agentjido / req_llm / 1a895f31789903fb06038f99a2a13b5ea96887b7

Builds Branch Commit Type Ran Committer Via Coverage
1a895f31789903fb06038f99a2a13b5ea96887b7 main Re-sync models, add Claude 4.5 push mikehostetler github
59.74
c5ff026cd32d2490fe5d5e3f7978bd7e01bee87a main Refactor streaming from Req to Finch for production stability (#63) * Streaming refactor * Quality * Formatting * Fix tests * Enhance Anthropic provider to ensure max_tokens is always present and update context encoding. * Add reasoning effo... push web-flow github
59.71
925070fb540d977a525748b424eef5ebffbf4df7-PR-63 refactor/req-streaming Example agent to test streaming tool calls Pull #63 mikehostetler github
59.71
dbe746939f4b3c626257c31bb20bab75b43bc44b-PR-63 refactor/req-streaming Formatting Pull #63 mikehostetler github
62.46
521c4a80b4366d5a20a99f17666b113ce071e6b4-PR-63 refactor/req-streaming Enhance Anthropic provider to ensure max_tokens is always present and update context encoding. Pull #63 mikehostetler github
63.24
3208a4ce7cd51bfdb4f0237ac45ba778adaef5e4-PR-63 refactor/req-streaming Fix tests Pull #63 mikehostetler github
63.32
05fa9f0e59afa4718cc54d19524e62c6fc9dab25-PR-63 refactor/req-streaming Formatting Pull #63 mikehostetler github
63.33
b609b98275878fa032903148b26198afa35f073a-PR-59 bug/openai-tool-calls Fix tool calling encoding for OpenAI provider - Implement role-specific message encoding in Provider.Defaults - Extract tool calls from ContentParts to top-level tool_calls field - Normalize function arguments to JSON strings as required by OpenA... Pull #59 mikehostetler github
61.68
dfd4b1779c529e1ff456e8d0ed760634fd5200b6 main Quality after merges push mikehostetler github
61.32
1d67c3d1fc988dcca8f9161bb3737b48993e2052 main Fix: Translate max_tokens to max_completion_tokens for OpenAI reasoning models (#58) * fix: translate max_tokens to max_completion_tokens for OpenAI reasoning models - Extended parameter translation to cover all reasoning models (GPT-5, O4, Code... push web-flow github
58.95
6bd06ca18d467d861e4cdb8f0eea029dcaa50daf-PR-58 fix-openai-max-tokens-param Formatting Pull #58 mikehostetler github
58.95
f81cbf718ccea2ea6d71746e285ffac680893cfe main Fix: Convert 'assistant' role to 'model' for Google Gemini API (#56) * fix: Convert 'assistant' role to 'model' for Google Gemini API The Google Gemini API expects role 'model' instead of 'assistant' for AI responses. Updated the convert_message... push web-flow github
58.77
11c806f2ce9a5dd31cfa0748e24524ac8abe2073 main Fix: Convert 'assistant' role to 'model' for Google Gemini API (#56) * fix: Convert 'assistant' role to 'model' for Google Gemini API The Google Gemini API expects role 'model' instead of 'assistant' for AI responses. Updated the convert_message... push web-flow github
58.77
9610a14d62ce8948f859ebe3b537d61e63d01519-PR-56 fix-groq-stream-error Formatting Pull #56 mikehostetler github
58.77
679763c4ce77c0ab0b8ec28d61aecee01436c1b8 main feat: add tool call support to Google Gemini provider (#54) * feat: add tool call support to Google Gemini provider - Extract function calls from Google response parts in decode_response - Preserve tool_calls in assistant messages when present -... push web-flow github
58.7