Codex TUI Massively Speeds Up Streaming Markdown

charliermarsh · x · 2026-07-19

A new version of Codex introduces incremental rendering for streaming Markdown in the TUI, making large outputs significantly faster.

The PR screenshots explain the issue: previously, streaming Markdown would continuously re-parse and redraw an increasingly large prefix as new content arrived, inflating the generation cost for long replies, lists, and tables. The new approach:

Benchmarks from the PR show that in block-heavy streams, the incremental approach achieves 17.8x / 55.3x / 259x speedups compared to full re-rendering.

Original post →

More from coding & agent

coding & agent channel →