The TOS, which is a contract of adhesion for consumer-facing products, does not really matter that much in my opinion since "we have to lock you in to our specific interface on our public offering" is not a cognizable interest. SCOTUS is also very clear in requiring actual damages (in incremental harms) to establish a CFAA violation. At any rate, opencode is essentially providing equitable estoppel as a service by being open and popular - cannot go after me without first dealing with the "unionized" project (last words)! I don't think they get to conflate the issues of alternative interface dispute and their intentional pricing strategy losing money on heavy users.

Of course, they are banning for financial economic interests, not nominal alleged contractual violations, so Anthropic is not sympathetic.

// NOT LEGAL ADVICE

Obviously, I think it can make sense to Anthropic since opencode users likely disproportionately cost them money with little lock-in - you can switch the moment a comparable model is available elsewhere. It does not (necessarily) mean there are any legal or ethical issues barring us from continuously using the built-in opencode OAuth though.