litellm/tests
Yujong Lee 7c716d5165 refactor(model-catalog): serve the fetched map row for row
The fetched map now replaces the bundled one at row level instead of patching it field by field, so a field or
model the map drops is gone on every wheel, and bundled only shows through for rejected rows. The cost map guard
drops the null rule, refuses null rows, and lets a PR delete a model only after its deprecation_date has passed

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-28 18:24:45 -07:00
..
_support
audio_tests
base_sdk_tests build(model-catalog): ship the cost map inside the native extension 2026-10-28 18:24:44 -07:00
benchmarks fix(streaming): keep merged think tags balanced and split SSE lines only on CR/LF (#48755) 2026-10-28 17:00:29 -07:00
code_coverage_tests refactor(router): fence the router surface and document the router-core boundary (#48839) 2026-10-29 00:01:52 +00:00
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
integration refactor(model-cost): load litellm.model_cost through the Rust catalog 2026-10-28 18:24:45 -07:00
rust-python-harness
test_litellm_rust refactor(rust-bridge): require the native extension (#48852) 2026-10-28 13:16:56 -07:00
typing
unit refactor(model-catalog): serve the fetched map row for row 2026-10-28 18:24:45 -07:00
windows_tests refactor(rust-bridge): require the native extension (#48852) 2026-10-28 13:16:56 -07:00
__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

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.