fix: eval isolation was inert — schema-valid plugin-disable map + real-argv tests - #14
Merged
Merged
Conversation
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01VRajFkyg9aBwbUFMhVaxNe
…uator findings)
Argv-recording stub replaces the model CLI: baseline leg must carry no --plugin-dir and a
schema-valid enabledPlugins OBJECT map disabling every user-enabled plugin; plugin arm must
carry --plugin-dir plus the same disable map; unparseable user settings fail closed.
Currently red: the runner passes the inert '{"enabledPlugins":[]}'.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VRajFkyg9aBwbUFMhVaxNe
…map, fail-closed Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01VRajFkyg9aBwbUFMhVaxNe
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01VRajFkyg9aBwbUFMhVaxNe
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Repairs the defect the independent closeout evaluator found when refuting the first baseline campaign (see PR #13's hold comment).
--settings '{"enabledPlugins":[]}'was schema-invalid (array vs object map) and silently disabled nothing — all threenonerows ran with user plugins (incl. lcd) loaded.{"enabledPlugins":{"<plugin>":false,…}}from the operator's real settings; fail-closed on unparseable settings or missingjq.--plugin-dirin baseline; disable map present in both arms) — replacing the printed-plan string checks the evaluator flagged.Campaign re-run under verified isolation follows; PR #13 will be updated with clean rows.
🤖 Generated with Claude Code
https://claude.ai/code/session_01VRajFkyg9aBwbUFMhVaxNe