fix: verify_eval_log works against current Inspect logs (0.3.1) - #21
Merged
Conversation
Inspect 0.3.x no longer records eval.dataset.sha, and results.scores[].name
carries the scorer name, not the metric -- so the from-log verification path
raised MalformedLogError ("missing fields: ['dataset_hash']") on every modern
log. A real user calling verify_eval_log would have hit this.
- verify_eval_log now accepts dataset_hash= and metric= overrides; both default
to whatever the log carries, so logs that include those fields are unaffected.
- the MalformedLogError now names exactly which fields to supply.
- +2 tests: override round-trip PASS, and helpful error when omitted.
- examples/offline-mockllm/: a fully offline, deterministic showcase running a
real Inspect eval with mockllm (no API key/network), PASS + a TAMPERED
model-swap via verify_live.
- bump 0.3.0 -> 0.3.1, CHANGELOG.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Inspect 0.3.x stopped recording eval.dataset.sha (and scores[].name is the scorer name, not the metric), so the from-log path raised MalformedLogError on every modern log. Adds dataset_hash= / metric= overrides (back-compatible), a clearer error, +2 tests, and an offline mockllm showcase. 34 tests green locally. Bumps 0.3.1.