555efd60b5
[Security] Fix: Ensure .info() logs are not used for request/responses + Add code QA check for possible violations ( #14386 )
...
* test: info log
* fixes for debug
* add info_log_check
* fix: debug level
* fix: debug level
* fix: use .debug
* fix info statements
* fix info log check
* fix: fix emit_standard_logging_payload
* fix RequestBody
* Potential fix for code scanning alert no. 3339: Clear-text logging of sensitive information
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* fix check
* fix code qa check
---------
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
2025-09-09 13:55:56 -07:00
mubashir1osmani
2626123aca
added litellm_spend_metric
2025-09-01 11:33:34 -04:00
mubashir1osmani
5649c0f0b9
Revert "feat: add persistence and management for guardrails on virtual keys"
...
This reverts commit 6cd5afa8b1 .
2025-09-01 10:45:46 -04:00
mubashir1osmani
a6790ac158
Revert "feat: add UI support for displaying and managing guardrails on virtual keys"
...
This reverts commit 83654c5608 .
2025-09-01 10:45:44 -04:00
mubashir1osmani
31cfe1fe0a
Revert "fix: import verbose_proxy_logger to resolve undefined name errors"
...
This reverts commit a8f2ebed9c .
2025-09-01 10:45:38 -04:00
mubashir1osmani
8de65e8448
fix: added prometheus missing metrics
2025-09-01 10:36:51 -04:00
mubashir1osmani
af2f447698
added prometheus metrics
2025-09-01 10:28:48 -04:00
mubashir1osmani (aider)
a8f2ebed9c
fix: import verbose_proxy_logger to resolve undefined name errors
2025-09-01 01:17:46 -04:00
mubashir1osmani (aider)
83654c5608
feat: add UI support for displaying and managing guardrails on virtual keys
2025-09-01 01:17:08 -04:00
mubashir1osmani (aider)
6cd5afa8b1
feat: add persistence and management for guardrails on virtual keys
2025-09-01 00:56:22 -04:00
Krrish Dholakia
dba78046b9
fix(internal_user_endpoints.py): show remaining users when free SSO users is enabled
2025-08-20 22:26:01 -07:00
Ishaan Jaff and GitHub
4d941c914e
[Feat] Responses API Session Handling - Multi media support ( #13347 )
...
* rename ResponsesSessionHandler
* use ResponsesSessionHandler
* test session handler
* refactor ResponsesSessionHandler
* fix get_proxy_server_request_from_spend_log
* use constant for LITELLM_TRUNCATED_PAYLOAD_FIELD
* add _should_check_cold_storage_for_full_payload
* add get_class_type_for_custom_logger_name
* get_active_custom_logger_for_callback_name
* add get_proxy_server_request_from_cold_storage to CustomLogger
* add ColdStorageHandler
* start using cold storage integration
* add get_proxy_server_request_from_cold_storage
* fixes from manual testing
* s3 v2 fix getting region name
* ChatCompletionImageUrlObject
* use _get_configured_cold_storage_custom_logger
* fixes for _should_check_cold_storage_for_full_payload
* fix _download_object_from_s3
* test_s3_v2_with_cold_storage
* add cold_storage_object_key to StandardLoggingMetadata
* use get_proxy_server_request_from_cold_storage_with_object_key
* add cold_storage_object_key to SpendLogsMetadata
* add cold_storage_object_key
* get_proxy_server_request_from_cold_storage_with_object_key
* use get_proxy_server_request_from_cold_storage_with_object_key
* test responses API
* add get_proxy_server_request_from_cold_storage_with_object_key
* session handler fixes
* test session handler
* fix ruff checks
* _download_object_from_s3
* cleanup
* test
* lint fix
* test_e2e_cold_storage_successful_retrieval
* test_e2e_generate_cold_storage_object_key_successful
* test_async_gcs_pub_sub_v1
* test fix
* test fix
* test fix
* test_standard_logging_metadata_has_cold_storage_object_key_field
* test_sanitize_request_body_for_spend_logs_payload_basic
* test_transform_input_image_item_to_image_item_with_image_data
2025-08-07 10:59:53 -07:00
Ishaan Jaff
da40b5ec47
bump litellm enterprise
2025-08-05 17:50:40 -07:00
Ishaan Jaff
0308a835b8
bump: version 0.1.17 → 0.1.18
2025-08-05 17:47:16 -07:00
Ishaan Jaff and GitHub
dab8ba03e3
[Feat] - When using custom tags on prometheus allow using wildcard patterns ( #13316 )
...
* _tag_matches_wildcard_configured_pattern
* test_get_custom_labels_from_tags_wildcard_patterns
* docs Custom Tags
* docs how custom tags work
* fix
2025-08-05 17:46:13 -07:00
Krish Dholakia and GitHub
eb49f987de
Ensure disable_llm_api_endpoints works + Add wildcard model support for 'team-byok' model ( #13278 )
...
* fix(route_checks.py): ensure disable llm api endpoints is correctly set
* fix(route_checks.py): raise httpexception
raise expected exceptions
* fix(router.py): handle team only wildcard models
fixes issue where team only wildcard models were not considered during auth checks
* fix(router.py): handle team only wildcard models
fixes issue where team only wildcard models were not considered during auth checks
2025-08-04 23:19:51 -07:00
Ishaan Jaff
ad26cba8b6
add litellm-enterprise==0.1.17
2025-08-04 17:26:50 -07:00
Ishaan Jaff and GitHub
ba1882fdd5
[Bug Fix] Prometheus - fix for litellm_input_tokens_metric, litellm_output_tokens_metric - Note this updates the metric name ( #13271 )
...
* fixes for litellm_tokens_metric
* test_prometheus_token_metrics_with_prometheus_config
2025-08-04 17:22:21 -07:00
Jugal D. Bhatt and GitHub
900c7f45c0
[MCP Gateway] Litellm mcp pre and during guardrails ( #13188 )
...
* add guardrail support
* add guardrail support
* guardrails for MCP
* added changes
* add mcp guardrails
* added test
* add ui
* fix guardrail form
* working with cursor
* remvoe print
* fix mcp servertests
* fix mypy and remove console logs
* fix mypy and remove console logs
* fix mypy tests
2025-08-01 20:02:25 -07:00
Krish Dholakia and GitHub
b7c5073d28
Custom Auth - bubble up custom exceptions ( #13093 )
...
* fix(enterprise/litellm_enterprise/proxy/auth/user_api_key_auth.py): bubble up exception if type is ProxyException
* docs(custom_auth.md): doc on bubbling up custom exceptions
2025-07-29 16:28:25 -07:00
Krish Dholakia and GitHub
d6423d913d
build: update pip package ( #12998 )
2025-07-25 16:23:53 -07:00
Krish Dholakia and GitHub
550211ba47
Prometheus - tags, fix '[tag]="false"' when tag is set ( #12916 )
...
* fix(prometheus.py): sanitize tag-based labels to handle colons (:) and spaces ( )
* fix(prometheus.py): working tag based metrics
* fix(prometheus.py): emit request tags on post call success hook
* fix(prometheus.py): add user agent tags on request failure
* fix(prometheus.py): add request tags to deployment failure metric
s
2025-07-24 16:39:13 -07:00
Ishaan Jaff
bf300f8ca7
Revert "Litellm dev 07 21 2025 p1 ( #12848 )"
...
This reverts commit e4e10aa4ed .
2025-07-22 18:28:36 -07:00
Krish Dholakia and GitHub
e4e10aa4ed
Litellm dev 07 21 2025 p1 ( #12848 )
...
* fix(main.py): fix async retryer
Fixes https://github.com/BerriAI/litellm/issues/12830
* fix(forward_clientside_headers_by_model_group.py): filter out 'content-type' from forwardable headers
clientside content-type != proxy content type, can cause requests to hang
* test(tests/): update tests
2025-07-21 22:09:39 -07:00
Krish Dholakia and GitHub
00677afefe
Litellm batch cost tracking debug ( #12782 )
...
* feat(proxy_server.py): support batch polling interval
allows admin to control batch polling interval (default is 3600s)
easier debugging
* fix(proxy_settings_endpoint.py): ensure value is actually set before updating env var
2025-07-21 20:17:56 -07:00
Ishaan Jaff
96f7eb6f78
bump litellm enterprise version
2025-07-19 10:12:33 -07:00
Ishaan Jaff and GitHub
06574a72b5
[Feat] Backend - Add support for disabling callbacks in request body ( #12762 )
...
* allow using standard_callback_dynamic_params to disable callbacks
* fix is_callback_disabled_dynamically
* test_callback_disabled_via_request_body_multiple
2025-07-19 10:10:30 -07:00
Ishaan Jaff and GitHub
99e2ea081d
[Feat] UI - Allow clicking into Vector Stores ( #12741 )
...
* Add View Vector Store
* add /info for vector store
* fix updated_at
2025-07-18 14:28:57 -07:00
a46b9d376f
[Prometheus] Move Prometheus to enterprise folder ( #12659 )
...
* fix tools fetch for keys
* add promethues to enterprise
* remove old prom
* remove old prom
* fix tests
* safe imports
* add if
* fix enterprise test
* rename imports
* added label import
* added label import
* move tests to enterprise
* fix tests
* add log
* build: update versions
---------
Co-authored-by: Krrish Dholakia <krrishdholakia@gmail.com >
2025-07-18 11:54:47 -07:00
Ishaan Jaff and GitHub
3051a9c68a
[Bug Fix] QA - Use PG Vector Vector Store with LiteLLM ( #12716 )
...
* store in generic litellm params
* handle storing litellm_params_json
* add litellm_params
* update file loc
* fix startup issue
* ui fix litellm_params
* fix typing
* fix adding PG Vector
* use litellm params
* fix transform_search_vector_store_request
* fix transform
* fix URL
* test fix
* test_pg_vector_search_request_construction
2025-07-18 08:41:18 -07:00
Ishaan Jaff and GitHub
95f7290e44
[Feat] Proxy - New LLM API Routes /v1/vector_stores and /v1/vector_stores/vs_abc123/search ( #12699 )
...
* add Search + Create vector stores
* add new vector_stores routes
* add avector_store_search routes
* docs vector stores
* docs vector stores
* Create Vector Store
* fix - refactor
* add vector_store_router
* fix imports
* fix ruff
2025-07-17 11:19:25 -07:00
yeahyung and GitHub
782969bb05
( #11794 ) use upsert for managed object table rather than create to avoid UniqueViolationError ( #11795 )
...
* (#11794 ) use upsert for managed object table rather than create to avoid UniqueViolationError
* (#11794 ) use upsert for managed object table rather than create to avoid UniqueViolationError
2025-07-15 20:20:01 -07:00
Krish Dholakia and GitHub
7c392475e6
Control Plane + Data Plane support ( #12601 )
...
* feat(route_checks.py): allow admin to disable proxy management endpoints on instance
useful for preventing multiple instances from doing admin actions
* docs(scaling_multiple_instances.md): add architecture doc on scaling multiple litellm instances
provide guidance on scaling proxy
* docs(scaling_multiple_instances.md): add doc on scaling across multiple regions for litellm
* fix(route_checks.py): allow disabling llm api endpoints on an instance
allows pure admin instance to exist
* refactor(enterprise/route_checks.py): refactor env var checks
* refactor: finish refactoring
* docs(control_plane_and_data_plane.md): refactor docs
* test: update tests
2025-07-14 21:31:56 -07:00
Ishaan Jaff and GitHub
57b0b4edf3
[Bug fix] [Bug]: Verbose log is enabled by default ( #12596 )
...
* test find_set_verbose_assignments
* fix set verbose
* test set verbose
* fix unused import
2025-07-14 20:06:16 -07:00
Ishaan Jaff
08ce596c55
bump litellm enterprise pkg
2025-07-12 18:31:52 -07:00
Krrish Dholakia
8b4673fe84
build(ui/): UI - Public Model Hub v2 ( #12532 )
...
Closes https://github.com/BerriAI/litellm/pull/12532
2025-07-11 22:24:31 -07:00
Krish Dholakia and GitHub
569ddde9fe
[Enterprise] Support tag based mode for guardrails ( #12508 )
...
* feat(custom_guardrail.py): allow admin to run guardrails on specific modes based on request tags
Enables pre-call checks for openwebui but logging for claude code guardrails
* refactor(custom_guardrail.py): move tag based mode to enterprise
* test(test_custom_guardrail.py): update test
* feat(quick_start.md): add doc on tag-based guardrail mode
* docs(quick_start.md): cleanup doc
* docs: cleanup
* docs(openweb_ui.md): add tutorial to doc
* fix(custom_guardrail.py): ensure user is premium user
* test: update test
2025-07-10 22:27:30 -07:00
Ishaan Jaff
a37dacb770
bump to litellm-enterprise==0.1.12
2025-07-09 18:35:28 -07:00
Ishaan Jaff and GitHub
17ea770ab5
[Feat] SSO - Allow users to run a custom sso login handler ( #12465 )
...
* fix return_ui_sso_redirect_response_after_sign_in
* add CustomSSOLoginHandler
* add handle_custom_ui_sso_sign_in
* fix handle_custom_ui_sso_sign_in
* fixes for /sso/key/generate
* add test_handle_custom_ui_sso_sign_in_success
* fixed for loading config
* add example custom handler
* test_custom_ui_sso_sign_in_handler_config_loading
* docs - custom sso
* move to enterprise folder
* EnterpriseCustomSSOHandler
* handle_custom_ui_sso_sign_in
* docs custom sso
* docs sso
* docs custom sso
* get_redirect_response_from_openid
* fix mock tests
2025-07-09 16:36:30 -07:00
Jugal D. Bhatt and GitHub
d55712b783
Add MCP url masking on frontend ( #12247 )
...
* add url masking on frontend
* fix test
* add signature
2025-07-02 16:32:26 -07:00
Ishaan Jaff
1ce71d6d61
bump litellm-enterprise = {version = "0.1.11", optional = true}
2025-07-02 15:00:28 -07:00
Jugal Bhatt
e53eb6eb37
change logger
2025-07-01 16:28:53 -07:00
Jugal Bhatt
7e6d27e6c3
change logger
2025-07-01 16:28:34 -07:00
Jugal Bhatt
fefc5fc33a
add warning message for non premium users
2025-07-01 16:27:31 -07:00
Jugal Bhatt
b63d64dcf5
add subject and signature tests
2025-07-01 15:15:40 -07:00
Jugal Bhatt
69670001de
email_templates
2025-07-01 14:34:15 -07:00
Ishaan Jaff
a021e7cb9d
bump poetry
2025-06-28 21:16:52 -07:00
Ishaan Jaff and GitHub
cfc07f361b
[Bug Fix] Invite links email should contain the correct invite id ( #12130 )
...
* use common helper create_invitation_for_user
* use common util in proxy
* fix create_invitation_for_user
* refactor base email
* test_get_invitation_link_creates_new_when_none_exist
* fix code QA checks
2025-06-28 09:19:32 -07:00
Krish Dholakia and GitHub
d895ae827d
Litellm batch api background cost calc ( #12125 )
...
* feat(check_batch_cost.py): emit spend log on successful request
ensures cost tracked for batch requests
* feat(proxy_server.py): add background job to poll completed batch jobs
used for calculating cost for batch jobs
* fix(proxy_server.py): run batch cost tracking job every hour
batch jobs take time to complete, no need to run every few seconds
* feat(proxy_server.py): run batch cost tracking job every hour
2025-06-27 21:46:25 -07:00
Krrish Dholakia
c3857e60f2
Store batch output file id in DB + Store batch file status in DB + (experimental) BATCH API COST TRACKING
2025-06-25 22:41:22 -07:00