ai_orchestrator/docs/storage/01_schema.md

Persistent Storage Schema Draft

Database Target

• production: PostgreSQL
• local development: SQLite

Persistence Path In Code

SQLAlchemy adapter реализован в:

• src/ai_orchestrator/infrastructure/storage/sqlalchemy.py
• src/ai_orchestrator/infrastructure/storage/factory.py

Migration skeleton:

• alembic.ini
• migrations/env.py
• migrations/versions/0001_initial_schema.py

Tables

projects

• project_id pk
• name
• config_blob
• created_at
• updated_at

conversations

• conversation_id pk
• project_id
• title
• created_at
• updated_at

messages

• message_id pk
• conversation_id
• role
• content
• attachments_json
• created_at

tasks

• task_id pk
• project_id
• conversation_id
• goal
• inputs_json
• status
• requested_mode
• effective_mode
• current_node_id
• result_summary_json
• created_at
• updated_at

task_graphs

• task_id pk
• graph_version
• graph_metadata_json
• created_at

task_nodes

• node_id pk
• task_id
• node_type
• status
• input_json
• output_json
• dependencies_json
• assigned_runner
• attempts
• retryable
• timeout_ms
• created_at
• updated_at

task_events

• event_id pk
• task_id
• conversation_id
• node_id
• event_type
• correlation_id
• causation_id
• payload_json
• occurred_at

confirmations

• confirmation_id pk
• task_id
• node_id
• status
• scope
• decision_json
• preview_json
• comment
• created_at
• resolved_at

worker_sessions

• session_id pk
• worker_id
• name
• machine
• os
• version
• status
• capabilities_json
• last_heartbeat_at
• current_task_id
• connected_at
• disconnected_at

model_invocations

• invocation_id pk
• task_id
• node_id
• slot
• provider
• model
• status
• request_json
• response_json
• usage_json
• fallback_from_invocation_id
• created_at

tool_invocations

• invocation_id pk
• task_id
• node_id
• source_type
• source_id
• tool_name
• status
• request_json
• response_json
• created_at

artifacts

• artifact_id pk
• task_id
• node_id
• artifact_type
• storage_uri
• metadata_json
• created_at

Required Indexes

• tasks(status, updated_at)
• task_nodes(task_id, status)
• task_events(task_id, occurred_at)
• confirmations(status, created_at)
• worker_sessions(status, last_heartbeat_at)

Query Support

Read-model adapters now support paginated queries for:

• task_events
• model_invocations
• tool_invocations
• artifacts

This is implemented in both in-memory and SQLAlchemy adapters to keep test/runtime behavior aligned.

Active Adapter Strategy

• memory backend остается для быстрых unit/integration прогонов;
• sqlite backend предназначен для локального development без Docker;
• postgres backend является production target.