4.3 KiB
4.3 KiB
TODO
Ordered backlog. CURRENT.md tracks the live session state.
Where the project finished (2026-09-13)
- The validated core bridge is live: a fixed action list, input validation, structured errors, and a
hard outbound rate limit. See
docs/core-bridge.md. - The daemon uses the core bridge. QR login, pacing, the trigger log, trust tiers, context, the response policy, the continuation window, the persistent action log, and the read-only voice state all work.
- Human pacing is live: a fast first send (30-200 ms), burst sends (500-2800 ms), and a variable
5-20 s burst reset. Reads take a small gap. See
docs/daemon.md. - User search reads the client cache and guild members.
voice.getsearches all guilds without aguildId.voice.overviewlists occupied channels per guild. - The web UI follows the Nocturne design handoff: the 7a debug shell with the guild rail, message
view, voice membership, agent console, Takeover read-only gate, and a Settings slide-over for
core process, login, visible guilds, and the action log. Messages fetch the latest 50 on open;
attachments use CDN links; avatars and guild icons load from the CDN. Drafts survive reloads.
Roadmap surfaces show as placeholders. See
docs/webui.md. dm.listlists cached DM and group DM channels.list_dmsexposes it over MCP.- The daemon starts, stops, and restarts the client, and the Settings panel runs the QR login.
- Mock end-to-end tests pass: tiers, continuation, sensitive replies, batch MCP, and voice state.
- Repo note: use
zib/Veskslop-t(remoteveskslop-t) until the original repo's server hook is fixed.
Paused
- The
pollcommand.POLL_ENABLEDisfalseinpoc/src/puppet.ts. The parser and tests stay. - The setup command flow. The reaction-based multiple-choice design is on hold.
- The LLM attachment and MCP event delivery. Parked by the owner.
Deferred
- Voice auto-leave,
stay @user, invite-link joins, audio in and out, and video streaming. The plan is indocs/voice.md. The basic voice actions exist; auto-leave and audio do not. - Client lightening. Low priority. The client must stay stable.
- Web UI authentication and remote accounts.
Next
- Voice auto-leave (
voiceLeaveDelaySeconds) and thestay @usercommand. - Live verification on the audio host: TTS local + API, ducking, capture,
voice.join/voice.leaveend to end, and a full QR approval. - Browser microphone puppeting: a mix sink so the browser mic and TTS share
veskslop_mic, apacatinput path, and echo handling. - Speech to text: Vosk (small CPU model in
poc/models/) is wired and verified; add more languages or a larger model when needed.VESKSLOP_STT_CMD/_API_URLstay available. - Notification parsing: edits, deletes, reactions, and message references.
- Reply-to-puppet counts as a trigger.
- Per-user rate limit and command cooldowns.
- Collector account: stripped-down read-only modules. Use it when the puppet cannot find a user's voice channel or the channel members.
Web UI follow-ups
Ordered after the voice backend unless the owner asks first.
- Favourites, presence dots, and real member counts.
- MCP tool-call tracing in the console Tool calls tab.
- Transcript tab fed by the audio capture and STT.
- Yield (stop mid-line) for TTS when a human speaks.
- DM scope in the header (the guild picker becomes "Direct messages").
- Message editing, deletion, reactions, and history pagination.
- The remaining mockup screens: 7b/7c console details, 6b history window, 4b group chat, 2c state legend, 1c phone layout.
Open decisions
- Web UI auth. Accepted: no auth, LAN or Tailscale only. Revisit before any wider exposure.
- MCP event delivery. Parked. Options when it returns:
- Poll
get_message_logandget_action_logwith asincecursor. No new transport work. - A stateful Streamable HTTP session. The server can send notifications.
- A separate local event stream over SSE or a WebSocket.
- Poll
- Untrusted logging. Untrusted interactions are ignored at this time. The separate 30-entry buffer exists but receives nothing. Decide whether to log untrusted DMs and mentions again.
- Privacy pass. Only token-shaped and
mfa.strings are redacted, and only in the persistent action log. Decide the fuller policy (retention, cache clearing, message redaction) later.