[Fix] Use cached async HTTP client in Vantage destination

Replace per-request `httpx.AsyncClient` with `get_async_httpx_client`
to avoid the +500ms latency penalty from creating new clients per
request. Updates tests to mock the cached client factory.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

litellm/integrations/focus/destinations/vantage_destination.py

@@ -9,6 +9,11 @@ from typing import Any, Optional
 import httpx
 
 from litellm._logging import verbose_logger
+from litellm.llms.custom_httpx.http_handler import (
+    AsyncHTTPHandler,
+    get_async_httpx_client,
+    httpxSpecialProvider,
+)
 
 from .base import FocusDestination, FocusTimeWindow
 
@@ -131,45 +136,38 @@ class FocusVantageDestination(FocusDestination):
         # rejection (e.g. InvoiceIssuerName, ProviderName, PublisherName).
         content = _strip_unsupported_columns(content)
 
-        # Reuse a single HTTP client for the entire deliver() call
-        async with httpx.AsyncClient(timeout=60.0) as client:
-            # Check both size and row-count limits before single-shot upload
-            lines = content.split(b"\n")
-            data_line_count = sum(1 for line in lines[1:] if line.strip())
-            within_limits = (
-                len(content) <= VANTAGE_MAX_BYTES_PER_UPLOAD
-                and data_line_count <= VANTAGE_MAX_ROWS_PER_UPLOAD
-            )
-            if within_limits:
-                await self._upload_csv(client, content, filename)
-                return
+        client = get_async_httpx_client(
+            llm_provider=httpxSpecialProvider.LoggingCallback,
+            params={"timeout": 60.0},
+        )
 
-            # Otherwise split into batches respecting both limits
-            await self._upload_batched(client, content, filename)
+        # Check both size and row-count limits before single-shot upload
+        lines = content.split(b"\n")
+        data_line_count = sum(1 for line in lines[1:] if line.strip())
+        within_limits = (
+            len(content) <= VANTAGE_MAX_BYTES_PER_UPLOAD
+            and data_line_count <= VANTAGE_MAX_ROWS_PER_UPLOAD
+        )
+        if within_limits:
+            await self._upload_csv(client, content, filename)
+            return
+
+        # Otherwise split into batches respecting both limits
+        await self._upload_batched(client, content, filename)
 
     async def _upload_csv(
-        self, client: httpx.AsyncClient, csv_bytes: bytes, filename: str
+        self, client: AsyncHTTPHandler, csv_bytes: bytes, filename: str
     ) -> None:
         url = f"{self.base_url}/v2/integrations/" f"{self.integration_token}/costs.csv"
         headers = {
             "Authorization": f"Bearer {self.api_key}",
         }
 
-        response = await client.post(
+        await client.post(
             url,
             headers=headers,
             files={"csv": (filename, csv_bytes, "text/csv")},
         )
-        try:
-            response.raise_for_status()
-        except httpx.HTTPStatusError as e:
-            verbose_logger.error(
-                "Vantage destination: upload failed for %s — %s — response body: %s",
-                filename,
-                e,
-                response.text,
-            )
-            raise
 
         verbose_logger.debug(
             "Vantage destination: uploaded %d bytes (%s)",
@@ -178,7 +176,7 @@ class FocusVantageDestination(FocusDestination):
         )
 
     async def _upload_batched(
-        self, client: httpx.AsyncClient, csv_bytes: bytes, filename: str
+        self, client: AsyncHTTPHandler, csv_bytes: bytes, filename: str
     ) -> None:
         """Split the CSV into batches and upload each.
 
@@ -217,7 +215,7 @@ class FocusVantageDestination(FocusDestination):
 
     async def _upload_size_limited(
         self,
-        client: httpx.AsyncClient,
+        client: AsyncHTTPHandler,
         header: bytes,
         data_lines: list[bytes],
         filename: str,

tests/test_litellm/integrations/focus/test_vantage_destination.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 
 from datetime import datetime, timedelta, timezone
 from typing import Any, Dict, List
-from unittest.mock import AsyncMock, patch
+from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
@@ -15,6 +15,8 @@ from litellm.integrations.focus.destinations.vantage_destination import (
     VANTAGE_MAX_ROWS_PER_UPLOAD,
 )
 
+MOCK_TARGET = "litellm.integrations.focus.destinations.vantage_destination.get_async_httpx_client"
+
 
 def _window(freq: str = "hourly", hour: int = 5) -> FocusTimeWindow:
     start = datetime(2024, 1, 2, hour, tzinfo=timezone.utc)
@@ -72,17 +74,14 @@ async def test_should_skip_empty_content():
 @pytest.mark.asyncio
 async def test_should_upload_csv_to_correct_url():
     dest = FocusVantageDestination(prefix="exports", config=_config())
-    captured: Dict[str, Any] = {}
 
     mock_response = AsyncMock()
     mock_response.raise_for_status = lambda: None
 
-    mock_client = AsyncMock()
+    mock_client = MagicMock()
     mock_client.post = AsyncMock(return_value=mock_response)
-    mock_client.__aenter__ = AsyncMock(return_value=mock_client)
-    mock_client.__aexit__ = AsyncMock(return_value=False)
 
-    with patch("litellm.integrations.focus.destinations.vantage_destination.httpx.AsyncClient", return_value=mock_client):
+    with patch(MOCK_TARGET, return_value=mock_client):
         await dest.deliver(
             content=b"header\nrow1\n",
             time_window=_window(),
@@ -114,9 +113,7 @@ async def test_should_batch_large_content():
     mock_response = AsyncMock()
     mock_response.raise_for_status = lambda: None
 
-    mock_client = AsyncMock()
-    mock_client.__aenter__ = AsyncMock(return_value=mock_client)
-    mock_client.__aexit__ = AsyncMock(return_value=False)
+    mock_client = MagicMock()
 
     async def capture_post(url, **kwargs):
         files = kwargs.get("files", {})
@@ -126,7 +123,7 @@ async def test_should_batch_large_content():
 
     mock_client.post = capture_post
 
-    with patch("litellm.integrations.focus.destinations.vantage_destination.httpx.AsyncClient", return_value=mock_client):
+    with patch(MOCK_TARGET, return_value=mock_client):
         await dest.deliver(
             content=large_content,
             time_window=_window(),
@@ -160,9 +157,7 @@ async def test_should_batch_by_row_count():
     mock_response = AsyncMock()
     mock_response.raise_for_status = lambda: None
 
-    mock_client = AsyncMock()
-    mock_client.__aenter__ = AsyncMock(return_value=mock_client)
-    mock_client.__aexit__ = AsyncMock(return_value=False)
+    mock_client = MagicMock()
 
     async def capture_post(url, **kwargs):
         files = kwargs.get("files", {})
@@ -172,7 +167,7 @@ async def test_should_batch_by_row_count():
 
     mock_client.post = capture_post
 
-    with patch("litellm.integrations.focus.destinations.vantage_destination.httpx.AsyncClient", return_value=mock_client):
+    with patch(MOCK_TARGET, return_value=mock_client):
         await dest.deliver(
             content=content,
             time_window=_window(),