litellm

History

user 12fe945e7b fix: keep skills handler FastAPI-free; fold gcs deny list into the body bouncer Two cleanups: * ``LiteLLMSkillsHandler.create_skill`` raised ``HTTPException`` for identity-less callers, importing FastAPI from a ``litellm/llms/`` module — that violates the project rule that FastAPI lives only under ``proxy/``. Switch to ``ValueError`` (the same shape the rest of the handler uses for not-found/forbidden) and update the test. * The proxy-auth body bouncer derived its observability ban list from ``_supported_callback_params`` only, missing ``_request_blocked_callback_params`` (where ``gcs_bucket_name`` and ``gcs_path_service_account`` live). Two recently-merged sibling PRs (#27019 added the deny list, #27081 added the test asserting these are rejected at the request body root) crossed without folding them together. Union the GCS deny list into the bouncer's derivation so the single source of truth covers both code paths.		2026-05-04 23:54:33 +00:00
..
agent_tests
audio_tests
basic_proxy_startup_tests
batches_tests	test(vertex-batches): set is_redirect=False on mocked retrieve response	2026-04-29 19:01:49 -07:00
benchmarks
code_coverage_tests	Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_vcr-cassette-llm-tests-af37	2026-04-30 17:56:02 -07:00
documentation_tests
enterprise	fix metric labels for litellm-side rejects	2026-05-01 15:46:53 -07:00
guardrails_tests
image_gen_tests
litellm	Merge remote-tracking branch 'origin/litellm_internal_staging' into codex/cloud-storage-file-guard	2026-05-04 11:25:41 -07:00
litellm_core_utils
litellm_utils_tests	[Test] Anthropic: Replace Legacy Claude-4-Sonnet Alias With Haiku 4.5	2026-05-01 19:10:27 -07:00
litellm-proxy-extras
llm_responses_api_testing	test(responses): replace legacy claude-4-sonnet alias in multiturn tool-call test	2026-05-03 07:48:56 +00:00
llm_translation	Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_oss_staging_04_25_2026	2026-05-02 06:04:39 +00:00
load_tests
local_testing	[Test] Anthropic: Replace Legacy Claude-4-Sonnet Alias With Haiku 4.5	2026-05-01 19:10:27 -07:00
logging_callback_tests	fix(callbacks): preserve langfuse secret alias	2026-04-30 14:36:51 -07:00
mcp_tests
multi_instance_e2e_tests
ocr_tests
old_proxy_tests/tests
openai_endpoints_tests
otel_tests	[Test] Proxy E2E: Opt In To Client Mock Response For Model Access Tests	2026-04-30 17:05:31 -07:00
pass_through_tests	[Test] Anthropic Passthrough: Bump Thinking Tests Off Legacy Sonnet 4 Alias	2026-05-01 19:33:08 -07:00
pass_through_unit_tests	fix: block path traversal SSRF in BitBucket, Arize Phoenix, and AssemblyAI clients (#26943 )	2026-05-01 11:45:12 -07:00
proxy_admin_ui_tests	[Fix] CI/Tooling: Correct min-release-age value in .npmrc files	2026-04-29 19:49:27 -07:00
proxy_e2e_anthropic_messages_tests
proxy_security_tests
proxy_unit_tests	Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_fix-ag-not-resolved	2026-05-01 17:21:29 -07:00
router_unit_tests	fix(router): apply decoded provider for managed container IDs without model_id	2026-04-30 21:29:38 +00:00
scim_tests
search_tests
spend_tracking_tests
store_model_in_db_tests
test_litellm	fix: keep skills handler FastAPI-free; fold gcs deny list into the body bouncer	2026-05-04 23:54:33 +00:00
unified_google_tests
vector_store_tests	fix: drop milvus dbName and partitionNames from MILVUS_OPTIONAL_PARAMS	2026-04-30 11:51:32 -07:00
windows_tests
__init__.py
_flush_vcr_cache.py	tests(vcr): isolate cassette redis to CASSETTE_REDIS_URL	2026-05-01 12:32:59 -07:00
_vcr_redis_persister.py	fix(tests): anchor VCR redis cassette key to repo root	2026-05-01 23:27:18 +00:00
eval_swe_bench.py
gettysburg.wav
large_text.py
openai_batch_completions.jsonl
README.MD
test_budget_management.py
test_callbacks_on_proxy.py
test_config.py
test_debug_warning.py
test_default_encoding_non_root.py
test_end_users.py
test_entrypoint.py
test_fallbacks.py
test_gpt5_azure_temperature_support.py
test_health.py
test_keys.py
test_litellm_proxy_responses_config.py
test_logging.conf
test_models.py
test_new_vector_store_endpoints.py
test_openai_endpoints.py
test_organizations.py
test_otel_thread_leak.py
test_passthrough_endpoints.py
test_presidio_latency.py
test_proxy_server_non_root.py
test_ratelimit.py
test_resource_cleanup.py
test_service_logger_otel.py
test_spend_logs.py
test_team_logging.py
test_team_members.py
test_team.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.