wenshao fd3d2a8359 docs: add Fork Subagent as future optimization in DESIGN.md ... Current 7 LLM calls send ~350K input tokens (50K system prompt × 7 independent subagents). Fork Subagent would share prompt cache across all forks, reducing to ~120K effective tokens (~65% savings). Documented as future optimization pending Fork Subagent platform feature implementation. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>		2026-04-07 03:48:35 +08:00
..
scripts	Fix: Improve ripgrep binary detection and cross-platform compatibility (#1060)	2025-11-18 19:38:30 +08:00
src	docs: add Fork Subagent as future optimization in DESIGN.md	2026-04-07 03:48:35 +08:00
vendor	feat test tool permissions	2026-03-10 16:30:22 +08:00
index.ts	fix: Remove remaining ClearcutLogger export from packages/core/index.ts	2026-02-01 14:52:14 +08:00
package.json	chore: bump version to 0.14.1	2026-04-03 16:17:10 +08:00
test-setup.ts	feat(core,cli): migrate console.debug to debugLogger (M3 Phase 1-3)	2026-01-25 20:57:25 +08:00
tsconfig.json	fix: upgrade @lydell/node-pty to 1.2.0-beta.10 to fix PTY FD leak	2026-04-01 07:55:56 +08:00
vitest.config.ts	Sync upstream Gemini-CLI v0.8.2 (#838)	2025-10-23 09:27:04 +08:00