-- Quality suites run against a model (`llmgw ctl eval`, and the gate on
-- `model update` and `model promote`): one row a run, filed under the model
-- it is about, with the revision its weights came from when that is known,
-- and the suite's hash, so two runs compare only when they asked the same
-- questions. Each case's score and answer beside it.
CREATE TABLE eval_runs (
  id         TEXT PRIMARY KEY,
  model      TEXT NOT NULL,
  target     TEXT NOT NULL DEFAULT '',
  repo       TEXT NOT NULL DEFAULT '',
  revision   TEXT NOT NULL DEFAULT '',
  suite      TEXT NOT NULL,
  suite_hash TEXT NOT NULL,
  started_at INTEGER NOT NULL,
  took_ms    INTEGER NOT NULL DEFAULT 0,
  score      REAL NOT NULL,
  threshold  REAL NOT NULL,
  passed     INTEGER NOT NULL,
  cases      INTEGER NOT NULL,
  below      INTEGER NOT NULL DEFAULT 0,
  errors     INTEGER NOT NULL DEFAULT 0,
  judge      TEXT NOT NULL DEFAULT '',
  actor      TEXT NOT NULL DEFAULT '',
  job        TEXT NOT NULL DEFAULT '',
  error      TEXT NOT NULL DEFAULT ''
);
CREATE INDEX eval_runs_model ON eval_runs (model, started_at);

CREATE TABLE eval_cases (
  run_id  TEXT NOT NULL REFERENCES eval_runs (id) ON DELETE CASCADE,
  idx     INTEGER NOT NULL,
  case_id TEXT NOT NULL,
  kind    TEXT NOT NULL,
  weight  REAL NOT NULL,
  score   REAL NOT NULL,
  passed  INTEGER NOT NULL,
  answer  TEXT NOT NULL DEFAULT '',
  detail  TEXT NOT NULL DEFAULT '',
  error   TEXT NOT NULL DEFAULT '',
  took_ms INTEGER NOT NULL DEFAULT 0,
  PRIMARY KEY (run_id, idx)
);