feat(config+preflight): warn that non-default models.qa LLM bindings are inert (P0-02)#118
Merged
Merged
Conversation
…are inert The QA stage is command-based (lint/build/test, engine/qa.go) — an LLM bound to the qa role is never called. Operators setting models.qa (e.g. codex/gpt-5.5) expected a review pass that never happened, and cost estimates looked wrong. The config still accepts the binding, but is no longer silent about it. - config.Config.Warnings(): non-fatal advisories; warns when models.qa differs from the shipped default (an explicit operator statement of intent), pointing at models.reviewer as the real LLM review binding. The default binding stays silent — warning every install is noise. - vxd config validate prints warnings before the PASSED line. - New qa_model preflight check (CheckQAModelInert / testable CheckQAModelInertWith), WARNING tier; AllChecks 18 → 19. - Tests: TestConfigValidate_QAModelInertWarning, TestPreflight_QAModelInertCheck; pinned counts updated (checks_test.go, TestAudit_PreflightCheckCounts). - Docs: README/CLAUDE.md/AGENTS.md check counts + Codex caveat note. Closes WEAKNESSES.md P0-02. Co-Authored-By: Claude Fable 5 <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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
qarole is never called. Operators settingmodels.qa(e.g.codex/gpt-5.5) expected a review pass that never happened; cost estimates looked wrong.config.Config.Warnings()(non-fatal advisories): warns whenmodels.qadiffers from the shipped default, pointing atmodels.reviewer.vxd config validateprints warnings.qa_modelpreflight check (CheckQAModelInert, WARNING tier); AllChecks 18 → 19 with pinned counts + docs updated (README/CLAUDE.md/AGENTS.md,TestAudit_PreflightCheckCounts).Tests
TestConfigValidate_QAModelInertWarning,TestPreflight_QAModelInertCheck, updated count pins.Closes WEAKNESSES.md P0-02.
🤖 Generated with Claude Code