Python API breakage checks

fix(llm): cap auto-detected max_output_tokens when it fills the entire context window #2136

Sign in to view logs

Triggered via pull request April 7, 2026 19:04

synchronize #2747

fix/nemotron-max-output-tokens-headroom

Status Success

Total duration 31s

Artifacts –

api-breakage.yml

on: pull_request