New updates on DB and JSON

app/api/batch_common.py

@@ -209,6 +209,11 @@ class BatchFileOut(BaseModel):
     # the run that took it, which is how a sender gets from the drop id they
     # hold to the batch that carries their results.
     released_to: Optional[str] = None
+    # The other direction: which drop this file came out of. A run can be
+    # assembled from several drops, and this is the only exact way for a sender
+    # to pick their own file out of one - `filename` is a coincidence, because
+    # two senders can both upload products.csv.
+    from_drop: Optional[str] = None
     stage_index: int = 0
     stage_name: str = ""
     total_stages: int = pipeline.TOTAL_STAGES

app/api/routers/batch_catalog.py

@@ -408,6 +408,23 @@ def list_inbox() -> InboxOut:
     return InboxOut(pending_count=pending_count, submissions=submissions)
 
 
+def _stamp_origins(manifest, origins: List[str]) -> None:
+    """Record which drop each file in a freshly staged run came from.
+
+    Done after staging, by position, for the same reason `stage_and_queue`
+    back-fills `rows_total` that way: the staging helpers take a
+    (filename, bytes, rows) tuple shared with the uploads router, and widening
+    it here would change a signature three callers depend on.
+
+    Safe by position because `from-inbox` stages with `invalid=[]`, so
+    manifest.files is exactly `picked` in order.
+    """
+    for entry, drop_id in zip(manifest.files, origins):
+        entry.from_drop = drop_id
+    batch_ingest.write_manifest(manifest)
+    batch_job_store.put(manifest)
+
+
 @router.post("/from-inbox", status_code=status.HTTP_202_ACCEPTED,
              dependencies=[Depends(require_admin)])
 def start_batch_from_inbox(request: InboxStartRequest) -> BatchOut:
@@ -438,6 +455,11 @@ def start_batch_from_inbox(request: InboxStartRequest) -> BatchOut:
     # what parse_all returns, so nothing needs reparsing here.
     picked: List[tuple] = []
     senders: List[str] = []
+    # The drop each picked file came out of, in the SAME ORDER as `picked`, so
+    # it can be stamped onto the staged manifest below. Kept parallel rather
+    # than folded into the tuple because that tuple shape is shared with
+    # parse_all and with the uploads router.
+    origins: List[str] = []
     for batch_id, indices in grouped.items():
         manifest = batch_ingest.read_manifest(batch_id)
         if not manifest or manifest.status != batch_ingest.PENDING:
@@ -454,6 +476,7 @@ def start_batch_from_inbox(request: InboxStartRequest) -> BatchOut:
                 # will show it has left the inbox.
                 continue
             picked.append((entry.filename, contents, entry.rows_total))
+            origins.append(batch_id)
             if manifest.submitted_by:
                 senders.append(manifest.submitted_by)
 
@@ -483,6 +506,7 @@ def start_batch_from_inbox(request: InboxStartRequest) -> BatchOut:
             fetch_images=request.fetch_images,
             submitted_by=submitted_by,
         )
+        _stamp_origins(manifest, origins)
     else:
         manifest, started = batch_common.stage_and_queue(
             picked,
@@ -491,6 +515,7 @@ def start_batch_from_inbox(request: InboxStartRequest) -> BatchOut:
             fetch_images=request.fetch_images,
             submitted_by=submitted_by,
         )
+        _stamp_origins(manifest, origins)
         if not started:
             raise HTTPException(
                 status_code=429,