-- 026_check_defs_last_run.up.sql
-- Make check_defs.interval_s actually mean something.
--
-- ListEnabledCheckDefs selected interval_s but never filtered on it, and
-- nothing in the scheduler read it except staleSweep. So every enabled check
-- ran on every 30-second pass and the declared per-check intervals were
-- decorative.
--
-- That went unnoticed at 17 enabled checks (~0.5 SSH/s). Restoring monitoring
-- coverage takes it to ~150, where it would have meant ~126 SSH connections
-- every 30s — roughly 363k/day — and, worst of all, `apt update` on every
-- machine every 30 seconds via updates_check.sh: 14,400 mirror hits a day to
-- answer a question whose answer changes about once a day.
--
-- last_run_at is a column rather than scheduler memory on purpose: an
-- in-memory map resets on restart, and this control plane restarts on every
-- deploy, so every check would fire at once each time — a thundering herd
-- exactly when the stack is least settled.
--
-- NULL means "never run", which is due immediately. Existing rows therefore
-- all fire once on the first pass after this migration, then settle into
-- their declared cadence.

ALTER TABLE check_defs ADD COLUMN IF NOT EXISTS last_run_at TIMESTAMPTZ;

-- The scheduler's hot query: enabled AND due. Partial on enabled since
-- disabled checks are never considered.
CREATE INDEX IF NOT EXISTS idx_check_defs_due
  ON check_defs (last_run_at)
  WHERE enabled;

COMMENT ON COLUMN check_defs.last_run_at IS 'When this check last executed. NULL = never, due immediately. Compared against interval_s to decide due-ness.';