Voice (dictate, read aloud) and Draw a picture over /v1, with the app's models scope

The server kept voice and images on /v1 (models scope, which the app's token
already asks for); /me's services and scopes decide what is offered. Rust
sends the recording to /v1/audio/transcriptions, reads /v1/audio/speech back
as a data: URL (CSP media-src data:), and for /v1/images/generations takes
only the id of each of the person's own files from the answer and fetches
/v1/files/<id>/content from the app's own server. The microphone is allowed
only within seconds of the page's own Dictate (voice_arm); WebKitGTK's
media stream is switched on through its settings getter.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

ui/js/draw.js

@@ -0,0 +1,86 @@
+// Draw a picture: the instance's own image generation (`POST /v1/images/generations`, its
+// workflow and default checkpoint), from Ctrl+K. Offered only where `GET /me` says the account may
+// (`services.images`) and the token holds `models`.
+//
+// The pictures are shown only as Rust read them: each one of the person's own files on this
+// server (`/v1/files/<id>/content`, fetched by id from the app's own server, never from an
+// address the answer named), handed over as a `data:` URL of an image type -- checked again here
+// before it becomes an <img>.
+
+import { h, icon, ICONS } from "./dom.js"
+import { invoke, why } from "./bridge.js"
+
+const PICTURE = /^data:image\/(png|jpeg|webp|gif);base64,[A-Za-z0-9+/=]+$/
+
+/** Whether pictures can be drawn here, for the account `me` (`GET /me`). */
+export function canDraw(me) {
+  const models = !Array.isArray(me?.scopes) || me.scopes.includes("models")
+  return !!me?.services?.images && models && me?.permissions?.["tools.image"] !== false
+}
+
+/** The dialog: a prompt, a shape, Draw, and the pictures under it. */
+export function openDraw() {
+  const prompt = h("textarea", { class: "textarea draw__prompt", rows: "3", placeholder: t("What to draw…"), "aria-label": t("What to draw…") })
+  const size = h(
+    "select",
+    { class: "draw__size", "aria-label": t("Shape") },
+    h("option", { value: "1024x1024", text: t("Square") }),
+    h("option", { value: "1344x768", text: t("Wide") }),
+    h("option", { value: "768x1344", text: t("Tall") }),
+  )
+  const status = h("p", { class: "status", role: "status", hidden: true })
+  const out = h("div", { class: "draw__out" })
+  const go = h("button", { type: "submit", class: "btn btn--primary", text: t("Draw") })
+  const form = h(
+    "form",
+    { class: "dialog__body draw", method: "dialog" },
+    h("h2", { class: "dialog__title" }, icon(ICONS.picture), h("span", { text: t("Draw a picture") })),
+    prompt,
+    h("div", { class: "draw__bar" }, size, h("button", { type: "button", class: "btn", text: t("Close"), onclick: () => close() }), go),
+    status,
+    out,
+  )
+  const dlg = h("dialog", { class: "dialog dialog--wide" }, form)
+  let asked = 0
+  const close = () => {
+    asked++
+    dlg.close()
+    dlg.remove()
+  }
+  const said = (text, error = false) => {
+    status.hidden = !text
+    status.textContent = text
+    status.className = `status${error ? " is-error" : ""}`
+    status.setAttribute("role", error ? "alert" : "status")
+  }
+  form.addEventListener("submit", async (e) => {
+    e.preventDefault()
+    const words = prompt.value.trim()
+    if (!words) return prompt.focus()
+    const mine = ++asked
+    go.disabled = true
+    said(t("Drawing… a picture can take a minute or two."))
+    try {
+      const urls = await invoke("draw", { prompt: words, size: size.value })
+      if (mine !== asked) return
+      const pictures = (urls || []).filter((u) => PICTURE.test(u))
+      if (!pictures.length) throw { detail: t("The server's answer had no picture in it.") }
+      out.prepend(...pictures.map((src) => h("figure", { class: "draw__pic" }, h("img", { src, alt: words }), h("figcaption", { text: words }))))
+      said("")
+    } catch (err) {
+      if (mine === asked) said(why(err), true)
+    } finally {
+      if (mine === asked) go.disabled = false
+    }
+  })
+  prompt.addEventListener("keydown", (e) => {
+    if (e.key === "Enter" && (e.ctrlKey || e.metaKey)) form.requestSubmit()
+  })
+  dlg.addEventListener("cancel", (e) => {
+    e.preventDefault()
+    close()
+  })
+  document.body.append(dlg)
+  dlg.showModal()
+  prompt.focus()
+}