litellm/tests/proxy_unit_tests
Alexsander Hamir eb5031da1e
[Perf] Fix bottlenecks degrading realtime endpoint performance (#16670)
* Cache realtime websocket request body

Move the realtime request payload builder out of the websocket handler and wrap it with an LRU cache so repeated connections reuse the same bytes object. This keeps the JSON formatting cost down while bounding memory usage.

* Optimize realtime websocket caching

Refactored /v1/realtime to use cached helpers for both the JSON body and query params, introduced a reusable request-scope template, and optimized header handling to avoid redundant work.

* Refine realtime websocket header handling

* Reuse websocket scope headers in auth

* Refactor realtime request body helper

Move the realtime request body formatter into proxy common utils so it can be reused across modules. Reuse it in the websocket auth flow to share LRU caching and avoid ad hoc byte builders.

* fix: revert to old pattern

The old pattern was necessary, we can just return the optimized function instead.

* Reuse SSL context for realtime

Create a shared SSLContext for OpenAI realtime websocket dials and pass it into websockets.connect so we stop re-reading verify paths on every session.

* feat: reuse shared TLS context for realtime websockets

- add `SHARED_REALTIME_SSL_CONTEXT` helper so all realtime websocket clients share the same TLS settings
- wire the shared context into OpenAI, Azure, custom HTTPX handlers, and realtime health checks
- update realtime tests to assert that the expected SSL context is passed to `websockets.connect`

This keeps TLS configuration consistent and avoids recreating SSL contexts per connection.

* Reuse HTTP SSL context for realtime

Remove the standalone realtime SSL helper, expose a shared context directly from the HTTP handler, and point all realtime websocket clients and tests to it. Add the websocket header comparison tool.

* Lazy-load shared realtime SSL context

Fix circular imports introduced by eagerly instantiating the shared TLS context. Make the HTTP handler lazily create the context and have realtime clients/tests fetch it on demand, keeping configuration consistent without breaking startup.

* add: unit test for realtime LRU caches

* fix: merge conflict with imports
2025-11-22 10:01:02 -08:00
..
example_config_yaml fix tests 2025-10-25 10:19:24 -07:00
test_configs fix tests 2025-10-25 10:19:24 -07:00
test_model_response_typing fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
adroit-crow-413218-bc47f303efc9.json vertex testing use pathrise-convert-1606954137718 2025-01-05 14:00:17 -08:00
azure_fine_tune.jsonl fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
batch_job_results_furniture.jsonl fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
conftest copy.py fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
conftest.py fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
data_map.txt fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
eagle.wav fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
gettysburg.wav fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
large_text.py fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
messages_with_counts.py fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
model_cost.json fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
openai_batch_completions.jsonl fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
openai_batch_completions_router.jsonl fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
speech_vertex.mp3 fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
test_aproxy_startup.py (Security fix) - Upgrade to fastapi==0.115.5 (#7447) 2024-12-28 17:08:19 -08:00
test_audit_logs_proxy.py fix: use fastuuid helper (#14903) 2025-09-25 15:47:01 -07:00
test_auth_checks.py [Performance] RPS Improvement +500 RPS when sending the user field (#14616) 2025-09-16 16:18:23 -07:00
test_banned_keyword_list.py fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
test_custom_callback_input.py fix: use fastuuid helper (#14903) 2025-09-25 15:47:01 -07:00
test_custom_logger_s3_gcs.py [Feat] Allow reading custom logger python scripts from s3 (#12623) 2025-07-16 15:07:01 -07:00
test_custom_tokenizer_bug.py fix(token-counter): extract model_info from deployment for custom_tokenizer (#15657) (#15680) 2025-10-17 19:38:45 -07:00
test_db_schema_changes.py test: initial test to enforce all functions in user_api_key_auth.py h… (#7797) 2025-01-15 21:52:45 -08:00
test_db_schema_migration.py Revert "Security fix - prevent proxy_admin_viewer from modifying other user's credentials + remove hardcoded sensitive keys from test repo" (#14362) 2025-09-08 18:40:54 -07:00
test_default_end_user_budget_simple.py [AI Gateway] - End User Budgets - Allow pointing max_end_user budget to an id, so the default ID applies to all end users (#16456) 2025-11-11 08:20:13 -08:00
test_deployed_proxy_keygen.py fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
test_e2e_pod_lock_manager.py fix: use fastuuid helper (#14903) 2025-09-25 15:47:01 -07:00
test_google_gemini_proxy_request.py Fix: Send Gemini API key via x-goog-api-key header with custom api_base (#16085) 2025-11-05 07:12:13 -08:00
test_jwt.py test_end_user_jwt_auth 2025-10-02 18:48:11 -07:00
test_key_generate_dynamodb.py fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
test_key_generate_prisma.py Litellm ci cd fixes 2 (#16693) 2025-11-15 14:12:44 -08:00
test_models_fallback_endpoint.py feat: extended /v1/models endpoint, now it returns with fallbacks on demand (#12811) 2025-07-22 23:16:46 -07:00
test_prisma_client_backoff_retry.py fix: prisma client state retries (#14925) 2025-09-25 21:54:00 -07:00
test_prompt_test_endpoint.py [Feat] UI - Prompt Management - Allow testing prompts with Chat UI (#16898) 2025-11-21 08:53:18 -08:00
test_proxy_config_unit_test.py (fix) - proxy reliability, ensure duplicate callbacks are not added to proxy (#8067) 2025-01-28 21:01:56 -08:00
test_proxy_custom_auth.py fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
test_proxy_custom_logger.py test_embedding 2025-09-27 16:57:27 -07:00
test_proxy_encrypt_decrypt.py test: fix test 2025-07-27 09:52:22 -07:00
test_proxy_exception_mapping.py [Perf] Embeddings: Use router's O(1) lookup and shared sessions (#16344) 2025-11-14 09:21:45 -08:00
test_proxy_gunicorn.py fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
test_proxy_pass_user_config.py fix tests 2025-10-25 10:19:24 -07:00
test_proxy_reject_logging.py [Security Bug Fix] Ensure only LLM API route fails get logged on Langfuse (and other loggers) (#12308) 2025-07-04 14:42:42 -07:00
test_proxy_routes.py [Bug fix]: Proxy Auth Layer - Allow Azure Realtime routes as llm_api_routes (#7684) 2025-01-10 20:38:06 -08:00
test_proxy_server.py [Perf] Embeddings: Use router's O(1) lookup and shared sessions (#16344) 2025-11-14 09:21:45 -08:00
test_proxy_server_caching.py fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
test_proxy_server_keys.py fix tests 2025-10-25 10:19:24 -07:00
test_proxy_server_langfuse.py (Security fix) - Upgrade to fastapi==0.115.5 (#7447) 2024-12-28 17:08:19 -08:00
test_proxy_server_spend.py fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
test_proxy_setting_guardrails.py fix(pattern_match_deployments.py): default to user input if unable to… (#6632) 2024-11-08 00:55:57 +05:30
test_proxy_token_counter.py fix typo of orginal (#16255) 2025-11-04 18:55:44 -08:00
test_proxy_utils.py feat: add parallel execution handling in during_call_hook (#16279) 2025-11-05 18:35:25 -08:00
test_realtime_cache.py [Perf] Fix bottlenecks degrading realtime endpoint performance (#16670) 2025-11-22 10:01:02 -08:00
test_unit_test_max_model_budget_limiter.py Support budget/rate limit tiers for keys (#7429) 2024-12-26 19:05:27 -08:00
test_unit_test_proxy_hooks.py test fixes 2025-03-31 19:33:10 -07:00
test_update_spend.py attempt to avoid/minimize deadlocks (#15281) 2025-10-24 12:22:38 -07:00
test_user_api_key_auth.py Make sure that user inherits team permissions (#16639) 2025-11-18 20:14:42 -08:00
vertex_key.json ci/cd update vertex acct 2025-01-05 13:43:32 -08:00