mirror of https://github.com/openai/codex.git synced 2026-11-10 21:00:47 +00:00

Files

T

Charlie Marsh d9446b4b01 Treat invalid access program stream errors as terminal (#60481 )

## Why

An `invalid_access_program` or `unsupported_access_program` streaming error should end the stream immediately, even if a later `response.completed` event arrives or the error includes a retry header.

## What changed

Map both error codes to `ApiError::InvalidRequest` and stop processing the response stream on invalid requests. Preserve a nonblank provider message, falling back to an explanation that the requested access program cannot be used with the model.

## Testing

Extend the terminal-error test to cover both codes in `error` and `response.failed` events, verifying that retry headers are ignored and the stream ends before a later completion event.

GitOrigin-RevId: 5431a2babec64eae5cdf6c138b98e91e84778e79

2026-11-10 00:55:01 +00:00

src

Treat invalid access program stream errors as terminal (#60481 )

2026-11-10 00:55:01 +00:00

tests

Add per-turn prompt cache TTL options (#59480 )

2026-11-04 19:58:24 +00:00

BUILD.bazel

feat: add support for building with Bazel (#8875 )

2026-01-09 11:09:43 -08:00

Cargo.toml

Preserve WebSocket probe evidence and redact diagnostic details (#57597 )

2026-10-27 23:51:43 +00:00

README.md

Normalize formatting in docs, web assets, and sample scripts (#52256 )

2026-10-08 20:11:43 +00:00

README.md

codex-api

Typed clients for Codex/OpenAI APIs built on top of the generic transport in codex-client.

Hosts the request/response models and request builders for Responses and related Codex APIs.
Owns provider configuration (base URLs, headers, query params), auth header injection, retry tuning, and stream idle settings.
Parses SSE streams into ResponseEvent/ResponseStream, including rate-limit snapshots and API-specific error mapping.
Serves as the wire-level layer consumed by codex-core; higher layers handle auth refresh and business logic.

Core interface

The public interface of this crate is intentionally small and uniform:

Responses endpoint
- Input:
  - ResponsesApiRequest for the request body (model, input, tools, parallel_tool_calls, reasoning/text controls).
  - ResponsesOptions for transport/header concerns (conversation_id, session_source, extra_headers, compression, turn_state).
- Output: a ResponseStream of ResponseEvent (both re-exported from common).
Memory summarize endpoint
- Input: MemorySummarizeInput (re-exported as codex_api::MemorySummarizeInput):
  - model: String.
  - raw_memories: Vec<RawMemory> (serialized as traces for wire compatibility).
    - RawMemory includes id, metadata.source_path, and normalized items.
  - reasoning: Option<Reasoning>.
- Output: Vec<MemorySummarizeOutput>.
- MemoriesClient::summarize_input(&MemorySummarizeInput, extra_headers) wraps JSON encoding and retry/telemetry wiring.

All HTTP details (URLs, headers, retry/backoff policies, SSE framing) are encapsulated in codex-api and codex-client. Callers construct prompts/inputs using protocol types and work with typed streams of ResponseEvent or other endpoint-specific response values.