Commit Graph

10 Commits

Author SHA1 Message Date
9aea6c1cd0 docs(ai): converge external wording to AI-assisted + human review, not full-auto
Per the architecture-review redline (EIP3 决策会纪要: AI claims limited to 'AI-assisted, human-reviewed'; never promise 'AI full-auto development'), soften endpoint @Operation summaries, the default task objective, and AI docs that read as committed full-automation. Endpoint paths/method names unchanged (API contract). Added a capability-boundary disclaimer at the top of AI_AGENT_AUTO_DEVELOPMENT.md. 33 platform-ai tests green.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 16:39:45 +08:00
4b2cedfd1d feat: add AI page preview URL 2026-06-17 14:17:53 +08:00
d91da77038 feat: add AI render plan gate 2026-06-17 13:28:49 +08:00
718c5a5b9b feat: add AI tree CRUD recipe 2026-06-17 13:03:38 +08:00
2b0b673ce9 feat: expose AI page recipes 2026-06-17 12:38:26 +08:00
fcc5719bc6 feat: enforce AI page recipe gate 2026-06-17 12:33:09 +08:00
e55072598e feat: add AI page blueprint compiler 2026-06-17 12:14:57 +08:00
c5bfbd3ca3 feat: add AI feature package revisions 2026-06-17 07:56:45 +08:00
5bf641838a feat: add EIP4 agent CLI and skills plan 2026-06-17 07:47:22 +08:00
3b4d3dbd24 feat: add AI agent auto-development pipeline 2026-06-17 07:32:54 +08:00