reactor-team

Extend this cloned HappyOyster example app - add worlds, controls, or UI on top of the typed `@reactor-models/happy-oyster` without breaking the patterns the existing code uses. Covers the per-session mode (adventure vs directing), the connect → createWorld/attachWorld → startTravel lifecycle, the authoritative world_state snapshot, the Adventure held-input model and Directing transport, and the getJwt auth route.

Extend this cloned Helios example app — add new controls, scenes, knobs, image flows, or features on top of `@reactor-models/helios` (pinned to ^0.9.0) without breaking the patterns the existing code already uses. Covers the SDK's connection / events / messages model, the phase-based UI architecture, the state snapshot pattern, the atomic `setConditioning({ prompt, image })` command for image-to-video flows, mid-stream prompt switching, the curated scene library, and prompt design rules for smooth continuous video generation.

Extend this cloned Lingbot example app — add new controls, scenes, knobs, or features on top of `@reactor-models/lingbot` without breaking the patterns the existing code already uses. Covers the SDK's connection / events / messages model, the phase-based UI architecture, the state snapshot pattern, the image-required preconditions and the `image_accepted` wait, the WASD + arrow-key driving model, and prompt design rules for coherent continuous generation.

Extend this cloned LingBot World 2 example app — add new controls, scenes, motion patterns, or knobs on top of `@reactor-models/lingbot-world-2` without breaking the patterns the existing code uses. Covers the SDK's connection / events / messages model, the layered prompt system and its override store, the per-chunk `set_camera_pose` motion channel, the WASD + mouse-look driving model, the auth route, and clip capture.

Extend this cloned XMAX X2 example app — add new controls, sources, or knobs on top of the Reactor JS SDK without breaking the patterns the existing code uses. Covers the typed @reactor-models/x2 client, the connection / commands / messages / tracks model, the single-owner source publish, the state_update reducer, the reference-image upload path, the pointer protocol, the auth route, and clip capture.

Extend this cloned SANA-Streaming example app — add controls, presets, or stage features on top of `@reactor-models/sana-streaming` without breaking the patterns the existing code uses. Covers the SDK connection / events / messages model, the two input sources (webcam and a streamed video clip) that both feed the `camera` track, the single model-driven reducer fed by the typed `state` hook, mid-stream re-prompting (~1 chunk latency), and the behaviors to preserve — the camera publish hint and streaming a clip in rather than uploading it.

Extend this cloned LongLive 2 example app — add controls, presets, timeline features, or directing affordances on top of `@reactor-models/longlive-v2` without breaking the patterns the existing code uses. Covers the SDK connection / events / messages model, the phase-based UI (setup composer vs live director), the shot-vs-cut grammar, the per-scene 48-chunk budget and how cuts extend length, scheduling against session_chunk, the storyboard store, and the read-only timeline.

Turn a loose scene idea (even a single short sentence, English or Chinese) into a production-ready LingBot-World 2 layered scene: a StructuredExample JSON — base / camera / movement layers with static+dynamic variants, stackable hold-key events (keys 1..9), and per-scene jump/crouch/stand prompts — that drops straight into the frontend's lib/lingbot-cases/, plus a derived seed-image prompt. Can also emit a single composed standalone prompt when the user wants just one prompt. Use whenever the user mentions LingBot 2, LingBot-World 2, lingbot-world-2, reactor/lingbot-world-2, layered scene, StructuredScene, composePrompt, isMoving, base/camera/ movement layers, hold keys, event keys, jumpPrompt/crouchPrompt, lib/lingbot-cases, a "playable character" video prompt, or gives a rough idea they want expanded into an interactive world-model prompt ("make a lingbot 2 scene for a knight in the desert"). Also handles requests phrased in the legacy actions.json / f-g slot export format (see references/legacy-sessions.md

Use whenever a user wants to author or refine a LingBot interactive video world, either a quick PROSE prompt or a full JSON virtual world. Covers all three viewpoints: third-person navigable-subject (driving / riding / chase), first-person traversal, and fixed spectator. Trigger on LingBot, LingBot-World, lingbot-world-fast-v1, "a prompt / base prompt / base + holds / hold-prompts" for a scene, "layered composition", a virtual world / scene file / world JSON, states / transitions / overlays / composeForRender, WASD-navigable scenes, or any "make me a prompt / scene / world for [subject/place]" request, even when the user doesn't say "LingBot" but is clearly describing an interactive video world or a steerable video-generation prompt.

Build real-time video AI applications with Reactor SDKs. Use when code imports `@reactor-team/js-sdk` or `reactor-sdk`; when connecting a web/mobile frontend to a GPU-powered Reactor model (Helios and others); when streaming video via WebRTC with command-based control; when publishing webcam input for video-to-video transformations; when handling JWT authentication for Reactor; or when debugging Reactor connection lifecycle (disconnected → connecting → waiting → ready). SKIP when project uses unrelated WebRTC (e.g., plain video calling), or video pipelines that don't touch Reactor.

Turn rough video-editing intent into precise, production-grade instructions for NVIDIA's SANA-Streaming real-time video-to-video editing model. Use whenever the user wants to edit, restyle, or transform an existing video with SANA-Streaming — swapping outfits, changing backgrounds, removing objects or watermarks, adding tracked overlays, applying an art style, re-rendering a whole scene, or restyling driving/robotics footage. Trigger on any mention of SANA, SANA-Streaming, "video edit prompt," or a request to write or improve a video-editing instruction, even when the user doesn't name the model.

Write effective prompt sequences for Reactor's Helios model, a real-time video frame generation API. Use when creating Helios prompts, video generation prompts, or when the user mentions Helios or Reactor. Covers start prompts, follow-ups, sequence planning, camera anchoring, lighting consistency, and progressive state tracking.

Build a queued, time-boxed Reactor demo with @reactor-team/queue — a PartyKit waiting-room server plus a JS/React client that admits N users at a time, has the server own session creation, mints short-lived Reactor JWTs only to admitted users, and releases sessions when time runs out. Use when adding a queue/waiting-room in front of a Reactor model, gating a viral launch, time-limiting demo sessions, migrating a non-queued Reactor app to a queued one, building an operator/admin dashboard for a queue, delegating session creation to another service (sessions sourced elsewhere or with another client already attached), or debugging queue admission, claim/session_ready, token minting, hibernation, or React autoConnect/StrictMode issues with the Reactor SDK.