Codex merges Memory V2 prompts: 10KB summary cap, citations and selective retrieval
morqon · x · 2026-09-26
- PR #43813 in openai/codex adds dedicated Memory V2 consolidation and read prompts.
- Consolidation: rollout summaries merge into memorysummary.md without rawmemories.md or a required MEMORY.md, validated for required sections and kept under 10,000 UTF-8 bytes.
- Reads: new instructions for selective history retrieval, evidence-grounded preferences, citations, and explicit memory edits; injected instructions are split into fragments to preserve the full summary within byte limits.
- Memory citation usage is now recorded in sessions; the repo sits at 127k stars.
More from coding & agent
- Andrew Ng: rigid testing on early-stage AI projects is a recipe for stall — DeepLearningAI · 2026-09-26
- Peter Steiberger says he codes with Codex plus an OC harness, not Claude — steipete · 2026-09-26
- One prompt makes Claude generate a 2-min video game history film entirely in code — prasenx · 2026-09-26
- Run /doctor prompt-audit to find stale paths and conflicting instructions in Claude Code — daniel_mac8 · 2026-09-26
- Repurpose your old M1/M2 Mac as a local test server with this open-source runner script — jasonkneen · 2026-09-26
- DHH says 37signals went "pencils down": 150k lines in August with agents vs 30k/year by hand — Recent-Tangerine2745 · 2026-09-26