"What is the OpenAI Agents SDK's defining architectural contribution?"	The 2-layer harness/compute split. Loop runs on your backend (harness layer); tool execution runs in a sandbox (compute layer). Credentials NEVER enter the compute layer — the SDK architecture PREVENTS it.	harness-engineering::dd11::recall
"Name the 7 sandbox providers."	Local bash · Docker · E2B · Modal · Daytona · Cloudflare · Vercel. Behind a uniform abstraction; swap by CONFIG, not code change. Harness is provider-agnostic.	harness-engineering::dd11::recall
"Why does the 2-layer split make credential isolation 'architectural, not optional'?"	The SDK PREVENTS credentials from entering the compute layer — there is no code path for it. You cannot accidentally put creds in the sandbox because the architecture doesn't allow it. Not a policy; a structural impossibility.	harness-engineering::dd11::analysis
"The SDK scores 38/55 — highest on which module?"	Module 5 (Sandboxing): 5/5. The 7-provider abstraction is the most architecturally thoughtful sandboxing in the roster. Also strong on Module 1.3 (Subagents): 4/5 — handoffs + agents-as-tools as first-class primitives.	harness-engineering::dd11::recall
"Handoffs vs agents-as-tools — what's the difference, and why does the SDK offer BOTH?"	Agents-as-tools: parent calls subagent like a tool, sync, keeps control, gets structured result. Handoffs: parent TRANSFERS control (terminal), loses visibility. The SDK offers both because different tasks need different control models (Module 1.3).	harness-engineering::dd11::analysis
"Why is the SDK described as 'not a finished harness'?"	It's PRIMITIVES — loop, tool, sandbox, handoff, agents-as-tools. You BUILD the harness with it. No built-in memory, observability, or permission model. You bring those. The SDK gives you the architectural foundation; you add the layers.	harness-engineering::dd11::application