Skip to content

feat: SVP philosophy section + signature extraction removal cleanup#15

Merged
xycld merged 8 commits intomainfrom
dev
Mar 24, 2026
Merged

feat: SVP philosophy section + signature extraction removal cleanup#15
xycld merged 8 commits intomainfrom
dev

Conversation

@xycld
Copy link
Copy Markdown
Member

@xycld xycld commented Mar 24, 2026

Summary

  • Comprehensive SVP philosophy section added to /svp skill (all adapters)
  • CONTENT_DRIFT dead documentation cleaned from workflow templates
  • Benchmark suite removed from repo (kept as independent local project)

Key Changes

SVP Philosophy in /svp Skill

Teaches AI agents the WHY behind SVP methodology:

  • Entropy spiral: why design-implementation drift kills projects
  • Compilation model: why one-way, why irreversible
  • L3 as pivot layer: precision determines compilation quality
  • refs/ as header files: missing context = wrong output
  • Error response: fixing L3 beats fixing L1
  • Context isolation: cognitive protection for main agent
  • Translation Validation: only viable strategy for non-deterministic compilers

Cleanup

  • Removed dead CONTENT_DRIFT workflow sections from shared adapter
  • Removed benchmark suite from repo (independent project)

Test plan

  • npx tsc --noEmit — zero errors
  • npx vitest run — 730/730 tests pass

xycld added 8 commits March 21, 2026 20:35
CONTENT_DRIFT diagnosis was removed as part of the Translation Validation
philosophy shift. Clean up the remaining workflow text in both Chinese
and English prompt templates.
Multi-tenant e-commerce SaaS benchmark with:
- Complete OpenSpec (2864 lines, 20 rounds, Chinese)
- OpenAPI 3.1 contract (45 endpoints, 36 schemas)
- 287 data-driven E2E test cases across 20 rounds
- Test runner with variable capture and cross-round persistence
- /bench-ai and /bench-svp slash commands for execution
- CONTENT_DRIFT dead documentation cleanup in shared.ts
Instead of reimplementing SVP methodology, bench-svp now instructs the
agent to strictly follow the original /svp skill. Only change: alignment
checkpoints auto-approve instead of waiting for user confirmation.

Key enforcements added:
- Must load and follow .claude/commands/svp.md
- Forbidden to skip SVP flow or write L1 code directly
- Every new endpoint must have a corresponding L3 block
- All code changes via subagent dispatch only
Teaches AI agents the WHY behind SVP, not just the HOW:
- L3 IS the API contract (pins = params, constraints = rules)
- One-way compilation: errors trace upward, never edit L1 directly
- Reference docs belong in refs/ (auto-injected into compile prompts)
- Context isolation: main Agent orchestrates, subagents write code

This addresses the root cause of benchmark failures: agents abandoned
SVP methodology because they understood the steps but not the principles.
When compilation output didn't match the API contract, they defaulted to
directly editing L1 instead of fixing L3 and recompiling.
Copilot AI review requested due to automatic review settings March 24, 2026 11:38
@xycld xycld merged commit 182bb37 into main Mar 24, 2026
8 checks passed
Copy link
Copy Markdown

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR updates the generated /svp skill content (shared across host adapters) by adding a new “SVP Philosophy” section, removes dead CONTENT_DRIFT workflow documentation from the shared workflow templates, and tweaks repo housekeeping around benchmarks/ignores.

Changes:

  • Add a Philosophy section (EN/ZH) to the shared skill file assembly.
  • Remove CONTENT_DRIFT blocks from the shared workflow templates.
  • Adjust TypeScript/glob and ignore configuration as part of benchmark cleanup.

Reviewed changes

Copilot reviewed 1 out of 3 changed files in this pull request and generated no comments.

File Description
tsconfig.json Updates TS include globs (currently includes benchmark/**/*.ts).
packages/skills/adapters/shared.ts Adds getPhilosophySection() and injects it into skill file generation; removes CONTENT_DRIFT workflow documentation blocks.
.gitignore Comment-only clarification for hidden-directory re-ignore/whitelist behavior.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants