* Azure LLM: fix passing through of azure_ad_token_provider parameter
* add test
---------
Co-authored-by: Clara Luise Pohland <clara-luise.pohland@telekom.de>
* fix(caching_handler.py): fix embedding str caching result
Fixes issue where str caching results were not being correctly assembled on str input
* feat(azure/image_generation): Support dropping response_format for azure gpt-image-1
Fixes LIT-118
* test(test_utils.py): add unit testing
* test: rename file to avoid testing conflict
* Add management client docs
* Docs enhancements
* Add "proxy/management_cli" to sidebar
* Small formatting changes
* Add overview table
* Wrap long line
* Add "Quick Start" section
* Document uv tool upgrade and uninstall
* Add blank lines to eliminate yellow squigglies in VS Code
* For each section link to section on swagger used
* Wrap some long command examples
* Break long http request command on to multiple lines
* Add --version flag to litellm-proxy CLI
```shell
$ litellm-proxy --version
litellm-proxy version: 1.68.1
```
* Return both client and server version
* Update docs
* Add a test for the version command
* Add litellm/proxy/client/health.py
* [FIX] Update token fields in schema.prisma to use BigInt for improved handling of large values across LiteLLM models.
* [FIX] revert SpendLogs back to Int
* fix support for python 3.11-
3.11 introduced datetime.UTC, this provides a fallback for 3.11-
* use litellm.utils.get_utc_datetime
* remove unused timezone import
Co-authored-by: Matthew Farrellee <matt@cs.wisc.edu>
* test(base_llm_unit_tests.py): return '<thinking>' tag in response content
* fix(converse_transformation.py): extract `<thinking>` block from nova tool use response
Fixes https://github.com/BerriAI/litellm/issues/9063
* fix(factory.py): handle non-signature reasoning blocks to bedrock
pass as text input - bedrock raises ""User messages cannot contain reasoning content. Please remove the r
easoning content and try again." otherwise
* fix(main.py): Add drop params support for gpt
Fixes https://github.com/BerriAI/litellm/issues/10501
* fix(converse_transformation.py): fix linting error
* fix(utils.py): fix linting error
* test: cleanup test
* test: skip test until we have bedrock prompt caching permission
* fix(user_api_key_auth.py): add 'headers' to constructed request for websocket
Fix issue on some datastructure versions which require a headers field in scope
* test(test_user_api_key_auth.py): add unit testing for headers in scope change
* fix(router.py): migrate `_arealtime` to generic router endpoint
Fix infinite loop on model name missing for realtime api calls
* test(test_router_helper_utils.py): cleanup test post refactor
* added status filtering on logs
* added model filter
* fix linter
* fix model filtering
* modified status filter to use status column from LiteLLM_SpendLogs
* remove json import
* Add support for nscale provider
* Add image generation support and fix unit tests
* Add docs for nscale
* Fix unit test import issues
* Minor doc improvement
* Remove redundant null tokens from model cost map
* Address PR review comments for doc updates
* Revert changes to large text
* Try to add prints
* more print
* fix print
* batch debugging
* Change batch size
* Revert "Change batch size"
This reverts commit af16d8635f17e3928da9000bb9fec5b0af920816.
* Look into periodic task problems
* Fix missing periodic in slack init
* Initialize periodic flush on startup
* Log update_values
* more logging
* Fix startup
* Cleanup change
* Add a unit test for the change
* Renamed and moved to standard
* Merging in with new test
* comment change
* Extend the timeout because normal runs are over 5 min
* refactor(managed_files.py): move enterprise feature into enterprise folder
prevent unexpected surprises
* refactor: safely handle enterprise hooks
* fix: fix ruff check errors
* fix(files_endpoints.py): cleanup enterprise code from OSS
* refactor: complete cleanup
* fix(managed_files.py): complete cleanup
* fix(managed_files.py): instrument to be able to update deployment values post-router selection and just before making llm call
* fix(managed_files.py): instrument to be able to update deployment values post-router selection and just before making llm call
* fix: fix linting error
* fix: fix linting error
* MCP Server DB Schema (#10634)
* feat: initial mcp db schema
* user -> team table for mcp_servers
* remove mcp_servers from team and verificationtoken tables
---------
Co-authored-by: wagnerjt <wagnerjt@github.com>
* add mcp table
* Team and Key Object Permission table for MCP Servers (#10643)
* feat: initial mcp db schema
* user -> team table for mcp_servers
* remove mcp_servers from team and verificationtoken tables
* adding ObjectPermissionTable relationship for mcpservers
* fix: object_permission_id and added relationship to User and Organization tables
---------
Co-authored-by: wagnerjt <wagnerjt@github.com>
* migration file - add_mcp_key_team_permission_mgmt
---------
Co-authored-by: Tyler Wagner <wagnerjt@users.noreply.github.com>
Co-authored-by: wagnerjt <wagnerjt@github.com>
