Treat KiCad Value/PNM as the IC MPN when the MPN column is empty.

Those 13 U* were in the BOM (TPS22965, TPD2E007, TMP117, …) but never entered ic_mpns, so review skipped them as missing PDFs. Also try the BOM Datasheet URL first.

Co-authored-by: Cursor <cursoragent@cursor.com>

backend/pinscopex/graph.py

@@ -301,7 +301,9 @@ def build_graph(
     for ref, footprint in parts.items():
         bom_entry = bom.get(ref, {})
         value = bom_entry.get("value", "")
-        mpn = bom_entry.get("mpn")
+        mpn = bom_entry.get("mpn") or None
+        if not mpn and _classify_component(ref, footprint) == ComponentType.IC:
+            mpn = (value or "").strip() or None
 
         components[ref] = Component(
             reference=ref,

backend/pinscopex/parsers.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import csv
+import re
 from pathlib import Path
 from typing import Literal
 
@@ -264,17 +265,27 @@ def parse_bom(
         refs_raw = row.get(reference_col, "")
         value = row.get("Value", "") or row.get("Comment", "")
         footprint = row.get("Footprint", "")
-        mpn = row.get(mpn_col, "") or None
+        mpn = (row.get(mpn_col, "") or "").strip() or None
         lcsc = row.get("LCSC", "") or None
+        datasheet_url = (row.get("Datasheet", "") or "").strip() or None
 
         # Expand grouped references: "C1,C2,C5" -> ["C1", "C2", "C5"]
-        for ref in (r.strip() for r in refs_raw.split(",")):
-            if ref:
-                result[ref] = {
-                    "value": value,
-                    "footprint": footprint,
-                    "mpn": mpn,
-                    "lcsc": lcsc,
-                }
+        refs = [r.strip() for r in refs_raw.split(",") if r.strip()]
+        # KiCad exports often leave Manufacturer Part Number empty and put
+        # the orderable code in Value (or PNM). Without this, U* never
+        # enter ic_mpns and review reports "no datasheet PDF".
+        if not mpn:
+            mpn = (row.get("PNM", "") or "").strip() or None
+        if not mpn and any(re.match(r"^U\d", r, re.I) for r in refs):
+            mpn = (value or "").strip() or None
+
+        for ref in refs:
+            result[ref] = {
+                "value": value,
+                "footprint": footprint,
+                "mpn": mpn,
+                "lcsc": lcsc,
+                "datasheet_url": datasheet_url,
+            }
 
     return result

backend/services/datasheet_finder.py

@@ -382,10 +382,13 @@ async def _from_digikey(mpn: str) -> DatasheetHit | None:
     return DatasheetHit(mpn, error=result.error, url=result.url, source="digikey")
 
 
-async def find_datasheet(mpn: str, lcsc_id: str | None = None) -> DatasheetHit:
+async def find_datasheet(
+    mpn: str, lcsc_id: str | None = None, url_hint: str | None = None,
+) -> DatasheetHit:
     """Find and download a datasheet PDF for ``mpn``.
 
-    Tries LCSC, then TI (when the MPN looks like a TI part), then DigiKey.
+    Tries an explicit BOM URL first, then LCSC, then TI (when the MPN
+    looks like a TI part), then DigiKey.
     """
     mpn = (mpn or "").strip()
     if not mpn:
@@ -394,6 +397,16 @@ async def find_datasheet(mpn: str, lcsc_id: str | None = None) -> DatasheetHit:
     errors: list[str] = []
     last_url: str | None = None
 
+    hint = (url_hint or "").strip()
+    if hint.startswith("http"):
+        try:
+            pdf = await _download_pdf(hint)
+            return DatasheetHit(mpn, pdf_bytes=pdf, url=hint, source="bom")
+        except Exception as exc:
+            log.info("BOM datasheet URL missed %s: %s", mpn, exc)
+            errors.append(f"bom: {exc}")
+            last_url = hint
+
     for source_fn in (_from_lcsc, _from_ti, _from_digikey):
         try:
             if source_fn is _from_lcsc:

backend/services/pipeline.py

@@ -369,7 +369,7 @@ class PipelineContext:
     # the primary numeric value from here without saving to the shared library.
     passive_values: dict[str, str] = field(default_factory=dict)
     simple_mpns: dict[str, list[str]] = field(default_factory=dict)
-    simple_mpn_types: dict[str, str] = field(default_factory=dict)
+    datasheet_urls: dict[str, str] = field(default_factory=dict)
     # Cached purple-parts payload (description, category, subcategory, manufacturer,
     # package, ...) keyed by *resolved* MPN. Populated by _resolve_lcsc_codes during
     # BOM parse; consumed by passive extraction as a first-pass auto-resolve source
@@ -605,6 +605,9 @@ async def _stage_bom_parse(ctx: PipelineContext) -> None:
 
     for ref, info in sorted(bom.items()):
         mpn = info.get("mpn")
+        url = (info.get("datasheet_url") or "").strip()
+        if mpn and url and mpn not in ctx.datasheet_urls:
+            ctx.datasheet_urls[mpn] = url
         if not mpn:
             continue
         typ = type_for_ref(ref)
@@ -705,7 +708,11 @@ async def _ensure_local_datasheet(
         {"stage": stage, "substep": mpn,
          "status": "running", "detail": "finding datasheet"},
     )
-    hit = await find_datasheet(mpn, lcsc_id=_lcsc_id_for_mpn(ctx, mpn))
+    hit = await find_datasheet(
+        mpn,
+        lcsc_id=_lcsc_id_for_mpn(ctx, mpn),
+        url_hint=ctx.datasheet_urls.get(mpn),
+    )
     if not hit.ok or not hit.pdf_bytes:
         return False
     pdf_path.parent.mkdir(parents=True, exist_ok=True)