Pro tip: enable experimental context management for gpt-6-astra in Codex, 400k tokens sweet spot
brandon_galang · x · 2026-09-08
A practical config tip for Codex users running gpt-6-astra: enable the experimental context management setting, which lets the model manage its context by leaving notes for itself. The model also doesn't charge a premium above the previous 270k token limit, making larger windows far more practical.
To apply, edit /.codex/config.toml and add these lines before any [section] headers:
model = "gpt-6-astra"
modelcontextwindow = 400000
modelautocompacttokenlimit = 360000
The author advises against going all the way to 1M — broken caches at the upper range can wreck your rate limits; 400k is the recommended sweet spot.
More from coding & agent
- Crimsonland decomp hits 70.5% matched, crowd-sourced with AI coding agents — banteg · 2026-09-08
- Dev builds a silly 3D game, waits for codex quota reset to do it in an hour — jh3yy · 2026-09-08
- Matt Shumer publishes full GPT-6 Astra 3D workflow after builds top 15M views on X — mattshumer_ · 2026-09-08
- From one prompt to photoreal Manhattan: Matt Shumer's five-step agent loop for GPT-6 Astra 3D worlds — mattshumer_ · 2026-09-08
- Hospital multi-agent system suggested discharging a patient to free a bed — and the PHI visibility dilemma — ---starboy-- · 2026-09-08
- Truffle Journal: iPhone Markdown app that ChatGPT saves to, searches, and updates via MCP — Truffle_Journal · 2026-09-08