v7.1.0

v7.1.0 Release Notes

What Changed

Mandatory Reuse Scan & Duplicate Prevention Gate

Added a hard-gated reuse scan protocol that runs before any new function, utility type, or class is written. The Reviewer independently re-verifies the scan, and the Architect enforces the verdict field.

Four-layer defense-in-depth:

1. Coder REUSE SCAN PROTOCOL — The Coder must semantically search src/utils/, src/hooks/, src/tools/, src/services/ for existing implementations before writing new code. Reports REUSE_SCAN in DONE output with self-audit checkbox.

2. Reviewer REUSE RE-VERIFICATION — The Reviewer independently runs 3+ semantic search queries per new export. DUPLICATION_DETECTED causes immediate Tier 1 CORRECTNESS rejection. Cross-checks the Coder's scan report. Outputs REUSE_RE_VERIFICATION in verdict format.

3. Slop Detector Passive Telemetry — New checkDuplicateUtility heuristic detects name collisions in utility directories at write/edit time. Advisory only — provides observability without blocking the pipeline.

4. Architect Enforcement — The Architect's Stage B gate mandates REUSE_RE_VERIFICATION field presence in reviewer verdicts. Completion checklist includes the field with semantic tuple validation (e.g., EXPORTS_ADDED non-empty → REUSE_RE_VERIFICATION must be VERIFIED or DUPLICATION_DETECTED).

Files Changed

• src/agents/coder.ts — REUSE SCAN PROTOCOL block, REUSE_SCAN field in DONE template, SELF-AUDIT checkbox
• src/agents/reviewer.ts — REUSE RE-VERIFICATION block, REUSE_RE_VERIFICATION in verdict/output format
• src/hooks/slop-detector.ts — DUPLICATE_UTILITY heuristic, type union extension
• src/agents/architect.ts — Stage B enforcement, ANTI-EXEMPTION pair, completion checklist
• src/agents/coder.test.ts — 15 tests for REUSE SCAN PROTOCOL
• src/agents/reviewer.test.ts — 14 tests for REUSE RE-VERIFICATION
• src/hooks/slop-detector.test.ts — 3 new tests for DUPLICATE_UTILITY
• src/agents/architect.commands-list.test.ts — 3 new tests for architect enforcement

Migration Steps

None. All changes are additive — no existing behavior is modified. The new gates activate automatically.

Known Caveats

• The slop detector's checkDuplicateUtility uses name-only collision detection (no signature analysis). False positives are possible but the heuristic is advisory-only.
• The reviewer's "implements the same behavior" criterion (step 3) requires human-level judgment — semantic similarity is assessed by the LLM, not a deterministic check.