mirror of https://github.com/tiennm99/litellm.git synced 2026-07-15 04:32:22 +00:00

Files

T

Marcelo DíazandGitHub 094ce8f772 feat(gemini): Add custom TTL support for context caching (#9810 ) (#12541 )

- Add ttl parameter to cache_control for Gemini models
- Support Google's TTL format (e.g., '3600s', '7200s')
- Implement robust TTL extraction and validation
- Extract TTL before system message transformation to handle all cases
- Add comprehensive test suite with 17 test cases in tests/test_litellm/
- Update documentation with TTL usage examples
- Maintain backward compatibility with existing cache_control usage

Fixes #9810

2025-07-14 22:30:54 -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

fix: handle reasoning parameters and response in responses bridge (#12433 )

2025-07-10 18:06:45 -07:00

enterprise/enterprise_callbacks

Add fix to tests (#12263 )

2025-07-02 16:57:49 -07:00

experimental_mcp_client

[MCP Gateway] Allow using stdio MCPs with LiteLLM (#12530 )

2025-07-11 20:21:02 -07:00

google_genai

[Bug Fix] /generateContent API - Only pass supported params when using OpenAI models (#12297 )

2025-07-04 12:08:10 -07:00

integrations

OTEL - OTEL_RESOURCE_ATTRIBUTES support + Model Hub - new model hub table view, new /public/model_hub endpoint, fix duplicates in /model_group/info (#12468 )

2025-07-09 22:00:57 -07:00

litellm_core_utils

Remove stream options from streaming + fix guardrail start time on log duration (#12346 )

2025-07-05 15:54:47 -07:00

llms

feat(gemini): Add custom TTL support for context caching (#9810 ) (#12541 )

2025-07-14 22:30:54 -07:00

passthrough

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

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

proxy

Control Plane + Data Plane support (#12601 )

2025-07-14 21:31:56 -07:00

responses

feat: add image support for Responses API to Chat Completion transformation (#12204 )

2025-07-07 21:17:54 -07:00

router_strategy

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

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

router_utils

fix mapped tests (#12320 )

2025-07-04 10:04:43 -07:00

secret_managers

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

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

types

feat(stream_chunk_builder_utils.py): correctly return web_search_requests on stream chunk builder

2025-07-03 10:56:26 -07:00

vector_stores

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

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

__init__.py

[Feat] Add github co-pilot as a new LLM API provider (#12325 )

2025-07-04 13:12:16 -07:00

conftest.py

fix mapped tests (#12320 )

2025-07-04 10:04:43 -07:00

log.txt

Litellm fix GitHub action testing (#11163 )

2025-05-26 14:41:42 -07:00

readme.md

Litellm fix GitHub action testing (#11163 )

2025-05-26 14:41:42 -07:00

test_constants.py

Litellm fix GitHub action testing (#11163 )

2025-05-26 14:41:42 -07:00

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

fix: add implicit caching cost calculation for Gemini 2.x models (#12585 )

2025-07-14 16:37:17 -07:00

test_logging.py

Litellm fix GitHub action testing (#11163 )

2025-05-26 14:41:42 -07:00

test_main.py

Add 'thinking blocks' to stream chunk builder + remove experimental 'by_tag' metrics on prometheus (fix cardinality issue) (#12395 )

2025-07-07 21:41:44 -07:00

test_router.py

Resolve model group alias on Auth + /v1/messages Fallback support (#12440 )

2025-07-09 22:27:55 -07:00

test_utils.py

Claude 4 Bedrock /invoke route support + Bedrock application inference profile tool choice support (#12599 )

2025-07-14 21:42:25 -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/`