Repository navigation
Add one-minute walkthrough and bounded assistant-operated smoke record - #93
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Reviewers can now watch a one-minute MP4/GIF walkthrough of the existing deletion-approval prototype and inspect a separate caller-operated smoke record. The current maintainer-assisted Codex session sent four JSON requests through a persistent stdin bridge: missing approval, wrong target, approved deletion, and attempted grant reuse. Actual filesystem postconditions were checked and the saved projection redacts the grant.
The record explicitly states that the host simulated approval, the assistant knew the scenario and had other parent-session tools, caller/model identity is not attested, and agent isolation and independent accuracy remain unvalidated. Separate CLI preflights failed to obtain a valid model response; those failures are not counted as evaluation samples. The rendered video labels these boundaries and is not presented as a screen recording.
Adds a reusable four-request bridge, failure-path and artifact-integrity tests, a development-only Pillow/ffmpeg renderer, and links from the challenge walkthrough. No runtime or package version changes.
Validation: local full suite (651 tests, 13 platform skips before the final artifact-integrity test was added); final focused bridge suite (4 passed); source hashes of the actual retained smoke; all four current-assistant requests; visual inspection of rendered frames; MP4 duration approximately 60 seconds. Full final cross-platform CI must pass before merge.