Snapshot resolved settings for each model step (#40651)

## Why

Thread settings can change while a turn is running, and delegated review or
compaction steps can select a different model. Each request needs a consistent
set of settings resolved against the model that will execute it.

## What changed

- Capture immutable resolved settings for each model step, including model
  metadata, reasoning options, service tier, approvals, and personality.
- Keep in-flight steps on their captured settings while applying thread updates
  to subsequent work.
- Resolve inherited reasoning summaries and filter service tiers against the
  selected model and feature configuration for review and compaction steps.

## Testing

Added coverage for settings updates during paused turns, model changes,
previous-model compaction, review-model defaults, and service-tier filtering.

GitOrigin-RevId: fca4b3b305379f1bf26a5cac75ee0dd1747ac1f6
This commit is contained in:
joeflorencio-openai authored and copyberry committed 2026-08-25 17:41:22 +00:00
1 parent ba6cf9c692
commit 68301fa45f
68 files changed
+1393 -516

No files matched your search

+2 -2
View File
@@ -130,7 +130,7 @@ impl PreparedTurnInputSettings {
updates.final_output_json_schema = Some(final_output_json_schema);
updates.service_tier_for_turn = service_tier;
let turn = match kind {
let turn_context = match kind {
TurnStartKind::User | TurnStartKind::Recovery => Some(
session
.new_turn_with_sub_id(submission_id.clone(), updates)
@@ -144,7 +144,7 @@ impl PreparedTurnInputSettings {
.await?
}
};
let Some((turn_context, settings_snapshot)) = turn else {
let Some((turn_context, settings_snapshot)) = turn_context else {
return Ok(None);
};
if emit_thread_settings_applied {