litellm

mirror of https://github.com/BerriAI/litellm.git synced 2026-09-15 23:31:29 +00:00

History

mateo-berri d664ca139e chore(router): suppress the retry-skip kwargs writes and correct the filter docstring The two writes that hand the skip list to the next attempt now carry a `# rebind-ok` reason, which is the sanctioned escape hatch for an unavoidable parameter mutation and matches how `log_retry` already writes into the same kwargs dict a few lines above `get_excluded_filtered_deployments`'s docstring said returning the unfiltered list would re-include the deployment that just failed. The retry skip does exactly that on purpose, so the docstring now says each caller decides what an empty result means The reliability registry cell the new e2e test claims is marked `fail_before_fix: proven`: the same config returns 400 at the merge base and 200 off a sibling deployment at the tip		2026-09-06 00:53:24 -07:00
..
agent_tests
audio_tests
base_sdk_tests
basic_proxy_startup_tests
batches_tests
benchmarks
code_coverage_tests	ci: allowlist the bounded _unqualified qualifier peel in the recursion detector	2026-09-04 18:13:51 -07:00
documentation_tests	Merge remote-tracking branch 'origin/main' into litellm_bedrock_messages_disconnect_billing	2026-08-31 08:58:37 -07:00
e2e	chore(router): suppress the retry-skip kwargs writes and correct the filter docstring	2026-09-06 00:53:24 -07:00
enterprise	fix(batches): register ownership for every batch create path (#39810 )	2026-09-04 23:59:51 -07:00
guardrails_tests	fix(logging): blocked requests no longer report guardrail_status=success in multi-guardrail configs (#39596 )	2026-09-03 17:33:31 -07:00
image_gen_tests
integration
litellm-proxy-extras	test(proxy-extras): fake run_prisma instead of subprocess.run in the migrate deploy harness	2026-09-03 16:10:44 -07:00
litellm_utils_tests	test(aiohttp): pin NO_PROXY so proxy env cannot hijack the refused-port probe	2026-08-28 12:45:46 -07:00
llm_responses_api_testing	fix(guardrails): deliver modify_response block as valid SSE on streaming chat and Responses	2026-08-31 16:01:39 -07:00
llm_translation	test: exempt MockTransport request-shape embedding tests from VCR replay	2026-09-01 13:29:12 -07:00
load_tests	feat(proxy): per-worker admission control that rejects excess requests with 503 (#39352 )	2026-09-03 18:19:04 -07:00
local_testing	fix(cache): use sync Redis batch reads (#39358 )	2026-09-03 14:37:48 -07:00
logging_callback_tests	Merge branch 'litellm_internal_staging' into litellm_fix_failing_request_slowdown	2026-09-03 00:20:51 -07:00
mcp_tests	fix(mcp): scope allow-all servers to virtual keys (#39531 )	2026-09-03 10:32:03 -07:00
multi_instance_e2e_tests
ocr_tests	fix(vertex): avoid duplicate DeepSeek OCR model namespace	2026-09-01 14:39:15 -07:00
openai_endpoints_tests	refactor(tests): assign the streamed id and lock poll once instead of rebinding	2026-09-03 13:49:43 -07:00
otel_tests
pass_through_tests	fix(logging): key bridged /v1/messages rows on the id the caller received	2026-09-03 01:15:06 -07:00
pass_through_unit_tests	test(websearch): carry a reasoned test-quality suppression on the router patch	2026-08-31 22:32:05 -07:00
proxy_admin_ui_tests	refactor(tests): assign the streamed id and lock poll once instead of rebinding	2026-09-03 13:49:43 -07:00
proxy_behavior	feat(team): report per-user spend within a team for JWT traffic (#39771 )	2026-09-04 12:00:47 -07:00
proxy_e2e_anthropic_messages_tests
proxy_migration_tests	fix(proxy-extras): kill the whole Prisma process group when a command times out	2026-09-02 18:29:55 -07:00
proxy_security_tests
proxy_unit_tests	fix(jwt): evict mapping cache after DB write in /jwt/key/mapping update and delete	2026-09-04 14:35:42 -07:00
router_unit_tests	test: repair two CI tests broken by intentional changes	2026-09-05 12:02:48 -07:00
rust-python-harness	test: address review notes on the chronic-test repairs	2026-09-04 10:18:15 -07:00
search_tests
spend_tracking_tests
store_model_in_db_tests	test(store_model_in_db): accept both 400 shapes in the unknown-model spend log test	2026-09-04 18:52:17 -07:00
test_litellm	test(router): cover the retry skip-list narrowing helper	2026-09-06 00:06:35 -07:00
unified_google_tests
vector_store_tests	fix(vector-store): carry request metadata into the Router executor built from the router kwarg	2026-09-02 16:53:05 -07:00
windows_tests
__init__.py
_fake_openai_endpoint_server.py	test(timeout): time out against the local fake endpoint instead of api.openai.com	2026-09-03 09:53:30 -07:00
_flush_vcr_cache.py
_live_test_helpers.py
_openai_record_replay_proxy.py
_vcr_conftest_common.py
_vcr_redis_persister.py
_wait_helpers.py
_ws_vcr.py
eval_swe_bench.py
fake_openai_endpoint.py
gettysburg.wav
large_text.py
openai_batch_completions.jsonl
pyrightconfig.json
README.MD
test_anthropic_compaction_usage.py
test_budget_management.py
test_callbacks_on_proxy.py
test_debug_warning.py
test_default_encoding_non_root.py
test_end_users.py
test_fallbacks.py
test_gpt5_azure_temperature_support.py
test_health.py
test_keys.py	test: fix staging CI regressions from #38182 , #38144 , #38265 , #37962 , and #37969	2026-08-25 23:01:20 -07:00
test_litellm_proxy_responses_config.py
test_logging.conf
test_models.py	test: address review notes on the chronic-test repairs	2026-09-04 10:18:15 -07:00
test_new_vector_store_endpoints.py
test_openai_endpoints.py
test_organizations.py
test_otel_thread_leak.py
test_presidio_latency.py
test_proxy_server_non_root.py
test_ratelimit.py
test_resource_cleanup.py
test_rust_python_harness.py	test: address review notes on the chronic-test repairs	2026-09-04 10:18:15 -07:00
test_service_logger_otel.py
test_spend_logs.py
test_team.py
test_team_logging.py
test_team_members.py
test_users.py

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/test_litellm

This folder can only run mock tests.