fix(scrape): use the full job_scraper/seen_jobs.json path in every step of the spec (#608)

* fix(scrape): use the full job_scraper/seen_jobs.json path in every step of the spec

Step 0 reads job_scraper/seen_jobs.json but Steps 1-4 and the rules used the bare
filename. Step 4 is where the file is written, so an agent following it literally
can create seen_jobs.json in the repo root, outside the **/job_scraper/seen_jobs.json
ignore rule, where it gets committed with the user's scrape history.

Adds a spec test that rejects bare references; relaxes the existing dedup-continuity
regex to accept the qualified path.

* docs(changelog): entry for #608

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

---------

Co-authored-by: Mads Lorentzen <madslorentzen_17@hotmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>

tests/test_scrape_contract.py

@@ -143,7 +143,7 @@ class SeenJobsDedupContinuityTests(unittest.TestCase):
         text = SCRAPER_SKILL.read_text(encoding="utf-8")
         self.assertRegex(
             text,
-            r"URL matches any existing `seen_jobs\.json` entry, regardless of\s+that entry's key",
+            r"URL matches any existing `(?:job_scraper/)?seen_jobs\.json` entry, regardless of\s+that entry's key",
             "legacy seen_jobs entries must be matched by URL during the key-rule transition",
         )
 

tests/test_scrape_seen_jobs_path.py

@@ -0,0 +1,30 @@
+"""Every seen_jobs.json reference in /scrape's spec names the full path.
+
+Step 0 reads `job_scraper/seen_jobs.json`, but later steps (notably Step 4,
+where the file is written) used the bare filename. An agent following Step 4
+literally can create `seen_jobs.json` in the repo root. The ignore rules only
+cover `**/job_scraper/seen_jobs.json`, so a root-level copy is untracked-by-rule
+only by accident: it shows up in `git status`, gets swept into a commit, and
+publishes the user's scrape history. Pinning the full path in the spec keeps
+the read path, the write path and the ignore rule pointing at the same file.
+"""
+import re
+import unittest
+from pathlib import Path
+
+SKILL = Path(__file__).resolve().parent.parent / ".claude" / "skills" / "job-scraper" / "SKILL.md"
+BARE = re.compile(r"(?<!job_scraper/)(?<![\w/.-])seen_jobs\.json")
+
+
+class ScrapeSeenJobsPathSpec(unittest.TestCase):
+    def test_no_bare_seen_jobs_reference(self):
+        offenders = [
+            f"line {i}: {line.strip()[:90]}"
+            for i, line in enumerate(SKILL.read_text(encoding="utf-8").splitlines(), 1)
+            if BARE.search(line)
+        ]
+        self.assertEqual(offenders, [], "use job_scraper/seen_jobs.json everywhere in the spec")
+
+
+if __name__ == "__main__":
+    unittest.main()