This repository has been archived on 2026-08-16. You can view files and clone it, but cannot push or open issues or pull requests.

Levi Neely c2cbc3e806 split execute_code into three tools; improve ollama backend and system prompt ... - Split execute_code into execute_code, execute_tool, execute_pipe for clearer model comprehension, especially on smaller models - Ollama: accumulate tool calls across all stream chunks (fixes llama3.1 which delivers tool calls only on the done event) - Ollama: add HTTP 429 / RateLimitError handling - Ollama: map ToolCallID on outbound messages - System prompt: inject cwd, current time, available tools - System prompt: clarify tool usage rules - Fix spurious spaces in streamed output (remove addStreamingContent heuristic) - Fix tool output display: preserve newlines, add blank line separation		2026-04-04 17:57:55 +02:00
..
backend.go	backend,agent,main: retry on HTTP 429 with live countdown	2026-04-04 11:25:05 +02:00
new.go	Remove openrouter backend alias	2026-04-01 00:57:18 +02:00
ollama.go	split execute_code into three tools; improve ollama backend and system prompt	2026-04-04 17:57:55 +02:00
openai.go	backend,agent,main: retry on HTTP 429 with live countdown	2026-04-04 11:25:05 +02:00