agentic-sdlc-wizard 1.48.0 → 1.50.0

package/.claude-plugin/marketplace.json

@@ -13,7 +13,7 @@
       "name": "sdlc-wizard",
       "source": ".",
       "description": "SDLC enforcement for AI agents — TDD, planning, self-review, CI shepherd",
-      "version": "1.48.0",
+      "version": "1.50.0",
       "author": {
         "name": "Stefan Ayala"
       },

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "sdlc-wizard",
-  "version": "1.48.0",
+  "version": "1.50.0",
   "description": "SDLC enforcement for AI agents — TDD, planning, self-review, CI shepherd",
   "author": {
     "name": "Stefan Ayala",

package/CHANGELOG.md

@@ -4,6 +4,50 @@ All notable changes to the SDLC Wizard.
 
 > **Note:** This changelog is for humans to read. Don't manually apply these changes - just run the wizard ("Check for SDLC wizard updates") and it handles everything automatically.
 
+## [1.50.0] - 2026-04-27
+
+### Added
+
+- **`local-shepherd.sh --strip-paths` flag** — closes ROADMAP #231 Phase 2. When CC ships native equivalents to wizard custom features, the maintainer runs `local-shepherd.sh <PR> --compare-baseline --strip-paths '[paths]'` locally on Max to A/B compare wizard-with-features (baseline) vs wizard-without-stripped-features (candidate). Same-commit comparison (no main worktree). Both `BASELINE_DIR` and `CANDIDATE_DIR` are tmpdirs laid out as project roots; the candidate's fixture has the requested paths removed via `create_stripped_fixture` from `tests/e2e/lib/prove-it.sh` (single source of truth for the allowlist). Score-history rows tagged with `comparison_role: "baseline" | "candidate"` (same contract as plain `--compare-baseline`).
+  - **Validation**: paths must be in `REMOVABLE_ALLOWLIST` from `tests/e2e/lib/prove-it.sh`. Non-allowlisted paths (e.g. `/etc/passwd`) are rejected — security against LLM-hallucinated arbitrary deletions.
+  - **Constraint**: `--strip-paths` requires `--compare-baseline` (lone `--strip-paths` exits with a clear error). No silent fall-through to single-run mode.
+  - 8 new quality tests (30/30 total in `test-local-shepherd.sh`).
+
+### Removed
+
+- **`prove-it-test` job in `.github/workflows/weekly-update.yml`** (251 lines) — replaced by the local `--strip-paths` flag. The CI job ran $6-12 per overlap detection with zero merged artifacts in 30 days. Local-Max replacement is $0 (sim leg on subscription) and gives the maintainer richer context to decide KEEP CUSTOM / SWITCH TO NATIVE.
+
+### Changed
+
+- `tests/test-prove-it.sh`: replaced workflow-existence tests (#11-#12) with local-shepherd integration tests; added a regression test that the `prove-it-test` job stays deleted. All 20 tests green.
+- `CI_CD.md` and `plans/AUTO_SELF_UPDATE.md`: updated to document the local replacement workflow. Historical section preserves the deleted CI job's intent.
+
+### Files
+
+- `tests/e2e/local-shepherd.sh` (+105 lines, ~35 changed)
+- `tests/test-local-shepherd.sh` (+~180 lines, +8 tests)
+- `tests/test-prove-it.sh` (replaced 3 tests with 4 better-targeted ones)
+- `.github/workflows/weekly-update.yml` (-251 lines)
+
+## [1.49.0] - 2026-04-27
+
+### Added
+
+- **`local-shepherd.sh --compare-baseline` flag** — closes ROADMAP #230. When set, the shepherd runs the same scenario on `main` (via `git worktree add --detach`) AND the current branch, then posts a baseline-vs-candidate delta to the check-run + PR comment. Both score-history rows are tagged with `comparison_role: "baseline" | "candidate"` so trend analytics can distinguish comparison runs from regular shepherd runs. Single-run mode (no flag) is unchanged for backward compat — no `comparison_role` field on those rows.
+  - **Atomic write** (Codex P1 round 1): both rows are appended together AFTER candidate sim+eval succeeds. A candidate failure leaves zero comparison rows in history (no orphan baseline). Verified by `test_compare_baseline_no_orphan_row_on_candidate_failure`.
+  - **Tempdir hygiene** (Codex P1 round 1): `BASELINE_TMPRUN` is nested under `TMPRUN` so the existing `trap` cleans it up on every exit path. No leaks even on early failures (history mkdir, evaluator crash). Verified by `test_compare_baseline_no_baseline_tmprun_leak`.
+  - 9 new quality tests (22/22 total in `test-local-shepherd.sh`). Codex round 2 CERTIFIED 9/10 (round 1 found 2 P1s, both fixed).
+- **Unblocks ROADMAP #231 Phase 2** — weekly-update workflow migration (currently burning $25-55/week on API). With `--compare-baseline`, the maintainer can run the comparison locally on Max instead of paying for it in CI.
+
+### Changed
+
+- `local-shepherd.sh`: provenance fields (`HOST_OS`, `CLI_VERSION`, `AUTH_MODE`, `EXECUTION_PATH`) now computed ONCE before any sim runs. Previously duplicated between baseline and candidate paths; consolidated for both DRY and correctness.
+
+### Files
+
+- `tests/e2e/local-shepherd.sh` (+247 lines, ~50 changed)
+- `tests/test-local-shepherd.sh` (+~280 lines, +9 tests)
+
 ## [1.48.0] - 2026-04-27
 
 ### Changed

package/CLAUDE_CODE_SDLC_WIZARD.md

@@ -2967,7 +2967,7 @@ If deployment fails or post-deploy verification catches issues:
 
 **SDLC.md:**
 ```markdown
-<!-- SDLC Wizard Version: 1.48.0 -->
+<!-- SDLC Wizard Version: 1.50.0 -->
 <!-- Setup Date: [DATE] -->
 <!-- Completed Steps: step-0.1, step-0.2, step-0.4, step-1, step-2, step-3, step-4, step-5, step-6, step-7, step-8, step-9 -->
 <!-- Git Workflow: [PRs or Solo] -->
@@ -4032,7 +4032,7 @@ Walk through updates? (y/n)
 Store wizard state in `SDLC.md` as metadata comments (invisible to readers, parseable by Claude):
 
 ```markdown
-<!-- SDLC Wizard Version: 1.48.0 -->
+<!-- SDLC Wizard Version: 1.50.0 -->
 <!-- Setup Date: 2026-01-24 -->
 <!-- Completed Steps: step-0.1, step-0.2, step-1, step-2, step-3, step-4, step-5, step-6, step-7, step-8, step-9 -->
 <!-- Git Workflow: PRs -->

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agentic-sdlc-wizard",
-  "version": "1.48.0",
+  "version": "1.50.0",
   "description": "SDLC enforcement for Claude Code — hooks, skills, and wizard setup in one command",
   "bin": {
     "sdlc-wizard": "cli/bin/sdlc-wizard.js"

package/skills/update/SKILL.md

@@ -93,9 +93,11 @@ Parse CHANGELOG entries between the user's installed version and latest. Present
 
 ```
 Installed: 1.42.0
-Latest:    1.48.0
+Latest:    1.50.0
 
 What changed:
+- [1.50.0] local-shepherd.sh --strip-paths flag (#231 Phase 2 — replaces deleted prove-it-test cron)
+- [1.49.0] local-shepherd.sh --compare-baseline flag (#230)
 - [1.48.0] SKILL.md trim — token bloat audit phase 2 follow-up
 - [1.47.0] Codex review progress wrapper (#259)
 - [1.46.1] npx check surfaces dangling+enabled plugin state (#266)