proagents 1.6.17 → 1.6.19

package/README.md

@@ -4,8 +4,9 @@
 
 A portable, universal development workflow framework that works with **any AI platform** (Claude, ChatGPT, Gemini, Cursor, Copilot, etc.) and enables **multi-AI collaboration** on the same project.
 
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![npm version](https://img.shields.io/npm/v/proagents.svg)](https://www.npmjs.com/package/proagents)
+[![npm downloads](https://img.shields.io/npm/dm/proagents.svg)](https://www.npmjs.com/package/proagents)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
 ---
 
@@ -80,36 +81,25 @@ Next: pa:test
 
 ## Features
 
-### Multi-AI Collaboration & Cross-AI Continuity
+### Multi-AI Collaboration
 
 Multiple AIs can work on the same project with full context sharing:
 
 | Feature | Description |
 |---------|-------------|
-| **Auto Context Loading** | AI automatically loads context on first command |
-| **Auto Change Logging** | Every code change logged automatically |
-| **Feature Changelogs** | Per-feature change history |
-| **Module Changelogs** | Per-module change history |
-| **Conflict Detection** | Warns if files modified by other AI |
-| **Activity Log** | Track what each AI does with model name |
-| **Smart Context Summary** | Auto-generated 5-line summary at top of context |
-| **Context Changed Alert** | Warns if another AI worked since your last session |
-| **Test Status Tracking** | Auto-updates test status after every test run |
-| **Feature Progress** | Auto-calculates progress from tasks |
-| **AI Performance Stats** | Tracks sessions, tasks, reverts per AI platform |
-| **Quick Undo (pa:undo-last)** | Revert last AI's entire session changes |
-| **Auto-Archive Old Logs** | Automatically archives logs older than 7 days |
+| **Auto Context Loading** | AI loads project context automatically on first command |
+| **Auto Change Logging** | Every code change logged with AI model name |
+| **Conflict Detection** | Warns if files were modified by another AI |
+| **Feature Changelogs** | Per-feature and per-module change history |
+| **Quick Undo** | `pa:undo-last` reverts last AI's entire session |
+| **Activity Tracking** | Track what each AI does with timestamps |
+| **Handoff Notes** | `pa:handoff` creates notes for next AI session |
+| **Test Status Sync** | Auto-updates test status after every test run |
+| **Progress Tracking** | Auto-calculates feature progress from tasks |
 
 ```bash
-# Just start working - context loads automatically!
 pa:feature "add login"    # AI auto-loads context, then works
-pa:fix "bug in auth"      # AI auto-loads context, then fixes
-
-# No manual pa:sync needed - it's automatic
-# No manual pa:session-end needed - changes logged automatically
-
-# Undo another AI's work if needed
-pa:undo-last              # Revert last AI's entire session
+pa:undo-last              # Revert last AI's changes if needed
 ```
 
 ### AI Learning & Feedback
@@ -174,6 +164,8 @@ Type these in any AI assistant (Claude, ChatGPT, Gemini, Cursor, etc.):
 |---------|-------------|
 | `pa:feature "name"` | Start new feature workflow (all phases) |
 | `pa:fix "description"` | Quick bug fix mode |
+| `pa:project-setup` | Interactive project setup wizard |
+| `pa:rnd` | Research & Development workflow |
 | `pa:status` | Show current progress |
 | `pa:sync` | Load project context (usually auto) |
 | `pa:test` | Run tests |
@@ -183,7 +175,7 @@ Type these in any AI assistant (Claude, ChatGPT, Gemini, Cursor, etc.):
 | `pa:undo-last` | Revert last AI's changes |
 | `pa:handoff` | Create notes for another AI |
 
-**Quick aliases:** `pa:f` (feature), `pa:s` (status), `pa:t` (test), `pa:h` (help)
+**Quick aliases:** `pa:f` (feature), `pa:s` (status), `pa:t` (test), `pa:h` (help), `pa:setup` (project-setup), `pa:research` (rnd)
 
 📖 **Want more?** See [COMMANDS.md](COMMANDS.md) for 100+ AI commands (debugging, testing, refactoring, code generation, sprints...)
 

package/package.json

@@ -1,21 +1,16 @@
 {
   "name": "proagents",
-  "version": "1.6.17",
+  "version": "1.6.19",
   "description": "AI-agnostic development workflow framework that automates the full software development lifecycle",
   "type": "module",
   "main": "lib/index.js",
   "bin": {
-    "proagents": "./bin/proagents.js"
+    "proagents": "bin/proagents.js"
   },
   "scripts": {
     "test": "echo \"No tests yet\" && exit 0",
     "lint": "echo \"No linting configured\" && exit 0"
   },
-  "files": [
-    "bin/",
-    "lib/",
-    ".proagents/"
-  ],
   "keywords": [
     "ai",
     "workflow",

package/.proagents/ai-models/README.md

@@ -1,141 +0,0 @@
-# AI Model Selection & Management
-
-Configure and manage AI models for different tasks.
-
----
-
-## Overview
-
-ProAgents is AI-agnostic and supports multiple AI providers. Configure which models to use for different tasks to optimize cost, speed, and quality.
-
-```
-┌─────────────────────────────────────────────────────────────┐
-│                    AI Model Architecture                     │
-├─────────────────────────────────────────────────────────────┤
-│                                                             │
-│  Task ──► Model Router ──► Selected Model ──► Response     │
-│               │                                             │
-│               ├── Task Type Detection                       │
-│               ├── Cost Optimization                         │
-│               ├── Fallback Handling                         │
-│               └── Rate Limiting                             │
-│                                                             │
-│  Supported Providers:                                       │
-│  ┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐         │
-│  │ Claude  │ │ OpenAI  │ │ Gemini  │ │ Others  │         │
-│  └─────────┘ └─────────┘ └─────────┘ └─────────┘         │
-│                                                             │
-└─────────────────────────────────────────────────────────────┘
-```
-
----
-
-## Quick Start
-
-### Configure Default Model
-
-```yaml
-# proagents.config.yaml
-
-ai:
-  default_provider: "anthropic"
-  default_model: "claude-3-sonnet"
-```
-
-### Use Different Models
-
-```bash
-# Use specific model for a task
-proagents analyze --model claude-3-opus
-
-# Use fast model for quick tasks
-proagents quick "Fix typo" --model claude-3-haiku
-```
-
----
-
-## Supported Providers
-
-| Provider | Models | Best For |
-|----------|--------|----------|
-| **Anthropic** | Claude 3 Opus, Sonnet, Haiku | Code analysis, planning |
-| **OpenAI** | GPT-4, GPT-4 Turbo, GPT-3.5 | General tasks, docs |
-| **Google** | Gemini Pro, Gemini Ultra | Research, analysis |
-| **Cohere** | Command, Command Light | Summarization |
-| **Local** | Ollama, LM Studio | Privacy, offline |
-
----
-
-## Documentation Files
-
-| File | Description |
-|------|-------------|
-| [model-config.md](./model-config.md) | Model configuration |
-| [task-routing.md](./task-routing.md) | Task-based model selection |
-| [cost-management.md](./cost-management.md) | Cost optimization |
-| [fallbacks.md](./fallbacks.md) | Fallback strategies |
-
----
-
-## Configuration
-
-```yaml
-# proagents.config.yaml
-
-ai:
-  # Default settings
-  default_provider: "anthropic"
-  default_model: "claude-3-sonnet"
-
-  # Provider configurations
-  providers:
-    anthropic:
-      api_key: "${ANTHROPIC_API_KEY}"
-      models:
-        - claude-3-opus
-        - claude-3-sonnet
-        - claude-3-haiku
-
-    openai:
-      api_key: "${OPENAI_API_KEY}"
-      models:
-        - gpt-4-turbo
-        - gpt-4
-        - gpt-3.5-turbo
-
-    google:
-      api_key: "${GOOGLE_API_KEY}"
-      models:
-        - gemini-pro
-        - gemini-ultra
-
-  # Task-specific models
-  task_routing:
-    code_analysis: "claude-3-opus"
-    code_generation: "claude-3-sonnet"
-    quick_tasks: "claude-3-haiku"
-    documentation: "gpt-4"
-
-  # Cost management
-  cost:
-    daily_limit: 50.00
-    alert_threshold: 40.00
-    fallback_on_limit: true
-
-  # Fallback chain
-  fallback:
-    primary: "claude-3-sonnet"
-    secondary: "gpt-4"
-    tertiary: "gemini-pro"
-```
-
----
-
-## Commands
-
-| Command | Description |
-|---------|-------------|
-| `proagents ai status` | Show AI configuration status |
-| `proagents ai models` | List available models |
-| `proagents ai usage` | Show usage and costs |
-| `proagents ai test` | Test model connectivity |

package/.proagents/ai-models/cost-management.md

@@ -1,362 +0,0 @@
-# Cost Management
-
-Manage and optimize AI model costs.
-
----
-
-## Overview
-
-Track and control AI usage costs to stay within budget.
-
-```
-┌─────────────────────────────────────────────────────────────┐
-│                    Cost Management                           │
-├─────────────────────────────────────────────────────────────┤
-│                                                             │
-│  Usage Tracking ──► Cost Calculation ──► Budget Control    │
-│        │                  │                   │             │
-│        ▼                  ▼                   ▼             │
-│  Token Counting      Rate Application     Alerts/Limits    │
-│  Request Logging     Provider Totals      Fallback Logic   │
-│                                                             │
-└─────────────────────────────────────────────────────────────┘
-```
-
----
-
-## Cost Configuration
-
-### Budget Limits
-
-```yaml
-ai:
-  cost:
-    # Daily spending limit
-    daily_limit: 50.00
-
-    # Weekly limit
-    weekly_limit: 250.00
-
-    # Monthly limit
-    monthly_limit: 1000.00
-
-    # Alert thresholds (percentage of limit)
-    alerts:
-      - threshold: 50
-        action: "notify"
-      - threshold: 80
-        action: "notify"
-      - threshold: 100
-        action: "block_or_fallback"
-
-    # On limit reached
-    on_limit:
-      action: "fallback"  # or "block"
-      fallback_model: "claude-3-haiku"
-```
-
-### Per-Team Budgets
-
-```yaml
-ai:
-  cost:
-    team_budgets:
-      frontend:
-        daily: 20.00
-        monthly: 400.00
-
-      backend:
-        daily: 25.00
-        monthly: 500.00
-
-      mobile:
-        daily: 15.00
-        monthly: 300.00
-```
-
----
-
-## Pricing Reference
-
-### Claude Models (Anthropic)
-
-| Model | Input (/1M tokens) | Output (/1M tokens) |
-|-------|-------------------|---------------------|
-| Opus | $15.00 | $75.00 |
-| Sonnet | $3.00 | $15.00 |
-| Haiku | $0.25 | $1.25 |
-
-### GPT Models (OpenAI)
-
-| Model | Input (/1M tokens) | Output (/1M tokens) |
-|-------|-------------------|---------------------|
-| GPT-4 Turbo | $10.00 | $30.00 |
-| GPT-4 | $30.00 | $60.00 |
-| GPT-3.5 | $0.50 | $1.50 |
-
-### Gemini Models (Google)
-
-| Model | Input (/1M tokens) | Output (/1M tokens) |
-|-------|-------------------|---------------------|
-| Gemini Pro | $0.50 | $1.50 |
-| Gemini Ultra | $7.00 | $21.00 |
-
----
-
-## Usage Tracking
-
-### View Current Usage
-
-```bash
-# Show today's usage
-proagents ai usage
-
-# Show weekly usage
-proagents ai usage --period week
-
-# Show by project
-proagents ai usage --by project
-
-# Show by model
-proagents ai usage --by model
-```
-
-### Usage Dashboard
-
-```
-┌─────────────────────────────────────────────────────────────┐
-│ AI Usage - January 2024                                     │
-├─────────────────────────────────────────────────────────────┤
-│                                                             │
-│ Today's Spend: $12.45 / $50.00                             │
-│ ████████████░░░░░░░░░░░░░░ 25%                             │
-│                                                             │
-│ This Month: $234.56 / $1000.00                             │
-│ ████████░░░░░░░░░░░░░░░░░░ 23%                             │
-│                                                             │
-│ By Model:                                                   │
-│ ├── claude-3-sonnet: $156.78 (67%)                        │
-│ ├── claude-3-opus: $45.23 (19%)                           │
-│ ├── claude-3-haiku: $18.90 (8%)                           │
-│ └── gpt-4: $13.65 (6%)                                    │
-│                                                             │
-│ By Task:                                                    │
-│ ├── Code Analysis: $89.45                                  │
-│ ├── Code Generation: $78.34                                │
-│ ├── Documentation: $34.56                                  │
-│ └── Quick Tasks: $32.21                                   │
-│                                                             │
-│ Tokens Used:                                                │
-│ ├── Input: 2.3M tokens                                    │
-│ └── Output: 890K tokens                                   │
-│                                                             │
-└─────────────────────────────────────────────────────────────┘
-```
-
----
-
-## Cost Optimization
-
-### Smart Model Selection
-
-```yaml
-ai:
-  optimization:
-    # Use cheaper models for simple tasks
-    auto_downgrade:
-      enabled: true
-      rules:
-        - task_type: "simple"
-          prefer: "haiku"
-        - task_type: "medium"
-          prefer: "sonnet"
-        - task_type: "complex"
-          prefer: "opus"
-
-    # Estimate before execution
-    estimate_first: true
-    confirm_expensive: true  # Confirm if > $1
-```
-
-### Caching
-
-```yaml
-ai:
-  caching:
-    enabled: true
-    ttl: "24h"
-
-    # Cache identical requests
-    request_cache: true
-
-    # Cache code analysis
-    analysis_cache: true
-    analysis_ttl: "7d"
-```
-
-### Token Optimization
-
-```yaml
-ai:
-  optimization:
-    # Compress context when possible
-    compress_context: true
-
-    # Truncate long files
-    max_file_tokens: 10000
-
-    # Summarize instead of full context
-    use_summaries: true
-```
-
----
-
-## Cost Alerts
-
-### Configuration
-
-```yaml
-ai:
-  alerts:
-    cost:
-      - name: "Daily 50%"
-        condition: "daily_spend >= daily_limit * 0.5"
-        channels: ["slack"]
-
-      - name: "Daily 80%"
-        condition: "daily_spend >= daily_limit * 0.8"
-        channels: ["slack", "email"]
-
-      - name: "Daily Limit"
-        condition: "daily_spend >= daily_limit"
-        channels: ["slack", "email", "sms"]
-        action: "fallback_to_cheaper"
-
-      - name: "Monthly 90%"
-        condition: "monthly_spend >= monthly_limit * 0.9"
-        channels: ["email"]
-        action: "notify_admin"
-```
-
-### Alert Example
-
-```
-🔔 AI Cost Alert
-
-Daily spend has reached 80% of limit.
-
-Current: $40.12 / $50.00
-Remaining: $9.88
-
-Top Consumers:
-• Code analysis: $18.45
-• Feature implementation: $12.34
-
-Recommendation: Consider using Haiku for remaining tasks today.
-
-[View Details] [Adjust Limit]
-```
-
----
-
-## Cost Reports
-
-### Generate Report
-
-```bash
-# Monthly cost report
-proagents ai report --period month
-
-# Export to CSV
-proagents ai report --format csv --output costs.csv
-```
-
-### Report Contents
-
-```markdown
-# AI Cost Report - January 2024
-
-## Summary
-- Total Spend: $845.67
-- Budget: $1000.00
-- Remaining: $154.33
-
-## By Provider
-| Provider | Spend | % of Total |
-|----------|-------|------------|
-| Anthropic | $678.45 | 80% |
-| OpenAI | $134.22 | 16% |
-| Google | $33.00 | 4% |
-
-## By Model
-| Model | Requests | Tokens | Cost |
-|-------|----------|--------|------|
-| claude-3-sonnet | 1,234 | 4.5M | $456.78 |
-| claude-3-opus | 89 | 890K | $178.90 |
-| claude-3-haiku | 567 | 1.2M | $42.77 |
-
-## By Team
-| Team | Spend | Budget | Status |
-|------|-------|--------|--------|
-| Frontend | $312.45 | $400 | ✅ |
-| Backend | $398.22 | $500 | ✅ |
-| Mobile | $135.00 | $300 | ✅ |
-
-## Trends
-- Daily average: $28.19
-- Peak day: Jan 15 ($67.89)
-- Lowest day: Jan 1 ($3.45)
-
-## Recommendations
-1. Consider caching repeated analysis requests
-2. Use Haiku for config/quick changes
-3. Team Backend approaching limit - review usage
-```
-
----
-
-## Budget Actions
-
-### On Budget Exceeded
-
-```yaml
-ai:
-  cost:
-    on_limit_exceeded:
-      # Options: block, fallback, notify_only, emergency_only
-      action: "fallback"
-
-      fallback_chain:
-        - "claude-3-haiku"
-        - "gpt-3.5-turbo"
-
-      emergency_override:
-        enabled: true
-        requires: "admin_approval"
-        max_additional: 20.00
-```
-
-### Manual Controls
-
-```bash
-# Pause AI usage
-proagents ai pause
-
-# Resume AI usage
-proagents ai resume
-
-# Emergency override (with approval)
-proagents ai override --reason "Critical production fix"
-```
-
----
-
-## Best Practices
-
-1. **Set Conservative Limits**: Start low, increase as needed
-2. **Enable Alerts Early**: Get notified at 50%
-3. **Use Right-Sized Models**: Don't use Opus for simple tasks
-4. **Enable Caching**: Avoid duplicate requests
-5. **Review Weekly**: Check usage patterns
-6. **Optimize Prompts**: Reduce token usage
-7. **Train Team**: Make team aware of costs