feat: user sovereignty — AI models recommend, users decide (v0.13.2.0)#603
Merged
feat: user sovereignty — AI models recommend, users decide (v0.13.2.0)#603
Conversation
When Claude and Codex agree on a scope change, they now present it to the user instead of auto-incorporating it. Adds User Sovereignty as the third core principle in ETHOS.md. Fixes the cross-model tension template in review.ts to present both perspectives neutrally instead of judging. Adds User Challenge category to autoplan with proper contract updates (intro, important rules, audit trail, gate handling). Adds Outside Voice Integration Rule to CEO and eng review templates.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
E2E Evals: ❌ FAIL56/57 tests passed | $6.00 total cost | 12 parallel runners
12x ubicloud-standard-2 (Docker: pre-baked toolchain + deps) | wall clock ≈ slowest suite Failures
|
…iting it Codex kept overwriting agents/openai.yaml with a browse-only description. Two fixes: (1) better description covering full PM/dev/eng/CEO/QA scope, (2) add agents/ to the filesystem boundary so Codex stops modifying it.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
When Claude and Codex agree on a scope change, they were auto-incorporating it without asking the user. Real incident: Codex said "merge two skills into one," Claude assessed "outside voice is right" and just did it. User had to push back twice.
This PR adds User Sovereignty as gstack's third core principle. Two root causes fixed:
review.tscross-model tension template said[Your assessment of who's right.], letting Claude judge and act. Now says[Present both perspectives neutrally. State what context you might be missing.]with expanded options (Accept/Keep/Investigate/Defer).autoplan/SKILL.md.tmplhad "auto-decide replaces the USER's judgment" with no carve-out for scope changes. Now has a User Challenge category that is never auto-decided, with proper contract updates (intro, important rules, audit trail schema, gate handling).Changes across 6 source files + 25 regenerated SKILL.md files:
Pre-Landing Review
Template-only changes (prompt text, no application code). Existing skill-validation and gen-skill-docs tests cover template correctness.
Outside Voice (Codex)
Codex plan review found 8 issues. Key accepted: autoplan contract breakage (intro text, important rules, audit trail schema, gate handling all need updating). Blocker carve-out for security/feasibility added per user decision.
Test plan
bun testpasses (pre-existing failures only, verified on main)bun run gen:skill-docsregenerates all 30 SKILL.md files successfully🤖 Generated with Claude Code