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
..
docs	feat(core): elide historic video-mode frames from model context	2026-07-07 20:43:26 +05:30
scripts	Code mode: make packaged builds work via managed engine provisioning (#625)	2026-06-17 21:53:15 +05:30
src	feat(core): elide historic video-mode frames from model context	2026-07-07 20:43:26 +05:30
.gitignore	bootstrap new electron app	2026-01-16 12:05:33 +05:30
package.json	feat(apps): M3 groundwork — packager, GitHub device-flow auth, registry client	2026-07-06 14:49:52 +05:30
tsconfig.build.json	Refactor builtin file tools beyond workspace scope	2026-05-25 16:21:51 +05:30
tsconfig.json	feat: extract presentation generator into executable code with builtin tool	2026-01-30 13:30:06 +05:30
vitest.config.ts	Refactor builtin file tools beyond workspace scope	2026-05-25 16:21:51 +05:30