Track cumulative MCP attribution across requests and thread history (#47081)

mirror of https://github.com/openai/codex.git synced 2026-11-13 21:30:47 +00:00

## What changed

- Record each MCP source and its first turn, including connector and plugin identifiers when available. Cover direct and Code Mode calls, including returned errors and results that are not printed.
- Persist cumulative attribution checkpoints and restore them across compaction, resume, and forks, including forks limited to recent turns.
- Attach fresh attribution to Responses API `client_metadata` under `mcp_attribution`, outside model-visible content. Restrict transmission to allowed OpenAI HTTPS destinations for both HTTP and WebSocket requests.
- Report `attribution_error` for legacy history without checkpoints, malformed or conflicting attribution, and serialized attribution exceeding 16 KiB.

## Testing

Add coverage for source deduplication, checkpoint persistence and restoration, recent-turn forks, direct and Code Mode calls, destination filtering, and the serialized size limit.

GitOrigin-RevId: fd285e152ca9e24bfa000debb20013709d67a86e

This commit is contained in:

peilin-openai

2026-09-21 18:19:07 +00:00

committed by

copyberry

parent 7cec3e110c

commit ac98537678

28 changed files with 1119 additions and 73 deletions

									
										codex-rs/utils/string/src/lib.rs
									
		+1
		
												View File
												
				@@ -2,6 +2,7 @@ mod json;

				mod truncate;

				pub use json::to_ascii_json_string;

				pub use json::to_json_string_bounded;

				pub use truncate::approx_bytes_for_tokens;

				pub use truncate::approx_token_count;

				pub use truncate::approx_tokens_from_byte_count;