feat: LuaJIT worker-pool VM, multimodal/disable-thinking passthrough, WebUI redesign, DeepSeek V4

This commit is contained in:
root
2026-08-07 13:34:16 +08:00
parent a0e6e6da90
commit ccbcede581
16 changed files with 1733 additions and 425 deletions

View File

@ -16,13 +16,15 @@ import (
// chatRequest mirrors the OpenAI chat completions request the gateway accepts.
type chatRequest struct {
Model string `json:"model"`
Messages []types.ChatMessage `json:"messages"`
Temperature *float64 `json:"temperature,omitempty"`
MaxTokens int `json:"max_tokens,omitempty"`
Stream bool `json:"stream,omitempty"`
Tools []interface{} `json:"tools,omitempty"`
ToolChoice interface{} `json:"tool_choice,omitempty"`
Model string `json:"model"`
Messages []types.ChatMessage `json:"messages"`
Temperature *float64 `json:"temperature,omitempty"`
MaxTokens int `json:"max_tokens,omitempty"`
Stream bool `json:"stream,omitempty"`
Tools []interface{} `json:"tools,omitempty"`
ToolChoice interface{} `json:"tool_choice,omitempty"`
DisableThinking bool `json:"disable_thinking"`
ExtraBody map[string]interface{} `json:"extra_body,omitempty"`
}
// ChatCompletion is the non-streaming OpenAI response object.
@ -111,13 +113,15 @@ func (g *Gateway) handleChat(w http.ResponseWriter, r *http.Request) {
ctx := r.Context()
inner := &types.ChatRequest{
Model: normalizeModel(model),
Messages: req.Messages,
Temperature: req.Temperature,
MaxTokens: req.MaxTokens,
Stream: req.Stream,
Tools: req.Tools,
ToolChoice: req.ToolChoice,
Model: effective,
Messages: req.Messages,
Temperature: req.Temperature,
MaxTokens: req.MaxTokens,
Stream: req.Stream,
Tools: req.Tools,
ToolChoice: req.ToolChoice,
DisableThinking: req.DisableThinking,
ExtraBody: req.ExtraBody,
}
if req.Stream {
g.streamChat(w, ctx, cands, inner, effective)