scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-06 08:16:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 79
litellm/tests
History
tin-berri 3300fc3a96
fix(moonshot, together_ai): send the reasoning effort Kimi K3 accepts (#38611) 
* fix(moonshot, together_ai): send the reasoning effort Kimi K3 accepts

Moonshot documents reasoning_effort as a top-level chat completions field for its reasoning
models, and defaults it to max, but MoonshotChatConfig builds its supported params by
subtracting from the OpenAI base list, which never carried that param. An explicit level
raised UnsupportedParamsError before the request left the proxy, so low and high were
unreachable and every call ran at the provider default

Together accepts low, high and max on Kimi K3. The per-model clamp added for the gpt-oss
family folds max down to high for every model except deepseek-ai/DeepSeek-V4-Pro, so a caller
asking for max silently got roughly half the reasoning budget they paid for

Moonshot now offers reasoning_effort whenever the registry says the model reasons. Together
sends a level the map entry declares unchanged, and keeps its existing table for every level
an entry does not name, so the only value that moves is Kimi K3 at max

* fix(moonshot): unwrap the bridges' effort object to the level string
2026-08-27 20:46:46 -07:00
..
agent_tests test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
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 test(cli): cover the keyless token record and keep keyring to the cli extra 2026-08-20 03:45:00 -07:00
basic_proxy_startup_tests
batches_tests test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
benchmarks
code_coverage_tests Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_deflake_20260821 2026-08-27 09:17:37 +00:00
documentation_tests test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
e2e test(e2e): drop the fixture helper docstring 2026-08-27 14:50:17 -07:00
enterprise test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
guardrails_tests test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
image_gen_tests test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
integration test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
litellm-proxy-extras fix: keep schema reconciliation from fighting a partitioned LiteLLM_SpendLogs (#38452) 2026-08-27 12:52:52 -07:00
litellm_utils_tests test: gate the test tree on B003 so a test cannot swap os.environ for a plain dict 2026-08-25 15:43:26 -07:00
llm_responses_api_testing test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
llm_translation test(together_ai): assert fail-open supported params for models missing from the registry 2026-08-27 01:27:32 -07:00
load_tests Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_ruff_dead_test_code 2026-08-24 09:46:56 -07:00
local_testing Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_ruff_dead_test_code 2026-08-24 09:46:56 -07:00
logging_callback_tests fix(router): persist attempted_fallbacks and original_model_group into spend logs metadata (#38107) 2026-08-25 16:22:01 -07:00
mcp_tests Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_deflake_20260821 2026-08-27 09:17:37 +00:00
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: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
openai_endpoints_tests test: enforce F811 so a duplicate definition cannot silently replace the first 2026-08-21 12:06:19 -07:00
otel_tests test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
pass_through_tests
pass_through_unit_tests test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
proxy_admin_ui_tests fix(team): serialize member_add, member_delete, and delete under the team's advisory lock (#37969) 2026-08-25 21:55:11 +00:00
proxy_behavior fix(proxy): reset a stuck team member's budget (#37971) 2026-08-25 09:50:09 -07:00
proxy_e2e_anthropic_messages_tests ci: lint the test tree for undefined names and fix all 30 (#37671) 2026-08-20 13:30:34 -07:00
proxy_migration_tests fix(ui): boot the UI image as an arbitrary uid by anchoring nginx writes under /tmp (#37982) 2026-08-24 11:57:36 -07:00
proxy_security_tests
proxy_unit_tests refactor: dedupe server_tool_use web search reads and type fresh test locals 2026-08-27 08:01:52 +00:00
router_unit_tests test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
search_tests fix(search): harden bing_grounding auth, result cap, status, and cost 2026-08-24 12:26:07 -07:00
spend_tracking_tests
store_model_in_db_tests test: enforce F811 so a duplicate definition cannot silently replace the first 2026-08-21 12:06:19 -07:00
test_litellm fix(moonshot, together_ai): send the reasoning effort Kimi K3 accepts (#38611) 2026-08-27 20:46:46 -07:00
unified_google_tests test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
vector_store_tests test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -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(ci): serve /moderations from the canned OpenAI mock (#37739) 2026-08-20 16:58:38 -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 test: replace blind sleeps with deadline waits in callback and caching tests (#37660) 2026-08-20 18:48:43 +00:00
_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: 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: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_litellm_proxy_responses_config.py
test_logging.conf
test_models.py
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: point the live web search, groq and vertex image suites at models that still exist (#37733) 2026-08-20 17:03:35 -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_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.