@topy-ai/maggie 0.5.0 → 0.5.1

package/README.md

@@ -80,8 +80,8 @@ with `--confirm`, removes only known retired EmDash artifacts. It preserves
 Recommended upgrade sequence for the current release:
 
 ```bash
-npx @topy-ai/maggie@0.2.9 update --project . --force
-npx @topy-ai/maggie@0.2.9 cleanup --project .
+npx @topy-ai/maggie@0.5.1 update --project . --force
+npx @topy-ai/maggie@0.5.1 cleanup --project .
 ```
 
 ## MaggieDash lifecycle

package/bin/maggie.js

@@ -208,7 +208,11 @@ function install(args) {
   const tools = join(root, "tools");
   if (existsSync(TOOLS_ROOT)) {
     for (const group of ["clis", "runtime", "integrations"]) {
-      if (existsSync(join(TOOLS_ROOT, group))) copyIfMissing(join(TOOLS_ROOT, group), join(tools, group), force);
+      if (existsSync(join(TOOLS_ROOT, group))) {
+        const target = join(tools, group);
+        if (existsSync(target)) syncTree(join(TOOLS_ROOT, group), target, force);
+        else copyIfMissing(join(TOOLS_ROOT, group), target, force);
+      }
     }
   }
   if (existsSync(join(DESIGN_ROOT, "SPA-DESIGN.md"))) {
@@ -244,7 +248,10 @@ function update(args) {
     if (existsSync(REFERENCES_ROOT) && existsSync(join(agentRoot, "references"))) updated += syncTree(REFERENCES_ROOT, join(agentRoot, "references"), force);
   }
   const tools = join(root, "tools");
-  if (existsSync(TOOLS_ROOT)) for (const group of ["clis", "integrations"]) if (existsSync(join(tools, group))) updated += syncTree(join(TOOLS_ROOT, group), join(tools, group), force);
+  if (existsSync(TOOLS_ROOT)) for (const group of ["clis", "runtime", "integrations"]) if (existsSync(join(TOOLS_ROOT, group))) {
+    const target = join(tools, group);
+    if (existsSync(target)) updated += syncTree(join(TOOLS_ROOT, group), target, force);
+  }
   if (existsSync(join(DESIGN_ROOT, "SPA-DESIGN.md")) && existsSync(join(root, ".maggie", "design-reference"))) {
     updated += syncTree(DESIGN_ROOT, join(root, ".maggie", "design-reference"), force);
   }

package/bundled-skills/maggie-seo-geo/SKILL.md

@@ -30,7 +30,10 @@ interpretation, and content creation remain agent-reviewed decisions.
 With `--crawl`, it resolves sitemap indexes and audits every listed HTML route
 for HTTP 200, one H1, title/description, locale, canonical, Open Graph/Twitter
 metadata, valid entity JSON-LD, and image alt text. Non-HTML endpoints such as
-RSS must not be included in the HTML page sitemap.
+RSS must not be included in the HTML page sitemap. Sitemap `<loc>` values must
+be absolute HTTP(S) URLs; the audit reports relative values as a failure even
+when it can resolve them for continued crawling, so one malformed entry cannot
+hide a protocol violation.
 Use `--output <project>/docs/site-audit.json` to persist the evidence used by
 the release review.
 

package/bundled-tools/clis/site_audit.py

@@ -134,10 +134,11 @@ def hreflang_check(url: str, page: PageParser, expected: set[str]) -> dict:
     return {"ok": not missing and not reciprocal_errors, "missing": missing, "reciprocal_errors": reciprocal_errors, "links": links}
 
 
-def sitemap_urls(base: str) -> list[str]:
-    """Resolve a sitemap index and return its public page URLs."""
+def sitemap_urls(base: str) -> tuple[list[str], list[dict[str, str]]]:
+    """Resolve a sitemap index and return page URLs plus raw loc violations."""
     pending = [urljoin(base + "/", "sitemap.xml")]
     pages = []
+    violations = []
     seen = set()
     while pending:
         sitemap_url = pending.pop(0)
@@ -145,12 +146,16 @@ def sitemap_urls(base: str) -> list[str]:
             continue
         seen.add(sitemap_url)
         _, _, body = fetch(sitemap_url)
-        locs = [urljoin(base + "/", value.strip()) for value in re.findall(r"<loc>\s*(.*?)\s*</loc>", body, re.I | re.S)]
+        raw_locs = [value.strip() for value in re.findall(r"<loc>\s*(.*?)\s*</loc>", body, re.I | re.S)]
+        for value in raw_locs:
+            if not re.match(r"^https?://[^\s]+$", value, re.I):
+                violations.append({"sitemap": sitemap_url, "loc": value, "reason": "sitemap loc must be an absolute HTTP(S) URL"})
+        locs = [urljoin(base + "/", value) for value in raw_locs]
         if re.search(r"<sitemapindex\b", body, re.I):
             pending.extend(locs)
         else:
             pages.extend(locs)
-    return list(dict.fromkeys(pages))
+    return list(dict.fromkeys(pages)), violations
 
 
 def main() -> int:
@@ -215,7 +220,8 @@ def main() -> int:
     crawl = {"enabled": args.crawl, "passed": True, "pages": []}
     if args.crawl:
         try:
-            urls = sitemap_urls(base)[: args.max_pages]
+            urls, sitemap_violations = sitemap_urls(base)
+            urls = urls[: args.max_pages]
             for page_url in urls:
                 try:
                     status, content_type, body = fetch(page_url)
@@ -232,7 +238,8 @@ def main() -> int:
                 except Exception as exc:
                     page_checks = {"url": page_url, "passed": False, "error": type(exc).__name__}
                 crawl["pages"].append(page_checks)
-            crawl["passed"] = bool(urls) and len(crawl["pages"]) == len(urls) and all(item["passed"] for item in crawl["pages"])
+            crawl["sitemap_loc_violations"] = sitemap_violations
+            crawl["passed"] = not sitemap_violations and bool(urls) and len(crawl["pages"]) == len(urls) and all(item["passed"] for item in crawl["pages"])
             crawl["url_count"] = len(urls)
         except Exception as exc:
             crawl = {"enabled": True, "passed": False, "error": type(exc).__name__, "pages": []}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@topy-ai/maggie",
-  "version": "0.5.0",
+  "version": "0.5.1",
   "description": "Install and manage Maggie Skills for AI coding agents",
   "license": "MIT",
   "type": "module",