chore(migration): rename-aware filter-repo extraction driver

docs/marketplace-polyrepo-migration/migration/10-extract.sh

@@ -0,0 +1,80 @@
+#!/usr/bin/env bash
+# Step 3 — Rename-aware extraction driver.
+# Given a target key from plugin-map.json, clones the dedicated mirror ($WORK/_mirror, built by
+# 00-preflight.sh — never the working checkout, R4/M6) into $WORK/<key>, runs a SINGLE git filter-repo
+# pass composing --path / --path-rename (both names for renamed plugins, F1) + the deterministic
+# ms-ai-architect blob strip (F3), then strips carried-over tags and re-creates exactly one annotated
+# tag v<version> at the rewritten HEAD (F5). Idempotent (wipes $WORK/<key> first). NULL push (D8).
+#
+# Renamed plugins are extracted under BOTH historical names (F1), driven by plugin-map.json:
+#   voyage ← ultraplan-local, llm-security ← llm-security-copilot, linkedin-studio ← linkedin-thought-leadership.
+# A single-path filter would silently drop the pre-rename history, so the map carries >=2 --path entries each.
+#
+# Usage: 10-extract.sh <target-key>     (e.g. voyage, llm-security, playground-design-system)
+# Override WORK= to relocate the workspace (default /tmp/polyrepo-migration).
+set -euo pipefail
+
+KEY="${1:-}"
+[ -n "$KEY" ] || { echo "usage: 10-extract.sh <target-key>" >&2; exit 2; }
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+MAP="$SCRIPT_DIR/plugin-map.json"
+WORK="${WORK:-/tmp/polyrepo-migration}"
+MIRROR="$WORK/_mirror"
+DEST="$WORK/$KEY"
+
+fail() { printf 'EXTRACT FAIL: %s\n' "$*" >&2; exit 1; }
+
+[ -f "$MAP" ] || fail "plugin-map.json missing at $MAP"
+python3 -c "import json,sys; m=json.load(open('$MAP')); sys.exit(0 if '$KEY' in m['targets'] else 1)" \
+  || fail "unknown target '$KEY' (not in plugin-map.json)"
+
+# Self-heal: if the mirror is absent, run preflight to build it (extraction never reads the working checkout).
+if [ ! -e "$MIRROR/HEAD" ] && [ ! -d "$MIRROR/.git" ]; then
+  echo "  mirror absent → running preflight to build it"
+  WORK="$WORK" bash "$SCRIPT_DIR/00-preflight.sh" >/dev/null
+fi
+[ -e "$MIRROR/HEAD" ] || [ -d "$MIRROR/.git" ] || fail "mirror still absent after preflight: $MIRROR"
+
+# Compose the filter-repo arg list from the map (one arg per line → bash 3.2 array).
+ARGS_FILE="$(mktemp)"
+python3 - "$MAP" "$KEY" >"$ARGS_FILE" <<'PY'
+import json, sys
+m = json.load(open(sys.argv[1]))
+t = m["targets"][sys.argv[2]]
+out = []
+for p in t["paths"]:
+    out += ["--path", p]
+for old, new in t.get("path_renames", {}).items():
+    out += ["--path-rename", old + ":" + new]
+if t.get("blob_strip"):
+    if t.get("blob_strip_safe"):
+        out += ["--strip-blobs-bigger-than", "1M"]
+    else:
+        # Surgical fallback (unreached while blob_strip_safe is true): drop only the screenshots.
+        out += ["--path-glob", "!plugins/ms-ai-architect/playground/screenshots/*"]
+for a in out:
+    print(a)
+PY
+FR_ARGS=()
+while IFS= read -r line; do FR_ARGS+=("$line"); done <"$ARGS_FILE"
+rm -f "$ARGS_FILE"
+
+TAG="$(python3 -c "import json; print(json.load(open('$MAP'))['targets']['$KEY']['tag'])")"
+
+# Fresh --no-local clone from the mirror, then the single composing filter-repo pass.
+rm -rf "$DEST"
+git clone --no-local --quiet "$MIRROR" "$DEST"
+git -C "$DEST" filter-repo --force "${FR_ARGS[@]}"
+
+# F5: strip every carried-over tag, re-create exactly one annotated tag at the rewritten HEAD.
+OLD_TAGS="$(git -C "$DEST" tag)"
+if [ -n "$OLD_TAGS" ]; then
+  printf '%s\n' "$OLD_TAGS" | while IFS= read -r tg; do
+    [ -n "$tg" ] && git -C "$DEST" tag -d "$tg" >/dev/null
+  done
+fi
+git -C "$DEST" tag -a "$TAG" -m "Release $TAG (extracted from ktg-plugin-marketplace monorepo)"
+
+COMMITS="$(git -C "$DEST" rev-list --count HEAD)"
+echo "EXTRACT OK $KEY → $DEST ($COMMITS commits, tag $TAG)"

docs/marketplace-polyrepo-migration/migration/10-extract.test.mjs

@@ -0,0 +1,44 @@
+// Step 3 integration test — runs the extraction driver against the live monorepo (via the mirror)
+// and asserts F1 (renamed-plugin history retained), F5 (single clean re-tag), root-level contents,
+// and origin removal. Pattern: plugins/voyage/tests/integration/*.test.mjs.
+import test from 'node:test';
+import assert from 'node:assert/strict';
+import { spawnSync } from 'node:child_process';
+import path from 'node:path';
+import { fileURLToPath } from 'node:url';
+
+const here = path.dirname(fileURLToPath(import.meta.url));
+const SCRIPT = path.join(here, '10-extract.sh');
+const WORK = process.env.WORK || '/tmp/polyrepo-migration';
+const EXTRACT = path.join(WORK, 'voyage');
+
+const git = (args) => spawnSync('git', ['-C', EXTRACT, ...args], { encoding: 'utf8' });
+
+// Reuse the extract if the verify already produced it (tagged v5.1.1); otherwise build it.
+(function ensureExtract() {
+  const tag = git(['tag']);
+  if (tag.status === 0 && tag.stdout.trim() === 'v5.1.1') return;
+  const r = spawnSync('bash', [SCRIPT, 'voyage'], { encoding: 'utf8', env: { ...process.env, WORK } });
+  if (r.status !== 0) throw new Error(`extract failed (status ${r.status}):\n${r.stdout}\n${r.stderr}`);
+})();
+
+test('voyage extract retains pre-rename (ultraplan-local) history — F1', () => {
+  const n = parseInt(git(['rev-list', '--count', 'HEAD']).stdout.trim(), 10);
+  assert.ok(n >= 150, `expected >=150 commits (voyage + ultraplan-local), got ${n}`);
+});
+
+test('voyage extract carries exactly one tag: v5.1.1 (F5)', () => {
+  const tags = git(['tag']).stdout.trim().split('\n').filter(Boolean).sort();
+  assert.deepEqual(tags, ['v5.1.1']);
+});
+
+test('voyage extract has no plugins/ prefix — contents at repo root', () => {
+  const files = git(['ls-files']).stdout.trim().split('\n').filter(Boolean);
+  assert.ok(files.length > 0, 'extract should have tracked files');
+  assert.ok(!files.some((f) => f.startsWith('plugins/')), 'no tracked path should start with plugins/');
+  assert.ok(files.includes('.claude-plugin/plugin.json'), 'voyage plugin.json should be at repo root');
+});
+
+test('origin remote is removed post-filter', () => {
+  assert.equal(git(['remote']).stdout.trim(), '', 'filter-repo should remove the origin remote');
+});