llmz 0.3.1 → 0.5.0

package/dist/transcript.d.ts

@@ -1,8 +1,40 @@
 export declare namespace Transcript {
+    /**
+     * A file attached to a transcript message.
+     *
+     * - `image`: a picture the model can see.
+     * - `audio`: a voice message — spoken audio of what the user said. Messages
+     *   carrying an audio attachment are presented to the model as spoken turns
+     *   (tagged `modality="voice"` in the prompt) and the audio is sent as model
+     *   input: audio-capable models hear it directly, others receive a
+     *   transcription (see `@botpress/cognitive`'s `transcriptionModel` option).
+     *
+     * `url` supports http(s) URLs and base64 `data:` URIs.
+     *
+     * `id` is an optional stable identifier for referencing the attachment from
+     * the message content (e.g. `screenshot-A` in a screen-share event log). It
+     * is used as the attachment's reference in the prompt; without it, a
+     * positional letter (A, B, C...) is auto-assigned.
+     *
+     * `alt` is an optional human-readable description shown to the model next to
+     * the attachment (e.g. "Screenshot of the checkout error page").
+     */
     type Attachment = {
-        type: 'image';
+        type: 'image' | 'audio';
         url: string;
+        id?: string;
+        alt?: string;
     };
+    /**
+     * How the user delivered a message. Defaults to `'text'`.
+     *
+     * Set to `'voice'` when the user spoke the message out loud. Use it when the
+     * speech was already transcribed upstream and no audio is attached — the
+     * message `content` is then treated as a transcript of what the user said.
+     * Messages with an `audio` attachment are always treated as voice; setting
+     * this field is not required for them.
+     */
+    type Modality = 'text' | 'voice';
     type AssistantMessage = {
         role: 'assistant';
         name?: string;
@@ -14,6 +46,8 @@ export declare namespace Transcript {
         createdAt?: string;
         name?: string;
         content: string;
+        /** How the user delivered this message. Defaults to 'text'. See {@link Modality}. */
+        modality?: Modality;
         attachments?: Array<Attachment>;
     };
     type EventMessage = {
@@ -30,6 +64,8 @@ export declare namespace Transcript {
     };
     type Message = AssistantMessage | UserMessage | EventMessage | SummaryMessage;
 }
+/** Whether the message is a spoken turn: explicit voice modality or an audio attachment. */
+export declare function isVoiceMessage(message: Transcript.Message): boolean;
 export declare class TranscriptArray extends Array<Transcript.Message> {
     constructor(items?: Transcript.Message[]);
     toString(): string;

package/package.json

@@ -2,7 +2,7 @@
   "name": "llmz",
   "type": "module",
   "description": "LLMz - An LLM-native Typescript VM built on top of Zui",
-  "version": "0.3.1",
+  "version": "0.5.0",
   "files": [
     "dist",
     "DOCS.md"
@@ -69,7 +69,7 @@
   },
   "peerDependencies": {
     "@botpress/client": "2.0.0",
-    "@botpress/cognitive": "1.0.1",
+    "@botpress/cognitive": "1.0.2",
     "@bpinternal/thicktoken": "^3.1.0",
     "@bpinternal/zui": "^2.4.0"
   },