scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-13 23:11:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 152

Merge pull request #23646 from BerriAI/litellm_fix_ci_test_failures_03_14

Browse source 
[Fix] Responses bridge variable mismatch and outdated CI tests
This commit is contained in:
yuneng-jiang 2026-03-14 12:26:54 -07:00 • committed by GitHub
commit 8be5323e20
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 51 additions and 52 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
docs/my-website/docs/proxy/config_settings.md
View file

@ -1021,6 +1021,11 @@ router_settings:
| UPSTREAM_LANGFUSE_SECRET_KEY | Secret key for upstream Langfuse authentication
| USE_AWS_KMS | Flag to enable AWS Key Management Service for encryption
| USE_PRISMA_MIGRATE | Flag to use prisma migrate instead of prisma db push. Recommended for production environments.
| VANTAGE_API_KEY | API key for Vantage cost-import integration
| VANTAGE_BASE_URL | Base URL for Vantage API. Default is `https://api.vantage.sh`
| VANTAGE_EXPORT_FREQUENCY | Export frequency for Vantage — `hourly` (default), `daily`, or `interval`
| VANTAGE_EXPORT_INTERVAL_SECONDS | Interval in seconds when VANTAGE_EXPORT_FREQUENCY is `interval`
| VANTAGE_INTEGRATION_TOKEN | Vantage integration token for the cost-import endpoint
| WANDB_API_KEY | API key for Weights & Biases (W&B) logging integration
| WANDB_HOST | Host URL for Weights & Biases (W&B) service
| WANDB_PROJECT_ID | Project ID for Weights & Biases (W&B) logging integration

53
litellm/integrations/focus/destinations/vantage_destination.py
View file

@ -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 +136,37 @@ 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,
)
# 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 +175,7 @@ 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 +214,7 @@ class FocusVantageDestination(FocusDestination):
async def _upload_size_limited(
self,
client: httpx.AsyncClient,
client: AsyncHTTPHandler,
header: bytes,
data_lines: list[bytes],
filename: str,

2
litellm/main.py
View file

@ -1613,7 +1613,7 @@ def completion( # type: ignore # noqa: PLR0915
)
## RESPONSES API BRIDGE LOGIC ## - check if model has 'mode: responses' in litellm.model_cost map
model_info, model = responses_api_bridge_check(
responses_api_model_info, model = responses_api_bridge_check(
model=model,
custom_llm_provider=custom_llm_provider,
web_search_options=web_search_options,

1
tests/local_testing/test_anthropic_prompt_caching.py
View file

@ -151,6 +151,7 @@ async def test_litellm_anthropic_prompt_caching_tools():
},
"required": ["location"],
},
"type": "custom",
}
],
"max_tokens": 64000,

4
tests/proxy_e2e_anthropic_messages_tests/test_claude_agent_sdk.py
View file

@ -110,8 +110,8 @@ async def test_claude_agent_sdk_streaming(litellm_proxy_config, model_name, mode
# Note: Very short responses might come in 1 chunk, so we just verify we got content
assert len(received_chunks) > 0, f"No chunks received from {model_name}"
# Verify response contains expected content (case insensitive)
assert "hello" in full_response.lower(), f"Response doesn't contain expected greeting: {full_response}"
# Verify response is non-empty (don't assert on specific LLM content — it's non-deterministic)
assert len(full_response.strip()) > 0, f"Empty response received from {model_name}"
print(f"✅ Test passed for {model_name}")

38
tests/test_litellm/integrations/focus/test_vantage_destination.py
View file

@ -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(),
@ -100,8 +99,9 @@ async def test_should_upload_csv_to_correct_url():
async def test_should_batch_large_content():
dest = FocusVantageDestination(prefix="exports", config=_config())
# Create content larger than 2 MB
header = b"col1,col2,col3"
# Create content larger than 2 MB — use supported column names so
# _strip_unsupported_columns does not remove them.
header = b"ChargeCategory,ChargePeriodStart,BilledCost"
row = b"a" * 100 + b"," + b"b" * 100 + b"," + b"c" * 100
num_rows = (VANTAGE_MAX_BYTES_PER_UPLOAD // len(row)) + 100
large_content = header + b"\n" + b"\n".join([row] * num_rows) + b"\n"
@ -113,19 +113,17 @@ 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", {})
if "file" in files:
upload_calls.append(files["file"][1])
if "csv" in files:
upload_calls.append(files["csv"][1])
return mock_response
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(),
@ -144,7 +142,7 @@ async def test_should_batch_by_row_count():
"""Verify batching triggers when row count exceeds 10K even if under 2 MB."""
dest = FocusVantageDestination(prefix="exports", config=_config())
header = b"col1"
header = b"ChargeCategory"
# Short rows so total size stays well under 2 MB
row = b"x"
num_rows = VANTAGE_MAX_ROWS_PER_UPLOAD + 500
@ -159,19 +157,17 @@ 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", {})
if "file" in files:
upload_calls.append(files["file"][1])
if "csv" in files:
upload_calls.append(files["csv"][1])
return mock_response
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(),