scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-28 01:32:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 42
litellm/tests
History
Jeremy Schoemaker 79577e1288
fix(gemini realtime): close the two review findings on the declared rate 
Both from the automated review on #40617, both real.

Vertex never recorded the declared rate. VertexAIRealtimeConfig handles
session.update in its own transform_realtime_request and returns without
reaching the parent's _handle_session_update, so the recording call added in the
previous commit never ran on that path and a Vertex client's declaration was
silently discarded. Recorded in the Vertex branch too, before the
first-setup/subsequent-setup split, matching where the parent records it.

A later declaration could reprice audio already sent. The estimate accumulated
raw bytes and divided by the rate current at consume time, so a client could
stream at 16kHz and then declare 24kHz before the estimate was read, billing two
thirds of what it actually sent while the backend processed all of it. Audio is
now converted to seconds at append time, at the rate in force when the chunk
arrived, so a mid-stream redeclaration cannot reach backwards. Mixed-rate
sessions bill each chunk at its own rate.

Also bounded the accepted rate to 8000-48000 Hz. The value is client-controlled
and now feeds the spend estimate directly; an unclamped declaration of 100 MHz
would bill a long session as a few milliseconds. Out-of-range declarations are
ignored with a warning and the native default stands.

6 tests added or extended, each verified to fail without these changes.
tests/test_litellm/llms/{gemini,vertex_ai}/realtime: 103 passed.
2026-09-23 15:25:06 -05:00
..
_support fix(params): stop stream_chunk_size reaching provider request bodies (#42664) 2026-09-23 10:27:47 -07:00
agent_tests fix(a2a): keep the upstream status on card discovery failures and inject the card client in tests 2026-09-16 23:55:57 +00:00
audio_tests test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
base_sdk_tests fix(mcp): explain missing public client dependencies 2026-09-19 19:52:13 -07:00
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 feat(tokenizer): preserve Python defaults with opt-in Rust dispatch (#42174) 2026-09-22 04:41:11 +00:00
code_coverage_tests ci: add merge smoke checks workflow with loopback-only harness and 11 curated cases (#42709) 2026-09-23 11:01:08 -07:00
documentation_tests fix(docs-test): restore line-anchored table regex in router settings check 2026-09-18 20:10:20 +00:00
e2e fix(ui): keep per-user MCP credentials updatable and clearable after setup (#42652) 2026-09-23 11:51:05 -07:00
enterprise fix(projects): persist explicit budget cap clears 2026-09-12 13:43:55 -07:00
guardrails_tests Revert "Merge pull request #41220 from BerriAI/litellm_post_call_guardrail_context" 2026-09-19 17:45:15 +00:00
image_gen_tests test: remove fully commented-out test files that collect no tests 2026-09-17 20:05:27 +00:00
integration fix(anthropic): preserve MCP tool results in the non-Anthropic Messages bridge (#42783) 2026-09-23 13:03:25 -07:00
litellm-proxy-extras Merge remote-tracking branch 'origin/main' into litellm_v2_migration_startup 2026-09-18 20:55:05 -07:00
litellm_utils_tests test: point CircleCI-only suites at models still in the cost map (#42617) 2026-09-22 17:28:34 -07:00
llm_responses_api_testing test: fix five tests left stale by #41311, #41337, #39996 and #41310 2026-09-16 17:47:27 -07:00
llm_translation test: point CircleCI-only suites at models still in the cost map (#42617) 2026-09-22 17:28:34 -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: repair seven regressions caught by CircleCI on main (#42640) 2026-09-23 02:26:36 +00:00
logging_callback_tests test: point CircleCI-only suites at models still in the cost map (#42617) 2026-09-22 17:28:34 -07:00
mcp_tests fix(mcp): apply post-call rewrites without stale structured output (#41530) 2026-09-22 13:44:25 -07:00
multi_instance_e2e_tests test: say whether a match= pattern is a regex or a literal (ruff RUF043) 2026-08-21 16:25:33 -07:00
ocr_tests test(ocr): replace per-provider OCR test classes with a declarative provider x auth x input matrix 2026-09-18 21:27:03 +00:00
openai_endpoints_tests test(responses): fix stale Anthropic smoke request 2026-09-11 13:56:27 -07:00
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 feat(proxy): add TinyFish Agent API passthrough with per-step billing (#41099) 2026-09-21 21:21:43 -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 Merge pull request #42026 from BerriAI/litellm_user_jwt_savings 2026-09-21 16:41:16 -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 fix(proxy): keep the in-flight daily spend batch when shutdown cancels the flush (#42593) 2026-09-22 17:58:08 -07:00
router_unit_tests Merge pull request #42283 from BerriAI/litellm_mid_stream_fallback_walks_full_list 2026-09-21 15:14:04 -07:00
rust-python-harness test: drop tests that pin provider-owned cost map values 2026-09-18 03:55:51 +00:00
search_tests test: remove fully commented-out test files that collect no tests 2026-09-17 20:05:27 +00:00
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(anthropic): preserve MCP tool results in the non-Anthropic Messages bridge (#42783) 2026-09-23 13:03:25 -07:00
test_litellm_rust test(rust): model the blocking OCR hook as a guardrail so its raise propagates (#42775) 2026-09-23 12:18:24 -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(gemini realtime): close the two review findings on the declared rate 2026-09-23 15:25:06 -05:00
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 test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
__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 refactor(test): validate cost-map entries into a typed model 2026-09-16 14:32:08 -07:00
_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 test(vcr): guard leaked cassette patches and make injected-transport embedding tests immune (#42542) 2026-09-22 14:20:18 -07:00
_vcr_redis_persister.py
_wait_helpers.py test: replace blind sleeps with deadline waits in callback and caching tests (#37660) 2026-08-20 18:48:43 +00:00
_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_anthropic_compaction_usage.py
test_budget_management.py
test_callbacks_on_proxy.py test: enforce F811 so a duplicate definition cannot silently replace the first 2026-08-21 12:06:19 -07:00
test_debug_warning.py
test_default_encoding_non_root.py
test_end_users.py ci: lint the test tree for undefined names and fix all 30 (#37671) 2026-08-20 13:30:34 -07:00
test_fallbacks.py test: enforce F811 so a duplicate definition cannot silently replace the first 2026-08-21 12:06:19 -07:00
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: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_openai_endpoints.py test: fix five tests left stale by #41311, #41337, #39996 and #41310 2026-09-16 17:47:27 -07:00
test_organizations.py
test_otel_thread_leak.py
test_presidio_latency.py
test_proxy_server_non_root.py
test_ratelimit.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_resource_cleanup.py
test_rust_python_harness.py refactor(rust): remove gateway, config, router, realtime, and trace-parity infrastructure 2026-09-16 16:00:07 +00:00
test_service_logger_otel.py
test_spend_logs.py
test_team.py test: add six ruff rules that catch tests which cannot fail (#37709) 2026-08-20 14:21:26 -07:00
test_team_logging.py test: enforce F811 so a duplicate definition cannot silently replace the first 2026-08-21 12:06:19 -07:00
test_team_members.py test: reject assertions on a caught error inside except (ruff PT017) 2026-08-21 13:35:08 -07:00
test_users.py test: enforce F811 so a duplicate definition cannot silently replace the first 2026-08-21 12:06:19 -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/test_litellm

This folder can only run mock tests.