@topy-ai/maggie 0.6.8 → 0.6.9

package/README.md

@@ -179,8 +179,8 @@ artifact schemas.
 Recommended upgrade sequence for the current release:
 
 ```bash
-npx @topy-ai/maggie@0.6.8 update --project . --force
-npx @topy-ai/maggie@0.6.8 cleanup --project .
+npx @topy-ai/maggie@0.6.9 update --project . --force
+npx @topy-ai/maggie@0.6.9 cleanup --project .
 ```
 
 ## MaggieDash lifecycle

package/README.zh-TW.md

@@ -8,7 +8,7 @@ Codex、Claude Code 與相容的 coding agents。
 ## 安裝
 
 ```bash
-npx @topy-ai/maggie@0.6.8 init --agent all
+npx @topy-ai/maggie@0.6.9 init --agent all
 npx @topy-ai/maggie doctor --project .
 ```
 

package/bundled-skills/maggie-content-localization/SKILL.md

@@ -2,7 +2,7 @@
 name: maggie-content-localization
 description: Manage translation, polish, rewrite, market localization, review, stale detection, and publishing for pages, guides, posts, services, products, and categories.
 metadata:
-  version: 1.2.0
+  version: 1.3.0
 ---
 
 # Maggie Content Localization

package/bundled-skills/maggie-deployment/SKILL.md

@@ -2,7 +2,7 @@
 name: maggie-deployment
 description: Deploy and operate Maggie blog projects with Cloudflare Workers as the default target, while preserving an adapter boundary for VPS, GCP, and AWS.
 metadata:
-  version: 1.2.0
+  version: 1.3.0
 ---
 
 # Maggie Deployment

package/bundled-skills/maggie-design/SKILL.md

@@ -2,7 +2,7 @@
 name: maggie-design
 description: Design authorized interior pages, review rendered responsive layouts, or explicitly rebrand a packaged homepage/template. Use rebrand only with a named source brand and target brand.
 metadata:
-  version: 1.3.0
+  version: 1.4.0
 ---
 
 # Maggie Design

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

@@ -2,7 +2,7 @@
 name: maggie-seo-geo
 description: Plan, audit, create, rewrite, and measure content for AI CMO's paid SEO and GEO workflow. Use for topic opportunities, AI visibility, technical SEO, extractable article structure, sitemap-based rewrites, GSC readback, or SEO/GEO client reports.
 metadata:
-  version: 1.0.0
+  version: 1.1.0
 ---
 
 # Maggie SEO and GEO

package/bundled-skills/maggie-service-booking/SKILL.md

@@ -2,7 +2,7 @@
 name: maggie-service-booking
 description: Import, synchronise, validate, and design SPA service pages from a booking provider such as Fresha. Use for service catalogues, treatment variants, prices, durations, booking links, payment links, and booking-aware page generation.
 metadata:
-  version: 1.0.0
+  version: 1.1.0
 ---
 
 # Maggie Service Booking

package/bundled-tools/clis/maggie_design.py

@@ -526,6 +526,18 @@ def in_place_job(project: Path, routes: list[str], force: bool = False) -> int:
             project / "src" / "app" / relative / "page.tsx",
         ]
         match = next((path for path in candidates if path.is_file()), None)
+        if not match:
+            # Dynamic catch-all routes are the source of truth for many page
+            # families; a concrete URL still needs to resolve to that route
+            # before an in-place design job can be created.
+            roots = [project / "src" / "pages", project / "src" / "app"]
+            catchalls = {"[...slug]", "[[...slug]]"}
+            for root in roots:
+                if not root.is_dir():
+                    continue
+                match = next((path for path in root.rglob("*") if path.is_file() and path.stem in catchalls), None)
+                if match:
+                    break
         if not match:
             raise ValueError(f"existing route required for in-place redesign: {route}")
         resolved_routes.append({"route": value, "source": str(match)})

package/bundled-tools/clis/maggie_localization.py

@@ -186,6 +186,12 @@ def plan_job(args: argparse.Namespace) -> int:
         "targetLanguage": args.target_lang,
         "targetLocale": args.locale,
         "operation": args.operation,
+        "generationContract": {
+            "mode": args.operation,
+            "preserveMeaning": args.operation in {"translate", "polish", "localise", "rebrand"},
+            "allowStructuralRewrite": args.operation in {"rewrite", "rebrand"},
+            "marketAdaptation": args.operation in {"localise", "rebrand"},
+        },
         "translationGroupId": identity.get("translationGroupId", f"tg-{content_id}"),
         "sourceRevision": args.source_revision or (source_artifact or {}).get("sourceRevision") or content.get("sourceRevision", "unknown"),
         "status": "draft",
@@ -218,6 +224,11 @@ def validate_job(path: Path, source_path: Path | None = None, render_path: Path
     if not valid_locale(job.get("targetLocale")) or parse_locale(job.get("targetLocale"))[0] != job.get("targetLanguage"):
         errors.append("targetLocale must be a supported tag matching targetLanguage")
     translation = job.get("translation", {})
+    generation = job.get("generationContract", {})
+    if generation.get("mode") and generation.get("mode") != job.get("operation"):
+        errors.append("generationContract mode must match operation")
+    if job.get("operation") == "rewrite" and not generation.get("allowStructuralRewrite"):
+        errors.append("rewrite requires structural rewrite permission")
     errors.extend(validate_translation({
         "contentId": job.get("contentId"), "lang": job.get("targetLanguage"),
         "locale": job.get("targetLocale"), "translationGroupId": job.get("translationGroupId", f"tg-{job.get('contentId')}"),

package/bundled-tools/clis/maggie_service_booking.py

@@ -793,9 +793,9 @@ def cmd_match_pages_review(args):
         out=project/".maggie"/"booking"/"page-matches.json"; out.parent.mkdir(parents=True,exist_ok=True); (project/"docs").mkdir(parents=True,exist_ok=True); payload={"matchedAt":NOW(),"requiresManualSelection":True,"candidateServices":report,"selected":0,"conflicts":conflicts}; out.write_text(json.dumps(payload,indent=2,ensure_ascii=False)+"\n",encoding="utf-8"); (project/"docs"/"service-page-matches.json").write_text(json.dumps(payload,indent=2,ensure_ascii=False)+"\n",encoding="utf-8"); print(json.dumps({"status":"conflict-review","pagesScanned":len(candidates),"servicesScanned":len(report),"selected":0,"conflicts":conflicts,"report":str(out)},indent=2)); return 1
     for service,path_value in selected:
         relation={"path":path_value,"role":"canonical","matchMethod":"manual-selection","confidence":1.0}; service["pages"]=[p for p in service.get("pages",[]) if p.get("path")!=path_value]+[relation]
-    candidate_paths={c["path"] for c in candidates}
-    for service in data.get("services",[]):
-        service["pages"]=[p for p in service.get("pages",[]) if p.get("role")!="supporting" or p.get("path") in candidate_paths]
+    # Reviewed selections must not erase existing supporting relations. They
+    # may have been imported from a route table or authored intentionally even
+    # when the current page scanner cannot see their source file.
     out=project/".maggie"/"booking"/"page-matches.json"; payload={"matchedAt":NOW(),"requiresManualSelection":True,"candidateServices":report,"selected":len(selected),"conflicts":[]}; out.parent.mkdir(parents=True,exist_ok=True); (project/"docs").mkdir(parents=True,exist_ok=True); out.write_text(json.dumps(payload,indent=2,ensure_ascii=False)+"\n",encoding="utf-8"); (project/"docs"/"service-page-matches.json").write_text(json.dumps(payload,indent=2,ensure_ascii=False)+"\n",encoding="utf-8"); save(project,data); print(json.dumps({"status":"review-required","pagesScanned":len(candidates),"servicesScanned":len(report),"selected":len(selected),"conflicts":[],"report":str(out)},indent=2)); return 0
 def cmd_run(args):
     project=root(args); job={"workflow":"maggie-service-booking","phase":"created","source":args.source,"provider":args.provider,"startedAt":NOW(),"history":[]}

package/bundled-tools/clis/site_audit.py

@@ -32,6 +32,7 @@ class PageParser(HTMLParser):
         self._jsonld = None
         self.images = []
         self.hreflang = []
+        self.robots_directives = []
 
     def handle_starttag(self, tag, attrs):
         data = dict(attrs)
@@ -39,6 +40,8 @@ class PageParser(HTMLParser):
             self.lang = data.get("lang", "")
         if tag == "meta" and data.get("name"):
             self.meta[data["name"].lower()] = data.get("content", "")
+            if data["name"].lower() == "robots":
+                self.robots_directives.append(data.get("content", "").lower())
         if tag == "meta" and data.get("property"):
             self.meta[data["property"].lower()] = data.get("content", "")
         if tag == "title":
@@ -86,6 +89,8 @@ def audit_page(url: str, html: str, status: int, content_type: str, expected_lan
     page = PageParser()
     page.feed(html)
     canonical = urljoin(url, page.canonical) if page.canonical else ""
+    robots = page.robots_directives
+    robots_tokens = [token.strip() for directive in robots for token in directive.split(",")]
     return {
         "url": url,
         "status": status,
@@ -105,6 +110,9 @@ def audit_page(url: str, html: str, status: int, content_type: str, expected_lan
         "image_count": len(page.images),
         "language": parse_locale(page.lang)[0],
         "hreflang": page.hreflang,
+        "robots": not robots or not any(token in {"noindex", "none", "nofollow"} for token in robots_tokens),
+        "robots_directives": robots,
+        "robots_conflict": len({token for token in robots_tokens if token in {"index", "noindex", "follow", "nofollow", "none"}} & {"index", "noindex"}) > 1 or len({token for token in robots_tokens if token in {"follow", "nofollow", "none"}} & {"follow", "nofollow"}) > 1,
     }
 
 
@@ -197,6 +205,9 @@ def main() -> int:
         checks["jsonld"] = {"ok": page.jsonld > 0 and all(item is not None for item in page.jsonld_values), "count": page.jsonld}
         checks["entity_jsonld"] = {"ok": any(isinstance(item, dict) and item.get("@type") and (item.get("url") or item.get("@id")) for item in page.jsonld_values), "count": page.jsonld}
         checks["crawlable_links"] = {"ok": page.anchors > 0, "count": page.anchors}
+        robots_tokens = [token.strip() for directive in page.robots_directives for token in directive.split(",")]
+        checks["robots_directive"] = {"ok": not page.robots_directives or not any(token in {"noindex", "none", "nofollow"} for token in robots_tokens), "directives": page.robots_directives}
+        checks["robots_conflict"] = {"ok": not (len({token for token in robots_tokens if token in {"index", "noindex"}}) > 1 or len({token for token in robots_tokens if token in {"follow", "nofollow"}}) > 1), "directives": page.robots_directives}
         if args.check_hreflang or args.check_translation_completeness:
             checks["hreflang"] = hreflang_check(base, page, expected_languages) if args.check_hreflang else {"ok": True, "links": page.hreflang}
             if args.check_translation_completeness and expected_languages:
@@ -233,7 +244,7 @@ def main() -> int:
                             page_checks["translation_completeness"] = {"ok": all(lang in {item["lang"] for item in parsed.hreflang} for lang in expected_languages), "expected": sorted(expected_languages)}
                     page_checks["passed"] = all(
                         page_checks[key]
-                        for key in ("ok", "title", "h1", "canonical", "description", "locale", "open_graph", "twitter_card", "jsonld", "entity_jsonld", "images")
+                        for key in ("ok", "title", "h1", "canonical", "description", "locale", "open_graph", "twitter_card", "jsonld", "entity_jsonld", "images", "robots", "robots_conflict")
                     ) and (not args.check_hreflang or page_checks["hreflang_check"]["ok"]) and (not args.check_translation_completeness or page_checks.get("translation_completeness", {}).get("ok", False))
                 except Exception as exc:
                     page_checks = {"url": page_url, "passed": False, "error": type(exc).__name__}

package/bundled-tools/runtime/maggie_sitemap.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import hashlib
+import json
 import re
 from datetime import datetime, timezone
 from html import escape
@@ -27,10 +28,18 @@ def parse_routes(text: str) -> list[dict[str, str]]:
             continue
         parts = line.split("\t")
         if len(parts) < 2:
-            raise ValueError("route lines must be type<TAB>absolute-url<TAB>optional-lastmod")
+            raise ValueError("route lines must be type<TAB>absolute-url<TAB>optional-lastmod<TAB>optional-alternates-json")
         item = {"type": parts[0].strip(), "url": parts[1].strip()}
         if len(parts) > 2 and parts[2].strip():
             item["lastmod"] = parts[2].strip()
+        if len(parts) > 3 and parts[3].strip():
+            try:
+                alternates = json.loads(parts[3])
+            except json.JSONDecodeError as exc:
+                raise ValueError("route alternates must be valid JSON") from exc
+            if not isinstance(alternates, dict):
+                raise ValueError("route alternates must be a JSON object")
+            item["alternates"] = alternates
         routes.append(item)
     return routes
 
@@ -63,8 +72,9 @@ def xml_file(urls: list[dict[str, str]]) -> str:
     rows = []
     for item in urls:
         lastmod = f"<lastmod>{escape(item['lastmod'])}</lastmod>" if item.get("lastmod") else ""
-        rows.append(f"<url><loc>{escape(item['url'])}</loc>{lastmod}</url>")
-    return '<?xml version="1.0" encoding="UTF-8"?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">' + "".join(rows) + "</urlset>\n"
+        alternate_xml = "".join(f'<xhtml:link rel="alternate" hreflang="{escape(str(lang))}" href="{escape(str(url))}" />' for lang, url in sorted((item.get("alternates") or {}).items()))
+        rows.append(f"<url><loc>{escape(item['url'])}</loc>{lastmod}{alternate_xml}</url>")
+    return '<?xml version="1.0" encoding="UTF-8"?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:xhtml="http://www.w3.org/1999/xhtml">' + "".join(rows) + "</urlset>\n"
 
 
 def build_plan(routes: list[dict[str, str]], origin: str, content_types: set[str], chunk_target: int = DEFAULT_CHUNK_TARGET, previous: dict | None = None) -> dict:
@@ -112,6 +122,9 @@ def validate_plan_data(plan: dict) -> dict:
                 locs = [element.text or "" for element in root.iter() if element.tag.endswith("loc")]
                 if any(not absolute_url(value, origin) for value in locs):
                     errors.append(f"chunk contains a relative or off-origin loc: {chunk.get('filename')}")
+                for link in root.iter():
+                    if link.tag.endswith("link") and link.get("rel") == "alternate" and not absolute_url(link.get("href", ""), origin):
+                        errors.append(f"chunk contains a relative or off-origin alternate: {chunk.get('filename')}")
             except ElementTree.ParseError:
                 errors.append(f"chunk is not valid XML: {chunk.get('filename')}")
     index = plan.get("index", {})

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@topy-ai/maggie",
-  "version": "0.6.8",
+  "version": "0.6.9",
   "description": "Install and manage Maggie Skills for AI coding agents",
   "license": "MIT",
   "type": "module",