Codex harness burns tokens polling idle loops; workaround: disable polling or delegate
brandon_galang · x · 2026-09-13
- The quoted post identifies the issue in the Codex harness itself: while waiting for background work, it keeps making repeated model calls to poll for updates, each carrying the full conversation context even when nothing changed. The goal mechanism can auto-start new turns, compounding the repeated-context loop.
- Brandon Galang's fix: instruct Astra not to continuously poll, or delegate repetitive loops to Luna, saving significant token costs. He expects this guidance to land in the system prompt within weeks.
More from coding & agent
- Trying to build a characters-to-video pipeline with Astra: consistency across shots still fails — Illustrious-Noise-96 · 2026-09-13
- model-compose: one YAML file to deploy production-ready agents, RAG and MCP servers — adnan_hashmi · 2026-09-13
- Ditch worktrees for AI coding agents: clones plus mega PRs work better — idanbeck · 2026-09-13
- Astra one-shots a complex Ultima-style RPG with agent feedback, but the plot is bland — emollick · 2026-09-13
- Skip Vercel: run your AI agent straight on a DigitalOcean droplet for instant deploys — Daniel_Farinax · 2026-09-13
- Dev ditches code editors: terminal plus Codex or Grok CLI is all you need — Kuprel · 2026-09-13