codex

PSA: If you can't switch your coding agent right away, you can just reroute Codex to a different model for the time being. https://github.com/openai/codex/issues/26#issuecomment-28116...

OpenAI forces users to verify with their ID + face scan when using Codex 5.3 if any of your conversations was redeemed as high risk. It seems like they currently have a lot of false positives: https://github.com/openai/codex/issues?q=High%20risk

Hi, i'm on codex pro plan and it silently routes to 5.2 today, WTF? Anyone else gets similar behaviour? I was working with it since morning (UTC) and afternoon sudenly it became much slower and got very different feeling, so I started digging and enabled codex logs and got: 2026-02-12T20:41:12.751950Z TRACE codex_api::sse::responses: SSE event: {"type":"response.completed","response":{"id":"resp_0fc56e20d02a6b5701698e3ae51fac8191a5bae8fc9962662c","object":"response","created_at":1770928869,"status":"completed","background":false,"completed_at":1770928872,"error":null,"frequency_penalty":0.0,"incomplete_details":null,"instructions":"...personality.\n...","max_output_tokens":null,"max_tool_calls":null,"model":"gpt-5.2-2025-12-11"," See also https://github.com/openai/codex/issues/11561

I was using a custom skill to spawn subagents, but it looks like the `/experimental` feature in codex-cli has the SubAgent setting (https://github.com/openai/codex/issues/2604#issuecomment-387...)

> Codex uses apply_patch: It takes a string as input, which is essentially an OpenAI-flavored diff, and instead of relying on a structured schema, the harness just expects this blob to follow a strict set of rules. Since OpenAI folks are without a doubt smart, I’m sure the token selection process is biased to fit this structure at the LLM gateway for the Codex variants of GPT, similar to how other constraints like JSON schemas or required tool calls work. Codex does in fact use a schema for constrained sampling, it's here: https://github.com/openai/codex/blob/main/codex-rs/core/src/... It still has to work to get an exact match, or at least I didn't read the code to see if there's any fuzzy matching used. Note the two codex models were the only ones doing worse with the author's proposed format. The author found them doing better with rep

Filed an issue for codex https://github.com/openai/codex/issues/11601

Yeah, happy to be more specific. No intention of making any technically true but misleading statements. The following are true: - In our API, we don't change model weights or model behavior over time (e.g., by time of day, or weeks/months after release) - Tiny caveats include: there is a bit of non-determinism in batched non-associative math that can vary by batch / hardware, bugs or API downtime can obviously change behavior, heavy load can slow down speeds, and this of course doesn't apply to the 'unpinned' models that are clearly supposed to change over time (e.g., xxx-latest). But we don't do any quantization or routing gimmicks that would change model weights. - In ChatGPT and Codex CLI, model behavior can change over time (e.g., we might change a tool, update a system prompt, tweak default thinking time, run an A/B test, or ship oth

Can you explain how to use it? I’ve tried asking it to do “create 3 files using multiple sub agents” and other similar wording. It never works. Is it in the main Codex build? There doesn’t seem to be an experiment for it. https://github.com/openai/codex/issues/2604

Here's OpenAI's docs page on how they sandbox Codex: https://developers.openai.com/codex/security/ Here's the macOS kernel-enforced sandbox profile that gets applied to processes spawned by the LLM: https://github.com/openai/codex/blob/main/codex-rs/core/src/... I think skepticism is healthy here, but there's no need to just guess.