Aryan Gorde 0509c8649e fix(a2a): cover the missing-sdk fallback and keep org prefetch warm ... The patch left the ImportError resolver base unhit in-process, so codecov patch coverage sat at two thirds. Call the fallback from a helper the tests can exercise when a2a-sdk is blocked Org prefetch also dropped rows whose JSON columns arrived as strings, and the 5s org TTL expired before the first proxy-behavior getter on a cold runner. Decode those columns the way team rows already do, and cache org entries for the same management TTL as user and team Co-authored-by: ARYAN GORDE <aryangorde8@users.noreply.github.com>		2026-09-13 08:10:17 +00:00
..
_experimental/mcp_server	test(mcp): remove unrelated formatting changes	2026-09-12 18:27:20 -07:00
a2a
agent_endpoints	fix(a2a): forward caller identity headers on message/send and message/stream (#40305)	2026-09-08 15:56:52 -07:00
analytics_endpoints	fix(proxy): attribute gate-rejected requests to their endpoint in cache analytics (#40824)	2026-09-12 16:03:38 -07:00
anthropic_endpoints	test(proxy): pass the request to get_marketplace in the archive marketplace test	2026-09-10 14:54:46 -07:00
auth	fix(a2a): cover the missing-sdk fallback and keep org prefetch warm	2026-09-13 08:10:17 +00:00
batches_endpoints	fix(batches): register ownership for every batch create path (#39810)	2026-09-04 23:59:51 -07:00
client	feat(cli): configure Claude Code and Codex with a gateway key (#40829)	2026-09-12 09:59:13 -07:00
common_utils	Merge pull request #40772 from BerriAI/litellm_lit6982_bucket_config_includes	2026-09-12 15:21:56 -07:00
config_resolvers
container_endpoints
credential_endpoints
db	fix(proxy): bound tool and guardrail index create_many by the spend-log statement budgets (#40561)	2026-09-12 19:00:47 -07:00
discovery_endpoints	perf: cache repacked Agent Skills archives per skill version	2026-09-06 03:20:37 -07:00
enterprise_billing
experimental/mcp_server
fine_tuning_endpoints
google_endpoints
guardrails	fix(proxy): bound tool and guardrail index create_many by the spend-log statement budgets (#40561)	2026-09-12 19:00:47 -07:00
health_endpoints	Merge pull request #40814 from BerriAI/litellm_gate_health_services_alert_tests	2026-09-12 21:13:30 -07:00
hooks	test(mcp): remove unrelated formatting changes	2026-09-12 18:27:20 -07:00
image_endpoints	fix(proxy): keep a ProxyException's status and label 408s in the OpenAI error payload	2026-09-08 12:16:08 -07:00
list_api	feat: page the public model hub table off /public/v1/model_hub, keeping every filter (#39691)	2026-09-03 22:36:16 -07:00
logging_endpoints
management_endpoints	Merge pull request #40657 from BerriAI/litellm_lit_7358_session_token_grant_resolver	2026-09-12 21:13:25 -07:00
management_helpers	feat(proxy): granular key/team access control for Claude Code marketplace plugins (#40518)	2026-09-10 14:26:09 -07:00
memory	feat(proxy): add a search param to key, memory, audit, and spend log listings	2026-09-03 15:20:13 -07:00
middleware	feat(proxy): resolve root_path per request from a configured prefix list (SERVER_ROOT_PATHS) (#35935)	2026-09-07 11:54:59 -07:00
ocr_endpoints
openai_files_endpoint	merge: bring litellm_internal_staging into the Bedrock files delete and list fix	2026-09-09 19:27:40 -07:00
pass_through_endpoints	Merge pull request #40771 from BerriAI/litellm_regression_coverage_followup	2026-09-12 15:29:36 -07:00
policy_engine	perf(policy_engine): dedup attachments in one pass after sorting (#40883)	2026-09-12 14:19:20 -07:00
prompts
proxy_server	Merge pull request #40772 from BerriAI/litellm_lit6982_bucket_config_includes	2026-09-12 15:21:56 -07:00
public_endpoints	test(proxy): drop docstrings from the Add Model provider tests	2026-09-07 15:12:41 -07:00
rag_endpoints	fix(proxy): emit SSE keepalives on queue, rag, azure passthrough, usage chat and policy enrich streams (#39273)	2026-09-03 18:23:37 -07:00
realtime_endpoints	test(proxy): type the realtime WebRTC fixtures with Protocols instead of a bare Callable	2026-09-08 15:01:17 -07:00
rerank_endpoints	fix(proxy): keep a ProxyException's status and label 408s in the OpenAI error payload	2026-09-08 12:16:08 -07:00
response_api_endpoints
shutdown
spend_tracking	Merge origin/litellm_internal_staging into litellm_spend_log_request_id_call_id	2026-09-12 21:04:25 -07:00
test_configs
types_utils
ui_crud_endpoints
utils	fix(proxy): attribute gate-rejected requests to their endpoint in cache analytics (#40824)	2026-09-12 16:03:38 -07:00
vector_store_endpoints	fix(proxy): let authorized internal users open vector store details (#40150)	2026-09-07 13:10:09 -07:00
vector_store_files_endpoints
video_endpoints
__init__.py
conftest.py
test__types.py
test_aiohttp_cleanup_closed.py
test_aiohttp_session_recovery.py
test_api_key_masking_in_errors.py
test_audio_speech_prometheus_hooks.py
test_batch_expiry.py
test_batch_metadata_none_fix.py
test_batch_retrieve_bedrock.py
test_batch_x_litellm_model_encoding.py
test_blocked_response_usage.py
test_budget_reservation.py	perf(proxy): pipeline spend counter increments into one Redis call per request (#40371)	2026-09-09 10:35:50 -07:00
test_caching_routes.py
test_chat_completion_metadata.py
test_claude_code_marketplace.py
test_collector.py	feat(proxy): offload spend tracking to a pod-local collector sidecar (#40545)	2026-09-10 17:14:13 -07:00
test_common_request_processing.py	Merge origin/litellm_internal_staging into litellm_spend_log_request_id_call_id	2026-09-12 21:04:25 -07:00
test_component_allowlists.py	fix(gateway): serve /debug/memory/summary on the data plane so the memory regression test can read each gateway's RSS	2026-09-10 18:12:40 -07:00
test_conftest.py
test_cors_config.py
test_custom_proxy.py
test_dynamic_mcp_route.py
test_empty_model_list.py
test_enforce_user_param.py
test_fallback_management_endpoints.py
test_fastapi_offline_routes.py
test_filter_models_by_team_access_group.py
test_health_check_functions.py	Merge pull request #40765 from BerriAI/litellm_fix_health_scoped_results_and_serialization	2026-09-11 21:21:44 -07:00
test_health_check_max_tokens.py	fix(health): keep team public names to the owning team and let model_id win over model	2026-09-11 19:49:37 -07:00
test_init_litellm_callbacks.py
test_langfuse_passthrough_security.py
test_lazy_openapi_snapshot.py
test_litellm_pre_call_utils.py	feat(ocr): add Azure Mistral adapter with native authentication (#40502)	2026-09-11 16:22:55 -07:00
test_max_budget_env_var.py
test_mcp_asgi_response.py
test_model_based_routing_files_batches.py
test_model_deprecations_endpoint.py
test_model_dump_with_preserved_fields.py
test_model_id_header_propagation.py
test_model_info_default_limits.py
test_model_level_guardrails.py
test_model_list_healthy_only.py
test_modify_response_streaming_passthrough.py
test_openai_ws_passthrough_routes.py	fix(proxy): keep the token's team model list in the websocket passthrough gate without a database	2026-09-04 19:05:35 -07:00
test_openapi_schema_validation.py
test_plugin_routes.py
test_pointfive_dashboard_config.py	feat(pointfive): add pointfive to the dashboard logging integrations	2026-09-10 14:02:35 +03:00
test_pointfive_ui_callback.py	feat(pointfive): list pointfive in the proxy callback registry	2026-09-10 14:02:35 +03:00
test_pricing_field_strip.py
test_prisma_engine_watchdog.py	fix(proxy): recreate the Prisma client when the writer session turns read-only (#40610)	2026-09-10 13:53:42 -07:00
test_prisma_migration.py	fix(proxy): run migrations through python -m prisma when the prisma console script is not on PATH	2026-09-09 18:17:12 -07:00
test_prometheus_cleanup.py	feat(deploy): metrics sidecar and separate metrics port in Helm and Terraform (#40163)	2026-09-08 13:31:07 -07:00
test_prometheus_metrics_server.py	feat(deploy): metrics sidecar and separate metrics port in Helm and Terraform (#40163)	2026-09-08 13:31:07 -07:00
test_provider_url_destination_guard.py
test_proxy_cli.py	fix(proxy): run migrations through python -m prisma when the prisma console script is not on PATH	2026-09-09 18:17:12 -07:00
test_proxy_logging_hook_detection.py	test(proxy): give the pipeline-managed native hook audit test its chat completions route	2026-09-09 14:15:01 -07:00
test_proxy_server.py	perf(proxy): one MGET and one pipeline for post-call spend counters, no team/user/org refetch on the response path (#40841)	2026-09-12 16:05:50 +00:00
test_proxy_types.py
test_proxy_utils.py	fix(proxy): keep call_type and request start time on failed-request spend logs (#40558)	2026-09-11 12:22:18 -07:00
test_pyroscope.py
test_read_model_list.py
test_redis_auth_cache_flag.py
test_response_model_sanitization.py
test_route_a2a_models.py
test_route_llm_request.py	fix(proxy): keep the raw model string out of the unknown-model spend-log error message	2026-09-11 18:42:08 -07:00
test_route_priority.py	perf(proxy): register liveness and core inference routes first (#40687)	2026-09-11 17:10:38 +00:00
test_sensitive_route_auth.py
test_shared_health_check.py
test_spend_log_cleanup.py
test_swagger_chat_completions.py
test_team_member_update.py
test_team_org_move.py
test_tools_allowlist_enforcement.py
test_update_llm_router_resilience.py