Upgrade Codex Dreaming V3 memory with two config lines for smarter, cheaper models
daniel_mac8 · x · 2026-10-27
danielmac8 notes that Codex's Dreaming V3 memory system defaults to GPT-5.6 Luna and Terra for extraction and consolidation. Upgrading takes two lines in config.toml: extractmodel = "gpt-6-luna" and consolidationmodel = "gpt-6.1-terra" — both models are reportedly more intelligent and cheaper than their predecessors, which he calls better than a free lunch.
More from coding & agent
- Box explains its Deep Agent architecture: parent-child agents over a LangGraph orchestrator — LangChain · 2026-10-28
- How Box built enterprise content agents on Deep Agents with a parent/child architecture — LangChain · 2026-10-28
- How do you inject instructions mid-run? Dev struggles with stage summaries agents don't trust — tinker_bob · 2026-10-28
- Harrison Chase to demo agents that catch their own mistakes and write the eval and fix — LangChain · 2026-10-28
- Parallel launches Parallel Decisions API at $0.001 per request with 5,000 free calls — schwentker · 2026-10-28
- Together breaks down the MIGHT stack: composable open-source AI from models to MCP tools — togethercompute · 2026-10-28