codex

mirror of https://github.com/openai/codex.git synced 2026-11-11 21:10:39 +00:00

Files

T

felixxia-oai 624b45c4dc Run Guardian conversation classifiers concurrently and preserve action order (#52061 )

## Why

A conversation classifier waiting for preparation or full response completion can block newer classifications. Concurrent reviews also need to prevent a later action's evidence or low-risk score from being reused for an earlier action.

## What changed

- Run conversation classifications independently, forking the latest compatible completed history from an earlier action. Only a valid completion with a newer action index can replace retained history.
- Keep admission and observation ordering atomic, and hold capacity permits through full response completion.
- Reject cached low-risk scores from later actions for tool-linked approvals, including initial approval checks.
- Track originating tool-call IDs separately from approval display IDs, preserving stdin write provenance and excluding synthetic MCP elicitation IDs from tool ordering.

## Testing

Add regression coverage for delayed preparation, capacity admission, out-of-order completion, cancellation, invalid retained output, and history snapshots. Exercise pending approval ordering in both `snapshot` and `conversation` modes, and verify linked and unlinked MCP elicitation provenance.

GitOrigin-RevId: 097476ccb3b8718369a69f55c3c39132f7f1a4c1

2026-10-08 10:42:28 +00:00

Run Guardian conversation classifiers concurrently and preserve action order (#52061 )

2026-10-08 10:42:28 +00:00

auth.rs

Expose selected workspace routing in app-server account reads (#45529 )

2026-09-14 22:31:32 +00:00

conversation_summary.rs

Apply shared network policy throughout embedded Codex startup (#47411 )

2026-09-23 00:49:19 +00:00

fuzzy_file_search.rs

Simplify app-server integration test setup (#34786 )

2026-07-22 16:30:12 +00:00