Repository navigation
Conversation
CI now posts the stored attack plans at policy and fails if a named code stops firing. The scorecard records that local run and a mock-planner pass. A live model was not called.
The firewall and mock traces now name the commit that added the cases. delayed-instruction latency on this pass is 1 ms. A live model was still not called.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
This branch was successfully deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
The fixture job checks canned plans. It does not fail when the payment-firewall cases start passing, and nothing in the repo shows the last real run of those cases.
Solution
packages/evals/attacks/v1holds eleven stored plans for the standing invoice. CI posts them at policy. A missing code, an allow on a deny case, or a missing frozen id fails the job./scorecardanddocs/scorecard.mdcopy the local firewall run (11 held, 0 failed) and the mock-planner traces. A live model was not called. The nightly workflow runs only on this repository and skips when the Anthropic key, the model, or the token prices are unset. That skip is not a score.How to test
:8090and runnpm testinpackages/evals./scorecard. The table matchespackages/evals/scorecard/firewall.json.EVAL_PLANNER=mock npm run test:attacksreplays the mock traces. There is no live-model number to check.