fix(call2): no metadata dump in long description

Long desc is Hook + Benefits (+ brief trust close) only; forbid Full specs /
Attribute list / product-name header that re-lists DECLARED ATTRIBUTES or
DIMENSION FACT BLOCK. Defensively strip trailing Category:/Length:/Board Feet:
labeled dumps in parse.

backend/inference.py

@@ -128,6 +128,11 @@ CALL2_SEED = (
     "- The product name may already appear in DECLARED ATTRIBUTES — do not invent a new title.\n"
     "- Lead with usable traits (species, figure, size, edge, moisture, grade) and what the piece "
     "suits (tabletop, bar, etc.) without ad-copy fluff.\n"
+    "- Specs live in taxonomy and dimension fields on the product. Do NOT restate DECLARED "
+    "ATTRIBUTES or the DIMENSION FACT BLOCK as a labeled metadata list in the description "
+    "(no Category:/Figure:/Edge:/Grade:/Moisture:/Length:/Board Feet: dump, no \"Full specs\" "
+    "section, no \"Maple Slab\" attribute-header block). You may weave 1–2 key traits into "
+    "prose or benefit bullets naturally.\n"
     "\n"
     "SHORT DESCRIPTION (~50 words — most important on-page copy; plain text only):\n"
     "1. Lead with a practical outcome for a maker (what they can build / how the stock helps), "
@@ -136,13 +141,13 @@ CALL2_SEED = (
     "3. Close with a trust signal or concrete reason to choose this piece.\n"
     "\n"
     "LONG DESCRIPTION (plain text only — newlines and \"- \" bullets; no HTML, no markdown "
-    "markup). Four parts, in order:\n"
+    "markup). Hook + Benefits only (+ brief trust close). Do NOT add a Full specs / Attribute "
+    "list / product-name header that re-lists DECLARED ATTRIBUTES or DIMENSION FACT BLOCK:\n"
     "1. Hook — one sentence on what the piece suits and its standout usable trait.\n"
-    "2. Benefits — 3–5 bullets; each maker-useful trait first, then the supporting spec.\n"
-    "3. Full specs — clean list from DECLARED ATTRIBUTES + DIMENSION FACT BLOCK "
-    "(dims, species, moisture, edge, figure, grade, etc.).\n"
-    "4. Trust close — return/warranty/brand; use Brand voice when present; otherwise a short "
-    "neutral close with no invented policies.\n"
+    "2. Benefits — 3–5 bullets; each maker-useful trait first, then the supporting detail. "
+    "Weave in at most 1–2 key traits naturally — not an exhaustive labeled catalog.\n"
+    "3. Trust close (optional, brief) — return/warranty/brand; use Brand voice when present; "
+    "otherwise a short neutral close with no invented policies.\n"
     "\n"
     "Return ONE JSON object only (no prose outside JSON) with exactly these keys:\n"
     '{"short_description": "<plain text ~50 words>", "description": "<plain text long description>"}'
@@ -693,6 +698,95 @@ async def call2_prompt(slab_id: str) -> dict:
     }
 
 
+# Labels that mark a Woo/taxonomy/dimension metadata dump when used as "- Label: …".
+_ATTR_DUMP_LABELS = (
+    "Category",
+    "Primary",
+    "Secondary",
+    "Species",
+    "Figure",
+    "Edge",
+    "Grade",
+    "Moisture",
+    "Features",
+    "Feature",
+    "Title",
+    "Length",
+    "Thickness",
+    "Width",
+    "Avg Width",
+    "Average Width",
+    "Width Min",
+    "Width Max",
+    "Min Width",
+    "Max Width",
+    "Board Feet",
+    "Bdft",
+    "BF",
+    "Dimensions",
+    "Dims",
+)
+_ATTR_DUMP_LABEL_RE = re.compile(
+    r"(?i)^\s*-\s*(?:"
+    + "|".join(re.escape(l) for l in _ATTR_DUMP_LABELS)
+    + r")\s*:",
+)
+_ATTR_DUMP_HEADER_RE = re.compile(
+    r"(?i)^\s*(?:Full\s+specs?|Specifications?|Attributes?|Attribute\s+list|"
+    r"[A-Za-z][A-Za-z0-9 /&-]{0,40}\s+Slab)\s*$",
+)
+
+
+def _strip_attribute_dump(value: str) -> str:
+    """Remove a labeled Category:/Length:/Board Feet: metadata dump from long desc.
+
+    Specs live in taxonomy/dims on the product; a trailing (or mid-body) block that
+    re-lists them as "- Label: value" lines drifts from Woo fields. Keeps Hook +
+    Benefits (+ trust close) prose around the dump.
+    """
+    if not value:
+        return ""
+    lines = value.split("\n")
+    n = len(lines)
+    is_attr = [_ATTR_DUMP_LABEL_RE.match(ln) is not None for ln in lines]
+
+    # Find contiguous runs of ≥3 attribute bullets (optionally preceded by a header).
+    runs: list[tuple[int, int]] = []
+    i = 0
+    while i < n:
+        if not is_attr[i]:
+            i += 1
+            continue
+        start = i
+        while i < n and is_attr[i]:
+            i += 1
+        end = i  # exclusive
+        if end - start >= 3:
+            # Absorb a single preceding header / "Maple Slab" title line.
+            hdr = start - 1
+            if hdr >= 0 and lines[hdr].strip() and _ATTR_DUMP_HEADER_RE.match(lines[hdr]):
+                # Do not swallow a benefits bullet that happens to match poorly.
+                if not is_attr[hdr]:
+                    start = hdr
+            # Absorb blank lines immediately before the block.
+            while start > 0 and not lines[start - 1].strip():
+                start -= 1
+            runs.append((start, end))
+
+    if not runs:
+        return value.strip()
+
+    # Prefer the last run (typical trailing dump); drop all qualifying runs.
+    keep = [True] * n
+    for start, end in runs:
+        for j in range(start, end):
+            keep[j] = False
+    out_lines = [ln for j, ln in enumerate(lines) if keep[j]]
+    text = "\n".join(out_lines)
+    text = re.sub(r"\n{3,}", "\n\n", text)
+    return text.strip()
+
+
 def _html_to_plain(value: str) -> str:
     """Defensive: strip HTML/markup so Review fields never show raw tags.
 
@@ -717,11 +811,18 @@ def _html_to_plain(value: str) -> str:
     return t.strip()
 
 
+def _plain_long_desc(value: str) -> str:
+    """HTML→plain then drop labeled attribute/metadata dumps from long description."""
+    return _strip_attribute_dump(_html_to_plain(value))
+
+
 def parse_call2_response(raw: str) -> tuple[str | None, str]:
     """Split Call 2 model output into (short_description, description).
 
     Preferred shape is a JSON object with short_description + description.
     Both fields are forced to plain text (HTML stripped) before return.
+    Long description also drops a trailing/mid labeled attribute dump
+    (Category:/Length:/Board Feet: …) so specs stay on Woo fields.
     If JSON is missing or incomplete, treat the whole body as description
     (stripped) and leave short_description None (caller keeps any prior short).
     """
@@ -747,11 +848,11 @@ def parse_call2_response(raw: str) -> tuple[str | None, str]:
             try:
                 obj = json.loads(body[start : end + 1])
             except (ValueError, TypeError):
-                return None, _html_to_plain(text)
+                return None, _plain_long_desc(text)
         else:
-            return None, _html_to_plain(text)
+            return None, _plain_long_desc(text)
     if not isinstance(obj, dict):
-        return None, _html_to_plain(text)
+        return None, _plain_long_desc(text)
     short = obj.get("short_description")
     desc = obj.get("description")
     if isinstance(short, str):
@@ -759,9 +860,9 @@ def parse_call2_response(raw: str) -> tuple[str | None, str]:
     else:
         short = None
     if isinstance(desc, str) and desc.strip():
-        return short, _html_to_plain(desc)
+        return short, _plain_long_desc(desc)
     # JSON without a usable description — fall back to raw (stripped).
-    return short, _html_to_plain(text)
+    return short, _plain_long_desc(text)
 
 
 @router.post("/slabs/{slab_id}/inference/call2")