mirror of https://github.com/openai/codex.git synced 2026-10-20 17:38:45 +00:00

Files

T

jif bc9cad3473 Treat incomplete responses as terminal errors (#53451 )

## Why

Incomplete responses such as `max_output_tokens` were classified as stream errors, allowing retries and compaction model fallback after the response had hit its output limit.

## What changed

Introduce `ResponseIncomplete` errors that preserve the server-provided reason and stop stream processing immediately. Make these errors non-retryable and stop compaction without falling back to the selected model. Record incomplete responses separately in sampler failure metrics.

## Testing

Add regression tests that verify incomplete responses surface a terminal error without retries over SSE and WebSocket, and that compaction stops without retrying or switching models for both local and remote compaction.

GitOrigin-RevId: 6e107d441b9bf03fa47ea47b88eeb94b71a9f729

2026-10-12 18:53:49 +00:00

src

Treat incomplete responses as terminal errors (#53451 )

2026-10-12 18:53:49 +00:00

BUILD.bazel

build: run buildifier from just fmt (#28125 )

2026-06-13 21:43:39 -07:00

Cargo.toml

Truncate input text in protocol debug output (#49415 )

2026-09-30 00:51:15 +00:00

README.md

fix: separate codex mcp into codex mcp-server and codex app-server (#4471 )

2025-09-30 07:06:18 +00:00

README.md

codex-protocol

This crate defines the "types" for the protocol used by Codex CLI, which includes both "internal types" for communication between codex-core and codex-tui, as well as "external types" used with codex app-server.

This crate should have minimal dependencies.

Ideally, we should avoid "material business logic" in this crate, as we can always introduce Ext-style traits to add functionality to types in other crates.