[FIX] Research recipe valid=False on every backend blocks open_kitchen#4071
Merged
Trecek merged 7 commits intoJun 11, 2026
Merged
Conversation
…enforce - Add # tracking: #4069 comments to agent-eval and skill-eval entries in _KNOWN_NON_CONFORMING_RULES - Reduce _ALLOWLIST_CAP from 5 to 4 (research entry already removed) - Add test_known_non_conforming_entries_have_tracking_comments to enforce that every allowlist entry carries a tracking issue reference - Update tests/arch/AGENTS.md and resolve-review/SKILL.md registries Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The research diagram omitted the remediate, check_audit_retry_loop, and pre_remediation_cleanup steps added in commit c4b884c. Update the diagram to show the bounded remediation cycle between audit_impl and run_experiment. Refresh the autoskillit-recipe-hash to match the current research.yaml content. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Trecek
force-pushed
the
research-recipe-valid-false-on-every-backend-blocks-open-kit/4061
branch
from
ecd4309 to
b9cd8bd
Compare
Trecek
deleted the
research-recipe-valid-false-on-every-backend-blocks-open-kit/4061
branch
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
The
research.yamlbundled recipe ships withvalid=Falsebecause itsaudit_implstep capturesremediation_pathbut routes all non-GO outcomes toescalate_stop(a terminal stop action). Theaudit-impl-remediation-routesemantic rule correctly identifies this as a contract violation — the captured remediation file can never reach a downstream re-plan step. Combined with the fail-closed guard inopen_kitchen(tools_kitchen.py:720), this blocks the entire research recipe at runtime.The test suite has comprehensive infrastructure to catch this (
test_bundled_recipes_dispatch_ready.py), but the recipe was exempted in four separate locations rather than being fixed. The exemptions are test-layer-only — production'sload_and_validatehas no exemption mechanism, creating a disconnect: CI passes whileopen_kitchenfails.Implementation Plan
Plan file:
/home/talon/projects/autoskillit-runs/remediation-20260611-080055-165251/.autoskillit/temp/rectify/rectify_research_recipe_remediation_route_2026-06-11_080055.mdCloses #4061
🤖 Generated with Claude Code via AutoSkillit
Token Usage Summary
* Step used a non-Anthropic provider; caching behavior may differ.
Model Usage Breakdown