scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-20 00:11:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 77
litellm/tests
History
Mateo Wang 6a57332f20
fix(vertex): strip output_config.effort for Vertex Claude models that reject it (Haiku 4.5) (#29585) 
* fix(vertex): strip output_config.effort for models that reject it

Haiku 4.5 on Vertex AI does not support output_config.effort and 400s with
"output_config.effort: Extra inputs are not permitted". PR #27074 emptied
VERTEX_UNSUPPORTED_OUTPUT_CONFIG_KEYS so effort would forward for Opus/Sonnet
4.6+, but that made the strip unconditional across every Vertex Anthropic
model, including ones that don't support it. Claude Code injects effort into
its default Messages payload, so `claude --model claude-haiku-4.5` started
failing.

Make the sanitizer model-aware: drop output_config.effort for models that
don't advertise output_config support (or any reasoning effort level) while
forwarding it for those that do. The fix covers both the chat-completion and
Messages pass-through transformation paths since they share the helper.

* chore(vertex): log at debug when dropping unsupported output_config.effort

Operators pointing an unregistered Vertex Claude alias that does support
effort would otherwise see it stripped with no signal. Debug level keeps it
out of normal logs since Claude Code sends effort on every request.

(cherry picked from commit cc55662e5f)
2026-06-03 22:53:31 +00:00
..
agent_tests style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
audio_tests [Test] Tests: Stop parametrizing API keys into pytest test IDs (#27249) 2026-05-05 17:21:18 -07:00
basic_proxy_startup_tests build: migrate packaging, CI, and Docker from Poetry to uv (#25007) 2026-04-09 11:46:23 -07:00
batches_tests fix(ci): unbreak realtime + bedrock batch tests (#27690) 2026-05-11 18:08:14 -07:00
benchmarks
code_coverage_tests feat(audio_transcription): add NVIDIA Riva STT provider (#27185) 2026-05-05 17:17:51 -07:00
documentation_tests style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
enterprise fix(tests): use canonical litellm_enterprise import path (#27699) 2026-05-12 12:32:57 -07:00
guardrails_tests test: add 24hr Redis-backed VCR cache to additional test suites (#27159) 2026-05-05 15:13:31 -07:00
image_gen_tests Ishaan - May 13th Staging LiteLLM (#27877) 2026-05-13 16:37:15 -07:00
litellm Add new chat model metadata (#27313) 2026-05-06 15:15:21 -07:00
litellm-proxy-extras style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
litellm_core_utils Merge branch 'litellm_internal_staging' into litellm_staging_03_22_2026 2026-04-20 19:56:00 +05:30
litellm_utils_tests fix(reset_budget): write only {spend, budget_reset_at} and stop pre-zeroing counter (#29358) 2026-06-01 16:23:01 -07:00
llm_responses_api_testing test: add 24hr Redis-backed VCR cache to additional test suites (#27159) 2026-05-05 15:13:31 -07:00
llm_translation fix(ci): unbreak realtime + bedrock batch tests (#27690) 2026-05-11 18:08:14 -07:00
load_tests style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
local_testing fix(tests): drop dall-e-only test classes; route live image tests via gpt-image-1 2026-05-12 16:55:19 -07:00
logging_callback_tests Merge pull request #27222 from BerriAI/litellm_s3AuditParams 2026-05-07 12:49:03 -07:00
mcp_tests feat: litellm shin agent oss staging 05 10 2026 (#27631) 2026-05-11 20:31:43 -07:00
multi_instance_e2e_tests
ocr_tests [Fix] Tests: Reduce VCR cassette bloat and fix multipart caching 2026-05-07 11:54:19 -07:00
old_proxy_tests/tests fix: cleanup tests 2026-03-30 16:24:35 -07:00
openai_endpoints_tests style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
otel_tests fix(tests): swap dall-e to gpt-image-1 after openai deprecation 2026-05-12 16:55:18 -07:00
pass_through_tests chore(deps): refresh dependency locks 2026-05-04 11:36:18 -07:00
pass_through_unit_tests [internal copy of #29089] fix: duplicate claude code traces (#29311) 2026-06-01 16:22:17 -07:00
proxy_admin_ui_tests chore(deps): refresh dependency locks 2026-05-04 11:36:18 -07:00
proxy_e2e_anthropic_messages_tests style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
proxy_security_tests style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
proxy_unit_tests [internal copy of #29089] fix: duplicate claude code traces (#29311) 2026-06-01 16:22:17 -07:00
router_unit_tests fix(prometheus): emit litellm_remaining_tokens_metric for Bedrock and Vertex (#27705) 2026-05-13 17:40:59 -07:00
scim_tests
search_tests test: add 24hr Redis-backed VCR cache to additional test suites (#27159) 2026-05-05 15:13:31 -07:00
spend_tracking_tests chore(proxy): guard sensitive public endpoints 2026-04-30 11:52:47 -07:00
store_model_in_db_tests style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_litellm fix(vertex): strip output_config.effort for Vertex Claude models that reject it (Haiku 4.5) (#29585) 2026-06-03 22:53:31 +00:00
unified_google_tests test: add 24hr Redis-backed VCR cache to additional test suites (#27159) 2026-05-05 15:13:31 -07:00
vector_store_tests fix: drop milvus dbName and partitionNames from MILVUS_OPTIONAL_PARAMS 2026-04-30 11:51:32 -07:00
windows_tests style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
__init__.py
_flush_vcr_cache.py tests(vcr): isolate cassette redis to CASSETTE_REDIS_URL 2026-05-01 12:32:59 -07:00
_vcr_conftest_common.py [Fix] Tests: Reduce VCR cassette bloat and fix multipart caching 2026-05-07 11:54:19 -07:00
_vcr_redis_persister.py test: add 24hr Redis-backed VCR cache to additional test suites (#27159) 2026-05-05 15:13:31 -07:00
eval_swe_bench.py Prompt Compression - add it to the proxy (#25729) 2026-04-20 15:08:00 -07:00
gettysburg.wav
large_text.py
openai_batch_completions.jsonl
README.MD
test_budget_management.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_callbacks_on_proxy.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_config.py
test_debug_warning.py
test_default_encoding_non_root.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_end_users.py
test_entrypoint.py
test_fallbacks.py
test_gpt5_azure_temperature_support.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_health.py fix(tests): swap dall-e to gpt-image-1 after openai deprecation 2026-05-12 16:55:18 -07:00
test_keys.py fix(tests): swap dall-e to gpt-image-1 after openai deprecation 2026-05-12 16:55:18 -07:00
test_litellm_proxy_responses_config.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_logging.conf
test_models.py test: replace test_add_and_delete_models integration test with mock 2026-03-30 21:30:57 -07:00
test_new_vector_store_endpoints.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_openai_endpoints.py fix(tests): swap dall-e to gpt-image-1 after openai deprecation 2026-05-12 16:55:18 -07:00
test_organizations.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_otel_thread_leak.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_passthrough_endpoints.py
test_presidio_latency.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_proxy_server_non_root.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_ratelimit.py [Fix] test_ratelimit: skip over-limit cases that race with background RPM tracking 2026-04-11 13:08:59 -07:00
test_resource_cleanup.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_service_logger_otel.py
test_spend_logs.py
test_team.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_team_logging.py test: cleanup dead tests 2026-03-28 20:49:02 -07:00
test_team_members.py
test_users.py Fix: tag budget reset must drop stale management-cache entry (#27568) 2026-05-10 00:18:55 +00:00

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.