7 Commits

Include renames

Author	SHA1	Message	Date
dwrz	7224fea99f	Refactor llm package	2026-09-20 12:49:42 +00:00
dwrz	6592bae15d	Add concurrent tool calls	2026-07-08 01:59:11 +00:00
dwrz	27fa702071	Add reasoning effort	2026-07-07 19:13:25 +00:00
dwrz	d212a52120	Add OpenRouter reasoning support	2026-06-29 16:25:42 +00:00
dwrz	f2edd39160	Add debug stats	2026-06-27 00:13:16 +00:00
dwrz	d21ed0dd4d	Add reasoning streaming	2026-06-26 18:03:43 +00:00
dwrz	f6fb21d40c	Replace go-openai with native client ... Drop the github.com/sashabaranov/go-openai dependency in favor of an internal HTTP client. The LLM package is now split into: - llm.go: type definitions (Message, ChatRequest, ChatResponse, etc.) - client.go: client construction and configuration - client_completions.go: Completions and CompletionsStream methods - client_models.go: ListModels - client_tools.go: tool call execution CompletionsStream uses typed SSE events (delta, done, message) so the frontend can render progressive streaming output. Move tool.go and tool_test.go from internal/tool/ into internal/llm/ to co-locate the registry with the client that consumes it. Update job.go and service.go to use the new llm.Message types and Completions/CompletionsStream methods. Remove the Voice field from chat request/response (voice is now tracked via message metadata). Frontend: handle delta/done/message SSE events, render a streaming placeholder that receives progressive text deltas, and finalize with full message binding (reasoning, tool calls, actions).	2026-06-26 14:22:05 +00:00