ""),
                description=p_data.get("description", ""),
                goal=p_data.get("goal", ""),
                status=p_data.get("status", "active"),
                color=p_data.get("color"),
                created_at=_dt(p_data.get("created_at")),
                updated_at=_dt(p_data.get("updated_at")),
            )
            session.add(proj)
            await session.flush()
            project_id_map[p_data["id"]] = proj.id
            stats["projects"] += 1

        # 3. Milestones
        for m_data in data.get("milestones", []):
            mapped_uid = user_id_map.get(m_data.get("user_id", 0))
            mapped_pid = project_id_map.get(m_data.get("project_id", 0))
            if mapped_uid is None or mapped_pid is None:
                continue
            ms = Milestone(
                user_id=mapped_uid,
                project_id=mapped_pid,
                title=m_data.get("title", ""),
                description=m_data.get("description"),
                status=m_data.get("status", "active"),
                order_index=m_data.get("order_index", 0),
                created_at=_dt(m_data.get("created_at")),
                updated_at=_dt(m_data.get("updated_at")),
            )
            session.add(ms)
            await session.flush()
            milestone_id_map[m_data["id"]] = ms.id
            stats["milestones"] += 1

        # 4a. Notes — first pass (no parent_id yet)
        notes_with_parents: list[tuple[int, int]] = []  # (new_note_id, old_parent_id)
        for n_data in data.get("notes", []):
            mapped_uid = user_id_map.get(n_data.get("user_id", 0))
            if mapped_uid is None:
                continue
            note = Note(
                user_id=mapped_uid,
                title=n_data.get("title", ""),
                body=n_data.get("body", ""),
                tags=n_data.get("tags", []),
                parent_id=None,
                project_id=project_id_map.get(n_data["project_id"]) if n_data.get("project_id") else None,
                milestone_id=milestone_id_map.get(n_data["milestone_id"]) if n_data.get("milestone_id") else None,
                status=n_data.get("status"),
                priority=n_data.get("priority"),
                due_date=_d(n_data.get("due_date")),
                created_at=_dt(n_data.get("created_at")),
                updated_at=_dt(n_data.get("updated_at")),
            )
            session.add(note)
            await session.flush()
            note_id_map[n_data["id"]] = note.id
            if n_data.get("parent_id"):
                notes_with_parents.append((note.id, n_data["parent_id"]))
            stats["notes"] += 1

        # 4b. Patch parent_id
        for new_note_id, old_parent_id in notes_with_parents:
            new_parent_id = note_id_map.get(old_parent_id)
            if new_parent_id:
                note_row = await session.get(Note, new_note_id)
                if note_row:
                    note_row.parent_id = new_parent_id

        # 5. TaskLogs
        for tl_data in data.get("task_logs", []):
            mapped_uid = user_id_map.get(tl_data.get("user_id", 0))
            mapped_tid = note_id_map.get(tl_data.get("task_id", 0))
            if mapped_uid is None or mapped_tid is None:
                continue
            tl = TaskLog(
                user_id=mapped_uid,
                task_id=mapped_tid,
                content=tl_data.get("content", ""),
                duration_minutes=tl_data.get("duration_minutes"),
                created_at=_dt(tl_data.get("created_at")),
                updated_at=_dt(tl_data.get("updated_at")),
            )
            session.add(tl)
            stats["task_logs"] += 1

        # 6. NoteDrafts
        for nd_data in data.get("note_drafts", []):
            mapped_uid = user_id_map.get(nd_data.get("user_id", 0))
            mapped_nid = note_id_map.get(nd_data.get("note_id", 0))
            if mapped_uid is None or mapped_nid is None:
                continue
            nd = NoteDraft(
                user_id=mapped_uid,
                note_id=mapped_nid,
                proposed_body=nd_data.get("proposed_body", ""),
                original_body=nd_data.get("original_body", ""),
                instruction=nd_data.get("instruction", ""),
                scope=nd_data.get("scope", "document"),
                created_at=_dt(nd_data.get("created_at")),
                updated_at=_dt(nd_data.get("updated_at")),
            )
            session.add(nd)
            stats["note_drafts"] += 1

        # 7. NoteVersions
        for nv_data in data.get("note_versions", []):
            mapped_uid = user_id_map.get(nv_data.get("user_id", 0))
            mapped_nid = note_id_map.get(nv_data.get("note_id", 0))
            if mapped_uid is None or mapped_nid is None:
                continue
            nv = NoteVersion(
                user_id=mapped_uid,
                note_id=mapped_nid,
                title=nv_data.get("title", ""),
                body=nv_data.get("body", ""),
                tags=nv_data.get("tags", []),
                pin_kind=nv_data.get("pin_kind"),
                pin_label=nv_data.get("pin_label"),
                created_at=_dt(nv_data.get("created_at")),
            )
            session.add(nv)
            stats["note_versions"] += 1

        # 8. Settings
        for s_data in data.get("settings", []):
            mapped_uid = user_id_map.get(s_data.get("user_id", 0))
            if mapped_uid is None:
                continue
            session.add(Setting(user_id=mapped_uid, key=s_data["key"], value=s_data.get("value", "")))
            stats["settings"] += 1

        # 9. Rulebooks (v3)
        for rb_data in data.get("rulebooks", []):
            mapped_uid = user_id_map.get(rb_data.get("owner_user_id", 0))
            if mapped_uid is None:
                continue
            rb = Rulebook(
                owner_user_id=mapped_uid,
                title=rb_data.get("title", ""),
                description=rb_data.get("description", ""),
                always_on=rb_data.get("always_on", False),
                created_at=_dt(rb_data.get("created_at")),
                updated_at=_dt(rb_data.get("updated_at")),
            )
            session.add(rb)
            await session.flush()
            rulebook_id_map[rb_data["id"]] = rb.id
            stats["rulebooks"] += 1

        # 10. Topics (v3)
        for t_data in data.get("rulebook_topics", []):
            mapped_rbid = rulebook_id_map.get(t_data.get("rulebook_id", 0))
            if mapped_rbid is None:
                continue
            topic = RulebookTopic(
                rulebook_id=mapped_rbid,
                title=t_data.get("title", ""),
                description=t_data.get("description"),
                order_index=t_data.get("order_index", 0),
                created_at=_dt(t_data.get("created_at")),
                updated_at=_dt(t_data.get("updated_at")),
            )
            session.add(topic)
            await session.flush()
            topic_id_map[t_data["id"]] = topic.id
            stats["rulebook_topics"] += 1

        # 11. Rules (v3) — topic-rule (topic_id) XOR project-rule (project_id)
        for r_data in data.get("rules", []):
            mapped_topic = topic_id_map.get(r_data["topic_id"]) if r_data.get("topic_id") else None
            mapped_proj = project_id_map.get(r_data["project_id"]) if r_data.get("project_id") else None
            if mapped_topic is None and mapped_proj is None:
                continue  # orphaned — its parent didn't restore
            rule = Rule(
                topic_id=mapped_topic,
                project_id=mapped_proj,
                title=r_data.get("title", ""),
                statement=r_data.get("statement", ""),
                why=r_data.get("why") or None,
                how_to_apply=r_data.get("how_to_apply") or None,
                order_index=r_data.get("order_index", 0),
                created_at=_dt(r_data.get("created_at")),
                updated_at=_dt(r_data.get("updated_at")),
            )
            session.add(rule)
            await session.flush()
            rule_id_map[r_data["id"]] = rule.id
            stats["rules"] += 1

        # 12. Rulebook subscriptions (v3 join table)
        for sub in data.get("rulebook_subscriptions", []):
            mapped_pid = project_id_map.get(sub.get("project_id", 0))
            mapped_rbid = rulebook_id_map.get(sub.get("rulebook_id", 0))
            if mapped_pid is None or mapped_rbid is None:
                continue
            await session.execute(project_rulebook_subscriptions.insert().values(
                project_id=mapped_pid, rulebook_id=mapped_rbid,
            ))
            stats["rulebook_subscriptions"] += 1

        # 13. Rule suppressions (v3 join table)
        for sup in data.get("rule_suppressions", []):
            mapped_pid = project_id_map.get(sup.get("project_id", 0))
            mapped_rid = rule_id_map.get(sup.get("rule_id", 0))
            if mapped_pid is None or mapped_rid is None:
                continue
            await session.execute(project_rule_suppressions.insert().values(
                project_id=mapped_pid, rule_id=mapped_rid,
            ))
            stats["rule_suppressions"] += 1

        # 14. Topic suppressions (v3 join table)
        for sup in data.get("topic_suppressions", []):
            mapped_pid = project_id_map.get(sup.get("project_id", 0))
            mapped_tid = topic_id_map.get(sup.get("topic_id", 0))
            if mapped_pid is None or mapped_tid is None:
                continue
            await session.execute(project_topic_suppressions.insert().values(
                project_id=mapped_pid, topic_id=mapped_tid,
            ))
            stats["topic_suppressions"] += 1

        # 14b. Always-on rulebook exclusions (v10, milestone 297)
        for exc in data.get("rulebook_exclusions", []):
            mapped_pid = project_id_map.get(exc.get("project_id", 0))
            mapped_rbid = rulebook_id_map.get(exc.get("rulebook_id", 0))
            if mapped_pid is None or mapped_rbid is None:
                continue
            await session.execute(project_rulebook_exclusions.insert().values(
                project_id=mapped_pid, rulebook_id=mapped_rbid,
            ))
            stats["rulebook_exclusions"] += 1

        # --- v5 sections. Every one is data.get()-guarded, so a v2/v3/v4
        # payload restores without them rather than failing on an absent key.

        # 15. Systems
        system_id_map: dict[int, int] = {}
        for sy_data in data.get("systems", []):
            mapped_uid = user_id_map.get(sy_data.get("user_id", 0))
            mapped_pid = project_id_map.get(sy_data.get("project_id", 0))
            if mapped_uid is None or mapped_pid is None:
                continue
            system = System(
                user_id=mapped_uid, project_id=mapped_pid,
                name=sy_data.get("name", ""),
                description=sy_data.get("description"),
                color=sy_data.get("color"),
                status=sy_data.get("status", "active"),
                order_index=sy_data.get("order_index", 0),
            )
            session.add(system)
            await session.flush()
            system_id_map[sy_data["id"]] = system.id
            stats["systems"] += 1

        # 16. Record↔system links
        for rs in data.get("record_systems", []):
            mapped_nid = note_id_map.get(rs.get("note_id", 0))
            mapped_sid = system_id_map.get(rs.get("system_id", 0))
            if mapped_nid is None or mapped_sid is None:
                continue
            session.add(RecordSystem(note_id=mapped_nid, system_id=mapped_sid))
            stats["record_systems"] += 1

        # 16b. Supersession claims. Guarded by `data.get` like every other
        # post-v2 section, so a v5 or older payload restores cleanly without it.
        #
        # Both ends must map. A claim is about a PAIR — half of one is not a
        # weaker claim, it is a dangling row pointing at whatever note happens
        # to hold that id next.
        for sup in data.get("note_supersessions", []):
            mapped_new = note_id_map.get(sup.get("superseder_id", 0))
            mapped_old = note_id_map.get(sup.get("superseded_id", 0))
            if mapped_new is None or mapped_old is None or mapped_new == mapped_old:
                continue
            session.add(
                NoteSupersession(
                    superseder_id=mapped_new, superseded_id=mapped_old
                )
            )
            stats["note_supersessions"] += 1

        # 17. Design systems. The export orders these parent-first, so a
        # parent's new id is always in the map by the time a child needs it —
        # no second pass, and a child whose parent is missing lands as a root
        # rather than failing the whole restore.
        design_system_id_map: dict[int, int] = {}
        for ds_data in data.get("design_systems", []):
            mapped_uid = user_id_map.get(ds_data.get("owner_user_id", 0))
            if mapped_uid is None:
                continue
            design = DesignSystem(
                owner_user_id=mapped_uid,
                title=ds_data.get("title", ""),
                description=ds_data.get("description"),
                guidance=ds_data.get("guidance"),
                parent_id=design_system_id_map.get(ds_data.get("parent_id") or 0),
            )
            session.add(design)
            await session.flush()
            design_system_id_map[ds_data["id"]] = design.id
            stats["design_systems"] += 1

        # 18. Design tokens
        for t_data in data.get("design_tokens", []):
            mapped_dsid = design_system_id_map.get(t_data.get("design_system_id", 0))
            if mapped_dsid is None:
                continue
            session.add(DesignToken(
                design_system_id=mapped_dsid,
                name=t_data.get("name", ""),
                value_by_mode=t_data.get("value_by_mode") or {},
                group_name=t_data.get("group_name"),
                purpose=t_data.get("purpose"),
                rationale=t_data.get("rationale"),
                supersedes=t_data.get("supersedes") or [],
                order_index=t_data.get("order_index", 0),
            ))
            stats["design_tokens"] += 1

        # 19. Usage events. Kept because pull-through is the evidence base for
        # whether recall works at all, and it is only ever accumulated — a
        # restore that dropped it would silently reset that measurement to zero
        # while everything still looked fine.
        for ev in data.get("note_usage_events", []):
            mapped_nid = note_id_map.get(ev.get("note_id", 0))
            if mapped_nid is None:
                continue
            session.add(NoteUsageEvent(
                user_id=user_id_map.get(ev.get("user_id") or 0),
                note_id=mapped_nid,
                event=ev.get("event", ""),
                source=ev.get("source", ""),
                created_at=_dt(ev.get("created_at")),
            ))
            stats["note_usage_events"] += 1

        # 20. Repo bindings — small, but losing them means every bound repo
        # quietly stops loading its project at session start.
        for rb_data in data.get("repo_bindings", []):
            mapped_uid = user_id_map.get(rb_data.get("user_id", 0))
            mapped_pid = project_id_map.get(rb_data.get("project_id", 0))
            if mapped_uid is None or mapped_pid is None:
                continue
            session.add(RepoBinding(
                user_id=mapped_uid, project_id=mapped_pid,
                repo_key=rb_data.get("repo_key", ""),
            ))
            stats["repo_bindings"] += 1

        # 21. Code shapes (v7, #2787) — the ledger's classifications are
        # judgments worth carrying. A judgment whose snippet target didn't
        # survive the re-mapping (canonical/instance/variant with a gone
        # snippet) is downgraded to unclassified so it rejoins the todo
        # honestly instead of dangling; exempt needs no target and keeps.
        shape_id_map: dict[int, int] = {}
        for cs_data in data.get("code_shapes", []):
            mapped_pid = project_id_map.get(cs_data.get("project_id", 0))
            if mapped_pid is None:
                continue
            status = cs_data.get("status", "unclassified")
            mapped_sid = note_id_map.get(cs_data.get("snippet_id") or 0)
            classified_by = cs_data.get("classified_by")
            classified_at = cs_data.get("classified_at")
            if status in ("canonical", "instance", "variant") and mapped_sid is None:
                status = "unclassified"
                classified_by = None
                classified_at = None
            shape = CodeShape(
                project_id=mapped_pid,
                repo_key=cs_data.get("repo_key", ""),
                path=cs_data.get("path", ""),
                symbol=cs_data.get("symbol", ""),
                kind=cs_data.get("kind", "sym"),
                status=status,
                snippet_id=mapped_sid,
                reason=cs_data.get("reason"),
                classified_by=classified_by,
                classified_at=_dt(classified_at) if classified_at else None,
                first_seen_commit=cs_data.get("first_seen_commit", ""),
                last_seen_commit=cs_data.get("last_seen_commit", ""),
                vanished_at=_dt(cs_data["vanished_at"]) if cs_data.get("vanished_at") else None,
                # Fingerprints restore; proposals (#2792) deliberately do not —
                # they are mechanical, and the next refresh recomputes them
                # against the restored snippet ids.
                signature=cs_data.get("signature", ""),
                body_sha=cs_data.get("body_sha", ""),
                classified_sha=cs_data.get("classified_sha", ""),
                created_at=_dt(cs_data.get("created_at")),
                updated_at=_dt(cs_data.get("updated_at")),
            )
            session.add(shape)
            await session.flush()
            if cs_data.get("id"):
                shape_id_map[int(cs_data["id"])] = shape.id
            stats["code_shapes"] += 1

        # v8: the ledger's history rides its shapes. snippet_id is kept as
        # the history's own claim (FK-free by design) but re-mapped when the
        # snippet survived, so a restored timeline points at restored records.
        for ev in data.get("code_shape_events", []):
            new_shape_id = shape_id_map.get(ev.get("shape_id") or 0)
            mapped_pid = project_id_map.get(ev.get("project_id", 0))
            if new_shape_id is None or mapped_pid is None:
                continue
            old_sid = ev.get("snippet_id")
            session.add(CodeShapeEvent(
                shape_id=new_shape_id,
                project_id=mapped_pid,
                path=ev.get("path", ""),
                symbol=ev.get("symbol", ""),
                kind=ev.get("kind", "sym"),
                event=ev.get("event", "classified"),
                status=ev.get("status"),
                snippet_id=note_id_map.get(old_sid, old_sid) if old_sid else None,
                classified_by=ev.get("classified_by"),
                reason=ev.get("reason"),
                commit=ev.get("commit", ""),
                at=_dt(ev.get("at")),
            ))
            stats["code_shape_events"] += 1

        # v9: consumption edges (#2870) ride their shape AND their snippet —
        # both ends must have survived, or the edge is no longer a fact.
        for use in data.get("code_shape_uses", []):
            new_shape_id = shape_id_map.get(use.get("shape_id") or 0)
            new_sid = note_id_map.get(use.get("snippet_id") or 0)
            if new_shape_id is None or new_sid is None:
                continue
            session.add(CodeShapeUse(
                shape_id=new_shape_id, snippet_id=new_sid,
                basis=use.get("basis", "import"), evidence=use.get("evidence"),
                created_at=_dt(use.get("created_at")),
            ))
            stats["code_shape_uses"] += 1

        # v10: a project's design-system pointer and its inception record ride
        # the project but point at design systems and rulebooks restored AFTER
        # it — so they are written last, with ids re-mapped. An id that did
        # not survive drops out of the record rather than dangling.
        for p_data in data.get("projects", []):
            new_pid = project_id_map.get(p_data.get("id") or 0)
            if new_pid is None:
                continue
            proj = await session.get(Project, new_pid)
            if proj is None:
                continue
            old_ds = p_data.get("design_system_id")
            if old_ds:
                proj.design_system_id = design_system_id_map.get(old_ds)
            inception = p_data.get("inception")
            if isinstance(inception, dict):
                choices = dict(inception.get("choices") or {})
                choices["exclude_always_on_rulebooks"] = [
                    rulebook_id_map[i] for i in choices.get("exclude_always_on_rulebooks") or []
                    if i in rulebook_id_map
                ]
                choices["subscribe_rulebooks"] = [
                    rulebook_id_map[i] for i in choices.get("subscribe_rulebooks") or []
                    if i in rulebook_id_map
                ]
                ds = choices.get("design_system_id")
                choices["design_system_id"] = design_system_id_map.get(ds) if ds else None
                proj.inception = {**inception, "choices": choices}

        await session.commit()

    logger.info("Restored v2/v3 backup: %s", stats)
    return stats