Use stable Guardian prompt cache keys (#24803)

Browse Source

## Why

Guardian review sessions are reusable across forks when their
`GuardianReviewSessionReuseKey` is unchanged, but the underlying
Responses request was still using the child thread ID as
`prompt_cache_key`. That meant forked Guardian reviews that should share
cache context produced different cache keys, reducing prompt cache reuse
and weakening the reuse invariant.

## What Changed

- Adds a `ModelClient` prompt cache key override and uses it for
`ResponsesApiRequest.prompt_cache_key`.
- Computes Guardian review cache keys as
`guardian:<sha1(parent_thread_id:reuse_key)>`, scoped to the parent
thread plus the reuse-sensitive Guardian config.
- Wires session construction to apply that override only for Guardian
sub-agent sessions.

## Testing

- Added coverage that Guardian cache keys are stable for the same
parent/reuse key, change when either the parent thread or reuse key
changes, fit within the Responses API length limit, and are absent for
non-Guardian sessions.
- Extended the parallel review test to assert forked Guardian reviews
send the same `prompt_cache_key`.

...

This commit is contained in:

jif-oai

2026-05-28 12:55:08 +02:00

committed by GitHub

Unverified

parent 4b9eda6ff6

commit 3307240195

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

Diff Content Not Available