Episode → maybe_learn → llm_free skills, plus abstract router backends (marqdo/small-llm/jev?/llm/auto) via plugins/agent; no core host changes. Co-authored-by: Cursor <cursoragent@cursor.com>
step/plan writeback=True shadowed lib/writeback; persist via host_writeback_record. Align ZH context builder, add dump_step_context, lock offline harness. Co-authored-by: Cursor <cursoragent@cursor.com>
Lock code-as-doc / call_site / OKF as first-class: reorder step context, ship agent-pong and okf-flywheel examples, offline harness, and skill/docs refresh. Dev LLM template via .env.example only. Co-authored-by: Cursor <cursoragent@cursor.com>