#codex

OpenAI confirmed GPT-5.6 Sol has deleted user files in Full-Access mode. The fix is not a smarter model but the permission tier you run the agent in.

OpenAI retires 13 model snapshots on July 23, 2026, including every pre-5.3 Codex variant. Replacements aren't 1:1, so pinned configs need testing first.

ChatGPT Work and Codex share one GPT-5.6 usage pool, per OpenAI's own docs. Access splits by plan and surface - plus the CLI update you need.

OpenAI launched ChatGPT Work on July 9: a GPT-5.6 agent that turns a goal into finished sheets, slides, docs and sites, with Codex merged into one desktop app.

OpenAI previews GPT-5.6 as three tiers — flagship Sol, balanced Terra, high-volume Luna — with new multi-agent reasoning, pricing, and a gated rollout.

OpenAI is acquiring Ona to give Codex persistent cloud environments for hours-to-days agent tasks. What it means for the build-vs-buy sandbox decision.

Oracle customers can soon apply Universal Credits to OpenAI models and Codex via OCI. Why this procurement-rails shift matters for regulated enterprises.

Wire OpenAI Codex into CI to generate Jest tests for new functions on every PR. Scripted prompts, diff parsing, and a PR-comment bot included.

OpenAI's GPT-5.5 ships April 23, 2026 with 1M context, Thinking and Pro variants, 82.7% Terminal-Bench, and same latency as GPT-5.4. Pricing inside.

OpenAI publishes Symphony on GitHub, an Elixir-based autonomous coding orchestration framework. Works with Codex for multi-agent code generation workflows.

GPT-5.3-Codex-Spark delivers 1,000+ tokens/sec on Cerebras hardware with 77.3% Terminal-Bench. Benchmarks, speed-accuracy tradeoffs, and developer guide.

OpenAI's GPT-5.3-Codex brings 25% faster inference and major Terminal-Bench and OSWorld gains. Full benchmarks, access details, and migration guide.

OpenAI launches GPT-5.2 and GPT-5.2-Codex optimized for agentic coding as GPT-4o retires February 13, 2026. Complete migration and implementation guide.