Database Migrations taste

• Keep every schema change in a versioned migration file committed next to the code that needs it. Confidence: 0.95
• Write migrations in plain SQL rather than ORM-generated diffs you have not read. Confidence: 0.80
• Never edit a migration that has already run in a shared environment; add a new one instead. Confidence: 0.95
• Use the expand and contract pattern: add the new column, backfill, switch reads, then drop the old column in a later release. Confidence: 0.90
• Make every migration safe to run while the previous app version is still serving traffic. Confidence: 0.90
• Add new columns as nullable or with a constant default to avoid long table rewrites. Confidence: 0.85
• Create indexes on large Postgres tables with CREATE INDEX CONCURRENTLY outside a transaction. Confidence: 0.90
• Set a short lock_timeout and statement_timeout at the top of each migration. Confidence: 0.85
• Run large backfills as batched background jobs, not inside the migration itself. Confidence: 0.90
• Keep one logical change per migration so failures are easy to read and retry. Confidence: 0.80
• Name migration files with a UTC timestamp prefix and a short verb phrase like 20261017_add_orders_status. Confidence: 0.75
• Prefer forward-only migrations and fix mistakes with a new migration instead of relying on down scripts. Confidence: 0.70
• Run migrations as a separate deploy step before the new application code starts. Confidence: 0.85
• Test every migration in CI against a fresh database and against a copy of production-sized data. Confidence: 0.80
• Add foreign keys and check constraints as NOT VALID first, then validate them in a separate step. Confidence: 0.80
• Rename columns and tables only through a view or dual-write period, never in a single step. Confidence: 0.75
• Store the applied migration history in the database and fail the deploy if it has drifted. Confidence: 0.85
• Review migrations as carefully as application code, with the generated SQL visible in the pull request. Confidence: 0.90
• Keep seed and fixture data out of schema migrations. Confidence: 0.80