tmpl/multi-agent-mux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: implement loop and discuss task delegation types in multi-agent-mux-delegate-job

Browse Source
This commit is contained in:
Godopu
2026-06-27 08:28:47 +09:00
parent 3b8db1eca2
commit dfd0a9483d
4 changed files with 417 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.agents/skills/multi-agent-mux-delegate-job/multi-agent-mux-delegate-job
+210 -46
View File
@@ -16,6 +16,13 @@ set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
# Load local .env if it exists in current dir or workspace root
if [[ -f .env ]]; then
set -a; source .env; set +a
elif [[ -f "$SCRIPT_DIR/../../.env" ]]; then
set -a; source "$SCRIPT_DIR/../../.env"; set +a
fi
# Pick an interpreter: prefer a project .venv, else python3.
pick_python() {
local py_bin
@@ -46,6 +53,8 @@ multi-agent-mux-delegate-job <command> [options]
submit --agent <name> --prompt <text> [--workdir <dir>] [--agent-session <label>]
[--timeout <sec>] [--idle-timeout <sec>] [--validate <script>]
[--registry-dir <dir>] [--dry-run]
[--type <direct|loop|discuss>] [--reviewer <reviewer_agent>]
[--reviewer-session <reviewer_session>] [--max-iterations <count>]
# The skill is tmux-interactive only; --mode print was removed.
status --job <id> [--registry-dir <dir>]
list [--registry-dir <dir>]
@@ -59,6 +68,7 @@ EOF
AGENT="claude-code"; PROMPT=""; WORKDIR="$(pwd)"; AGENT_SESSION="tmux:claude"
TIMEOUT=3600; IDLE_TIMEOUT=120; VALIDATE=""; DRY_RUN=0
JOB_ID=""; REGISTRY_DIR="$REGISTRY_DIR_DEFAULT"
TYPE="direct"; REVIEWER="hermes"; REVIEWER_SESSION="tmux:hermes"; MAX_ITERATIONS=5
parse_opts() {
while [[ $# -gt 0 ]]; do
@@ -73,6 +83,10 @@ parse_opts() {
--job) JOB_ID="$2"; shift 2;;
--registry-dir) REGISTRY_DIR="$2"; shift 2;;
--dry-run) DRY_RUN=1; shift;;
--type) TYPE="$2"; shift 2;;
--reviewer) REVIEWER="$2"; shift 2;;
--reviewer-session) REVIEWER_SESSION="$2"; shift 2;;
--max-iterations) MAX_ITERATIONS="$2"; shift 2;;
*) echo "unknown option: $1" >&2; usage; exit 1;;
esac
done
@@ -88,26 +102,29 @@ cmd_submit() {
# 1) register job (prints the new job id)
JOB_ID="$("$PY" "$SCRIPT_DIR/scripts/registry.py" --registry-dir "$REGISTRY_DIR" register \
--prompt "$PROMPT" --agent "$AGENT" --agent-session "$AGENT_SESSION" \
--timeout "$TIMEOUT" --idle-timeout "$IDLE_TIMEOUT")"
--timeout "$TIMEOUT" --idle-timeout "$IDLE_TIMEOUT" \
--job-type "$TYPE" --reviewer "$REVIEWER" --reviewer-session "$REVIEWER_SESSION" \
--max-iterations "$MAX_ITERATIONS")"
echo "registered job: $JOB_ID"
# 2) START THE SUBSCRIBER FIRST (ordering dependency — MQTT does not queue
# non-retained messages for absent subscribers).
local logf="$REGISTRY_DIR/$JOB_ID.subscriber.out"
"$PY" "$SCRIPT_DIR/scripts/job_subscriber.py" --registry-dir "$REGISTRY_DIR" \
--job "$JOB_ID" --timeout "$TIMEOUT" --idle-timeout "$IDLE_TIMEOUT" \
>"$logf" 2>&1 &
local sub_pid=$!
echo "subscriber pid: $sub_pid (log: $logf)"
sleep 1 # give the subscriber time to CONNACK + SUBSCRIBE before the agent runs
if [[ "$TYPE" == "direct" ]]; then
# 2) START THE SUBSCRIBER FIRST (ordering dependency — MQTT does not queue
# non-retained messages for absent subscribers).
local logf="$REGISTRY_DIR/$JOB_ID.subscriber.out"
"$PY" "$SCRIPT_DIR/scripts/job_subscriber.py" --registry-dir "$REGISTRY_DIR" \
--job "$JOB_ID" --timeout "$TIMEOUT" --idle-timeout "$IDLE_TIMEOUT" \
>"$logf" 2>&1 &
local sub_pid=$!
echo "subscriber pid: $sub_pid (log: $logf)"
sleep 1 # give the subscriber time to CONNACK + SUBSCRIBE before the agent runs
# 3) run the agent (or print the command for dry-run / missing binary)
local pub="$PY $SCRIPT_DIR/scripts/publish_event.py --registry-dir $REGISTRY_DIR --job $JOB_ID"
# NOTE: the agent MUST use --job "$JOB_ID" (the one we just minted). Hard-coding
# an id from an earlier session is the #1 reason a delegated job sits idle and
# times out (see SKILL.md "Wrong job_id propagated to the agent"). We make the
# freshness explicit in the instruction header.
local instructions="Your job_id is \"$JOB_ID\" (the one just registered for THIS delegation — read it from the registry record, do NOT reuse any job_id you saw in earlier runs).
# 3) run the agent (or print the command for dry-run / missing binary)
local pub="$PY $SCRIPT_DIR/scripts/publish_event.py --registry-dir $REGISTRY_DIR --job $JOB_ID"
# NOTE: the agent MUST use --job "$JOB_ID" (the one we just minted). Hard-coding
# an id from an earlier session is the #1 reason a delegated job sits idle and
# times out (see SKILL.md "Wrong job_id propagated to the agent"). We make the
# freshness explicit in the instruction header.
local instructions="Your job_id is \"$JOB_ID\" (the one just registered for THIS delegation — read it from the registry record, do NOT reuse any job_id you saw in earlier runs).
On start run: $pub --event started.
On permission/tool prompt run: $pub --event permission_required --detail '<tool>:<what>'.
@@ -119,40 +136,187 @@ The subscriber for this job_id is already running; your completed/error event en
Task: $PROMPT"
run_agent "$JOB_ID" "$instructions"
run_agent "$JOB_ID" "$instructions"
# 4) optional validation hook
if [[ -n "$VALIDATE" ]]; then
echo "running validation: $VALIDATE"
if JOB_ID="$JOB_ID" REGISTRY_DIR="$REGISTRY_DIR" bash "$VALIDATE"; then
echo "validation: PASS"
else
local rc=$?
echo "validation: FAIL (exit $rc)"
# 4) optional validation hook
if [[ -n "$VALIDATE" ]]; then
echo "running validation: $VALIDATE"
if JOB_ID="$JOB_ID" REGISTRY_DIR="$REGISTRY_DIR" bash "$VALIDATE"; then
echo "validation: PASS"
else
local rc=$?
echo "validation: FAIL (exit $rc)"
fi
fi
if [[ "$DRY_RUN" == "1" ]]; then
# In dry-run we never started a real subscriber (the wrapper short-circuits
# before launching one), but the wait below would still try to join the
# background sub_pid from cmd_submit. Skip both the wait and the subscriber
# log dump; the user just wants to see the instruction that would have run.
local logs_root_dry="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
echo "$logs_root_dry/$JOB_ID"
return 0
fi
wait "$sub_pid" || true
echo "subscriber output:"; cat "$logf" || true
# Last stdout line: the persistent audit-log dir for this job (see SKILL.md
# "Audit Logs"). Callers can scrape `tail -n1` to find it.
local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
echo "$logs_root/$JOB_ID"
else
# Implement loop/discuss orchestrator
local iteration=1
local current_prompt="$PROMPT"
local current_session="$AGENT_SESSION"
local current_role="worker"
if [[ "$DRY_RUN" == "1" ]]; then
echo "[dry-run] orchestrator loop would start for job: $JOB_ID type: $TYPE"
echo "worker session: $AGENT_SESSION, reviewer session: $REVIEWER_SESSION"
local logs_root_dry="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
echo "$logs_root_dry/$JOB_ID"
return 0
fi
while true; do
echo "=================================================="
echo "Iteration $iteration - Role: $current_role"
echo "Session: $current_session"
echo "=================================================="
# Update job details in registry
"$PY" "$SCRIPT_DIR/scripts/registry.py" --registry-dir "$REGISTRY_DIR" update \
--job "$JOB_ID" \
--agent-session "$current_session" \
--prompt "$current_prompt" \
--iteration "$iteration" \
--status "pending"
# Start subscriber
local logf="$REGISTRY_DIR/${JOB_ID}.iter_${iteration}_${current_role}.subscriber.out"
"$PY" "$SCRIPT_DIR/scripts/job_subscriber.py" --registry-dir "$REGISTRY_DIR" \
--job "$JOB_ID" --timeout "$TIMEOUT" --idle-timeout "$IDLE_TIMEOUT" \
>"$logf" 2>&1 &
local sub_pid=$!
echo "subscriber pid: $sub_pid (log: $logf)"
sleep 1
# Format instruction block
local pub="$PY $SCRIPT_DIR/scripts/publish_event.py --registry-dir $REGISTRY_DIR --job $JOB_ID"
local instructions="Your job_id is \"$JOB_ID\" (the one just registered for THIS delegation — read it from the registry record, do NOT reuse any job_id you saw in earlier runs).
On start run: $pub --event started.
On permission/tool prompt run: $pub --event permission_required --detail '<tool>:<what>'.
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>'.
The subscriber for this job_id is already running; your completed/error event ends the job. Exit codes: 0 completed, 1 error, 2 publish failure.
Task: $current_prompt"
# Trigger agent
run_agent "$JOB_ID" "$instructions" "$current_session"
# Wait for subscriber
# Wait for subscriber
local sub_rc=0
wait "$sub_pid" || sub_rc=$?
echo "subscriber output:"; cat "$logf" || true
# Check job status based on subscriber exit code
local job_status="running"
if [[ $sub_rc -eq 0 ]]; then
job_status="completed"
elif [[ $sub_rc -eq 1 ]]; then
job_status="error"
else
job_status="timeout"
fi
echo "Job role $current_role finished with status: $job_status"
# Retrieve feedback from the last event
local feedback
feedback="$("$PY" "$SCRIPT_DIR/scripts/registry.py" --registry-dir "$REGISTRY_DIR" get-feedback --job "$JOB_ID")"
echo "Feedback/Detail: $feedback"
if [[ "$current_role" == "worker" ]]; then
if [[ "$job_status" != "completed" ]]; then
echo "Worker did not complete successfully (status: $job_status). Terminating workflow."
break
fi
# Worker completed successfully, now switch to reviewer
current_role="reviewer"
current_session="$REVIEWER_SESSION"
# Build reviewer prompt based on type
if [[ "$TYPE" == "loop" ]]; then
current_prompt="Review the changes/artifacts generated for job $JOB_ID. Check if they meet the requirements. If correct, publish completed event with 'PASS'. If there are issues, publish error event with detailed feedback/nits."
elif [[ "$TYPE" == "discuss" ]]; then
current_prompt="Read draft/documents generated for job $JOB_ID. Review the feasibility and content. Write your feedback/objections. If you agree with the plan, reply with 'AGREE'."
fi
else
if [[ "$job_status" != "completed" ]]; then
echo "Reviewer did not complete successfully (status: $job_status). Terminating workflow."
break
fi
# Reviewer finished. Check if pass/agree
local success=0
if [[ "$TYPE" == "loop" ]]; then
if [[ "${feedback,,}" == *"pass"* ]]; then
success=1
fi
elif [[ "$TYPE" == "discuss" ]]; then
if [[ "${feedback,,}" == *"agree"* ]]; then
success=1
fi
fi
if [[ "$success" == "1" ]]; then
echo "Reviewer approved the work. Finalizing job as completed."
"$PY" "$SCRIPT_DIR/scripts/registry.py" --registry-dir "$REGISTRY_DIR" status --job "$JOB_ID" --set "completed"
break
else
# Reviewer rejected/provided feedback. Increment & check max iterations
if [[ $iteration -ge $MAX_ITERATIONS ]]; then
echo "Max iterations ($MAX_ITERATIONS) reached without approval. Terminating workflow."
"$PY" "$SCRIPT_DIR/scripts/registry.py" --registry-dir "$REGISTRY_DIR" status --job "$JOB_ID" --set "error"
break
fi
iteration=$((iteration + 1))
current_role="worker"
current_session="$AGENT_SESSION"
current_prompt="The reviewer provided the following feedback for job $JOB_ID: $feedback. Please modify the code/artifacts to address these comments."
fi
fi
done
# 4) optional validation hook
if [[ -n "$VALIDATE" ]]; then
echo "running validation: $VALIDATE"
if JOB_ID="$JOB_ID" REGISTRY_DIR="$REGISTRY_DIR" bash "$VALIDATE"; then
echo "validation: PASS"
else
local rc=$?
echo "validation: FAIL (exit $rc)"
fi
fi
# Last stdout line: the persistent audit-log dir
local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
echo "$logs_root/$JOB_ID"
fi
if [[ "$DRY_RUN" == "1" ]]; then
# In dry-run we never started a real subscriber (the wrapper short-circuits
# before launching one), but the wait below would still try to join the
# background sub_pid from cmd_submit. Skip both the wait and the subscriber
# log dump; the user just wants to see the instruction that would have run.
local logs_root_dry="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
echo "$logs_root_dry/$JOB_ID"
return 0
fi
wait "$sub_pid" || true
echo "subscriber output:"; cat "$logf" || true
# Last stdout line: the persistent audit-log dir for this job (see SKILL.md
# "Audit Logs"). Callers can scrape `tail -n1` to find it.
local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
echo "$logs_root/$JOB_ID"
}
run_agent() {
local job_id="$1"; local instructions="$2"
local job_id="$1"; local instructions="$2"; local target_session="${3:-$AGENT_SESSION}"
# The skill is INTERACTIVE-ONLY. We never invoke `claude -p` or any other
# one-shot print mode, because:
# - claude -p exits the moment stdin is drained, so there's nothing to
@@ -168,7 +332,7 @@ run_agent() {
echo "[human agent] complete the task, then run publish_event.py --event completed"
return
fi
local sess="${AGENT_SESSION#tmux:}"
local sess="${target_session#tmux:}"
if [[ "$DRY_RUN" == "1" ]]; then
echo "[dry-run] would delegate task to running agent '$AGENT' in tmux session '$sess' with instructions:"