845 lines
34 KiB
Bash
845 lines
34 KiB
Bash
#!/usr/bin/env bash
|
|
# ===========================================================================
|
|
# run_loop.sh — Autonomous Planning, Execution, and Peer-Review Orchestrator
|
|
# ===========================================================================
|
|
|
|
set -euo pipefail
|
|
|
|
# 1. Load Common Framework Library
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
REPO_ROOT="$(cd "$SCRIPT_DIR/../../../.." && pwd)"
|
|
# shellcheck disable=SC1091
|
|
source "$REPO_ROOT/.agents/skills/lib.sh"
|
|
# shellcheck disable=SC1091
|
|
source "$REPO_ROOT/.agents/skills/multi-agent-mux-loop/scripts/diff_collect.sh"
|
|
|
|
# Default configuration parameters
|
|
PLAN_MODE=false
|
|
PLAN_TALK_TURNS=1
|
|
ALL_REVIEWERS=false
|
|
MAX_LOOP=3
|
|
MAX_REBUT=1
|
|
VERBOSE=false
|
|
CLEANUP=false
|
|
TARGET_AGENT=""
|
|
TASK=""
|
|
REVIEWER_LIST=""
|
|
|
|
# Print usage instructions
|
|
usage() {
|
|
echo "Usage: $0 [options] --target-agent <agent-session-name> --task <goal-text>"
|
|
echo "Options:"
|
|
echo " --plan Enable Planner agent intervention & design phase"
|
|
echo " --plan-talk N Planner-Creator discussion limit turns (default: 1)"
|
|
echo " --reviewer \"A,B\" Targeted reviewer session name list (comma-separated)"
|
|
echo " --all-reviewer Enforce PASS verdict from all active reviewer sessions"
|
|
echo " --max-loop N Max execution-review corrective loop runs (default: 3)"
|
|
echo " --max-rebut N Max rebuttal attempts per review iteration (default: 1, 0: disabled)"
|
|
echo " --verbose Print detailed execution timeline traces"
|
|
echo " --cleanup Purge temporary job directories upon success"
|
|
exit 1
|
|
}
|
|
|
|
# Parse options safely
|
|
while [[ "$#" -gt 0 ]]; do
|
|
case "$1" in
|
|
--plan) PLAN_MODE=true; shift ;;
|
|
--plan-talk)
|
|
if [[ ! "$2" =~ ^[0-9]+$ ]]; then
|
|
echo "ERROR: --plan-talk requires a positive integer."
|
|
exit 1
|
|
fi
|
|
PLAN_TALK_TURNS="$2"; shift 2 ;;
|
|
--reviewer) REVIEWER_LIST="$2"; shift 2 ;;
|
|
--all-reviewer) ALL_REVIEWERS=true; shift ;;
|
|
--max-loop)
|
|
if [[ ! "$2" =~ ^[0-9]+$ ]] || [ "$2" -le 0 ]; then
|
|
echo "ERROR: --max-loop requires a positive non-zero integer."
|
|
exit 1
|
|
fi
|
|
MAX_LOOP="$2"; shift 2 ;;
|
|
--max-rebut)
|
|
if [[ ! "$2" =~ ^[0-9]+$ ]]; then
|
|
echo "ERROR: --max-rebut requires a non-negative integer."
|
|
exit 1
|
|
fi
|
|
MAX_REBUT="$2"; shift 2 ;;
|
|
--verbose) VERBOSE=true; shift ;;
|
|
--cleanup) CLEANUP=true; shift ;;
|
|
--target-agent) TARGET_AGENT="$2"; shift 2 ;;
|
|
--task) TASK="$2"; shift 2 ;;
|
|
-h|--help) usage ;;
|
|
*) echo "Unknown option: $1"; usage ;;
|
|
esac
|
|
done
|
|
|
|
# Run-wide cap on rebuttal rounds. Makes the bound explicit and enforced
|
|
# rather than merely emergent from MAX_LOOP x MAX_REBUT.
|
|
REBUT_TOTAL_BUDGET=$((MAX_REBUT * MAX_LOOP))
|
|
|
|
if [ -z "$TARGET_AGENT" ] || [ -z "$TASK" ]; then
|
|
echo "ERROR: --target-agent and --task are mandatory fields."
|
|
usage
|
|
fi
|
|
|
|
MAM_LOOP_MARKER="$REPO_ROOT/.mam/loop-guard-active"
|
|
mkdir -p "$(dirname "$MAM_LOOP_MARKER")"
|
|
_mam_lstart() { ps -p "$1" -o lstart= 2>/dev/null | tr -s ' ' | sed 's/^ *//;s/ *$//'; }
|
|
printf 'pid=%s\nlstart=%s\nstarted=%s\n' \
|
|
"$$" "$(_mam_lstart $$)" "$(date -u +%Y-%m-%dT%H:%M:%SZ)" > "$MAM_LOOP_MARKER"
|
|
_mam_release_guard() { rm -f "$MAM_LOOP_MARKER"; }
|
|
trap _mam_release_guard EXIT INT TERM HUP
|
|
|
|
delegate_job_safe() {
|
|
local orig_script="$REPO_ROOT/.agents/skills/multi-agent-mux-delegate-job/multi-agent-mux-delegate-job"
|
|
local tmp_script
|
|
tmp_script="${orig_script}.${RANDOM}_$$.tmp"
|
|
cp "$orig_script" "$tmp_script"
|
|
trap 'rm -f "$tmp_script"' EXIT INT TERM HUP
|
|
local rc=0
|
|
bash "$tmp_script" "$@" || rc=$?
|
|
rm -f "$tmp_script"
|
|
trap _mam_release_guard EXIT INT TERM HUP
|
|
return $rc
|
|
}
|
|
|
|
log_info() {
|
|
echo -e "\033[1;34m[*]\033[0m $1"
|
|
}
|
|
|
|
log_success() {
|
|
echo -e "\033[1;32m[✓]\033[0m $1"
|
|
}
|
|
|
|
log_warn() {
|
|
echo -e "\033[1;33m[!]\033[0m $1"
|
|
}
|
|
|
|
log_error() {
|
|
echo -e "\033[1;31m[✗]\033[0m $1"
|
|
}
|
|
|
|
# --all-reviewer silently takes precedence over an explicit --reviewer list;
|
|
# warn so the discarded list isn't mistaken for having been honored (P2-1).
|
|
if [ "$ALL_REVIEWERS" = true ] && [ -n "$REVIEWER_LIST" ]; then
|
|
log_warn "--all-reviewer takes precedence; ignoring --reviewer list ('$REVIEWER_LIST')."
|
|
fi
|
|
|
|
if [ "$PLAN_TALK_TURNS" -gt 0 ] && [ "$PLAN_MODE" = false ]; then
|
|
log_warn "--plan-talk was specified but --plan mode is not enabled. Discussion turns will be ignored."
|
|
fi
|
|
|
|
# Verdict must occupy the report's last non-blank line — a standalone token
|
|
# quoted mid-report (e.g. as a formatting example) never matches (P0-2).
|
|
has_verdict() {
|
|
local file="$1" verdict="$2"
|
|
local last_line pattern
|
|
last_line=$(grep -v '^[[:space:]]*$' "$file" 2>/dev/null | tail -n 1)
|
|
pattern="^\[VERDICT: ${verdict}\][[:space:]]*\r?\$"
|
|
[[ "$last_line" =~ $pattern ]]
|
|
}
|
|
|
|
# Detect a standalone '[TAG]' line anywhere in a report FILE.
|
|
#
|
|
# Always read the file, never a concatenated aggregate: FEEDBACK_AGGREGATE
|
|
# joins reports with a literal backslash-n (bash `echo` without -e leaves it
|
|
# as text), so a tag on a report's FIRST line ends up sharing a physical line
|
|
# with the '--- Reviewer (x) Feedback ---' banner and the '^' anchor misses it.
|
|
has_tag_line() {
|
|
local file="$1" tag="$2"
|
|
[ -f "$file" ] || return 1
|
|
grep -qE "^\[${tag}\][[:space:]]*\r?\$" "$file"
|
|
}
|
|
|
|
# Emit the payload of every standalone '[KEY: value]' line in a report file.
|
|
extract_tag_values() {
|
|
local file="$1" key="$2"
|
|
[ -f "$file" ] || return 0
|
|
sed -n -E "s/^\[${key}:[[:space:]]*([^]]*)\][[:space:]]*\r?$/\1/p" "$file" \
|
|
| sed -E 's/[[:space:]]+$//' | grep -v '^$' || true
|
|
}
|
|
|
|
# Locate a job's final report (transient .mam job tree, agent-name subdir).
|
|
find_report() {
|
|
find ".mam/jobs/$1" -maxdepth 2 -name "report-final.md" 2>/dev/null | head -n 1 || true
|
|
}
|
|
|
|
# Helper: Blocking wait for a delegate job's completion or error state (with safety timeout)
|
|
wait_for_job() {
|
|
local job_id="$1"
|
|
local check_interval=3
|
|
local max_wait="${2:-3900}"
|
|
local deadline
|
|
deadline=$((SECONDS + max_wait))
|
|
|
|
if [ "$VERBOSE" = true ]; then
|
|
log_info "Monitoring job '$job_id' for status changes (timeout: ${max_wait}s)..."
|
|
fi
|
|
|
|
while [ "$SECONDS" -lt "$deadline" ]; do
|
|
local status
|
|
status=$(python3 -c "
|
|
import json, os
|
|
try:
|
|
with open('.mam/jobs/$job_id.json') as f:
|
|
print(json.load(f).get('status', 'unknown'))
|
|
except Exception:
|
|
print('unknown')
|
|
" 2>/dev/null || echo "unknown")
|
|
|
|
if [ "$status" = "completed" ]; then
|
|
if [ "$VERBOSE" = true ]; then
|
|
log_success "Job '$job_id' completed successfully."
|
|
fi
|
|
return 0
|
|
elif [ "$status" = "error" ]; then
|
|
log_error "Job '$job_id' finished with errors."
|
|
return 1
|
|
elif [ "$status" = "cancelled" ]; then
|
|
log_error "Job '$job_id' was cancelled."
|
|
return 1
|
|
fi
|
|
sleep "$check_interval"
|
|
done
|
|
log_error "Job '$job_id' timed out after ${max_wait}s."
|
|
return 1
|
|
}
|
|
|
|
# Resolve active reviewers (excluding $TARGET_AGENT) via lib.sh's
|
|
# load_state_json — the single source of truth for the merged DB/YAML
|
|
# session state, instead of hand-rolling a 4th copy of that lookup (P1-2).
|
|
resolve_all_reviewers() {
|
|
TARGET_AGENT="$TARGET_AGENT" MAM_STATE_JSON="$(load_state_json)" python3 -c "
|
|
import os, json
|
|
d = json.loads(os.environ.get('MAM_STATE_JSON', '{}'))
|
|
target_agent = os.environ.get('TARGET_AGENT')
|
|
reviewers = [s.get('name') for s in d.get('herdr_sessions', [])
|
|
if 'reviewer' in (s.get('role') or '').lower() and s.get('status') == 'running' and s.get('name') != target_agent]
|
|
print(','.join(reviewers))
|
|
"
|
|
}
|
|
|
|
# Resolve target agent type (claude, cline, agy) via load_state_json.
|
|
resolve_agent_type() {
|
|
local name="$1"
|
|
NAME="$name" MAM_STATE_JSON="$(load_state_json)" python3 -c "
|
|
import os, json
|
|
name = os.environ.get('NAME')
|
|
d = json.loads(os.environ.get('MAM_STATE_JSON', '{}'))
|
|
agent = None
|
|
for s in d.get('herdr_sessions', []):
|
|
if s.get('name') == name:
|
|
agent = s.get('agent') or s.get('pane', {}).get('cmd')
|
|
break
|
|
if not agent:
|
|
# Exact hyphen-segment match, not a naive substring 'in' check, so a
|
|
# decoy substring inside an unrelated segment can't misclassify.
|
|
segments = name.split('-')
|
|
if 'agy' in segments:
|
|
agent = 'agy'
|
|
elif 'cline' in segments:
|
|
agent = 'cline'
|
|
elif 'hermes' in segments:
|
|
agent = 'hermes'
|
|
else:
|
|
agent = 'claude'
|
|
print(agent)
|
|
"
|
|
}
|
|
|
|
# Resolve planner session dynamically via load_state_json.
|
|
resolve_planner_session() {
|
|
MAM_STATE_JSON="$(load_state_json)" python3 -c "
|
|
import os, json
|
|
d = json.loads(os.environ.get('MAM_STATE_JSON', '{}'))
|
|
planner = ''
|
|
for s in d.get('herdr_sessions', []):
|
|
if 'planner' in (s.get('role') or '').lower() and s.get('status') == 'running':
|
|
planner = s.get('name')
|
|
break
|
|
print(planner)
|
|
"
|
|
}
|
|
|
|
# Portable Job ID extraction helper (fails-safe, avoids SC1091/grep GNU dependency)
|
|
extract_job_id() {
|
|
local output="$1"
|
|
local job_id
|
|
# Portable extraction equivalent to PCRE K
|
|
job_id=$(echo "$output" | grep -o 'registered job: [A-Za-z0-9]*' | awk '{print $3}' || true)
|
|
echo "$job_id"
|
|
}
|
|
|
|
# Main Execution Loop Flow
|
|
log_info "Initializing multi-agent-mux-loop controller..."
|
|
log_info "Target Agent: $TARGET_AGENT"
|
|
log_info "Task Goal: $TASK"
|
|
|
|
# Validate that Target Agent is registered and running
|
|
TARGET_STATUS=$(MAM_STATE_JSON="$(load_state_json)" TARGET="$TARGET_AGENT" python3 -c "
|
|
import os, json
|
|
d = json.loads(os.environ.get('MAM_STATE_JSON', '{}'))
|
|
target = os.environ.get('TARGET')
|
|
status = ''
|
|
for s in d.get('herdr_sessions', []):
|
|
if s.get('name') == target:
|
|
status = s.get('status')
|
|
break
|
|
print(status)
|
|
")
|
|
|
|
if [ -z "$TARGET_STATUS" ]; then
|
|
log_error "Target agent session '$TARGET_AGENT' is not registered in the session registry."
|
|
exit 1
|
|
elif [ "$TARGET_STATUS" != "running" ]; then
|
|
log_error "Target agent session '$TARGET_AGENT' is not running (current status: '$TARGET_STATUS'). Please start it first."
|
|
exit 1
|
|
fi
|
|
|
|
PLANNER_SESSION=$(resolve_planner_session)
|
|
log_info "Resolved Planner session: $PLANNER_SESSION"
|
|
|
|
if [ "$PLAN_MODE" = true ]; then
|
|
if [ -z "$PLANNER_SESSION" ]; then
|
|
log_error "Planner mode enabled (--plan) but no running session with a 'planner' role was found."
|
|
exit 1
|
|
fi
|
|
fi
|
|
|
|
CURRENT_PLAN=""
|
|
CREATED_JOBS=()
|
|
|
|
# ===========================================================================
|
|
# PHASE 1: PLANNING & DISCUSSIONS
|
|
# ===========================================================================
|
|
if [ "$PLAN_MODE" = true ]; then
|
|
log_info "=== Phase 1: Interactive Planning Phase ==="
|
|
|
|
# Step 1.1: Request initial plan from Planner
|
|
log_info "Requesting initial implementation plan from Planner..."
|
|
PLAN_JOB_OUTPUT=$(delegate_job_safe submit \
|
|
--agent-session "herdr:$PLANNER_SESSION" \
|
|
--agent "$(resolve_agent_type "$PLANNER_SESSION")" \
|
|
--type "direct" \
|
|
--role "Planner" \
|
|
--prompt "태스크 목표를 바탕으로 구체적인 구현 계획서를 작성해주세요. 목표: $TASK")
|
|
|
|
PLAN_JOB_ID=$(extract_job_id "$PLAN_JOB_OUTPUT")
|
|
if [ -z "$PLAN_JOB_ID" ]; then
|
|
log_error "Failed to register planner job. Output:\n$PLAN_JOB_OUTPUT"
|
|
exit 1
|
|
fi
|
|
CREATED_JOBS+=("$PLAN_JOB_ID")
|
|
log_info "Planner Job ID: $PLAN_JOB_ID"
|
|
|
|
if ! wait_for_job "$PLAN_JOB_ID"; then
|
|
log_error "Planning phase failed during initial plan design."
|
|
exit 1
|
|
fi
|
|
|
|
# Retrieve plan text safely
|
|
PLAN_FILE=$(find ".mam/jobs/$PLAN_JOB_ID" -maxdepth 2 -name "report-final.md" 2>/dev/null | head -n 1 || true)
|
|
if [ -z "$PLAN_FILE" ] || [ ! -f "$PLAN_FILE" ]; then
|
|
log_error "Final plan file not found."
|
|
exit 1
|
|
fi
|
|
CURRENT_PLAN=$(cat "$PLAN_FILE")
|
|
|
|
# Step 1.2: Interactive Creator-Planner Debate
|
|
turn=1
|
|
while [ "$turn" -le "$PLAN_TALK_TURNS" ]; do
|
|
log_info "Discussion Turn $turn/$PLAN_TALK_TURNS: Creator challenging the plan..."
|
|
|
|
# Creator critique job
|
|
DEBATE_JOB_OUTPUT=$(delegate_job_safe submit \
|
|
--agent-session "herdr:$TARGET_AGENT" \
|
|
--agent "$(resolve_agent_type "$TARGET_AGENT")" \
|
|
--type "direct" \
|
|
--role "Worker" \
|
|
--prompt "Planner가 제시한 다음 계획서를 꼼꼼히 검토하고, 실제 구현 시 마주할 수 있는 맹점이나 제약사항 1가지를 발굴하여 Planner에게 이의를 제기(Challenge)해주세요. 계획서:\n$CURRENT_PLAN")
|
|
|
|
DEBATE_JOB_ID=$(extract_job_id "$DEBATE_JOB_OUTPUT")
|
|
if [ -z "$DEBATE_JOB_ID" ]; then
|
|
log_error "Failed to register Creator critique job. Output:\n$DEBATE_JOB_OUTPUT"
|
|
exit 1
|
|
fi
|
|
CREATED_JOBS+=("$DEBATE_JOB_ID")
|
|
log_info "Critique Job ID: $DEBATE_JOB_ID"
|
|
|
|
if ! wait_for_job "$DEBATE_JOB_ID"; then
|
|
log_error "Creator critique step failed."
|
|
exit 1
|
|
fi
|
|
|
|
CRITIQUE_FILE=$(find ".mam/jobs/$DEBATE_JOB_ID" -maxdepth 2 -name "report-final.md" 2>/dev/null | head -n 1 || true)
|
|
if [ -z "$CRITIQUE_FILE" ] || [ ! -f "$CRITIQUE_FILE" ]; then
|
|
log_error "Critique file not found."
|
|
exit 1
|
|
fi
|
|
CRITIQUE_TEXT=$(cat "$CRITIQUE_FILE")
|
|
|
|
log_info "Planner refining plan with Creator's feedback..."
|
|
REFINE_JOB_OUTPUT=$(delegate_job_safe submit \
|
|
--agent-session "herdr:$PLANNER_SESSION" \
|
|
--agent "$(resolve_agent_type "$PLANNER_SESSION")" \
|
|
--type "direct" \
|
|
--role "Planner" \
|
|
--prompt "작업자(Creator)로부터 다음 이의제기 피드백을 받았습니다. 피드백을 반영하여 계획서를 정교하게 업데이트(Refine)하여 다시 출력해주세요. 피드백:\n$CRITIQUE_TEXT\n기존 계획서:\n$CURRENT_PLAN")
|
|
|
|
REFINE_JOB_ID=$(extract_job_id "$REFINE_JOB_OUTPUT")
|
|
if [ -z "$REFINE_JOB_ID" ]; then
|
|
log_error "Failed to register plan refinement job. Output:\n$REFINE_JOB_OUTPUT"
|
|
exit 1
|
|
fi
|
|
CREATED_JOBS+=("$REFINE_JOB_ID")
|
|
log_info "Refinement Job ID: $REFINE_JOB_ID"
|
|
|
|
if ! wait_for_job "$REFINE_JOB_ID"; then
|
|
log_error "Planner refinement step failed."
|
|
exit 1
|
|
fi
|
|
|
|
REFINE_FILE=$(find ".mam/jobs/$REFINE_JOB_ID" -maxdepth 2 -name "report-final.md" 2>/dev/null | head -n 1 || true)
|
|
if [ -z "$REFINE_FILE" ] || [ ! -f "$REFINE_FILE" ]; then
|
|
log_error "Refinement plan file not found."
|
|
exit 1
|
|
fi
|
|
CURRENT_PLAN=$(cat "$REFINE_FILE")
|
|
|
|
turn=$((turn + 1))
|
|
done
|
|
log_success "Interactive planning completed. Plan finalized."
|
|
else
|
|
log_info "=== Phase 1: Self-Planning Mode (Direct Execution) ==="
|
|
EXISTING_PLAN_FILE=""
|
|
if [ -n "$PLANNER_SESSION" ]; then
|
|
# Promoted plans are saved as plan-<job-id>.md by the Phase 3 promotion
|
|
# step below, not report-final.md; pick the most recently promoted one.
|
|
EXISTING_PLAN_FILE=$(ls -t ".agents/reports/$PLANNER_SESSION"/plan-*.md 2>/dev/null | head -n 1 || true)
|
|
fi
|
|
if [ -n "$EXISTING_PLAN_FILE" ] && [ -f "$EXISTING_PLAN_FILE" ]; then
|
|
log_info "Found existing promoted plan at '$EXISTING_PLAN_FILE'. Loading plan..."
|
|
CURRENT_PLAN=$(cat "$EXISTING_PLAN_FILE")
|
|
fi
|
|
fi
|
|
|
|
# ===========================================================================
|
|
# PHASE 2: IMPLEMENTATION (CREATION)
|
|
# ===========================================================================
|
|
log_info "=== Phase 2: Code Implementation ==="
|
|
|
|
# Fix the pre-implementation commit as the diff baseline so review diffs stay
|
|
# cumulative and non-empty even after the Creator commits per DoD (P0-1).
|
|
BASE_COMMIT=$(cd -P "$REPO_ROOT" 2>/dev/null && git rev-parse HEAD 2>/dev/null || echo "")
|
|
|
|
EXECUTION_PROMPT="계획서가 존재하지 않으므로, 작업자(Creator)의 판단하에 스스로 구현 계획 및 설계를 수립한 뒤, 이를 바탕으로 코드를 구현하고 다음 작업 목표를 완성해주세요. 작업 목표: $TASK"
|
|
if [ -n "$CURRENT_PLAN" ]; then
|
|
EXECUTION_PROMPT="이미 수립된 다음 계획서에 입각하여 작업자의 판단하에 코드를 구현하고 작업 목표를 완성해주세요. 계획서:\n$CURRENT_PLAN\n\n작업 목표: $TASK"
|
|
fi
|
|
|
|
EXEC_JOB_OUTPUT=$(delegate_job_safe submit \
|
|
--agent-session "herdr:$TARGET_AGENT" \
|
|
--agent "$(resolve_agent_type "$TARGET_AGENT")" \
|
|
--type "direct" \
|
|
--role "Worker" \
|
|
--prompt "$EXECUTION_PROMPT")
|
|
|
|
EXEC_JOB_ID=$(extract_job_id "$EXEC_JOB_OUTPUT")
|
|
if [ -z "$EXEC_JOB_ID" ]; then
|
|
log_error "Failed to register Creator execution job. Output:\n$EXEC_JOB_OUTPUT"
|
|
exit 1
|
|
fi
|
|
CREATED_JOBS+=("$EXEC_JOB_ID")
|
|
log_info "Creator Job ID: $EXEC_JOB_ID"
|
|
|
|
if ! wait_for_job "$EXEC_JOB_ID"; then
|
|
log_error "Creator execution failed."
|
|
exit 1
|
|
fi
|
|
log_success "Initial implementation finished."
|
|
|
|
# ===========================================================================
|
|
# PHASE 3: VERIFICATION LOOP (PEER REVIEW)
|
|
# ===========================================================================
|
|
log_info "=== Phase 3: Verification & Corrective Review Loop ==="
|
|
|
|
# Resolve reviewer array
|
|
REVIEWERS=()
|
|
if [ "$ALL_REVIEWERS" = true ]; then
|
|
# Parse list safely using command substitution + fallback
|
|
RESOLVED_REVS=$(resolve_all_reviewers)
|
|
if [ -n "$RESOLVED_REVS" ]; then
|
|
IFS=' ,' read -r -a REVIEWERS <<< "$RESOLVED_REVS"
|
|
fi
|
|
if [ "${#REVIEWERS[@]}" -eq 0 ]; then
|
|
log_error "--all-reviewer was specified, but no running reviewer sessions were found."
|
|
exit 1
|
|
fi
|
|
elif [ -n "$REVIEWER_LIST" ]; then
|
|
# Strip whitespaces first to prevent empty array elements from trailing spaces
|
|
CLEAN_REVS=$(echo "$REVIEWER_LIST" | tr -d '[:space:]')
|
|
IFS=',' read -r -a REVIEWERS <<< "$CLEAN_REVS"
|
|
fi
|
|
|
|
loop_count=1
|
|
while [ "$loop_count" -le "$MAX_LOOP" ]; do
|
|
log_info "Review Loop Iteration $loop_count/$MAX_LOOP..."
|
|
|
|
# O-1: the per-iteration budget resets each pass, because each pass produces
|
|
# NEW findings that may be legitimately rebuttable. The run-wide total is
|
|
# capped separately by REBUT_TOTAL_BUDGET so the reset cannot be mistaken for
|
|
# an unbounded channel (see MULTI_AGENT_RULES.md §3.1 rule 3).
|
|
REBUT_BUDGET="$MAX_REBUT"
|
|
|
|
if [ "${#REVIEWERS[@]}" -eq 0 ]; then
|
|
log_warn "No reviewers specified. Conducting Creator Self-Review..."
|
|
SELF_REV_OUTPUT=$(delegate_job_safe submit \
|
|
--agent-session "herdr:$TARGET_AGENT" \
|
|
--agent "$(resolve_agent_type "$TARGET_AGENT")" \
|
|
--type "direct" \
|
|
--role "Reviewer" \
|
|
--prompt "작업 완료 상태에 대해 스스로 검증(Self-Review)하여 결함이 없음을 확인하고 종결해주세요. 리뷰 리포트 마지막에 단독 행으로 반드시 '[VERDICT: PASS]' 혹은 '[VERDICT: NOT PASS]' 태그를 명시해주세요.")
|
|
|
|
SELF_REV_ID=$(extract_job_id "$SELF_REV_OUTPUT")
|
|
if [ -z "$SELF_REV_ID" ]; then
|
|
log_error "Failed to register Self-Review job."
|
|
exit 1
|
|
fi
|
|
CREATED_JOBS+=("$SELF_REV_ID")
|
|
wait_for_job "$SELF_REV_ID"
|
|
|
|
REPORT_FILE=$(find ".mam/jobs/$SELF_REV_ID" -maxdepth 2 -name "report-final.md" 2>/dev/null | head -n 1 || true)
|
|
if [ -n "$REPORT_FILE" ] && [ -f "$REPORT_FILE" ] && has_verdict "$REPORT_FILE" "PASS" && ! has_verdict "$REPORT_FILE" "NOT PASS"; then
|
|
log_success "Self-Review PASS."
|
|
break
|
|
else
|
|
log_warn "Self-Review NOT PASS."
|
|
if [ "$loop_count" -eq "$MAX_LOOP" ]; then
|
|
log_error "Reached max loop count. Self-review loop aborted with failures."
|
|
exit 1
|
|
fi
|
|
fi
|
|
else
|
|
log_info "Active reviewers: ${REVIEWERS[*]}"
|
|
|
|
CHANGES_DIFF=$(mam_collect_changes_diff "$REPO_ROOT" "$BASE_COMMIT") || {
|
|
log_error "Could not determine the change set; refusing to request a review on no evidence."
|
|
log_error "$CHANGES_DIFF"
|
|
exit 1
|
|
}
|
|
|
|
# We use space-separated lists or simple loops to bypass bash-4 associative array requirement (M-7 macOS compatibility)
|
|
declare -a JOB_IDS=()
|
|
declare -a JOB_REVS=()
|
|
# Objecting reviewers and their report paths, kept in parallel arrays so the
|
|
# rebuttal round can address each objection individually (O-1).
|
|
declare -a FAIL_REVS=()
|
|
declare -a FAIL_REPORTS=()
|
|
|
|
for rev in "${REVIEWERS[@]}"; do
|
|
log_info "Requesting code review from Reviewer '$rev'..."
|
|
|
|
REV_OUTPUT=$(delegate_job_safe submit \
|
|
--agent-session "herdr:$rev" \
|
|
--agent "$(resolve_agent_type "$rev")" \
|
|
--type "direct" \
|
|
--role "Reviewer" \
|
|
--prompt "다음 구현 사항(작업 목표: $TASK) 및 누적 변경분(git diff)에 대해 린트, 동작성, 유실 등의 관점에서 교차 코드 리뷰를 수행해주세요. 확인 후 최종 Verdict로 '[VERDICT: PASS]' 혹은 '[VERDICT: NOT PASS]' 태그를 리뷰 리포트 마지막에 단독 행으로 명시적으로 작성해주세요. 만약 단순 버그 수정으로는 부족하고 설계 변경/재작업 수준의 재계획이 필요하다고 판단되면, 리포트 아무 곳에나 단독 행으로 '[ESCALATE: PLANNER]' 태그도 함께 남겨주세요. 변경분:\n$CHANGES_DIFF")
|
|
|
|
REV_JOB_ID=$(extract_job_id "$REV_OUTPUT")
|
|
if [ -z "$REV_JOB_ID" ]; then
|
|
log_error "Failed to register review job for '$rev'."
|
|
exit 1
|
|
fi
|
|
CREATED_JOBS+=("$REV_JOB_ID")
|
|
JOB_IDS+=("$REV_JOB_ID")
|
|
JOB_REVS+=("$rev")
|
|
done
|
|
|
|
# Wait for all reviews
|
|
all_passed=true
|
|
FEEDBACK_AGGREGATE=""
|
|
|
|
for idx in "${!JOB_IDS[@]}"; do
|
|
job_id="${JOB_IDS[$idx]}"
|
|
rev="${JOB_REVS[$idx]}"
|
|
|
|
if ! wait_for_job "$job_id"; then
|
|
log_warn "Reviewer '$rev' job crashed."
|
|
all_passed=false
|
|
continue
|
|
fi
|
|
|
|
# Parse verdict from report file (fails-safe, M-2 anchored checks)
|
|
REPORT_FILE=$(find ".mam/jobs/$job_id" -maxdepth 2 -name "report-final.md" 2>/dev/null | head -n 1 || true)
|
|
if [ -z "$REPORT_FILE" ] || [ ! -f "$REPORT_FILE" ]; then
|
|
log_warn "Reviewer '$rev' report not found. Counting as NOT PASS."
|
|
all_passed=false
|
|
continue
|
|
fi
|
|
|
|
REPORT_CONTENT=$(cat "$REPORT_FILE" 2>/dev/null || echo "")
|
|
|
|
# Precedence rules: NOT PASS wins over PASS. Absence of verdict tags is treated as NOT PASS (fail-closed)
|
|
if has_verdict "$REPORT_FILE" "NOT PASS" || ! has_verdict "$REPORT_FILE" "PASS"; then
|
|
log_warn "Reviewer '$rev': NOT PASS"
|
|
all_passed=false
|
|
FAIL_REVS+=("$rev")
|
|
FAIL_REPORTS+=("$REPORT_FILE")
|
|
FEEDBACK_AGGREGATE="$FEEDBACK_AGGREGATE\n--- Reviewer ($rev) Feedback ---\n$REPORT_CONTENT"
|
|
else
|
|
log_success "Reviewer '$rev': PASS"
|
|
fi
|
|
done
|
|
|
|
if [ "$all_passed" = true ]; then
|
|
log_success "All reviewers issued [VERDICT: PASS]. Loop completed successfully."
|
|
break
|
|
else
|
|
if [ "$loop_count" -eq "$MAX_LOOP" ]; then
|
|
log_error "Reached max loop count ($MAX_LOOP). Review loop aborted with failures."
|
|
exit 1
|
|
fi
|
|
|
|
# Scan the report FILES, not FEEDBACK_AGGREGATE: the aggregate's literal
|
|
# '\n' separators break '^' anchoring for a tag on a report's first line.
|
|
# bash 3.2 (macOS stock) aborts on "${arr[@]}" when arr is empty under
|
|
# `set -u`. FAIL_REPORTS IS empty on the crashed-job / missing-report
|
|
# paths above, which reach here via all_passed=false without appending.
|
|
COMPLEX_FIX=false
|
|
for _fr in ${FAIL_REPORTS[@]+"${FAIL_REPORTS[@]}"}; do
|
|
if has_tag_line "$_fr" "ESCALATE: PLANNER"; then
|
|
COMPLEX_FIX=true
|
|
break
|
|
fi
|
|
done
|
|
|
|
if [ "$PLAN_MODE" = true ] && [ "$COMPLEX_FIX" = true ]; then
|
|
log_warn "Feedback involves complex code modifications. Diverting to Planner to revise plan..."
|
|
|
|
REFINE_PLAN_OUTPUT=$(delegate_job_safe submit \
|
|
--agent-session "herdr:$PLANNER_SESSION" \
|
|
--agent "$(resolve_agent_type "$PLANNER_SESSION")" \
|
|
--type "direct" \
|
|
--role "Planner" \
|
|
--prompt "리뷰어들로부터 다음과 같이 정교한 코드 수정 피드백이 도착했습니다. 해당 피드백을 수렴하여 구현 계획서(Plan)를 갱신(Refine)하여 다시 작성해주세요. 피드백:\n$FEEDBACK_AGGREGATE\n기존 계획서:\n$CURRENT_PLAN")
|
|
|
|
REFINE_PLAN_ID=$(extract_job_id "$REFINE_PLAN_OUTPUT")
|
|
if [ -z "$REFINE_PLAN_ID" ]; then
|
|
log_error "Failed to register plan refinement job."
|
|
exit 1
|
|
fi
|
|
CREATED_JOBS+=("$REFINE_PLAN_ID")
|
|
wait_for_job "$REFINE_PLAN_ID"
|
|
|
|
REFINE_PLAN_FILE=$(find ".mam/jobs/$REFINE_PLAN_ID" -maxdepth 2 -name "report-final.md" 2>/dev/null | head -n 1 || true)
|
|
if [ -z "$REFINE_PLAN_FILE" ] || [ ! -f "$REFINE_PLAN_FILE" ]; then
|
|
log_error "Refined plan file not found."
|
|
exit 1
|
|
fi
|
|
CURRENT_PLAN=$(cat "$REFINE_PLAN_FILE")
|
|
|
|
CORRECTION_PROMPT="갱신된 다음 계획서에 입각하여 지적된 오류들을 수정하고 코드를 다시 구현해주세요. 계획서:\n$CURRENT_PLAN\n피드백 상세:\n$FEEDBACK_AGGREGATE"
|
|
else
|
|
log_info "Applying straight bugfixes based on reviewer feedback..."
|
|
CORRECTION_PROMPT="리뷰어들이 지적한 다음 피드백에 입각하여 코드를 수정해주세요. 피드백:\n$FEEDBACK_AGGREGATE"
|
|
fi
|
|
|
|
if [ "$MAX_REBUT" -gt 0 ]; then
|
|
CORRECTION_PROMPT="$CORRECTION_PROMPT\n\n[이의제기 채널] 위 피드백 중 타당하지 않다고 판단되는 항목이 있다면, 그 항목은 구현하지 말고 반론을 제기하십시오. 반론 시 리포트에 단독 행으로 '[REBUT: <리뷰어_세션명>]' 태그를 남기고, 해당 리뷰어의 지적 중 어느 항목을 왜 거부하는지 근거를 함께 서술하십시오. 타당한 지적은 정상적으로 반영하십시오. 반론할 항목이 없으면 태그를 남기지 마십시오. 대상 리뷰어 세션명: ${FAIL_REVS[*]-(없음)}"
|
|
fi
|
|
|
|
# Creator execution corrective job
|
|
CORRECT_JOB_OUTPUT=$(delegate_job_safe submit \
|
|
--agent-session "herdr:$TARGET_AGENT" \
|
|
--agent "$(resolve_agent_type "$TARGET_AGENT")" \
|
|
--type "direct" \
|
|
--role "Worker" \
|
|
--prompt "$CORRECTION_PROMPT")
|
|
|
|
CORRECT_JOB_ID=$(extract_job_id "$CORRECT_JOB_OUTPUT")
|
|
if [ -z "$CORRECT_JOB_ID" ]; then
|
|
log_error "Failed to register Creator correction job."
|
|
exit 1
|
|
fi
|
|
CREATED_JOBS+=("$CORRECT_JOB_ID")
|
|
wait_for_job "$CORRECT_JOB_ID"
|
|
|
|
# ---------------------------------------------------------------------
|
|
# O-1: REBUTTAL & ADJUDICATION ROUND
|
|
# ---------------------------------------------------------------------
|
|
# The Creator's correction report was previously produced and discarded.
|
|
# Read it: standalone '[REBUT: <reviewer>]' lines open an adjudication
|
|
# round with exactly those reviewers.
|
|
#
|
|
# Invariant: a rebuttal NEVER substitutes for a PASS. A sustained
|
|
# rebuttal only withdraws an objection; the next iteration still runs a
|
|
# full review pass, so the loop can still only exit 0 on unanimous
|
|
# [VERDICT: PASS].
|
|
if [ "$MAX_REBUT" -gt 0 ] && [ "$REBUT_BUDGET" -gt 0 ] && [ "$REBUT_TOTAL_BUDGET" -gt 0 ]; then
|
|
CORRECT_REPORT=$(find_report "$CORRECT_JOB_ID")
|
|
REBUT_TARGETS=()
|
|
if [ -n "$CORRECT_REPORT" ]; then
|
|
while IFS= read -r _t; do
|
|
[ -n "$_t" ] || continue
|
|
# Only honour rebuttals aimed at a reviewer that actually objected,
|
|
# and de-duplicate: a Creator may file one [REBUT:] per rejected
|
|
# finding, all naming the same reviewer — that is ONE adjudication.
|
|
for _fv in ${FAIL_REVS[@]+"${FAIL_REVS[@]}"}; do
|
|
[ "$_t" = "$_fv" ] || continue
|
|
_dup=0
|
|
for _e in ${REBUT_TARGETS[@]+"${REBUT_TARGETS[@]}"}; do
|
|
if [ "$_e" = "$_t" ]; then _dup=1; break; fi
|
|
done
|
|
[ "$_dup" -eq 0 ] && REBUT_TARGETS+=("$_t")
|
|
break
|
|
done
|
|
done <<< "$(extract_tag_values "$CORRECT_REPORT" "REBUT")"
|
|
fi
|
|
|
|
if [ "${#REBUT_TARGETS[@]}" -gt 0 ]; then
|
|
REBUT_BUDGET=$((REBUT_BUDGET - 1))
|
|
REBUT_TOTAL_BUDGET=$((REBUT_TOTAL_BUDGET - 1))
|
|
REBUTTAL_TEXT=$(cat "$CORRECT_REPORT" 2>/dev/null || echo "")
|
|
log_warn "Creator filed a rebuttal against: ${REBUT_TARGETS[*]} (iteration budget left: $REBUT_BUDGET, run total left: $REBUT_TOTAL_BUDGET)"
|
|
|
|
OVERRULED_REVS=()
|
|
for rt in "${REBUT_TARGETS[@]}"; do
|
|
log_info "Re-adjudication: returning rebuttal to Reviewer '$rt'..."
|
|
ADJ_OUTPUT=$(delegate_job_safe submit \
|
|
--agent-session "herdr:$rt" \
|
|
--agent "$(resolve_agent_type "$rt")" \
|
|
--type "direct" \
|
|
--role "Reviewer" \
|
|
--prompt "작업자(Creator)가 귀하의 리뷰 지적 중 일부를 타당하지 않다고 판단하여 반론을 제기했습니다. 반론을 검토하고 재심(re-adjudication)하십시오. 반론이 타당하여 귀하의 지적을 철회한다면 리포트 마지막에 단독 행으로 '[ADJUDICATION: SUSTAINED]' 를, 반론이 타당하지 않아 지적을 유지한다면 '[ADJUDICATION: OVERRULED]' 를 명시하십시오. 반론 내용:\n$REBUTTAL_TEXT")
|
|
|
|
ADJ_JOB_ID=$(extract_job_id "$ADJ_OUTPUT")
|
|
if [ -z "$ADJ_JOB_ID" ]; then
|
|
log_error "Failed to register re-adjudication job for '$rt'."
|
|
exit 1
|
|
fi
|
|
CREATED_JOBS+=("$ADJ_JOB_ID")
|
|
if ! wait_for_job "$ADJ_JOB_ID"; then
|
|
log_warn "Re-adjudication job for '$rt' failed; objection stands."
|
|
OVERRULED_REVS+=("$rt")
|
|
continue
|
|
fi
|
|
|
|
ADJ_REPORT=$(find_report "$ADJ_JOB_ID")
|
|
# Fail-closed: anything that is not an explicit SUSTAINED keeps the
|
|
# reviewer's objection alive.
|
|
if [ -n "$ADJ_REPORT" ] && has_tag_line "$ADJ_REPORT" "ADJUDICATION: SUSTAINED"; then
|
|
log_success "Reviewer '$rt' SUSTAINED the rebuttal; objection withdrawn."
|
|
else
|
|
log_warn "Reviewer '$rt' OVERRULED the rebuttal; objection stands."
|
|
OVERRULED_REVS+=("$rt")
|
|
fi
|
|
done
|
|
|
|
# Deadlock: the Creator rebutted and the reviewer held. In --plan mode
|
|
# the Planner arbitrates; otherwise the reviewer prevails (fail-closed,
|
|
# charter §1: a reviewer's PASS is the completion gate).
|
|
if [ "${#OVERRULED_REVS[@]}" -gt 0 ]; then
|
|
ARBITRATION="REVIEWER"
|
|
if [ "$PLAN_MODE" = true ] && [ -n "$PLANNER_SESSION" ]; then
|
|
log_info "Deadlock on ${OVERRULED_REVS[*]}; escalating to Planner for arbitration..."
|
|
ARB_OUTPUT=$(delegate_job_safe submit \
|
|
--agent-session "herdr:$PLANNER_SESSION" \
|
|
--agent "$(resolve_agent_type "$PLANNER_SESSION")" \
|
|
--type "direct" \
|
|
--role "Planner" \
|
|
--prompt "작업자(Creator)와 리뷰어의 의견이 충돌하여 교착 상태입니다. 계획서 관점에서 어느 쪽이 타당한지 재정(arbitration)하십시오. 리포트 마지막에 단독 행으로 '[ARBITRATION: CREATOR]' 또는 '[ARBITRATION: REVIEWER]' 를 명시하십시오. 리뷰어 지적:\n$FEEDBACK_AGGREGATE\n작업자 반론:\n$REBUTTAL_TEXT\n기존 계획서:\n$CURRENT_PLAN")
|
|
|
|
ARB_JOB_ID=$(extract_job_id "$ARB_OUTPUT")
|
|
if [ -z "$ARB_JOB_ID" ]; then
|
|
log_error "Failed to register Planner arbitration job."
|
|
exit 1
|
|
fi
|
|
CREATED_JOBS+=("$ARB_JOB_ID")
|
|
if wait_for_job "$ARB_JOB_ID"; then
|
|
ARB_REPORT=$(find_report "$ARB_JOB_ID")
|
|
if [ -n "$ARB_REPORT" ] && has_tag_line "$ARB_REPORT" "ARBITRATION: CREATOR"; then
|
|
ARBITRATION="CREATOR"
|
|
fi
|
|
else
|
|
log_warn "Planner arbitration job failed; defaulting to REVIEWER."
|
|
fi
|
|
fi
|
|
|
|
if [ "$ARBITRATION" = "CREATOR" ]; then
|
|
log_success "Planner ruled for the Creator; objections withdrawn for this round."
|
|
else
|
|
log_warn "Ruling stands with the reviewer(s); Creator must comply."
|
|
# Close the channel for the REST OF THIS ITERATION and require
|
|
# compliance. Note this does not persist into the next iteration
|
|
# (which re-reviews and may raise different findings); the
|
|
# run-wide cap REBUT_TOTAL_BUDGET is what bounds the whole run.
|
|
REBUT_BUDGET=0
|
|
COMPLY_OUTPUT=$(delegate_job_safe submit \
|
|
--agent-session "herdr:$TARGET_AGENT" \
|
|
--agent "$(resolve_agent_type "$TARGET_AGENT")" \
|
|
--type "direct" \
|
|
--role "Worker" \
|
|
--prompt "귀하의 반론은 재심 결과 기각되었습니다. 더 이상 반론하지 말고 다음 리뷰 피드백을 그대로 반영하여 코드를 수정하십시오. 피드백:\n$FEEDBACK_AGGREGATE")
|
|
|
|
COMPLY_JOB_ID=$(extract_job_id "$COMPLY_OUTPUT")
|
|
if [ -z "$COMPLY_JOB_ID" ]; then
|
|
log_error "Failed to register Creator compliance job."
|
|
exit 1
|
|
fi
|
|
CREATED_JOBS+=("$COMPLY_JOB_ID")
|
|
wait_for_job "$COMPLY_JOB_ID"
|
|
fi
|
|
fi
|
|
fi
|
|
fi
|
|
fi
|
|
fi
|
|
|
|
loop_count=$((loop_count + 1))
|
|
done
|
|
|
|
# Promote finalized plan and passed reviewer reports to durable location
|
|
if [ "$PLAN_MODE" = true ] && [ -n "${CURRENT_PLAN:-}" ] && [ -n "${PLAN_JOB_ID:-}" ]; then
|
|
plan_dest_dir=".agents/reports/$PLANNER_SESSION"
|
|
log_info "Promoting final plan to durable location: $plan_dest_dir"
|
|
mkdir -p "$plan_dest_dir"
|
|
echo "$CURRENT_PLAN" > "$plan_dest_dir/plan-${PLAN_JOB_ID}.md.tmp"
|
|
mv -f "$plan_dest_dir/plan-${PLAN_JOB_ID}.md.tmp" "$plan_dest_dir/plan-${PLAN_JOB_ID}.md"
|
|
fi
|
|
|
|
if [ "${#REVIEWERS[@]}" -gt 0 ]; then
|
|
log_info "Promoting final review reports to durable location..."
|
|
for idx in "${!JOB_IDS[@]}"; do
|
|
job_id="${JOB_IDS[$idx]}"
|
|
rev="${JOB_REVS[$idx]}"
|
|
report_file=$(find ".mam/jobs/$job_id" -maxdepth 2 -name "report-final.md" 2>/dev/null | head -n 1 || true)
|
|
if [ -n "$report_file" ] && [ -f "$report_file" ]; then
|
|
dest_dir=".agents/reports/$rev"
|
|
mkdir -p "$dest_dir"
|
|
cp "$report_file" "$dest_dir/report-${job_id}.md.tmp"
|
|
mv -f "$dest_dir/report-${job_id}.md.tmp" "$dest_dir/report-${job_id}.md"
|
|
fi
|
|
done
|
|
fi
|
|
|
|
# ===========================================================================
|
|
# PHASE 4: CLEANUP
|
|
# ===========================================================================
|
|
if [ "$CLEANUP" = true ]; then
|
|
log_info "Cleaning up temporary job directories created during this loop run..."
|
|
for job in "${CREATED_JOBS[@]}"; do
|
|
if [ -d ".mam/jobs/$job" ]; then
|
|
rm -rf ".mam/jobs/$job"
|
|
rm -f ".mam/jobs/$job.subscriber.out"
|
|
if [ "$VERBOSE" = true ]; then
|
|
log_info "Purged temp assets for job: $job"
|
|
fi
|
|
fi
|
|
done
|
|
log_success "Cleanup complete."
|
|
fi
|
|
|
|
log_success "Mux loop finished with 100% PASS verdicts."
|
|
exit 0
|