proxy,ui-svelte: replace old UI with svelte+playground

Replace the legacy React UI with the new Svelte-based one. Introduce a Playground in the UI to quickly test out text, image, text to speech and speech to text models behind llama-swap. Key Changes New Svelte UI (ui-svelte/) - Multi-tab Playground with Chat, Image Generation, Audio Transcription, and Speech interfaces - Chat: message editing/regeneration, markdown rendering with LaTeX math support, image attachments, code syntax highlighting - Image: size selector, download/fullscreen viewing - Audio: transcription with peer support - Speech: voice caching with manual refresh, download button - Responsive mobile layout with collapsible navigation - XSS fixes and accessibility improvements Proxy Improvements - Add gzip/brotli compression for UI static assets (proxy/ui_compress.go) - Add GET /v1/audio/voices?model={model} endpoint for voice listing - Add peer support for /v1/audio/transcriptions
2026-01-31 22:49:13 -08:00
parent cdea7d16bd
commit 20738f3623
65 changed files with 5031 additions and 6078 deletions
@@ -0,0 +1,108 @@
+import type { ChatMessage, ChatCompletionRequest } from "./types";
+
+export interface StreamChunk {
+  content: string;
+  reasoning_content?: string;
+  done: boolean;
+}
+
+export interface ChatOptions {
+  temperature?: number;
+}
+
+function parseSSELine(line: string): StreamChunk | null {
+  const trimmed = line.trim();
+  if (!trimmed || !trimmed.startsWith("data: ")) {
+    return null;
+  }
+
+  const data = trimmed.slice(6);
+  if (data === "[DONE]") {
+    return { content: "", done: true };
+  }
+
+  try {
+    const parsed = JSON.parse(data);
+    const delta = parsed.choices?.[0]?.delta;
+    const content = delta?.content || "";
+    const reasoning_content = delta?.reasoning_content || "";
+
+    if (content || reasoning_content) {
+      return { content, reasoning_content, done: false };
+    }
+    return null;
+  } catch {
+    return null;
+  }
+}
+
+export async function* streamChatCompletion(
+  model: string,
+  messages: ChatMessage[],
+  signal?: AbortSignal,
+  options?: ChatOptions
+): AsyncGenerator<StreamChunk> {
+  const request: ChatCompletionRequest = {
+    model,
+    messages,
+    stream: true,
+    temperature: options?.temperature,
+  };
+
+  const response = await fetch("/v1/chat/completions", {
+    method: "POST",
+    headers: {
+      "Content-Type": "application/json",
+    },
+    body: JSON.stringify(request),
+    signal,
+  });
+
+  if (!response.ok) {
+    const errorText = await response.text();
+    throw new Error(`Chat API error: ${response.status} - ${errorText}`);
+  }
+
+  const reader = response.body?.getReader();
+  if (!reader) {
+    throw new Error("Response body is not readable");
+  }
+
+  const decoder = new TextDecoder();
+  let buffer = "";
+
+  try {
+    while (true) {
+      const { done, value } = await reader.read();
+
+      if (done) {
+        break;
+      }
+
+      buffer += decoder.decode(value, { stream: true });
+      const lines = buffer.split("\n");
+      buffer = lines.pop() || "";
+
+      for (const line of lines) {
+        const result = parseSSELine(line);
+        if (result?.done) {
+          yield result;
+          return;
+        }
+        if (result) {
+          yield result;
+        }
+      }
+    }
+
+    // Process any remaining buffer
+    const result = parseSSELine(buffer);
+    if (result && !result.done) {
+      yield result;
+    }
+
+    yield { content: "", done: true };
+  } finally {
+    reader.releaseLock();
+  }
+}