claude-flow-novice 2.14.28 → 2.14.30

package/.claude/skills/cfn-loop-orchestration/orchestrate.sh

@@ -21,6 +21,10 @@
 
 set -euo pipefail
 
+# Determine PROJECT_ROOT first before any other operations
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PROJECT_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
+
 # ⚠️ ANTI-023 MEMORY LEAK PROTECTION: Block Task Mode agents
 # Task Mode agents spawn via Task() tool and should NOT use orchestration scripts
 if [[ -z "${TASK_ID:-}" || -z "${LOOP3_AGENTS:-}" ]]; then
@@ -31,14 +35,39 @@ if [[ -z "${TASK_ID:-}" || -z "${LOOP3_AGENTS:-}" ]]; then
     exit 1
 fi
 
+# ⚠️ ANTI-023 MEMORY LEAK PROTECTION: Environment Sanitization
+# Load and apply environment sanitization to prevent memory leaks
+if [[ -f "$PROJECT_ROOT/.claude/skills/cfn-task-mode-sanitize/task-mode-env-sanitizer.sh" ]]; then
+    source "$PROJECT_ROOT/.claude/skills/cfn-task-mode-sanitize/task-mode-env-sanitizer.sh"
+    sanitize_task_mode_environment "cli"
+    echo "✅ Environment sanitization applied" >&2
+else
+    echo "⚠️ Environment sanitization not available - proceeding without protection" >&2
+fi
+
+# ⚠️ ANTI-023 MEMORY LEAK PROTECTION: Process Instrumentation
+# Load process instrumentation and monitoring for the orchestrator
+if [[ -f "$PROJECT_ROOT/.claude/skills/cfn-validation-runner-instrumentation/wrapped-executor.sh" ]]; then
+    source "$PROJECT_ROOT/.claude/skills/cfn-validation-runner-instrumentation/wrapped-executor.sh"
+    echo "✅ Orchestrator process instrumentation enabled" >&2
+else
+    echo "⚠️ Process instrumentation not available - proceeding without monitoring" >&2
+fi
+
+# ⚠️ ANTI-023 MEMORY LEAK PROTECTION: Environment Configuration
+# Set stabilization environment variables with sensible defaults
+export CFN_VALIDATION_TIMEOUT="${CFN_VALIDATION_TIMEOUT:-300}"   # 5 minutes
+export CFN_MEMORY_LIMIT="${CFN_MEMORY_LIMIT:-2048}"              # 2GB memory limit
+export CFN_CPU_LIMIT="${CFN_CPU_LIMIT:-80}"                      # 80% CPU limit
+export CFN_TELEMETRY_DIR="${CFN_TELEMETRY_DIR:-$PROJECT_ROOT/.artifacts/telemetry}"
+mkdir -p "$CFN_TELEMETRY_DIR"
+
 # Load security utilities
 # shellcheck source=./security_utils.sh
 source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/security_utils.sh"
 
-# Determine script directory
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 HELPERS_DIR="$SCRIPT_DIR/helpers"
-PROJECT_ROOT="$(cd "$SCRIPT_DIR/../../.." && pwd)" && REDIS_COORD_SKILL="$PROJECT_ROOT/.claude/skills/cfn-redis-coordination"
+REDIS_COORD_SKILL="$PROJECT_ROOT/.claude/skills/cfn-redis-coordination"
 
 # Configuration
 TASK_ID=""
@@ -250,6 +279,16 @@ if [ -z "$TASK_ID" ] || [ -z "$LOOP3_AGENTS" ] || [ -z "$LOOP2_AGENTS" ] || [ -z
   exit 1
 fi
 
+# ⚠️ ANTI-023 MEMORY LEAK PROTECTION: Process Instrumentation
+# Load process instrumentation and monitoring for the orchestrator
+# shellcheck source=../cfn-process-instrumentation/instrument-process.sh
+if [[ -f "$PROJECT_ROOT/.claude/skills/cfn-process-instrumentation/instrument-process.sh" ]]; then
+    source "$PROJECT_ROOT/.claude/skills/cfn-process-instrumentation/instrument-process.sh"
+    echo "✅ Orchestrator process instrumentation enabled" >&2
+else
+    echo "⚠️ Process instrumentation not available - proceeding without monitoring" >&2
+fi
+
 # Get thresholds for mode
 # Add additional mode validation with safe fallback
 case "$MODE" in
@@ -435,12 +474,22 @@ function spawn_loop3_agents() {
     safe_task_id=$(sanitize_input "$task_id") || continue
     safe_agent_id=$(sanitize_input "$UNIQUE_AGENT_ID") || continue
 
-    # Spawn agent in background with explicit agent ID
-    npx claude-flow-novice agent "$safe_agent_type" \
-      --task-id "$safe_task_id" \
-      --agent-id "$safe_agent_id" \
-      --iteration "$iteration" \
-      --context "$(build_agent_context "$safe_task_id" "$iteration" "$safe_agent_type" "" "loop3")" &
+    # Spawn agent in background with process instrumentation and memory limits
+    if command -v execute_instrumented >/dev/null 2>&1; then
+        execute_instrumented "npx" "$CFN_VALIDATION_TIMEOUT" "$CFN_MEMORY_LIMIT" \
+          claude-flow-novice agent "$safe_agent_type" \
+          --task-id "$safe_task_id" \
+          --agent-id "$safe_agent_id" \
+          --iteration "$iteration" \
+          --context "$(build_agent_context "$safe_task_id" "$iteration" "$safe_agent_type" "" "loop3")" &
+    else
+        # Fallback to raw spawn if instrumentation unavailable
+        npx claude-flow-novice agent "$safe_agent_type" \
+          --task-id "$safe_task_id" \
+          --agent-id "$safe_agent_id" \
+          --iteration "$iteration" \
+          --context "$(build_agent_context "$safe_task_id" "$iteration" "$safe_agent_type" "" "loop3")" &
+    fi
 
     # Store PID for monitoring using unique agent ID
     AGENT_PID=$!
@@ -450,6 +499,17 @@ function spawn_loop3_agents() {
       --value "{\"pid\": $AGENT_PID}" \
       --namespace "swarm" >/dev/null
 
+    # ⚠️ ANTI-023 MEMORY LEAK PROTECTION: Start telemetry monitoring
+    if [[ -f "$PROJECT_ROOT/.claude/skills/cfn-telemetry/collect-metrics.sh" ]]; then
+        MONITOR_PID=$("$PROJECT_ROOT/.claude/skills/cfn-telemetry/collect-metrics.sh" start-monitoring "$UNIQUE_AGENT_ID" "$AGENT_PID" "$iteration" "$safe_agent_type")
+        "$REDIS_COORD_SKILL/store-context.sh" \
+          --task-id "$task_id" \
+          --key "${UNIQUE_AGENT_ID}:monitor_pid" \
+          --value "{\"pid\": $MONITOR_PID}" \
+          --namespace "swarm" >/dev/null
+        echo "🔍 Started monitoring for $UNIQUE_AGENT_ID (Agent PID: $AGENT_PID, Monitor PID: $MONITOR_PID)" >&2
+    fi
+
     # Store agent ID mapping for later retrieval using Redis SADD for set storage
     redis-cli SADD "swarm:${task_id}:loop3:agent_ids:iteration${iteration}" "$UNIQUE_AGENT_ID" >/dev/null
   done
@@ -524,6 +584,16 @@ function wait_for_agents() {
     wait "$pid" 2>/dev/null || true
   done
 
+  # ⚠️ ANTI-023 MEMORY LEAK PROTECTION: Stop monitoring for all agents
+  echo "  Stopping telemetry monitoring for Loop 3 agents..." >&2
+  for unique_agent_id in "${AGENT_IDS[@]}"; do
+    local monitor_pid=$("$REDIS_COORD_SKILL/get-context.sh" --task-id "$task_id" --key "${unique_agent_id}:monitor_pid" --namespace "swarm" 2>/dev/null | jq -r '.pid // 0' || echo "0")
+    if [[ "$monitor_pid" -gt 0 ]] && kill -0 "$monitor_pid" 2>/dev/null; then
+      "$PROJECT_ROOT/.claude/skills/cfn-telemetry/collect-metrics.sh" stop-monitoring "$monitor_pid" >/dev/null 2>&1 || true
+      echo "    Stopped monitoring for $unique_agent_id (Monitor PID: $monitor_pid)" >&2
+    fi
+  done
+
   # Calculate actual elapsed time
   local end_time=$(date +%s)
   local elapsed=$((end_time - start_time))
@@ -668,12 +738,22 @@ function spawn_loop2_agents() {
 
     echo "  Spawning: $agent_type (ID: $UNIQUE_VALIDATOR_ID)"
 
-    # Spawn agent in background with explicit agent ID
-    npx claude-flow-novice agent "$agent_type" \
-      --task-id "$task_id" \
-      --agent-id "$UNIQUE_VALIDATOR_ID" \
-      --iteration "$iteration" \
-      --context "$(build_agent_context "$task_id" "$iteration" "$agent_type" "" "loop2")" &
+    # Spawn validator in background with process instrumentation and memory limits
+    if command -v execute_instrumented >/dev/null 2>&1; then
+        execute_instrumented "npx" "$CFN_VALIDATION_TIMEOUT" "$CFN_MEMORY_LIMIT" \
+          claude-flow-novice agent "$agent_type" \
+          --task-id "$task_id" \
+          --agent-id "$UNIQUE_VALIDATOR_ID" \
+          --iteration "$iteration" \
+          --context "$(build_agent_context "$task_id" "$iteration" "$agent_type" "" "loop2")" &
+    else
+        # Fallback to raw spawn if instrumentation unavailable
+        npx claude-flow-novice agent "$agent_type" \
+          --task-id "$task_id" \
+          --agent-id "$UNIQUE_VALIDATOR_ID" \
+          --iteration "$iteration" \
+          --context "$(build_agent_context "$task_id" "$iteration" "$agent_type" "" "loop2")" &
+    fi
 
     # Store PID for monitoring using unique agent ID
     AGENT_PID=$!

package/.claude/skills/cfn-loop-orchestration/orchestrate.sh.backup

@@ -21,6 +21,16 @@
 
 set -euo pipefail
 
+# ⚠️ ANTI-023 MEMORY LEAK PROTECTION: Block Task Mode agents
+# Task Mode agents spawn via Task() tool and should NOT use orchestration scripts
+if [[ -z "${TASK_ID:-}" || -z "${LOOP3_AGENTS:-}" ]]; then
+    echo "❌ TASK MODE DETECTED - Orchestration forbidden" >&2
+    echo "🚨 ANTI-023: This script is for CLI-spawned coordinators only" >&2
+    echo "💡 Task Mode coordination should be handled directly by Main Chat" >&2
+    echo "🔧 Coordinator spawned via Task() tool - Main Chat should coordinate directly" >&2
+    exit 1
+fi
+
 # Load security utilities
 # shellcheck source=./security_utils.sh
 source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/security_utils.sh"
@@ -317,23 +327,78 @@ function store_context() {
 }
 
 build_agent_context() {
-    local iteration="$1"
-    local agent_type="$2"
-    local feedback="$3"
-    local loop_type="${4:-}"  # NEW: loop3, loop2, or loop4 (optional)
+    local task_id="$1"
+    local iteration="$2"
+    local agent_type="$3"
+    local feedback="$4"
+    local loop_type="${5:-}"  # NEW: loop3, loop2, or loop4 (optional)
 
-    # Extract from SUCCESS_CRITERIA JSON
+    # Initialize context variables
     local task_desc="CFN Loop implementation"
-    local deliverables=$(echo "$SUCCESS_CRITERIA" | jq -r '.deliverables // [] | join(", ")' 2>/dev/null || echo "")
-    local acceptance=$(echo "$SUCCESS_CRITERIA" | jq -r '.acceptanceCriteria // [] | join(", ")' 2>/dev/null || echo "")
+    local deliverables=""
+    local acceptance=""
+    local epic_context=""
+    local phase_context=""
+    local target_files=""
+
+    # Try to retrieve complete context from Redis
+    if command -v "$REDIS_COORD_SKILL/get-context.sh" >/dev/null 2>&1; then
+        if redis_context=$("$REDIS_COORD_SKILL/get-context.sh" --task-id "$task_id" --namespace "swarm" 2>/dev/null); then
+            echo "📥 Retrieved Redis context for task: $task_id" >&2
+
+            # Extract fields from Redis context
+            task_desc=$(echo "$redis_context" | jq -r '.["epic-context"] // .epic_context // "CFN Loop implementation"' 2>/dev/null || echo "CFN Loop implementation")
+            deliverables=$(echo "$redis_context" | jq -r '.deliverables // [] | if type == "array" then join(", ") else . end' 2>/dev/null || echo "")
+            acceptance=$(echo "$redis_context" | jq -r '.acceptanceCriteria // .["acceptance-criteria"] // [] | if type == "array" then join(", ") else . end' 2>/dev/null || echo "")
+            epic_context=$(echo "$redis_context" | jq -r '.["epic-context"] // ""' 2>/dev/null || echo "")
+            phase_context=$(echo "$redis_context" | jq -r '.["phase-context"] // ""' 2>/dev/null || echo "")
+            target_files=$(echo "$redis_context" | jq -r '.["target-files"] // ""' 2>/dev/null || echo "")
+
+            echo "📋 Redis context extracted - Task: $task_desc" >&2
+        else
+            echo "⚠️  Failed to retrieve Redis context, using local SUCCESS_CRITERIA" >&2
+        fi
+    else
+        echo "⚠️  get-context.sh not found, using local SUCCESS_CRITERIA" >&2
+    fi
+
+    # Fallback to local SUCCESS_CRITERIA if Redis retrieval failed or incomplete
+    if [ -z "$deliverables" ] && [ -n "$SUCCESS_CRITERIA" ]; then
+        deliverables=$(echo "$SUCCESS_CRITERIA" | jq -r '.deliverables // [] | join(", ")' 2>/dev/null || echo "")
+        acceptance=$(echo "$SUCCESS_CRITERIA" | jq -r '.acceptanceCriteria // [] | join(", ")' 2>/dev/null || echo "")
+        echo "🔄 Using local SUCCESS_CRITERIA as fallback" >&2
+    fi
+
+    # Build comprehensive context string
+    local context="Task: $task_desc"
+
+    if [ -n "$deliverables" ]; then
+        context="$context | Deliverables: $deliverables"
+    fi
+
+    if [ -n "$acceptance" ]; then
+        context="$context | Acceptance Criteria: $acceptance"
+    fi
+
+    if [ -n "$target_files" ]; then
+        context="$context | Target Files: $target_files"
+    fi
 
-    # Build base context
-    local context="Task: $task_desc | Deliverables: $deliverables | Acceptance: $acceptance | Iteration: $iteration"
+    context="$context | Iteration: $iteration"
 
     if [[ -n "$feedback" ]]; then
         context="$context | Feedback: $feedback"
     fi
 
+    # Add epic/phase context if available
+    if [ -n "$epic_context" ]; then
+        context="$context | Epic: $epic_context"
+    fi
+
+    if [ -n "$phase_context" ]; then
+        context="$context | Phase: $phase_context"
+    fi
+
     # Inject CFN Loop context if injection script exists and loop_type provided
     if [[ -n "$loop_type" ]] && [[ -x "$SCRIPT_DIR/inject-loop-context.sh" ]]; then
         context=$("$SCRIPT_DIR/inject-loop-context.sh" "$loop_type" "$context" 2>/dev/null || echo "$context")
@@ -375,7 +440,7 @@ function spawn_loop3_agents() {
       --task-id "$safe_task_id" \
       --agent-id "$safe_agent_id" \
       --iteration "$iteration" \
-      --context "$(build_agent_context "$iteration" "$safe_agent_type" "" "loop3")" &
+      --context "$(build_agent_context "$safe_task_id" "$iteration" "$safe_agent_type" "" "loop3")" &
 
     # Store PID for monitoring using unique agent ID
     AGENT_PID=$!
@@ -608,7 +673,7 @@ function spawn_loop2_agents() {
       --task-id "$task_id" \
       --agent-id "$UNIQUE_VALIDATOR_ID" \
       --iteration "$iteration" \
-      --context "$(build_agent_context "$iteration" "$agent_type" "" "loop2")" &
+      --context "$(build_agent_context "$task_id" "$iteration" "$agent_type" "" "loop2")" &
 
     # Store PID for monitoring using unique agent ID
     AGENT_PID=$!