Bridge Trace: Why Execution Should Be Planned Before Calling SketchUp
Explains why live SketchUp execution should be preceded by an inspectable, testable, replayable bridge trace.
sketchup-agent-harness
8 public items tagged sketchup-agent-harness.
Why design_model.json Has to Come Before the SketchUp Scene
Explains why the SketchUp scene is an execution view while the structured design model is better for agent reasoning, validation, repair, and replay.
Headless Smoke, Live Bridge, and Installed Packages: How to Verify an Agent Harness
Explains why an agent harness needs headless smoke, live bridge checks, release smoke, and installed package verification.
From MCP Server to Ruby Bridge: Turning Natural Language into Executable SketchUp Operations
Explains how the MCP server, execution trace, JSON-RPC, Ruby bridge, and feedback loop turn natural language into executable operations.
Making Imports Repairable: From Source Evidence to Working Truth
Explains why plan import should preserve source evidence and generate repairable working truth instead of promising perfect recognition.
Runtime Skill Boundaries: Designer Skills, Dynamic Skills, and Development Skills Should Not Mix
Explains the product boundary between product runtime skills, project dynamic skills, and maintainer development skills.
Semantic Component Registry: Letting Agents Place Objects Instead of Merely Searching Model Assets
Explains why agents need a semantic component registry instead of only searching 3D model assets.
SketchUp Agent Harness Technical Architecture: Why the Agent CLI Is Only the Entry Point
Explains why Codex and Claude are entry points while the durable SAH core is the MCP server, project workspace, bridge trace, and SketchUp bridge.