Fixes#15995
When using the Responses API with providers that don't have a native
ResponsesAPIConfig implementation (like Gemini, Anthropic, Cohere, etc.),
the text.format parameter was being ignored. This happened because these
providers fall back to using the LiteLLMCompletionTransformationHandler,
which converts Responses API requests to Chat Completion API requests.
Changes:
- Added 'text' to the list of supported parameters in
LiteLLMCompletionResponsesConfig.get_supported_openai_params()
- Added transformation logic to convert text.format (Responses API format)
to response_format (Chat Completion API format) in
transform_responses_api_request_to_chat_completion_request()
- Created _transform_text_format_to_response_format() method to handle
the conversion between the two format structures
The transformation supports:
- json_schema: Converts to Chat Completion's json_schema format with
proper nested structure
- json_object: Converts to Chat Completion's json_object mode
- text: Returns None (default text format)
This fix benefits all providers that use the fallback transformation
handler, ensuring consistent behavior with OpenAI's native Responses API
implementation.
* fix: Preserve Bedrock inference profile IDs in health checks
- Fixes issue where health checks were stripping inference profile IDs
- Preserves cross-region inference profile prefixes (us., eu., apac., jp., au., us-gov., global.)
- Strips only AWS region routing while preserving routes and handlers
- Resolves both issue #15807 and inference profile requirement errors
- Adds comprehensive tests for all Bedrock model format combinations
Issue #15807 attempted to fix regional Bedrock model health checks but was too
aggressive, stripping cross-region inference profile prefixes that AWS requires.
This caused errors: "Invocation of model ID X with on-demand throughput isn't
supported. Retry your request with the ID or ARN of an inference profile."
The fix now correctly:
- Strips AWS regions (us-west-2, eu-central-1, etc.) from routing
- Preserves CRIS prefixes (us., eu., etc.) required by AWS
- Preserves routes (converse/, invoke/)
- Preserves handlers (llama/, deepseek_r1/)
- Only affects Bedrock models (checked via startswith)
Test coverage includes 20+ scenarios for all Bedrock model format combinations.
* Remove unused traceback import
* perf: Skip sleep delays in base_mail.py during tests to improve test speed
* perf: Mock datetime.now in parallel_request_limiter_v3.py to improve test speed
* pref: Mock urllib system calls in test_aiohttp_transport.py to improve test speed
* chore: add --durations=50 to visualize slowest tests
* pref: reduce setup phase overhead by widening fixture scope in conftest.py
* test: stabilize flaky tests
* fix: minor issue
Added a new "Configuration with Environment Variables" section demonstrating:
- Using os.getenv() to dynamically retrieve OpenRouter configuration
- Explicitly passing base_url parameter with environment variables
- Benefits of this approach for managing configs across environments
This helps users implement production-ready configuration patterns.
* 1. add v3 classify
2. add new classifix for masking
3. support same id for the conversation for pre and post
working with duplicates
* clean code, remove some debug and run tests
* update liter errors
* improvment for Code Organization, httpx Error Handling Specificity, Logging Improvements and Type
* transfer test test_lasso_guard_config to the new location
* Fix type hints and linting errors in lasso.py
- Add type: ignore for httpx module when None
- Fix return type issues in _handle_classification and _handle_masking
- Ensure masked_messages is not None before passing to _apply_masking_to_model_response
- Convert LassoResponse to dict for _log_masking_applied call
* feat(lasso): Upgrade to Lasso API v3 and fix ULID generation
- Update Lasso API endpoints from v2 to v3 (/gateway/v3/classify)
- Update masking endpoints from v1 to v3 (/gateway/v3/classifix)
- Fix ULID generation: use ulid.new() instead of ULID() constructor
- Resolve MemoryView error that occurred with incorrect ULID usage
Tested with real proxy server and verified:
- Malicious content (jailbreak) properly blocked
- Safe content passes through guardrail
- PII detection and masking works correctly
- No ULID generation errors
* docs(lasso): Add ulid-py>=1.1.0 dependency prerequisite
Add Prerequisites section documenting the required ulid-py package
(version 1.1.0 or higher) for Lasso guardrail conversation tracking.
* update docs with the right api_key format
