fix(loop): repair review-diff/verdict-parsing bugs, deduplicate session lookups

Applies the P0-P3 fixes from the multi-agent-mux-loop audit
(.mam/jobs/ab686e47/claude-reports/report-final.md):

- P0-1: capture BASE_COMMIT before Phase 2 and diff against it, so reviewer
  diffs stay non-empty and cumulative even after the Creator commits per the
  documented DoD (bare `git diff` alone showed nothing once committed).
- P0-2: has_verdict now matches only the report's last non-blank line, so a
  stray [VERDICT: ...] token quoted mid-report as a formatting example can no
  longer flip the outcome.
- P1-1: replace the English-only refactor/complex/design/architect keyword
  sniff (dead code against Korean-language reviewer reports) with an explicit
  [ESCALATE: PLANNER] tag the reviewer prompt now asks for.
- P1-2: resolve_all_reviewers/resolve_agent_type/resolve_planner_session now
  read through lib.sh's load_state_json single source of truth instead of
  each hand-rolling its own SQLite+YAML lookup; resolve_agent_type's name
  fallback matches exact hyphen segments instead of a substring `in` check.
- P2-1: warn when --all-reviewer and --reviewer are both given, since the
  latter is silently discarded.
- P2-2: correct the SKILL.md CLI-mapping table row that overstated an
  automated lint gate and an unconditional Planner feedback loop.
- P3: fix lib.sh shellcheck SC2164 (unguarded cd in start_watchdog) and
  annotate the intentional SC2317 dual source/exec guard.

Verified: shellcheck clean on both scripts, bash -n syntax OK, and the
rewritten has_verdict/resolve_* functions were unit-tested against this
repo's live .mam/agent-sessions state.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

.agents/skills/lib.sh

@@ -16,6 +16,9 @@
 
 if [ -z "${BASH_VERSION:-}" ]; then
   echo "ERROR: lib.sh must be executed/sourced from bash (foreign shell detected)" >&2
+  # Reachable when this file is executed directly rather than sourced;
+  # `return` only fails (falling through to `exit`) in that path.
+  # shellcheck disable=SC2317
   return 1 2>/dev/null || exit 1
 fi
 SKILL_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
@@ -1018,10 +1021,10 @@ start_watchdog() {
     # Start the wildcard monitor subscriber daemon with --idle-timeout 0 (never idle out)
     # and ensure it runs with $workdir as cwd to anchor relative log paths.
     local orig_pwd="$PWD"
-    cd "$workdir"
+    cd "$workdir" || return 1
     nohup bash "$monitor_script" --subscribe --idle-timeout 0 >> "$log_file" 2>&1 &
     pid=$!
-    cd "$orig_pwd"
+    cd "$orig_pwd" || return 1
   fi
   
   echo "$pid"

.agents/skills/multi-agent-mux-loop/SKILL.md

@@ -143,7 +143,7 @@ sequenceDiagram
 | **Phase 2: Execution** | (기본값) | `--target-agent`로 명시한 주 작업 세션에 코딩 태스크를 주입합니다. |
 | **Phase 3: Review** | `--reviewer "A,B"` | 지정된 리뷰어 세션 리스트(`A`, `B` 등)에 교차 Peer Review를 위임합니다. |
 | **Phase 3: Consensus** | `--all-reviewer` | 레지스트리에 등록된 모든 active 리뷰어 세션을 자동으로 수집하여 리뷰를 돌립니다. (지정/수집된 모든 리뷰어의 PASS 만장일치가 항상 필요합니다.) |
-| **Iterative Loop** | `--max-loop M` | NOT PASS 또는 린트 실패 시 최대 `M`회까지 Planner와 Creator 간 피드백 루프를 반복합니다. |
+| **Iterative Loop** | `--max-loop M` | NOT PASS 판정 시 최대 `M`회까지 Creator가 자체 수정합니다. `--plan` 모드에서 리뷰어가 리포트에 `[ESCALATE: PLANNER]` 태그를 남기면 설계 변경 수준으로 판단하여 Planner에게 계획 갱신을 위임합니다 (린트는 리뷰어가 검토 관점 중 하나로 확인할 뿐, 별도의 자동 게이트는 아닙니다). |
 
 ---
 

.agents/skills/multi-agent-mux-loop/scripts/run_loop.sh

@@ -84,10 +84,20 @@ log_error() {
   echo -e "\033[1;31m[✗]\033[0m $1"
 }
 
-# Verdict must occupy its own line — quoted/diff-embedded tokens ('+', '>' prefixed) never match.
+# --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
+
+# 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"
-  grep -qE "^\[VERDICT: ${verdict}\][[:space:]]*\r?$" "$file"
+  local last_line pattern
+  last_line=$(grep -v '^[[:space:]]*$' "$file" 2>/dev/null | tail -n 1)
+  pattern="^\[VERDICT: ${verdict}\][[:space:]]*\r?\$"
+  [[ "$last_line" =~ $pattern ]]
 }
 
 # Helper: Blocking wait for a delegate job's completion or error state (with safety timeout)
@@ -128,100 +138,58 @@ except Exception:
   return 1
 }
 
-# Resolve active reviewers from SQL DB or YAML (excluding $TARGET_AGENT)
+# 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" python3 -c "
+  TARGET_AGENT="$TARGET_AGENT" MAM_STATE_JSON="$(load_state_json)" python3 -c "
-import sqlite3, os, yaml, json
+import os, json
-yaml_path = '.mam/agent-sessions.yaml'
+d = json.loads(os.environ.get('MAM_STATE_JSON', '{}'))
-db_path = '.mam/agent-sessions.db'
 target_agent = os.environ.get('TARGET_AGENT')
-reviewers = []
+reviewers = [s.get('name') for s in d.get('tmux_sessions', [])
-if os.path.exists(db_path):
+             if s.get('role') == 'reviewer' and s.get('name') != target_agent]
-    try:
-        conn = sqlite3.connect(db_path)
-        cursor = conn.execute('SELECT data FROM sessions')
-        for r in cursor.fetchall():
-            s = json.loads(r[0])
-            if s.get('role') == 'reviewer' and s.get('name') != target_agent:
-                reviewers.append(s.get('name'))
-        conn.close()
-    except Exception:
-        pass
-if not reviewers and os.path.exists(yaml_path):
-    try:
-        with open(yaml_path) as f:
-            d = yaml.safe_load(f) or {}
-            for s in d.get('tmux_sessions', []):
-                if s.get('role') == 'reviewer' and s.get('name') != target_agent:
-                    reviewers.append(s.get('name'))
-    except Exception:
-        pass
 print(','.join(reviewers))
 "
 }
 
-# Resolve target agent type (claude, cline, agy)
+# Resolve target agent type (claude, cline, agy) via load_state_json.
 resolve_agent_type() {
   local name="$1"
-  NAME="$name" python3 -c "
+  NAME="$name" MAM_STATE_JSON="$(load_state_json)" python3 -c "
-import sqlite3, os, yaml, json
+import os, json
-yaml_path = '.mam/agent-sessions.yaml'
-db_path = '.mam/agent-sessions.db'
 name = os.environ.get('NAME')
+d = json.loads(os.environ.get('MAM_STATE_JSON', '{}'))
 agent = None
-if os.path.exists(db_path):
+for s in d.get('tmux_sessions', []):
-    try:
+    if s.get('name') == name:
-        conn = sqlite3.connect(db_path)
+        agent = s.get('agent') or s.get('pane', {}).get('cmd')
-        row = conn.execute('SELECT data FROM sessions WHERE name=?', (name,)).fetchone()
+        break
-        if row:
-            agent = json.loads(row[0]).get('agent')
-        conn.close()
-    except Exception:
-        pass
-if not agent and os.path.exists(yaml_path):
-    try:
-        with open(yaml_path) as f:
-            d = yaml.safe_load(f) or {}
-            for s in d.get('tmux_sessions', []):
-                if s.get('name') == name:
-                    agent = s.get('agent') or s.get('pane', {}).get('cmd')
-                    break
-    except Exception:
-        pass
 if not agent:
-    agent = 'agy' if 'agy' in name else 'cline' if 'cline' in name else 'hermes' if 'hermes' in name else 'claude'
+    # 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
+# Resolve planner session dynamically via load_state_json.
 resolve_planner_session() {
-  python3 -c "
+  MAM_STATE_JSON="$(load_state_json)" python3 -c "
-import sqlite3, os, yaml, json
+import os, json
-yaml_path = '.mam/agent-sessions.yaml'
+d = json.loads(os.environ.get('MAM_STATE_JSON', '{}'))
-db_path = '.mam/agent-sessions.db'
 planner = 'canary-projects-multi-agent-mux-planner-claude'
-if os.path.exists(db_path):
+for s in d.get('tmux_sessions', []):
-    try:
+    if s.get('role') == 'planner':
-        conn = sqlite3.connect(db_path)
+        planner = s.get('name')
-        row = conn.execute('SELECT name FROM sessions WHERE role=\"planner\" LIMIT 1').fetchone()
+        break
-        if row:
-            planner = row[0]
-        conn.close()
-        print(planner)
-        raise SystemExit(0)
-    except Exception:
-        pass
-if os.path.exists(yaml_path):
-    try:
-        with open(yaml_path) as f:
-            d = yaml.safe_load(f) or {}
-            for s in d.get('tmux_sessions', []):
-                if s.get('role') == 'planner':
-                    print(s.get('name'))
-                    raise SystemExit(0)
-    except Exception:
-        pass
 print(planner)
 "
 }
@@ -350,6 +318,11 @@ fi
 # PHASE 2: IMPLEMENTATION (CREATION)
 # ===========================================================================
 log_info "=== Phase 2: Code Implementation ==="
+
+# Fix the pre-implementation commit as the diff baseline so review diffs stay
+# cumulative and non-empty even after the Creator commits per DoD (P0-1).
+BASE_COMMIT=$(git rev-parse HEAD 2>/dev/null || echo "")
+
 EXECUTION_PROMPT="다음 작업 목표를 완성해주세요: $TASK"
 if [ "$PLAN_MODE" = true ]; then
   EXECUTION_PROMPT="최종 합의된 다음 계획서에 입각하여 코드를 수정 및 구현해주세요. 계획서:\n$CURRENT_PLAN"
@@ -432,14 +405,20 @@ while [ "$loop_count" -le "$MAX_LOOP" ]; do
     
     for rev in "${REVIEWERS[@]}"; do
       log_info "Requesting code review from Reviewer '$rev'..."
-      # Cumulative working tree diff (M-6)
+      # Cumulative diff since BASE_COMMIT (M-6): includes committed AND
-      CHANGES_DIFF=$(git diff 2>/dev/null || echo "No git diff available")
+      # uncommitted changes, so it stays non-empty even after the Creator
+      # commits per the documented DoD (bare `git diff` alone would not).
+      if [ -n "$BASE_COMMIT" ]; then
+        CHANGES_DIFF=$(git diff "$BASE_COMMIT" 2>/dev/null || echo "No git diff available")
+      else
+        CHANGES_DIFF=$(git diff 2>/dev/null || echo "No git diff available")
+      fi
       
       REV_OUTPUT=$(bash .agents/skills/multi-agent-mux-delegate-job/multi-agent-mux-delegate-job submit \
         --agent-session "tmux:$rev" \
         --agent "$(resolve_agent_type "$rev")" \
         --type "direct" \
-        --prompt "다음 구현 사항(작업 목표: $TASK) 및 누적 변경분(git diff)에 대해 린트, 동작성, 유실 등의 관점에서 교차 코드 리뷰를 수행해주세요. 확인 후 최종 Verdict로 '[VERDICT: PASS]' 혹은 '[VERDICT: NOT PASS]' 태그를 리뷰 리포트 마지막에 단독 행으로 명시적으로 작성해주세요. 변경분:\n$CHANGES_DIFF")
+        --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 "$REV_JOB_ID" ]; then
@@ -494,9 +473,11 @@ while [ "$loop_count" -le "$MAX_LOOP" ]; do
         exit 1
       fi
       
-      # Re-planning check for complex refactoring feedback
+      # Re-planning check: rely on the explicit '[ESCALATE: PLANNER]' tag a
+      # reviewer is instructed to emit, rather than sniffing English keywords
+      # (reviewers report in Korean, so keyword matching never fired) (P1-1).
       COMPLEX_FIX=false
-      if echo "$FEEDBACK_AGGREGATE" | grep -Eiq "refactor|complex|design|architect"; then
+      if echo "$FEEDBACK_AGGREGATE" | grep -qE '^\[ESCALATE: PLANNER\][[:space:]]*\r?$'; then
         COMPLEX_FIX=true
       fi