Surface thinking level for scenariobench bands; backfill Ollama Cloud runs to low
This commit is contained in:
parent
4bfa1c75ea
commit
f334538866
1 changed files with 7 additions and 1 deletions
|
|
@ -277,11 +277,17 @@ private function aggregateScenarioBand(array $runs): array
|
|||
->selectRaw('sum(gen_tokens) / nullif(sum(wall), 0) as gen_tps')
|
||||
->first();
|
||||
|
||||
// Thinking level: keep it only when every scenario row in the band
|
||||
// agrees — matches the per-run runLevel() rule, applied at band scope.
|
||||
$level = DB::table('scenario_runs')
|
||||
->whereIn('benchmark_run_id', $runPks)
|
||||
->distinct()->pluck('level')->filter()->values();
|
||||
|
||||
return [
|
||||
'run_pk' => $first->id,
|
||||
'run_id' => $first->run_id,
|
||||
'suite' => 'scenariobench',
|
||||
'level' => null,
|
||||
'level' => $level->count() === 1 ? $level->first() : null,
|
||||
'passed' => (int) ($agg->passed ?? 0),
|
||||
'failed' => (int) ($agg->failed ?? 0),
|
||||
'avg_user_tps' => null,
|
||||
|
|
|
|||
Loading…
Reference in a new issue