Commit graph

15 commits

Author SHA1 Message Date
Shivam Rawat
d49abf8577
[Fix] Pass MCP auth headers from request into tool fetch for /v1/responses and chat completions (#22291)
* fixed dynamic auth for /responses with mcp

* fixed greptile concern
2026-02-27 19:15:51 -08:00
Julio Quinteros Pro
c3346962a9 fix: replace silent if-hasattr guards with unconditional assertions in MCP streaming tests
The `if hasattr(...)` guards in test_acompletion_with_mcp_adds_metadata_to_streaming
and test_acompletion_with_mcp_streaming_metadata_in_correct_chunks could silently skip
the provider_specific_fields assertions if chunks lacked choices/delta. Replace with
unconditional `assert hasattr(...)` so failures surface immediately.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-17 21:42:31 -03:00
Julio Quinteros Pro
ab6d2eefb9 fix: improve test isolation for parallel execution
Fixes test failures that occur during parallel test execution (pytest -n 4)
due to module reloading issues with conftest.py reloading litellm.

Changes:
- Add module reload fixtures to ensure fresh references after conftest reloads
- Use patch.object and string-based patches instead of direct attribute assignment
- Use class name comparison instead of isinstance for reloaded modules
- Handle case where litellm is missing from sys.modules during parallel runs
- Move stream consumption inside patch contexts to avoid real API calls
- Mock litellm.acompletion instead of low-level HTTP handlers
- Add skipif decorator for enterprise-only test classes

Affected test files:
- test_container_integration.py
- test_responses_background_cost.py
- test_huggingface_embedding_handler.py
- test_vertex_ai_rerank_integration.py
- test_volcengine_responses_transformation.py
- test_pillar_guardrails.py
- test_litellm_pre_call_utils.py
- test_proxy_server.py
- test_converse_transformation.py
- test_chat_completions_handler.py
- test_aresponses_api_with_mcp.py
- test_anthropic_experimental_pass_through_messages_handler.py

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-17 21:28:23 -03:00
Julio Quinteros Pro
8d15996b5a test: Fix flaky tests with proper mocking and skip conditions
1. test_acompletion_with_mcp_streaming_metadata_in_correct_chunks:
   - Moved stream consumption inside patch context to avoid real API calls
   - The previous implementation had assertions outside the `with patch(...)`
     block, causing real OpenAI API calls when consuming the stream

2. TestCheckResponsesCost tests:
   - Added skip condition when litellm_enterprise module is not available
   - These tests import from litellm_enterprise.proxy.common_utils.check_responses_cost
     which is only available in the enterprise version
2026-02-15 13:08:30 -03:00
Krish Dholakia
fa0b26c611
ci/cd fixes (#21218)
* fix: add a2a-sdk to dev deps

* fix: fix test

* fix: update poetry lock

* test: cleanup bad/hanging tests
2026-02-14 12:11:53 -08:00
Yuta Saito
919033a6d0 fix: include tool arguments in proxy_server_request for spend logs callbacks 2026-01-23 16:36:37 +09:00
Yuta Saito
6a60b3d848 test: completions mcp output test 2026-01-23 15:17:14 +09:00
Yuta Saito
ed67bf2705 feat: Add MCP tools response to chat completions 2026-01-22 15:32:04 +09:00
Yuta Saito
caf5f7f8ae test: add test 2026-01-21 14:51:56 +09:00
Yuta Saito
ba43f742ab fix: event loop nesting issue in MCP chat completions with streaming
Problem: When using MCP tools with  and , the following error occurred:

RuntimeError: Timeout context manager should be used inside a task
2026-01-15 15:36:56 +09:00
Yuta Saito
864b61b433 fix: support ResponseFunctionToolCall in follow-up input 2025-12-13 07:55:13 +09:00
Yuta Saito
48579eafe3 fix: strip mcp server prefixes in responses 2025-12-13 07:17:50 +09:00
Yuta Saito
8cccf3e9f0 fix: update MCP handler invocation to pass full call context from main.py 2025-12-12 06:41:58 +09:00
Yuta Saito
6393277bf4 fix: separate MCP handling out of main.py 2025-12-11 10:39:14 +09:00
Yuta Saito
ed5cbdac2f feat: add support for using MCPs on /chat/completions 2025-12-10 10:55:33 +09:00