AI providers: review follow-ups to 0060ccd
Build & Deploy / Build & push images (push) Successful in 4m59s
Build & Deploy / Deploy Firestore rules & indexes (push) Successful in 27s
Build & Deploy / Deploy to VM (push) Successful in 2m48s
Build & Deploy / Report a failed deploy (push) Skipped

Replay usage key gemini_usage -> llm_usage (backend + ReplayTab), re-price the
correction/correlation estimates for gpt-4o-mini, no temperature for o-series
or gpt-5 models, and refresh comments still naming Gemini.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Logan Cusano
2026-11-08 01:27:16 -05:00
co-authored by Claude Opus 5.5
parent 0060ccde75
commit 4fab959ddb
7 changed files with 19 additions and 15 deletions
+1 -1
View File
@@ -669,7 +669,7 @@ export interface ReplayMetrics {
llm_decisions: number;
est_cost_usd: number;
ai_failures?: Record<string, number>;
gemini_usage?: Record<string, { calls: number; in: number; out: number; thinking: number }>;
llm_usage?: Record<string, { calls: number; in: number; out: number; thinking: number }>;
}
export interface ReplayRun {