AI Agent Orchestra API Documentation

Enterprise-Grade AI Agent Orchestration REST API

Complete API reference for the AI Agent Orchestra module, providing real-time workflow management, multi-agent coordination, and comprehensive analytics for enterprise Drupal applications.

Base URL

https://your-site.com/ai-orchestra/api

Authentication

All API endpoints support standard Drupal authentication methods:

Session Cookie: For logged-in users via web interface
Basic Auth: Username/password for simple integrations
OAuth2: For third-party applications (requires oauth module)
API Keys: Custom key-based authentication (requires api_key module)

Example Request Headers

Authorization: Bearer YOUR_API_TOKEN
Content-Type: application/json
Accept: application/json

Rate Limiting

Default Limit: 100 requests per hour per IP
Admin Users: 1000 requests per hour
Authenticated Users: 500 requests per hour

Rate limit headers are included in all responses:

X-RateLimit-Limit: 100
X-RateLimit-Remaining: 95
X-RateLimit-Reset: 1640995800

Live Monitoring APIs

Get Real-Time System Status

Get comprehensive real-time system status including active workflows, resource usage, and provider health.

GET /live-status

Response Schema:

{
  "system_status": {
    "status": "operational",
    "uptime": "2d 14h 32m",
    "version": "1.0.0",
    "environment": "production"
  },
  "active_workflows": [
    {
      "id": "content_processing_123",
      "started_at": 1640995200,
      "progress": 75.5,
      "current_step": "seo_optimization",
      "estimated_completion": 1640995500
    }
  ],
  "resource_usage": {
    "cpu_usage": 23.5,
    "memory_usage": 67.2,
    "disk_usage": 45.2,
    "network_io": "moderate"
  },
  "ai_provider_status": {
    "ollama": {
      "status": "online",
      "response_time": "120ms",
      "active_connections": 3,
      "models_available": ["llama3.2:latest", "nomic-embed-text"]
    },
    "openai": {
      "status": "online", 
      "response_time": "340ms",
      "active_connections": 1,
      "rate_limit_remaining": 2400
    },
    "anthropic": {
      "status": "offline",
      "response_time": "n/a",
      "last_error": "Connection timeout"
    }
  },
  "queue_status": {
    "pending_items": 12,
    "processing_rate": "2.3 items/min",
    "estimated_wait": "45 seconds",
    "failed_items_24h": 3
  },
  "timestamp": 1640995800,
  "server_time": "2025-01-01T12:30:00Z"
}

Response Codes:

200: Success
500: System error
503: System temporarily unavailable

Get Workflow Analytics

Advanced analytics with execution trends, success rates, and cost analysis.

GET /workflow-metrics?timeframe={timeframe}&include_trends={boolean}

Query Parameters:

timeframe (string): Time period for metrics (1h, 24h, 7d, 30d)
include_trends (boolean): Include trend analysis (default: true)
flow_ids (array): Filter by specific workflow IDs
group_by (string): Group results by flow, hour, day

Response Schema:

{
  "metrics": {
    "total_executions": 156,
    "successful_executions": 142,
    "failed_executions": 14,
    "success_rate": 91.0,
    "average_duration": 32.5,
    "median_duration": 28.0,
    "total_cost": 2.45,
    "tokens_consumed": 45200,
    "unique_workflows": 8,
    "peak_concurrent_executions": 5
  },
  "trends": {
    "execution_trend": "+12%",
    "success_rate_trend": "+3%",
    "cost_trend": "-8%",
    "performance_trend": "+15%",
    "trend_period": "vs_previous_24h"
  },
  "by_workflow": {
    "content_processing": {
      "executions": 89,
      "success_rate": 94.4,
      "avg_duration": 28.5,
      "cost": 1.23,
      "trend": "+8%"
    },
    "seo_optimization": {
      "executions": 45,
      "success_rate": 86.7,
      "avg_duration": 41.2,
      "cost": 0.89,
      "trend": "+15%"
    }
  },
  "hourly_breakdown": [
    {
      "hour": "2025-01-01T12:00:00Z",
      "executions": 23,
      "success_rate": 91.3,
      "avg_duration": 31.2
    }
  ],
  "timeframe": "24h",
  "generated_at": 1640995800
}

Get Agent Analytics

Performance insights, usage statistics, and recommendation scores for all agents.

GET /agent-analytics?include_costs={boolean}&include_recommendations={boolean}

Query Parameters:

include_costs (boolean): Include detailed cost analysis
include_recommendations (boolean): Include recommendation scores
agent_ids (array): Filter by specific agent IDs

Response Schema:

{
  "analytics": {
    "performance_metrics": {
      "content_analyzer": {
        "avg_time": 2.3,
        "success_rate": 95.2,
        "executions_24h": 89,
        "error_rate": 4.8,
        "avg_tokens": 450,
        "confidence_score": 0.92
      },
      "data_validator": {
        "avg_time": 1.8,
        "success_rate": 98.1,
        "executions_24h": 67,
        "error_rate": 1.9,
        "avg_tokens": 280,
        "confidence_score": 0.96
      }
    },
    "usage_statistics": {
      "most_used_agent": "content_analyzer",
      "usage_distribution": {
        "content_analyzer": 45,
        "data_validator": 30,
        "seo_optimizer": 25
      },
      "peak_usage_hours": ["09:00-11:00", "14:00-16:00"],
      "least_used_agent": "legacy_processor"
    },
    "cost_analysis": {
      "total_cost_24h": 2.45,
      "cost_per_execution": 0.016,
      "most_expensive_agent": "seo_optimizer",
      "cost_breakdown": {
        "content_analyzer": 1.20,
        "data_validator": 0.65,
        "seo_optimizer": 0.60
      },
      "cost_trends": {
        "24h_change": "-8%",
        "7d_average": 2.85,
        "projected_monthly": 73.50
      }
    },
    "recommendation_scores": {
      "content_analyzer": 8.7,
      "data_validator": 9.2,
      "seo_optimizer": 7.8,
      "scoring_criteria": [
        "success_rate",
        "performance",
        "cost_efficiency",
        "user_satisfaction"
      ]
    },
    "execution_patterns": {
      "peak_hours": ["09:00-11:00", "14:00-16:00"],
      "common_workflows": ["content_processing", "data_validation"],
      "failure_patterns": ["timeout_errors", "api_rate_limits"],
      "seasonal_trends": {
        "weekday_avg": 156,
        "weekend_avg": 89,
        "monthly_pattern": "increasing"
      }
    }
  },
  "timestamp": 1640995800,
  "data_freshness": "real-time",
  "cache_status": "fresh"
}

Server-Sent Events Stream

Real-time data stream for live dashboard updates.

GET /live-stream
Accept: text/event-stream

Stream Events:

event: status_update
data: {"active_workflows": 3, "queue_size": 12, "system_load": 0.65, "timestamp": 1640995800}

event: workflow_started
data: {"workflow_id": "content_processing_456", "started_at": 1640995801, "estimated_duration": 45}

event: workflow_completed
data: {"workflow_id": "content_processing_123", "completed_at": 1640995802, "success": true, "duration": 42.5}

event: agent_performance
data: {"agent_id": "content_analyzer", "avg_response_time": 2.1, "success_rate": 96.2}

event: cost_alert
data: {"alert_type": "budget_threshold", "current_cost": 15.67, "threshold": 15.00, "period": "daily"}

event: error
data: {"error": "Provider temporarily unavailable", "provider": "openai", "retry_in": 30}

Event Types:

status_update: General system status updates
workflow_started: New workflow execution started
workflow_completed: Workflow execution finished
workflow_failed: Workflow execution failed
agent_performance: Agent performance metrics update
cost_alert: Cost threshold alerts
provider_status: AI provider status changes
error: System errors and warnings

Workflow Management APIs

Execute Workflow

Execute a workflow with context data and monitoring options.

POST /execute-workflow
Content-Type: application/json

{
  "workflow_id": "content_processing",
  "context": {
    "content": "Content to process",
    "user_id": 123,
    "node_id": 456,
    "metadata": {
      "source": "api",
      "priority": "high",
      "category": "blog_post"
    }
  },
  "options": {
    "async": false,
    "timeout": 300,
    "retry_attempts": 3,
    "callback_url": "https://mysite.com/webhook/workflow-complete",
    "notification_email": "admin@example.com",
    "monitoring": {
      "enable_detailed_logging": true,
      "track_intermediate_results": true,
      "send_progress_updates": true
    }
  }
}

Response Schema:

{
  "success": true,
  "execution_id": "exec_content_processing_abc123",
  "status": "completed",
  "result": {
    "workflow_id": "content_processing",
    "steps_executed": 3,
    "execution_time": 45.2,
    "cost_estimate": 0.08,
    "results": {
      "content_analysis": {
        "sentiment": 0.85,
        "readability": 7.2,
        "seo_score": 78,
        "quality_score": 8.5,
        "word_count": 1250,
        "reading_time": "5 minutes"
      },
      "optimization_suggestions": [
        "Add more subheadings for better structure",
        "Improve meta description for SEO",
        "Consider adding internal links",
        "Optimize images with alt text"
      ],
      "final_recommendations": {
        "publish_ready": true,
        "confidence": 0.92,
        "priority_improvements": 2
      }
    },
    "step_details": [
      {
        "step_id": "content_analysis",
        "duration": 15.2,
        "tokens_used": 456,
        "cost": 0.023,
        "success": true
      },
      {
        "step_id": "seo_optimization",
        "duration": 18.5,
        "tokens_used": 589,
        "cost": 0.031,
        "success": true
      },
      {
        "step_id": "final_review",
        "duration": 11.5,
        "tokens_used": 234,
        "cost": 0.012,
        "success": true
      }
    ]
  },
  "metrics": {
    "total_tokens": 1279,
    "ai_calls": 3,
    "cache_hits": 1,
    "providers_used": ["ollama", "openai"]
  },
  "timestamp": 1640995800
}

Response Codes:

200: Workflow executed successfully
202: Workflow queued for async execution
400: Invalid request data
404: Workflow not found
429: Rate limit exceeded
500: Execution error

Get Workflow Status

Get detailed status of a specific workflow execution.

GET /workflow-status/{execution_id}

Path Parameters:

execution_id (string): Unique execution identifier

Response Schema:

{
  "execution_id": "exec_content_processing_abc123",
  "workflow_id": "content_processing",
  "status": "running",
  "progress_percentage": 65.0,
  "current_step": "seo_optimization",
  "current_step_progress": 80.0,
  "started_at": 1640995200,
  "estimated_completion": 1640995500,
  "elapsed_time": 180.5,
  "remaining_time": 45.2,
  "steps_completed": ["content_analysis", "sentiment_check"],
  "steps_remaining": ["final_review", "quality_validation"],
  "agent_decisions": [
    {
      "agent": "content_analyzer",
      "decision": "proceed_with_optimization",
      "confidence": 0.92,
      "reasoning": "Content quality score above threshold",
      "timestamp": 1640995300,
      "context_used": ["readability_score", "keyword_density"]
    }
  ],
  "intermediate_results": {
    "content_analysis": {
      "quality_score": 8.2,
      "sentiment": 0.85,
      "complexity": "intermediate"
    },
    "sentiment_check": {
      "overall_sentiment": "positive",
      "confidence": 0.91,
      "key_emotions": ["optimism", "enthusiasm"]
    }
  },
  "metrics": {
    "execution_time": 180.5,
    "ai_calls": 3,
    "tokens_used": 1250,
    "cost_estimate": 0.045,
    "cache_hits": 2,
    "api_calls": 1
  },
  "resource_usage": {
    "peak_memory": "64MB",
    "cpu_time": "12.5s",
    "network_requests": 8
  },
  "warnings": [
    {
      "type": "performance",
      "message": "Step execution slower than expected",
      "step": "seo_optimization",
      "threshold": 15.0,
      "actual": 18.5
    }
  ]
}

Cancel Workflow

Cancel a running workflow execution.

POST /workflow-cancel/{execution_id}
Content-Type: application/json

{
  "reason": "User requested cancellation",
  "force": false,
  "cleanup": true
}

Response Schema:

{
  "success": true,
  "execution_id": "exec_content_processing_abc123",
  "status": "cancelled",
  "cancelled_at": 1640995800,
  "steps_completed": 2,
  "steps_cancelled": 1,
  "partial_results": {
    "content_analysis": {...},
    "sentiment_check": {...}
  },
  "cleanup_status": "completed",
  "refund_amount": 0.023
}

Agent Management APIs

Get Available Agents

List all available AI agents with their capabilities and performance metrics.

GET /agents?category={category}&status={status}&include_metrics={boolean}

Query Parameters:

category (string): Filter by agent category (content, seo, validation, transformation)
status (string): Filter by status (active, inactive, maintenance)
include_metrics (boolean): Include performance metrics (default: false)
sort (string): Sort by field (name, success_rate, cost, usage)
limit (integer): Maximum number of results (default: 50)

Response Schema:

{
  "agents": [
    {
      "id": "content_analyzer",
      "label": "Content Quality Analyzer",
      "description": "Analyzes content quality, readability, and structure",
      "category": "content",
      "status": "active",
      "version": "2.1.0",
      "capabilities": [
        "sentiment_analysis",
        "readability_scoring",
        "seo_analysis",
        "quality_assessment",
        "keyword_extraction"
      ],
      "supported_languages": ["en", "es", "fr", "de"],
      "input_types": ["text", "html", "markdown"],
      "output_format": "structured_json",
      "configuration": {
        "supports_streaming": true,
        "max_input_length": 50000,
        "timeout": 30,
        "retry_limit": 3
      },
      "performance_metrics": {
        "average_cost": 0.02,
        "success_rate": 95.2,
        "average_duration": 2.3,
        "executions_24h": 89,
        "user_rating": 4.7,
        "last_updated": 1640995800
      },
      "pricing": {
        "base_cost": 0.001,
        "per_token": 0.00002,
        "bulk_discount": 0.15,
        "enterprise_rate": 0.00015
      }
    }
  ],
  "total": 12,
  "categories": ["content", "seo", "validation", "transformation", "analysis"],
  "filters_applied": {
    "category": "content",
    "status": "active"
  },
  "pagination": {
    "page": 1,
    "per_page": 50,
    "total_pages": 1
  }
}

Get Agent Recommendations

Get AI-powered agent recommendations based on context and requirements.

POST /agents/recommend
Content-Type: application/json

{
  "context": {
    "content_type": "blog_post",
    "content_length": 2000,
    "language": "en",
    "target_audience": "developers",
    "current_quality_score": 6.5,
    "seo_requirements": ["keyword_optimization", "meta_tags"],
    "deadline": "2025-01-02T10:00:00Z"
  },
  "requirements": {
    "max_cost": 0.10,
    "max_duration": 60,
    "min_confidence": 0.8,
    "preferred_providers": ["ollama", "openai"],
    "exclude_agents": ["legacy_processor"],
    "quality_level": "premium"
  },
  "preferences": {
    "prioritize": "accuracy",
    "risk_tolerance": "low",
    "explain_recommendations": true
  }
}

Response Schema:

{
  "recommendations": [
    {
      "agent_id": "content_analyzer",
      "confidence": 0.95,
      "match_score": 9.2,
      "reasoning": "Perfect match for technical blog content analysis with excellent track record for developer-focused content",
      "estimated_cost": 0.02,
      "estimated_duration": 15,
      "success_probability": 0.96,
      "quality_improvement_potential": 2.3,
      "provider": "ollama",
      "pros": [
        "Specialized in technical content",
        "Fast execution time",
        "Cost-effective",
        "High accuracy for developer content"
      ],
      "cons": [
        "Limited to English language",
        "May require technical context"
      ],
      "alternative_configs": [
        {
          "config": "high_accuracy",
          "cost": 0.035,
          "duration": 25,
          "accuracy": 0.98
        }
      ]
    },
    {
      "agent_id": "seo_optimizer",
      "confidence": 0.87,
      "match_score": 8.4,
      "reasoning": "Strong SEO capabilities matching your requirements, though slightly higher cost",
      "estimated_cost": 0.045,
      "estimated_duration": 22,
      "success_probability": 0.91,
      "quality_improvement_potential": 1.8
    }
  ],
  "context_analysis": {
    "complexity": "moderate",
    "domain": "technical",
    "estimated_tokens": 500,
    "processing_difficulty": "standard",
    "similar_workflows": ["technical_blog_processing", "developer_content_review"],
    "success_factors": [
      "Clear technical writing",
      "Good structure",
      "Specific target audience"
    ]
  },
  "workflow_suggestions": [
    {
      "type": "sequential",
      "agents": ["content_analyzer", "seo_optimizer"],
      "estimated_total_cost": 0.065,
      "estimated_total_duration": 37,
      "confidence": 0.93
    },
    {
      "type": "parallel",
      "agents": ["content_analyzer", "technical_validator"],
      "estimated_total_cost": 0.055,
      "estimated_total_duration": 18,
      "confidence": 0.89
    }
  ],
  "cost_breakdown": {
    "base_processing": 0.02,
    "premium_features": 0.015,
    "bulk_discount": -0.005,
    "total_estimated": 0.065
  },
  "total_agents_analyzed": 12,
  "recommendation_timestamp": 1640995800
}

Monitoring & Analytics APIs

Get System Health

Comprehensive system health check including all components.

GET /health?include_details={boolean}&check_providers={boolean}

Response Schema:

{
  "overall_status": "healthy",
  "health_score": 95.2,
  "components": {
    "orchestrator": {
      "status": "operational",
      "response_time": "45ms",
      "uptime": "99.8%",
      "last_restart": "2025-01-01T00:00:00Z"
    },
    "queue_processor": {
      "status": "operational", 
      "queue_size": 12,
      "processing_rate": "2.3/min",
      "failed_jobs_24h": 2
    },
    "ai_providers": {
      "status": "partial",
      "healthy_providers": 2,
      "total_providers": 3,
      "degraded_providers": ["anthropic"]
    },
    "database": {
      "status": "operational",
      "connection_pool": "80% utilized",
      "query_performance": "excellent",
      "replication_lag": "0ms"
    },
    "cache": {
      "status": "operational",
      "hit_rate": "94.5%",
      "memory_usage": "67%",
      "eviction_rate": "low"
    }
  },
  "performance_metrics": {
    "avg_response_time": "156ms",
    "throughput": "45 requests/min",
    "error_rate": "0.2%",
    "availability": "99.95%"
  },
  "alerts": [
    {
      "level": "warning",
      "component": "ai_providers",
      "message": "Anthropic provider offline",
      "since": "2025-01-01T08:30:00Z",
      "impact": "low"
    }
  ],
  "recommendations": [
    "Consider increasing queue worker processes during peak hours",
    "Monitor anthropic provider connection",
    "Cache hit rate could be improved with longer TTL"
  ],
  "next_maintenance": "2025-01-15T02:00:00Z",
  "timestamp": 1640995800
}

Get Performance Metrics

Detailed performance metrics for system optimization.

GET /metrics/performance?timeframe={timeframe}&granularity={granularity}

Query Parameters:

timeframe (string): Time period (1h, 24h, 7d, 30d)
granularity (string): Data granularity (minute, hour, day)
metrics (array): Specific metrics to include
include_predictions (boolean): Include performance predictions

Response Schema:

{
  "metrics": {
    "response_times": {
      "avg": 156.7,
      "p50": 142.0,
      "p95": 285.0,
      "p99": 450.0,
      "max": 1200.0
    },
    "throughput": {
      "requests_per_minute": 45.2,
      "workflows_per_hour": 156,
      "peak_concurrent": 8,
      "capacity_utilization": 65.5
    },
    "error_rates": {
      "total_error_rate": 0.2,
      "timeout_rate": 0.05,
      "provider_error_rate": 0.1,
      "system_error_rate": 0.05
    },
    "resource_utilization": {
      "cpu_usage": 68.5,
      "memory_usage": 72.1,
      "disk_io": 45.2,
      "network_io": 23.8
    }
  },
  "trends": {
    "response_time_trend": "-5%",
    "throughput_trend": "+12%",
    "error_rate_trend": "-15%",
    "resource_trend": "+8%"
  },
  "timeseries": [
    {
      "timestamp": "2025-01-01T12:00:00Z",
      "response_time": 145.2,
      "throughput": 42.1,
      "error_rate": 0.15,
      "cpu_usage": 65.2
    }
  ],
  "predictions": {
    "next_hour": {
      "expected_load": 52.3,
      "predicted_response_time": 162.5,
      "confidence": 0.87
    },
    "capacity_warnings": [
      {
        "metric": "concurrent_workflows",
        "predicted_peak": "2025-01-01T15:30:00Z",
        "expected_value": 12,
        "threshold": 15,
        "risk_level": "medium"
      }
    ]
  },
  "recommendations": [
    {
      "type": "performance",
      "priority": "high",
      "description": "Consider scaling up during predicted 3PM peak",
      "estimated_benefit": "25% response time improvement"
    }
  ]
}

Error Handling

All API endpoints follow consistent error response format:

{
  "error": {
    "code": "WORKFLOW_NOT_FOUND",
    "message": "The specified workflow could not be found",
    "details": {
      "workflow_id": "invalid_workflow",
      "suggested_workflows": ["content_processing", "seo_optimization"]
    },
    "timestamp": 1640995800,
    "request_id": "req_abc123def456",
    "documentation": "https://docs.example.com/api/errors#workflow-not-found"
  }
}

Common Error Codes

INVALID_REQUEST: Malformed request data
AUTHENTICATION_REQUIRED: Missing or invalid authentication
PERMISSION_DENIED: Insufficient permissions
WORKFLOW_NOT_FOUND: Specified workflow doesn't exist
EXECUTION_FAILED: Workflow execution error
RATE_LIMIT_EXCEEDED: Too many requests
PROVIDER_UNAVAILABLE: AI provider is offline
SYSTEM_OVERLOADED: System at capacity
VALIDATION_ERROR: Input validation failed
TIMEOUT_ERROR: Request timed out

SDKs and Integration Examples

PHP/Drupal Integration

// Using Drupal HTTP client
$client = \Drupal::httpClient();

$response = $client->post('https://your-site.com/ai-orchestra/api/execute-workflow', [
  'json' => [
    'workflow_id' => 'content_processing',
    'context' => ['content' => $content],
    'options' => ['async' => false]
  ],
  'headers' => [
    'Authorization' => 'Bearer ' . $api_token,
    'Accept' => 'application/json'
  ]
]);

$result = json_decode($response->getBody(), true);

JavaScript/Node.js Integration

const axios = require('axios');

async function executeWorkflow(workflowId, context) {
  try {
    const response = await axios.post('/ai-orchestra/api/execute-workflow', {
      workflow_id: workflowId,
      context: context,
      options: { async: false }
    }, {
      headers: {
        'Authorization': `Bearer ${apiToken}`,
        'Content-Type': 'application/json'
      }
    });
    
    return response.data;
  } catch (error) {
    console.error('Workflow execution failed:', error.response.data);
    throw error;
  }
}

// Real-time monitoring with Server-Sent Events
const eventSource = new EventSource('/ai-orchestra/api/live-stream');

eventSource.onmessage = function(event) {
  const data = JSON.parse(event.data);
  updateDashboard(data);
};

eventSource.addEventListener('workflow_completed', function(event) {
  const workflow = JSON.parse(event.data);
  handleWorkflowCompletion(workflow);
});

Python Integration

import requests
import json
from sseclient import SSEClient

class AiOrchestraClient:
    def __init__(self, base_url, api_token):
        self.base_url = base_url
        self.headers = {
            'Authorization': f'Bearer {api_token}',
            'Content-Type': 'application/json'
        }
    
    def execute_workflow(self, workflow_id, context, options=None):
        """Execute a workflow synchronously."""
        payload = {
            'workflow_id': workflow_id,
            'context': context,
            'options': options or {}
        }
        
        response = requests.post(
            f'{self.base_url}/execute-workflow',
            json=payload,
            headers=self.headers
        )
        
        response.raise_for_status()
        return response.json()
    
    def get_workflow_status(self, execution_id):
        """Get workflow execution status."""
        response = requests.get(
            f'{self.base_url}/workflow-status/{execution_id}',
            headers=self.headers
        )
        
        response.raise_for_status()
        return response.json()
    
    def stream_live_updates(self, callback):
        """Stream live updates via Server-Sent Events."""
        messages = SSEClient(f'{self.base_url}/live-stream')
        
        for msg in messages:
            if msg.data:
                data = json.loads(msg.data)
                callback(msg.event, data)

# Usage example
client = AiOrchestraClient('https://your-site.com/ai-orchestra/api', 'your-token')

# Execute workflow
result = client.execute_workflow('content_processing', {
    'content': 'Your content here',
    'user_id': 123
})

# Monitor live updates
def handle_update(event_type, data):
    print(f"Event: {event_type}, Data: {data}")

client.stream_live_updates(handle_update)

Webhooks

Configure webhook endpoints to receive real-time notifications about workflow events.

Webhook Configuration

POST /webhooks
Content-Type: application/json

{
  "url": "https://your-app.com/webhook/ai-orchestra",
  "events": [
    "workflow.completed",
    "workflow.failed", 
    "agent.performance_alert",
    "system.cost_threshold"
  ],
  "secret": "your-webhook-secret",
  "active": true,
  "retry_config": {
    "max_attempts": 3,
    "retry_delay": 5,
    "timeout": 30
  }
}

Webhook Payload Example

{
  "event": "workflow.completed",
  "timestamp": 1640995800,
  "data": {
    "execution_id": "exec_content_processing_abc123",
    "workflow_id": "content_processing",
    "status": "completed",
    "duration": 45.2,
    "cost": 0.08,
    "results": {...}
  },
  "signature": "sha256=abc123def456..."
}

Rate Limits and Quotas

Rate Limit Tiers

Tier	Requests/Hour	Concurrent Workflows	Cost Limit/Day
Basic	100	2	$1.00
Professional	500	5	$10.00
Enterprise	2000	20	$100.00
Custom	Negotiable	Negotiable	Negotiable

Quota Management

GET /quotas/current

Response:

{
  "current_usage": {
    "requests_this_hour": 45,
    "concurrent_workflows": 3,  
    "cost_today": 2.45
  },
  "limits": {
    "requests_per_hour": 500,
    "max_concurrent_workflows": 5,
    "daily_cost_limit": 10.00
  },
  "remaining": {
    "requests": 455,
    "concurrent_slots": 2,
    "cost_budget": 7.55
  },
  "reset_times": {
    "hourly_reset": "2025-01-01T13:00:00Z",
    "daily_reset": "2025-01-02T00:00:00Z"
  }
}

Support and Resources

API Status Page: https://status.your-site.com/api
Interactive API Explorer: https://your-site.com/api/docs
Postman Collection: Download
OpenAPI Specification: Download
Support: support@your-site.com
Developer Community: https://community.your-site.com

Last Updated: 2025-01-24
API Version: 1.0.0
Documentation Version: 1.2.0

Base URL​

Authentication​

Example Request Headers​

Rate Limiting​

Live Monitoring APIs​

Get Real-Time System Status​

Get Workflow Analytics​

Get Agent Analytics​

Server-Sent Events Stream​

Workflow Management APIs​

Execute Workflow​

Get Workflow Status​

Cancel Workflow​

Agent Management APIs​

Get Available Agents​

Get Agent Recommendations​

Monitoring & Analytics APIs​

Get System Health​

Get Performance Metrics​

Error Handling​

Common Error Codes​

SDKs and Integration Examples​

PHP/Drupal Integration​

JavaScript/Node.js Integration​

Python Integration​

Webhooks​

Webhook Configuration​

Webhook Payload Example​

Rate Limits and Quotas​

Rate Limit Tiers​

Quota Management​

Support and Resources​

Base URL

Authentication

Example Request Headers

Rate Limiting

Live Monitoring APIs

Get Real-Time System Status

Get Workflow Analytics

Get Agent Analytics

Server-Sent Events Stream

Workflow Management APIs

Execute Workflow

Get Workflow Status

Cancel Workflow

Agent Management APIs

Get Available Agents

Get Agent Recommendations

Monitoring & Analytics APIs

Get System Health

Get Performance Metrics

Error Handling

Common Error Codes

SDKs and Integration Examples

PHP/Drupal Integration

JavaScript/Node.js Integration

Python Integration

Webhooks

Webhook Configuration

Webhook Payload Example

Rate Limits and Quotas

Rate Limit Tiers

Quota Management

Support and Resources