To reduce the codex polling I slapped this into my ~/.codex/config.toml:

  [features.multi_agent_v2]
  enabled = true
  wait_agent_enabled = true
  min_wait_timeout_ms = 10000 # 10s
  default_wait_timeout_ms = 300000 # 5m
  max_wait_timeout_ms = 3600000 # 1h

Seems to do the job and reduce usage; I just ran Astra for ~5 hours (using a goal) and it used the last 30% of my usage. And now they released GPT-6 Sol and Luna (which is basically 5.6 Sol and Luna, but a bit better and also 50% cheaper) ;_;