refactor(proxy/batches): make managed-file resolution purely additive, fall back like base (#34584)

Restore the original PR's behavior on every path that did not already
resolve: no database, a lookup error, a missing managed-file row, or a
row without a storage_url all fall back to dispatching the original id,
which the managed-files deployment hook still maps. This drops the 404
and 503 fail-closed responses I had added, which were the only behaviors
that diverged from litellm_internal_staging.

The change is now strictly additive: when a managed-file row with a
storage_url exists, the unified batch branch substitutes it so providers
like Vertex receive a real gs:// path instead of the opaque token; every
other path behaves exactly as before. Verified live that non-managed,
managed-owner, multi-model load-balanced, and missing-row requests are
byte-identical to base

litellm/proxy/batches_endpoints/endpoints.py

@@ -49,12 +49,11 @@ async def _resolve_managed_input_file_storage_url(input_file_id: str) -> "str |
 
     Provider batch handlers (e.g. Vertex AI, which parses a `publishers/`
     segment out of the file URI) need a real storage location; the opaque
-    unified token crashes them. Returns None only when there is no database or
-    the row has no storage_url yet, so callers fall back to the original id
-    (which the managed-files deployment hook can still map). Fails closed
-    rather than dispatch a token that cannot be resolved: 404 when no
-    managed-file row exists, 503 when the lookup itself errors so the caller
-    can retry.
+    unified token crashes them. Returns None whenever a storage_url cannot be
+    produced (no database, lookup error, no managed-file row, or a row without
+    a storage_url yet) so callers fall back to dispatching the original id,
+    which the managed-files deployment hook still maps. This adds resolution
+    without changing behavior on any path that did not resolve before.
     """
     from litellm.proxy.proxy_server import prisma_client
 
@@ -64,15 +63,9 @@ async def _resolve_managed_input_file_storage_url(input_file_id: str) -> "str |
         db_file = await ManagedFileRepository(prisma_client).table.find_first(where={"unified_file_id": input_file_id})
     except Exception as e:
         verbose_proxy_logger.warning("create_batch: managed file lookup failed for %s: %s", input_file_id, e)
-        raise HTTPException(
-            status_code=503,
-            detail={"error": "Could not resolve managed file; please retry"},
-        )
+        return None
     if db_file is None:
-        raise HTTPException(
-            status_code=404,
-            detail={"error": f"Managed file not found: {input_file_id}"},
-        )
+        return None
     return db_file.storage_url or None
 
 

tests/test_litellm/proxy/batches_endpoints/test_endpoints.py

@@ -561,10 +561,11 @@ async def test_create__unified_file_id_resolves_real_storage_url(harness):
 
 
 @pytest.mark.asyncio
-async def test_create__unified_file_id_db_error_fails_closed_503(harness):
-    """A lookup error leaves the token unresolved, so it fails closed with a
-    retryable 503 rather than dispatching the opaque id into the provider crash
-    it cannot parse. Nothing is dispatched."""
+async def test_create__unified_file_id_db_error_falls_back_to_raw_id(harness):
+    """Resolution is additive and best-effort: a lookup error leaves the id
+    unresolved and dispatch falls back to the original id, exactly as before
+    this change (the managed-files deployment hook still maps it). No new
+    failure mode is introduced."""
     set_body(
         harness,
         {
@@ -585,12 +586,9 @@ async def test_create__unified_file_id_db_error_fails_closed_503(harness):
         patch.object(proxy_server, "prisma_client", MagicMock()),
         patch.object(endpoints, "ManagedFileRepository", fake_repo_cls),
     ):
-        with pytest.raises(ProxyException) as exc:
-            await call_create(harness)
+        await call_create(harness)
 
-    assert exc.value.code == "503"
-    harness.router_acreate.assert_not_called()
-    harness.litellm_acreate.assert_not_called()
+    assert harness.router_kwargs()["input_file_id"] == "litellm_proxy_unified_id"
 
 
 @pytest.mark.asyncio
@@ -626,11 +624,11 @@ async def test_create__multi_model_unified_file_with_loadbalancing_keeps_router_
 
 
 @pytest.mark.asyncio
-async def test_create__unified_file_id_missing_row_fails_closed_404(harness):
-    """With a database present, a managed unified id that has no row cannot be
-    resolved to a real storage location, so it fails closed with a 404 rather
-    than dispatching the opaque token, which would hit the Vertex
-    publishers-segment IndexError this PR exists to prevent."""
+async def test_create__unified_file_id_missing_row_falls_back_to_raw_id(harness):
+    """Resolution is additive: when no managed-file row exists there is nothing
+    to substitute, so dispatch falls back to the original id exactly as before
+    this change (the managed-files deployment hook still maps it). No new
+    failure mode is introduced for this case."""
     set_body(
         harness,
         {
@@ -651,12 +649,9 @@ async def test_create__unified_file_id_missing_row_fails_closed_404(harness):
         patch.object(proxy_server, "prisma_client", MagicMock()),
         patch.object(endpoints, "ManagedFileRepository", fake_repo_cls),
     ):
-        with pytest.raises(ProxyException) as exc:
-            await call_create(harness)
+        await call_create(harness)
 
-    assert exc.value.code == "404"
-    harness.router_acreate.assert_not_called()
-    harness.litellm_acreate.assert_not_called()
+    assert harness.router_kwargs()["input_file_id"] == "litellm_proxy_unified_id"
 
 
 @pytest.mark.asyncio