Claude Code's self-hosted beta is not self-hosted inference.

Anthropic's own docs confirm prompts, model responses, tool results (which include code Claude reads) and session transcripts still travel to and are retained by Anthropic. Inference can't be routed through Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, or an LLM gateway, which closes the usual enterprise escape hatches. If you're evaluating this for compliance, read it as network and filesystem isolation, not data isolation. The win is over artifacts and secrets, not over the conversation.