agentjido / req_llm

23%

main: 49%

LAST BUILD ON BRANCH feature/unique-model-provider-options

branch: feature/unique-model-provider-options

CHANGE BRANCH

x

Reset

Sync Branches

• feature/unique-model-provider-options
• add-vllm-provider
• bedrock-clean
• bug/api-return-types
• bug/codec-tool-calls
• bug/debug-stream-return
• bug/incorrect-model-spec-docs
• bug/openai-tool-calls
• bug/streaming-race-condition
• cerebras
• chore/refresh-coverage-tests
• chore/update-models-2025-09-21
• copilot/fix-32
• devtools
• feat/context-json-serialization
• feat/google-upload-file
• feat/in-type-support
• feat/structured-output-openai-google
• feature/cerebras-provider
• feature/pre-release-fixes
• feature/refactor-llm-api-fixtures
• feature/refined-key-management
• fix-anthropic-streaming
• fix-duplicate-clause
• fix-google
• fix-groq-stream-error
• fix-mix-task-docs
• fix-openai-max-tokens-param
• fix/cost-calculation-in-usage
• fix/google-file-support
• fix/proxy-options
• fix/registry-get-provider-nil-module
• google-vision
• improve-metadata-provider-errors
• main
• patch-1
• refactor/req-streaming

Build # 56683a4cb50c99c9f38265cfa4419f20280ad9f8-PR-11

Build Type

Pull #11

github

Committed by mikehostetler

Commit Message

Enhance OpenAI provider parameter handling

- Introduced a new validation function `validate_mutex!/3` in the `ReqLLM.Provider.DSL` module to ensure that conflicting parameters are not used together, improving error handling for provider options.
- Updated the OpenAI provider to dynamically determine the appropriate token parameter (`max_tokens` or `max_completion_tokens`) based on the model name, enhancing compatibility with different OpenAI models.

This change improves the robustness of parameter handling and aligns with the recent enhancements for model-specific option translation.

Pull Request Pull Request #11: Fix OpenAI o1 model parameter translation (resolves #8)

Run Details

2 of 34 new or added lines in 2 files covered. (5.88%)

269 existing lines in 9 files now uncovered.

525 of 2300 relevant lines covered (22.83%)

122.19 hits per line