litellm

mirror of https://github.com/BerriAI/litellm.git synced 2026-10-29 06:33:28 +00:00

History

moe-berri 208ef99b88 fix(images): honor max_retries and prevent Router retry amplification (#48705 ) * test(images): cover SDK retry budgets and router ownership Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(images): forward max_retries to the OpenAI image generation client Per-call, deployment and default_litellm_params max_retries were filtered out before reaching the OpenAI-compatible image handler, which then always used 2 SDK retries. Forward the caller's value, and pin it to 0 for routed calls so the Router stays the only retry owner, matching completion() Co-authored-by: Ericz <yonglzh@gmail.com> Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(images): read image max_retries through a typed kwargs view Co-authored-by: Ericz <yonglzh@gmail.com> Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(images): assert the public invalid retry error mapping Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(images): preserve the invalid retry status code Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(images): group the proxy test imports Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(images): discard proxy retry test routers Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: Ericz <yonglzh@gmail.com>		2026-10-28 10:46:47 -07:00
..
_support	fix(proxy)!: end a chat completions stream with an error event when a guardrail blocks mid-stream (#46953 )	2026-10-17 18:00:12 -07:00
audio_tests	feat(vertex-ai)!: support gemini 3.1 flash tts (#31915 )	2026-10-21 04:18:42 +00:00
base_sdk_tests	refactor(mcp): drop the experimental label from the MCP server and client paths (#48513 )	2026-10-27 17:47:50 +00:00
benchmarks	refactor(mcp): drop the experimental label from the MCP server and client paths (#48513 )	2026-10-27 17:47:50 +00:00
code_coverage_tests	fix(router): continue Responses mid-stream fallbacks on models without assistant prefill (#47672 )	2026-10-28 04:34:40 -07:00
documentation_tests
e2e	fix(responses): forward top-level moderation param to OpenAI (#48708 )	2026-10-28 10:33:11 -07:00
e2e_harness	test(perf): ramp the load cases until the pod stops keeping up and floor sustained_rps (#47758 )	2026-10-20 22:31:08 -07:00
fixtures
harness_e2e	fix(harness): set PWD to the working directory of local sandbox commands (#47530 )	2026-10-20 20:06:11 +00:00
integration	fix(images): honor max_retries and prevent Router retry amplification (#48705 )	2026-10-28 10:46:47 -07:00
rust-python-harness	feat(rust): encode LiteLLM response ids on native responses (#46572 )	2026-10-18 20:52:34 -07:00
test_litellm_rust	feat(rust): one typed decline from core up to each host (#47772 )	2026-10-28 09:22:11 -07:00
typing
unit	fix(images): honor max_retries and prevent Router retry amplification (#48705 )	2026-10-28 10:46:47 -07:00
windows_tests
__init__.py
_fake_openai_endpoint_server.py
_flush_vcr_cache.py
_live_test_helpers.py
_master_key.py
_openai_record_replay_proxy.py
_process_helpers.py
_vcr_conftest_common.py
_vcr_redis_persister.py
_wait_helpers.py
_ws_vcr.py
AGENTS.md
capturing_transport.py
eval_swe_bench.py
fake_openai_endpoint.py
gettysburg.wav
large_text.py
openai_batch_completions.jsonl
pyrightconfig.json
README.MD
test_logging.conf
test_rust_python_harness.py
VCR_TESTING.md
white_100x100.png

README.MD

In total litellm runs 1000+ tests

[02/20/2025] Update:

To make it easier to contribute and map what behavior is tested,

we've started mapping the litellm directory in tests/unit

This folder can only run mock tests.