mirror of https://github.com/tiennm99/litellm.git synced 2026-07-08 21:03:08 +00:00

Files

T

Krish Dholakia f7af8902b0 /v1/messages - Remove hardcoded model name on streaming + Tags - enable setting custom header tags (#12131 )

* fix(anthropic/experimental_pass_through): use given model name when returning streaming chunks

don't harcode model name on streaming

confusing for user

* fix(anthropic/streaming_iterator.py): remove scope of import

* feat(litellm_logging.py): allow admin to specify additional headers for using as spend tags

Closes https://github.com/BerriAI/litellm/issues/12129

* test(test_litellm_logging.py): add unit tests

* feat(openweb_ui.md): add custom tag tutorial to docs

* docs(cost_tracking.md): add tag based usage UI screenshot

* test: update test

* fix: fix import

2025-06-28 21:49:35 -07:00

caching

fix(redis_cache.py): support pipeline redis lpop for older redis vers… (#11425 )

2025-06-05 00:05:54 -07:00

completion_extras/litellm_responses_transformation

Completion-To-Responses Bridge: Support passing image url's (#11833 )

2025-06-18 12:48:17 -07:00

enterprise/enterprise_callbacks

[Bug Fix] Invite links email should contain the correct invite id (#12130 )

2025-06-28 09:19:32 -07:00

experimental_mcp_client

…

google_genai

[Feat] Add Bridge from generateContent <> /chat/completions (#12081 )

2025-06-27 11:08:55 -07:00

integrations

LiteLLM SDK <-> Proxy improvement (don't transform message client-side) + Bedrock - handle qs:.. in base64 file data + Tag Management - support adding public model names (#11908 )

2025-06-19 22:34:18 -07:00

litellm_core_utils

/v1/messages - Remove hardcoded model name on streaming + Tags - enable setting custom header tags (#12131 )

2025-06-28 21:49:35 -07:00

llms

/v1/messages - Remove hardcoded model name on streaming + Tags - enable setting custom header tags (#12131 )

2025-06-28 21:49:35 -07:00

passthrough

Refactor: bedrock passthrough fixes - migrate to Passthrough SDK (#12089 )

2025-06-26 22:51:35 -07:00

proxy

Fix user-team association issues in LiteLLM proxy (#12082 )

2025-06-27 21:29:49 -07:00

responses

Responses API - Add reasoning content support for non-OpenAI providers (#12055 )

2025-06-26 14:21:49 -07:00

router_strategy

Simplify experimental multi-instance rate limiter - more accurate (#11424 )

2025-06-07 11:10:55 -07:00

router_utils

Litellm dev 06 25 2025 p2 (#12049 )

2025-06-25 21:54:13 -07:00

secret_managers

fix(secret-managers): Break AzureCredentialType restriction on AZURE_CREDENTIAL (#11272 )

2025-05-31 01:03:08 -07:00

types

Convert scientific notation str to int + Bubble up azure content filter results (#11655 )

2025-06-11 23:07:22 -07:00

vector_stores

[Fix] QA Fixes - Vector Store Object Permissions (#11291 )

2025-05-31 09:41:05 -07:00

__init__.py

…

conftest.py

…

log.txt

…

readme.md

…

test_constants.py

…

test_cost_calculation_log_level.py

fix: change cost calculation logs from INFO to DEBUG level

2025-06-27 11:36:58 -06:00

test_cost_calculator.py

VertexAI Anthropic passthrough cost calc fixes + Filter litellm params from request sent to passthrough endpoint (#11992 )

2025-06-23 22:24:47 -07:00

test_logging.py

…

test_main.py

fix: tests

2025-05-31 13:14:37 -07:00

test_router.py

Store batch output file id in DB + Store batch file status in DB + (experimental) BATCH API COST TRACKING

2025-06-25 22:41:22 -07:00

test_utils.py

Fix unpack_defs handling of nested $ref inside anyOf items (#11964 )

2025-06-24 09:08:15 -07:00

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/`