fix(sitemap): improve blog coverage and link resolution with regression tests (#70)

* cowork-bot: fix ruff E402 noqa on test imports

tests/test_linkcheck_additional.py and tests/test_linkcheck_edge_cases.py
perform a sys.path.insert before importing linkcheck, which means the
import must come after the path manipulation. Ruff flags this as E402
(module-level import not at top of file). Add '# noqa: E402' to silence
the expected warning, matching the existing suppression in test_linkcheck.py.

This makes 'ruff check .' pass cleanly and unblocks CI.

* cowork-bot: add cowork-auto-pr workflow

Seeds the GitHub Actions workflow that opens a PR server-side for this
branch (sandbox cannot reach the GitHub API directly).

* cowork-bot: fix link resolution for ../ intermediates and absolute paths; update article count

* cowork-bot: fix sitemap.xml coverage — remove stale traction-hits URL, add 5 missing blog articles; add regression tests

---------

Co-authored-by: DevForge Engineer <engineer@devforge.dev>

Author: Coding-Dev-Tools

.github/workflows/cowork-auto-pr.yml

@@ -0,0 +1,28 @@
+# Seeded by the repo-improver-rotation Cowork job into cowork/improve-* branches.
+# Opens a PR automatically when such a branch is pushed (sandbox cannot reach
+# the GitHub API directly; this runs server-side with the repo's GITHUB_TOKEN).
+name: cowork-auto-pr
+on:
+  push:
+    branches: ['cowork/improve-**']
+permissions:
+  contents: read
+  pull-requests: write
+jobs:
+  ensure-pr:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Open PR for this branch if none exists
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: |
+          set -eu
+          existing=$(gh pr list --repo "$GITHUB_REPOSITORY" --head "$GITHUB_REF_NAME" --state open --json number --jq 'length')
+          if [ "$existing" = "0" ]; then
+            gh pr create --repo "$GITHUB_REPOSITORY" \
+              --head "$GITHUB_REF_NAME" \
+              --title "cowork-bot: automated improvements ($GITHUB_REF_NAME)" \
+              --body "Automated improvement PR from the Cowork repo-improver rotation (one coherent senior-dev improvement per run; see individual commit messages). Subsequent runs push additional commits to this PR rather than opening new ones."
+          else
+            echo "Open PR already exists for $GITHUB_REF_NAME — nothing to do."
+          fi

.hermes/linkcheck.py

@@ -37,17 +37,25 @@ def build_actual_pages(all_files: set[str]) -> set[str]:
 
 def resolve_link(link: str, source_dir: str) -> str:
     """Resolve a relative href to an absolute site-relative path."""
-    if link.startswith("../"):
-        parts = source_dir.split("/") if source_dir else []
-        up_count = link.count("../")
-        resolved_parts = parts[:-up_count] if len(parts) >= up_count else []
-        remaining = link[3 * up_count :]
-        resolved = "/".join(resolved_parts + [remaining]) if resolved_parts else remaining
-    elif link.startswith("./"):
-        resolved = (source_dir + "/" + link[2:]) if source_dir else link[2:]
+    if link.startswith("http://") or link.startswith("https://") or link.startswith("#"):
+        return link
+    if link.startswith("/"):
+        return link.lstrip("/")
+
+    if source_dir:
+        path = source_dir + "/" + link
     else:
-        resolved = (source_dir + "/" + link) if source_dir else link
-    return resolved.replace("//", "/")
+        path = link
+
+    normalized = os.path.normpath(path).replace(os.sep, "/")
+
+    # Cap at site root: strip any leading ../ that goes above root
+    while normalized.startswith("../"):
+        normalized = normalized[3:]
+        if normalized.startswith("/"):
+            normalized = normalized[1:]
+
+    return normalized
 
 
 def check_links(root_dir: str, verbose: bool = False) -> int:

README.md

@@ -3,7 +3,7 @@
 [![Deploy](https://img.shields.io/badge/deploy-GitHub%20Pages-brightgreen)](https://coding-dev-tools.github.io/devforge/)
 [![Stars](https://img.shields.io/github/stars/Coding-Dev-Tools/devforge?style=social)](https://github.com/Coding-Dev-Tools/devforge/stargazers)
 
-Landing page, documentation, pricing, alternatives, and blog for the **DevForge CLI tool suite** — 11 developer CLI tools for API contracts, SQL, infrastructure, config drift, and more. **60 articles and growing.**
+Landing page, documentation, pricing, alternatives, and blog for the **DevForge CLI tool suite** — 11 developer CLI tools for API contracts, SQL, infrastructure, config drift, and more. **70 articles and growing.**
 
 **Live site:** [coding-dev-tools.github.io/devforge/](https://coding-dev-tools.github.io/devforge/)
 
@@ -14,7 +14,7 @@ Landing page, documentation, pricing, alternatives, and blog for the **DevForge
 | [Home](https://coding-dev-tools.github.io/devforge/) | Hero, stats, feature cards, CTA |
 | [Pricing](https://coding-dev-tools.github.io/devforge/pricing.html) | Free / Pro / Team / Enterprise tiers |
 | [Alternatives](https://coding-dev-tools.github.io/devforge/alternatives.html) | 11 comparison tables vs competitors |
-| [Blog](https://coding-dev-tools.github.io/devforge/blog.html) | 60+ articles and tutorials |
+| [Blog](https://coding-dev-tools.github.io/devforge/blog.html) | 70+ articles and tutorials |
 | [Docs](https://coding-dev-tools.github.io/devforge/docs.html) | Tool documentation hub |
 | [Quickstart](https://coding-dev-tools.github.io/devforge/quickstart.html) | Get started in 60 seconds |
 | [FAQ](https://coding-dev-tools.github.io/devforge/#faq) | Common questions |

sitemap.xml

@@ -33,9 +33,6 @@
   <url>
     <loc>https://coding-dev-tools.github.io/devforge/quickstart.html</loc>
     <lastmod>2026-05-17</lastmod>
-
-    <loc>https://coding-dev-tools.github.io/revenueholdings.dev/blog/openapi-diff-tools-comparison.html</loc>
-    <lastmod>2026-05-15</lastmod>
     <changefreq>monthly</changefreq>
     <priority>0.9</priority>
   </url>
@@ -447,28 +444,58 @@
  <changefreq>monthly</changefreq>
  <priority>0.6</priority>
  </url>
- <url>
- <loc>https://coding-dev-tools.github.io/devforge/blog/traction-hits-680-developers.html</loc>
- <lastmod>2026-05-17</lastmod>
- <changefreq>monthly</changefreq>
- <priority>0.6</priority>
- </url>
-
-    <loc>https://coding-dev-tools.github.io/revenueholdings.dev/alternatives.html</loc>
-    <lastmod>2026-05-15</lastmod>
+  <url>
+    <loc>https://coding-dev-tools.github.io/devforge/blog/click-to-mcp-three-distribution-channels.html</loc>
+    <lastmod>2026-06-13</lastmod>
     <changefreq>monthly</changefreq>
-    <priority>0.9</priority>
+    <priority>0.6</priority>
+  </url>
+  <url>
+    <loc>https://coding-dev-tools.github.io/devforge/blog/click-to-mcp-three-transport-modes.html</loc>
+    <lastmod>2026-05-28</lastmod>
+    <changefreq>monthly</changefreq>
+    <priority>0.6</priority>
   </url>
+  <url>
+    <loc>https://coding-dev-tools.github.io/devforge/blog/configdrift-scan-multi-environment-configs-one-command.html</loc>
+    <lastmod>2026-05-28</lastmod>
+    <changefreq>monthly</changefreq>
+    <priority>0.6</priority>
+  </url>
+  <url>
+    <loc>https://coding-dev-tools.github.io/devforge/blog/deploydiff-cost-governance-before-you-deploy.html</loc>
+    <lastmod>2026-05-28</lastmod>
+    <changefreq>monthly</changefreq>
+    <priority>0.6</priority>
+  </url>
+  <url>
+    <loc>https://coding-dev-tools.github.io/devforge/blog/saas-churn-predictor-launch.html</loc>
+    <lastmod>2026-05-28</lastmod>
+    <changefreq>monthly</changefreq>
+    <priority>0.6</priority>
+  </url>
+<url>
+  <loc>https://coding-dev-tools.github.io/devforge/blog/apicontractguardian-git-branch-openapi-diff-pr-review.html</loc>
+  <lastmod>2026-08-26</lastmod>
+  <changefreq>weekly</changefreq>
+  <priority>0.6</priority>
+</url>
 <url>
-  <loc>https://coding-dev-tools.github.io/revenueholdings.dev/quickstart.html</loc>
-  <lastmod>2026-05-15</lastmod>
-  <changefreq>monthly</changefreq>
-  <priority>0.9</priority>
+  <loc>https://coding-dev-tools.github.io/devforge/blog/deadcode-remove-dead-code-nextjs-app-router.html</loc>
+  <lastmod>2026-08-26</lastmod>
+  <changefreq>weekly</changefreq>
+  <priority>0.6</priority>
+</url>
+<url>
+  <loc>https://coding-dev-tools.github.io/devforge/blog/json2sql-cicd-automated-database-seeding.html</loc>
+  <lastmod>2026-08-26</lastmod>
+  <changefreq>weekly</changefreq>
+  <priority>0.6</priority>
 </url>
 <url>
-  <loc>https://coding-dev-tools.github.io/revenueholdings.dev/blog/clean-up-react-dead-code.html</loc>
-  <lastmod>2026-05-15</lastmod>
-  <changefreq>monthly</changefreq>
+  <loc>https://coding-dev-tools.github.io/devforge/blog/schemaforge-convert-prisma-to-drizzle-migration-guide.html</loc>
+  <lastmod>2026-08-26</lastmod>
+  <changefreq>weekly</changefreq>
   <priority>0.6</priority>
 </url>
 </urlset>

tests/test_linkcheck.py

@@ -167,6 +167,24 @@ def test_resolve_link_double_slash():
     assert result == "blog/page.html"
 
 
+def test_resolve_link_absolute_path():
+    """Absolute path /about.html strips leading slash."""
+    result = resolve_link("/about.html", "blog")
+    assert result == "about.html"
+
+
+def test_resolve_link_up_with_intermediate_segments():
+    """../foo/../bar.html correctly cancels the intermediate segment."""
+    result = resolve_link("../foo/../bar.html", "blog/2024")
+    assert result == "blog/bar.html"
+
+
+def test_resolve_link_up_capped_at_root():
+    """../../ from a shallow dir is capped at site root."""
+    result = resolve_link("../../page.html", "blog")
+    assert result == "page.html"
+
+
 # ---- CLI argument parsing ----
 
 

tests/test_linkcheck_additional.py

@@ -11,7 +11,7 @@
 _SCRIPT_DIR = Path(__file__).resolve().parent.parent / ".hermes"
 sys.path.insert(0, str(_SCRIPT_DIR))
 
-from linkcheck import build_actual_pages
+from linkcheck import build_actual_pages  # noqa: E402
 
 
 class TestBuildActualPages:

tests/test_linkcheck_edge_cases.py

@@ -16,7 +16,7 @@
 _SCRIPT_DIR = Path(__file__).resolve().parent.parent / ".hermes"
 sys.path.insert(0, str(_SCRIPT_DIR))
 
-from linkcheck import check_links, main
+from linkcheck import check_links, main  # noqa: E402
 
 
 class TestCheckLinksEdgeCases:

tests/test_sitemap.py

@@ -0,0 +1,51 @@
+"""Regression tests: sitemap.xml must exactly cover the site's real pages.
+
+Every non-404 HTML file in the repo must have a <loc> entry, and every
+<loc> must resolve to a real page (index.html is represented as "/").
+"""
+
+import os
+import re
+import xml.etree.ElementTree as ET
+from pathlib import Path
+
+REPO = Path(__file__).resolve().parent.parent
+SITEMAP = REPO / "sitemap.xml"
+BASE = "https://coding-dev-tools.github.io/devforge/"
+NS = "{http://www.sitemaps.org/schemas/sitemap/0.9}"
+
+
+def _actual_pages():
+    pages = set()
+    for root, dirs, files in os.walk(REPO):
+        rel_root = Path(root).relative_to(REPO)
+        dirs[:] = [d for d in dirs if d not in (".git", "drafts", ".hermes", "tests")]
+        for fn in files:
+            if fn.endswith(".html") and fn != "404.html":
+                p = str(rel_root / fn).replace(os.sep, "/")
+                pages.add(BASE if p == "index.html" else BASE + p)
+    return pages
+
+
+def _sitemap_urls():
+    tree = ET.parse(SITEMAP)
+    return {e.text for e in tree.getroot().iter(NS + "loc")}
+
+
+def test_sitemap_parses():
+    ET.parse(SITEMAP)
+
+
+def test_sitemap_covers_every_page():
+    missing = _actual_pages() - _sitemap_urls()
+    assert not missing, f"pages missing from sitemap.xml: {sorted(missing)}"
+
+
+def test_sitemap_has_no_stale_urls():
+    stale = _sitemap_urls() - _actual_pages()
+    assert not stale, f"stale sitemap.xml URLs with no page: {sorted(stale)}"
+
+
+def test_no_duplicate_locs():
+    urls = re.findall(r"<loc>(.*?)</loc>", SITEMAP.read_text(encoding="utf-8"))
+    assert len(urls) == len(set(urls))