v2.5.1

Released August 28, 2026

A maintenance release that restores real‑time streaming for government GPT‑5.6 Terra & Luna models and improves reliability.

🔧 Improvements & fixes

• Real‑time streaming for government models. Responses from government models (including GPT‑5.6 Terra & Luna and GPT‑5.4) now stream in real time as they are generated, instead of buffering until the full reply is ready.
• No more stalls during coding‑assistant sessions. Resolved an issue where certain government models could appear to hang during Codex interactions because responses were buffered rather than streamed.
• Improved Google model integration. Updated the Google model integration for more reliable responses.

🔒 Security & platform

Ask Sage services are delivered as FIPS‑hardened, digest‑pinned, and cosign‑signed images within the FedRAMP Class D authorization boundary, and are continuously rebuilt against the latest patched base images as part of Ask Sage’s continuous‑monitoring commitment.