Ships

Fix credits page: center content, hide offline indicator on non-chat pages

Deploy new credits page (replace old ElevenLabs version)

Add credits page: balance display, buy packs via Stripe, transaction history, clickable balance in header

Fix think-only: if AI only thinks and doesn't speak, retry with nudge to respond

Fix CreateAgentDTO: add plan, tasks fields

Add max tokens slider to agent create/edit, default 2500

Add max tokens slider to agent create/edit, default 2500, range 500-8000

Auto-fill agent name from template on selection

Default ON: memory, think, intent coherence, memory coherence for new rooms

Fix dedup: raise threshold to 0.8, shorten window to 5min — stops blocking normal responses. Louder thinking sound

Add thinking sound + typing indicator

Add thinking sound (gentle pulse) and improved typing indicator while AI generates response

Voice debounce: 3s delay before AI responds to voice, waits for user to finish speaking

Fix: STT messages now trigger AI agent responses (mention detection + alone-in-room)

Fix: say/text always available even when think is OFF — agents must always be able to speak

Styled Add/Edit Agent dialogs: dark gradient, template cards grid, teal accents, mobile fullscreen

20 agent templates, increase agent limit to 5 per room

Fix voice selector gap: remove minWidth, disable autoWidth

Fix voice on load: fetch fresh voice_id from DB, don't trust stale session cookie

Fix: accept any voice_id in profile update, remove old browser/premium validation

Fix voice: read user voice_id from DB on each transcript, not just session start

Voice: server handles everything — broadcast message + TTS directly from transcript callback, no client round-trip

Fix voice: emit directly in onTranscript callback, bypass sendMessage stale closure

Don't pause voiceCapture during audio playback — echo filter handles it, pausing kills the stream

Fix Transcribe stream dying: send silence to keep connection alive between speech

Fix voice default: fallback old browser voices to Joanna in preferences context

Voice selector: show short name in toolbar, full name in dropdown, min 70px width

Fix TTS: fallback invalid voice IDs to Joanna, updated all users/agents in DB

Fix TS2345: non-null assert on data.voice

Server-side TTS for user messages, fix duplicate transcripts, remove client TTS calls

Fix duplicate text, add TTS debug logging, deduplicate transcripts

Fix: 5s flush for long speech, increase TTS text limit to 5000, mobile voice selector sizing

Real-time voice: text sent immediately, TTS generated in background, chat_audio broadcast

Skip TTS generation for voice-captured messages — user already spoke them

Real-time STT: streaming Transcribe session, transcripts arrive as you speak

STT debug logging: chunk sizes, total bytes, transcript output

Voice mic: show errors as toast, fall back to Web Speech API on failure

Voice capture: raw PCM via Web Audio API instead of MediaRecorder webm, 16kHz downsampled

Fix Transcribe: type casts, ogg-opus encoding, 48kHz sample rate for webm audio

Fix double message: voiceCapture takes priority over voiceStream, remove duplicate path

Fix Comprehend LanguageCode type cast

Voice pipeline: MediaRecorder STT (no beeps), Amazon Transcribe, Comprehend sentiment, emotion-aware Polly TTS

Fix mic beeping: only restart after recent speech, stop silently after 30s of silence

Add Clear My Data: deletes content but keeps account and financial records

Add Claude Opus 4 to available models

Fix x-forwarded-for type in profile route

Fix deleteAccount: correct field names for claude_log and panel_log

Profile: clickable username, delete account with audit log, signup IP logging

Add credit balance to header next to connection status

Add Claude API, fix voice echo (pause mic during AI playback), increase restart delay

Add Android download button on desktop with mobile app setup popup

Terminal onboarding: context-aware for native app, mobile browser, and desktop

Fix TypeScript cast for native terminal agent check

Terminal panel: Share This Phone button for native app, mobile agent toggle

Terminal panel: creator-only downloads and input, informational view for non-creators

Terminal onboarding: download buttons in empty state, localStorage persistence, auto-open for new rooms

Make all X close buttons red and bigger (22px) across all panels

Fix room settings dialog: add safe area top padding on mobile

Room settings: reorder sections, collapsible AI Commands, members and invite at top

Fix syntax error in room settings styling

Room settings: teal gradient theme, glowing borders, compact layout, styled sections

Room settings: fullscreen on mobile, responsive grids, close button, tighter spacing

Move 'hear my own voice' to room settings, remove settings gear icon and panel

YouTube-style volume slider, remove stop audio button

Add tiny volume slider in chat input toolbar next to voice selector

Add voice selector dropdown in chat input toolbar next to mic button

Fix invite link: switch room immediately on connect instead of unreliable timeout

Default voice to Joanna when none selected

Add echo cancellation: filter mic input that matches recent AI speech output

Fix speech recognition: reduce restart noise, keep session alive longer

Fix speech recognition: reduce restart noise, use interimResults to keep session alive longer

Remove browser voices from Room Settings agent voice dropdown

Remove browser voices entirely, Polly only

Fix Polly: list all voices (not just neural), auto-pick best engine per voice

Fix: rename ELEVENLABS_COST_PER_CHAR export to POLLY_COST_PER_CHAR

Fix Polly VoiceId type cast

Fix: include Polly adapter in deploy

Replace ElevenLabs with Amazon Polly TTS — 75x cheaper, same AWS region

Fix settings panel mobile: position fixed with left/right anchoring to fill screen

Shrink settings panel width from 280px to 220px

Remove alarm button, fix settings panel mobile overlay with safe area

Mobile safe area: status bar padding, correct chat height, viewport-fit cover

Make website mobile-responsive: compact header, responsive activity bar, fullscreen panels on mobile, hide format toolbar

Add SEO: meta tags, OG image, robots.txt, sitemap.xml, landing page metadata

Add landing page for new visitors

Add landing page with CTA, update register features, redirect home to landing

Fix header layout: push connection status, username, profile, logout to right side

Restore credit and payment API routes for monetization

Remove web browser, watch party, watchlist, screen share, scheduled jobs, daily stats, about page

Remove entire forum system: pages, panel, routes, actions, data layer, AI commands

Add close button to settings panel

Remove cost calculator display, spending bar, credits page, and payment routes from UI

Default off: intent/memory coherence, think, effort, tokens, audit, extended thinking

Add toggleable Intent Coherence and Memory Coherence settings in room settings

Remove entire hologram system

Credits page: line graph for Grok + ElevenLabs usage by day

Redesign credits page with usage graph, time range filter, service breakdown

Add Room AI Controls: create/delete/update agents via Helper Bot

Auto-create default hologram avatar for new AI agents

Set Helper Bot voice to Ash - Conversation (ElevenLabs)