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:
- Only incrementally renders the stable prefix
- Tracks the final top-level block during rendering
- Subsequent increments only retain the mutable suffix
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.
More from coding & agent
- Gergely Orosz: Shipping 10x PRs With AI Agents, Sites Fill With Small Regressions — ducha_aiki · 2026-09-11
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11
- Codex tip: use Sol with Astra and Luna sub-agents to save usage — pvncher · 2026-09-11
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11