session-management

Session SQL Database Management

Why This is Copilot-Exclusive

Copilot CLI includes a built-in SQLite database per session accessible via a native sql tool. It comes with pre-built todos and todo_deps tables and supports creating any custom tables you need. This structured data layer enables proper task tracking, batch processing, and state management — all queryable with SQL. Claude Code has no database; state management is limited to reading/writing files or keeping everything in the conversation context.

When to Use

• Tracking progress on multi-step tasks with dependencies
• Batch-processing items (issues, files, test cases) with status tracking
• Storing intermediate results from analysis or exploration
• Managing key-value state across a complex workflow
• Building reports from structured data (test results, PR reviews, audit findings)

Workflow

1. Pre-Built Todo Tracking

The todos table is ready to use immediately:

-- Create todos for your task
INSERT INTO todos (id, title, description, status) VALUES
  ('setup-db', 'Set up database', 'Initialize Prisma schema with User and Post models', 'pending'),
  ('seed-data', 'Create seed data', 'Add development seed script with 10 users', 'pending'),
  ('api-routes', 'Build API routes', 'REST endpoints for User CRUD operations', 'pending');

-- Define dependencies
INSERT INTO todo_deps (todo_id, depends_on) VALUES
  ('seed-data', 'setup-db'),
  ('api-routes', 'setup-db');

2. Track Progress as You Work

-- Start working on a todo
UPDATE todos SET status = 'in_progress', updated_at = datetime('now') WHERE id = 'setup-db';

-- Complete it
UPDATE todos SET status = 'done', updated_at = datetime('now') WHERE id = 'setup-db';

-- Check what's ready to start next
SELECT t.id, t.title FROM todos t
WHERE t.status = 'pending'
AND NOT EXISTS (
  SELECT 1 FROM todo_deps td
  JOIN todos dep ON td.depends_on = dep.id
  WHERE td.todo_id = t.id AND dep.status != 'done'
);

3. Custom Tables for Any Purpose