scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103
litellm/tests/test_litellm
History
Tai An 8a65e68c65 fix(mcp): coerce YAML 1.1 string costs to floats; defend UI .toFixed (#27097) 
PyYAML (YAML 1.1) parses scientific notation without a decimal point
(e.g. `default_cost_per_query: 7e-05`) as a string, not a float. The
string round-trips through MCPInfo into the JSONB column verbatim, and
the UI later crashes on `e.default_cost_per_query.toFixed is not a
function` when opening the MCP server settings page.

Fix at the boundary plus a UI safety net (defense in depth):

- mcp_server_manager.py: introduce `_coerce_optional_float` and
  `_coerce_mcp_cost_info_in_place` and call them in
  `load_servers_from_config` so `default_cost_per_query` and each
  `tool_name_to_cost_per_query` value are coerced to float at ingest.
  Genuinely non-numeric values are dropped with a warning that points at
  the server name and explains the YAML-1.1 caveat (write `7.0e-5`
  instead of `7e-5`).
- ui/.../types.tsx: add `toFiniteNumber(unknown): number | null` so any
  pre-existing bad data already in users' DBs (or anything that bypasses
  the loader) is coerced before `.toFixed`.
- ui/.../mcp_server_cost_display.tsx and mcp_server_cost_config.tsx:
  pass values through `toFiniteNumber` before formatting and before
  feeding `InputNumber.value`, so the settings page renders even if the
  server returned a string.

Tests in `test_mcp_server_manager.py` cover the YAML repro, ints/floats
passthrough, scientific-notation strings, garbage rejection, and the
no-op cases (missing or non-dict cost_info).
2026-05-03 18:19:49 -07:00
..
a2a_protocol style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
anthropic_interface/exceptions style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
caching Refresh Redis TTL on counter writes and skip stale in-memory on Redis miss 2026-04-30 17:50:58 -07:00
completion_extras style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
containers style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
enterprise feat: add configurable multi-threshold budget alerts for virtual keys 2026-04-17 17:12:35 -07:00
expected_fine_tuning_api refactor: refactor testing 2026-03-28 18:39:32 -07:00
expected_responses_api_request [Feat] Adds support for server-side compaction on the OpenAI Responses API context_management (#21058) 2026-02-12 10:00:30 -08:00
experimental_mcp_client style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
google_genai style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
images fix(image_edit): read vertex_project/location from litellm_params in Imagen get_complete_url 2026-04-21 15:03:40 +05:30
integrations fix(tests): replace deprecated Bedrock Claude 3.7 Sonnet model ID 2026-04-28 14:24:19 -07:00
interactions style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
litellm_core_utils fix(logging): redact standard logging choice metadata 2026-04-30 00:35:29 -07:00
llms Merge pull request #26222 from BerriAI/litellm_anthropic-json-mode-nonstreaming-mixed-tools 2026-05-01 08:24:38 +05:30
ocr style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
passthrough refactor: trim explanatory comments from streaming-flush fix 2026-04-30 02:39:28 +00:00
proxy fix(mcp): coerce YAML 1.1 string costs to floats; defend UI .toFixed (#27097) 2026-05-03 18:19:49 -07:00
responses Revert "Merge pull request #24417 from Chesars/refactor/shared-format-mapping" 2026-04-25 15:03:24 -03:00
router_strategy refactor(adaptive_router): move update_queue out of litellm.proxy 2026-04-21 18:02:44 -07:00
router_utils style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
secret_managers style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_router fix: use atomic increment-first pattern for model RPM rate limiting 2026-02-24 09:55:07 -03:00
types Merge pull request #25256 from BerriAI/litellm_ishaan_april6 2026-04-17 16:26:45 -07:00
vector_stores style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
__init__.py
conftest.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
log.txt
readme.md
test_a2a_registry_lookup.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_acompletion_session_reuse_e2e.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_add_deployment_no_master_key.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_aembedding_session_reuse_e2e.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_anthropic_beta_headers_filtering.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_anthropic_skills_transformation.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_azure_video_router.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_bedrock_anthropic_1hr_cache_pricing.py fix(bedrock): add 1-hour cache write tier for Claude 4.5/4.6/4.7 (Global, US) 2026-04-29 19:21:57 +00:00
test_chat_ui_responses_session.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_claude_haiku_4_5_config.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_claude_opus_4_6_config.py Revert "Merge pull request #24164 from dongyu-turo/feat/update-bedrock-claude-price-above-200k" 2026-04-25 15:04:05 -03:00
test_completion_timeout_resolution.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_compression.py Prompt Compression - add it to the proxy (#25729) 2026-04-20 15:08:00 -07:00
test_constants.py Fix test 2026-03-27 21:21:43 +05:30
test_container_router.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_cost_calculation_log_level.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_cost_calculator.py fix(utils): allowed_openai_params must not forward unset params as None (#25777) 2026-04-16 19:04:26 +05:30
test_count_tokens_public_api.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_dashscope_image_generation.py fix(dashscope): fail fast on image generation API errors 2026-04-23 18:41:01 +05:30
test_deepseek_model_metadata.py fix(model-info): sync DeepSeek model metadata and add bare-name fallback (#20885) 2026-02-11 12:48:10 +05:30
test_dockerfile_non_root.py fix(docker.non_root): use numeric UID 65534 for K8s runAsNonRoot (#26268) 2026-04-22 18:00:04 -07:00
test_eager_tiktoken_load.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_exception_exports.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_exception_header_preservation.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_exception_mapping_request_attribute.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_filter_out_litellm_params.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_get_blog_posts.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_gpt_image_cost_calculator.py Add gpt-image-2 support (#26644) (#26705) 2026-04-28 20:10:42 -07:00
test_groq_streaming_encoding.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_lazy_imports.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
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 style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_lowest_latency_zero_tokens.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_main.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_model_cost_aliases.py [Feat] - Ishaan main merge branch (#23596) 2026-03-14 09:40:00 -07:00
test_model_param_helper.py style: black format test_model_param_helper.py 2026-04-15 18:18:52 -07:00
test_model_response_normalization.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_nested_drop_params.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_project_alias_tracking.py feat(proxy): add project_alias tracking through callback metadata pipeline 2026-03-23 10:44:17 -07:00
test_project_tags_pydantic.py fix: req changes 2026-02-27 13:33:34 +05:30
test_redact_string_in_error_paths.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_redis.py fix(redis): cache GCP IAM token to prevent async event loop blocking (#26441) 2026-04-25 23:13:39 -07:00
test_register_model_custom_pricing.py test: fix misleading precedence test per review feedback 2026-03-02 08:31:33 +00:00
test_responses_api_bridge_non_stream.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_responses_id_security.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_router.py fix(router): propagate custom cost_per_token from db model_info in fallback path (#25888) 2026-04-27 08:58:41 +05:30
test_router_google_genai.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_router_model_cost_isolation.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_router_order_fallback.py fix(router): enable order fallback for wildcard model groups 2026-04-15 17:48:25 +05:30
test_router_per_deployment_num_retries.py
test_router_redis_init.py
test_router_retry_non_retryable_errors.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_router_silent_experiment.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_secret_redaction.py Litellm ishaan march30 (#24887) (#25151) 2026-04-04 14:44:07 -07:00
test_service_logger.py fix(proxy): fix master key rotation Prisma validation errors (#21330) 2026-02-16 15:13:05 -08:00
test_setup_wizard.py test: test 2026-03-28 19:17:38 -07:00
test_shared_session_integration.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_ssl_verify_unit.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
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 style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_system_message_format_bug.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_utils.py Add gpt-image-2 support (#26644) (#26705) 2026-04-28 20:10:42 -07:00
test_uuid_helper.py
test_video_generation.py feat(gemini): Veo Lite pricing, size→resolution, usage video_resolution for cost tiers 2026-04-08 19:50:50 +05:30
test_xai_responses_auto_routing.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00

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:

  1. Increase test coverage of litellm/
  2. 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