* fix(volcengine): handle thinking disabled parameter properly
When thinking is set to {"type": "disabled"} in volcengine provider config,
skip adding the parameter to extra_body entirely instead of passing it through.
This prevents "thinking: undefined" from appearing in request logs.
Fixes#13039
* test(volcengine): fix and enhance thinking parameter tests
- Fixed existing test that expected broken behavior
- Added comprehensive test coverage for all thinking parameter scenarios:
* thinking disabled → omitted from extra_body
* thinking enabled → included in extra_body
* thinking None → included in extra_body as None
* custom thinking values → included in extra_body
* no thinking parameter → empty result
All tests passing, verifying the fix for issue #13039
- Renamed `AmazonAnthropicClaude3MessagesConfig` to `AmazonAnthropicClaudeMessagesConfig` in the test file to align with recent refactoring.
- Adjusted the instantiation of the configuration class in the test to reflect the new naming convention.
- Updated test cases to use the renamed `AmazonAnthropicClaudeConfig` instead of `AmazonAnthropicClaude3Config` for consistency with recent changes.
- Adjusted imports and assertions in test files to reflect the new configuration class name.
- Renamed `AmazonAnthropicClaude3Config` and `AmazonAnthropicClaude3MessagesConfig` to `AmazonAnthropicClaudeConfig` and `AmazonAnthropicClaudeMessagesConfig` respectively for consistency.
- Implemented `get_anthropic_beta_from_headers` function to extract and handle `anthropic-beta` headers across various transformations.
- Updated request transformations in `AmazonConverseConfig` and `AmazonInvokeConfig` to include `anthropic_beta` parameters based on user headers.
- Added tests to ensure proper handling of `anthropic_beta` headers in different scenarios.
* Remove litellm_params.client_secret from /model/info
Added pop of client_secret (Azure provider secret) from litellm_params in remove_sensitive_info_from_deployment used by /model/info endpoints
* Added test for litellm.proxy.common_utils.openai_endpoint_utils.remove_sensitive_info_from_deployment
* fix(litellm_proxy/chat/transformation.py): support 'user' and all other openai chat completion params
Fixes issue where 'user' was not being sent in request to litellm proxy via sdk
* fix(prisma_migration.py): remove 'use_prisma_migrate' flag, is now default
* docs: cleanup docs
* fix(proxy_cli.py): remove --use_prisma_migrate flag
* refactor: remove references to use_prisma_migrate env var
This is now the default flow for db migrations
* Added access_groups and description fields to MCPServerManager for better server configuration.
* Implemented tests to verify integration of config-based servers with database servers, ensuring correct handling of access_groups and description.
* Updated add_update_server method to accommodate new fields and validate server addition in the registry.
* feat: add CometAPI support with config, error handling and tests
* fix: specify type for extra_body in CometAPIConfig
---------
Signed-off-by: NULL <129579691+TensorNull@users.noreply.github.com>
Updated the chunk_parser method to return a ModelResponseStream when handling 'thinking' field content, allowing UIs to render reasoning information. Adjusted tests to verify the new behavior, ensuring that reasoning content is correctly returned in the response.
* fix(router.py): support base model for model group usage
allows model group info to show accurate cost information for azure models
* fix(router.py): fix changes
* test: add unit tests
* build(pyproject.toml): bump openai version requirements
support custom tool from responses api
Closes https://github.com/BerriAI/litellm/issues/13391
* docs(responses_api.md): add verbosity + free-form function calling parameters
* docs(responses_api.md): add cfg + minimal reasoning to docs
Closes https://github.com/BerriAI/litellm/issues/13391
* docs(responses_api.md): add proxy examples to docs
* refactor: fix ruff error
* added mcp guardrails doc in mcp.md
* add button to reload models
* Added button changes
* added button for scheduling reload
* add multi pod support to reloading the model price json
* fix ruff
* feat(proxy/utils.py): track pre-call hooks in OTEL
some pre call hooks can cause latency in high traffic - make sure this is tracked
* fix(router.py): move redis call on deployment_callback_on_success to pipeline operation
reduces p99 latency by half when redis is enabled
* fix(parallel_request_limiter_v3.py): only run check if any item has rate limits set
Prevents unnecessary latency added by rate limit checks
* test: add unit tests
* Latency Improvements: only track tpm/rpm usage when set on deployment+ LLM Caching - use an in-memory cache to reduce redis calls + OTEL - track time spent on LLM caching (#13472)
* fix(router.py): only track usage for deployments with tpm/rpm set
ensures additional latency avoided for non-tpm/rpm models
* fix(caching_handler.py): log time spent on request get cache to OTEL
enables easy debugging of call latency
* fix(caching_handler.py): use dual cache object for in-memory caching + trace redis call within caching handler
* fix(caching_handler.py): working in-memory cache for redis calls
ensures dual cache works when redis cache setup for llm calls
makes calls quicker by only checking redis when in-memory cache missed for llm api call
* test: remove redundant test
* test: add unit tests
