Architecture: Should Vitto have its own database or share the existing Mon...

Documentation for Sessions

🏗️ Architecture: Should Vitto have its own database or share the existing Mon...

Date: 2026-02-07
Time: 18:10:55 UTC
Session: gspace1-98.3
Agent: backend
Confidence: 90%
Status: ✅ Documented

📋 Decision Context

Question:

Should Vitto have its own database or share the existing MongoDB?

Task: Vitto Mind database design

🎯 Decision Made

Chosen:

Separate MongoDB database (vitto-mind) for Vitto's operational intelligence, while accessing platform data from existing backends via HTTP

Options Considered:

Share existing MongoDB databases
Separate vitto-mind database
Use Redis for operational cache
SQLite for local-only storage

💭 Reasoning

Vitto needs Jarvis-like operational intelligence — execution traces, strategy memory, agent performance scores, user patterns. This is Vitto-only data that shouldn't pollute the shared platform databases. Platform's shared knowledge (decisions, episodes, conventions) stays in backend-ai-api accessed via HTTP. Separation enables independent scaling, migration, and backup of Vitto's mind.

📁 Files Involved

apis/backend-vitto-api/src/app/mind/mind.module.ts
apis/backend-vitto-api/src/app/mind/mind.service.ts
apis/backend-vitto-api/src/app/mind/schemas/execution-trace.schema.ts
apis/backend-vitto-api/src/app/mind/schemas/strategy-memory.schema.ts

🔗 Related

Decision ID: dev_1770487855673_mabpip4
Session: 98
Workspace: gspace1

Auto-generated by MCP Smart Consolidation