litellm/tests/test_litellm/proxy
Krish Dholakia e7f1fa26ab
UI - Azure Content Guardrails (#12341)
* build(model_prices_and_context_window.json): remove 'supports_tool_choice' for specific mistral models

Closes https://github.com/BerriAI/litellm/issues/11750

* feat: initial commit adding cleaner ui for azure text moderation guardrails

* feat(guardrail_endpoints.py): add discoverable guardrail configs and improve converting base model to dict with types

* fix(guardrail_provider_fields.tsx): render from api endpoint correctly

* fix(guardrail_provider_fields.tsx): cleanup

* refactor(guardrail_endpoints.py): refactor to handle dictionaries with literal - allows multiselect

* feat(ui/): render dictionary with known keys correctly

* feat(ui/): render optional params on separate page

* style(ui/): style improvements to rendering optional params on the UI

* feat(azure/prompt_shield.py): add azure prompt shield back on UI

* fix(add_guardrail_form.tsx): fix form to handle updated api

* fix(guardrail_optional_params.tsx): ensure values are nested correctly for writing to api

* fix: fix linting error

* feat(text_moderation.py): handle str to int conversion

* fix(guardrail_info.tsx): only render pii settings if guardrail is presidio

* fix(guardrail_info.tsx): add guardrail specific fields to update settings

allows updating guardrail fields (e.g. severity threshold) post-create

* fix(guardrail_endpoints.py): set guardrail_id in guardrail object

ensures duplicate objects not created on guardrail update

* fix(guardrail_endpoints.py): allow provider specific fields to be updated on patch update

* refactor(guardrail_endpoints.py): remove duplicate info endpoint

* fix(guardrail_endpoints.py): mask sensitive keys on returning via guardrail `/info`

Prevent leaking keys

* fix(guardrail_optional_params.tsx): return numerical input when numerical component used

fixes issue where output was a str

* fix(guardrail_optional_params.tsx): render dict keys correctly

* fix(text_moderation.py): fix severity by category check

* fix(proxy/utils.py): check if guardrail should run for post call streaming hook

Prevents invalid guardrails from running if not requested

* test: fix import

* fix: fix linting error

* test: update test

* fix: fix tests

* fix: fix code qa errors

* fix(guardrail_endpoints.py): set max depth for function

* test: update recursive_detector.py

* test: update list

* build: merge main

* fix: fix ruff check errors
2025-07-05 10:19:29 -07:00
..
_experimental/mcp_server/auth UI - Azure Content Guardrails (#12341) 2025-07-05 10:19:29 -07:00
anthropic_endpoints test fixes 2025-06-25 18:42:06 -07:00
auth [Feat] JWT - Sync user roles and team memberships when JWT Auth is used (#11994) 2025-07-05 08:58:34 -07:00
client test fix creds test 2025-07-03 22:01:52 -07:00
common_utils Update enduser spend and budget reset date based on budget duration (#8460) 2025-06-08 08:39:14 -07:00
db build(VLLM-Passthrough-with-loadbalancing-support-(enables-using-model-list-for-VLLM-/classify-endpoint)): Closes #11205 2025-05-31 09:00:04 -07:00
experimental/mcp_server
guardrails UI - Azure Content Guardrails (#12341) 2025-07-05 10:19:29 -07:00
health_endpoints
hooks GA Multi-instance rate limiting v2 Requirements + New - specify token rate limit type - output / input / total (#11646) 2025-06-11 22:05:13 -07:00
image_endpoints Feat: add add azure endpoint for image endpoints (#11482) 2025-06-06 10:38:37 -07:00
management_endpoints fix test 2025-07-03 15:37:10 -07:00
management_helpers Squashed commit of the following: 2025-06-20 23:11:53 -07:00
middleware
openai_files_endpoint fix(proxy): Add managed_files hook to test_mock_create_audio_file 2025-06-26 10:42:25 -06:00
pass_through_endpoints [Feat] UI QA: Pass through endpoints (#11939) 2025-06-20 18:35:38 -07:00
spend_tracking Fix boto3 tracer wrapping for observability (#11869) 2025-06-18 15:47:55 -07:00
test_configs
types_utils
ui_crud_endpoints Refactor settings response models in proxy_setting_endpoints.py 2025-06-04 15:08:05 -06:00
test_caching_routes.py [Bug Fix] Ensure /redis/info works on GCP Redis (#11732) 2025-06-14 15:35:09 -07:00
test_common_request_processing.py [Feat] DD Trace - Add instrumentation for streaming chunks (#11338) 2025-06-02 16:48:39 -07:00
test_custom_proxy.py Custom Root Path Improvements: don't require reserving /litellm route (#11460) 2025-06-05 16:36:47 -07:00
test_health_check_functions.py Implement health check backend API and storage functionality - fix ci/cd (#11852) 2025-06-18 06:57:08 -07:00
test_litellm_pre_call_utils.py [Feat] Add Arize Team Based Logging (#12264) 2025-07-02 17:15:35 -07:00
test_proxy_cli.py add ciphers in command and pass to hypercorn for proxy (#11916) 2025-06-20 14:45:48 -07:00
test_proxy_server.py Fix - handle empty config.yaml + Fix gemini /models - replace models/ as expected, instead of using 'strip' (#12189) 2025-06-30 21:56:03 -07:00
test_proxy_types.py Litellm dev 06 06 2025 p1 (#11496) 2025-06-07 09:12:16 -07:00
test_proxy_utils.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_route_llm_request.py Update mistral 'supports_response_schema' field + Fix ollama embedding (#12024) 2025-06-25 07:20:13 -07:00
test_spend_log_cleanup.py [Feat] Make batch size for maximum retention in spend logs a controllable parameter (#11459) 2025-06-05 17:11:51 -07:00
test_team_member_update.py fix mapped tests (#12320) 2025-07-04 10:04:43 -07:00