haozhe.yang 5b57a3297a feat(cli): run kimi -p on agent-core-v2 behind experimental flag ... - add PromptHarness/PromptSession interfaces so the print driver is decoupled from the concrete SDK harness/session - add an in-process agent-core-v2 harness (bootstrap + session + prompt/goal/permission adapters) under cli/v2/ - adapt v2 IEventBus events to the v1 Event union, with unit tests - select the engine in createPromptHarness via isKimiV2Enabled() (KIMI_CODE_EXPERIMENTAL_FLAG), lazy-importing v2 off the default path		2026-07-07 23:37:03 +08:00
..
cli	feat(cli): run kimi -p on agent-core-v2 behind experimental flag	2026-07-07 23:37:03 +08:00
e2e	refactor: split SDK RPC client (#339)	2026-06-03 15:30:38 +08:00
feedback/codebase-upload	feat(feedback): support attaching logs and codebase (#1120)	2026-06-26 16:15:08 +08:00
helpers	Kimi For Coding	2026-05-22 15:54:50 +08:00
migration	feat: custom color themes (#484)	2026-06-09 18:55:15 +08:00
native	feat(web): introduce Kimi web app and daemon gateway (#625)	2026-06-17 20:53:46 +08:00
scripts/native	feat(kimi-code): vendor @moonshot-ai/pi-tui (#1254)	2026-07-01 20:23:35 +08:00
tui	fix(agent-core): harden goal-mode budget and outcome flow (#1456)	2026-07-07 15:23:57 +08:00
utils	feat(timing): split TTFT into api-server and client portions (#1228)	2026-06-30 19:15:02 +08:00