agentic-loop-upgrade

Files (123)

• INSTRUCTIONS.md
• README.md
• SECURITY.md
• SKILL.md
• _meta.json
• confidence-gates.md · references/
• context-management.md · references/
• error-recovery.md · references/
• parallel-execution.md · references/
• planning-reflection.md · references/
• state-machine.md · references/
• task-hierarchy.md · references/
• analyze-task-graph.py · scripts/
• validate-plan.py · scripts/
• verify.sh · scripts/
• skill.json
• agent-paths.ts · src/
• manager.ts · src/context/
• summarizer.ts · src/context/
• agent-paths.d.ts · src/dist/
• agent-paths.d.ts.map · src/dist/
• agent-paths.js · src/dist/
• agent-paths.js.map · src/dist/
• clawdbot-hook.d.ts.map · src/dist/
• clawdbot-hook.js · src/dist/
• clawdbot-hook.js.map · src/dist/
• manager.d.ts · src/dist/context/
• manager.d.ts.map · src/dist/context/
• manager.js · src/dist/context/
• manager.js.map · src/dist/context/
• summarizer.d.ts · src/dist/context/
• summarizer.d.ts.map · src/dist/context/
• summarizer.js · src/dist/context/
• summarizer.js.map · src/dist/context/
• enhanced-loop.d.ts · src/dist/
• enhanced-loop.d.ts.map · src/dist/
• enhanced-loop.js · src/dist/
• enhanced-loop.js.map · src/dist/
• approval-gate.d.ts · src/dist/execution/
• approval-gate.d.ts.map · src/dist/execution/
• approval-gate.js · src/dist/execution/
• approval-gate.js.map · src/dist/execution/
• confidence-gate.d.ts · src/dist/execution/
• confidence-gate.d.ts.map · src/dist/execution/
• confidence-gate.js · src/dist/execution/
• confidence-gate.js.map · src/dist/execution/
• error-recovery.d.ts · src/dist/execution/
• error-recovery.d.ts.map · src/dist/execution/
• error-recovery.js · src/dist/execution/
• error-recovery.js.map · src/dist/execution/
• parallel.d.ts · src/dist/execution/
• parallel.d.ts.map · src/dist/execution/
• parallel.js · src/dist/execution/
• parallel.js.map · src/dist/execution/
• retry-engine.d.ts · src/dist/execution/
• retry-engine.d.ts.map · src/dist/execution/
• retry-engine.js · src/dist/execution/
• retry-engine.js.map · src/dist/execution/
• index.d.ts · src/dist/
• index.d.ts.map · src/dist/
• …and 63 more

SKILL.md (first lines)

# Enhanced Agentic Loop Skill

A comprehensive upgrade to OpenClaw's agentic capabilities with persistent state, automatic planning, approval gates, retry logic, context management, checkpointing, knowledge graph auto-injection, and channel-aware plan rendering.

> 📋 **Security review?** See [SECURITY.md](./SECURITY.md) for a complete trust and capability audit document including network activity, file write scope, credential handling, and rollback instructions.

## Security & Trust Summary

| Property | Value |
|---|---|
| Outbound network | LLM provider only (inherited from host) |
| Telemetry / phone-home | ❌ None |
| System prompt modification | ✅ Additive-only (appends plan status; never replaces core prompt) |
| Runner wrapping | ✅ Transparent (original runner always called; interceptions logged) |
| Credential storage | ❌ None (inherits host agent auth, stores nothing new) |
| Persistence | Local `~/.openclaw/` only |
| Enabled by default | ❌ No — explicit opt-in required |
| Approval gates default | ✅ On for high/critical risk operations |

## Status: ✅ Active (v2.3.0)

All components are integrated and working.

| Component | Status |
|-----------|--------|
| Mode Dashboard UI | ✅ Working |
| Configuration System | ✅ Working |
| Hook/Wrapper Integration | ✅ Working |
| State Machine | ✅ Working |
| Planning Layer | ✅ Working |
| Parallel Execution | ✅ Working |
| Confidence Gates | ✅ Working |
| Error Recovery | ✅ Working |
| Checkpointing | ✅ Working |
| Memory Auto-Inject | ✅ Working (v2) |
| Discord Plan Rendering | ✅ Working (v2) |

## Features

### 1. Persistent Plan State
Plans survive across conversation turns. The agent knows where it left off.

```typescript
import { getStateManager } from "@openclaw/enhanced-loop";

const state = getStateManager();
await state.init(sessionId);

// Plan persists in ~/.openclaw/agent-state/{sessionId}.json
state.setPlan(plan);
state.completeStep("step_1", "Files created");
const progress = state.getProgress(); // { completed: 1, total: 5, percent: 20 }
```

### 2. Automatic Step Completion Detection
Analyzes tool results to determine if plan steps are complete.

```typescript
import { createStepTracker } from "@openclaw/enhanced-loop";

const tracker = createStepTracker(stateManager);

// After each tool execution
const analysis = await tracker.analyzeToolResult(tool, result);
if (analysis.isComplete) {
  console.log(`Step done: ${analysis.suggestedResult}`);
}
```

### 3. Tool Approval Gates with Timeout
Risky operations pause for human approval, but auto-proceed after N seconds.

```typescript
import { getApprovalGate } from "@openclaw/enhanced-loop";

const gate = getApprovalGate({
  enabled: true,
  timeoutMs: 15000, // 15 seconds to respond
  requireApprovalFor: ["high", "critical"],
  onApprovalNeeded: (request) => {
    // Notify user: "⚠️ Approve rm -rf? Auto-proceeding in 15s..."
  },
});

// Before risky tool execution
if (gate.requiresApproval(tool)) {
  const result = await gate.requestApproval(tool);
  if (!result.proceed) {
    return { blocked: true, reason: result.request.riskReason };
  }
}

// User can respond with:
gate.approve(requestId);  // Allow it
gate.deny(requestId);     // Block it
// Or wait for timeout → auto-proceeds
```

**Risk Levels:**
- `low`: Read operations (auto-approved)
- `medium`: Write/Edit, safe exec
- `high`: Messages, browser actions, git push
- `critical`: rm -rf, database drops, format commands

### 4. Automatic Retry with Alternatives
Failed tools get diagnosed and retried with modified approaches.

```typescript
import { createRetryEngine } from "@openclaw/enhanced-loop";

const retry = createRetryEngine({
  enabled: true,
  maxAttempts: 3,
  retryDelayMs: 1000,
});

const result = await retry.executeWithRetry(tool, executor);
// Automatically:
// - Diagnoses errors (permission, network, not_found, etc.)

From LeoYeAI/openclaw-master-skills, MIT.

More from LeoYeAI/openclaw-master-skills