Use captured step settings for request metadata and tool hooks (#45248)

## Why

Model and reasoning effort updates during a turn can leave request metadata and tool hooks reporting the turn's initial settings. Metadata should describe the step that issued the request or tool call.

## What changed

- Share captured execution metadata across Responses, MCP, and extension tool calls, including model, reasoning effort, and automatic review and Node REPL flags.
- Build Responses tool inventory metadata from the issuing step's finalized tool router. Attach the finalized inventory separately for remote compaction.
- Use captured step settings for pre- and post-tool hooks, and captured review settings for permission-request hooks.

## Testing

Add and extend regression tests for model and effort changes during a turn, MCP metadata, pre-tool hook model attribution, captured review flags, and tool inventory matching the issuing request.

GitOrigin-RevId: 9dee46a8b4839de8b434cdad4ed441cc0bb6ff9b
This commit is contained in:
Abhinav authored and copyberry committed 2026-09-13 15:47:59 +00:00
1 parent 36f0dbe796
commit 16537b20a5
20 files changed
+545 -255

No files matched your search

+1 -1
View File
@@ -98,7 +98,7 @@ pub(crate) async fn finalize(
ReasoningSummary::None,
/*service_tier*/ None,
&session
.responses_metadata(&step.turn, CodexResponsesRequestKind::Turn)
.responses_metadata(step, CodexResponsesRequestKind::Turn)
.await,
)?;
let mut existing = super::request_budget::estimate_request_tokens(&request)