feat(robocasa): add reproducible resources and model identity - #126
Closed
ye1457 wants to merge 2 commits into
Closed
feat(robocasa): add reproducible resources and model identity#126ye1457 wants to merge 2 commits into
ye1457 wants to merge 2 commits into
Conversation
This was referenced Aug 28, 2026
Contributor
Author
|
Superseded by #130 for the basic integration. The replacement reuses the existing |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
RLDX-1-FT-RC365model and VLM metadatarobots.*backends plus the RoboCasa checkpoint manifest and delivery patch in built wheelsRLinf/robosuiteto the actually tested commit85abee228d1c43ab1939bce33028099945d453b4navviewXML patch required by perception-isolated RoboCasa runsensure_resourcespath, with explicit local-memory mode instead of silent fallbackReproduction boundary
This repository still does not contain model weights, RoboCasa assets, planner credentials, or memory payloads. Reproducers provision those inputs themselves. The future memory dataset is selected through the existing robot resource repository contract and will be downloaded at runtime; an offline local path requires explicit local mode.
The checkpoint attestation is generated locally after hashing user-provisioned files. It must be an owner-controlled regular file with mode
0600, and the VLA process validates both the authority and file identity before accepting it.The benchmark protocol and runner are deliberately excluded from this PR and remain follow-up layers for #21.
Verification
pytest -q: 31 passedruff check .: passedruff format --check .: passed