mirror of https://github.com/tiennm99/litellm.git synced 2026-07-20 06:19:51 +00:00

Files

T

Ephrim StanleyandClaude 477c54184b perf: avoid unconditional router lookups in success handler

Replace bare _get_deployment_default_tpm/rpm_limit calls in the
async_log_success_event condition with get_key_model_tpm/rpm_limit
(model_name=model_group). The higher-level getters short-circuit on
key/team metadata hits before ever reaching the router, so requests
that don't use deployment defaults incur no extra router lookup. Remove
the now-unused bare helper imports.

Also fix invalid `int = None` type hints in test helper signatures
to `Optional[int] = None`.

Co-Authored-By: Claude (claude-sonnet-4-6) <noreply@anthropic.com>

2026-03-19 02:07:50 -04:00

a2a_protocol

…

anthropic_interface/exceptions

…

caching

Reapply "feat: add model_cost aliases expansion support"

2026-03-12 13:36:57 -03:00

completion_extras

fix(ci): skip tests requiring openai>=2.x and MCP M2M oauth2_flow

2026-03-13 01:09:56 +00:00

containers

…

enterprise

Revert "[Fix] Populate _hidden_params.model_id in batch terminal-state shortcut path"

2026-03-13 12:21:39 -07:00

expected_responses_api_request

…

experimental_mcp_client

…

google_genai

Revert "QA: improve gpt-5.4 code/bugs"

2026-03-13 10:15:47 -07:00

images

Root cause fix - migrate all logging update to use 1 function - for centralized kwarg updates (#23659 )

2026-03-15 23:21:01 -07:00

integrations

Code review

2026-03-18 16:25:42 -05:00

interactions

[Staging] - Ishaan March 17th (#23903 )

2026-03-18 15:09:01 -07:00

litellm_core_utils

fix: fix responses cost calc

2026-03-18 19:52:59 -07:00

llms

[Staging] - Ishaan March 17th (#23903 )

2026-03-18 15:09:01 -07:00

ocr

…

passthrough

…

proxy

perf: avoid unconditional router lookups in success handler

2026-03-19 02:07:50 -04:00

responses

Fix test isolation: clear litellm.callbacks and model_fallbacks between tests

2026-03-15 16:43:15 -07:00

router_strategy

[Feat] - Ishaan main merge branch (#23596 )

2026-03-14 09:40:00 -07:00

router_utils

Fix flaky encrypted_content_affinity tests: mock at handler level

2026-03-15 15:39:25 -07:00

secret_managers

…

test_router

…

types

merge: resolve conflicts between main and litellm_oss_staging_03_11_2026

2026-03-12 09:38:31 -03:00

vector_stores

…

__init__.py

…

conftest.py

Fix test isolation: clear litellm.callbacks and model_fallbacks between tests

2026-03-15 16:43:15 -07:00

log.txt

…

readme.md

…

test_a2a_registry_lookup.py

…

test_acompletion_session_reuse_e2e.py

…

test_add_deployment_no_master_key.py

…

test_aembedding_session_reuse_e2e.py

…

test_anthropic_beta_headers_filtering.py

Refactor: Filtering beta header after transformation

2026-03-16 10:47:15 +05:30

test_anthropic_skills_transformation.py

Clean up skills test: remove duplicate imports, parameterize mock HTTP method (#23360 )

2026-03-11 22:10:27 +05:30

test_azure_video_router.py

…

test_chat_ui_responses_session.py

[Docs] Fix "Page Not Found" link for Anthropic endpoint (#23349 )

2026-03-11 20:17:41 +05:30

test_claude_haiku_4_5_config.py

…

test_claude_opus_4_6_config.py

…

test_constants.py

…

test_container_router.py

…

test_cost_calculation_log_level.py

…

test_cost_calculator.py

[Infra] Merging RC Branch with Main (#23786 )

2026-03-16 15:32:20 -07:00

test_count_tokens_public_api.py

merge: resolve conflicts between main and litellm_oss_staging_03_11_2026

2026-03-12 09:38:31 -03:00

test_deepseek_model_metadata.py

…

test_eager_tiktoken_load.py

Fix test isolation: run eager tiktoken tests in subprocesses

2026-03-15 17:32:31 -07:00

test_exception_exports.py

…

test_exception_header_preservation.py

…

test_exception_mapping_request_attribute.py

…

test_filter_out_litellm_params.py

…

test_get_blog_posts.py

feat: fetch blog posts from docs RSS feed instead of static JSON on GitHub

2026-03-16 15:55:16 -07:00

test_gpt_image_cost_calculator.py

…

test_groq_streaming_encoding.py

…

test_lazy_imports.py

…

test_litellm_params_reserved_keys.py

fix(snowflake): transform tool_choice string to object format (#23268 )

2026-03-11 01:41:24 +05:30

test_logging.py

…

test_lowest_latency_zero_tokens.py

…

test_main.py

Reserve reasoning for responses via chat completion

2026-03-13 23:59:57 +05:30

test_model_cost_aliases.py

[Feat] - Ishaan main merge branch (#23596 )

2026-03-14 09:40:00 -07:00

test_model_param_helper.py

…

test_model_response_normalization.py

…

test_nested_drop_params.py

…

test_project_tags_pydantic.py

…

test_redis.py

…

test_register_model_custom_pricing.py

…

test_responses_api_bridge_non_stream.py

…

test_responses_id_security.py

…

test_router_google_genai.py

…

test_router_model_cost_isolation.py

…

test_router_per_deployment_num_retries.py

…

test_router_redis_init.py

…

test_router_retry_non_retryable_errors.py

Reapply "feat: add model_cost aliases expansion support"

2026-03-12 13:36:57 -03:00

test_router_silent_experiment.py

Update tests/test_litellm/test_router_silent_experiment.py

2026-03-14 16:47:56 +05:30

test_router.py

Merge pull request #22390 from Harshit28j/litellm_langfuse-session-trace-fix

2026-03-14 12:49:04 -07:00

test_secret_redaction.py

fix: redact secrets from proxy log output

2026-03-14 15:52:31 -07:00

test_service_logger.py

…

test_setup_wizard.py

[Staging] - Ishaan March 17th (#23903 )

2026-03-18 15:09:01 -07:00

test_shared_session_integration.py

…

test_ssl_verify_unit.py

…

test_stream_chunk_builder_annotations.py

fix: merge annotations from all streaming chunks in stream_chunk_builder

2026-03-15 14:20:45 +05:30

test_streaming_connection_cleanup.py

…

test_system_message_format_bug.py

…

test_utils.py

Merge branch 'main' into litellm_oss_staging_03_11_2026

2026-03-12 10:43:08 -03:00

test_uuid_helper.py

…

test_video_generation.py

Add new videos transformation

2026-03-16 17:56:21 +05:30

test_xai_responses_auto_routing.py

…

readme.md

Testing for `litellm/`

This directory 1:1 maps the the litellm/ directory, and can only contain mocked tests.

The point of this is to:

Increase test coverage of litellm/
Make it easy for contributors to add tests for the litellm/ package and easily run tests without needing LLM API keys.

File name conventions

litellm/proxy/test_caching_routes.py maps to litellm/proxy/caching_routes.py
test_<filename>.py maps to litellm/<filename>.py

readme.md

Testing for litellm/

File name conventions

Testing for `litellm/`