generate-scene

name	generate-scene
description	Turn a natural-language scene request into a Genie Sim scene — an LLM writes a Scene-Language DSL program (`LLM_RESULT.py`), and `geniesim_generator.app` compiles it into `scene.usda` + a layout graph under benchmark/config/llm_task/. Works either through the Open WebUI agent, OR by having Claude write the DSL program directly and run the compiler (no WebUI / no MCP server needed). Trigger: When the user asks to "生成一个场景", "按需求生成场景", "generate a scene", "make a scene with <objects>", "build a tabletop layout", "create scene.usda from a description", "直接写脚本生成场景", "绕过 webui 生成场景", or wants the generator to produce a scene from a prompt.
license	MPL-2.0
metadata	{"author":"genie-sim","version":"1.0"}
prerequisites	["geniesim_generator:search-assets","geniesim_generator:deploy-generator"]
inputs	[{"name":"prompt","desc":"Natural-language description of the scene to generate","required":true},{"name":"output_name","desc":"Stem for the produced `LLM_RESULT.py` + `scene.usda`","required":false},{"name":"use_webui","desc":"Route through Open WebUI (true) vs author DSL directly (false)","required":false,"default":"true"}]
outputs	[{"desc":"`scene.usda` + layout graph under `benchmark/config/llm_task/<output_name>/`, plus the `LLM_RESULT.py` source"}]

When to Use

• User describes a scene in words and wants the generator to produce it (scene.usda + scene_info.json + layout graph).
• User has an LLM_RESULT.py (hand-written or LLM-produced) and wants to compile / preview it.
• User wants a quick one-shot scene without standing up Open WebUI / MCP — Claude writes the DSL program directly (Path B below).

Prerequisite only for Path A (the Open WebUI agent loop): the MCP stack + Open WebUI are running (deploy-generator first). Path B needs just the package importable + ASSETS_INDEX available — no servers.

Do not use for:

• Standing up the servers → deploy-generator skill.
• Just browsing assets → search-assets skill.

The pipeline (what actually happens)

NL request
  │  ── Path A: Open WebUI "geniesimscenegen" agent (uses search_assets/get_interactions)
  │  ── Path B: Claude writes the DSL program directly (no WebUI / no MCP server)
  ▼
Python program:  from helper import *  →  @register()… def root_scene() -> Shape
  │  written to → src/geniesim_generator/LLM_RESULT.py
  ▼
cd src/geniesim_generator && python app.py  (imports LLM_RESULT.root_scene, runs it)
  │  gen_scene_layout_info → (scene_info, networkx graph)
  │  gen_scene_usda        → scene.usda
  ▼
benchmark/config/llm_task/<scene_id>/<n>/{scene.usda, scene_info.json, graph.dot, graph.svg, LLM_RESULT.py}

The program is the only handoff between "write" and "compile" — so Path A and Path B differ only in who writes it. Path B (Claude writes it directly) needs neither Open WebUI nor the MCP servers running; it only needs the package importable and ASSETS_INDEX available.

Workflow

Step 1 — Produce LLM_RESULT.py from the request

Two ways; pick by whether the WebUI/MCP stack is up.

Path A — via the Open WebUI agent (the deployed loop)

Drive the geniesimscenegen agent (import config/geniesimscenegen.json; MCP tools wired via config/openwebui.json). Describe the scene; the agent searches the asset library, writes a DSL program, and its "save to file" action drops it at generator/LLM_RESULT.py. Requires deploy-generator first.

Path B — Claude writes the program directly (no WebUI, no MCP)

When the servers aren't up (or you just want a one-shot scene), and run the compiler. This is the lightweight path.