mlx-bun 0.0.8 → 0.0.9

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mlx-bun",
-  "version": "0.0.8",
+  "version": "0.0.9",
   "description": "Native MLX inference for Bun on Apple Silicon — local LLM server (OpenAI/Anthropic-compatible) and TypeScript library. No Python.",
   "type": "module",
   "license": "MIT",

package/src/anthropic.ts

@@ -50,6 +50,18 @@ export interface AnthropicRequest {
   top_k?: number;
   stop_sequences?: string[];
   stream?: boolean;
+  /** mlx-lm sampler/penalty extensions — not part of the Anthropic protocol,
+   *  accepted as pass-through extras with the same names as our /v1 chat
+   *  surface. Anthropic has NO logit_bias, so none is accepted here. */
+  min_p?: number;
+  xtc_probability?: number;
+  xtc_threshold?: number;
+  repetition_penalty?: number;
+  repetition_context_size?: number;
+  presence_penalty?: number;
+  presence_context_size?: number;
+  frequency_penalty?: number;
+  frequency_context_size?: number;
   tools?: Array<{
     name?: string;
     description?: string;
@@ -167,6 +179,16 @@ export function anthropicToChatBody(body: AnthropicRequest): Record<string, unkn
   if (body.top_k != null) oai.top_k = body.top_k;
   if (body.stop_sequences?.length) oai.stop = body.stop_sequences;
   if (body.stream) oai.stream = true;
+  // mlx-lm sampler/penalty extensions: straight pass-through (same wire names
+  // on the chat surface). No logit_bias — it doesn't exist in this protocol.
+  for (const k of [
+    "min_p", "xtc_probability", "xtc_threshold",
+    "repetition_penalty", "repetition_context_size",
+    "presence_penalty", "presence_context_size",
+    "frequency_penalty", "frequency_context_size",
+  ] as const) {
+    if (body[k] != null) oai[k] = body[k];
+  }
 
   // Client tools only (entries with name + input_schema); server-tool
   // types (web_search etc.) have no local meaning and are dropped.

package/src/assets/curve-designer.html

@@ -89,7 +89,7 @@ button.ghost{background:var(--card);border:1px solid var(--bd);border-radius:8px
 <script>
 const ln=Math.log;
 const UMIN=ln(1e-6); // bottom-left / plot floor (matches src/curve-sampler.ts CURVE_UMIN)
-const ENGINE_BASE = location.protocol.startsWith("http") ? location.origin : "http://localhost:8090";
+const ENGINE_BASE = location.protocol.startsWith("http") ? location.origin : "http://localhost:8080";
 // ---- curve state: 5 movable control points, sorted ascending in p_in ----
 function identityPoints(){ return [{x_pct:1e-4,y_pct:1e-4},{x_pct:0.1,y_pct:0.1},{x_pct:1,y_pct:1},{x_pct:9,y_pct:9},{x_pct:100,y_pct:100}]; }
 let C = { space:"logprob", points:identityPoints(), monotonic:true };

package/src/chat-template.ts

@@ -131,20 +131,38 @@ export class ChatTemplate {
   /** True when the model has a switchable reasoning channel we can parse. */
   readonly supportsThinking: boolean;
 
-  private constructor(source: string, bosToken: string | null, eosToken: string | null) {
+  private constructor(
+    source: string,
+    bosToken: string | null,
+    eosToken: string | null,
+    forceNoThinking = false,
+  ) {
     this.#template = new Template(source);
     this.#bosToken = bosToken;
     this.#eosToken = eosToken;
     const gatesThinking = source.includes("enable_thinking");
-    this.thinkingFormat = gatesThinking && source.includes("<think>")
-      ? "think-tag"
-      : gatesThinking && source.includes("<|channel>")
-        ? "gemma-channel"
-        : null;
+    // `forceNoThinking` suppresses the switchable channel even when the template
+    // carries the gemma markers. DiffusionGemma ships the shared gemma-family
+    // template (with the `<|channel>thought…<channel|>` reasoning channel), but
+    // its non-autoregressive canvas decode cannot reliably emit the `<channel|>`
+    // close, so an enabled channel never ends (everything is captured as
+    // reasoning, no answer). The OptiQ reference never enables thinking for this
+    // model — it always renders the template's `default(false)` pre-closed empty
+    // channel and decodes the whole canvas as plain text. We match that.
+    this.thinkingFormat = forceNoThinking
+      ? null
+      : gatesThinking && source.includes("<think>")
+        ? "think-tag"
+        : gatesThinking && source.includes("<|channel>")
+          ? "gemma-channel"
+          : null;
     this.supportsThinking = this.thinkingFormat !== null;
   }
 
-  static async load(modelDir: string): Promise<ChatTemplate> {
+  static async load(
+    modelDir: string,
+    opts: { disableThinking?: boolean } = {},
+  ): Promise<ChatTemplate> {
     const config = (await Bun.file(`${modelDir}/tokenizer_config.json`).json()) as Record<string, any>;
     let source: string | undefined = config.chat_template;
     if (!source) {