scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-15 23:31:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 165
litellm/tests/local_testing
History
Clement 95c0f9db7d
fix(router): rank streaming latency routing by raw TTFT, not TTFT per token (#40202) 
* fix(router): rank streaming latency routing by raw TTFT, not TTFT per token

Latency-based routing divided time-to-first-token by completion_tokens
before storing it, so a deployment that streamed a long answer looked
faster to first token than one that answered briefly. TTFT is now stored
as plain seconds (first token time minus request start) in both the sync
and async success handlers, which is what the routing decision compares.

Non-streaming latency normalization per output token is unchanged.

Claude-Session: https://claude.ai/code/session_01Ttd5Q9ZhRPB4ch5guos3rj

* fix(router): store streaming TTFT under a seconds-only cache key

Workers on the previous release keep writing seconds-per-token samples
under "time_to_first_token" in the shared router cache during a rolling
deploy, so mixing the new raw-seconds samples into the same list averaged
incompatible units. Raw TTFT now lives under "time_to_first_token_seconds"
and routing reads only that key.

Also fix the regression test's token counts: with 50 tokens on the fast
deployment and 500 on the slow one the old per-token formula picks the
slow deployment, so the routing assertion now catches the bug.

Claude-Session: https://claude.ai/code/session_01Ttd5Q9ZhRPB4ch5guos3rj

* test(router): cover the TTFT sliding window from the unit-test shard

Move the TTFT list trimming checks from the CircleCI-only suite into the
mapped unit test file as one sync/async parametrized test, so the changed
lines in lowest_latency.py are exercised by the GitHub unit-test shard
that reports patch coverage.

Claude-Session: https://claude.ai/code/session_01Ttd5Q9ZhRPB4ch5guos3rj
2026-09-08 10:05:23 -07:00
..
.litellm_cache
auto_router [Feat] Backend Router - Add Auto-Router powered by semantic-router (#12955) 2025-07-24 18:32:56 -07:00
example_config_yaml test: test 2026-03-28 19:17:38 -07:00
test_configs test: test 2026-03-28 19:17:38 -07:00
test_model_response_typing
azure_fine_tune.jsonl
azure_speech.mp3 [Feat] Add Azure AVA TTS integration (#15749) 2025-10-20 16:52:23 -07:00
batch_job_results_furniture.jsonl
cache_unit_tests.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
conftest.py test: exempt MockTransport request-shape embedding tests from VCR replay 2026-09-01 13:29:12 -07:00
create_mock_standard_logging_payload.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
data_map.txt
eagle.wav
example.jsonl VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
gettysburg.wav
large_text.py
model_cost.json
openai_batch_completions.jsonl
openai_batch_completions_router.jsonl
speech_vertex.mp3
stream_chunk_testdata.py
test_acompletion.py Complete o3 model support (#8183) 2025-02-02 22:36:37 -08:00
test_acompletion_fallbacks.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_acooldowns_router.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_add_function_to_prompt.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_aim_guardrails.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_alangfuse.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_amazing_vertex_completion.py Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_ruff_dead_test_code 2026-08-24 09:46:56 -07:00
test_anthropic_prompt_caching.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_arize_ai.py test: rename env var 2026-03-28 20:27:39 -07:00
test_arize_phoenix.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_assistants.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_async_fn.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_auth_utils.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_azure_anthropic_sync_post.py fix(mcp): honor server_id for REST tool calls with shared upstream URLs (#30184) 2026-06-12 07:25:53 -07:00
test_azure_openai.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_azure_perf.py test: test 2026-03-28 19:17:38 -07:00
test_basic_python_version.py revert: default the proxy back to the v1 migration resolver 2026-09-01 12:56:08 -07:00
test_batch_completion_return_exceptions.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_batch_completions.py test(batch): make the upstream-failure tolerance actually reachable 2026-08-28 00:25:53 -07:00
test_blocked_user_list.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_braintrust.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_budget_manager.py
test_cache_preset_key.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_caching.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_caching_handler.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_caching_ssl.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_class.py test: test 2026-03-28 19:17:38 -07:00
test_completion.py test(bedrock): drop EOL cohere.command-r-plus-v1:0 from local_testing 2026-09-03 11:50:51 -07:00
test_completion_cost.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_completion_with_retries.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_config.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_cost_calc.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_custom_callback_input.py test: fix staging CI regressions from #38182, #38144, #38265, #37962, and #37969 2026-08-25 23:01:20 -07:00
test_custom_llm.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_custom_logger.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_disk_cache_unit_tests.py LiteLLM Minor Fixes & Improvements (11/12/2024) (#6705) 2024-11-12 22:50:51 +05:30
test_docker_no_network_on_deploy.py build: migrate packaging, CI, and Docker from Poetry to uv (#25007) 2026-04-09 11:46:23 -07:00
test_dual_cache.py fix(cache): use sync Redis batch reads (#39358) 2026-09-03 14:37:48 -07:00
test_dynamic_rate_limit_handler.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_embedding.py test(timeout): time out against the local fake endpoint instead of api.openai.com 2026-09-03 09:53:30 -07:00
test_exceptions.py test(embeddings): move legacy intercepts to the wire for the omitted-format path 2026-08-29 12:04:44 -07:00
test_fake_openai_endpoint.py test(ci): serve /moderations from the canned OpenAI mock (#37739) 2026-08-20 16:58:38 -07:00
test_file_types.py test: require a match= on broad pytest.raises, and drop duplicate parametrize cases (#37769) 2026-08-20 20:24:49 -07:00
test_function_call_parsing.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_function_calling.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_function_setup.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_gcs_bucket.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_gcs_cache_unit_tests.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_gemini_reasoning_content.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_get_llm_provider.py test: allow dashscope domain in qwen alias default api_base check 2026-09-01 13:29:12 -07:00
test_get_model_file.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_get_model_info.py test: collapse blank lines left by removed tests 2026-09-08 02:21:55 +00:00
test_get_optional_params_embeddings.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_get_optional_params_functions_not_supported.py
test_google_ai_studio_gemini.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_guardrails_ai.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_helicone_integration.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_http_parsing_utils.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_img_resize.py fix: Support WebP image format and avoid token calculation error (#7182) 2024-12-12 14:32:39 -08:00
test_langchain_ChatLiteLLM.py
test_least_busy_routing.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_litellm_max_budget.py
test_llm_guard.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_load_test_router_s3.py fix tests 2025-10-25 10:19:24 -07:00
test_loadtest_router.py test: test 2026-03-28 19:17:38 -07:00
test_logging.py
test_longer_context_fallback.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_lowest_cost_routing.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_lowest_latency_routing.py fix(router): rank streaming latency routing by raw TTFT, not TTFT per token (#40202) 2026-09-08 10:05:23 -07:00
test_lunary.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_max_tpm_rpm_limiter.py
test_mem_leak.py
test_mem_usage.py fix tests 2025-10-25 10:19:24 -07:00
test_mock_request.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_model_alias_map.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_multiple_deployments.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_no_top_level_test_invocations.py fix(tests): drop module-level test calls that break local_testing collection (#29520) 2026-06-02 13:07:05 -07:00
test_ollama.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_ollama_local.py
test_ollama_local_chat.py
test_openai_moderations_hook.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_opik.py test(opik): stop the batching test racing its own 5-second flush timer 2026-08-27 23:43:38 -07:00
test_pass_through_endpoints.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_profiling_router.py
test_prometheus_service.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_prompt_caching.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_prompt_injection_detection.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_provider_specific_config.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_pydantic.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_pydantic_namespaces.py
test_redis_batch_optimizations.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_register_model.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_responses_stream_cache_keys.py fix(cache): persist and replay streamed Responses API requests (#24580) 2026-05-01 11:55:36 +05:30
test_router.py test(timeout): time out against the local fake endpoint instead of api.openai.com 2026-09-03 09:53:30 -07:00
test_router_batch_completion.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_router_budget_limiter.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_router_caching.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_router_client_init.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_router_cooldown_handlers.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_router_custom_routing.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_router_debug_logs.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_router_fallback_handlers.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_router_fallbacks.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_router_get_deployments.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_router_max_parallel_requests.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_router_pattern_matching.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_router_retries.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_router_timeout.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_router_utils.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_router_with_fallbacks.py
test_rules.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_sagemaker.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_sagemaker_nova_integration.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_scheduler.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_secret_detect_hook.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_spend_calculate_endpoint.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_stream_chunk_builder.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_streaming.py test(bedrock): drop EOL cohere.command-r-plus-v1:0 from local_testing 2026-09-03 11:50:51 -07:00
test_supabase_integration.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_team_config.py
test_text_completion.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_timeout.py test(timeout): time out against the local fake endpoint instead of api.openai.com 2026-09-03 09:53:30 -07:00
test_together_ai.py
test_tpm_rpm_routing_v2.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_ui_sso_helper_utils.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_unit_test_caching.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_update_spend.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_validate_environment.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_wandb.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
user_cost.json
vertex_ai.jsonl
vertex_batch_completions.jsonl (feat) add Vertex Batches API support in OpenAI format (#7032) 2024-12-04 19:40:28 -08:00
vertex_key.json test: update to new vertex ai keys 2026-03-28 20:19:05 -07:00
whitelisted_bedrock_models.txt Litellm fix update bedrock models (#24947) 2026-04-01 19:22:54 -07:00