Files
FabledScribe/src/fabledassistant/services/backup.py
T
bvandeusen 878b149f4d feat(backup): v2 backup/restore with all models and FK re-mapping
Export now includes: projects, milestones, task_logs, note_drafts,
note_versions, push_subscriptions; full user fields (oauth_sub,
session_version); full message fields (status, tool_calls).

Restore v2 builds ID maps for all tables and patches FKs in dependency
order (users → projects → milestones → notes → child records). Notes
restored in two passes to handle self-referential parent_id correctly.
v1 backups still restore via _restore_v1 path (parent_id bug also fixed).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-11 11:57:21 -04:00

653 lines
24 KiB
Python

import logging
from datetime import date, datetime, timezone
from sqlalchemy import select
from sqlalchemy.orm import selectinload
from fabledassistant.models import async_session
from fabledassistant.models.conversation import Conversation, Message
from fabledassistant.models.milestone import Milestone
from fabledassistant.models.note import Note
from fabledassistant.models.note_draft import NoteDraft
from fabledassistant.models.note_version import NoteVersion
from fabledassistant.models.project import Project
from fabledassistant.models.push_subscription import PushSubscription
from fabledassistant.models.setting import Setting
from fabledassistant.models.task_log import TaskLog
from fabledassistant.models.user import User
logger = logging.getLogger(__name__)
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
# ---------------------------------------------------------------------------
# Export
# ---------------------------------------------------------------------------
async def export_full_backup() -> dict:
"""Export all data as version-2 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()
conversations = (await session.execute(
select(Conversation).options(selectinload(Conversation.messages))
)).scalars().all()
settings = (await session.execute(select(Setting))).scalars().all()
push_subs = (await session.execute(select(PushSubscription))).scalars().all()
return {
"version": 2,
"scope": "full",
"exported_at": datetime.now(timezone.utc).isoformat(),
"_security_notice": (
"This backup contains hashed passwords and push subscription keys. "
"Store it securely and restrict access."
),
"users": [
{
"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 users
],
"projects": [
{
"id": p.id,
"user_id": p.user_id,
"title": p.title,
"description": p.description,
"goal": p.goal,
"status": p.status,
"color": p.color,
"created_at": p.created_at.isoformat(),
"updated_at": p.updated_at.isoformat(),
}
for p in projects
],
"milestones": [
{
"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 milestones
],
"notes": [
{
"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 notes
],
"task_logs": [
{
"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 task_logs
],
"note_drafts": [
{
"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 note_drafts
],
"note_versions": [
{
"id": nv.id,
"user_id": nv.user_id,
"note_id": nv.note_id,
"title": nv.title,
"body": nv.body,
"tags": nv.tags or [],
"created_at": nv.created_at.isoformat(),
}
for nv in note_versions
],
"conversations": [
{
"id": c.id,
"user_id": c.user_id,
"title": c.title,
"model": c.model,
"created_at": c.created_at.isoformat(),
"updated_at": c.updated_at.isoformat(),
"messages": [
{
"id": m.id,
"role": m.role,
"content": m.content,
"status": m.status,
"context_note_id": m.context_note_id,
"tool_calls": m.tool_calls,
"created_at": m.created_at.isoformat(),
}
for m in c.messages
],
}
for c in conversations
],
"settings": [
{"user_id": s.user_id, "key": s.key, "value": s.value}
for s in settings
],
"push_subscriptions": [
{
"user_id": ps.user_id,
"endpoint": ps.endpoint,
"p256dh": ps.p256dh,
"auth": ps.auth,
"user_agent": ps.user_agent,
"created_at": ps.created_at.isoformat(),
}
for ps in push_subs
],
}
async def export_user_backup(user_id: int) -> dict:
"""Export a single user's data as version-2 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()
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()
conversations = (await session.execute(
select(Conversation)
.options(selectinload(Conversation.messages))
.where(Conversation.user_id == user_id)
)).scalars().all()
settings = (await session.execute(
select(Setting).where(Setting.user_id == user_id)
)).scalars().all()
return {
"version": 2,
"scope": "user",
"exported_at": datetime.now(timezone.utc).isoformat(),
"user": {
"id": user.id,
"username": user.username,
"email": user.email,
"role": user.role,
"created_at": user.created_at.isoformat(),
} if user else None,
"projects": [
{
"id": p.id,
"user_id": p.user_id,
"title": p.title,
"description": p.description,
"goal": p.goal,
"status": p.status,
"color": p.color,
"created_at": p.created_at.isoformat(),
"updated_at": p.updated_at.isoformat(),
}
for p in projects
],
"milestones": [
{
"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 milestones
],
"notes": [
{
"id": n.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 notes
],
"task_logs": [
{
"id": tl.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 task_logs
],
"note_drafts": [
{
"id": nd.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 note_drafts
],
"note_versions": [
{
"id": nv.id,
"note_id": nv.note_id,
"title": nv.title,
"body": nv.body,
"tags": nv.tags or [],
"created_at": nv.created_at.isoformat(),
}
for nv in note_versions
],
"conversations": [
{
"id": c.id,
"title": c.title,
"model": c.model,
"created_at": c.created_at.isoformat(),
"updated_at": c.updated_at.isoformat(),
"messages": [
{
"id": m.id,
"role": m.role,
"content": m.content,
"status": m.status,
"context_note_id": m.context_note_id,
"tool_calls": m.tool_calls,
"created_at": m.created_at.isoformat(),
}
for m in c.messages
],
}
for c in conversations
],
"settings": [
{"key": s.key, "value": s.value}
for s in settings
],
}
# ---------------------------------------------------------------------------
# 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)
return await _restore_v2(data)
async def _restore_v1(data: dict) -> dict:
"""Restore legacy v1 backup (original format)."""
stats = {"users": 0, "notes": 0, "conversations": 0, "messages": 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 c_data in data.get("conversations", []):
mapped_user_id = user_id_map.get(c_data.get("user_id", 0))
if mapped_user_id is None:
continue
conv = Conversation(
user_id=mapped_user_id,
title=c_data.get("title", ""),
model=c_data.get("model", ""),
created_at=_dt(c_data.get("created_at")),
updated_at=_dt(c_data.get("updated_at")),
)
session.add(conv)
await session.flush()
stats["conversations"] += 1
for m_data in c_data.get("messages", []):
msg = Message(
conversation_id=conv.id,
role=m_data["role"],
content=m_data.get("content", ""),
context_note_id=note_id_map.get(m_data["context_note_id"]) if m_data.get("context_note_id") else None,
created_at=_dt(m_data.get("created_at")),
)
session.add(msg)
stats["messages"] += 1
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 backup with full FK re-mapping."""
stats: dict[str, int] = {
"users": 0, "projects": 0, "milestones": 0, "notes": 0,
"task_logs": 0, "note_drafts": 0, "note_versions": 0,
"conversations": 0, "messages": 0, "settings": 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] = {}
# 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", []),
created_at=_dt(nv_data.get("created_at")),
)
session.add(nv)
stats["note_versions"] += 1
# 8. Conversations + Messages
for c_data in data.get("conversations", []):
mapped_uid = user_id_map.get(c_data.get("user_id", 0))
if mapped_uid is None:
continue
conv = Conversation(
user_id=mapped_uid,
title=c_data.get("title", ""),
model=c_data.get("model", ""),
created_at=_dt(c_data.get("created_at")),
updated_at=_dt(c_data.get("updated_at")),
)
session.add(conv)
await session.flush()
stats["conversations"] += 1
for m_data in c_data.get("messages", []):
msg = Message(
conversation_id=conv.id,
role=m_data["role"],
content=m_data.get("content", ""),
status=m_data.get("status", "complete"),
context_note_id=note_id_map.get(m_data["context_note_id"]) if m_data.get("context_note_id") else None,
tool_calls=m_data.get("tool_calls"),
created_at=_dt(m_data.get("created_at")),
)
session.add(msg)
stats["messages"] += 1
# 9. 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
await session.commit()
logger.info("Restored v2 backup: %s", stats)
return stats