• Home
  • Features
  • Pricing
  • Docs
  • Announcements
  • Sign In

agentjido / req_llm / b699102cd05f1deef43b5b4eeb2a6bbf5432d3f1

21 Sep 2025 06:36PM UTC coverage: 57.807% (+36.8%) from 21.036%
b699102cd05f1deef43b5b4eeb2a6bbf5432d3f1

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)

1087 of 1956 new or added lines in 50 files covered. (55.57%)

21 existing lines in 9 files now uncovered.

1666 of 2882 relevant lines covered (57.81%)

310.26 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

0.0
/test/support/fixture_assert.ex


Source Not Available

STATUS · Troubleshooting · Open an Issue · Sales · Support · CAREERS · ENTERPRISE · START FREE · SCHEDULE DEMO
ANNOUNCEMENTS · TWITTER · TOS & SLA · Supported CI Services · What's a CI service? · Automated Testing

© 2026 Coveralls, Inc