@topy-ai/maggie 0.7.9 → 0.7.11

package/bundled-tools/runtime/site_baseline.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 import json
 from datetime import datetime, timezone
 from pathlib import Path
+from urllib.parse import urlparse
 
 
 def snapshot(report: dict, reviewer: str) -> dict:
@@ -16,15 +17,25 @@ def snapshot(report: dict, reviewer: str) -> dict:
     if not pages or len(pages) != crawl.get("discovered_url_count"):
         raise ValueError("baseline page coverage is incomplete")
     contracts = {}
+    content = {}
+    excluded_query_urls = []
     for page in pages:
         if not page.get("passed") or not isinstance(page.get("contract"), dict):
             raise ValueError("baseline requires successful page contracts")
         if page["url"] in contracts:
             raise ValueError("duplicate page URL")
+        if urlparse(page["url"]).query:
+            excluded_query_urls.append(page["url"])
+            continue
         contracts[page["url"]] = page["contract"]
+        if isinstance(page.get("contentContract"), dict):
+            content[page["url"]] = page["contentContract"]
+    if not contracts:
+        raise ValueError("baseline has no non-query page contracts")
     return {"schemaVersion": "maggie-site-baseline.v1", "url": report["url"],
             "reviewer": reviewer.strip(), "createdAt": datetime.now(timezone.utc).isoformat(),
-            "pages": contracts}
+            "pages": contracts, "content": content,
+            "excludedQueryUrls": sorted(excluded_query_urls)}
 
 
 def compare(baseline: dict, report: dict) -> dict:
@@ -36,7 +47,10 @@ def compare(baseline: dict, report: dict) -> dict:
         errors.append("site origin/base URL differs from baseline")
     if not crawl.get("enabled") or not crawl.get("complete"):
         errors.append("complete sitemap crawl required")
-    current = {page["url"]: page.get("contract") for page in crawl.get("pages", [])}
+    crawl_pages = crawl.get("pages", [])
+    query_urls = sorted(page["url"] for page in crawl_pages if urlparse(page["url"]).query)
+    current = {page["url"]: page.get("contract") for page in crawl_pages if not urlparse(page["url"]).query}
+    current_content = {page["url"]: page.get("contentContract") for page in crawl_pages if not urlparse(page["url"]).query and isinstance(page.get("contentContract"), dict)}
     expected = baseline["pages"]
     added, removed = sorted(current.keys() - expected.keys()), sorted(expected.keys() - current.keys())
     changes = []
@@ -48,8 +62,27 @@ def compare(baseline: dict, report: dict) -> dict:
         fields = sorted(key for key in expected[url].keys() | actual.keys() if expected[url].get(key) != actual.get(key))
         if fields:
             changes.append({"url": url, "fields": fields})
-    return {"passed": not errors and not added and not removed and not changes,
-            "errors": errors, "added": added, "removed": removed, "changed": changes}
+    expected_content = baseline.get("content", {})
+    content_changes = []
+    content_not_compared = []
+    if expected_content:
+        for url in sorted(expected_content.keys() & current_content.keys()):
+            expected_contract = expected_content[url]
+            current_contract = current_content[url]
+            ignored_legacy_fields = {"images", "imageAlts"} if "images" not in expected_contract else set()
+            fields = sorted(key for key in expected_contract.keys() | current_contract.keys() if key not in ignored_legacy_fields and expected_contract.get(key) != current_contract.get(key))
+            if "images" not in expected_contract:
+                content_not_compared.append({"url": url, "fields": ["images", "imageAlts"], "reason": "baseline predates image content contract"})
+            if fields:
+                content_changes.append({"url": url, "fields": fields})
+        missing_content = sorted(expected_content.keys() - current_content.keys())
+        if missing_content:
+            errors.append("missing content contract: " + ", ".join(missing_content))
+    return {"passed": not errors and not added and not removed and not changes and not content_changes,
+            "errors": errors, "added": added, "removed": removed, "changed": changes,
+            "contentChanged": content_changes,
+            "contentNotCompared": content_not_compared,
+            "excludedQueryUrls": query_urls}
 
 
 def save(path: Path, baseline: dict) -> None:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@topy-ai/maggie",
-  "version": "0.7.9",
+  "version": "0.7.11",
   "description": "Install and manage Maggie Skills for AI coding agents",
   "license": "MIT",
   "type": "module",