@seanyao/roll 2026.511.1 → 2026.511.3

package/CHANGELOG.md

@@ -1,5 +1,16 @@
 # Changelog
 
+## v2026.511.3
+- **Fixed**: loop/dream/brief 多项目运行隔离 — 共享 run.sh 导致所有项目的 loop 在同一目录执行，改为每个项目独立 runner 脚本（run-{slug}.sh），彻底隔离多项目并发执行环境
+- **Fixed**: roll release 自发版拦截 — 在 roll 自身项目执行 `roll release` 时自动拦截并提示改用 scripts/release.sh，防止误操作绕过 2FA
+
+## v2026.511.2
+- **Added**: roll loop monitor 三服务状态 — 监控台新增 loop/dream/brief 三个 launchd 服务的运行状态、调度时间和实时 log tail，一屏掌握全局执行情况
+- **Fixed**: dashboard 多处展示问题 — 修复 pending_count 算术错误、brief 内联显示 release readiness、移除底部冗余命令列表
+- **Fixed**: loop 异常退出后 state 未重置 — 防止 queue 卡住导致后续任务无法执行
+- **Fixed**: CI 稳定性 — 修复 _notify_update 裸返回和时间断言，消除环境差异引起的随机失败
+- **Improved**: roll-brief 输出格式 — 序号命名、省略空 section、元信息格式精简，减少无效噪音
+
 ## v2026.511.1
 - **Changed**: roll loop 调度器切换到 launchd（macOS）— `roll setup` 自动安装 loop/dream/brief 三个 launchd 服务（默认关闭），`roll loop on/off/status` 统一走 launchctl 管理，幂等安装，Linux 保留 crontab 回退路径
 - **Added**: roll-loop TCR 硬校验 — 故事完成后自动统计 `tcr:` 微提交数量，为 0 时将故事状态回退为 📋 Todo 并写 ALERT，防止 agent 跳过 TCR 节奏

package/README.md

@@ -9,6 +9,8 @@
 
 > Roll out features with AI agents — _Move fast, no sprints._
 
+**[中文版 README](README_CN.md)**
+
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
 [![npm version](https://img.shields.io/npm/v/@seanyao/roll.svg)](https://www.npmjs.com/package/@seanyao/roll)
 [![CI](https://github.com/seanyao/roll/actions/workflows/ci.yml/badge.svg)](https://github.com/seanyao/roll/actions/workflows/ci.yml)
@@ -17,20 +19,21 @@
 
 ## What is Roll?
 
-Roll solves a specific problem: when developers on the same team use different AI clients (Claude Code, Cursor, Gemini CLI, Codex), each agent operates under different engineering constraints. One developer's Claude runs tests another's Cursor never even considers.
+Roll solves a specific problem: when developers on the same team use different AI clients (Claude Code, Cursor, Gemini CLI, Kimi, Codex, DeepSeek, Pi, OpenCode, Trae), each agent operates under different engineering constraints. One developer's Claude runs tests another's Cursor never even considers.
 
-Roll fixes this through two mechanisms:
+Roll fixes this through three mechanisms:
 
-1. **Convention CLI** — a single source of engineering conventions distributed to every AI client on the machine (`~/.claude/`, `~/.cursor/`, `~/.gemini/`, etc.)
-2. **Skill System** — proven engineering practices (TDD, TCR, SRE, INVEST) encoded as instructions that any AI agent can follow
+1. **Convention CLI** — a single source of engineering conventions distributed to every AI client on the machine (`~/.claude/`, `~/.cursor/`, `~/.gemini/`, `~/.kimi/`, `~/.codex/`, `~/.deepseek/`, etc.)
+2. **Skill System** — 20 proven engineering practices (TDD, TCR, SRE, INVEST, DDD) encoded as instructions that any AI agent can follow
+3. **Autonomous Evolution** — an optional layer that lets the agent work unattended: `roll-loop` executes BACKLOG items hourly, `roll-.dream` scans code health nightly, and `roll-brief` briefs the human each morning. The human retains sole authority over releases.
 
-The result: any agent, any client, same constraints.
+The result: any agent, any client, same constraints — and optionally, continuous autonomous delivery.
 
 ---
 
 ## Start Here
 
-Before commands and skills, read the Engineering Methodology — it explains the three-loop architecture (Research → Build → Observe), why each skill exists, and how they connect into a complete delivery system.
+Before commands and skills, read the Engineering Methodology — it explains the three-loop architecture (Research → Build → Observe), the autonomous evolution layer, why each skill exists, and how they connect into a complete delivery system.
 
 **[English](docs/methodology-en.md)** · **[中文](docs/methodology.md)**
 
@@ -57,17 +60,25 @@ roll update
 
 ## Convention Management
 
-Unified behavioral conventions for Claude Code / Gemini CLI / Cursor / Codex — all from one source.
+Unified behavioral conventions for Claude Code / Gemini CLI / Cursor / Kimi / Codex / DeepSeek / Pi / OpenCode / Trae — all from one source.
 
 ### Commands
 
+Commands fall into two categories: **bash commands** run pure shell logic; **agent commands** (marked with 🤖) launch a full AI agent session to execute a SKILL.md.
+
 | Command | Description |
 |---------|-------------|
-| `roll setup` | First-time install on this machine, or re-sync after editing `~/.roll/config.yaml` (use `--force` to overwrite local cache) |
-| `roll update` | One-step upgrade: `npm install -g @seanyao/roll@latest` + re-sync via `roll setup` |
+| `roll setup [-f]` | First-time install on this machine, or re-sync (use `--force` to overwrite local cache) |
+| `roll update` | One-step upgrade: `npm install -g @seanyao/roll@latest` + re-sync via setup |
 | `roll init` | New project: create `AGENTS.md` + `BACKLOG.md` + `docs/features/` |
-
 | `roll status` | Show sync state, skill links, and detected AI tools |
+| `roll backlog` | Show all pending tasks from BACKLOG.md |
+| `roll agent [use <name>\|list]` | Per-project agent selection — affects all 🤖 commands |
+| `roll loop <on\|off\|now\|status\|monitor\|resume\|reset>` | 🤖 Manage the autonomous BACKLOG executor (three-service: loop/dream/brief) |
+| `roll brief` | 🤖 Show latest owner brief (regenerate if stale >24h) |
+| `roll peer` | 🤖 Cross-agent code review and negotiation |
+| `roll release` | 🤖 Sync changelog + version bump + tag + npm publish + GitHub Release |
+| `roll` _(no args, in project dir)_ | Dashboard: loop status, pending count, latest brief summary |
 
 ### Typical Flow
 
@@ -83,7 +94,13 @@ roll init
 # 3. Upgrade to a new release
 roll update
 
+# 4. Enable autonomous evolution (optional)
+roll loop on                  # three services: loop (hourly) + dream (nightly) + brief (daily)
+roll loop monitor             # real-time top-like dashboard
+roll brief                    # read the latest digest
 
+# 5. Switch agent per project
+roll agent use kimi           # all 🤖 commands now use kimi for this project
 ```
 
 ### How Convention Layering Works
@@ -137,29 +154,90 @@ Research → Design → Build → Check → Fix → (loop)
 | Fast backlog capture (bug / idea) | `$roll-idea "description"` |
 | High-risk logic (payments, auth, state machines) | `$roll-spar "feature"` |
 | Deep research (product / company / tech) | `$roll-research "subject"` |
+| Cross-agent code review | `$roll-peer` |
 | Patrol production for regressions | `$roll-sentinel patrol` |
 | Debug a broken page | `$roll-debug <URL>` |
 | Record a dev moment / diary entry | `$roll-notes "just fixed that nasty bug"` |
+| Let the agent work overnight | `roll loop on` |
 
 ### Full Skill List
 
-| Skill | Phase | Description |
-|-------|-------|-------------|
-| `$roll-build` | DESIGN+BUILD | Universal entry: Story ID, fix ID, or free-text fly mode |
-| `$roll-design` | DESIGN | Multi-turn discuss → [peer review] → DDD model → solution design → [peer review] → write Stories to BACKLOG |
-| `$roll-fix` | FIX | Bug fix / hotfix from BACKLOG |
-| `$roll-idea` | Support | Fast capture a bug or idea into BACKLOG.md |
-| `$roll-spar` | BUILD | Adversarial TDD — Attacker writes tests, Defender writes code |
-| `$roll-sentinel` | CHECK | Scheduled production patrol |
-| `$roll-debug` | CHECK | Deep page diagnostics + root cause analysis |
-| `$roll-research` | RESEARCH | HV Analysis framework, outputs PDF report |
-| `$roll-release` | RELEASE | One-command publish: auto version (YYYY.MMDD.N) → tag → npm publish |
-| `$roll-.review` | Support | Pre-commit self code review |
-| `$roll-.qa` | Support | Test pyramid and coverage standards reference |
-| `$roll-.changelog` | Support | Auto-generate CHANGELOG from BACKLOG |
-| `$roll-.echo` | Support | Passive intent clarification |
-| `$roll-.clarify` | Support | Passive scope clarification for vague build requests |
-| `$roll-notes` | Support | Project diary — append dev moments to `notes/YYYY-MM-DD.md` |
+**Loop A — Research & Design**
+
+| Skill | Description |
+|-------|-------------|
+| `$roll-research` | HV Analysis (Horizontal-Vertical) deep research framework, outputs PDF report |
+| `$roll-design` | Multi-turn discuss → [peer review] → DDD model → solution design → [peer review] → write Stories to BACKLOG |
+
+**Loop B — Implementation & Iteration**
+
+| Skill | Description |
+|-------|-------------|
+| `$roll-build` | Universal entry: Story ID, fix ID, or free-text fly mode. TCR-driven micro-commits |
+| `$roll-spar` | Adversarial TDD — Attacker writes tests, Defender writes code |
+| `$roll-fix` | Bug fix / hotfix from BACKLOG |
+| `$roll-release` | One-command publish: auto version (YYYY.MMDD.N) → tag → npm publish → GitHub Release |
+| `$roll-peer` | Cross-agent code review — Claude / Kimi / DeepSeek / Codex bilateral negotiation |
+
+**Loop C — Observability & Maintenance**
+
+| Skill | Description |
+|-------|-------------|
+| `$roll-sentinel` | Randomized production patrol with adaptive hot-spot weighting |
+| `$roll-debug` | Deep page diagnostics + root cause analysis (Black Box probe) |
+
+**Autonomous Evolution (optional, via `roll loop on`)**
+
+| Skill | Description |
+|-------|-------------|
+| `$roll-loop` | Hourly BACKLOG executor — routes US/FIX/REFACTOR to the right skill, enforces TCR |
+| `$roll-.dream` | Nightly code health scan — dead code, architectural drift → REFACTOR entries |
+| `$roll-brief` | Owner-facing digest — what's done, what's pending, release readiness verdict |
+
+**Passive Support**
+
+| Skill | Description |
+|-------|-------------|
+| `$roll-.review` | Pre-commit multi-dimensional self code review |
+| `$roll-.qa` | Test pyramid and coverage standards reference |
+| `$roll-.changelog` | Auto-generate CHANGELOG from BACKLOG |
+| `$roll-.echo` | Passive intent clarification |
+| `$roll-.clarify` | Passive scope clarification for vague build requests |
+| `$roll-idea` | Fast capture a bug or idea into BACKLOG.md |
+| `$roll-notes` | Project diary — append dev moments to `notes/YYYY-MM-DD.md` |
+| `$roll-doctor` | One-command dev toolchain health check |
+
+---
+
+## Autonomous Evolution
+
+Off by default. Enable with `roll loop on` to let the agent work unattended on your project.
+
+```
+┌─────────────────────────────────────────────────────────┐
+│  Base layer (always active)                             │
+│  $roll-design → $roll-build → $roll-fix → $roll-spar   │
+│  Human drives every action                              │
+├─────────────────────────────────────────────────────────┤
+│  Autonomous layer (opt-in: roll loop on)                │
+│  roll-loop   — hourly BACKLOG executor                  │
+│  roll-.dream — nightly code health scan                 │
+│  roll-brief  — daily morning digest + release readiness │
+│  Human reviews briefs; retains sole release authority   │
+└─────────────────────────────────────────────────────────┘
+```
+
+Three services are scheduled via macOS launchd (Linux: crontab) and managed as a unit:
+
+- **roll-loop** runs hourly, picks up `📋 Todo` items from BACKLOG, routes them (`US-XXX → $roll-build`, `FIX-XXX → $roll-fix`, `REFACTOR-XXX → $roll-build`), and enforces TCR discipline — if a story completes with zero `tcr:` micro-commits, it reverts to Todo with an ALERT.
+- **roll-.dream** runs nightly, scanning for dead code, architectural drift, and refactoring opportunities. Outputs `REFACTOR-XXX` entries to BACKLOG.
+- **roll-brief** runs each morning (or on-demand via `roll brief`), producing an owner-facing digest with a release-readiness verdict.
+
+The autonomous layer **never** invokes `roll-release`. Production deployment is always a human decision.
+
+Use `roll loop monitor` for a real-time `top`-like view of all three services: launchd status, current execution state, pending queue, alerts, and live log tail.
+
+Per-project agent configuration: `roll agent use <name>` writes `.roll.yaml` so each project can use a different AI client (claude / kimi / deepseek / pi / codex / opencode). Lookup order: `.roll.yaml` → `~/.roll/config.yaml` → `claude` (default).
 
 ---
 

package/bin/roll

@@ -4,7 +4,7 @@ set -euo pipefail
 # Roll — AI Agent Convention Manager
 # Single source of truth for how all AI coding agents behave.
 
-VERSION="2026.511.1"
+VERSION="2026.511.3"
 ROLL_HOME="${ROLL_HOME:-${HOME}/.roll}"
 ROLL_CONFIG="${ROLL_HOME}/config.yaml"
 ROLL_GLOBAL="${ROLL_HOME}/conventions/global"
@@ -1827,7 +1827,7 @@ _install_launchd_plists() {
   local services=("loop" "dream" "brief")
   local skill_names=("roll-loop" "roll-.dream" "roll-brief")
   local minutes=("0" "0" "0")
-  local hours=("" "1" "8")
+  local hours=("" "3" "9")
 
   local updated=0
   for i in "${!services[@]}"; do
@@ -1837,7 +1837,8 @@ _install_launchd_plists() {
     local hour="${hours[$i]}"
     local label; label=$(_launchd_label "$svc" "$project_path")
     local plist; plist=$(_launchd_plist_path "$svc" "$project_path")
-    local runner="${shared}/${svc}/run.sh"
+    local slug; slug=$(_project_slug "$project_path")
+    local runner="${shared}/${svc}/run-${slug}.sh"
     local log="${shared}/${svc}/cron.log"
     local cmd; cmd=$(_agent_skill_cmd "${sd}/${skill}/SKILL.md" 2>/dev/null || echo "roll loop now")
 
@@ -1910,8 +1911,8 @@ _loop_on() {
 
     ok "Loop enabled  已启用"
     echo "  • roll-loop   every hour :00    每小时整点"
-    echo "  • roll-.dream nightly at 01:00  每晚 01:00"
-    echo "  • roll-brief  daily at 08:00    每天 08:00"
+    echo "  • roll-.dream nightly at 03:00  每晚 03:00"
+    echo "  • roll-brief  daily at 09:00    每天 09:00"
     echo "  • Agent: ${agent}  (change: roll agent use <name>)"
     return 0
   fi
@@ -1938,8 +1939,8 @@ _loop_on() {
 
   ok "Loop enabled  已启用"
   echo "  • roll-loop   every hour :00    每小时整点"
-  echo "  • roll-.dream nightly at 01:00  每晚 01:00"
-  echo "  • roll-brief  daily at 08:00    每天 08:00"
+  echo "  • roll-.dream nightly at 03:00  每晚 03:00"
+  echo "  • roll-brief  daily at 09:00    每天 09:00"
   echo "  • Agent: ${agent}  (change: roll agent use <name>)"
 }
 
@@ -1958,6 +1959,10 @@ _loop_off() {
     if ! $any_loaded; then
       warn "Loop not enabled for this project  当前项目 loop 未启用"; return 0
     fi
+    local slug; slug=$(_project_slug "$project_path")
+    for svc in loop dream brief; do
+      rm -f "${_SHARED_ROOT}/${svc}/run-${slug}.sh"
+    done
     ok "Loop disabled  已停用"
     return 0
   fi
@@ -1977,7 +1982,11 @@ _loop_now() {
   info "Triggering loop cycle...  正在触发一个周期..."
   local log_file="${_SHARED_ROOT}/loop/launchd.log"
   mkdir -p "$(dirname "$log_file")"
-  _agent_run_skill "roll-loop" | tee -a "$log_file"
+  _agent_run_skill "roll-loop" 2>&1 | tee -a "$log_file" || true
+  # Reset stale running state if skill exited without cleanup (e.g. API error, SIGKILL)
+  if [[ -f "$_LOOP_STATE" ]] && grep -q "^status: running" "$_LOOP_STATE" 2>/dev/null; then
+    printf "status: idle\n" > "$_LOOP_STATE"
+  fi
 }
 
 _loop_status() {
@@ -2085,7 +2094,7 @@ _loop_monitor() {
     echo -e "  ${BOLD}Services  服务状态${NC}   Agent: ${CYAN}${agent}${NC}"
     if [[ "$(uname)" == "Darwin" ]]; then
       local svc_info svc schedule
-      for svc_info in "loop:hourly" "dream:01:00" "brief:08:00"; do
+      for svc_info in "loop:hourly" "dream:03:00" "brief:09:00"; do
         svc="${svc_info%%:*}"
         schedule="${svc_info#*:}"
         if _launchd_is_loaded "$(_launchd_label "$svc" "$project_path")"; then
@@ -2135,9 +2144,9 @@ _loop_monitor() {
     if [[ -f "$backlog" ]]; then
       local queue_count=0
       local fix_pending us_pending refactor_pending
-      fix_pending=$(grep -E '^\| FIX-' "$backlog" | grep '📋 Todo' || true)
-      us_pending=$(grep -E '^\| \[US-' "$backlog" | grep '📋 Todo' || true)
-      refactor_pending=$(grep -E '^\| REFACTOR-' "$backlog" | grep '📋 Todo' || true)
+      fix_pending=$(grep -E '^\| FIX-' "$backlog" | grep -F '| 📋 Todo |' || true)
+      us_pending=$(grep -E '^\| \[US-' "$backlog" | grep -F '| 📋 Todo |' || true)
+      refactor_pending=$(grep -E '^\| REFACTOR-' "$backlog" | grep -F '| 📋 Todo |' || true)
 
       # FIX first (priority)
       while IFS= read -r line; do
@@ -2217,6 +2226,12 @@ cmd_brief() {
 }
 
 cmd_release() {
+  local pkg; pkg=$(node -p "require('./package.json').name" 2>/dev/null || true)
+  if [[ "$pkg" == "@seanyao/roll" ]]; then
+    err "roll 自身发版请用 scripts/release.sh（npm publish 需要人工 2FA）"
+    echo "  Run: scripts/release.sh"
+    exit 1
+  fi
   _agent_run_skill "roll-release"
 }
 
@@ -2233,9 +2248,9 @@ cmd_backlog() {
 
   local us_items fix_items refactor_items total=0
 
-  us_items=$(grep -E '^\| \[US-' "$backlog" | grep '📋 Todo' || true)
-  fix_items=$(grep -E '^\| FIX-' "$backlog" | grep '📋 Todo' || true)
-  refactor_items=$(grep -E '^\| REFACTOR-' "$backlog" | grep '📋 Todo' || true)
+  us_items=$(grep -E '^\| \[US-' "$backlog" | grep -F '| 📋 Todo |' || true)
+  fix_items=$(grep -E '^\| FIX-' "$backlog" | grep -F '| 📋 Todo |' || true)
+  refactor_items=$(grep -E '^\| REFACTOR-' "$backlog" | grep -F '| 📋 Todo |' || true)
 
   local us_count fix_count refactor_count
   us_count=$(echo "$us_items" | grep -c . || true)
@@ -2298,8 +2313,24 @@ _dashboard() {
 
   echo -e "\n  ${BOLD}${CYAN}${project_name}${NC}  ${YELLOW}v${VERSION}${NC}\n"
 
-  if crontab -l 2>/dev/null | grep -q "${_LOOP_TAG}:${project_path}"; then
+  local _dash_loop_enabled=false
+  if [[ "$(uname)" == "Darwin" ]]; then
+    _launchd_is_loaded "$(_launchd_label "loop" "$project_path")" && _dash_loop_enabled=true
+  else
+    crontab -l 2>/dev/null | grep -q "${_LOOP_TAG}:${project_path}" && _dash_loop_enabled=true
+  fi
+  if $_dash_loop_enabled; then
     echo -e "  Loop  ${GREEN}● on${NC}   Agent: ${CYAN}${agent}${NC}"
+    if [[ "$(uname)" == "Darwin" ]]; then
+      for svc_info in "loop:hourly" "dream:03:00" "brief:09:00"; do
+        local svc="${svc_info%%:*}" schedule="${svc_info#*:}"
+        if _launchd_is_loaded "$(_launchd_label "$svc" "$project_path")"; then
+          printf "    ${GREEN}%-8s ● enabled${NC}  (%s)\n" "$svc" "$schedule"
+        else
+          printf "    ${YELLOW}%-8s ○ disabled${NC} (%s)\n" "$svc" "$schedule"
+        fi
+      done
+    fi
   else
     echo -e "  Loop  ${YELLOW}○ off${NC}   run: roll loop on"
   fi
@@ -2308,7 +2339,7 @@ _dashboard() {
   # Backlog summary
   if [[ -f "BACKLOG.md" ]]; then
     local pending_count
-    pending_count=$(grep -c '📋 Todo' "BACKLOG.md" 2>/dev/null || echo 0)
+    pending_count=$(grep -cF '| 📋 Todo |' "BACKLOG.md" 2>/dev/null) || pending_count=0
     if (( pending_count > 0 )); then
       echo -e "  Backlog  ${YELLOW}${pending_count} pending${NC}   run: roll backlog"
     else
@@ -2322,18 +2353,15 @@ _dashboard() {
     local mod_time now age
     mod_time=$(stat -c %Y "$latest" 2>/dev/null || stat -f %m "$latest" 2>/dev/null || echo 0)
     now=$(date +%s); age=$(( (now - mod_time) / 3600 ))
-    echo -e "\n  Brief  ${CYAN}$(basename "$latest")${NC}  (${age}h ago)"
-    grep -A1 "## Release Readiness" "$latest" 2>/dev/null | tail -1 | sed 's/^/  /'
-    echo ""
-    echo "  run: roll brief   for full brief"
+    local readiness; readiness=$(awk '/^## Release Readiness/{found=1;next} found && /[^[:space:]]/{gsub(/\*\*/,""); print; exit}' "$latest" 2>/dev/null || true)
+    local done_count; done_count=$(grep -c '| Story\|| Fix\|| Refactor' "$latest" 2>/dev/null) || done_count=0
+    echo -e "\n  Brief  (${age}h ago)  ${readiness:+${CYAN}${readiness}${NC}}"
+    [[ "$done_count" -gt 0 ]] && echo -e "  This cycle: ${done_count} items completed"
   else
     echo -e "\n  No brief yet — run: roll brief"
   fi
 
   echo ""
-  echo "  loop <on|off|now|status|monitor|resume|reset>  ·  brief  ·  backlog  ·  agent use <name>  ·  release"
-  echo "  setup  ·  update  ·  init  ·  status  ·  peer  ·  help"
-  echo ""
 }
 
 # ═══════════════════════════════════════════════════════════════════════════════
@@ -2443,7 +2471,7 @@ _check_update_async() {
 
 _notify_update() {
   local cache="${ROLL_HOME}/.update-check"
-  [[ -f "$cache" ]] || return
+  [[ -f "$cache" ]] || return 0
   local latest; latest=$(awk '{print $2}' "$cache" 2>/dev/null || true)
   [[ -z "$latest" || "$latest" == "$VERSION" ]] && return
   local newer; newer=$(printf '%s\n%s\n' "$VERSION" "$latest" | sort -V | tail -1)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@seanyao/roll",
-  "version": "2026.511.1",
+  "version": "2026.511.3",
   "description": "Roll — Roll out features with AI agents",
   "scripts": {
     "test": "find tests/unit tests/integration -name '*.bats' | sort | xargs ./tests/helpers/bats-core/bin/bats"

package/skills/roll-brief/SKILL.md

@@ -95,39 +95,60 @@ A simple heuristic — not a gate, just a signal for the human:
 
 ### Step 4 — Write Brief
 
-Output to `docs/briefs/YYYY-MM-DD-HH.md`，全部用中文输出：
+文件命名：`docs/briefs/YYYY-MM-DD-{NN}.md`，NN 为当日序号（01 起，零填充两位）。
+计算方式：`ls docs/briefs/YYYY-MM-DD-*.md 2>/dev/null | wc -l`，+1 即为本次序号。
+
+全部用中文输出。**省略空 section**（无内容时连标题一起不输出）：
 
 ```markdown
 # 简报 {YYYY-MM-DD HH:mm}
 
-## 已完成
+> 触发：{触发原因} | 覆盖：{起止时间范围}
+
+## 已完成（{N} 项）
 | 编号 | 描述 | 类型 |
 |----|-------------|------|
 | US-XXX | {标题} | 用户故事 |
 | FIX-XXX | {标题} | 缺陷修复 |
 | REFACTOR-XXX | {标题} | 重构 |
 
+<!-- 仅当有 🔨 条目时输出 -->
 ## 进行中
 | 编号 | 描述 |
 |----|-------------|
 | US-XXX | {标题} — 开始于 {date} |
 
+<!-- 仅当有 📋 条目时输出 -->
 ## 待处理队列（{N} 项）
 | 编号 | 描述 | 优先级 |
 |----|-------------|----------|
 | US-XXX | {标题} | 高 |
 
-## 夜间巡检发现
-{来自 docs/dream/ 的摘要，无则写"暂无新发现。"}
+<!-- 仅当 roll-.dream 有新发现时输出 -->
+## 悟见
+{来自 docs/dream/ 的摘要}
+
+<!-- 仅当有 ESCALATE 告警时输出 -->
+## 需人工介入
+{告警内容}
+
+## 发版就绪
+{✅ 可发版 / ⚠️ 暂缓 — 原因}
 
-## 需要人工介入的升级事项
-{任何告警，无则写"无 — agent 运行正常。"}
+**下一版本：** `v{YYYY}.{MMDD}.{序号}`
 
-## 发布就绪状态
-{✅ 可发布 / ⚠️ 暂缓 — 原因}
+- {本轮新增 1}
+- {本轮新增 2}
 
 ---
-*下次定时简报：{datetime}*
+*状态：进行中 {N} · 待处理 {N} · 告警 {N} | 下次简报：{datetime}*
+```
+
+**首份简报或传入 `--full-history`**：在"已完成"表格后追加历史汇总区块：
+
+```markdown
+### 历史汇总
+**Epic: {Name}** — {done}/{total} ✅
 ```
 
 ### Step 5 — Notify
@@ -135,8 +156,8 @@ Output to `docs/briefs/YYYY-MM-DD-HH.md`，全部用中文输出：
 写完文件后在终端或 CI 日志中打印简报路径：
 
 ```
-📋 简报已生成：docs/briefs/2026-05-10-08.md
-   发布就绪：✅ 可发布
+📋 简报已生成：docs/briefs/2026-05-10-01.md
+   发布就绪：✅ 可发版
 ```
 
 有升级事项时须显著打印，不得遗漏。