Merged
Conversation
This reverts commit 2835d3a3743e6411b9914a0b01381050e2273ad7.
- Adjusted input and output cost per token for existing models. - Added new model configuration for "openrouter/qwen/qwen3-coder" with specified token limits and costs.
If the user specified in the configuration e.g. "user_header_name: X-OpenWebUI-User-Email", here we were looking for a dict key "X-OpenWebUI-User-Email" when the dict actually contained "x-openwebui-user-email". Switch to iteration and case insensitive string comparison instead to fix this. This fixes customer budget enforcement when the customer ID is passed in as a header rather than as a "user" value in the body.
…viously "fix" guards had no effect in llmOutput mode. (#12891)
* fix(router.py): return global retry policy on `get/config/callbacks` Partial fix for BerriAI/litellm#12855 * fix(model_dashboard.tsx): accept global retry policy Fixes BerriAI/litellm#12855 * fix(model_dashboard.tsx): update global retry policy, if that's what was edited
* fix(custom_guardrail.py): initial logic for model level guardrails * feat(custom_guardrail.py): working pre call guardrails * fix(custom_guardrails.py): check if custom guardrails set before running event hook * test(test_custom_guardrail.py): add unit tests for async pre call deployment hook on custom guardrail * feat(custom_guardrail.py): add post call processing support for guardrails allows model based guardrails to run on the post call event for that model only * fix(utils.py): only run if call type is in enum * test: update unit tests to work
… package - used for pushing dev releases (#12985) * build(github/manual_pypi_publish.yml): manual workflow to publish pip package - used for pushing dev releases * ci: remove redundant file
* add bytedance model * add source
* clean and verify key * change checking logic * Add unit test
* fix query params for realtime api intent * fix my py * Add typed dict * remove typed dict * fix comments * add test * add test * added proxt log revert * add real time q params
enables guardrails to work with streaming
…ils post call hook ensures streaming guardrails are actually useful
* fix + test * remove test comments * fix mypy * fix mypy * fix tests
* added check option * Add underline * make less verbosE
…_identifier` supported params (#13258) * test_aresponses_service_tier_and_safety_identifier * add service_tier + safety_identifier * fix get_supported_openai_params * add safety_identifier + service_tier for responses()
…` (#13260) * add _transform_responses_api_function_call_to_chat_completion_message * test_responses_api_with_tool_calls * TestFunctionCallTransformation * fixes for responses API testing google ai studio * TestGoogleAIStudioResponsesAPITest * test_responses_api_with_tool_calls * test_responses_api_with_tool_calls * test_basic_openai_responses_streaming_delete_endpoint
…13267) * bug fix serve_login_page * test_serve_login_page_server_root_path
* create OCI required files * request and response conversion for non-streaming chat * support tool calling with OCI generic API without streaming * adaptation of api call for generic and cohere format * include tool calls and responses in generic api and dropping support for cohere * fix invalid content-length error * support streaming for generic api * fix auth error when using acompletion with streaming * refactor: use base_llm_http_handler and include API type definitions * update types and add type safety in different methods * fix OCIFunction format * create custom stream wrapper for decoding OCI stream * remove unused files * create unit tests for OCI * lint the code * remove manual test * docs: update the docs to include OCI
… (#13045) * Fix: Langfuse reporting "client closed" error due to httpx client TTL * remove log
…m_output_tokens_metric` - Note this updates the metric name (#13271) * fixes for litellm_tokens_metric * test_prometheus_token_metrics_with_prometheus_config
* added model id endpoint * fix test * add route to internal users * make the functions reusable * fixed mypy
* update model alias on keys * team model aliases * fix model aliases * fixes for teams
* fix(types/llms/oci.py): fix linting errors * fix(oci.py): fix linting error * fix(oci.py): fix linting errors * fix: fix linting error * fix: fix linting error
…or '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
* fix(main.py): handle tool being a pydantic object Fixes BerriAI/litellm#13064 * fix(prompt_templates/common_utils.py): fix unpack defs deepcopy issue Fixes BerriAI/litellm#13151 * fix(utils.py): handle tools is none
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
20 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Title
Relevant issues
Pre-Submission checklist
Please complete all items before asking a LiteLLM maintainer to review your PR
tests/litellm/directory, Adding at least 1 test is a hard requirement - see detailsmake test-unitType
🆕 New Feature
🐛 Bug Fix
🧹 Refactoring
📖 Documentation
🚄 Infrastructure
✅ Test
Changes