Add dictation and streamed read-aloud to the chat

- A mic in the composer records, transcribes with the bot's
  transcription model (api/admin/bots/transcribe) and writes the text
  into the input at the cursor to edit before sending. Escape cancels;
  recordings aren't stored.
- Every bot message has a read-aloud button that plays
  GET api/admin/bots/speak-message, streamed from the provider as the
  audio is made, so it starts in a couple of seconds. One message plays
  at a time; only the user's own sessions can be read.
- Both buttons stay visible but disabled while the bot has no model for
  them (bot_voice page prop).
- Transcription and speech no longer pick free models automatically:
  they're not available until a model is picked, and Settings says so.
  Transcription lists speech-to-text models only, so the chat-model
  transcript path and its missing-audio check are gone.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

src/functions/backend/db/bot-sessions/grab-conversation-props.ts

@@ -6,6 +6,7 @@ import grabBotExtensionsOverview from "../extensions/grab-bot-extensions-overvie
 import grabBotComputers from "../computers/grab-bot-computers";
 import grabBotHarnessOverview from "../harness/grab-bot-harness-overview";
 import grabHarnessOverview from "../harness/grab-harness-overview";
+import resolveHarnessCandidates from "@/src/harness/resolve/resolve-harness-candidates";
 import grabUserWorkspaces from "../workspaces/grab-user-workspaces";
 import ensureBotSession from "./ensure-bot-session";
 import grabUserConversation from "./grab-user-conversation";
@@ -25,7 +26,8 @@ type Params = {
  * `/admin/workspaces/<id>/bots/<id>`): the rail's crew (the workspace's
  * in a workspace) and workspaces, the bot, its active session (marked
  * read) and its messages, its models, computers, tools and MCP servers
- * and active task there.
+ * and active task there, and whether its mic and read-aloud have a model
+ * to run on.
  * Null when the user can't chat with the bot there.
  */
 export default async function grabConversationProps({
@@ -64,7 +66,7 @@ export default async function grabConversationProps({
      * workspace the workspace's own models come first, so what runs now
      * shows its pick.
      */
-    const [bot_messages, bot_harness_overview, bot_computers, bot_task, bot_extensions] = await Promise.all([
+    const [bot_messages, bot_harness_overview, bot_computers, bot_task, bot_extensions, transcription, speech] = await Promise.all([
         grabBotMessages({ session_id: session.id! }),
         (bot.kind == "coordinator" && !scope
             ? grabHarnessOverview().then(({ harnesses }) => ({ harnesses }))
@@ -76,6 +78,8 @@ export default async function grabConversationProps({
         grabBotComputers({ bot_id: bot.id, workspace_id: scope }),
         grabActiveBotTask({ bot_id: bot.id, session_id: session.id }),
         grabBotExtensionsOverview({ user_id, bot_id: bot.id, workspace_id: scope }),
+        hasHarnessModel({ harness: "transcription", bot_id: bot.id, workspace_id: scope }),
+        hasHarnessModel({ harness: "speech", bot_id: bot.id, workspace_id: scope }),
     ]);
 
     return {
@@ -89,5 +93,15 @@ export default async function grabConversationProps({
         bot_computers,
         bot_task,
         bot_extensions,
+        bot_voice: { transcription, speech },
     };
 }
+
+/**
+ * Whether the harness is on and has a model to run on for the bot there.
+ */
+async function hasHarnessModel(params: Parameters<typeof resolveHarnessCandidates>[0]) {
+    return await resolveHarnessCandidates(params)
+        .then((candidates) => candidates.length > 0)
+        .catch(() => false);
+}

src/functions/backend/db/bots/grab-speakable-message.ts

@@ -0,0 +1,37 @@
+import BunSQLite from "@moduletrace/bun-sqlite";
+import type { BUN_SQLITE_COBBLE_BOT_MESSAGES } from "@/db/types/db";
+import AppError from "@/src/utils/app-error";
+import grabUserConversation from "../bot-sessions/grab-user-conversation";
+
+type Params = {
+    user_id: number;
+    message_id: number;
+};
+
+/**
+ * A bot message in one of the user's own sessions, for reading aloud,
+ * with the conversation it's in (so a lost grant blocks it). Throws when
+ * it isn't theirs.
+ */
+export default async function grabSpeakableMessage({ user_id, message_id }: Params) {
+    const message = (
+        await BunSQLite.sql<BUN_SQLITE_COBBLE_BOT_MESSAGES>({
+            sql: `SELECT m.* FROM bot_messages m
+                JOIN bot_sessions s ON s.id = m.session_id
+                WHERE m.id = ? AND m.author = 'bot' AND s.user_id = ?`,
+            values: [message_id, user_id],
+        })
+    ).payload?.[0];
+
+    if (!message?.id || !message.bot_id) {
+        throw new AppError(`Message not found`);
+    }
+
+    const conversation = await grabUserConversation({
+        user_id,
+        bot_id: message.bot_id,
+        workspace_id: message.workspace_id || null,
+    });
+
+    return { message, conversation };
+}

src/functions/backend/db/harness/grab-harness-overview-item.ts

@@ -55,6 +55,7 @@ export default async function grabHarnessOverviewItem({
         title: meta.title,
         description: meta.description,
         required: meta.required,
+        automatic: meta.automatic,
         model_id: setting.model_id,
         provider_id: setting.provider_id,
         providers,