* feat: initial commit - enable dev to see translated request
* feat(utils.py): expose new endpoint - `/utils/transform_request` to see the raw request sent by litellm
* feat(transform_request.tsx): allow user to see their transformed request
* refactor(litellm_logging.py): return raw request in 3 parts - api_base, headers, request body
easier to render each individually on UI vs. extracting from combined string
* feat: transform_request.tsx
working e2e raw request viewing
* fix(litellm_logging.py): fix transform viewing for bedrock models
* fix(litellm_logging.py): don't return sensitive headers in raw request headers
prevent accidental leak
* feat(transform_request.tsx): style improvements
* fix(anthropic_claude3_transformation.py): fix amazon anthropic claude 3 tool calling transformation on invoke route
move to using anthropic config as base
* fix(utils.py): expose anthropic config via providerconfigmanager
* fix(llm_http_handler.py): support json mode on async completion calls
* fix(invoke_handler/make_call): support json mode for anthropic called via bedrock invoke
* fix(anthropic/): handle 'response_format: {"type": "text"}` + migrate amazon claude 3 invoke config to inherit from anthropic config
Prevents error when passing in 'response_format: {"type": "text"}
* test: fix test
* fix(utils.py): fix base invoke provider check
* fix(anthropic_claude3_transformation.py): don't pass 'stream' param
* fix: fix linting errors
* fix(converse_transformation.py): handle response_format type=text for converse
* feat(organization_endpoints.py): expose new `/organization/delete` endpoint. Cascade org deletion to member, teams and keys
Ensures any org deletion is handled correctly
* test(test_organizations.py): add simple test to ensure org deletion works
* feat(organization_endpoints.py): expose /organization/update endpoint, and define response models for org delete + update
* fix(organizations.tsx): support org delete on UI + move org/delete endpoint to use DELETE
* feat(organization_endpoints.py): support `/organization/member_update` endpoint
Allow admin to update member's role within org
* feat(organization_endpoints.py): support deleting member from org
* test(test_organizations.py): add e2e test to ensure org member flow works
* fix(organization_endpoints.py): fix code qa check
* fix(schema.prisma): don't introduce ondelete:cascade - breaking change
* docs(organization_endpoints.py): document missing params
* refactor(organization_view.tsx): initial commit creating a generic update member component shared between org and team member classes
* feat(organization_view.tsx): support updating org member role on UI
* feat(organization_view.tsx): allow proxy admin to delete members from org
* refactor(organization.tsx): initial commit with orgs tab refactor
make it similar to 'Teams' tab - simplifies org management actions
* fix(page.tsx): pass user orgs to component
* fix(organization_view.tsx): fix to pull info from org info endpoint
* feat(organization_endpoints.py): return org members when calling /org/info
* fix(organization_view.tsx): show org members on info page
* feat(organization_view.tsx): allow adding user to org via user email
Resolves https://github.com/BerriAI/litellm/issues/8330
* fix(organization_endpoints.py): raise better error when duplicate user_email found in db
* fix(organization_view.tsx): cleanup user_email for now
not in initial org info - will need to prefetch
* fix(page.tsx): fix getting user models on page load
allows passing down the user models to org
* fix(organizations.tsx): fix creating org on ui
* fix(proxy/_types.py): include org created at and updated at
cleans up ui
* fix(navbar.tsx): cleanup
* fix(organizations.tsx): fix tpm/rpm limits on org
* fix(organizations.tsx): fix linting error
* fix(organizations.tsx): fix linting \
* (Feat) - Add `/bedrock/meta.llama3-3-70b-instruct-v1:0` tool calling support + cost tracking + base llm unit test for tool calling (#8545)
* Add support for bedrock meta.llama3-3-70b-instruct-v1:0 tool calling (#8512)
* fix(converse_transformation.py): fixing bedrock meta.llama3-3-70b tool calling
* test(test_bedrock_completion.py): adding llama3.3 tool compatibility check
* add TestBedrockTestSuite
* add bedrock llama 3.3 to base llm class
* us.meta.llama3-3-70b-instruct-v1:0
* test_basic_tool_calling
* TestAzureOpenAIO1
* test_basic_tool_calling
* test_basic_tool_calling
---------
Co-authored-by: miraclebakelaser <65143272+miraclebakelaser@users.noreply.github.com>
* fix(general_settings.tsx): filter out empty dictionaries post fallback delete (#8550)
Fixes https://github.com/BerriAI/litellm/issues/8331
* bump: version 1.61.3 → 1.61.4
* (perf) Fix memory leak on `/completions` route (#8551)
* initial mem util test
* fix _cached_get_model_info_helper
* test memory usage
* fix tests
* fix mem usage
---------
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: miraclebakelaser <65143272+miraclebakelaser@users.noreply.github.com>
* fix(key_management_endpoints.py): fix `/key/list` to include `return_full_object` as a top-level query param
Allows user to specify they want the keys as a list of objects
* refactor(key_list.tsx): initial refactor of key table in user dashboard
offloads key filtering logic to backend api
prevents common error of user not being able to see their keys
* fix(key_management_endpoints.py): allow internal user to query `/key/list` to see their keys
* fix(key_management_endpoints.py): add validation checks and filtering to `/key/list` endpoint
allow internal user to see their keys. not anybody else's
* fix(view_key_table.tsx): fix issue where internal user could not see default team keys
* fix: fix linting error
* fix: fix linting error
* fix: fix linting error
* fix: fix linting error
* fix: fix linting error
* fix: fix linting error
* fix: fix linting error
* Fixed issue #8246 (#8250)
* Fixed issue #8246
* Added unit tests for discard() and for remove_callback_from_list_by_object()
* fix(openai.py): support dynamic passing of organization param to openai
handles scenario where client-side org id is passed to openai
---------
Co-authored-by: Erez Hadad <erezh@il.ibm.com>
* fix(caching_routes.py): mask redis password on `/cache/ping` route
* fix(caching_routes.py): fix linting erro
* fix(caching_routes.py): fix linting error on caching routes
* fix: fix test - ignore mask_dict - has a breakpoint
* fix(azure.py): add timeout param + elapsed time in azure timeout error
* fix(http_handler.py): add elapsed time to http timeout request
makes it easier to debug how long request took before failing
