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

internal/lua/vm_test.go

@@ -1,6 +1,7 @@
 package lua
 
 import (
+	"encoding/json"
 	"strings"
 	"testing"
 )
@@ -85,3 +86,110 @@ func TestBuildHeadersCustomHook(t *testing.T) {
 		t.Fatalf("timestamp = %q", hdrs["X-Timestamp"])
 	}
 }
+
+func TestDisableThinkingPassthrough(t *testing.T) {
+	vm := NewVM(t.TempDir())
+	if err := vm.Start(); err != nil {
+		t.Fatal(err)
+	}
+	defer vm.Stop()
+	body := `{"model":"x","disable_thinking":true,"messages":[{"role":"user","content":"hi"}]}`
+	out, err := vm.Transform("deepseek", "transform_request", body)
+	if err != nil {
+		t.Fatalf("deepseek transform: %v", err)
+	}
+	var req struct {
+		ExtraBody map[string]interface{} `json:"extra_body"`
+	}
+	if err := json.Unmarshal([]byte(out), &req); err != nil {
+		t.Fatalf("unmarshal: %v (%s)", err, out)
+	}
+	thinking, ok := req.ExtraBody["thinking"].(map[string]interface{})
+	if !ok {
+		t.Fatalf("deepseek should emit extra_body.thinking on disable_thinking: %s", out)
+	}
+	if thinking["type"] != "disabled" {
+		t.Fatalf("thinking.type = %v", thinking["type"])
+	}
+
+	// anthropic: disable_thinking removes the thinking block
+	out2, err := vm.Transform("anthropic", "transform_request", body)
+	if err != nil {
+		t.Fatalf("anthropic transform: %v", err)
+	}
+	if strings.Contains(out2, "thinking") {
+		t.Fatalf("anthropic should drop thinking when disable_thinking: %s", out2)
+	}
+	out3, err := vm.Transform("anthropic", "transform_request", `{"model":"x","messages":[{"role":"user","content":"hi"}]}`)
+	if err != nil {
+		t.Fatalf("anthropic transform: %v", err)
+	}
+	if !strings.Contains(out3, "enabled") {
+		t.Fatalf("anthropic should enable thinking by default: %s", out3)
+	}
+}
+
+func TestMultimodalTransform(t *testing.T) {
+	vm := NewVM(t.TempDir())
+	if err := vm.Start(); err != nil {
+		t.Fatal(err)
+	}
+	defer vm.Stop()
+	body := `{"model":"x","messages":[{"role":"user","content":[
+		{"type":"text","text":"what is this?"},
+		{"type":"image_url","image_url":{"url":"data:image/png;base64,QUJD"}},
+		{"type":"image_url","image_url":{"url":"https://ex.com/a.png"}}
+	]}]}`
+
+	// anthropic: image_url -> image block (base64/url), text preserved
+	out, err := vm.Transform("anthropic", "transform_request", body)
+	if err != nil {
+		t.Fatalf("anthropic: %v", err)
+	}
+	for _, want := range []string{`"media_type":"image/png"`, `"data":"QUJD"`, `"type":"url","url":"https://ex.com/a.png"`, `"what is this?"`} {
+		if !strings.Contains(out, want) {
+			t.Fatalf("anthropic multimodal missing %s: %s", want, out)
+		}
+	}
+
+	// gemini: image_url -> inline_data
+	gout, err := vm.Transform("gemini", "transform_request", body)
+	if err != nil {
+		t.Fatalf("gemini: %v", err)
+	}
+	var g struct {
+		Contents []struct {
+			Parts []map[string]interface{} `json:"parts"`
+		} `json:"contents"`
+	}
+	if err := json.Unmarshal([]byte(gout), &g); err != nil {
+		t.Fatalf("gemini unmarshal: %v", err)
+	}
+	if len(g.Contents) == 0 {
+		t.Fatalf("gemini no contents")
+	}
+	var found bool
+	for _, p := range g.Contents[0].Parts {
+		if v, ok := p["inline_data"].(map[string]interface{}); ok && v["data"] == "QUJD" && v["mime_type"] == "image/png" {
+			found = true
+		}
+	}
+	if !found {
+		t.Fatalf("gemini missing inline_data image: %s", gout)
+	}
+
+	// ollama: image_url -> images base64 array
+	out, err = vm.Transform("ollama", "transform_request", body)
+	if err != nil {
+		t.Fatalf("ollama: %v", err)
+	}
+	if !strings.Contains(out, `"images":["QUJD"]`) {
+		t.Fatalf("ollama multimodal missing images: %s", out)
+	}
+
+	// openai passthrough keeps the content array intact
+	po, _ := vm.Transform("openai", "transform_request", body)
+	if !strings.Contains(po, `"image_url"`) || !strings.Contains(po, `,QUJD"`) {
+		t.Fatalf("openai passthrough lost multimodal content: %s", po)
+	}
+}