Arjun 05d7fa41cf feat(core): elide historic video-mode frames from model context ... Video-mode webcam and screen-share frames matter for the response they were captured for; afterwards the assistant's own text carries the takeaway and fresh frames arrive with every new call message, yet each message's frames (~10k tokens) were resent on every subsequent model call. The elision decorator now strips image parts from prior-turn user messages, leaving a text part recording how many frames of each kind were dropped. The current turn's just-captured frames are always sent verbatim, and the policy generalizes the existing config (elideHistoricImages, default on). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>		2026-07-07 20:43:26 +05:30
..
session-design.md	docs(x): turn runtime + session layer design specs	2026-07-02 14:20:44 +05:30
turn-runtime-design.md	feat(core): elide historic video-mode frames from model context	2026-07-07 20:43:26 +05:30