feat: migrate backend persistence from TinyDB to MongoDB Atlas

- Implement lazy MongoDB client initialization in backend/db/mongo_client.py.
- Create Gunicorn configuration to ensure MongoDB client is initialized per worker.
- Refactor database access layer to support MongoDB with a new MongoLockedTable adapter.
- Add migration script to transfer existing TinyDB data to MongoDB, preserving idempotency.
- Update tracking event handling to ensure deterministic ordering with a monotonic sequence.
- Modify tests to use mongomock for MongoDB integration and ensure existing tests pass.
- Add integration test script to run tests against a local MongoDB Docker container.
- Document environment variables and migration process in specs/feat-database-migration.md.
This commit is contained in:
2026-07-28 01:10:52 -04:00
parent c9c1fa18a2
commit da7ed41938
17 changed files with 1364 additions and 62 deletions
+22 -8
View File
@@ -1,4 +1,5 @@
"""Helper functions for tracking events database operations."""
import itertools
import logging
from typing import Optional, List
from tinydb import Query
@@ -8,6 +9,10 @@ from models.tracking_event import TrackingEvent, EntityType, ActionType
logger = logging.getLogger(__name__)
# Monotonic sequence used as a deterministic tiebreaker when tracking events
# share the same ``occurred_at``/``created_at`` timestamps (common in tests).
_tracking_event_seq = itertools.count()
def insert_tracking_event(event: TrackingEvent) -> str:
"""
@@ -20,7 +25,9 @@ def insert_tracking_event(event: TrackingEvent) -> str:
The event ID
"""
try:
tracking_events_db.insert(event.to_dict())
event_dict = event.to_dict()
event_dict['_seq'] = next(_tracking_event_seq)
tracking_events_db.insert(event_dict)
logger.info(f"Tracking event created: {event.action} {event.entity_type} {event.entity_id} for child {event.child_id}")
return event.id
except Exception as e:
@@ -61,12 +68,16 @@ def get_tracking_events_by_child(
all_results = tracking_events_db.search(query_condition)
total = len(all_results)
# Sort by occurred_at desc, then created_at desc
all_results.sort(key=lambda x: (x.get('occurred_at', ''), x.get('created_at', 0)), reverse=True)
# Sort by occurred_at desc, then created_at desc, then _seq desc for
# deterministic ordering when timestamps collide (common in fast tests).
all_results.sort(
key=lambda x: (x.get('occurred_at', ''), x.get('created_at', 0), x.get('_seq', 0)),
reverse=True,
)
paginated = all_results[offset:offset + limit]
events = [TrackingEvent.from_dict(r) for r in paginated]
return events, total
@@ -99,11 +110,14 @@ def get_tracking_events_by_user(
all_results = tracking_events_db.search(query_condition)
total = len(all_results)
all_results.sort(key=lambda x: (x.get('occurred_at', ''), x.get('created_at', 0)), reverse=True)
all_results.sort(
key=lambda x: (x.get('occurred_at', ''), x.get('created_at', 0), x.get('_seq', 0)),
reverse=True,
)
paginated = all_results[offset:offset + limit]
events = [TrackingEvent.from_dict(r) for r in paginated]
return events, total