Summary
Open Code Review 1.11.6 adds first-class controls for effort, maximum token budget and LLM reasoning effort, alongside live review progress. It also adds OCaml and ReasonML allowlists, line numbering in the existing-code viewer and signal-forwarding fixes.
Why it matters
Budget and effort controls make LLM code review more governable, helping teams balance review depth, latency and inference cost in automated pipelines.
Related coverage
- OpenAI reports coding agents now exceed human research labour inside its organisation
- Microsoft APM 0.30.0 hardens agent package installation and cache lifecycle
- Qwen Code 0.23.1-preview.2 makes multi-agent sessions and workflow runs inspectable