ai-workspace-services/litellm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
10bda4456a
litellm/tests
History
Mateo Wang a55817cbc6
fix(anthropic): stop injecting unsupported output_config.effort=xhigh for Claude Code on Sonnet/Opus 4.6 (#29304) 
* fix(anthropic): don't inject output_config.effort=xhigh on models without xhigh

The legacy-thinking translator on the /v1/messages route mapped any
thinking.budget_tokens >= 24000 to effort=xhigh and injected it into
output_config without checking model support. Claude Code's default
thinking budget (31999) hit this bucket, so Sonnet 4.6 (and Opus 4.6)
on Bedrock/Vertex started returning

  400 output_config.effort: Input should be 'low', 'medium', 'high' or 'max'

Gate the xhigh choice on _supports_effort_level(model, "xhigh"), the
same capability check the reasoning_effort path already uses. Models
that advertise xhigh (Opus 4.7) keep it; everything else falls to high.

Fixes #29282

* test(anthropic): pin Opus 4.6 in legacy-thinking xhigh-clamp regression test

Opus 4.6 (bare, bedrock/invoke, vertex_ai) has supports_adaptive_thinking
but no supports_xhigh_reasoning_effort, so it hits the same clamping path as
Sonnet 4.6. It was named in the PR scope but lacked a pinned regression
guard; add the three variants to the parametrize list.
2026-05-29 13:55:06 -07:00
..
agent_tests chore(tests): migrate Bedrock CI to AWS account 941277531214 (#28728) 2026-05-25 12:03:17 -07:00
audio_tests fix(tests): stabilize image-edit VCR cassettes to stop live gpt-image-1 spend (#28110) 2026-05-18 09:15:39 -07:00
basic_proxy_startup_tests
batches_tests feat(openai): apply regional-processing cost uplift for EU/US data residency (#28626) 2026-05-25 20:36:14 -07:00
benchmarks
code_coverage_tests bump deps (#29208) (#29226) 2026-05-28 16:48:14 -07:00
documentation_tests
enterprise feat(guardrails): wire apply_guardrail into proxy logging callbacks (#28970) 2026-05-28 09:41:02 -07:00
guardrails_tests chore(tests): migrate Bedrock CI to AWS account 941277531214 (#28728) 2026-05-25 12:03:17 -07:00
image_gen_tests chore(tests): migrate Bedrock CI to AWS account 941277531214 (#28728) 2026-05-25 12:03:17 -07:00
integration CI: copy of #25177 (OCI GenAI: embeddings, streaming/reasoning fixes, model catalog) (#28223) 2026-05-23 12:15:41 -07:00
litellm CI: copy of #25177 (OCI GenAI: embeddings, streaming/reasoning fixes, model catalog) (#28223) 2026-05-23 12:15:41 -07:00
litellm_core_utils
litellm_utils_tests fix(tests/vcr): make Redis cassette cache replay deterministically (zero VCR misses on consecutive runs) (#28826) 2026-05-26 11:30:44 -07:00
litellm-proxy-extras
llm_responses_api_testing fix(responses): use OpenAI SSEDecoder for Responses API streaming (#28566) 2026-05-22 10:03:36 -07:00
llm_translation fix(tests/vcr): mint Google OAuth tokens live to prevent stale-token replay (#29229) 2026-05-28 17:12:02 -07:00
load_tests
local_testing fix(tests/vcr): make Redis cassette cache replay deterministically (zero VCR misses on consecutive runs) (#28826) 2026-05-26 11:30:44 -07:00
logging_callback_tests chore(tests): migrate Bedrock CI to AWS account 941277531214 (#28728) 2026-05-25 12:03:17 -07:00
mcp_tests feat(mcp): Add tool call and tool list support via UI for Oauth mcps (#28454) 2026-05-22 09:04:04 -07:00
multi_instance_e2e_tests
ocr_tests fix(tests/vcr): make Redis cassette cache replay deterministically (zero VCR misses on consecutive runs) (#28826) 2026-05-26 11:30:44 -07:00
old_proxy_tests/tests
openai_endpoints_tests chore(ci): modernize model references in tests and configs (#27856) 2026-05-15 15:44:28 -07:00
otel_tests feat(prometheus): add user_email and user_alias to user budget metrics (#28155) 2026-05-18 16:28:14 -07:00
pass_through_tests chore(deps): bump deps (#28528) 2026-05-22 00:42:21 +00:00
pass_through_unit_tests fix(tests): stabilize image-edit VCR cassettes to stop live gpt-image-1 spend (#28110) 2026-05-18 09:15:39 -07:00
proxy_admin_ui_tests fix(guardrails): persist disable_global_guardrails on keys (#29233) 2026-05-28 21:19:04 -07:00
proxy_behavior test(proxy): phase-4 payload behavior pinning for tier-2/3 key + team management endpoints (#28681) 2026-05-23 12:16:29 -07:00
proxy_e2e_anthropic_messages_tests chore(ci): modernize model references in tests and configs (#27856) 2026-05-15 15:44:28 -07:00
proxy_security_tests
proxy_unit_tests chore(ci): merge dev branch (#28801) 2026-05-25 13:44:49 -07:00
router_unit_tests Litellm oss staging 1 (#28337) 2026-05-20 17:27:03 -07:00
scim_tests
search_tests fix(tests): stabilize image-edit VCR cassettes to stop live gpt-image-1 spend (#28110) 2026-05-18 09:15:39 -07:00
spend_tracking_tests chore(ci): modernize model references in tests and configs (#27856) 2026-05-15 15:44:28 -07:00
store_model_in_db_tests
test_litellm fix(anthropic): stop injecting unsupported output_config.effort=xhigh for Claude Code on Sonnet/Opus 4.6 (#29304) 2026-05-29 13:55:06 -07:00
unified_google_tests fix(tests): stabilize image-edit VCR cassettes to stop live gpt-image-1 spend (#28110) 2026-05-18 09:15:39 -07:00
vector_store_tests chore(tests): migrate Bedrock CI to AWS account 941277531214 (#28728) 2026-05-25 12:03:17 -07:00
windows_tests
__init__.py
_flush_vcr_cache.py
_vcr_conftest_common.py fix(tests/vcr): mint Google OAuth tokens live to prevent stale-token replay (#29229) 2026-05-28 17:12:02 -07:00
_vcr_redis_persister.py fix(tests/vcr): make Redis cassette cache replay deterministically (zero VCR misses on consecutive runs) (#28826) 2026-05-26 11:30:44 -07:00
eval_swe_bench.py
gettysburg.wav
large_text.py
openai_batch_completions.jsonl
README.MD
test_budget_management.py
test_callbacks_on_proxy.py test(callbacks): harden flaky proxy callback-leak detector (#28195) 2026-05-18 16:39:02 -07:00
test_config.py
test_debug_warning.py
test_default_encoding_non_root.py
test_end_users.py chore(ci): modernize model references in tests and configs (#27856) 2026-05-15 15:44:28 -07:00
test_entrypoint.py
test_fallbacks.py
test_gpt5_azure_temperature_support.py
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 chore(ci): modernize model references in tests and configs (#27856) 2026-05-15 15:44:28 -07:00
test_logging.conf
test_models.py
test_new_vector_store_endpoints.py
test_openai_endpoints.py chore(tests): migrate Bedrock CI to AWS account 941277531214 (#28728) 2026-05-25 12:03:17 -07:00
test_organizations.py
test_otel_thread_leak.py
test_passthrough_endpoints.py
test_presidio_latency.py
test_proxy_server_non_root.py
test_ratelimit.py chore(ci): modernize model references in tests and configs (#27856) 2026-05-15 15:44:28 -07:00
test_resource_cleanup.py
test_service_logger_otel.py
test_spend_logs.py Litellm oss staging 04 21 2026 2 (#26569) 2026-05-20 21:25:19 -07:00
test_team_logging.py
test_team_members.py Litellm oss staging 04 21 2026 2 (#26569) 2026-05-20 21:25:19 -07:00
test_team.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.