Post

We’re announcing Standard Code: a new coding agent with unlimited use, like a cell phone plan. Each line has no 5-hour, weekly, or rate limit and powers one coding session. More lines = more parallel sessions. How is unlimited use possible? 👇

In Standard Code you don’t pick models, you pick Agents. At launch, two agents are included: - Unlimited One - Sama One (for OpenAI subs) Each is a carefully curated, Pareto-optimized coding agent that uses many models across the various domains in coding.

For Unlimited One, each parallel session requires purchasing a line of service. Just like a cell phone bill, it’s a predictable expense and won’t leave you out of tokens at the end of the week.

Sama One lets you bring your Codex sub to Standard Code, unlocking infinite parallel lines. It sips your weekly OpenAI usage because it, too, is a heavily optimized, curated collection of domain-specific agents built on OpenAI’s latest models.

Where is the durable boundary between cloud thread and machine daemon? If the daemon drops after receiving a tool request but before its result is acknowledged, does reconnect replay an idempotency-keyed intent/result, or can the mutation run twice? That's the ‘walk away’ case I'd test.

The cloud sends the tool call and suspends and waits for the result to arrive via endpoint. Execution is not always idempotent (can’t be, you cant delete a file twice) but the call is, and is tracked. Any connection failures buffer the tools and replay them after negotiation

Tracking the call ID closes the retry boundary only if the daemon durably records accepted/completed state and a replay returns the stored result instead of re-executing. On reconnect, does the cloud resend the same call ID, and does the daemon retain the result until the cloud acknowledges it?