fix(rollout): persist post-action frames - #209
Open
Vedangalle wants to merge 5 commits into
Open
Conversation
Vedangalle
marked this pull request as ready for review
July 28, 2026 21:32
jeqcho
force-pushed
the
agent/persist-post-action-frames
branch
from
July 29, 2026 06:15
ca7340d to
25c30bc
Compare
Collaborator
|
Heads up: main's history was rewritten today to purge 3 GB of accidentally committed eval logs (#212). Your branch was based on one of the rewritten commits, so I rebased it onto the new main and force-pushed (maintainer edits are enabled on this PR). No changes to your commits themselves; CI will re-run. If you have local work on this branch, run git fetch and rebase onto the updated remote branch before pushing. |
Updated StepRecord to include result_image_refs and modified frame storage logic.
Vedangalle
force-pushed
the
agent/persist-post-action-frames
branch
from
July 29, 2026 06:50
25c30bc to
c98fd9c
Compare
Contributor
Author
|
@jeqcho When you have a chance, I’d appreciate your (any) feedback on the FrameStore contract here - particularly whether |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Persist every distinct rollout observation through
FrameStore, including the terminal post-action state.Previously, the rollout stored only each step's pre-action observation. That left full camera arrays inside
StepResult.observationand gave the terminal observation no sidecar reference, because it never becomes a later step's pre-action input.Changes
0and each step result att + 1;StepRecord.result_image_refsfor post-action frame handles;plans/0032-post-action-frame-persistence.md;A one-camera rollout with
nsteps now writes exactlyn + 1frame files.Compatibility
result_image_refsis appended with a default ofNone.FrameStorepreserve the original observation and result objects.StepRecordis not part of the schema-versionedEvalLog, so no log migration is required.Verification
main: 876 passed, 3 skippedruff check .passesruff format --check .passesmypypassesCHANGELOG.mdupdated under "Unreleased"The gap surfaced while building a process-aware evaluator on top of Inspect Robots: https://github.com/Vedangalle/inspect-robots-verifier