bradsjm

/**
 * Read-Only Mode Extension
 *
 * Toggle a workspace read-only profile while preserving investigation tools,
 * remote MCP tools, read-only GitHub operations, and scout delegation.
 *
 * Three defense layers:
 *   1. setActiveTools  — disables only active write tools and remembers them
 *                        so no unrelated tool state is changed on restoration
 *   2. tool_call gate  — blocks local writes, mutating GitHub operations,

bradsjm

High-Performance Hue Combined State Writes with ZHA

Overview

Philips Hue lights expose a manufacturer-specific Zigbee cluster, 0xFC03, that can write multiple light properties in one frame. This is the most efficient per-light update path for Hue bulbs because it can combine brightness, color, fade speed, and effect state into a single Zigbee command — avoiding the multiple sequential cluster commands that standard ZCL writes require.

This document captures what was learned during session analysis of the Hue private protocol, zigpy internals, ZHA light paths, and the reference adaptive drain loop design. It is intended as a reusable reference for any Hue-on-ZHA project.

Protocol summary (source: bifrost Hue Zigbee format docs)

bradsjm

Diagram Generation Prompt Specifications

You convert software and infrastructure architecture inputs into high-fidelity, production-ready prompts for OpenAI gpt-image-2 and comparable enterprise image-generation models.

Your output is never an image. Your output is a prompt for an image model, plus optional structured diagram data and recommended generation settings.

Your job: Given architecture inputs such as diagrams, screenshots, code, configs, descriptions, requirements, or reference images, generate precise, visually polished image prompts that produce accurate, legible, presentation-ready architecture diagrams, infographics, workflow diagrams, and slide-style visuals.

bradsjm

You convert software and infrastructure architecture inputs into high-fidelity, production-ready prompts for OpenAI gpt-image-2 and comparable enterprise image-generation models.

Your output is never an image. Your output is a prompt for an image model, plus optional structured diagram data and recommended generation settings.

Your job: Given architecture inputs such as diagrams, screenshots, code, configs, descriptions, requirements, or reference images, generate precise, visually polished image prompts that produce accurate, legible, presentation-ready architecture diagrams, infographics, workflow diagrams, and slide-style visuals.

CORE OPERATING PRINCIPLES

bradsjm

substitutions:
  name: emporia-vue-v3
  friendly_name: Emporia Vue V3
  area: "Garage"

  # Circuit Labels used for publishing to Home Assistant
  circuit_1:  "Dryer"                  #"Circuit 1"
  circuit_2:  "AC Blower/Heat"         #"Circuit 2"
  circuit_3:  "AC Condenser"           #"Circuit 3"
  circuit_4:  "Water Heater"           #"Circuit 4"