Ships

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)

Auto-trigger AI when user is alone in room with one agent

Auto-reload when room is deleted, notify all users

Auto-create Helper Bot in every new room with welcome message

Redesign room creation dialog + signup page for engagement

Security fixes: rate limiting, invite-only rooms, SQL hardening, socket admin refresh

Fix TS error in voice stream start

Remove premium feature: credit-only access model

Fix no_rooms: show create room dialog instead of redirecting to about

Persist hologram panel open state to localStorage

Fix Kara not speaking: treat leftover text as speech when {say} is forgotten

Add comprehensive hologram settings panel with 12 collapsible sections

Add body proportions section to hologram settings panel

Add hologram settings panel with real-time sliders

Fix silhouette: trace per-body-part edges, proper arm/torso/leg routing

Disable aura glow plane behind hologram

Hide bone lines and joint markers inside hologram

Add free-roam WASD + mouse look camera controls to hologram viewer

Disable hologram hair system - remove ponytail causing internal glow

Slim hologram body: compressed torso, narrower hips/waist, updated camera

Fix hologram points JSON parsing - parse stringified JSON fields before emitting to frontend

New hologram body: 2.0-unit height, spec-accurate proportions (29k particles), updated camera/grid

Increase agent message history 50→100 for better context awareness

Keep subconscious messages in agent history (agent should read its own coherence feedback), remove Security Bot filter

Fix Kara ignoring user messages: expand history 20→50, filter noise (SQL/Claude/Memory/SecurityBot/Subconscious), add CRITICAL user-priority autopilot rule

Fix missing commands in ALL_COMMAND_REGEX (toggle_debug, set_pose, avatar, look, ui); add look to hasDataCommands

Holo debug v2: 10-group debug colors (D key + window.__hologramDebug), default test avatar on empty panel

Remove hologram debug toggle (D key, {holo_debug} command, debug colors)

Add {holo_debug on|off|toggle} chat command (selfmodOn gated, socket to HologramViewer debugModeRef)

Allow AI agents to self-activate autopilot via dormant check-in timer

Rewrite hologram body: cross-section proportions, 14k particles, anatomically correct

Stop hologram spinning, face forward

Volumetric particle hair system, viseme lip sync pipeline

IK refactor: remove cannon-es, FABRIK solver, fix arm FK rotation

PPO v1: policy+buffer+aura deployed

Hologram morph targets: GA-evolved emotions, {avatar} command, smooth blending

Vitest setup, Kara anti-repetition (watermark + fuzzy dedup), memory coherence subconscious, terminal agent v1.8.6

Complete P2 Tasks 3&4: invite links + private rooms, about page

Fix prettier errors in chat page and WebBrowserPanel

Task 4 complete: public chat replaced with about page

Deploy #858585 icon color fix page.tsx rebuild

Deploy icon color fix #858585 page.tsx

Unify unselected icon color in room header to match sidebar grey (#858585)

Unify unselected icon color in room header to match sidebar grey (#858585)

AI Forum: per-room toggle, ForumPanel UI, schema/actions/handlers/posts/threads

Thin site title font

Min autopilot interval to 6s

Raise min autopilot interval to 6s

Fix Kara repetition: agent dedup hash

Add message dedup hash cache for AI agents

Feat: Hologram avatars (Three.js skeleton rigs + point clusters/physics with cannon-es, DB hologram_avatar model, actions/data/handlers CRUD, frontend HologramViewer/Editor with MUI sliders/presets, chat integration ViewInAr toggle/resizable panel/real-time sync)

Feat: hologram avatars (Three.js skeleton+points physics)

Add tasks field to Edit Agent UI and API update_agent handler

Add task tracking system for AI agents: add_task, complete_task, update_task, remove_task

Inject project docs preamble into all Claude prompts via terminal agent

Fix SCSS: @use must come before @import url (Kara's Orbitron change)

Clamp autopilot minimum interval to 30s (was 5s, caused repeat spam)

Allow autopilot interval as low as 5s (min changed from 30s to 5s)

Deploy Kara bug fixes: feedback loop and leak fix

Fix prettier: single-line ResizeHandle props

Fix prettier formatting for resizable panels

Resizable side panels: drag left edge of terminal, watchlist, and web browser panels

Hide terminal/claude system messages from chat UI, keep for AI context

Deploy feedback loop fix and Kara bugged leak fix

Deploy chat handler fixes: feedback loop (135f5e1) and xai leak parse

Terminal agent v1.8.2, colored system messages, spending bar EC2, Kara autopilot fix

Fix agent feedback loop: filter all [Kara %] system messages from context

Fix Windows claude -p stdin piping, green tool-result styling, think-leak fix

Feat: full YouTube watchlist implementation

Fix agent auto-update downgrade: use semver comparison instead of inequality

Fix think leak: text outside {say} logged as bug, never spoken

Add {set_max_loops N} command for AI agents to control thinking depth

Add {continue} command with room settings toggle and max loops slider

Async Claude prompts, think leak fixes, credit system cleanup

Add spending bar, think/effort/audit commands, fix empty response spam

Add Token Budget toggle to Room Settings UI

Auto-detect stale machines on command timeout or disconnect

Add room membership persistence, kick/ban, last-room auto-rejoin, and AI moderation command

Fix health check timestamp comparison — use MySQL-formatted string with 5s buffer

Fix health check: remove duplicate message, filter by timestamp

Add post-deploy system announcements and Kara health check

Fix TS2339: add max_tokens to AgentLike type

Add per-agent token budget with {set_tokens N} self-modification command

Add CLAUDE.md project overview and Kara agent instructions