recover

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

/recover — Context Recovery After Compaction

/recover — 压缩后的上下文恢复

Purpose: Help you get back up to speed after Claude Code context compaction. Automatically detects in-progress work (RPI runs, evolve cycles), loads relevant knowledge, and summarizes what you were doing and what's next.

YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it.

CLI dependencies: gt, ao, bd — all optional. Shows what's available, skips what isn't.

用途： 帮助您在Claude Code上下文压缩后快速恢复工作状态。自动检测进行中的工作（RPI运行、evolve周期），加载相关知识，并总结您之前正在做的工作以及下一步计划。

您必须执行此工作流，而不只是描述它。

CLI依赖： gt、ao、bd — 均为可选工具。会显示可用的工具，跳过不可用的。

Quick Start

快速开始

bash

/recover              # Full recovery dashboard
/recover --json       # Machine-readable JSON output

bash

/recover              # 完整恢复仪表盘
/recover --json       # 机器可读的JSON输出

Execution Steps

执行步骤

Step 1: Detect In-Progress Sessions (Parallel)

步骤1：检测进行中的会话（并行执行）

Run ALL of the following in parallel bash calls:

Call 1 — RPI Phased State:

bash

if [ -f .agents/rpi/phased-state.json ]; then
  echo "=== RPI_STATE ==="
  cat .agents/rpi/phased-state.json
else
  echo "RPI_STATE=NONE"
fi

Call 2 — Evolve Cycle History:

bash

if [ -f .agents/evolve/cycle-history.jsonl ]; then
  echo "=== EVOLVE_STATE ==="
  tail -3 .agents/evolve/cycle-history.jsonl
else
  echo "EVOLVE_STATE=NONE"
fi

Call 3 — Git Recent Changes:

bash

echo "=== GIT_STATUS ==="
git status --short

echo "=== GIT_LOG ==="
git log --oneline -5

echo "=== GIT_BRANCH ==="
git branch --show-current

Call 4 — Work Queue State:

bash

if command -v bd &>/dev/null; then
  echo "=== IN_PROGRESS ==="
  bd list --status in_progress 2>/dev/null | head -3
  echo "=== READY ==="
  bd ready 2>/dev/null | head -3
else
  echo "BD_UNAVAILABLE"
fi

Call 5 — Knowledge and Messages:

bash

undefined

并行运行以下所有bash命令：

调用1 — RPI阶段状态：

bash

if [ -f .agents/rpi/phased-state.json ]; then
  echo "=== RPI_STATE ==="
  cat .agents/rpi/phased-state.json
else
  echo "RPI_STATE=NONE"
fi

调用2 — Evolve周期历史：

bash

if [ -f .agents/evolve/cycle-history.jsonl ]; then
  echo "=== EVOLVE_STATE ==="
  tail -3 .agents/evolve/cycle-history.jsonl
else
  echo "EVOLVE_STATE=NONE"
fi

调用3 — Git近期变更：

bash

echo "=== GIT_STATUS ==="
git status --short

echo "=== GIT_LOG ==="
git log --oneline -5

echo "=== GIT_BRANCH ==="
git branch --show-current

调用4 — 工作队列状态：

bash

if command -v bd &>/dev/null; then
  echo "=== IN_PROGRESS ==="
  bd list --status in_progress 2>/dev/null | head -3
  echo "=== READY ==="
  bd ready 2>/dev/null | head -3
else
  echo "BD_UNAVAILABLE"
fi

调用5 — 知识与消息：

bash

undefined

Knowledge artifacts

知识工件

echo "=== KNOWLEDGE_COUNT ===" echo "Learnings=$(ls .agents/learnings/ 2>/dev/null | wc -l | tr -d ' ')" echo "Patterns=$(ls .agents/patterns/ 2>/dev/null | wc -l | tr -d ' ')"

Inbox if gt available

若gt可用则显示收件箱

if command -v gt &>/dev/null; then echo "=== MESSAGES ===" gt mail inbox 2>/dev/null | head -3 else echo "GT_UNAVAILABLE" fi

undefined

if command -v gt &>/dev/null; then echo "=== MESSAGES ===" gt mail inbox 2>/dev/null | head -3 else echo "GT_UNAVAILABLE" fi

undefined

Step 2: Load Context from Knowledge Base

步骤2：从知识库加载上下文

If RPI state detected, run:

bash

if command -v ao &>/dev/null; then
  ao inject --apply-decay --format markdown --max-tokens 2000
fi

若检测到RPI状态，运行：

bash

if command -v ao &>/dev/null; then
  ao inject --apply-decay --format markdown --max-tokens 2000
fi

Step 3: Parse and Summarize Session State

步骤3：解析并总结会话状态

Extract from collected data:

RPI Detection: If
```
.agents/rpi/phased-state.json
```
exists:
- Extract
```
goal
```
  ,
```
epic_id
```
  ,
```
phase
```
  ,
```
cycle
```
  ,
```
started_at
```
- Map phase number to phase name (1=research, 2=plan, 3=implement, 4=validate)
- Show elapsed time since started_at
Evolve Detection: If
```
.agents/evolve/cycle-history.jsonl
```
exists:
- Read last entry for most recent cycle
- Extract
```
goals_fixed
```
  ,
```
result
```
  ,
```
timestamp
```
- Show latest cycle summary
Recent Work: From git log:
- Last 3 commits (extracted in Call 3)
- Uncommitted changes count
Pending Work: From beads:
- In-progress issues (up to 3)
- Ready issues count
Knowledge State:
- Total learnings and patterns available
- Unread messages count if gt available

从收集的数据中提取信息：

RPI检测： 若
```
.agents/rpi/phased-state.json
```
存在：
- 提取
```
goal
```
  、
```
epic_id
```
  、
```
phase
```
  、
```
cycle
```
  、
```
started_at
```
- 将阶段编号映射为阶段名称（1=研究，2=规划，3=实现，4=验证）
- 显示自
```
started_at
```
  以来的耗时
Evolve检测： 若
```
.agents/evolve/cycle-history.jsonl
```
存在：
- 读取最后一条记录以获取最新周期
- 提取
```
goals_fixed
```
  、
```
result
```
  、
```
timestamp
```
- 显示最新周期摘要
近期工作： 来自git日志：
- 最近3次提交（在调用3中提取）
- 未提交变更的数量
待办工作： 来自beads：
- 进行中的问题（最多3个）
- 就绪问题的数量
知识状态：
- 可用的学习内容和模式总数
- 若gt可用则显示未读消息数量

Step 4: Render Recovery Dashboard

步骤4：渲染恢复仪表盘

Assemble gathered data into this format:

══════════════════════════════════════════════════════════════
  Context Recovery Dashboard
══════════════════════════════════════════════════════════════

IN-PROGRESS RPI RUN
  Epic: <epic_id>
  Goal: <first 80 chars of goal>
  Phase: <phase name: research | plan | implement | validate>
  Cycle: <cycle #>
  Started: <time ago (e.g., "2 hours ago")>
  Status: <PHASE_START | IN_PROGRESS | READY_FOR_GATE | ...>

  ─ Next Step: <state-aware suggestion from Step 5>

OR

RECENT EVOLVE CYCLE (IF NO RPI)
  Cycle: <cycle #>
  Latest Goal: <goal_id or summary>
  Result: <result>
  Items Completed: <count or "—">
  Timestamp: <time ago>

  ─ Next Step: <state-aware suggestion from Step 5>

OR

[NO ACTIVE SESSION]
  No RPI run or evolve cycle in progress.
  Last activity: <time of last commit or "unknown">

IN-PROGRESS WORK
  <list up to 3 in-progress issues with IDs>
  <or "No in-progress work">

READY TO WORK
  <count of ready issues>
  <or "No ready issues">

RECENT COMMITS
  <last 3 commits>

PENDING CHANGES
  <uncommitted file count or "clean">

KNOWLEDGE AVAILABLE
  Learnings: <count>  Patterns: <count>

INBOX
  <message count or "No messages" or "gt not installed">

──────────────────────────────────────────────────────────────
SUGGESTED NEXT ACTION
  <state-aware command from Step 5>
──────────────────────────────────────────────────────────────

QUICK COMMANDS
  /status       Current workflow dashboard
  /research     Deep codebase exploration
  /plan         Decompose work into issues
  /implement    Execute a single issue
  /crank        Autonomous epic execution
  /vibe         Validate code quality
══════════════════════════════════════════════════════════════

将收集到的数据组装为以下格式：

══════════════════════════════════════════════════════════════
  上下文恢复仪表盘
══════════════════════════════════════════════════════════════

进行中的RPI运行
  史诗ID: <epic_id>
  目标: <目标的前80个字符>
  阶段: <阶段名称：research | plan | implement | validate>
  周期: <周期编号>
  开始时间: <多久之前（例如："2小时前"）>
  状态: <PHASE_START | IN_PROGRESS | READY_FOR_GATE | ...>

  ─ 下一步：<来自步骤5的状态感知建议>

或

近期Evolve周期（若无RPI）
  周期: <周期编号>
  最新目标: <goal_id或摘要>
  结果: <result>
  已完成项: <数量或"—">
  时间戳: <多久之前>

  ─ 下一步：<来自步骤5的状态感知建议>

或

[无活动会话]
  无进行中的RPI运行或evolve周期。
  最后活动: <最后一次提交的时间或"未知">

进行中的工作
  <最多列出3个带ID的进行中问题>
  <或"无进行中工作">

就绪工作
  <就绪问题的数量>
  <或"无就绪问题">

近期提交
  <最近3次提交>

待提交变更
  <未提交文件数量或"干净">

可用知识
  学习内容: <数量>  模式: <数量>

收件箱
  <消息数量或"无消息"或"gt未安装">

──────────────────────────────────────────────────────────────
建议的下一步操作
  <来自步骤5的状态感知命令>
──────────────────────────────────────────────────────────────

快捷命令
  /status       当前工作流仪表盘
  /research     深度代码库探索
  /plan         将工作分解为问题
  /implement    执行单个问题
  /crank        自主史诗执行
  /vibe         验证代码质量
══════════════════════════════════════════════════════════════

Step 5: Suggest Next Action (State-Aware)

步骤5：状态感知的下一步建议

Evaluate context top-to-bottom. Use the FIRST matching condition:


/inbox
/research
/pre-mortem
/implement <next-issue-id>
/post-mortem
/evolve --resume
/implement <issue-id>
/implement <first-ready-id>
/vibe recent
/status

Priority	Condition	Suggestion
1	Unread messages in inbox	"Check messages: `/inbox` "
2	RPI run in-progress + phase=research	"Continue research: `/research` or `/plan` if ready"
3	RPI run in-progress + phase=plan	"Review plan: `/pre-mortem` to validate before coding"
4	RPI run in-progress + phase=implement	"Resume implementation: `/implement <next-issue-id>` "
5	RPI run in-progress + phase=validate	"Complete cycle: `/post-mortem` to extract learnings"
6	Evolve cycle in-progress	"Continue autonomous improvements: `/evolve --resume` "
7	In-progress issues exist	"Continue work: `/implement <issue-id>` "
8	Ready issues available	"Pick next issue: `/implement <first-ready-id>` "
9	Uncommitted changes	"Review changes: `/vibe recent` "
10	Clean state, nothing pending	"Session recovered. Start with `/status` to plan next work"

自上而下评估上下文，使用第一个匹配的条件：


/inbox
/research
/pre-mortem
/implement <下一个问题ID>
/post-mortem
/evolve --resume
/implement <问题ID>
/implement <第一个就绪ID>
/vibe recent
/status

优先级	条件	建议
1	收件箱中有未读消息	"查看消息： `/inbox` "
2	进行中的RPI运行 + 阶段=research	"继续研究： `/research` 或准备就绪时使用 `/plan` "
3	进行中的RPI运行 + 阶段=plan	"审查规划： `/pre-mortem` 以在编码前验证"
4	进行中的RPI运行 + 阶段=implement	"恢复实现： `/implement <下一个问题ID>` "
5	进行中的RPI运行 + 阶段=validate	"完成周期： `/post-mortem` 以提取学习内容"
6	进行中的Evolve周期	"继续自主改进： `/evolve --resume` "
7	存在进行中的问题	"继续工作： `/implement <问题ID>` "
8	存在就绪问题	"选择下一个问题： `/implement <第一个就绪ID>` "
9	存在未提交变更	"审查变更： `/vibe recent` "
10	状态干净，无待办事项	"会话已恢复。使用 `/status` 规划下一步工作"

Step 6: JSON Output (--json flag)

步骤6：JSON输出（--json参数）

If the user passed

--json

, output all recovery data as structured JSON:

json

{
  "session_type": "rpi|evolve|none",
  "rpi": {
    "epic_id": "ag-l2pu",
    "goal": "Implement...",
    "phase": 2,
    "phase_name": "plan",
    "cycle": 1,
    "started_at": "2026-02-15T14:33:36-05:00",
    "elapsed_minutes": 120
  },
  "evolve": {
    "cycle": 3,
    "result": "improved",
    "goals_fixed": ["goal1", "goal2"],
    "timestamp": "2026-02-15T22:00:00-05:00"
  },
  "work_state": {
    "in_progress_count": 3,
    "in_progress_issues": ["ag-042.1", "ag-042.2"],
    "ready_count": 5,
    "uncommitted_changes": 2
  },
  "git": {
    "branch": "main",
    "recent_commits": [
      "7de51c8 feat: wave 2 — structural assertions",
      "25004f8 fix: replace per-wave vibe gate"
    ]
  },
  "knowledge": {
    "learnings_count": 12,
    "patterns_count": 5
  },
  "inbox": {
    "unread_count": 0
  },
  "suggestion": {
    "priority": 4,
    "message": "Resume implementation: /implement ag-042.1"
  }
}

Render this with a single code block. No visual dashboard when

--json

is active.

若用户传递了

--json

，则以结构化JSON格式输出所有恢复数据：

json

{
  "session_type": "rpi|evolve|none",
  "rpi": {
    "epic_id": "ag-l2pu",
    "goal": "Implement...",
    "phase": 2,
    "phase_name": "plan",
    "cycle": 1,
    "started_at": "2026-02-15T14:33:36-05:00",
    "elapsed_minutes": 120
  },
  "evolve": {
    "cycle": 3,
    "result": "improved",
    "goals_fixed": ["goal1", "goal2"],
    "timestamp": "2026-02-15T22:00:00-05:00"
  },
  "work_state": {
    "in_progress_count": 3,
    "in_progress_issues": ["ag-042.1", "ag-042.2"],
    "ready_count": 5,
    "uncommitted_changes": 2
  },
  "git": {
    "branch": "main",
    "recent_commits": [
      "7de51c8 feat: wave 2 — structural assertions",
      "25004f8 fix: replace per-wave vibe gate"
    ]
  },
  "knowledge": {
    "learnings_count": 12,
    "patterns_count": 5
  },
  "inbox": {
    "unread_count": 0
  },
  "suggestion": {
    "priority": 4,
    "message": "Resume implementation: /implement ag-042.1"
  }
}

使用单个代码块渲染此内容。当

--json

激活时，不显示可视化仪表盘。

Examples

示例

Recovery After Compaction Mid-RPI

压缩期间RPI运行中的恢复

User says:

/recover

What happens:

Agent runs 5 parallel bash calls to gather state
Agent detects RPI run in phased-state.json (phase=2, epic ag-l2pu)
Agent runs
```
ao inject
```
to load relevant knowledge
Agent shows goal, current phase (plan), cycle 1, started 2 hours ago
Agent lists 2 in-progress issues and 3 ready issues
Agent shows clean git state, recent commit
Agent suggests: "Review plan:
```
/pre-mortem
```
to validate before coding"

Result: Dashboard confirms in-progress RPI session, loads context, suggests next step.

用户输入：

/recover

执行过程：

Agent运行5个并行bash调用以收集状态
Agent在phased-state.json中检测到RPI运行（阶段=2，史诗ag-l2pu）
Agent运行
```
ao inject
```
以加载相关知识
Agent显示目标、当前阶段（规划）、周期1、2小时前开始
Agent列出2个进行中的问题和3个就绪问题
Agent显示干净的git状态和近期提交
Agent建议："审查规划：
```
/pre-mortem
```
以在编码前验证"

结果： 仪表盘确认进行中的RPI会话，加载上下文，建议下一步操作。

Recovery After Compaction With Evolve Cycle

压缩期间Evolve周期中的恢复

User says:

/recover

What happens:

Agent gathers state in parallel
Agent finds no RPI run
Agent detects evolve cycle (most recent: cycle 3, result "improved", goals_fixed=["goal1", "goal2"])
Agent shows timestamp (1 hour ago), items_completed (8)
Agent loads knowledge with
```
ao inject
```
Agent suggests: "Continue autonomous improvements:
```
/evolve --resume
```
"

Result: Dashboard confirms evolve cycle, shows progress, offers resume command.

用户输入：

/recover

执行过程：

Agent并行收集状态
Agent未找到RPI运行
Agent检测到evolve周期（最新：周期3，结果"improved"，goals_fixed=["goal1", "goal2"]）
Agent显示时间戳（1小时前）、已完成项（8个）
Agent使用
```
ao inject
```
加载知识
Agent建议："继续自主改进：
```
/evolve --resume
```
"

结果： 仪表盘确认evolve周期，显示进度，提供恢复命令。

Recovery in Clean State (No Active Session)

干净状态下的恢复（无活动会话）

User says:

/recover

What happens:

Agent gathers state in parallel
Agent finds no RPI run, no evolve cycle
Agent shows last 3 commits only
Agent finds no in-progress work, no ready issues
Agent shows 12 learnings available from knowledge base
Agent suggests: "Session recovered. Start with
```
/status
```
to plan next work"

Result: Dashboard confirms clean state, points user to entry points.

用户输入：

/recover

执行过程：

Agent并行收集状态
Agent未找到RPI运行或evolve周期
Agent仅显示最近3次提交
Agent未找到进行中工作或就绪问题
Agent显示知识库中有12个学习内容可用
Agent建议："会话已恢复。使用
```
/status
```
规划下一步工作"

结果： 仪表盘确认干净状态，为用户提供入口点指引。

Troubleshooting

故障排除

Problem	Cause	Solution
Shows "BD_UNAVAILABLE" or "GT_UNAVAILABLE"	CLI tools not installed or not in PATH	Install missing tools: `brew install bd` or `brew install gt` . Skill gracefully degrades by showing available state only.
RPI state shows wrong phase	Stale phased-state.json not updated	Check timestamp of `.agents/rpi/phased-state.json` . If stale, it may be from a previous run. Run `/status` to verify current phase.
Evolve history shows wrong cycle	Old cycle-history.jsonl entries not pruned	Tail -3 shows most recent entries. Check all entries with `tail -20 .agents/evolve/cycle-history.jsonl` .
Knowledge injection fails silently	ao CLI not installed or no knowledge artifacts	Ensure ao installed: `brew install ao` . If no learnings exist, run `/post-mortem` to seed the knowledge base.
Suggested action doesn't match context	State-aware rules didn't capture edge case	Use `--json` to inspect raw state and verify which condition matched. Review priority table in Step 5.
JSON output malformed	Parallel bash calls returned unexpected format	Check each bash call individually. Ensure jq parsing works on actual data. Validate JSON structure before returning to user.

问题	原因	解决方案
显示"BD_UNAVAILABLE"或"GT_UNAVAILABLE"	CLI工具未安装或不在PATH中	安装缺失的工具： `brew install bd` 或 `brew install gt` 。Skill会优雅降级，仅显示可用状态。
RPI状态显示错误阶段	过时的phased-state.json未更新	检查 `.agents/rpi/phased-state.json` 的时间戳。若已过时，可能来自之前的运行。运行 `/status` 以验证当前阶段。
Evolve历史显示错误周期	旧的cycle-history.jsonl条目未被修剪	`tail -3` 显示最新条目。使用 `tail -20 .agents/evolve/cycle-history.jsonl` 查看所有条目。
知识注入静默失败	ao CLI未安装或无知识工件	确保已安装ao： `brew install ao` 。若没有学习内容，运行 `/post-mortem` 以初始化知识库。
建议的操作与上下文不匹配	状态感知规则未捕获边缘情况	使用 `--json` 检查原始状态并验证匹配的条件。查看步骤5中的优先级表。
JSON输出格式错误	并行bash调用返回了意外格式	单独检查每个bash调用。确保jq解析可处理实际数据。返回给用户前验证JSON结构。