This paper presents a unified modeling, estimation, and feedback framework for reconfigurable intelligent surface RIS-assisted optical wireless links. The key modeling element is a long-exposure pixel gain that extends the classical diffraction-limited response by statistically averaging angular jitter and mispointing; it admits an exact real-integral form and captures boresight attenuation and progressive sidelobe filling. The end-to-end system couples free-space path loss, Beer--Lambert atmospheric extinction, pixel-level diffraction, and optical efficiency with a unitary-pilot least-squares channel estimator and quantized phase feedback. Analysis closely matches Monte Carlo simulations and yields concrete design rules: with a surface of N=64 pixels, pilot length $M=2N$, and pilot SNR=20 dB, the normalized mean-squared error is0.005, implying an effective-SNR loss of about 0.5 and a capacity penalty of 0.007bits-s. Six-bit phase quantization introduces no measurable additional penalty at these operating points, setting a practical benchmark for feedback resolution. Training overhead scales strongly with pixel geometry: halving pixel width (quartering pixel area) increases the pilot length required to maintain the same NMSE by roughly fourfold. The framework reconciles physical-optics modeling with estimation-and-feedback design and provides a principled basis for scalable link budgeting in RIS-assisted optical networks.