Ahmed Ibrahim 15e79f3c26 [codex] Harden overflow auto-compaction recovery (#22141)
## Why
Dogfooder feedback exposed two correctness gaps in normal-loop overflow
recovery:

1. a sampling request that hit `ContextWindowExceeded` could keep
re-entering auto-compaction indefinitely if the compacted retry still
did not fit, and
2. local compact-history rebuilds flattened user messages down to text,
so an overflowing `[image, "what is this?"]` turn could be retried
without the image after compaction.

That means recovery could either fail to terminate cleanly or proceed
with a materially weakened version of the user request.

## What changed
- Move normal-loop `ContextWindowExceeded` handling into the sampling
retry loop, so successful rescue compaction consumes the provider retry
budget instead of creating an unbounded outer-turn loop.
- Keep compacted user-history rebuilds structured:
`collect_user_messages` now carries user `UserInput` content rather than
flattened strings, and `build_compacted_history` reconstructs full user
messages from that structured representation.
- Preserve image inputs while retaining the existing text-budget
truncation behavior for compacted user history.
- Preserve existing compaction-task failure handling and client-session
reset behavior while bounding repeated overflow retries.
- Add focused regression coverage for:
  - recovery after a normal-loop overflow,
  - retry-budget exhaustion after repeated overflow,
  - local recovery preserving image + text input,
  - remote recovery preserving image + text input,
  - remote compaction v2 preserving image + text input, and
  - compaction failure still terminating cleanly.

The main behavior changes are in `codex-rs/core/src/session/turn.rs` and
`codex-rs/core/src/compact.rs`.

## Verification
- Not run locally; relying on PR CI for this update.

---------

Co-authored-by: Codex <noreply@openai.com>
2026-05-11 16:16:49 +00:00
2026-04-24 17:49:29 -07:00
2025-04-16 12:56:08 -04:00
2025-04-16 12:56:08 -04:00
2026-04-24 17:49:29 -07:00
2026-04-07 10:55:58 -07:00

npm i -g @openai/codex
or brew install --cask codex

Codex CLI is a coding agent from OpenAI that runs locally on your computer.

Codex CLI splash


If you want Codex in your code editor (VS Code, Cursor, Windsurf), install in your IDE.
If you want the desktop app experience, run codex app or visit the Codex App page.
If you are looking for the cloud-based agent from OpenAI, Codex Web, go to chatgpt.com/codex.


Quickstart

Installing and running Codex CLI

Install globally with your preferred package manager:

# Install using npm
npm install -g @openai/codex
# Install using Homebrew
brew install --cask codex

Then simply run codex to get started.

You can also go to the latest GitHub Release and download the appropriate binary for your platform.

Each GitHub Release contains many executables, but in practice, you likely want one of these:

  • macOS
    • Apple Silicon/arm64: codex-aarch64-apple-darwin.tar.gz
    • x86_64 (older Mac hardware): codex-x86_64-apple-darwin.tar.gz
  • Linux
    • x86_64: codex-x86_64-unknown-linux-musl.tar.gz
    • arm64: codex-aarch64-unknown-linux-musl.tar.gz

Each archive contains a single entry with the platform baked into the name (e.g., codex-x86_64-unknown-linux-musl), so you likely want to rename it to codex after extracting it.

Using Codex with your ChatGPT plan

Run codex and select Sign in with ChatGPT. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan. Learn more about what's included in your ChatGPT plan.

You can also use Codex with an API key, but this requires additional setup.

Docs

This repository is licensed under the Apache-2.0 License.

Description
No description provided
Readme Apache-2.0 1.3 GiB
Languages
Rust 96%
Python 3%
TypeScript 0.3%
Starlark 0.2%
Shell 0.2%
Other 0.1%