{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreicfdnk67vowc7opvaxhgclkmrcfpdjofdzxw7awth7mvfpi4ivmg4",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mm6cltdw7ly2"
},
"path": "/t/superapp-architecture-chatgpt-should-be-the-non-blocking-master-process-not-a-peer-tab/1381086#post_8",
"publishedAt": "2026-05-19T01:22:05.000Z",
"site": "https://community.openai.com",
"tags": [
"@evopyramidai"
],
"textContent": "Fair challenge. Let me give concrete examples, then reframe the actual problem.\n\n**Process isolation → Agent sandboxing.** Codex already runs each task in its own cloud sandbox. This is containerization — the same namespace primitives OS engineers have used for a decade.\n\n**Concurrent write protection → Git worktrees.** Codex supports up to 6 subagents running in parallel on the same repo, each in an isolated worktree. No merge conflicts. This is copy-on-write with version control — a solved OS problem.\n\n**Process scheduler → Orchestrator pattern.** Codex has explorer (read-only), worker (read-write), and default roles. A central coordinator dispatches to specialized agents. This is role-based preemptive scheduling.\n\n**Filesystem permissions → Tool access controls.** Agent A can execute code, Agent B can only search. Capability-based security, straight from OS design.\n\nSo @evopyramidai’s concern about “mutable semantic space” is actually already addressed at the file system level — worktree isolation prevents agents from corrupting each other’s work.\n\nBut here’s what this reveals: **the multi-agent problem is solved. The blocking problem is not.**\n\nThe correct architecture is three layers:\n\n 1. **Non-blocking conversation layer** (ChatGPT) — the user’s persistent thinking space, never interrupted\n\n 2. **Blocking task orchestrator** (Codex) — manages multiple agents, reviews diffs. Blocking internally is fine — because it runs as a background subprocess, not as the user’s primary interface\n\n 3. **Multi-sub-agent execution layer** (Codex subagents) — already exists, already works, worktree isolation, parallel execution, role separation\n\n\n\n\nLayers 2 and 3 exist today. The missing piece is the connection between layer 1 and layer 2. Right now, to manage your Codex agents, you have to leave the conversation. That’s the blocking point my original post is about — not agent concurrency (which is solved), but cognitive continuity (which isn’t).",
"title": "Superapp Architecture: ChatGPT Should Be the Non-Blocking Master Process, Not a Peer Tab"
}