litellm

mirror of https://github.com/BerriAI/litellm.git synced 2026-09-17 23:51:30 +00:00

History

mateo-berri 3c15f64fd4 fix(bedrock): make prompt caching work on the Nova InvokeModel route Nova InvokeModel rejects the standalone cachePoint blocks the shared Converse transform emits, so each one is folded into the block it caches and tool_config injection points are dropped before the transform runs, since this route has no tool caching to credit. Usage reads Bedrock's Count-suffixed cache keys and adds cached tokens into prompt_tokens, streaming routes every wrapped InvokeModel event through the Converse chunk parser and tolerates the missing totalTokens, and the Nova 1 cost-map entries gain cache_read_input_token_cost at a quarter of the input rate		2026-09-15 18:01:21 -07:00
..
agent_tests
audio_tests
base_sdk_tests
basic_proxy_startup_tests
batches_tests	feat(batches): enrich batch cost rows with breakdown, identity, session, and org spend	2026-09-03 17:23:53 -04:00
benchmarks
code_coverage_tests	Merge branch 'main' into litellm_strict_provider_identity	2026-09-14 20:43:55 -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	Merge pull request #39857 from BerriAI/litellm_e2e_reliability_module_cells	2026-09-15 11:38:51 -07:00
enterprise	fix(projects): persist explicit budget cap clears	2026-09-12 13:43:55 -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	test: preserve immutable integration observations and cleanup outcomes	2026-09-14 10:58:36 -07:00
litellm-proxy-extras	fix(jwt): cascade-delete JWT key mappings when their virtual key is deleted	2026-09-09 15:39:21 -07:00
litellm_utils_tests	fix(reset_budget_job): reset end users by budget link, not by user id	2026-09-10 16:57:53 -07:00
llm_responses_api_testing	fix(responses): keep context-window events out of mid-stream fallback and fix stale exception assertions	2026-09-13 03:18:59 -07:00
llm_translation	test: fix stale completion response fixtures	2026-09-10 17:18:56 -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(router): stop registering a caller-supplied credential as a router deployment	2026-09-15 14:18:03 -07:00
logging_callback_tests	fix(proxy): keep client User-Agent on auth failure spend logs	2026-09-15 21:02:06 +00:00
mcp_tests	fix(mcp): reject initialize with 403 when the key grants no MCP servers (#40616 )	2026-09-10 14:25:30 -07:00
multi_instance_e2e_tests
ocr_tests	test(ocr): exempt native parity requests from cassette replay	2026-09-11 22:50:39 -07:00
openai_endpoints_tests	test(responses): fix stale Anthropic smoke request	2026-09-11 13:56:27 -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	Merge pull request #40262 from BerriAI/litellm_lit_7190_inline_token_counts	2026-09-15 13:38:00 -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	fix(proxy): match an id-only bulk member delete against a legacy email-only roster entry	2026-09-14 23:51:15 +00:00
proxy_e2e_anthropic_messages_tests
proxy_migration_tests	fix(proxy): run migrations through python -m prisma when the prisma console script is not on PATH	2026-09-09 18:17:12 -07:00
proxy_security_tests
proxy_unit_tests	perf(proxy): serialize /model/info listing once with orjson	2026-09-14 19:47:51 +00:00
router_unit_tests	fix(router): stop registering a caller-supplied credential as a router deployment	2026-09-15 14:18:03 -07:00
rust-python-harness	fix(harness): skip unavailable Rust traces	2026-09-14 14:01:28 -07:00
search_tests
spend_tracking_tests
store_model_in_db_tests	test(proxy): expect the sanitized unknown-model message in the spend-log error test	2026-09-11 19:18:10 -07:00
test_gateway	feat(proxy): offload spend tracking to a pod-local collector sidecar (#40545 )	2026-09-10 17:14:13 -07:00
test_litellm	fix(bedrock): make prompt caching work on the Nova InvokeModel route	2026-09-15 18:01:21 -07:00
test_litellm_rust	fix(router): ignore planted request_retry_count seeds and cover the rust OCR cap path	2026-09-15 00:04:02 -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_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.