agentjido / req_llm / b699102cd05f1deef43b5b4eeb2a6bbf5432d3f1 / 1
49%
main: 49%

DEFAULT BRANCH: main
Ran
Files 55
Run time 1s
Badge
Embed ▾
README BADGES
x

If you need to use a raster PNG badge, change the '.svg' to '.png' in the link

Markdown

Textile

RDoc

HTML

Rst
coverage: 57.704% (+36.9%) from 20.817%
b699102cd05f1deef43b5b4eeb2a6bbf5432d3f1.1

push

github

web-flow 
Refine Stream Return system (#26)

* build fixtures

* Enhance Groq provider implementation and streaming capabilities

- Updated the Groq provider to utilize a more streamlined approach, removing unnecessary context and response wrapper modules.
- Introduced new options for Groq, including `service_tier` and `reasoning_effort`, with conditional handling to omit default values.
- Improved the `ReqLLM.Step.Stream` module to handle Server-Sent Events (SSE) more effectively, allowing for better integration with provider-specific decoding.
- Enhanced the `ReqLLM.Response.Codec` protocol to support both non-streaming and streaming responses, ensuring compatibility with various providers.
- Refactored the `stream_text` mix task to improve usage documentation and error handling, providing clearer examples for users.

These changes improve the overall functionality and usability of the Groq provider within the ReqLLM library, enhancing the streaming experience and simplifying the integration process.

* Enhance Groq object generation tests and update fixtures

- Refactored the Groq object generation test module to improve clarity and maintainability.
- Added new fixture files for various object generation scenarios, including basic and complex object generation, streaming responses, and consistency checks.
- Updated existing fixture files to reflect new response data and timestamps for accurate testing.
- Removed obsolete fixture files to streamline the testing framework.

These changes enhance the overall testing strategy for Groq, ensuring comprehensive coverage of object generation capabilities and improving the robustness of the testing framework.

* Refactor provider addition guide for clarity and structure

- Updated the guide for adding new providers to split the developer checklist into two distinct paths: a fast path for OpenAI-compatible providers and an advanced path for custom protocols.
- Enhanced the documentation to clarify the minimal skeleton... (continued)

1659 of 2875 relevant lines covered (57.7%)

155.58 hits per line

Source Files on job b699102cd05f1deef43b5b4eeb2a6bbf5432d3f1.1