loki-mode 5.48.2 → 5.49.1

package/README.md

@@ -1,6 +1,6 @@
 # Loki Mode
 
-**The Flagship Product of [Autonomi](https://www.autonomi.dev/) -- The First Truly Autonomous Multi-Agent Startup System**
+**The Flagship Product of [Autonomi](https://www.autonomi.dev/) -- An Autonomous Multi-Agent Development System**
 
 [![npm version](https://img.shields.io/npm/v/loki-mode)](https://www.npmjs.com/package/loki-mode)
 [![npm downloads](https://img.shields.io/npm/dw/loki-mode)](https://www.npmjs.com/package/loki-mode)
@@ -9,17 +9,15 @@
 [![GitHub Marketplace](https://img.shields.io/badge/Marketplace-Loki%20Mode-purple?logo=github)](https://github.com/marketplace/actions/loki-mode-code-review)
 [![Autonomi](https://img.shields.io/badge/Autonomi-autonomi.dev-5B4EEA)](https://www.autonomi.dev/)
 [![Agent Types](https://img.shields.io/badge/Agent%20Types-41-blue)]()
-[![Loki Mode](https://img.shields.io/badge/Loki%20Mode-98.78%25%20Pass%401-blueviolet)](benchmarks/results/)
-[![HumanEval](https://img.shields.io/badge/HumanEval-98.17%25%20Pass%401-brightgreen)](benchmarks/results/)
-[![SWE-bench](https://img.shields.io/badge/SWE--bench-99.67%25%20Patch%20Gen-brightgreen)](benchmarks/results/)
+[![Benchmarks](https://img.shields.io/badge/Benchmarks-Infrastructure%20Ready-blue)](benchmarks/)
 
-**Current Version: v5.47.0**
+**Current Version: v5.49.0**
 
 **[Autonomi](https://www.autonomi.dev/)** | **[Documentation](https://www.autonomi.dev/docs)** | **[GitHub](https://github.com/asklokesh/loki-mode)**
 
-> **PRD → Deployed Product in Zero Human Intervention**
+> **PRD to Deployed Product with Minimal Human Intervention**
 >
-> Loki Mode transforms a Product Requirements Document into a fully built, tested, deployed, and revenue-generating product while you sleep. No manual steps. No intervention. Just results.
+> Loki Mode transforms a Product Requirements Document into a fully built, tested, and deployed product with autonomous multi-agent execution. Human oversight for deployment credentials, domain setup, and critical decisions.
 
 ---
 
@@ -79,7 +77,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: asklokesh/loki-mode@v5.38
+      - uses: asklokesh/loki-mode@v5
         with:
           github_token: ${{ secrets.GITHUB_TOKEN }}
           mode: review          # review, fix, or test
@@ -163,40 +161,27 @@ See [skills/providers.md](skills/providers.md) for full provider documentation.
 
 ---
 
-## Benchmark Results
+## Benchmarks
 
-### Three-Way Comparison (HumanEval)
+Benchmark infrastructure is included for HumanEval and SWE-bench evaluation. Results are self-reported from the included test harness and have not been independently verified.
 
-| System | Pass@1 | Details |
-|--------|--------|---------|
-| **Loki Mode (Multi-Agent)** | **98.78%** | 162/164 problems, RARV cycle recovered 2 |
-| Direct Claude | 98.17% | 161/164 problems (baseline) |
-| MetaGPT | 85.9-87.7% | Published benchmark |
+| Benchmark | Result | Notes |
+|-----------|--------|-------|
+| HumanEval | 162/164 (98.78%) | Self-reported, max 3 retries per problem |
+| SWE-bench | 299/300 patches generated | Patch generation only -- SWE-bench evaluator not yet run to verify correctness |
 
-**Loki Mode beats MetaGPT by +11-13%** thanks to the RARV (Reason-Act-Reflect-Verify) cycle.
+**Note:** SWE-bench "patch generation" means the system produced a patch file, not that the patch correctly resolves the issue. The SWE-bench evaluator should be run to determine actual resolution rates.
 
-### Full Results
-
-| Benchmark | Score | Details |
-|-----------|-------|---------|
-| **Loki Mode HumanEval** | **98.78% Pass@1** | 162/164 (multi-agent with RARV) |
-| **Direct Claude HumanEval** | **98.17% Pass@1** | 161/164 (single agent baseline) |
-| **Direct Claude SWE-bench** | **99.67% patch gen** | 299/300 problems |
-| **Loki Mode SWE-bench** | **99.67% patch gen** | 299/300 problems |
-| Model | Claude Opus 4.5 | |
-
-**Key Finding:** Multi-agent RARV matches single-agent performance on both benchmarks after timeout optimization. The 4-agent pipeline (Architect->Engineer->QA->Reviewer) achieves the same 99.67% patch generation as direct Claude.
-
-See [benchmarks/results/](benchmarks/results/) for full methodology and solutions.
+See [benchmarks/](benchmarks/) for the test harness and raw results.
 
 ---
 
 ## What is Loki Mode?
 
-Loki Mode is a multi-provider AI skill that orchestrates **41 specialized AI agent types** across **7 swarms** to autonomously build, test, deploy, and scale complete startups. Works with **Claude Code**, **OpenAI Codex CLI**, and **Google Gemini CLI**. It dynamically spawns only the agents you need—**5-10 for simple projects, 100+ for complex startups**—working in parallel with continuous self-verification.
+Loki Mode is a multi-provider AI skill that orchestrates **41 specialized AI agent types** across **8 swarms** to autonomously build, test, and deploy software projects. Works with **Claude Code**, **OpenAI Codex CLI**, and **Google Gemini CLI**. It dynamically spawns agents as needed -- typically **5-10 for simple projects, more for complex ones** -- working in parallel with continuous self-verification.
 
 ```
-PRD → Research → Architecture → Development → Testing → Deployment → Marketing → Revenue
+PRD → Research → Architecture → Development → Testing → Deployment → Marketing
 ```
 
 **Just say "Loki Mode" and point to a PRD. Walk away. Come back to a deployed product.**
@@ -205,11 +190,11 @@ PRD → Research → Architecture → Development → Testing → Deployment →
 
 ## Why Loki Mode?
 
-### **Better Than Anything Out There**
+### **How It Works**
 
 | What Others Do | What Loki Mode Does |
 |----------------|---------------------|
-| **Single agent** writes code linearly | **100+ agents** work in parallel across engineering, ops, business, data, product, and growth |
+| **Single agent** writes code linearly | **Multiple agents** work in parallel across engineering, ops, business, data, product, and growth |
 | **Manual deployment** required | **Autonomous deployment** to AWS, GCP, Azure, Vercel, Railway with blue-green and canary strategies |
 | **No testing** or basic unit tests | **7 automated quality gates**: input/output guardrails, static analysis, blind review, anti-sycophancy, severity blocking, test coverage |
 | **Code only** - you handle the rest | **Full business operations**: marketing, sales, legal, HR, finance, investor relations |
@@ -221,8 +206,8 @@ PRD → Research → Architecture → Development → Testing → Deployment →
 
 ### **Core Advantages**
 
-1. **Truly Autonomous**: RARV (Reason-Act-Reflect-Verify) cycle with self-verification achieves 2-3x quality improvement
-2. **Massively Parallel**: 100+ agents working simultaneously, not sequential single-agent bottlenecks
+1. **Self-Verifying**: RARV (Reason-Act-Reflect-Verify) cycle with continuous self-verification catches errors early
+2. **Parallel Execution**: Multiple agents working simultaneously, not sequential single-agent bottlenecks
 3. **Production-Ready**: Not just code—handles deployment, monitoring, incident response, and business operations
 4. **Self-Improving**: Learns from mistakes, updates continuity logs, prevents repeated errors
 5. **Zero Babysitting**: Auto-resumes on rate limits, recovers from failures, runs until completion
@@ -255,7 +240,7 @@ PRD → Research → Architecture → Development → Testing → Deployment →
 | **GitHub Integration** | Issue import, PR creation, status sync | [GitHub Integration](skills/github-integration.md) |
 | **Distribution** | npm, Homebrew, Docker installation | [Installation Guide](docs/INSTALLATION.md) |
 | **Research Foundation** | OpenAI, DeepMind, Anthropic patterns | [Acknowledgements](docs/ACKNOWLEDGEMENTS.md) |
-| **Benchmarks** | HumanEval 98.78%, SWE-bench 99.67% | [Benchmark Results](benchmarks/results/) |
+| **Benchmarks** | HumanEval and SWE-bench infrastructure included | [Benchmark Harness](benchmarks/) |
 | **Comparisons** | vs Auto-Claude, Cursor | [Auto-Claude](docs/auto-claude-comparison.md), [Cursor](docs/cursor-comparison.md) |
 
 ---
@@ -424,7 +409,7 @@ Loki Mode doesn't just write code—it **thinks, acts, learns, and verifies**:
    └─ Apply learning and RETRY from REASON
 ```
 
-**Result:** 2-3x quality improvement through continuous self-verification.
+**Result:** Improved quality through continuous self-verification and multi-reviewer code review.
 
 ### **Perpetual Improvement Mode**
 
@@ -561,7 +546,7 @@ graph TB
 **Key components:**
 - **RARV+C Cycle** -- Reason, Act, Reflect, Verify, Compound. Every iteration follows this loop. Failed verification triggers retry from Reason.
 - **Provider Layer** -- Claude Code (full parallel agents, Task tool, MCP), Codex CLI and Gemini CLI (sequential, degraded mode).
-- **Agent Swarms** -- 41 specialized agent types across 7 swarms, spawned on demand based on project complexity.
+- **Agent Swarms** -- 41 specialized agent types across 8 swarms, spawned on demand based on project complexity.
 - **Completion Council** -- 3 members vote on whether the project is done. Anti-sycophancy devil's advocate on unanimous votes.
 - **Memory System** -- Episodic traces, semantic patterns, procedural skills. Progressive disclosure reduces context usage by 60-80%.
 - **Dashboard** -- FastAPI server reading `.loki/` flat files, with real-time web UI for task queue, agents, logs, and council state. Now with TLS/HTTPS, OIDC/SSO, and RBAC (v5.36.0-v5.37.0).
@@ -609,7 +594,7 @@ Config search order: `.loki/config.yaml` (project) -> `~/.config/loki-mode/confi
 
 ## Agent Swarms (41 Types)
 
-Loki Mode has **41 predefined agent types** organized into **7 specialized swarms**. The orchestrator spawns only what you need—simple projects use 5-10 agents, complex startups spawn 100+.
+Loki Mode has **41 predefined agent types** organized into **8 specialized swarms**. The orchestrator spawns only what you need -- simple projects typically use 5-10 agents, complex ones may use more.
 
 <img width="5309" height="979" alt="Agent Swarms Visualization" src="https://github.com/user-attachments/assets/7d18635d-a606-401f-8d9f-430e6e4ee689" />
 
@@ -981,7 +966,7 @@ Built for the [Claude Code](https://claude.ai) ecosystem, powered by Anthropic's
 
 Loki Mode is the flagship product of **[Autonomi](https://www.autonomi.dev/)** -- a platform for autonomous AI systems. Like Alphabet is to Google, Autonomi is the parent brand under which Loki Mode and future products operate.
 
-**Why Autonomi?** Loki Mode proved that multi-agent autonomous systems can build real software from a PRD with zero human intervention. Autonomi is the expansion of that vision into a broader platform of autonomous services and products.
+**Why Autonomi?** Loki Mode proved that multi-agent autonomous systems can build real software from a PRD with minimal human intervention. Autonomi is the expansion of that vision into a broader platform of autonomous services and products.
 
 - **[autonomi.dev](https://www.autonomi.dev/)** -- Main website
 - **[Documentation](https://www.autonomi.dev/docs)** -- Full documentation

package/SKILL.md

@@ -1,9 +1,9 @@
 ---
 name: loki-mode
-description: Multi-agent autonomous startup system. Triggers on "Loki Mode". Takes PRD to deployed product with zero human intervention. Requires --dangerously-skip-permissions flag.
+description: Multi-agent autonomous startup system. Triggers on "Loki Mode". Takes PRD to deployed product with minimal human intervention. Requires --dangerously-skip-permissions flag.
 ---
 
-# Loki Mode v5.48.2
+# Loki Mode v5.49.1
 
 **You are an autonomous agent. You make decisions. You do not ask questions. You do not stop.**
 
@@ -263,4 +263,4 @@ The following features are documented in skill modules but not yet fully automat
 | Quality gates 3-reviewer system | Implemented (v5.35.0) | 5 specialist reviewers in `skills/quality-gates.md`; execution in run.sh |
 | Benchmarks (HumanEval, SWE-bench) | Infrastructure only | Runner scripts and datasets exist in `benchmarks/`; no published results |
 
-**v5.48.2 | [Autonomi](https://www.autonomi.dev/) flagship product | ~260 lines core**
+**v5.49.1 | [Autonomi](https://www.autonomi.dev/) flagship product | ~260 lines core**

package/VERSION

@@ -1 +1 @@
-5.48.2
+5.49.1

package/autonomy/CONSTITUTION.md

@@ -142,7 +142,7 @@ GROWTH ──[continuous improvement loop]──> GROWTH
 - `Bash` - Command execution
 - `platform-orchestrator` - Deployment and service management
 
-**The 37 agent types are ROLES defined through prompts, not subagent_types.**
+**The 41 agent types are ROLES defined through prompts, not subagent_types.**
 
 ---
 
@@ -158,7 +158,7 @@ skills/
   quality-gates.md             # 7-gate system, anti-sycophancy
   testing.md                   # Playwright, E2E, property-based
   production.md                # CI/CD, batch processing
-  agents.md                    # 37 agent types, A2A patterns
+  agents.md                    # 41 agent types, A2A patterns
   parallel-workflows.md        # Git worktrees, parallel streams
   troubleshooting.md           # Error recovery, fallbacks
   artifacts.md                 # Code generation patterns

package/autonomy/app-runner.sh

@@ -432,6 +432,10 @@ app_runner_start() {
         (cd "$dir" && bash -c "$_APP_RUNNER_METHOD" >> "$_APP_RUNNER_DIR/app.log" 2>&1) &
     fi
     _APP_RUNNER_PID=$!
+    # Register with central PID registry if available
+    if type register_pid &>/dev/null; then
+        register_pid "$_APP_RUNNER_PID" "app-runner" "method=$_APP_RUNNER_METHOD"
+    fi
 
     # Write PID file
     echo "$_APP_RUNNER_PID" > "$_APP_RUNNER_DIR/app.pid"
@@ -497,6 +501,11 @@ app_runner_stop() {
         kill -KILL "-$_APP_RUNNER_PID" 2>/dev/null || kill -KILL "$_APP_RUNNER_PID" 2>/dev/null || true
     fi
 
+    # Unregister from central PID registry
+    if type unregister_pid &>/dev/null && [ -n "$_APP_RUNNER_PID" ]; then
+        unregister_pid "$_APP_RUNNER_PID"
+    fi
+
     rm -f "$_APP_RUNNER_DIR/app.pid"
     _write_app_state "stopped"
     log_info "App Runner: application stopped"

package/autonomy/completion-council.sh

@@ -45,6 +45,14 @@ COUNCIL_MIN_ITERATIONS=${LOKI_COUNCIL_MIN_ITERATIONS:-3}
 COUNCIL_CONVERGENCE_WINDOW=${LOKI_COUNCIL_CONVERGENCE_WINDOW:-3}
 COUNCIL_STAGNATION_LIMIT=${LOKI_COUNCIL_STAGNATION_LIMIT:-5}
 
+# Error budget: severity-aware completion (v5.49.0)
+# SEVERITY_THRESHOLD: minimum severity that blocks completion (critical, high, medium, low)
+#   "critical" = only critical issues block (most permissive)
+#   "low" = all issues block (strictest, default for backwards compat)
+# ERROR_BUDGET: fraction of non-blocking issues allowed (0.0 = none, 0.1 = 10% tolerance)
+COUNCIL_SEVERITY_THRESHOLD=${LOKI_COUNCIL_SEVERITY_THRESHOLD:-low}
+COUNCIL_ERROR_BUDGET=${LOKI_COUNCIL_ERROR_BUDGET:-0.0}
+
 # Internal state
 COUNCIL_STATE_DIR=""
 COUNCIL_PRD_PATH=""
@@ -235,6 +243,38 @@ council_vote() {
         local vote_result
         vote_result=$(echo "$verdict" | grep -oE "VOTE:\s*(APPROVE|REJECT)" | grep -oE "APPROVE|REJECT" | head -1)
 
+        # Extract severity-categorized issues (v5.49.0 error budget)
+        local member_issues=""
+        member_issues=$(echo "$verdict" | grep -oE "ISSUES:\s*(CRITICAL|HIGH|MEDIUM|LOW):.*" || true)
+
+        # If error budget is active and member rejected, check if rejection
+        # is based only on issues below the severity threshold
+        if [ "$vote_result" = "REJECT" ] && [ "$COUNCIL_SEVERITY_THRESHOLD" != "low" ] && [ -n "$member_issues" ]; then
+            local has_blocking_issue=false
+            local severity_order="critical high medium low"
+            local threshold_reached=false
+
+            while IFS= read -r issue_line; do
+                local issue_severity
+                issue_severity=$(echo "$issue_line" | grep -oE "(CRITICAL|HIGH|MEDIUM|LOW)" | head -1 | tr '[:upper:]' '[:lower:]')
+                # Check if this severity meets or exceeds the threshold
+                for sev in $severity_order; do
+                    if [ "$sev" = "$COUNCIL_SEVERITY_THRESHOLD" ]; then
+                        threshold_reached=true
+                    fi
+                    if [ "$sev" = "$issue_severity" ] && [ "$threshold_reached" = "false" ]; then
+                        has_blocking_issue=true
+                        break
+                    fi
+                done
+            done <<< "$member_issues"
+
+            if [ "$has_blocking_issue" = "false" ]; then
+                log_info "  Member $member ($role): REJECT overridden to APPROVE (issues below ${COUNCIL_SEVERITY_THRESHOLD} threshold)"
+                vote_result="APPROVE"
+            fi
+        fi
+
         if [ "$vote_result" = "APPROVE" ]; then
             ((approve_count++))
             log_info "  Member $member ($role): APPROVE"
@@ -618,23 +658,37 @@ council_member_review() {
             ;;
     esac
 
+    local severity_instruction=""
+    if [ "$COUNCIL_SEVERITY_THRESHOLD" != "low" ]; then
+        severity_instruction="
+ERROR BUDGET: This council uses severity-aware evaluation.
+- Categorize each issue as CRITICAL, HIGH, MEDIUM, or LOW severity
+- Blocking threshold: ${COUNCIL_SEVERITY_THRESHOLD} and above
+- Only issues at ${COUNCIL_SEVERITY_THRESHOLD} severity or above should cause REJECT
+- Issues below threshold are acceptable (error budget: ${COUNCIL_ERROR_BUDGET})
+- List issues as ISSUES: SEVERITY:description (one per line)"
+    fi
+
     local prompt="You are a council member reviewing project completion.
 
 ${role_instruction}
 
 EVIDENCE:
 ${evidence}
+${severity_instruction}
 
 INSTRUCTIONS:
 1. Review the evidence carefully
 2. Determine if the project meets completion criteria
 3. Output EXACTLY one line starting with VOTE:APPROVE or VOTE:REJECT
 4. Output EXACTLY one line starting with REASON: explaining your decision
-5. Be honest - do not approve incomplete work
+5. If issues found, output lines starting with ISSUES: SEVERITY:description
+6. Be honest - do not approve incomplete work
 
-Output format (exactly two lines):
+Output format:
 VOTE:APPROVE or VOTE:REJECT
-REASON: your reasoning here"
+REASON: your reasoning here
+ISSUES: CRITICAL:description (optional, one per line per issue)"
 
     local verdict_file="$vote_dir/member-${member_id}.txt"
 
@@ -1300,5 +1354,5 @@ council_get_dashboard_state() {
         state_json=$(cat "$COUNCIL_STATE_DIR/state.json" 2>/dev/null || echo "{}")
     fi
 
-    echo "\"council\": {\"enabled\": true, \"size\": $COUNCIL_SIZE, \"threshold\": $COUNCIL_THRESHOLD, \"check_interval\": $COUNCIL_CHECK_INTERVAL, \"consecutive_no_change\": $COUNCIL_CONSECUTIVE_NO_CHANGE, \"done_signals\": $COUNCIL_DONE_SIGNALS, \"iteration\": $ITERATION_COUNT, \"state\": $state_json}"
+    echo "\"council\": {\"enabled\": true, \"size\": $COUNCIL_SIZE, \"threshold\": $COUNCIL_THRESHOLD, \"check_interval\": $COUNCIL_CHECK_INTERVAL, \"consecutive_no_change\": $COUNCIL_CONSECUTIVE_NO_CHANGE, \"done_signals\": $COUNCIL_DONE_SIGNALS, \"iteration\": $ITERATION_COUNT, \"severity_threshold\": \"$COUNCIL_SEVERITY_THRESHOLD\", \"error_budget\": $COUNCIL_ERROR_BUDGET, \"state\": $state_json}"
 }

package/autonomy/hooks/validate-bash.sh

@@ -30,11 +30,21 @@ BLOCKED_PATTERNS=(
     "wget.*\|.*sh"
     "curl.*\|.*bash"
     "wget.*\|.*bash"
+    # Config self-protection: prevent agents from corrupting internal state
+    "rm -rf \.loki"
+    "rm -rf \./\.loki"
+    "rm .*\.loki/council/"
+    "rm .*\.loki/config\.yaml"
+    "rm .*\.loki/logs/bash-audit"
+    "rm .*\.loki/session\.lock"
+    "> \.loki/council/"
+    "> \.loki/config\.yaml"
 )
 
-# Safe path patterns that override rm -rf / matches
+# Safe path patterns that override blocked pattern matches
 SAFE_PATTERNS=(
     "rm -rf /tmp/"
+    "rm -rf \.loki/queue/dead-letter"
 )
 
 # Check for blocked patterns

package/autonomy/loki

@@ -9,6 +9,7 @@
 # Usage:
 #   loki start [PRD]      - Start Loki Mode (optionally with PRD)
 #   loki stop             - Stop execution immediately
+#   loki cleanup          - Kill orphaned processes from crashed sessions
 #   loki pause            - Pause after current session
 #   loki resume           - Resume paused execution
 #   loki status           - Show current status
@@ -312,6 +313,7 @@ show_help() {
     echo "  init             Build a PRD interactively or from templates"
     echo "  issue <url|num>  Generate PRD from GitHub issue and optionally start"
     echo "  stop             Stop execution immediately"
+    echo "  cleanup          Kill orphaned processes from crashed sessions"
     echo "  pause            Pause after current session"
     echo "  resume           Resume paused execution"
     echo "  status [--json]  Show current status (--json for machine-readable)"
@@ -704,6 +706,28 @@ except: pass
             rm -f "$LOKI_DIR/dashboard/dashboard.pid"
         fi
 
+        # Kill any remaining registered processes (2s graceful window matches run.sh)
+        if [ -d "$LOKI_DIR/pids" ]; then
+            for entry_file in "$LOKI_DIR/pids"/*.json; do
+                [ -f "$entry_file" ] || continue
+                local reg_pid
+                reg_pid=$(basename "$entry_file" .json)
+                case "$reg_pid" in ''|*[!0-9]*) continue ;; esac
+                if kill -0 "$reg_pid" 2>/dev/null; then
+                    kill "$reg_pid" 2>/dev/null || true
+                    local w=0
+                    while [ $w -lt 4 ] && kill -0 "$reg_pid" 2>/dev/null; do
+                        sleep 0.5
+                        w=$((w + 1))
+                    done
+                    if kill -0 "$reg_pid" 2>/dev/null; then
+                        kill -9 "$reg_pid" 2>/dev/null || true
+                    fi
+                fi
+                rm -f "$entry_file"
+            done
+        fi
+
         # Emit session stop event
         emit_event session cli stop "reason=user_requested"
         # Emit success pattern for clean stop (SYN-018)
@@ -730,6 +754,86 @@ except: pass
     fi
 }
 
+# Kill orphaned processes from crashed sessions
+cmd_cleanup() {
+    local pids_dir="$LOKI_DIR/pids"
+    local killed=0
+    local stale=0
+
+    if [ ! -d "$pids_dir" ]; then
+        echo "No PID registry found. Nothing to clean up."
+        exit 0
+    fi
+
+    echo -e "${BOLD}Scanning for orphaned processes...${NC}"
+
+    for entry_file in "$pids_dir"/*.json; do
+        [ -f "$entry_file" ] || continue
+        local pid
+        pid=$(basename "$entry_file" .json)
+        case "$pid" in
+            ''|*[!0-9]*) continue ;;
+        esac
+
+        local label=""
+        local ppid_val=""
+        # Parse JSON fields (python3 with shell fallback)
+        if command -v python3 >/dev/null 2>&1; then
+            label=$(python3 -c "import json,sys; print(json.load(open(sys.argv[1])).get('label','unknown'))" "$entry_file" 2>/dev/null) || label="unknown"
+            ppid_val=$(python3 -c "import json,sys; print(json.load(open(sys.argv[1])).get('ppid',''))" "$entry_file" 2>/dev/null) || true
+        else
+            label=$(sed 's/.*"label":"//' "$entry_file" 2>/dev/null | sed 's/".*//' | head -1) || label="unknown"
+            ppid_val=$(sed 's/.*"ppid"://' "$entry_file" 2>/dev/null | sed 's/[,}].*//' | head -1) || true
+        fi
+
+        if kill -0 "$pid" 2>/dev/null; then
+            # Process is alive - check if parent is dead (orphan)
+            local is_orphan=false
+            # Validate ppid_val is numeric before using with kill
+            case "$ppid_val" in ''|*[!0-9]*) ppid_val="" ;; esac
+            if [ -n "$ppid_val" ] && ! kill -0 "$ppid_val" 2>/dev/null; then
+                is_orphan=true
+            fi
+
+            if [ "$is_orphan" = true ] || [ "${1:-}" = "--force" ]; then
+                echo -e "  ${RED}Killing${NC} PID=$pid label=$label (parent $ppid_val dead)"
+                kill "$pid" 2>/dev/null || true
+                sleep 0.5
+                if kill -0 "$pid" 2>/dev/null; then
+                    kill -9 "$pid" 2>/dev/null || true
+                fi
+                rm -f "$entry_file"
+                killed=$((killed + 1))
+            else
+                echo -e "  ${GREEN}Alive${NC}  PID=$pid label=$label (parent $ppid_val alive)"
+            fi
+        else
+            # Process is dead - clean up stale entry
+            rm -f "$entry_file"
+            stale=$((stale + 1))
+        fi
+    done
+
+    echo ""
+    echo "Results: $killed orphan(s) killed, $stale stale entries cleaned"
+
+    # Also kill orphaned loki-run temp scripts
+    local temp_killed=0
+    if pgrep -f "loki-run-" >/dev/null 2>&1; then
+        if ! is_session_running; then
+            echo "Killing orphaned loki-run temp scripts..."
+            pkill -f "loki-run-" 2>/dev/null || true
+            sleep 0.5
+            pkill -9 -f "loki-run-" 2>/dev/null || true
+            temp_killed=1
+        fi
+    fi
+
+    if [ $killed -eq 0 ] && [ $stale -eq 0 ] && [ $temp_killed -eq 0 ]; then
+        echo -e "${GREEN}System is clean. No orphans found.${NC}"
+    fi
+}
+
 # Pause after current session
 cmd_pause() {
     if [ ! -d "$LOKI_DIR" ]; then
@@ -4497,6 +4601,9 @@ main() {
         stop)
             cmd_stop
             ;;
+        cleanup)
+            cmd_cleanup "$@"
+            ;;
         pause)
             cmd_pause
             ;;