From b021c1bd01e8710ff82c3746c3d1fedc217aae1a Mon Sep 17 00:00:00 2001 From: jsPark Date: Thu, 18 Jun 2026 12:50:18 +0900 Subject: [PATCH] Prepare v0.6.8 release path --- .agents/skills/hyper-run/SKILL.md | 4 ++-- docs/CHANGELOG.md | 7 +++++++ docs/CHANGELOG_ko.md | 7 +++++++ 3 files changed, 16 insertions(+), 2 deletions(-) diff --git a/.agents/skills/hyper-run/SKILL.md b/.agents/skills/hyper-run/SKILL.md index eaace64..63fbc21 100644 --- a/.agents/skills/hyper-run/SKILL.md +++ b/.agents/skills/hyper-run/SKILL.md @@ -17,10 +17,10 @@ Behavior: - Run the safest available validation or record why validation is blocked. - Update `evidence.md` with validation output, readiness evidence, active capability evidence, pressure signals, changed files, decisions, reusable patterns, and blockers. - Write `next.md` with the next recommended runtime episode and Learn Notes. -- Run `hyper complete` after evidence and next notes are written; if the finish gate fails, fix the same packet using `review.md`. +- Run `hyper complete` internally as the agent finish gate after evidence and next notes are written; if it fails, fix the same packet using `review.md`. - In auto mode, read `.hyper/next-packet.md`, obey its Guard and Progress Guard, and continue through the planned command until a guard stops progress. - If `.hyper/next-packet.md` says `Action: run`, execute only its `Command` and continue the next packet. - If it says `Action: advance`, continue only when the Stage Advancement Review authorizes the active auto target or the user accepts the stage change. - If it says `Action: complete-current`, stay in the same packet and fix evidence.md, next.md, and review.md findings. - If it says `Action: stop`, report the reason shown in `.hyper/next-packet.md`; this may be target proof complete, blocked, waiting for user input, or another stop condition. -- Do not start another `hyper run` until evidence, next notes, and `hyper complete` are done. +- Do not start another `hyper run` until evidence, next notes, and the agent finish gate are done. diff --git a/docs/CHANGELOG.md b/docs/CHANGELOG.md index 009e6ab..73b0de8 100644 --- a/docs/CHANGELOG.md +++ b/docs/CHANGELOG.md @@ -2,6 +2,13 @@ ## Unreleased +## v0.6.8 - 2026-06-18 + +- Keep the normal human flow centered on `hyper run` by describing `hyper complete` as the agent finish gate and manual recovery command across README, status, doctor, run-blocking, repair, advance, migrate, resume, and generated Codex routing output. +- Update generated runtime handoffs so `goal.md`/`tasks.md` still name the finish gate, while user-facing payloads, status, and doctor tell the agent to finish evidence/next notes and run the gate internally. +- Refresh the project-installed `$hyper-run` skill routing through `hyper migrate` so it matches the generated agent finish-gate wording. +- Harden `.gitignore` for local secrets, certificates, logs, coverage, temporary build outputs, and editor/cache files. + ## v0.6.7 - 2026-06-16 - Add generated runtime-packet sections for Decision Hierarchy, Autonomous Work Plan, Autonomous Safety Policy, Capability Expansion Policy, Research Evidence Policy, Loop Progress Policy, and Product Satisfaction Policy, with matching task and evidence rows. diff --git a/docs/CHANGELOG_ko.md b/docs/CHANGELOG_ko.md index 19dac23..a0b2579 100644 --- a/docs/CHANGELOG_ko.md +++ b/docs/CHANGELOG_ko.md @@ -2,6 +2,13 @@ ## Unreleased +## v0.6.8 - 2026-06-18 + +- 일반 사용자의 흐름을 `hyper run` 중심으로 유지하도록 README, status, doctor, run-blocking, repair, advance, migrate, resume, 생성된 Codex routing 출력에서 `hyper complete`를 agent finish gate 및 수동 복구 명령으로 설명하게 했습니다. +- 생성 runtime handoff를 갱신했습니다. `goal.md`/`tasks.md`에는 finish gate를 계속 명시하되, user-facing payload, status, doctor는 agent가 evidence/next notes를 마무리하고 gate를 내부적으로 실행하도록 안내합니다. +- `hyper migrate`가 project-installed `$hyper-run` skill routing을 최신 agent finish-gate wording에 맞게 갱신하게 했습니다. +- local secret, certificate, log, coverage, 임시 build output, editor/cache file이 Git에 들어가지 않도록 `.gitignore`를 보강했습니다. + ## v0.6.7 - 2026-06-16 - Decision Hierarchy, Autonomous Work Plan, Autonomous Safety Policy, Capability Expansion Policy, Research Evidence Policy, Loop Progress Policy, Product Satisfaction Policy를 runtime packet에 생성하고, 이에 맞는 task/evidence row를 함께 생성하게 했습니다.