Document plan B for field-testing while the hostile gate is environmentally red#50
Merged
Conversation
The 2026-07-14 session showed the hostile gate fails for reasons no prompt edit can fix (stale published docs, release freshness), so document how to keep testing: stub self-test, standard persona, hostile rounds attributed by refusal reason, and a possible local-registry mode. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
Concise, comprehensive Plan B documentation supplements the field-testing README effectively. 🎯 Quality: 99% Elite · 📦 Size: Small 📈 This month: Your 214th PR — above team average · Averaging Elite |
mariojgt
approved these changes
Jul 14, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds a "plan B" section to
field-test/README.mdfor the situation the 2026-07-14 session hit: the hostile gate failing for reasons no prompt edit can fix, because agents audit the published tarball (stale shipped docs) and treat release freshness as an attack signal. It explains the two environmental drivers and their different decay (publishing fixes the docs but resets the freshness clock; re-gate 24–48h after a publish), then gives an escalation ladder for immediate testing: stub self-test, standard persona, hostile rounds scored by refusal reason rather than exit code, and a not-yet-built local-registry mode for exercising unpublished changes end-to-end.🤖 Generated with Claude Code