litellm/tests/unit/proxy
tavren27 27c796c412
fix(proxy): count the request's tool_choice on the token count routes (#51133)
* fix(proxy): count the request's tool_choice on the token count routes

/utils/token_counter, /v1/messages/count_tokens and /v1/responses/input_tokens now pass tool_choice into the local estimate, and every DeepSeek model counts it as 0, as its providers bill

* fix(token_counter): count a request with no model name again

* fix(token_counter): count grok tool_choice the way xAI bills it

xAI bills grok-4.3 and grok-4-1-fast-reasoning 21 tokens for "none", 11 for
"required" and 12 plus the name for a named tool, where the OpenAI costs
counted 1, 0 and 7 plus the name. The grok-4-1 and grok-4.3 chat template
tool sections now carry those costs, so a grok count matches its bill for
every tool_choice

* fix(token_counter): count xAI's grok tool_choice costs only where xAI serves grok

Azure AI Foundry bills grok-4-1's tool_choice differently, so grok on other hosts keeps counting it as 0. A tool_choice sent without tools counts nothing, since OpenAI and xAI reject it

* fix(token_counter): key xAI's grok tool_choice costs on the provider that serves the deployment

The count routes strip the provider prefix before counting, so Azure, Vertex AI and Perplexity grok matched the xAI name pattern. The routes now resolve the serving provider with get_llm_provider and drop xAI's costs when it is not xAI or OpenRouter's x-ai route. The costs move onto the grok tool sections so one pattern decides them

* fix(token_counter): count no tool_choice for Gemini and none without tools in the Rust counter

Gemini bills the same prompt tokens for every tool_choice, so it skips the
OpenAI choice costs the way DeepSeek does. The Rust reservation counter now
adds tool_choice tokens only when tools are present, matching the Python counter

* fix(proxy): count no tool_choice a deployment drops, and treat an api.x.ai api_base as xAI

A deployment that lists tool_choice in additional_drop_params never sends it, so the count routes no longer add its cost. An openai/ model whose api_base is on api.x.ai is served by xAI, so it gets xAI's tool_choice costs like xai/ grok

* fix(proxy): count no tool_choice a request drops in its body

/v1/messages/count_tokens takes additional_drop_params from the request body, and inference drops tool_choice when it is listed there, so the count no longer adds its cost either

* fix(proxy): take additional_drop_params on /utils/token_counter and treat a malformed api_base as not xAI

/utils/token_counter now passes a request body's additional_drop_params into the count, so a tool_choice the request drops counts as 0 there like on the other two count routes. An api_base that does not parse falls back to the deployment's provider instead of failing the count with a 500

* fix(proxy): take chatgpt and github_copilot providers from the model name in the count host check

Resolving them through get_llm_provider read the saved login, logged a warning and could refresh a token on every count with a tool_choice

* fix(proxy): skip a tool_choice or additional_drop_params too deeply nested to validate on the count routes

A value nested 300 levels deep failed TokenCountRequest validation, so the count routes answered 422 or 400 where they used to count the request without it

* fix(bedrock): count Kimi K3's forced tool_choice message on the exact count path

Kimi K3's chat template adds a tool-choice system message when Bedrock gets toolChoice any or a named tool, and Bedrock bills it (170 input tokens unforced, 206 forced). The exact count path now passes tool_choice through the same Converse mapping inference uses and renders that message

* test(proxy): type the Kimi K3 count test's tools parameter

* perf(count_tokens): validate each kept count option once instead of twice

* fix(dot_notation): parse drop paths in linear time when brackets never close

* test(count_tokens): benchmark the unclosed-bracket drop path instead of timing it in a unit test

---------

Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
2026-11-14 07:53:27 -05:00
..
_experimental fix(mcp): load deprecated package aliases on demand (#48615) 2026-10-27 19:46:19 +00:00
a2a fix(agents): show non-admin callers the proxy URL in agent cards (#49483) 2026-10-31 16:17:11 -07:00
agent_endpoints fix(azure)!: answer 401 when Entra rejects the deployment's credential (#49863) 2026-11-04 20:44:55 +00:00
alerting_endpoints feat(alerts): add management controls and opt-in daily summaries (#51418) 2026-11-12 10:06:07 -08:00
analytics_endpoints fix(proxy): cancel the Admin UI's raw spend-log reads in Postgres after 30s (#49965) 2026-11-03 16:07:00 -08:00
anthropic_endpoints fix(skills): honor dashboard user and team grants (#51416) 2026-11-12 10:12:32 -08:00
auth feat(proxy): support budget_limits windows on internal users (#51763) 2026-11-14 07:44:35 -05:00
batches_endpoints fix(proxy)!: reject client-supplied Vertex location and project unless the admin opts in (#47028) 2026-11-10 20:50:17 +00:00
client fix(cli): let Claude Code renew a --pkce login's key through lite's apiKeyHelper (#51319) 2026-11-14 04:04:38 +00:00
common_utils feat(proxy): support budget_limits windows on internal users (#51763) 2026-11-14 07:44:35 -05:00
config_resolvers fix(proxy)!: ignore stored general_settings keys no settings API manages (#48967) 2026-11-02 14:58:46 -08:00
container_endpoints test(proxy): move utils, agent_endpoints and endpoint tests into tests/unit/proxy (#44006) 2026-10-01 11:06:42 -07:00
credential_endpoints fix(proxy): hold DB_RECONCILE_LOCK around credential create, update and delete (#50551) 2026-11-07 16:02:44 -08:00
db feat(proxy): support budget_limits windows on internal users (#51763) 2026-11-14 07:44:35 -05:00
decisions_endpoints feat(decisions): support Ollama decision models (#48871) 2026-10-28 12:35:26 -07:00
deps refactor(proxy): inject gateway activity through a typed repository (#49116) 2026-10-30 16:25:11 -07:00
discovery_endpoints feat(skills): let authors edit and withdraw pending submissions (#51312) 2026-11-12 08:30:10 -08:00
enterprise_billing feat(proxy): authenticate billing metrics with a cognito bearer token (#49852) 2026-11-04 14:08:40 -08:00
example_config_yaml
fine_tuning_endpoints fix(managed_files): send provider file ids when creating a fine-tuning job from managed files (#46552) 2026-10-19 14:40:15 -07:00
google_endpoints fix(interactions): bind Deep Research agents and record their costs (#51517) 2026-11-13 00:20:53 -08:00
guardrails fix(bedrock): send s3:// image, document and video URLs to Converse as S3 sources (#50577) 2026-11-13 21:33:21 -08:00
health_endpoints fix(proxy)!: reject client-supplied Vertex location and project unless the admin opts in (#47028) 2026-11-10 20:50:17 +00:00
hooks fix(dynamic_rate_limiter_v3): publish a team's share gauges for requests served while the model is idle (#51709) 2026-11-13 14:58:54 -08:00
image_endpoints fix(proxy): log each endpoint's own call type on failed audio, moderation, image, and rerank spend rows (#49684) 2026-11-02 23:57:11 +00:00
lens fix(proxy): validate JSON object bodies before request handling (#48438) 2026-10-26 16:11:38 -07:00
list_api test(proxy): move utils, agent_endpoints and endpoint tests into tests/unit/proxy (#44006) 2026-10-01 11:06:42 -07:00
logging_endpoints test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
management fix(ui): take the dashboard's user role and identity from the server (#47025) 2026-10-17 14:39:33 -07:00
management_endpoints feat(proxy): support budget_limits windows on internal users (#51763) 2026-11-14 07:44:35 -05:00
management_helpers feat(proxy): support budget_limits windows on internal users (#51763) 2026-11-14 07:44:35 -05:00
mcp_server fix(mcp): give the MCP client exactly the servers left on in the connect page (#50973) 2026-11-13 16:36:49 -08:00
memory test(proxy): move utils, agent_endpoints and endpoint tests into tests/unit/proxy (#44006) 2026-10-01 11:06:42 -07:00
middleware feat(skills): let authors edit and withdraw pending submissions (#51312) 2026-11-12 08:30:10 -08:00
ocr_endpoints fix(proxy)!: return provider-matching 4xx for the LIT-8062 status code follow-ups (#45537) 2026-10-13 11:42:39 -07:00
openai_files_endpoint fix(proxy): retrieve and delete a managed file when the request also names a model (#51780) 2026-11-14 04:55:36 -05:00
pass_through_endpoints feat(vertex_ai): label Vertex requests with the caller's key, team, org, and project (#50732) 2026-11-14 00:39:01 -05:00
policy_engine fix(anthropic): map pause_turn and return refusal explanations on chat and responses (#49192) 2026-10-31 02:53:59 -07:00
prompts fix(security): remove the publicly known master key from the repo (#44718) 2026-10-06 10:55:24 -07:00
proxy_server feat(proxy): support budget_limits windows on internal users (#51763) 2026-11-14 07:44:35 -05:00
public_endpoints fix(proxy): fetch blog posts without blocking the event loop (#51369) 2026-11-12 10:32:44 -08:00
rag_endpoints fix(bedrock): send s3:// image, document and video URLs to Converse as S3 sources (#50577) 2026-11-13 21:33:21 -08:00
realtime_endpoints feat(realtime)!: support latest OpenAI audio models (#35600) 2026-11-03 07:27:52 +00:00
rerank_endpoints fix(proxy): honor cancel_on_disconnect on the rerank endpoints (#51252) 2026-11-14 03:59:22 -05:00
response_api_endpoints fix(bedrock): send s3:// image, document and video URLs to Converse as S3 sources (#50577) 2026-11-13 21:33:21 -08:00
response_polling fix(proxy)!: preserve Responses SSE event framing (#47980) 2026-11-06 20:17:57 -08:00
roi_calculator fix: cap cold MCP schema workers at usable CPUs and deflake wall-clock unit tests (#45791) 2026-10-15 00:47:59 -07:00
rust_forward test(proxy): make the cancelled supervisor test deterministic (#51258) 2026-11-11 15:48:02 -08:00
search_endpoints feat(proxy): total_timeout bounds a whole non-streaming request (#50496) 2026-11-08 00:43:50 -08:00
shutdown fix(proxy): persist tag spend and drain success callbacks within the shutdown budget (#48988) 2026-10-29 09:32:18 -07:00
spend_tracking feat(proxy): support budget_limits windows on internal users (#51763) 2026-11-14 07:44:35 -05:00
telemetry feat(chat): add Moyai UI, model hub, images, and usage metrics (#40557) (#48108) 2026-10-23 23:39:23 +00:00
test_configs test: migrate legacy unit dirs and unrun folders into tests/unit, tests/integration and tests/e2e (#45940) 2026-10-11 06:24:57 -07:00
types_utils refactor(mcp): drop the experimental label from the MCP server and client paths (#48513) 2026-10-27 17:47:50 +00:00
ui_crud_endpoints feat(ui): let admins control Aria access for internal users (#51641) 2026-11-13 16:17:12 -05:00
utils fix(proxy): retain unwritten rollups after database disconnects (#51706) 2026-11-13 13:36:12 -08:00
vector_store_endpoints feat(opensearch): map vector store search filters to k-NN filters and add hybrid search (#51131) 2026-11-14 03:30:55 +00:00
vector_store_files_endpoints fix(proxy)!: return managed file ids from rag ingest and use team credentials on vector store file routes (#50459) 2026-11-10 05:44:28 +00:00
video_endpoints fix(proxy): align ownership and scope handling (#50600) 2026-11-08 07:03:36 +00:00
__init__.py
conftest.py fix(sdk): stop requiring redis to import the Messages streaming path (#51685) 2026-11-13 11:43:53 -08:00
proxy_server_config.yaml chore: move config and docs off the repo root (#50966) 2026-11-11 18:29:35 -08:00
router_entry_point_stubs.py fix(proxy): send a prompt-only call_endpoint token count to every provider count API (#50783) 2026-11-10 18:09:19 +00:00
skill_submission_rows.py feat(skills): add optional manual security scans (#50194) 2026-11-05 01:57:39 -08:00
test__lazy_features.py feat(realtime)!: support latest OpenAI audio models (#35600) 2026-11-03 07:27:52 +00:00
test__types.py feat(mcp): cache upstream tool lists with an admin-set lifetime (#51160) 2026-11-12 08:48:04 -08:00
test_admin_mcp.py fix: enforce LiteAdmin MCP route permissions (#48080) 2026-10-30 02:00:04 +00:00
test_aiohttp_cleanup_closed.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_aiohttp_session_recovery.py refactor(proxy): expose public names for private proxy helpers (#45170) 2026-10-07 18:59:27 -07:00
test_api_key_masking_in_errors.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_aproxy_startup.py
test_audio_speech_prometheus_hooks.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_batch_expiry.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_batch_metadata_none_fix.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_batch_retrieve_bedrock.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_batch_x_litellm_model_encoding.py fix(rag)!: use team provider credentials and allow viewer and JWT team access (#45497) 2026-10-17 23:51:48 +00:00
test_blocked_response_usage.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_body_snapshot_callback_params.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_budget_reservation.py feat(proxy): customer budget rollup, reset on the budget row's window, named templates, team overrides, multi-window limits and pause_allow_increase (#51582) 2026-11-13 16:05:35 +00:00
test_bug_report_config.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_caching_routes.py refactor(typing): clear about 1,100 basedpyright Any errors across 303 files (#49986) 2026-11-06 13:31:15 -08:00
test_chat_completion_metadata.py feat(accounting): capture request usage through the durable meter (#49133) 2026-10-31 07:32:25 -07:00
test_claude_code_marketplace.py chore: move scripts and runtime sources under litellm (#51006) 2026-11-12 04:19:57 +00:00
test_collector.py test(unit): keep unix socket paths in unit tests under the macOS AF_UNIX limit (#45040) 2026-10-28 20:23:22 -07:00
test_common_request_processing.py fix(proxy): honor cancel_on_disconnect on the rerank endpoints (#51252) 2026-11-14 03:59:22 -05:00
test_component_allowlists.py test: drop the unit tests that flaked on main this week (#51488) 2026-11-12 17:32:49 -08:00
test_conftest.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_cors_config.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_credential_slot_registry.py fix(proxy): stop request body fields from conflicting with admin-set deployment fields (#51254) 2026-11-11 23:39:17 +00:00
test_custom_callback_input.py
test_custom_logger_s3_gcs.py
test_custom_proxy.py test(ci): fix six CircleCI test regressions on main (#44429) 2026-10-03 20:55:01 -07:00
test_custom_tokenizer_bug.py fix(proxy): answer x-litellm-call-id on every token count response (#51037) 2026-11-11 22:26:47 +00:00
test_db_schema_changes.py refactor(proxy): name customer member budget columns budget_id and budget_override_id (#51490) 2026-11-12 17:33:22 -08:00
test_deprecated_key_grace_period.py
test_dev_reload.py refactor(proxy): let the gunicorn server take a private listener (#50871) 2026-11-11 19:40:00 +00:00
test_dynamic_mcp_route.py refactor(mcp): drop the experimental label from the MCP server and client paths (#48513) 2026-10-27 17:47:50 +00:00
test_empty_model_list.py refactor(router): move router callers onto the entry points and invert the proxy imports (#48847) 2026-10-29 17:26:33 +00:00
test_enforce_user_param.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_fallback_management_endpoints.py fix(fallback): preserve concurrent writes and serve saved configuration (#51245) 2026-11-11 15:26:23 -08:00
test_fastapi_offline_routes.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_filter_models_by_team_access_group.py refactor(router): move router callers onto the entry points and invert the proxy imports (#48847) 2026-10-29 17:26:33 +00:00
test_get_favicon.py
test_get_image.py
test_health_check_functions.py fix(health): log Test Connection spend with the mode's call type and model id (#50987) 2026-11-11 16:07:33 -08:00
test_health_check_max_tokens.py fix(router)!: keep a deployment's own model_id over the request body's (#49045) 2026-10-30 02:40:01 -07:00
test_init_litellm_callbacks.py feat(custom-logger-v2): add the contract for rust callbacks and bind the proxy request scope (#51526) 2026-11-14 02:33:27 +00:00
test_langfuse_passthrough_security.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_lazy_openapi_snapshot.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_litellm_pre_call_utils.py feat(proxy): customer budget rollup, reset on the budget row's window, named templates, team overrides, multi-window limits and pause_allow_increase (#51582) 2026-11-13 16:05:35 +00:00
test_max_budget_env_var.py feat(proxy)!: add suppress_startup_output to turn off startup prints (#47708) 2026-10-29 03:47:04 -07:00
test_mcp_asgi_response.py fix(mcp): log SDK request rejections (#49184) 2026-10-30 20:08:59 -07:00
test_model_based_routing_files_batches.py feat(proxy)!: only let clients pick S3 buckets the admin allowed (#47496) 2026-11-06 02:50:15 +00:00
test_model_deprecations_endpoint.py feat(ui): show model deprecation banner on the models page (#50080) 2026-11-04 18:50:14 -08:00
test_model_dump_with_preserved_fields.py feat(hosted_vllm)!: keep vLLM's stop_reason and token_ids on chat choices and stream chunks (#48393) 2026-11-02 13:26:29 -08:00
test_model_id_header_propagation.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_model_info_default_limits.py refactor(router): move router callers onto the entry points and invert the proxy imports (#48847) 2026-10-29 17:26:33 +00:00
test_model_level_guardrails.py refactor(router): move router callers onto the entry points and invert the proxy imports (#48847) 2026-10-29 17:26:33 +00:00
test_model_list_aliases.py fix(proxy): list key and team aliases on /model_group/info and apply listing callbacks to them (#51754) 2026-11-14 01:10:32 -05:00
test_model_list_callback_filter.py refactor(proxy): expose public names for private proxy helpers (#45170) 2026-10-07 18:59:27 -07:00
test_model_list_discoverable.py refactor(proxy): expose public names for private proxy helpers (#45170) 2026-10-07 18:59:27 -07:00
test_model_list_healthy_only.py refactor(router): move router callers onto the entry points and invert the proxy imports (#48847) 2026-10-29 17:26:33 +00:00
test_modify_response_streaming_passthrough.py fix(proxy): stream the guardrail block response when the block comes after an SSE keepalive ping (#51114) 2026-11-11 21:39:19 +00:00
test_moyai_endpoints.py test: fix flaky team delete, refusal sink, loop-blocking, Moyai tamper and model-cost leak tests (#47135) 2026-10-20 18:01:36 +00:00
test_native_compaction.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_openai_ws_passthrough_routes.py fix(proxy): check the model in every OpenAI websocket passthrough frame (#48979) 2026-11-02 09:48:59 -08:00
test_openapi_schema_validation.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_plugin_routes.py fix(proxy): build plugin session claims from FIPS provider services in fips_mode (#50544) 2026-11-09 11:07:57 -08:00
test_pointfive_dashboard_config.py chore: move ui and vscode-extension under litellm and delete docs (#50992) 2026-11-12 04:19:57 +00:00
test_pointfive_ui_callback.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_pricing_field_strip.py fix(security)!: build proxy-only failure logs from an allowlist and drop caller guardrail info (#48599) 2026-10-27 12:40:59 -07:00
test_prisma_client_backoff_retry.py
test_prisma_engine_watchdog.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_prisma_migration.py fix(proxy): always exit when database setup fails at boot (#44141) 2026-10-01 21:51:06 -07:00
test_prometheus_cleanup.py feat(prometheus): cap series per metric for every labeled metric (#44420) 2026-10-06 01:28:44 +00:00
test_prometheus_metrics_server.py feat(gemini): support gemini-decision-1 on /v1/decisions and /v1/systemone (#51220) 2026-11-11 18:33:22 -08:00
test_prompt_test_endpoint.py refactor: expose core private helpers under public names (#44871) 2026-10-07 00:05:27 +00:00
test_provider_url_destination_guard.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_proxy_cli.py feat(proxy): supervise the opt-in Rust forwarding server (#49606) 2026-11-11 19:40:00 +00:00
test_proxy_config_unit_test.py feat(mcp): add mcp_disabled_capabilities to stop advertising prompts and resources (#46563) 2026-10-15 15:15:40 -07:00
test_proxy_custom_auth.py
test_proxy_logging_hook_detection.py feat(custom-logger-v2): add types, dispatcher and route callback call sites (step 0) (#51214) 2026-11-13 22:08:05 +00:00
test_proxy_reject_logging.py fix(logging)!: fire one CustomLogger failure hook per async call outside the async flag list (#47124) 2026-10-20 15:19:14 -07:00
test_proxy_server.py fix(bedrock): send s3:// image, document and video URLs to Converse as S3 sources (#50577) 2026-11-13 21:33:21 -08:00
test_proxy_server_custom_logger.py test: migrate legacy unit dirs and unrun folders into tests/unit, tests/integration and tests/e2e (#45940) 2026-10-11 06:24:57 -07:00
test_proxy_server_endpoints_and_startup.py feat(budgets): support annual calendar reset periods (#51508) 2026-11-12 19:40:40 -08:00
test_proxy_server_exception_mapping.py test: migrate legacy unit dirs and unrun folders into tests/unit, tests/integration and tests/e2e (#45940) 2026-10-11 06:24:57 -07:00
test_proxy_setting_guardrails.py refactor(proxy): expose public names for private proxy helpers (#45170) 2026-10-07 18:59:27 -07:00
test_proxy_token_counter.py fix(proxy): count the request's tool_choice on the token count routes (#51133) 2026-11-14 07:53:27 -05:00
test_proxy_types.py fix(mcp): scope gateway OAuth consent to x-mcp-servers and add explicit scope setting (#44957) 2026-10-15 15:58:34 -07:00
test_proxy_utils.py fix(proxy): cancel the Admin UI's raw spend-log reads in Postgres after 30s (#49965) 2026-11-03 16:07:00 -08:00
test_proxy_utils_model_creation_and_error_logging.py fix(proxy): honor cancel_on_disconnect on the rerank endpoints (#51252) 2026-11-14 03:59:22 -05:00
test_pyroscope.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_read_model_list.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_redis_auth_cache_flag.py fix(redis): share one native circuit breaker between RedisCache and the Rust stores (#50473) 2026-11-07 17:50:06 +09:00
test_reducto_ocr_route.py
test_response_model_sanitization.py fix(proxy)!: preserve Responses SSE event framing (#47980) 2026-11-06 20:17:57 -08:00
test_response_polling_pre_call_checks.py feat(proxy): router_settings.fallback_on_saturation walks key and team fallbacks before a model saturates, replacing team model_preferences (#51439) 2026-11-13 05:57:18 +00:00
test_route_a2a_models.py refactor(router): move router callers onto the entry points and invert the proxy imports (#48847) 2026-10-29 17:26:33 +00:00
test_route_llm_request.py chore: move config and docs off the repo root (#50966) 2026-11-11 18:29:35 -08:00
test_route_priority.py fix(proxy): let configured pass-through endpoints outrank built-in provider prefix routes (#44133) 2026-10-10 12:26:17 -07:00
test_sensitive_route_auth.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_server_listener.py refactor(proxy): let the gunicorn server take a private listener (#50871) 2026-11-11 19:40:00 +00:00
test_server_root_path.py
test_shared_health_check.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_spend_log_cleanup.py feat(proxy): run spend log cleanup from a DB-backed scheduled job table (#50131) 2026-11-11 18:22:02 -08:00
test_swagger_chat_completions.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_team_member_update.py refactor(proxy): expose public names for private proxy helpers (#45170) 2026-10-07 18:59:27 -07:00
test_team_org_move.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_tools_allowlist_enforcement.py feat(proxy): mixed Codex model picker and LiteLLM routing on native codex routes (#49408) 2026-11-06 11:14:47 -08:00
test_tracing_endpoints.py refactor(rust-bridge): require the native extension (#48852) 2026-10-28 13:16:56 -07:00
test_ui_path_detection.py refactor(ui): remove the deprecated API Reference page (#51246) 2026-11-11 22:55:32 +00:00
test_unit_test_proxy_hooks.py feat(accounting)!: make the SpendLogs ledger the default accounting path (#49872) 2026-11-05 09:14:10 -08:00
test_update_llm_router_resilience.py refactor(router): move router callers onto the entry points and invert the proxy imports (#48847) 2026-10-29 17:26:33 +00:00
test_update_spend.py feat(accounting): add opt-in SpendLogs ledger (#49856) 2026-11-04 17:49:15 -08:00
test_v2_hook_routing.py feat(custom-logger-v2): add the contract for rust callbacks and bind the proxy request scope (#51526) 2026-11-14 02:33:27 +00:00
test_v2_proxy_fields.py feat(custom-logger-v2): add the contract for rust callbacks and bind the proxy request scope (#51526) 2026-11-14 02:33:27 +00:00
test_zero_cost_model_budget_bypass.py fix(proxy): judge the zero-cost budget waiver by the model a key or team alias serves (#51058) 2026-11-10 18:28:49 -08:00
test_zerobus_dashboard_config.py chore: move ui and vscode-extension under litellm and delete docs (#50992) 2026-11-12 04:19:57 +00:00
vector_store_access_group_state.py feat(access-groups): grant vector stores through access groups (#50290) 2026-11-12 14:59:17 -08:00
vertex_key.json