Repeated context compaction in Astra, with old and irrelevant information still hanging…
This is a dev post classified by Jev as AI dev tools (a tutorial), kept by the Dev Radar because it carries real work, not commentary.
Repeated context compaction in Astra, with old and irrelevant information still hanging around, really gets in the way of development. I’ve turned on Codex’s experimental context management, which is off by default: features.context_management.experimental_mode = true It uses notes and searchable history to preserve details. Astra can keep notes across context windows and look up earlier messages and tool results from the same task. Add the setting at the top level of config.toml, then start a new task. Over the next few days, I’m going to test whether it can find previously agreed require
Posted by Vox (20.1k followers) 3 days ago · 52 likes · 14k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: ChatGPT Learn, OpenAI Developers.
More dev work like this
- 💥什么鬼！本地开源 Jev 居然杀到了 0 输出 Token，自带三档模型直接落地结构化判断！ — @NFT_Chen
- AI Agent System for Deep Learning Model Migration from TensorFlow to JAX! #BigData… — @gp_pulipaka
- Vectorizing the Math for LLM! #BigData #Analytics #DataScience #AI #MachineLearning #IoT… — @gp_pulipaka
- Hermes Wingtips #79: `agent[.]disabled_toolsets` — @witcheer
- Give your coding agent a box — not your whole machine. — @DanKornas
- it's awesome to see the reception here 🔥 — @jerryjliu0
- 🌙 中秋福利续上！OpenCode 官方再延长一周！DeepSeek V4.1 Flash 的 4 倍额度已延至 9 月 27 日，完美覆盖中秋！ — @NFT_Chen
- 🚨 Step 5 Preview — @chetaslua
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 18.9k posts from 4.9k X accounts over the last 21 days, 2.1k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 06:12 UTC. Full method.