jev-effort
Per-turn reasoning effort for coding agents, classified by TypeSafe's Jev via AI SDK (Vercel AI Gateway / OpenRouter / TypeSafe). Claude Code plugin; Codex, Cursor, Amp next.
Unverified: Jev confidence 0.61; publishing needs more than 0.65. Category confidence 0.43; publishing needs more than 0.60. all unverified
- Author
- pc-style
- Category
- benchmark
- Primitives
- unknown
- Source
- github
Classified by jev-1.13.0. Description taken from the source, not generated.