Adds a web-based UI for generating scene skill packages:
- Node.js HTTP server (zero npm dependencies) on port 3210
- HTML page with glass-morphism UI, dual-panel layout, settings modal
- LLM-powered scene-id/scene-name auto-extraction from directory contents
- Real-time SSE progress streaming during skill generation
- Spawns sg_scene_generate CLI with configurable parameters
- Windows-compatible startup scripts (serve.sh + serve.cmd)
- Rust integration tests for server files and HTML structure
Architecture:
Browser (HTML/JS) → Node.js server → LLM API + cargo run → sg_scene_generate
Files:
frontend/scene-generator/{server.js,config-loader.js,llm-client.js,generator-runner.js,sg_scene_generator.html,serve.sh,serve.cmd}
tests/{scene_generator_server_test.rs,scene_generator_html_test.rs,scene_generator_llm_test.js}
docs/superpowers/{plans,specs}/2026-04-16-scene-skill-generator*
🤖 Generated with [Qoder][https://qoder.com]
- Auto-connect WebSocket on page load in service console
- Settings modal for editing sgclaw_config.json (API key, base URL, model, skills dir, etc.)
- UpdateConfig/ConfigUpdated protocol messages for remote config save
- save_to_path() for SgClawSettings serialization
- ConfigUpdated handler in sg_claw_client binary
- Protocol serialization tests for new message types
- HTML test assertions for auto-connect and settings UI
- Additional pending changes: deterministic submit, org units, lineloss xlsx export, browser script tool, and docs
🤖 Generated with [Qoder][https://qoder.com]
The `expected_domain` was removed from args for normalization but never
re-inserted, causing JS scripts to receive empty expected_domain and
report "missing_expected_domain" errors.
🤖 Generated with [Qoder][https://qoder.com]
Plan for modifying build_eval_js to support async scripts.
Two tasks: modify callback_backend.rs, add test case.
🤖 Generated with [Qoder][https://qoder.com]
Design for fixing Promise serialization issue in build_eval_js.
Async functions return Promise which gets JSON.stringify'd to "{}".
🤖 Generated with [Qoder][https://qoder.com]
Keep the ws submit path while bringing over main's deterministic lineloss routing and the focused merge verification updates.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add the tq lineloss design spec and implementation plan documents used for the deterministic submit work.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Keep browser-attached workflows on the configured direct-skill path and align the Zhihu export/browser regression contracts with the current ws merge state.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Keep the ws branch focused on websocket and Zhihu behavior by dropping staged scene-routing artifacts and restoring single-path skills dir semantics.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Capture the approved fault-details staged-skill design and implementation plan so the remaining work can be resumed from the documented contract.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add fixed direct-submit skill loading from configured staged skills and validate directSubmitSkill early so malformed configs fail before routing.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Document the post-main cleanup steps for removing staged scene routing from the ws branch while preserving websocket and Zhihu flows.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Capture the command-center operation analyses, inventory outputs, and browser pipeline reference files produced during the current research pass so they can be reviewed from the branch.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add registry-driven scene routing and multi-root skill loading so fault-details and 95598 scene skills can be triggered from natural language while still running through the browser-backed runtime.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Consolidate the browser task runtime around the callback path, add safer artifact opening for Zhihu exports, and cover the new service/browser flows with focused tests and supporting docs.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
