scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-11 03:38:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 82
litellm/tests
History
Caduri Katzav f7e934677b fix(guardrails): harden generic_guardrail_api fire_and_forget dispatch 
Parse fire_and_forget and fire_and_forget_max_inflight the way pydantic parses config values, so "true" and "5" work. A value that cannot be read is ignored with a warning: fire_and_forget falls back to false, so the guardrail keeps enforcing, and fire_and_forget_max_inflight falls back to 100

Force streaming_transform_mode to block_only under fire_and_forget. With incremental_diff the unified guardrail buffered the stream and dispatched one call per chunk, so a stream now sends a single end-of-stream call while the chunks reach the client live

The background POST now honors the guardrail's timeout and falls back to 30 seconds when it is unset. It is built from the same URL, headers and payload as the awaited call. A payload that cannot be serialized is recorded as not_run before anything is dispatched

Tests that build GenericGuardrailAPI move to a mirror test_generic_guardrail_api.py, the dispatcher and parser tests stay in test_background_dispatch.py, and a shared conftest.py captures proxy warnings
2026-10-03 14:53:48 +03:00
..
_support fix(params): validate stream_chunk_size once, before any provider call (#43222) 2026-09-26 23:01:20 +00:00
agent_tests
audio_tests
base_sdk_tests fix(mcp): explain missing public client dependencies 2026-09-19 19:52:13 -07:00
basic_proxy_startup_tests
batches_tests
benchmarks feat(tokenizer): preserve Python defaults with opt-in Rust dispatch (#42174) 2026-09-22 04:41:11 +00:00
code_coverage_tests test(e2e): typed per-test metadata for the e2e suite (#42044) 2026-09-30 21:03:21 -07:00
documentation_tests fix(s3_v2): upload fresh events first, drop terminal failures and hour-old retries by default, opt-in adaptive concurrency (#43022) 2026-09-26 14:58:28 -07:00
e2e test(e2e): typed per-test metadata for the e2e suite (#42044) 2026-09-30 21:03:21 -07:00
guardrails_tests fix(packaging): keep wheel paths under Windows MAX_PATH for Store Python (#43903) 2026-09-30 22:20:36 +00:00
image_gen_tests fix(logging): pass provider response headers to callbacks on every endpoint (#42824) 2026-09-24 13:01:12 -07:00
integration test(proxy): migrate DB and Redis backed proxy tests into tests/integration (#43996) 2026-10-01 09:23:36 -07:00
litellm_utils_tests fix(ci): stop stale CI reds, keep unit tests off the host env, retry CyberArk policy conflicts (#43294) 2026-09-26 09:25:13 -07:00
llm_responses_api_testing test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199) 2026-09-25 17:10:13 -07:00
llm_translation test(bedrock): restore the AWS env after a failed live call in the auth tests (#43921) 2026-09-30 22:36:57 +00:00
load_tests
local_testing test(ci): repair stale tests and move retired OpenAI text-completion fixtures (#43958) 2026-09-30 19:19:59 -07:00
logging_callback_tests test(ci): repair stale tests and move retired OpenAI text-completion fixtures (#43958) 2026-09-30 19:19:59 -07:00
mcp_tests ci: move provider-independent MCP tests into tests/unit and run mcp-integration from litellm-tests (#42904) 2026-09-24 23:07:48 +00:00
multi_instance_e2e_tests
ocr_tests refactor(ocr): remove the Python OCR execution path and require the Rust route (#43081) 2026-09-24 18:18:50 -07:00
openai_endpoints_tests
otel_tests test: fix stale budget-status and bad-database-url assertions 2026-09-21 15:00:54 -07:00
pass_through_tests fix(mcp): preserve legacy behavior on SDK2 and streamline verification 2026-09-18 22:28:31 -07:00
pass_through_unit_tests refactor(anthropic): rename experimental_pass_through to pass_through (#43329) 2026-09-26 13:00:50 -07:00
proxy_admin_ui_tests
proxy_behavior feat(lens): investigate sampled traces and retain batch results (#43942) 2026-09-30 22:30:04 -07:00
proxy_e2e_anthropic_messages_tests fix(test): run the all-beta-headers bedrock cases on Claude Fable 5.1 2026-09-19 23:33:29 +00:00
proxy_migration_tests test: count a zombie grandchild as gone in the migrate deploy timeout test (#42570) 2026-09-22 14:59:26 -07:00
proxy_security_tests refactor(proxy): rename the local development override to dangerously_permit_weak_or_unset_master_key so the name says exactly what it permits 2026-09-19 18:53:14 -07:00
proxy_unit_tests ci: move tests/proxy_unit_tests to tests/unit/proxy and run the proxy-db shards from litellm-tests (#42903) 2026-09-24 22:59:11 +00:00
router_unit_tests fix(ci): stop stale CI reds, keep unit tests off the host env, retry CyberArk policy conflicts (#43294) 2026-09-26 09:25:13 -07:00
rust-python-harness refactor(ocr): remove the Python OCR execution path and require the Rust route (#43081) 2026-09-24 18:18:50 -07:00
search_tests fix(cost-map): retirement dates, chatgpt reasoning flags, bing pricing, bedrock mantle and mythos, azure gpt-5.6 alias, anthropic batch rates, new nebius, openrouter and xai rows (#42951) 2026-09-25 19:12:36 -07:00
spend_tracking_tests
store_model_in_db_tests test(ci): repair MCP Responses and budget fixtures (#43788) 2026-09-29 23:29:52 -07:00
test_litellm test(proxy): migrate DB and Redis backed proxy tests into tests/integration (#43996) 2026-10-01 09:23:36 -07:00
test_litellm_rust feat(lens): investigate sampled traces and retain batch results (#43942) 2026-09-30 22:30:04 -07:00
unified_google_tests test(google_genai): move unified_google_tests to gemini-3.5-flash-lite (#42520) 2026-09-22 13:07:37 -07:00
unit fix(guardrails): harden generic_guardrail_api fire_and_forget dispatch 2026-10-03 14:53:48 +03:00
vector_store_tests
windows_tests fix(packaging): keep wheel paths under Windows MAX_PATH for Store Python (#43903) 2026-09-30 22:20:36 +00:00
__init__.py
_fake_openai_endpoint_server.py
_flush_vcr_cache.py
_live_test_helpers.py
_openai_record_replay_proxy.py
_process_helpers.py test: count a zombie grandchild as gone in the migrate deploy timeout test (#42570) 2026-09-22 14:59:26 -07:00
_vcr_conftest_common.py fix(tests): stop VCR recording and replaying a test's own localhost upstream (#43346) 2026-09-26 15:49:39 -07:00
_vcr_redis_persister.py
_wait_helpers.py
_ws_vcr.py
AGENTS.md ci(tests): wire tests/unit into CircleCI and drain legacy unit shards green 2026-09-20 07:05:42 +00:00
capturing_transport.py test(vcr): guard leaked cassette patches and make injected-transport embedding tests immune (#42542) 2026-09-22 14:20:18 -07:00
eval_swe_bench.py
fake_openai_endpoint.py
gettysburg.wav
large_text.py
openai_batch_completions.jsonl
pyrightconfig.json
README.MD test: finish the non-proxy half of tests/test_litellm (#43281) 2026-09-25 22:43:41 -07:00
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(ci): refresh qualified retired OpenAI fixtures (#43938) 2026-09-30 16:10:18 -07:00
test_gpt5_azure_temperature_support.py
test_health.py
test_keys.py fix(proxy): authorize key model aliases the same way as team aliases (#43049) 2026-09-24 19:51:02 -07:00
test_litellm_proxy_responses_config.py
test_logging.conf
test_models.py
test_new_vector_store_endpoints.py
test_openai_endpoints.py test(ci): refresh qualified retired OpenAI fixtures (#43938) 2026-09-30 16:10:18 -07:00
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: fix stale and state-leaking tests red on scheduled CircleCI (#43266) 2026-09-25 19:10:20 -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
white_100x100.png test: stop CI tests from downloading tokenizer files and images (#43257) 2026-09-25 19:27:48 -07:00

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.