agentjido / req_llm

49%

main: 49%

LAST BUILD ON BRANCH chore/object-fixtures

branch: chore/object-fixtures

CHANGE BRANCH

x

Reset

Sync Branches

• chore/object-fixtures
• 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/object-fixtures-resurrected
• 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
• feature/unique-model-provider-options
• 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/google-structured-output
• fix/proxy-options
• fix/registry-get-provider-nil-module
• google-vision
• improve-metadata-provider-errors
• main
• patch-1
• refactor/req-streaming
• zai

Build # b471913a906afb6b96001e5c9a7bffe69744b742-PR-87

Build Type

Pull #87

github

Committed by mikehostetler

Commit Message

Enhance model compatibility task and update provider implementations

- Added new options for model compatibility checks in `Mix.Tasks.ReqLlm.ModelCompat`, including `migrate` and `failed_only`.
- Improved state management and error handling in the model compatibility task.
- Introduced new helper functions for building request bodies and headers across providers, enhancing code reuse.
- Updated the `supports_object_generation?/1` function in `ReqLLM.Capability` to check for object generation support across different providers.
- Refactored provider implementations for Anthropic and Google to streamline request handling and improve error messaging.
- Expanded test coverage for object generation scenarios and updated existing tests to reflect new capabilities.

This commit aims to improve the overall robustness and maintainability of the model compatibility and provider integration features.

Pull Request Pull Request #87: Optimize model compatibility testing with true parallelization

Run Details

57 of 161 new or added lines in 7 files covered. (35.4%)

10 existing lines in 4 files now uncovered.

2686 of 5505 relevant lines covered (48.79%)

177.48 hits per line