Ishaan Jaff
bc311b7a47
ui logs - view messages / responses
2025-01-17 20:20:49 -08:00
Krish Dholakia and GitHub
80f7af510b
Improve Proxy Resiliency: Cooldown single-deployment model groups if 100% calls failed in high traffic ( #7823 )
...
* refactor(_is_cooldown_required): move '_is_cooldown_required' into cooldown_handlers.py
* refactor(cooldown_handlers.py): move cooldown constants into `.constants.py`
* fix(cooldown_handlers.py): remove if single deployment don't cooldown logic
move to traffic based cooldown logic
Addresses https://github.com/BerriAI/litellm/issues/7822
* fix: add unit tests for '_should_cooldown_deployment'
* test: ensure all tests pass
* test: update test
* fix(cooldown_handlers.py): don't cooldown single deployment models for anything besides traffic related errors
* fix(cooldown_handlers.py): fix cooldown handler logic
* fix(cooldown_handlers.py): fix check
2025-01-17 20:17:02 -08:00
Krish Dholakia and GitHub
d00febcdaa
/key/delete - allow team admin to delete team keys (#7846 )
...
* fix(key_management_endpoints.py): fix key delete to allow team admins + other proxy admins to delete keys
Fixes https://github.com/BerriAI/litellm/issues/7760
* fix(key_management_endpoints.py): remove unused variables
* fix(key_management_endpoints.py): fix linting error
2025-01-17 20:16:12 -08:00
Krish Dholakia and GitHub
c4ff0b6487
refactor: make bedrock image transformation requests async ( #7840 )
...
* refactor: initial commit for using separate sync vs. async transformation routes for bedrock
ensures no blocking calls e.g. when converting image url to b64
* perf(converse_transformation.py): make bedrock converse transformation async
asyncify's the bedrock message transformation - useful for handling image urls for bedrock
* fix(converse_handler.py): fix logging for async streaming
* style: cleanup unused imports
2025-01-17 20:14:15 -08:00
Ishaan Jaff
2f6829fd2a
ui - new build
2025-01-17 20:07:06 -08:00
Ishaan Jaff
b701fe1f5e
view logs
2025-01-17 20:05:25 -08:00
Krish Dholakia and GitHub
71c41f8f33
QA: ensure all bedrock regional models have same supported_ as base + Anthropic nested pydantic object support ( #7844 )
...
* build: ensure all regional bedrock models have same supported values as base bedrock model
prevents drift
* test(base_llm_unit_tests.py): add testing for nested pydantic objects
* fix(test_utils.py): add test_get_potential_model_names
* fix(anthropic/chat/transformation.py): support nested pydantic objects
Fixes https://github.com/BerriAI/litellm/issues/7755
2025-01-17 19:49:12 -08:00
Ishaan Jaff
62188a01b0
bump: version 1.58.4 → 1.59.0
2025-01-17 19:35:15 -08:00
Ishaan Jaff and GitHub
2c117264a2
[Hashicorp - secret manager] - use vault namespace for tls auth ( #7834 )
...
* hcorp - use x-vault-namespace
* _get_tls_cert_auth_body
* HCP_VAULT_CERT_ROLE
* test_hashicorp_secret_manager_tls_cert_auth
* HCP_VAULT_CERT_ROLE
2025-01-17 19:27:56 -08:00
Ishaan Jaff
69d876f4c7
ui new build
2025-01-17 19:23:41 -08:00
Ishaan Jaff
f54e662c57
rename ui tab to ExperimentOutlined
2025-01-17 19:22:32 -08:00
Ishaan Jaff
6d1a5a0e5d
ui new build
2025-01-17 19:14:44 -08:00
Ishaan Jaff and GitHub
a489c5d95a
[fix dd llm obs] - use env vars for setting dd tags, service name ( #7835 )
...
* fix custom logger
* fix debugging dd llm obs
2025-01-17 18:57:16 -08:00
Ishaan Jaff and GitHub
d3c2f4331a
(UI - View SpendLogs Table) ( #7842 )
...
* litellm log messages / responses
* add messages/response to schema.prisma
* add support for logging messages / responses in DB
* test_spend_logs_payload_with_prompts_enabled
* _get_messages_for_spend_logs_payload
* ui_view_spend_logs endpoint
* add tanstack and moment
* add uiSpendLogsCall
* ui view logs table
* ui view spendLogs table
* ui_view_spend_logs
* fix code quality
* test_spend_logs_payload_with_prompts_enabled
* _get_messages_for_spend_logs_payload
* test_spend_logs_payload_with_prompts_enabled
* test_spend_logs_payload_with_prompts_enabled
* ui view spend logs
* minor ui fix
* ui - update leftnav
* ui - clean up ui
* fix leftnav
* ui fix navbar
* ui fix moving chat ui tab
2025-01-17 18:53:45 -08:00
Krish Dholakia and GitHub
a99deb6d0a
fix(key_management_endpoints.py): fix default allowed team member roles ( #7843 )
...
admin and user, not admin and member
2025-01-17 17:15:22 -08:00
yujonglee and GitHub
7584369fbe
add key and team level budget ( #7831 )
2025-01-17 09:04:12 -08:00
Ishaan Jaff
7cfda2fb76
bump: version 1.58.3 → 1.58.4
v1.58.4
2025-01-17 08:29:13 -08:00
Ishaan Jaff
2d5f8ea2c6
Revert "fix custom logger"
...
This reverts commit 9d2707ecfe .
2025-01-17 08:26:59 -08:00
Ishaan Jaff
9d2707ecfe
fix custom logger
2025-01-17 07:39:49 -08:00
Ishaan Jaff
632ba92af1
Revert "fix: fix test"
...
This reverts commit 0642a78abb .
2025-01-17 07:21:19 -08:00
Ishaan Jaff
b30e05b54f
Revert "test_completion_mistral_api_mistral_large_function_call"
...
This reverts commit ef9177f0a8 .
2025-01-17 07:20:46 -08:00
Krrish Dholakia
0642a78abb
fix: fix test
2025-01-17 07:16:32 -08:00
Ishaan Jaff
15e0a605e4
_handle_tool_call_message linting
2025-01-16 22:34:16 -08:00
Ishaan Jaff
c8febaca2e
test_watsonx_token_in_env_var
2025-01-16 22:28:37 -08:00
Ishaan Jaff
7f63e7c15a
test_completion_mistral_api_mistral_large_function_call
2025-01-16 22:27:48 -08:00
Ishaan Jaff and GitHub
f3268b6b06
sec fix minor ( #7810 )
2025-01-16 22:03:28 -08:00
Ishaan Jaff and GitHub
9b944ca60c
(Fix + Testing) - Add dd-trace-run to litellm ci/cd pipeline + fix bug caused by dd-trace patching OpenAI sdk ( #7820 )
...
* add dd trace to e2e docker run tests
* update dd trace v
* fix entrypoint
* dd trace fixes
* proxy_build_from_pip_tests
* build python3.13
* use py 3.13
* fix build from pip
* dd trace fix
* proxy_build_from_pip_tests
* bump build from pip
2025-01-16 22:03:09 -08:00
Ishaan Jaff and GitHub
b492551d3d
(fix) IBM Watsonx using ZenApiKey ( #7821 )
...
* ibm watsonx fix
* test ZenAPIKey
* fix zenapikey
2025-01-16 22:02:36 -08:00
Ishaan Jaff and GitHub
939e1c9b19
(datadog llm observability) - fixes + improvements for using datadog llm observability logging integration ( #7824 )
...
* dd llm obs fixes
* _ensure_string_content
* fix _get_dd_llm_obs_payload_metadata
2025-01-16 22:02:24 -08:00
Ishaan Jaff
5b36985c00
run ci/cd again
2025-01-16 22:02:03 -08:00
Ishaan Jaff
ef9177f0a8
test_completion_mistral_api_mistral_large_function_call
2025-01-16 21:50:56 -08:00
Ishaan Jaff
117256d264
test_async_vertexai_streaming_response
2025-01-16 21:45:12 -08:00
Ishaan Jaff
de41abeace
llama-v3p1-8b-instruct
2025-01-16 21:34:42 -08:00
Ishaan Jaff
5458a2ff33
fireworks ai use llama-v3p1-8b-instruct
2025-01-16 21:28:44 -08:00
Krrish Dholakia
8ab1335ae0
test: fix unit test
2025-01-16 21:11:17 -08:00
Ishaan Jaff
2f38e72026
test commit on main
2025-01-16 20:52:55 -08:00
Krish Dholakia and GitHub
4ec2c2c8e4
build: bump certifi version - see if that fixes asyncio ssl issue on python 3.13 ( #7800 )
2025-01-15 22:02:45 -08:00
Krish Dholakia and GitHub
c57266c9dc
test: initial commit enforcing testing on all anthropic pass through … ( #7794 )
...
* test: initial commit enforcing testing on all anthropic pass through functions
prevents future regressions
* test(test_unit_test_anthropic_pass_through.py): add unit test for '_get_user_from_metadata' function
* test(test_unit_test_anthropic_passthrough.py): add unit test for handle_logging_anthropic_collected_chunks
* test(test_unit_test_anthropic_pass_through): add coverage for all anthropic pass through functions
2025-01-15 22:02:35 -08:00
Krish Dholakia and GitHub
843cd3b7c6
test: initial test to enforce all functions in user_api_key_auth.py h… ( #7797 )
...
* test: initial test to enforce all functions in user_api_key_auth.py have direct testing
* test(test_user_api_key_auth.py): add is_allowed_route unit test
* test(test_user_api_key_auth.py): add more tests
* test(test_user_api_key_auth.py): add complete testing coverage for all functions in `user_api_key_auth.py`
* test(test_db_schema_changes.py): add a unit test to ensure all db schema changes are backwards compatible
gives user an easy rollback path
* test: fix schema compatibility test filepath
* test: fix test
2025-01-15 21:52:45 -08:00
d4ed985173
Add back in non root image fixes ( #7781 ) ( #7795 )
...
* Add back in non root image fixes (#7781 )
* Add back in non root image fixes
* Fix dockerfile
* Fix perms
* Add in container structure tests for the nonroot image (#7796 )
* feat(helm): add securityContext and pull policy values to migration job (#7652 )
* fix(helm): corrected indentation in migration-job.yaml
* feat(helm): add securityContext and pull policy values to migration job
* fix confusing save button label (#7778 )
* [integrations/lunary] Improve Lunary documentaiton (#7770 )
* update lunary doc
* better title
* tweaks
* Update langchain.md
* Update lunary_integration.md
* Fix wrong URL for internal user invitation (#7762 )
* format
* done
* Update instructor tutorial (#7784 )
* Add in container structure tests for the nonroot image
---------
Co-authored-by: Zackeus Bengtsson <32719220+Hexoplon@users.noreply.github.com >
Co-authored-by: yujonglee <yujonglee.dev@gmail.com >
Co-authored-by: Hugues Chocart <chocart.hugues@icloud.com >
Co-authored-by: Nikolaiev Dmytro <dima.nikol.99@gmail.com >
---------
Co-authored-by: Rajat Vig <rajatvig@users.noreply.github.com >
Co-authored-by: Zackeus Bengtsson <32719220+Hexoplon@users.noreply.github.com >
Co-authored-by: yujonglee <yujonglee.dev@gmail.com >
Co-authored-by: Hugues Chocart <chocart.hugues@icloud.com >
Co-authored-by: Nikolaiev Dmytro <dima.nikol.99@gmail.com >
2025-01-15 21:49:03 -08:00
Krish Dholakia and GitHub
80d6bbec29
Litellm dev 01 14 2025 p2 ( #7772 )
...
* feat(pass_through_endpoints.py): fix anthropic end user cost tracking
* fix(anthropic/chat/transformation.py): use returned provider model for anthropic
handles anthropic `-latest` tag in request body throwing cost calculation errors
ensures we can be accurate in our model cost tracking
* feat(model_prices_and_context_window.json): add gemini-2.0-flash-thinking-exp pricing
* test: update test to use assumption that user_api_key_dict can get anthropic user id
* test: fix test
* fix: fix test
* fix(anthropic_pass_through.py): uncomment previous anthropic end-user cost tracking code block
can't guarantee user api key dict always has end user id - too many code paths
* fix(user_api_key_auth.py): this allows end user id from request body to always be read and set in auth object
* fix(auth_check.py): fix linting error
* test: fix auth check
* fix(auth_utils.py): fix get end user id to handle metadata = None
2025-01-15 21:34:50 -08:00
Ishaan Jaff and GitHub
4081aeb15e
(helm) - allow specifying envVars on values.yaml + add helm lint test ( #7789 )
...
* litellm use envVars values.yaml
* fix values.yaml
* add helm lint to ci/cd pipeline
* working values.yaml
* add helm tests to ci/cd
* fix helm chart testing
* update helm tests
* fix helm test
* fix use test values in ci
* fix busy box testing on helm
* fix test-values.yaml
* update helm tests
* fix test connection
2025-01-15 21:11:17 -08:00
Nikolaiev Dmytro and GitHub
7b45349145
Update instructor tutorial ( #7784 )
2025-01-15 15:10:50 -08:00
yujonglee and GitHub
503b38e609
Fix wrong URL for internal user invitation ( #7762 )
...
* format
* done
2025-01-15 15:10:32 -08:00
Hugues Chocart and GitHub
6fff77d131
[integrations/lunary] Improve Lunary documentaiton ( #7770 )
...
* update lunary doc
* better title
* tweaks
* Update langchain.md
* Update lunary_integration.md
2025-01-15 15:00:25 -08:00
yujonglee and GitHub
01357add4d
fix confusing save button label ( #7778 )
2025-01-15 13:51:07 -08:00
Zackeus Bengtsson and GitHub
801f450e8c
feat(helm): add securityContext and pull policy values to migration job ( #7652 )
...
* fix(helm): corrected indentation in migration-job.yaml
* feat(helm): add securityContext and pull policy values to migration job
2025-01-15 12:51:08 -08:00
Krrish Dholakia
8c26e1a66d
build: bump: version 1.58.2 → 1.58.3
2025-01-15 07:46:57 -08:00
Krish Dholakia and GitHub
fe60a38c8e
Litellm dev 01 2025 p4 ( #7776 )
...
* fix(gemini/): support gemini 'frequency_penalty' and 'presence_penalty'
Closes https://github.com/BerriAI/litellm/issues/7748
* feat(proxy_server.py): new env var to disable prisma health check on startup
* test: fix test
2025-01-14 21:49:25 -08:00
Krish Dholakia and GitHub
8353caa485
build(pyproject.toml): bump uvicorn depedency requirement ( #7773 )
...
* build(pyproject.toml): bump uvicorn depedency requirement
Fixes https://github.com/BerriAI/litellm/issues/7768
* fix(anthropic/chat/transformation.py): fix is_vertex_request check to actually use optional param passed in
Fixes https://github.com/BerriAI/litellm/issues/6898#issuecomment-2590860695
* fix(o1_transformation.py): fix azure o1 'is_o1_model' check to just check for o1 in model string
https://github.com/BerriAI/litellm/issues/7743
* test: load vertex creds
2025-01-14 21:47:11 -08:00