mirror of https://github.com/tiennm99/litellm.git synced 2026-07-08 19:16:32 +00:00

Files

T

Kris Xia 5e00a49e7f fix(streaming): normalize status code extraction to prevent 4xx errors from triggering mid-stream fallback (#18698 )

在流式处理错误时，添加状态码标准化逻辑，确保 4xx 客户端错误直接抛出而不是被包装成 MidStreamFallbackError。

- 新增 _normalize_status_code 函数用于从异常对象提取状态码
- 优先从异常的 status_code 属性获取，其次从 response.status_code 获取
- 当映射异常或原始异常的状态码在 400-499 范围内时，直接抛出映射异常
- 添加单元测试验证 Vertex AI 400 错误正确抛出为 BadRequestError
- 确保流式处理中的客户端错误能够正确传播，而不会触发回退机制

2026-01-06 23:41:23 +05:30

a2a_protocol

…

caching

…

completion_extras

Put reasoning summary behind feat flag

2026-01-06 11:36:20 +05:30

containers

…

enterprise

Tests

2025-12-17 16:07:01 -08:00

experimental_mcp_client

…

google_genai

fix: auth header for custom api base in generate Content request

2026-01-05 12:25:13 +05:30

images

fix(image_edit): add drop_params support and fix Vertex AI config (#18077 )

2025-12-17 11:28:34 +05:30

integrations

Merge pull request #18663 from BerriAI/litellm_staging_01_05_2026

2026-01-06 10:46:04 +05:30

interactions

fix: test_create_simple_string_input

2026-01-05 17:15:12 +05:30

litellm_core_utils

fix(streaming): normalize status code extraction to prevent 4xx errors from triggering mid-stream fallback (#18698 )

2026-01-06 23:41:23 +05:30

llms

fix(streaming): normalize status code extraction to prevent 4xx errors from triggering mid-stream fallback (#18698 )

2026-01-06 23:41:23 +05:30

passthrough

…

proxy

fix: test_update_ui_settings_allowlisted_value

2026-01-06 13:58:37 +05:30

responses

Fix CI: Revert security scan changes and add GitGuardian ignore rules (#18358 )

2025-12-22 17:03:53 -08:00

router_strategy

…

router_utils

[Feat] New Logging Integration - Azure Sentinel Logger (#18146 )

2025-12-18 02:04:49 +05:30

secret_managers

…

types

fix: extend case normalization to ALL guardrail types (not just tool_permission) (#18664 )

2026-01-05 11:59:00 -08:00

vector_stores

…

__init__.py

…

conftest.py

…

log.txt

…

readme.md

…

test_acompletion_session_reuse_e2e.py

…

test_add_deployment_no_master_key.py

…

test_aembedding_session_reuse_e2e.py

…

test_azure_video_router.py

…

test_claude_haiku_4_5_config.py

…

test_constants.py

…

test_container_router.py

…

test_cost_calculation_log_level.py

…

test_cost_calculator.py

[Feat] AI Gateway - Add support for Platform Fee / Margins (#18427 )

2025-12-25 11:07:27 +05:30

test_exception_mapping_request_attribute.py

…

test_filter_out_litellm_params.py

…

test_gpt_image_cost_calculator.py

fix(cost_calculator): correct gpt-image-1 cost calculation using token-based pricing (#17906 )

2026-01-02 23:08:52 +05:30

test_groq_streaming_encoding.py

…

test_lazy_imports.py

refactor: migrate utils.py lazy imports to registry pattern (#18657 )

2026-01-05 09:55:48 -08:00

test_logging.py

…

test_lowest_latency_zero_tokens.py

…

test_main.py

…

test_nested_drop_params.py

…

test_redis.py

…

test_responses_id_security.py

…

test_router_google_genai.py

…

test_router.py

[Feat] Guardrails Load Balancing - Allow Platform admins to load balance between guardrails (#18181 )

2025-12-19 00:08:03 +05:30

test_shared_session_integration.py

…

test_system_message_format_bug.py

…

test_utils.py

Revert "feat(model_cost): add display_name, model_vendor, and model_version metadata to model entries"

2026-01-06 15:29:42 +05:30

test_uuid_helper.py

…

test_video_generation.py

…

readme.md

Testing for `litellm/`

This directory 1:1 maps the the litellm/ directory, and can only contain mocked tests.

The point of this is to:

Increase test coverage of litellm/
Make it easy for contributors to add tests for the litellm/ package and easily run tests without needing LLM API keys.

File name conventions

litellm/proxy/test_caching_routes.py maps to litellm/proxy/caching_routes.py
test_<filename>.py maps to litellm/<filename>.py

readme.md

Testing for litellm/

File name conventions

Testing for `litellm/`