- Fix supports_reasoning() call to use lowercase model names for proper lookup
- Remove custom_llm_provider parameter as model registry entries are provider-agnostic
- Update tests to use full model names with date stamps (required for supports_reasoning)
- Add test coverage for models without extended thinking support
Responses API - add default api version for openai responses api calls + Openrouter - fix claude-sonnet-4 on openrouter + Azure - Handle `openai/v1/responses`
- Add dynamic parameter support for anthropic models through GitHub Copilot
- Include thinking parameter for anthropic model compatibility
- Support reasoning_effort parameter for both anthropic and reasoning models
- Update test coverage for parameter validation logic
- Ensure proper parameter filtering based on model type
- Add github_copilot case to get_supported_openai_params function
- Implement get_supported_openai_params method in GithubCopilotConfig
- Dynamically add thinking and reasoning_effort params for Anthropic models
- Add comprehensive tests for parameter support validation
- Ensure case-insensitive model detection for parameter inclusion
Fixes UnsupportedParamsError when using advanced reasoning parameters
with Anthropic models through GitHub Copilot proxy.
- test_assistant_message_cache_control: Tests assistant messages with string content and cache_control
- test_assistant_message_list_content_cache_control: Tests assistant messages with list content and cache_control
- test_tool_message_cache_control: Tests tool messages with list content and cache_control
- test_tool_message_string_content_cache_control: Tests tool messages with string content and cache_control
- test_assistant_tool_calls_cache_control: Tests assistant tool_calls with cache_control
- test_multiple_tool_calls_with_mixed_cache_control: Tests multiple tool calls with mixed cache_control
- test_no_cache_control_no_cache_point: Tests that messages without cache_control don't generate cachePoint blocks
These tests ensure that cachePoint blocks are correctly generated for all message types when cache_control is present.
* fix intent params
* Add responses
* fix unrelated test
* test fix - fireworks API endpoint is down
* test fix fireworks ai is having an active outage
* test_completion_cost_databricks
* dbrx fix test API currently not responding
* Update OpenAI Realtime handler to use the correct endpoint and include all query parameters. Adjusted error messages for missing API base and key. Updated health check URL construction to pass model as a query parameter.
* Enhance OpenAI Realtime handler tests to ensure model parameter inclusion in WebSocket URL. Added new tests to verify correct URL construction with model and additional parameters, preventing 'missing_model' errors. Updated existing tests for consistency.
* Remove debug print statements for API base and key in OpenAIRealtime handler to clean up the code.
---------
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
* 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.
* 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
* 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.
Fixed MyPy type error in Ollama completion transformation where finish_reason
was set to None instead of expected string type. Changed finish_reason=None to
finish_reason="" to match GenericStreamingChunk TypedDict requirements.
Also updated corresponding test to expect empty string instead of None.
- Handle chunks containing 'thinking' field with empty 'response'
- Treat these as intermediate chunks that don't contain user content
- Add comprehensive tests for chunk parsing scenarios
- Resolves APIConnectionError for GPT-OSS model streaming
Fixes#13340
* (#13284) add avector_store_create to route_type which doesn't require model
* (#13284) exclude hidden params in metadata when create vector store
* (#13284) fix lint error
* (#13284) keep metadata None if metadata is None(not empty dict)
* (#13284) add test code
* (#13284) change test code name
* (#13284) add avector_store_search to route_type which doesn't require model
* 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
* fix(bedrock): prevent duplicate role assumption in EKS/IRSA environments
Fixes issue where AWS role assumption would fail in EKS/IRSA environments
when trying to assume the same role that's already being used.
The problem occurred when:
1. EKS/IRSA automatically assumes a role (e.g., LitellmRole)
2. LiteLLM tries to assume the same role again, causing AccessDenied errors
3. Different models with different roles would fail due to incorrect role context
Changes:
- Added check in _auth_with_aws_role() to detect if already using target role
- Skip role assumption if current identity matches target role
- Return current credentials instead of attempting duplicate assumption
- Added comprehensive test coverage for the fix
This ensures proper role chaining works in EKS/IRSA environments where:
- Service Account can assume Role A
- Role A can assume Role B for different models/accounts
Resolves the AccessDenied errors reported in bedrock usage scenarios.
* fix(bedrock): simplify role assumption for EKS/IRSA environments
Fixes AWS Bedrock role assumption in EKS/IRSA environments by properly
handling ambient credentials when no explicit credentials are provided.
The issue occurred because commit 197e7efa8f
introduced changes that broke role assumption in EKS/IRSA environments.
Changes:
- Simplified _auth_with_aws_role() to use ambient credentials when no
explicit AWS credentials are provided (aws_access_key_id and
aws_secret_access_key are both None)
- This allows web identity tokens in EKS/IRSA to work automatically
through boto3's credential chain
- Maintains backward compatibility for explicit credential scenarios
Added comprehensive test coverage:
- test_eks_irsa_ambient_credentials_used: Verifies ambient credentials work
- test_explicit_credentials_used_when_provided: Ensures explicit creds still work
- test_partial_credentials_still_use_ambient: Edge case handling
- test_cross_account_role_assumption: Multi-account scenarios
- test_role_assumption_with_custom_session_name: Custom session names
- test_role_assumption_ttl_calculation: TTL calculation verification
- test_role_assumption_error_handling: Error propagation
- test_multiple_role_assumptions_in_sequence: Sequential role assumptions
This fix ensures that in EKS/IRSA environments:
1. Service accounts can assume their initial role via web identity
2. That role can then assume other roles across accounts as configured
3. Different models can use different roles without conflicts
* fix(bedrock): add automatic IRSA detection for EKS environments
- Detect AWS_WEB_IDENTITY_TOKEN_FILE and AWS_ROLE_ARN environment variables
- Automatically use web identity token flow when IRSA is detected
- Read web identity token from file and pass to existing auth method
- Add test coverage for IRSA environment detection
- Fixes authentication errors in EKS with IRSA when no explicit credentials provided
* fix(bedrock): skip role assumption when IRSA role matches requested role
- Detect when AWS_ROLE_ARN environment variable matches the requested role
- Skip unnecessary role assumption when already running as the target role
- Use existing env vars authentication method for IRSA credentials
- Add test coverage for same-role IRSA scenario
- Fixes 'not authorized to perform: sts:AssumeRole' errors when trying to assume the same role
* fix(bedrock): use boto3's native IRSA support for cross-account role assumption
- Replace custom web identity token handling with boto3's built-in IRSA support
- boto3 automatically reads AWS_WEB_IDENTITY_TOKEN_FILE and assumes initial role
- Then use standard assume_role for cross-account access
- Update test to mock boto3 STS client instead of internal methods
- Fixes 'OIDC token could not be retrieved from secret manager' error
* fix(bedrock): improve IRSA error handling and add debug logging
- Add debug logging to show current identity and role assumption attempts
- Provide clearer error messages for trust policy issues
- Fix region handling in IRSA flow
- Re-raise exceptions instead of silently falling through
- This helps diagnose cross-account role assumption permission issues
* fix(bedrock): manually assume IRSA role with correct session name for cross-account scenarios
- When doing cross-account role assumption, manually assume the IRSA role first with the desired session name
- This ensures the session name in the assumed role ARN matches what's expected in trust policies
- For same-account scenarios, continue using boto3's automatic IRSA support
- Updated tests to handle the new flow
- This fixes the issue where cross-account trust policies require specific session names
* fix: Fix linting issues in base_aws_llm.py
- Fix f-string without placeholders (F541)
- Refactor _auth_with_aws_role to reduce statements count (PLR0915)
- Extract _handle_irsa_cross_account helper method
- Extract _handle_irsa_same_account helper method
- Extract _extract_credentials_and_ttl helper method
---------
Co-authored-by: openhands <openhands@all-hands.dev>
