feat: implement --onboard flag in multi-agent-mux-create and update AGENT.md onboarding handshake protocol
This commit is contained in:
@@ -138,4 +138,23 @@ TMUX 환경에서 실행되는 에이전트가 화면 스크롤 한계로 인해
|
||||
|
||||
---
|
||||
|
||||
## 6. 온보딩 핸드셰이크 프로토콜 (Onboarding Handshake)
|
||||
|
||||
새롭게 기동되는 팀장 에이전트는 실무 작업을 수임하기 전에 반드시 `--onboard` 메커니즘을 통해 맥락을 파악하고 동기화(Alignment)해야 합니다. 이를 통해 올바른 설계 규칙과 저장소 이력을 숙지한 상태에서 안전하게 협업에 참여할 수 있습니다.
|
||||
|
||||
### 🔄 온보딩 핸드셰이크 흐름 (Onboarding Handshake Sequence)
|
||||
1. **온보딩 플래그와 함께 생성**: 총괄 매니저가 다음 명령을 통해 새 세션을 생성합니다:
|
||||
```bash
|
||||
bash .agents/skills/multi-agent-mux-create/scripts/create_session.sh --workspace "$(pwd)" --agent <agent> --role <role> --onboard
|
||||
```
|
||||
2. **에이전트 맥락 동기화**: 에이전트가 시작되면 아래 지시사항이 담긴 잡이 자동으로 인가됩니다:
|
||||
- `README.md` 및 `.agents/AGENT.md`를 필독하여 설계 규약과 제약사항을 인지한다.
|
||||
- `git status` 및 `git diff`를 실행하여 레포지토리의 활성 수정 내역을 분석한다.
|
||||
- `.mam/agent-sessions.yaml`을 읽어 현재 러닝 상태인 타 에이전트 목록을 확인하고, 자신의 지정된 `role`을 검증한다.
|
||||
3. **핸드셰이크 완료 발행**: 에이전트는 위의 맥락 파악 작업을 완료한 후, `publish_event.py`를 호출하여 다음과 같은 단말 완료 이벤트를 발행합니다:
|
||||
- Detail: `"Onboarding complete; aligned with role <role>"`
|
||||
4. **총괄 매니저 승인 게이트**: 총괄 매니저는 이 `completed` 핸드셰이크 신호가 오디팅 로그에 수렴될 때까지 대기(gating)해야 하며, 핸드셰이크가 통과된 것이 검증된 이후에야 해당 세션에 실무 또는 검수 작업을 위임합니다.
|
||||
|
||||
---
|
||||
|
||||
*본 가이드는 협업 효율성과 코드 보안의 엄격한 균형을 유지하기 위한 규범입니다. 변경 사항이 필요한 경우 총괄 매니저 및 전체 팀장의 합의를 거쳐 본 문서를 업데이트해야 합니다.*
|
||||
@@ -138,4 +138,23 @@ Use this checklist when deploying this agent orchestration model to a new projec
|
||||
|
||||
---
|
||||
|
||||
## 6. Onboarding Handshake Protocol (Onboarding Handshake)
|
||||
|
||||
Newly spawned Team Leader agents must align their context using the `--onboard` mechanism before receiving any real work. This ensures they operate with the correct design rules and repository history.
|
||||
|
||||
### 🔄 The Onboarding Handshake Sequence
|
||||
1. **Creation with Onboard flag**: The General Manager spawns a new session with:
|
||||
```bash
|
||||
bash .agents/skills/multi-agent-mux-create/scripts/create_session.sh --workspace "$(pwd)" --agent <agent> --role <role> --onboard
|
||||
```
|
||||
2. **Orienting the Agent**: The agent session starts up and automatically receives a registered job instructing it to:
|
||||
- Read `README.md` and `.agents/AGENT.md` to align with design principles and constraints.
|
||||
- Run `git status` and `git diff` to analyze active modifications.
|
||||
- Read `.mam/agent-sessions.yaml` to identify other running agents and verify its own assigned `role`.
|
||||
3. **Handshake Publication**: The agent executes these orientation tasks and publishes a `completed` event to the broker (using `publish_event.py`) with:
|
||||
- Detail: `"Onboarding complete; aligned with role <role>"`
|
||||
4. **GM Gating Check**: The General Manager polls or subscribes to this `completed` event. The GM **must** wait for this onboarding handshake to succeed before delegating any implementation or review jobs to the new session.
|
||||
|
||||
---
|
||||
|
||||
*This guide balances collaboration efficiency with strict code security. Any required changes must be discussed and agreed upon by the General Manager and all Team Leaders before updating this document.*
|
||||
@@ -826,4 +826,67 @@ start_watchdog() {
|
||||
echo "$pid"
|
||||
}
|
||||
|
||||
# wait_for_tui_ready <session_name> <agent>
|
||||
# Gated wait to ensure that the agent's TUI is fully loaded and responsive
|
||||
# before injecting any keyboard instructions.
|
||||
wait_for_tui_ready() {
|
||||
local sess="$1" agent="$2"
|
||||
local local_tmux="tmux"
|
||||
if [ -n "${TMUX_SERVER_NAME:-}" ] && [ "$TMUX_SERVER_NAME" != "default" ]; then
|
||||
local_tmux="tmux -L $TMUX_SERVER_NAME"
|
||||
fi
|
||||
|
||||
echo "🔍 Waiting for $agent TUI to become ready..."
|
||||
for i in {1..15}; do
|
||||
local content
|
||||
content=$($local_tmux capture-pane -p -t "$sess" 2>/dev/null || echo "")
|
||||
if [ -n "$content" ]; then
|
||||
case "$agent" in
|
||||
claude)
|
||||
if echo "$content" | grep -E -q "Anthropic|Assistant|Chat|Dangerously|dangerously|Enter|Welcome|projects" 2>/dev/null; then
|
||||
echo "✅ Claude TUI detected ready."
|
||||
return 0
|
||||
fi
|
||||
;;
|
||||
agy)
|
||||
if echo "$content" | grep -q "Antigravity" 2>/dev/null; then
|
||||
echo "✅ Antigravity TUI detected ready."
|
||||
return 0
|
||||
fi
|
||||
;;
|
||||
hermes)
|
||||
if echo "$content" | grep -q "Hermes" 2>/dev/null; then
|
||||
echo "✅ Hermes TUI detected ready."
|
||||
return 0
|
||||
fi
|
||||
;;
|
||||
cline)
|
||||
if echo "$content" | grep -E -q "Cline|history|Chat" 2>/dev/null; then
|
||||
echo "✅ Cline TUI detected ready."
|
||||
return 0
|
||||
fi
|
||||
;;
|
||||
esac
|
||||
fi
|
||||
sleep 1
|
||||
done
|
||||
echo "⚠️ Warning: TUI readiness check timed out. Proceeding anyway..."
|
||||
}
|
||||
|
||||
# inject_instructions <session_name> <instructions> [job_id]
|
||||
# Injects instructions into the tmux session using paste-buffer and C-m.
|
||||
inject_instructions() {
|
||||
local sess="$1" instructions="$2" job_id="${3:-onboard}"
|
||||
local local_tmux="tmux"
|
||||
if [ -n "${TMUX_SERVER_NAME:-}" ] && [ "$TMUX_SERVER_NAME" != "default" ]; then
|
||||
local_tmux="tmux -L $TMUX_SERVER_NAME"
|
||||
fi
|
||||
|
||||
$local_tmux set-buffer -b "job_buf_$job_id" "$instructions"
|
||||
$local_tmux paste-buffer -b "job_buf_$job_id" -t "$sess"
|
||||
sleep 0.5
|
||||
$local_tmux send-keys -t "$sess" C-m
|
||||
$local_tmux delete-buffer -b "job_buf_$job_id"
|
||||
}
|
||||
|
||||
|
||||
|
||||
@@ -81,6 +81,11 @@ To prevent this, you can run this skill inside an **isolated tmux server** using
|
||||
```bash
|
||||
bash scripts/create_session.sh --workspace /path/to/project --agent claude --role developer --submit-job "Task prompt here"
|
||||
```
|
||||
4. **Onboard Integration**:
|
||||
You can automatically submit a project alignment/orientation job to the new agent when creating a session:
|
||||
```bash
|
||||
bash scripts/create_session.sh --workspace /path/to/project --agent claude --role developer --onboard
|
||||
```
|
||||
|
||||
### Recommended Alias
|
||||
You can set an alias in your shell to easily query sessions on the isolated server:
|
||||
|
||||
@@ -34,6 +34,7 @@ Options:
|
||||
--dry-run print commands without executing
|
||||
--tmux-server NAME specify isolated tmux server name
|
||||
--submit-job PROMPT submit a job to multi-agent-mux-delegate-job registry with the given prompt
|
||||
--onboard automatically submit a project alignment/orientation job to the new agent
|
||||
-h, --help this help
|
||||
EOF
|
||||
}
|
||||
@@ -46,6 +47,7 @@ USE_WRAPPER=0
|
||||
DRY_RUN=0
|
||||
TMUX_SERVER_OPT=""
|
||||
SUBMIT_JOB_PROMPT=""
|
||||
ONBOARD=0
|
||||
|
||||
while [ $# -gt 0 ]; do
|
||||
case "$1" in
|
||||
@@ -57,6 +59,7 @@ while [ $# -gt 0 ]; do
|
||||
--dry-run) DRY_RUN=1; shift ;;
|
||||
--tmux-server) TMUX_SERVER_OPT="$2"; shift 2 ;;
|
||||
--submit-job) SUBMIT_JOB_PROMPT="$2"; shift 2 ;;
|
||||
--onboard) ONBOARD=1; shift ;;
|
||||
-h|--help) usage; exit 0 ;;
|
||||
*) echo "ERROR: unknown arg: $1" >&2; usage; exit 2 ;;
|
||||
esac
|
||||
@@ -143,7 +146,7 @@ fi
|
||||
spawn
|
||||
|
||||
# TUI 준비 대기
|
||||
sleep 6
|
||||
wait_for_tui_ready "$SESSION_NAME" "$AGENT"
|
||||
|
||||
# pane 메타 캡처
|
||||
PANE_PID=$(_tmux list-panes -t "$SESSION_NAME" -F '#{pane_pid}' 2>/dev/null || echo "")
|
||||
@@ -179,6 +182,15 @@ case "$AGENT" in
|
||||
;;
|
||||
esac
|
||||
|
||||
# If --onboard is specified, automatically build the onboarding prompt
|
||||
if [ "$ONBOARD" = "1" ] && [ -z "$SUBMIT_JOB_PROMPT" ]; then
|
||||
SUBMIT_JOB_PROMPT="You are a newly spawned $ROLE Team Leader agent in this workspace. To align yourself with the project context, perform the following tasks:
|
||||
1. Read the project documentation at README.md and the multi-agent protocol guidelines at .agents/AGENT.md to understand the design rules.
|
||||
2. Run 'git status' and 'git diff' to analyze the current modifications and active work in the repository.
|
||||
3. Read .mam/agent-sessions.yaml to see other running agent sessions, their roles, and confirm your own assigned role: $ROLE.
|
||||
4. Once you have fully comprehended the project state, publish a completed event (using publish_event.py) with the detail 'Onboarding complete; aligned with role $ROLE'."
|
||||
fi
|
||||
|
||||
# agent-sessions.yaml 에 append
|
||||
DELEGATE_JOB_ID=""
|
||||
if [ -n "$SUBMIT_JOB_PROMPT" ]; then
|
||||
@@ -301,7 +313,22 @@ echo "=== created ==="
|
||||
echo "tmux session: $SESSION_NAME (pane pid $PANE_PID, cmd $PANE_CMD, cwd $PANE_CWD)"
|
||||
if [ -n "$DELEGATE_JOB_ID" ]; then
|
||||
echo "delegate job: $DELEGATE_JOB_ID"
|
||||
delegate_publish_event "$DELEGATE_JOB_ID" started "multi-agent-mux session created"
|
||||
|
||||
# Construct instructions matching multi-agent-mux-delegate-job format
|
||||
pub="python3 .agents/skills/multi-agent-mux-delegate-job/scripts/publish_event.py --job $DELEGATE_JOB_ID"
|
||||
instructions="Your job_id is \"$DELEGATE_JOB_ID\" (the one just registered for THIS delegation).
|
||||
|
||||
On start run: $pub --event started.
|
||||
On progress (optional): $pub --event progress --detail '<short status>'.
|
||||
On success run: $pub --event completed --detail '<one-line summary>'.
|
||||
On failure run: $pub --event error --detail '<one-line reason>'.
|
||||
|
||||
Task: $SUBMIT_JOB_PROMPT"
|
||||
|
||||
# Inject instructions into the tmux pane
|
||||
inject_instructions "$SESSION_NAME" "$instructions" "$DELEGATE_JOB_ID"
|
||||
|
||||
delegate_publish_event "$DELEGATE_JOB_ID" started "multi-agent-mux session created and instructions injected"
|
||||
WD_PID=$(start_watchdog "$DELEGATE_JOB_ID" "$WORKSPACE")
|
||||
echo "watchdog PID: $WD_PID"
|
||||
fi
|
||||
|
||||
Reference in New Issue
Block a user