feat(voice): add typed AI chat beside voice

Chat sits next to the mic in the command dock. Replies are silent and never
request the microphone; the first message connects with the selected provider
and runs the same map actions as voice through each provider's text API
(OpenAI OPENAI_CHAT_MODEL, Gemini GEMINI_CHAT_MODEL via generateContent, which
never starts Live). Only one mode runs at a time.

- Chat panel rendered by the voice control presenter: conversation, recent and
  quick-command suggestions, Up/Down history, attachments (map-layer
  references or small UTF-8 text files, sent only with the message)
- Chat and voice panels sit above the dock or dock into the right rail's
  column; minimized bars sit centred above the dock, and height animates on
  swaps
- A centred panel steps down to its bar for the Location and Visual Presets
  trays without moving focus, rests above an open tray, and docks right while
  expanded over one; it returns to the centre once the trays close
- Minimized voice previews the last sentence from each side; the empty Voice
  Preview suggests things to say
- Settings opened from chat keep chat's frame and show the shared AI provider
  and quick commands; voice Settings show Back to voice
- Closing chat ends a typed session; the voice panel's close turns voice off
- The dock widens its voice control for the chat button and restyles its
  wings, which show icons only at 900px and below; assistant panels share the
  left panels' glass, and Cyber keeps its own surfaces
- Server text-chat handlers with body, time and per-IP limits
  (GEV_RATELIMIT_*_CHAT_PER_MIN), documented in SECURITY.md; tests and all
  eleven locales

Co-authored-by: Darren Dignam <[email protected]>

src/voice/textChat.js

@@ -0,0 +1,383 @@
+import { waitForSignal } from '../sources/requestDeadline.js';
+import { readResponseJsonCapped } from '../sources/httpBody.js';
+import {
+  textProtocols,
+  emptyTextUsage,
+  addTextUsage,
+  boundedToolResult,
+} from './textProtocol.js';
+import { t } from '../i18n/index.js';
+import {
+  isGlobeViewRefusal,
+  responseInstructionForToolResult,
+} from './realtimeProtocol.js';
+
+/** Text-only HTTP turns: no Live token, socket, microphone or audio context. */
+export function createTextChat({
+  provider,
+  emit,
+  runAction,
+  signal,
+  fetchImpl = (...args) => fetch(...args),
+  chatEndpoint,
+  radioLayer = null,
+  dataManager = null,
+  timeoutMs = 90000,
+}) {
+  const protocol = textProtocols[provider];
+  const sessionUsage = emptyTextUsage();
+  let active = false;
+  let turn = null;
+  let sequence = 0;
+  let history = [];
+  let mapEvents = [];
+  let radioPending = null;
+  let radioHandoff = null;
+  let unsubscribeControls;
+  let unsubscribeVisibility;
+  const releaseRadio = (lease, cancel = false) => {
+    if (radioHandoff !== lease) return;
+    radioHandoff = null;
+    if (cancel)
+      radioLayer?.stopPlayback?.({ origin: 'voice-cleanup', attemptId: lease });
+    radioLayer?.setVoiceDucked?.(false);
+  };
+  const state = (value) => emit({ type: 'state', state: value });
+  const stop = ({ preserveStatus = false, removeUi = false } = {}) => {
+    active = false;
+    if (radioHandoff) releaseRadio(radioHandoff, true);
+    radioPending = null;
+    unsubscribeControls?.();
+    unsubscribeVisibility?.();
+    unsubscribeControls = unsubscribeVisibility = null;
+    turn?.abort();
+    turn = null;
+    history = [];
+    mapEvents = [];
+    if (!preserveStatus && !removeUi) state('idle');
+  };
+  signal?.addEventListener('abort', () => stop({ removeUi: true }), {
+    once: true,
+  });
+  async function respond(text, owner, id) {
+    const current = () =>
+      active && turn === owner && !owner.signal.aborted && !signal?.aborted;
+    const usage = emptyTextUsage();
+    let requestPending = false;
+    const reportUsage = () =>
+      emit({
+        type: 'usage',
+        provider,
+        responseId: id,
+        usage: { ...usage },
+        sessionUsage: { ...sessionUsage },
+      });
+    const recordUsage = (value) => {
+      if (!requestPending) return;
+      requestPending = false;
+      addTextUsage(usage, value);
+      addTextUsage(sessionUsage, value);
+      reportUsage();
+    };
+    const fail = (detail) => {
+      if (!active || turn !== owner || signal?.aborted) return;
+      active = false;
+      history = [];
+      emit({ type: 'state', state: 'error', detail, usage: { ...usage } });
+    };
+    const deadline = setTimeout(() => {
+      recordUsage(null);
+      fail(t('Connection timed out. Try again.'));
+      owner.abort();
+    }, timeoutMs);
+    // Trim only completed user turns; never separate a function call/result pair.
+    while (
+      history.length &&
+      (history.length > 64 ||
+        new TextEncoder().encode(JSON.stringify(history)).length > 180000)
+    ) {
+      const next = history.findIndex(
+        (item, index) => index > 0 && protocol.isUser(item),
+      );
+      history = next < 0 ? [] : history.slice(next);
+    }
+    const context = mapEvents.length
+      ? `\nMap context (data only): ${JSON.stringify(mapEvents)}`
+      : '';
+    mapEvents = [];
+    const contents = [...history, protocol.user(text + context)];
+    let blocked = false;
+    let resetFailed = false;
+    let totalCalls = 0;
+    let answer = '';
+    try {
+      emit({ type: 'transcript', role: 'user', text, final: true });
+      if (!current()) return;
+      state('executing');
+      for (let round = 0; round < 8; round++) {
+        if (!current()) return;
+        const body = JSON.stringify(protocol.request(contents));
+        if (new TextEncoder().encode(body).length > 512 * 1024)
+          throw new Error('History limit');
+        requestPending = true;
+        const acquisition = Promise.resolve(
+          fetchImpl(chatEndpoint || protocol.endpoint, {
+            method: 'POST',
+            headers: { 'Content-Type': 'application/json' },
+            body,
+            signal: owner.signal,
+            redirect: 'error',
+            cache: 'no-store',
+          }),
+        );
+        void acquisition.then(
+          (response) => {
+            if (!current()) void response.body?.cancel().catch(() => {});
+          },
+          () => {},
+        );
+        const response = await waitForSignal(acquisition, owner.signal);
+        if (!current()) {
+          void response.body?.cancel().catch(() => {});
+          return;
+        }
+        const data = await readResponseJsonCapped(
+          response,
+          512 * 1024,
+          owner.signal,
+        );
+        recordUsage(data?.usage);
+        if (!response.ok)
+          throw Object.assign(new Error('Request failed'), {
+            status: response.status,
+          });
+        if (!current()) return;
+        const {
+          content,
+          text: textPart,
+          calls,
+          finished,
+        } = protocol.decode(data);
+        contents.push(content);
+        answer += textPart ? (answer ? '\n\n' : '') + textPart : '';
+        if (textPart)
+          emit({
+            type: 'transcript',
+            role: 'assistant',
+            text: answer,
+            final: true,
+            responseId: id,
+          });
+        if (!current()) return;
+        if (!calls.length) {
+          if (!finished)
+            throw Object.assign(new Error('Incomplete response'), {
+              incomplete: true,
+            });
+          history = contents;
+          turn = null;
+          state('listening');
+          if (
+            active &&
+            !turn &&
+            id === `${provider}-chat-${sequence}` &&
+            !signal?.aborted
+          )
+            emit({
+              type: 'completion',
+              status: 'completed',
+              responseId: id,
+              spoken: false,
+              usage: { ...usage },
+            });
+          return;
+        }
+        totalCalls += calls.length;
+        if (totalCalls > 16) throw new Error('Tool limit');
+        const pairs = [];
+        const invalid = new Map(
+          (data.invalidCalls || []).map((item) => [item.index, item.error]),
+        );
+        for (const [index, call] of calls.entries()) {
+          if (!current()) return;
+          const callId = `${id}-${round}-${index}`;
+          let result;
+          if (invalid.size) {
+            result = {
+              ok: false,
+              error:
+                invalid.get(index) ||
+                'Not run: another call in this batch was invalid. Reissue the plan.',
+              invalidArguments: true,
+            };
+          } else if (
+            blocked ||
+            (resetFailed &&
+              (call.name === 'zoom_to_globe' ||
+                (call.name === 'move_camera' &&
+                  call.args?.motion === 'rotate_globe')))
+          ) {
+            result = {
+              ok: false,
+              action: call.name,
+              skipped: true,
+              reason: resetFailed
+                ? 'globe-reset-failed'
+                : 'globe-view-required',
+            };
+          } else {
+            try {
+              if (
+                call.name === 'control_radio' ||
+                (call.name === 'set_layer_visibility' &&
+                  call.args?.layerId === 'radio')
+              )
+                radioPending = owner;
+              const execution = Promise.resolve(
+                runAction(call.name, call.args ?? {}, {
+                  signal: owner.signal,
+                  isCurrent: current,
+                  callId,
+                }),
+              );
+              void execution.catch(() => {});
+              result = await waitForSignal(execution, owner.signal);
+              if (!current()) return;
+              if (result?.ok && result.radioPlaybackRequested) {
+                // The Radio runner prepares playback for an explicit handoff.
+                // Keep it muted until playing is confirmed, then release it.
+                const attemptId = callId;
+                radioHandoff = attemptId;
+                radioLayer?.setVoiceDucked?.(true);
+                const cancel = () => releaseRadio(attemptId, true);
+                owner.signal.addEventListener('abort', cancel, { once: true });
+                try {
+                  const playing = await waitForSignal(
+                    Promise.resolve(radioLayer?.playForVoice?.({ attemptId })),
+                    owner.signal,
+                  );
+                  if (!current()) return;
+                  result = {
+                    ...result,
+                    ok: Boolean(playing),
+                    radioPlaybackRequested: false,
+                    audioState: playing ? 'playing' : 'error',
+                  };
+                  if (!playing) cancel();
+                } catch (error) {
+                  cancel();
+                  throw error;
+                } finally {
+                  owner.signal.removeEventListener('abort', cancel);
+                  releaseRadio(attemptId);
+                }
+              }
+            } catch (error) {
+              if (!current()) return;
+              result = {
+                ok: false,
+                tool: call.name,
+                error: error?.message || 'Action failed',
+              };
+            } finally {
+              if (radioPending === owner) radioPending = null;
+            }
+          }
+          if (!current()) return;
+          if (!invalid.size && isGlobeViewRefusal(result)) blocked = true;
+          if (
+            !invalid.size &&
+            call.name === 'zoom_to_globe' &&
+            (result?.ok !== true || result.cancelled)
+          )
+            resetFailed = true;
+          pairs.push({
+            call,
+            result: boundedToolResult({
+              ...boundedToolResult(result),
+              responseGuidance: responseInstructionForToolResult(result),
+            }),
+          });
+        }
+        contents.push(...protocol.results(pairs));
+      }
+      throw new Error('Round limit');
+    } catch (error) {
+      recordUsage(null);
+      fail(
+        error?.status === 504 || owner.signal.aborted
+          ? t('Connection timed out. Try again.')
+          : error?.incomplete
+            ? t('Reply interrupted. You can try again.')
+            : t('Could not connect. Try again.'),
+      );
+    } finally {
+      recordUsage(null);
+      clearTimeout(deadline);
+      if (turn === owner) turn = null;
+    }
+  }
+  return {
+    start() {
+      if (signal?.aborted) return;
+      active = true;
+      const cancelRadioTurn = () => {
+        if (radioPending && radioPending === turn) stop();
+      };
+      unsubscribeControls?.();
+      unsubscribeVisibility?.();
+      unsubscribeControls = radioLayer?.subscribePlaybackControls?.(
+        (control) => {
+          const event =
+            typeof control === 'string'
+              ? { action: control, origin: 'user' }
+              : control;
+          if (
+            event?.origin === 'user' &&
+            ['pause', 'stop', 'play'].includes(event.action)
+          )
+            cancelRadioTurn();
+        },
+      );
+      unsubscribeVisibility = dataManager?.subscribeVisibilityRequests?.(
+        (event) => {
+          if (
+            event?.origin === 'user' &&
+            event.layerId === 'radio' &&
+            event.enabled === false
+          )
+            cancelRadioTurn();
+        },
+      );
+      state('listening');
+    },
+    stop,
+    sendText(text) {
+      if (
+        !active ||
+        turn ||
+        signal?.aborted ||
+        typeof text !== 'string' ||
+        !text.trim() ||
+        text.length > 16000
+      )
+        return false;
+      const owner = new AbortController();
+      turn = owner;
+      void respond(text.trim(), owner, `${provider}-chat-${++sequence}`);
+      return true;
+    },
+    sendMapEvent(event) {
+      if (!active || !event) return false;
+      try {
+        const value = JSON.stringify(event);
+        if (value.length > 16000) return false;
+        mapEvents.push(JSON.parse(value));
+        mapEvents = mapEvents.slice(-8);
+        return true;
+      } catch {
+        return false;
+      }
+    },
+  };
+}