product-video, vos-footage: verified it with agent-browser? make it a take - #20
Merged
Conversation
evals/count.mjs runs vos validate --json over every kit a run produced and prints the one deterministic line a results file ends on (N problems across M assets on K kits), exit 1 on any problem. Re-run on the two adopter kits it reproduces the published number, 0 across 22. evals/launch-kit/RUN.md is the procedure for a model tier: the fixtures, the skill installed project-scope for the agent under test, the blind A/B against a no-skill copy (the baseline every scenario file asked for), the non-interactive claude -p and codex exec commands, the results file shape. The scenarios header, the results README and the repo README point at it.
… take agent-browser's --json result does not say what ran, so the skills give the agent a one-line ab() wrapper that keeps each command beside its result (the batch record shape), and vos actions from-agent-browser (plugin 0.22.0) writes actions.json from that log, naming whatever the recorder cannot follow. The product-video description says when to reach for it.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The OG6 seam, skill side. agent-browser leaves no command log and its
--jsonresult does not carry its arguments (scrollanswers{scrolled:true}; a ref is role and name in the preceding snapshot only), so the skills give the agent a one-lineab()wrapper that keeps each command beside its result, the same record shape agent-browser's ownbatchemits.vos actions from-agent-browser steps.jsonl(plugin 0.22.0) writesactions.jsonfrom that log and names every step the recorder cannot follow.product-video: the paragraph under step 1 of the core loop, and the description says when to reach for it.vos-footage: one sentence under "Record the real thing".node scripts/check.mjspasses.