feat: independently grade robot evidence and expose all GPU agent trials - #10
Merged
Merged
Conversation
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Agent workflow completion and skill delivery do not establish task acceptance. Add a robot-evidence-review task with independently derived numerical checks and six fault controls, a bounded non-root model workspace, separate Docker startup readiness, and Harbor/ATIF interoperability.
The new homepage explorers retain 27 real skill-delivery trials, 12 composition trials and six cross-model handoffs, including all failures, candidate files, original receipts and independent grades. Source-checked manifests reject invented headlines even when rehashed. Funes retrieval and native Harbor oracle/NOP execution are recorded; no efficacy gain or full-benchmark claim is made.
Validation: 302 tests; Ruff check/format; independent installed-wheel checks for both robot task languages; real Python/JavaScript Docker fault audits; 33 exports validated by Harbor0.23.0's ATIF schema; browser checks at1440/390/320 including recovery and shared state. Version0.9.0. Public immutable dataset: https://huggingface.co/datasets/glayguo/noteflow-research-pilots/tree/v2026-09-14.