OpenAI-compatible inference relay with model-bound profiles

Hive can now act as an OpenAI-compatible inference relay. Model-bound profiles give you a stable model name that can be retargeted to a different upstream provider or model without changing client settings. Each profile carries one or more tokens, so you can issue separate tokens per repository, workflow, or team and still get a single usage and cost view. The relay exposes OpenAI-compatible models and chat completion endpoints, including streamed responses, and records input tokens, output tokens, estimated United States dollar cost, and audit activity per request. Providers can be created in the dashboard or loaded from environment configuration, with credentials encrypted when managed in Hive. The operations dashboard adds an Inference section with profile and provider lists, detail and