From 3be7d2fc2122f684ffd97cc7a60a3b639f44d9ec Mon Sep 17 00:00:00 2001
From: Michele Bigi <mikbigi@gmail.com>
Date: Fri, 28 Aug 2026 02:18:50 +0200
Subject: [PATCH] Copy library datasheets onto every graph IC before review.

Review skipped U* when the PDF was stored under a catalog MPN or the part was only in the netlist. Lookup now uses spelling variants and aliases.

Co-authored-by: Cursor <cursoragent@cursor.com>
---
 backend/services/pipeline.py   | 32 ++++++++++++++++++++++++++------
 backend/services/validation.py | 17 +++++++++++++----
 2 files changed, 39 insertions(+), 10 deletions(-)

diff --git a/backend/services/pipeline.py b/backend/services/pipeline.py
index cc191d4..f3ab1c3 100644
--- a/backend/services/pipeline.py
+++ b/backend/services/pipeline.py
@@ -681,11 +681,19 @@ async def _ensure_local_datasheet(
     """
     if pdf_path.is_file():
         return True
-    lib_ds_key = proj_svc.library_has_datasheet(ctx.storage, mpn)
-    if lib_ds_key:
-        ctx.storage.download_to_local(lib_ds_key, pdf_path)
-        return True
-    from backend.services.datasheet_finder import find_datasheet
+    from backend.services.datasheet_finder import find_datasheet, mpn_query_variants
+
+    for name in mpn_query_variants(mpn) or [mpn]:
+        alt = pdf_path.parent / f"{safe_mpn(name)}.pdf"
+        if alt.is_file():
+            if alt.resolve() != pdf_path.resolve():
+                pdf_path.parent.mkdir(parents=True, exist_ok=True)
+                pdf_path.write_bytes(alt.read_bytes())
+            return True
+        lib_ds_key = proj_svc.library_has_datasheet(ctx.storage, name)
+        if lib_ds_key:
+            ctx.storage.download_to_local(lib_ds_key, pdf_path)
+            return True
 
     broker.publish(
         ctx.project_id, "step_update",
@@ -1474,7 +1482,19 @@ async def _stage_validation(ctx: PipelineContext) -> None:
     # Ensure all IC datasheet PDFs are available locally for review.
     # Cached ICs skipped pintable extraction, so their PDFs may not
     # have been downloaded yet. Auto-fetch fills remaining gaps.
-    for mpn in ctx.ic_mpns:
+    # Ensure PDFs for BOM ICs and any extra U* the netlist classified as IC.
+    seen_mpn: set[str] = set()
+    mpns_to_place = list(ctx.ic_mpns)
+    for comp in ctx.graph.components.values():
+        if comp.component_type != ComponentType.IC:
+            continue
+        extra = (comp.mpn or "").strip()
+        if extra:
+            mpns_to_place.append(extra)
+    for mpn in mpns_to_place:
+        if mpn in seen_mpn:
+            continue
+        seen_mpn.add(mpn)
         safe = safe_mpn(mpn)
         pdf_path = ds_dir / f"{safe}.pdf"
         if not pdf_path.is_file():
diff --git a/backend/services/validation.py b/backend/services/validation.py
index 3c078ff..36ffb7d 100644
--- a/backend/services/validation.py
+++ b/backend/services/validation.py
@@ -571,15 +571,24 @@ def _find_pdf(
     """Find the datasheet PDF for an MPN.  Checks local dir first,
     then tries to download from the library.
     """
-    safe = safe_mpn(mpn)
-    local = pdf_dir / f"{safe}.pdf"
-    if local.is_file():
-        return local
+    from backend.services.datasheet_finder import mpn_query_variants
+    from backend.pinscopex.utils import safe_mpn as _safe
+
+    names = mpn_query_variants(mpn) or [mpn]
+    for name in names:
+        local = pdf_dir / f"{_safe(name)}.pdf"
+        if local.is_file():
+            wanted = pdf_dir / f"{_safe(mpn)}.pdf"
+            if local != wanted and not wanted.is_file():
+                wanted.write_bytes(local.read_bytes())
+                return wanted
+            return local
 
     if storage:
         from backend.services import projects as proj_svc
         lib_key = proj_svc.library_has_datasheet(storage, mpn)
         if lib_key:
+            local = pdf_dir / f"{_safe(mpn)}.pdf"
             storage.download_to_local(lib_key, local)
             if local.is_file():
                 return local