litellm/tests at 3cac6b0a402c16a2b341e3cd06802d5d886f73aa - litellm - Gitea: Git with a cup of tea

tiennm99/litellm

mirror of https://github.com/tiennm99/litellm.git synced 2026-06-28 19:09:32 +00:00

Files

T

History

Cesar Garcia c892c2c83d fix(anthropic): use dynamic max_tokens based on model (#17900 )

* fix(anthropic): use dynamic max_tokens based on model

When users don't specify max_tokens in requests to Anthropic models,
LiteLLM now uses the correct max_output_tokens value from the model
pricing JSON instead of a hardcoded 4096.

This fixes truncated responses for Claude 3.5+ models which support
higher output limits (8192 for Claude 3.5, 128k for Claude 3.7, etc.)

Fixes #8835

* fix(anthropic): restore env var support for backwards compatibility

Keep DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS as fallback when model is not
found in JSON, allowing users to configure via environment variable.

2025-12-14 08:31:27 +05:30

..

[Feat] Agent Gateway - allow adding langgraph, bedrock agent core agents (#17802 )

2025-12-10 19:13:50 -08:00

test_runwayml_tts_async

2025-12-13 16:10:48 -08:00

basic_proxy_startup_tests

Fix: remove merge markdown (#17586 )

2025-12-06 05:38:16 -08:00

Fix: apply_guardrail method and improve test isolation (#17555 )

2025-12-05 12:59:35 -08:00

code_coverage_tests

[Fix] CI/CD - Fix Bedrock tool calling test failures with non-serializable objects and internal parameters (#17930 )

2025-12-13 12:38:07 -08:00

documentation_tests

…

fix(prometheus): add 'exception_status' to prometheus logger (#17847 )

2025-12-12 03:57:46 -08:00

guardrails_tests

…

image_gen_tests

TestRunwaymlImageGeneration

2025-12-13 17:21:20 -08:00

feat(deepseek): add native support for thinking and reasoning_effort params (#17712 )

2025-12-11 15:28:43 -08:00

litellm_utils_tests

Fix flanky tests (#17665 )

2025-12-08 12:21:26 -08:00

litellm-proxy-extras

…

llm_responses_api_testing

…

llm_translation

TestNvidiaNim

2025-12-13 16:38:11 -08:00

…

fix: filter internal params in fallback code and fix test issues (#17941 )

2025-12-13 15:05:26 -08:00

logging_callback_tests

fix: add agent_id field to GCS PubSub spend_logs_payload.json test expectation (#17938 )

2025-12-13 13:35:20 -08:00

feat: add support for using MCPs on /chat/completions

2025-12-10 10:55:33 +09:00

multi_instance_e2e_tests

…

…

old_proxy_tests/tests

…

openai_endpoints_tests

…

…

pass_through_tests

…

pass_through_unit_tests

…

proxy_admin_ui_tests

Fixing e2e

2025-12-05 12:40:58 -08:00

proxy_security_tests

…

proxy_unit_tests

fix: Add headers to Request scope in JWT tests to fix KeyError (#17927 )

2025-12-13 10:36:13 -08:00

router_unit_tests

fix(router): add minimum request threshold for error rate cooldown (#17464 )

2025-12-12 04:36:10 -08:00

…

…

spend_tracking_tests

…

store_model_in_db_tests

…

fix(anthropic): use dynamic max_tokens based on model (#17900 )

2025-12-14 08:31:27 +05:30

unified_google_tests

…

vector_store_tests

…

…

__init__.py

…

gettysburg.wav

…

large_text.py

…

openai_batch_completions.jsonl

…

README.MD

…

test_budget_management.py

…

test_callbacks_on_proxy.py

…

test_config.py

…

test_debug_warning.py

…

test_end_users.py

…

test_entrypoint.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_openai_endpoints.py

…

test_organizations.py

…

test_passthrough_endpoints.py

…

test_ratelimit.py

…

test_resource_cleanup.py

…

test_spend_logs.py

…

test_team_logging.py

…

test_team_members.py

…

test_team.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.