Feature Request: Plan Editing & Approval Workflow with Feedback Loop

[mohd-talib0]

Feature Request: Plan Editing & Approval Workflow with Feedback Loop

Summary

Add a plan approval workflow that allows users to review, modify (via feedback), approve, or cancel generated plans before execution begins.

---

Problem

Currently, when a user submits a task:

1. The planner agent generates a plan
2. The plan is immediately executed without user review
3. Users have no control over:
   • Reviewing the plan before execution
   • Requesting modifications to the plan
   • Cancelling execution before it starts
   • Approving individual sensitive steps (web automation, code execution)

This leads to:

• Unexpected agent behavior
• Wasted compute on incorrect plans
• Security concerns for sensitive operations
• Poor user experience when plans need refinement

---

Proposed Solution

User Flow

[User Query] → [Plan Generated] → [USER REVIEW]
                                       ↓
                              ┌────────┼────────┐
                              ↓        ↓        ↓
                         [Approve] [Request   [Cancel]
                            &Run    Changes]     Run
                              ↓        ↓        ↓
                         [Execute] [Feedback] [Stop]
                                       ↓
                                 [Regenerate Plan] → [USER REVIEW] (loop)

Features

1. Plan Approval Gate

   • Display generated plan to user before execution
   • Three options: Approve & Run, Request Changes, Cancel Run

2. Feedback-Based Plan Modification

   • User provides text feedback (e.g., "Include budget considerations")
   • AI regenerates plan incorporating feedback
   • Loop continues until user approves or cancels
   • Maximum retry limit (e.g., 5) to prevent infinite loops

3. Read-Only Plan Display

   • Users cannot manually edit plan text (prevents sync issues)
   • Modifications only through AI-powered feedback loop

4. Optional Step-by-Step Approval

   • Checkbox: "Require approval before each web action"
   • Checkbox: "Require approval before each coding step"
   • For sensitive workflows (logins, form submissions, code execution)

5. Graceful Cancellation

   • Friendly message: "Task cancelled by user. No changes were made."
   • No Python tracebacks shown to users

---

UI Mockup

Plan Approval Card

┌─────────────────────────────────────────────────────────┐
│ Review the generated plan before execution.             │
│                                                         │
│ 📋 Click to view plan                            [→]    │
│                                                         │
│ ☐ Require approval before each web action              │
│ ☐ Require approval before each coding step             │
│                                                         │
│     [Cancel Run]  [Request Changes]  [Approve & Run]   │
└─────────────────────────────────────────────────────────┘

Feedback Input (when "Request Changes" clicked)

┌─────────────────────────────────────────────────────────┐
│ What changes would you like to see in the plan?         │
│ ┌─────────────────────────────────────────────────────┐ │
│ │ E.g., Include a visit to the Louvre, add budget... │ │
│ └─────────────────────────────────────────────────────┘ │
│                                                         │
│                        [Cancel]  [Submit Feedback]      │
└─────────────────────────────────────────────────────────┘

---

Acceptance Criteria

• User can review generated plan before execution
• User can approve plan to start execution
• User can cancel plan to abort without traceback
• User can request changes with text feedback
• AI regenerates plan incorporating user feedback
• Feedback loop limited to prevent infinite iterations
• Plan is read-only (no manual editing)
• Optional checkboxes for step-by-step approval
• Step approval UI for web/coding operations (when enabled)
• Graceful cancellation with user-friendly message

---

Benefits

• User Control: Users decide what gets executed
• Safety: Sensitive operations require explicit approval
• Efficiency: Catch plan errors before wasting compute
• Flexibility: Refine plans through natural language feedback
• Better UX: No technical errors shown to users

---

Labels

enhancement feature-request ux frontend backend