feat(kaizen): recurrence count + referenced-path existence

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

scripts/friction-scan.py

@@ -18,6 +18,10 @@ FRICTION = os.path.join(REPO_ROOT, "docs", "FRICTION.md")
 
 TAG_RE = re.compile(r"`\[(friction|gotcha|recurring|unused)\]`")
 DATE_RE = re.compile(r"(\d{4})-(\d{2})-(\d{2})")
+ORDINAL_RE = re.compile(r"(\d+)(?:st|nd|rd|th)\s+(?:occurrence|reinforcement|time)", re.I)
+DATELIST_RE = re.compile(r"\((\d{2}-\d{2}(?:/[\d/-]+)+)\)")
+BACKTICK_RE = re.compile(r"`([^`]+)`")
+PATH_EXTS = (".py", ".yml", ".yaml", ".md", ".sh", ".tf", ".j2", ".toml", ".cfg", ".hcl")
 
 
 def extract_open_section(text):
@@ -62,6 +66,29 @@ def split_signals(section):
     return [s for s in signals if s]
 
 
+def parse_recurrence(text):
+    """Best-effort recurrence count from explicit markers; default 1."""
+    counts = [1]
+    m = ORDINAL_RE.search(text)
+    if m:
+        counts.append(int(m.group(1)))
+    dl = DATELIST_RE.search(text)
+    if dl:
+        counts.append(dl.group(1).count("/") + 1)
+    return max(counts)
+
+
+def parse_paths(text):
+    """Backtick tokens that look like repo paths (contain '/' or a known ext)."""
+    out, seen = [], set()
+    for m in BACKTICK_RE.finditer(text):
+        tok = m.group(1).strip()
+        if ("/" in tok or tok.endswith(PATH_EXTS)) and tok not in seen:
+            seen.add(tok)
+            out.append(tok)
+    return out
+
+
 def parse_signal(raw, today):
     """Turn one raw signal block into a structured dict."""
     tag_m = TAG_RE.search(raw)
@@ -73,13 +100,15 @@ def parse_signal(raw, today):
     else:
         first_seen = None
         age_days = None
+    paths = parse_paths(raw)
+    still_exists = all(os.path.exists(os.path.join(REPO_ROOT, p)) for p in paths) if paths else True
     return {
         "tag": tag_m.group(1) if tag_m else None,
         "first_seen": first_seen,
         "age_days": age_days,
-        "recurrence_count": 1,          # refined in Task 3
-        "referenced_paths": [],         # filled in Task 3
-        "still_exists": True,           # filled in Task 3
+        "recurrence_count": parse_recurrence(raw),
+        "referenced_paths": paths,
+        "still_exists": still_exists,
         "text": " ".join(raw.split()),
     }
 

tests/test_friction_scan.py

@@ -59,3 +59,33 @@ def test_parse_signal_handles_missing_date():
     assert sig["tag"] == "unused"
     assert sig["first_seen"] is None
     assert sig["age_days"] is None
+
+
+def test_recurrence_from_ordinal():
+    assert fs.parse_recurrence("blah 5th occurrence (06-05/06/06) blah") == 5
+
+
+def test_recurrence_from_datelist_when_no_ordinal():
+    # three slash-separated date fragments -> recurrence 3
+    assert fs.parse_recurrence("recurred (06-05/06-09/06-10) again") == 3
+
+
+def test_recurrence_defaults_to_one():
+    assert fs.parse_recurrence("a one-off gotcha") == 1
+
+
+def test_parse_paths_picks_repo_paths_only():
+    paths = fs.parse_paths("see `scripts/repo-scan.py` and `latest` and `foo.yml`")
+    assert "scripts/repo-scan.py" in paths
+    assert "foo.yml" in paths
+    assert "latest" not in paths
+
+
+def test_still_exists_false_for_missing_path():
+    sig = fs.parse_signal("`[unused]` **x** (2026-06-01): `scripts/nope-not-real.py`", TODAY)
+    assert sig["still_exists"] is False
+
+
+def test_still_exists_true_for_real_path():
+    sig = fs.parse_signal("`[gotcha]` **x** (2026-06-01): `scripts/repo-scan.py`", TODAY)
+    assert sig["still_exists"] is True