We introduce Continuous Interaction Diffusion (CID), a diffusion-native model-runtime architecture that integrates tool interaction into iterative denoising. CID separates a model-read-only fact channel, a thought channel represented by a Typed Cognitive Tensor, and a display channel. Information needs can emerge before a textual or JSON call is fully serialized, allowing perceptual bindings to launch external reads while denoising continues. Returned results are projected into the evolving thought state and can revise earlier cognition and display regions. Persistent bindings reuse static results without repeated external execution and refresh changing sources when needed. CID is designed to expose evidence earlier, overlap tool latency with model computation, reduce duplicate external work, and preserve useful computation after new evidence arrives. We formalize the architecture, runtime, and training objectives, and define an evaluation protocol for task quality and end-to-end efficiency. This first paper focuses on read-only tools and makes no empirical performance claims. Blogger's Review: This paper proposes an innovative diffusion-native model-runtime architecture that integrates tool interaction into iterative denoising, aiming to improve task quality and end-to-end efficiency. Although the paper makes no empirical performance claims, the potential of this architecture is worth further exploration and research.