Self-improving AI Employees for everyone
Python ai-agentsai-employeeai-employeesassistantautonomous-agentsco-employeescompanygrok-botinstinctloop-agentsmuseown-your-datapersonalself-hosted
feat: Transparent proxy on HTTP nodes, useProxy tool schema, docs update
trohitga85ab77ca8cb
diff --git a/CLAUDE.md b/CLAUDE.mdindex 6a12e91f..3efae3b9 100644--- a/CLAUDE.md+++ b/CLAUDE.md@@ -68,6 +68,11 @@ server/services/├── pricing.py # LLM and API cost calculation (loads config/pricing.json)├── telegram_service.py # TelegramService with python-telegram-bot long-polling├── tracked_http.py # HTTPX event hooks for automatic API cost tracking+├── proxy/ # Residential proxy provider management+│ ├── __init__.py # Exports get_proxy_service, ProxyService+│ ├── service.py # ProxyService singleton - provider selection, URL generation+│ ├── providers.py # TemplateProxyProvider - JSON url_template formatting+│ └── models.py # ProxyProvider, RoutingRule, SessionType enums├── deployment/ # Event-driven deployment lifecycle│ ├── __init__.py│ ├── state.py # DeploymentState, TriggerInfo dataclasses@@ -368,14 +373,14 @@ class CacheEntry(SQLModel, table=True):## Codebase Summary- **Hybrid architecture**: Node.js + Python + React TypeScript-- **89 implemented workflow nodes** with clean service separation (6 AI models + 3 AI agents/memory + 13 specialized agents + 1 skill + 4 dedicated tools + 3 search + 16 Android + 3 WhatsApp + 4 Twitter + 2 Telegram + 2 Social + 3 Location + 3 Code + 6 Utility + 6 Document + 2 Chat + 2 Scheduler + 2 Workflow + 7 Google Workspace + 1 Apify)+- **92 implemented workflow nodes** with clean service separation (6 AI models + 3 AI agents/memory + 13 specialized agents + 1 skill + 4 dedicated tools + 3 search + 16 Android + 3 WhatsApp + 4 Twitter + 2 Telegram + 2 Social + 3 Location + 3 Code + 6 Utility + 6 Document + 2 Chat + 2 Scheduler + 2 Workflow + 7 Google Workspace + 1 Apify + 3 Proxy)- **WebSocket-First Architecture**: WebSocket as primary frontend-backend communication (119 message handlers)- **Recent optimizations**: REST APIs replaced with WebSocket, AI endpoints migrated to Python, Android automation integrated## Architecture RefactoringThe project was completely refactored from schema-based node definitions to explicit INodeProperties interface system inspired by n8n architecture. Key changes:- **Pure INodeProperties System**: Removed all backward compatibility layers-- **89 Implemented Node Components**: AI models, agents, skills, location services, Android automation, WhatsApp, Twitter/X, Telegram, social, code execution, HTTP/Webhook utilities, document processing, chat, schedulers, and search+- **92 Implemented Node Components**: AI models, agents, skills, location services, Android automation, WhatsApp, Twitter/X, Telegram, social, code execution, HTTP/Webhook utilities, document processing, chat, schedulers, search, and proxy- **WebSocket-First Communication**: 119 WebSocket message handlers replace most REST API calls- **Resource-Operation Pattern**: Organized by functional categories (AI, Location, Android, WhatsApp)- **TypeScript-First**: Full type safety with proper interface alignment@@ -404,6 +409,7 @@ The project was completely refactored from schema-based node definitions to expl- `src/nodeDefinitions/telegramNodes.ts` - Telegram bot integration (2 nodes: send, receive)- `src/nodeDefinitions/socialNodes.ts` - Unified social messaging nodes (socialReceive, socialSend)- `src/nodeDefinitions/codeNodes.ts` - Python, JavaScript, and TypeScript code execution nodes+- `src/nodeDefinitions/proxyNodes.ts` - Proxy nodes (proxyRequest, proxyConfig, proxyStatus) and shared PROXY_PARAMETERS- `src/nodeDefinitions/utilityNodes.ts` - HTTP, Webhook, chatTrigger, and console nodes- `src/nodeDefinitions/documentNodes.ts` - Document processing nodes (httpScraper, fileDownloader, documentParser, textChunker, embeddingGenerator, vectorStore)- `src/nodeDefinitions/chatNodes.ts` - Chat send and history nodes@@ -526,7 +532,7 @@ The project uses WebSocket as the primary communication method between frontend- `server/services/status_broadcaster.py` - Connection management and broadcasting## Implemented Node Types-The following 89 nodes are currently implemented and functional:+The following 92 nodes are currently implemented and functional:### AI Chat Models (6 nodes)- **openaiChatModel**: OpenAI GPT models with response format options. O-series models (o1, o3, o4) support reasoning effort parameter.@@ -594,7 +600,9 @@ server/skills/│ └── nearby-places-skill/SKILL.md└── web_agent/ # Web automation skills├── web-search-skill/SKILL.md- └── http-request-skill/SKILL.md+ ├── http-request-skill/SKILL.md+ ├── proxy-config-skill/SKILL.md+ └── apify-skill/SKILL.md```**SKILL.md Format:**@@ -1114,6 +1122,29 @@ Web scraping service for social media, search engines, and websites using pre-bu**Authentication:** Single API token (Personal or Organization) from Apify Console -> Settings -> Integrations.+### Proxy Nodes (3 nodes)+Residential proxy provider management with geo-targeting, session control, and automatic failover.++- **proxyRequest**: Make HTTP requests through residential proxy providers with geo-targeting and failover. Parameters: method, url, headers, body, timeout, proxyProvider (auto-select or specific), proxyCountry (ISO code), sessionType (rotating/sticky), stickyDuration, maxRetries, followRedirects.+- **proxyConfig**: **Dual-purpose node** - Configure proxy providers and routing rules. Works as workflow node OR AI Agent tool. Operations: list_providers, add_provider, update_provider, remove_provider, set_credentials, test_provider, get_stats, add_routing_rule, list_routing_rules, remove_routing_rule.+- **proxyStatus**: View proxy provider health, scores, and usage statistics. Filter by specific provider name or view all.++**Key Architecture:**+- **TemplateProxyProvider**: Single class using JSON `url_template` to format proxy URLs for any provider (username-based, password-based, or no encoding)+- **Auto-selection**: ProxyService ranks providers by health score (success rate, latency) and selects the best one+- **Transparent proxy on HTTP nodes**: `httpRequest` and `httpScraper` nodes support `useProxy: true` flag. The proxy service handles provider selection, geo-targeting, and session type automatically.++**Key Files:**+| File | Description |+|------|-------------|+| `client/src/nodeDefinitions/proxyNodes.ts` | 3 node definitions + shared PROXY_PARAMETERS |+| `server/services/proxy/service.py` | ProxyService singleton with provider selection and URL generation |+| `server/services/proxy/providers.py` | TemplateProxyProvider for JSON url_template formatting |+| `server/services/proxy/models.py` | ProxyProvider, RoutingRule, SessionType dataclasses |+| `server/services/handlers/proxy.py` | Handler functions for proxy_config, proxy_request, proxy_status |+| `server/skills/web_agent/proxy-config-skill/SKILL.md` | AI agent skill for proxy configuration |+| `server/skills/web_agent/http-request-skill/SKILL.md` | HTTP request skill with proxy usage docs |+### Workflow Nodes (2 nodes)- **start**: Manual workflow trigger to start workflow execution- **taskTrigger**: Event-driven trigger that fires when a delegated child agent completes its task (success or error). Filters by task_id, agent_name, status (all/completed/error), and parent_node_id. Output includes task_id, status, agent_name, result/error, workflow_id.@@ -1124,7 +1155,7 @@ Web scraping service for social media, search engines, and websites using pre-bu- **typescriptExecutor**: **Dual-purpose node** - Execute TypeScript code via persistent Node.js server with type safety, syntax-highlighted editor and console output. Works as workflow node OR AI Agent tool (`typescript_code`).### Utility Nodes (6 nodes)-- **httpRequest**: Make HTTP requests to external APIs (GET, POST, PUT, DELETE, PATCH) with configurable headers, body, and timeout+- **httpRequest**: Make HTTP requests to external APIs (GET, POST, PUT, DELETE, PATCH) with configurable headers, body, timeout, and optional proxy support (`useProxy: true` routes through configured residential proxy)- **webhookTrigger**: Event-driven trigger that waits for incoming HTTP requests at `/webhook/{path}` with method filtering and authentication options- **webhookResponse**: Send custom response back to webhook caller with configurable status code, body, and content type- **chatTrigger**: Trigger node that receives messages from the Console Panel chat interface@@ -1134,7 +1165,7 @@ Web scraping service for social media, search engines, and websites using pre-bu### Document Processing Nodes (6 nodes)RAG pipeline nodes for document ingestion, processing, and vector storage. Supports multiple providers and backends.-- **httpScraper**: Scrape links from web pages with date/page pagination support. Modes: single request, date range iteration, page pagination. Outputs: items array with URLs.+- **httpScraper**: Scrape links from web pages with date/page pagination support. Modes: single request, date range iteration, page pagination. Outputs: items array with URLs. Supports `useProxy: true` for proxy routing.- **fileDownloader**: Download files from URLs in parallel using semaphore-based concurrency. Parameters: output directory, max workers (1-32), skip existing, timeout.- **documentParser**: Parse documents to text using configurable parsers. Parsers: PyPDF (fast), Marker (GPU OCR), Unstructured (multi-format), BeautifulSoup (HTML).- **textChunker**: Split text into overlapping chunks for embedding. Strategies: recursive (recommended), markdown, token. Parameters: chunk size (100-8000), overlap (0-1000).@@ -1340,7 +1371,7 @@ All scripts in `scripts/` are cross-platform Node.js (Windows, macOS, Linux, WSLSee **[Scripts Reference](./docs-internal/SCRIPTS.md)** for full documentation.## Current Status-✅ **INodeProperties System**: Fully implemented with 89 functional node components+✅ **INodeProperties System**: Fully implemented with 92 functional node components✅ **WebSocket-First Architecture**: 119 message handlers replacing REST APIs✅ **Code Editor**: Python, JavaScript, and TypeScript executors with syntax-highlighted editor (react-simple-code-editor + prismjs) and console output✅ **Node.js Executor**: Persistent Node.js server (Express + tsx) for fast JS/TS execution, replacing subprocess spawning@@ -1372,6 +1403,7 @@ See **[Scripts Reference](./docs-internal/SCRIPTS.md)** for full documentation.✅ **Cache System**: n8n-pattern cache with Redis (production) / SQLite (local dev) / Memory fallback hierarchy✅ **AI Thinking/Reasoning**: Extended thinking for Claude, Gemini 2.5/3, OpenAI GPT-5/o-series, Groq Qwen3 with output available in Input Data & Variables for downstream nodes✅ **Onboarding Service**: 5-step welcome wizard with Ant Design UI, database persistence, skip/resume/replay support+✅ **Proxy System**: Residential proxy provider management with template-based URL formatting, auto-selection by health score, transparent proxy injection on httpRequest/httpScraper nodes via `useProxy: true`## Key Featuresdiff --git a/client/src/Dashboard.tsx b/client/src/Dashboard.tsxindex 1697aabf..6d8a9992 100644--- a/client/src/Dashboard.tsx+++ b/client/src/Dashboard.tsx@@ -35,6 +35,7 @@ import { SEARCH_NODE_TYPES } from './nodeDefinitions/searchNodes';import { SOCIAL_NODE_TYPES } from './nodeDefinitions/socialNodes';import { APIFY_NODE_TYPES } from './nodeDefinitions/apifyNodes';import { GOOGLE_WORKSPACE_NODE_TYPES } from './nodeDefinitions/googleWorkspaceNodes';+import { PROXY_NODE_TYPES } from './nodeDefinitions/proxyNodes';import ParameterPanel from './ParameterPanel';import LocationParameterPanel from './components/LocationParameterPanel';import { useAppStore } from './store/useAppStore';@@ -140,6 +141,9 @@ const createNodeTypes = (): Record<string, React.ComponentType<any>> => {} else if (SEARCH_NODE_TYPES.includes(type)) {// Search API nodes use SquareNode componenttypes[type] = SquareNode;+ } else if (PROXY_NODE_TYPES.includes(type)) {+ // Proxy nodes use SquareNode component+ types[type] = SquareNode;} else if (SOCIAL_NODE_TYPES.includes(type)) {// Social nodes use AIAgentNode for multiple output handles supporttypes[type] = AIAgentNode;diff --git a/client/src/components/parameterPanel/InputSection.tsx b/client/src/components/parameterPanel/InputSection.tsxindex eaac9700..89ff793c 100644--- a/client/src/components/parameterPanel/InputSection.tsx+++ b/client/src/components/parameterPanel/InputSection.tsx@@ -637,6 +637,28 @@ const InputSection: React.FC<InputSectionProps> = ({ nodeId, visible = true }) =compute_units: 'number',started_at: 'string',finished_at: 'string'+ },+ // Proxy node schemas+ proxyRequest: {+ status: 'number',+ data: 'any',+ headers: 'object',+ url: 'string',+ method: 'string',+ proxy_provider: 'string',+ latency_ms: 'number',+ bytes_transferred: 'number',+ attempt: 'number'+ },+ proxyStatus: {+ enabled: 'boolean',+ providers: 'array',+ stats: 'object'+ },+ proxyConfig: {+ operation: 'string',+ success: 'boolean',+ data: 'any'}};@@ -687,6 +709,10 @@ const InputSection: React.FC<InputSectionProps> = ({ nodeId, visible = true }) =// Apify web scraping node detectionconst isApify = nodeType === 'apifyActor';+ // Proxy node detection+ const proxyNodeTypes = ['proxyRequest', 'proxyStatus', 'proxyConfig'];+ const isProxyNode = proxyNodeTypes.includes(nodeType);+// Select appropriate schemaif (isAndroidLocation) {outputSchema = sampleSchemas.androidLocation;@@ -696,6 +722,8 @@ const InputSection: React.FC<InputSectionProps> = ({ nodeId, visible = true }) =outputSchema = sampleSchemas[nodeType as keyof typeof sampleSchemas];} else if (isGoogleWorkspaceNode && sampleSchemas[nodeType as keyof typeof sampleSchemas]) {outputSchema = sampleSchemas[nodeType as keyof typeof sampleSchemas];+ } else if (isProxyNode && sampleSchemas[nodeType as keyof typeof sampleSchemas]) {+ outputSchema = sampleSchemas[nodeType as keyof typeof sampleSchemas];} else {outputSchema = isLocationNode || isGoogleMaps ? sampleSchemas.location :isMemory ? sampleSchemas.memory :diff --git a/client/src/components/ui/ComponentPalette.tsx b/client/src/components/ui/ComponentPalette.tsxindex 7697603a..8a9268c0 100644--- a/client/src/components/ui/ComponentPalette.tsx+++ b/client/src/components/ui/ComponentPalette.tsx@@ -26,6 +26,7 @@ const CATEGORY_ICONS: Record<string, string | { svg: string }> = {search: '🔍',google: { svg: googleSvg },scheduler: '📅',+ proxy: '🛡',};// Categories that should be merged into 'social' (Social Media)@@ -68,6 +69,7 @@ const ComponentPalette: React.FC<ComponentPaletteProps> = ({search: colors.categoryModel || theme.dracula.cyan,google: theme.accent.blue,scheduler: colors.categoryTrigger || theme.dracula.pink,+ proxy: colors.categoryUtil || theme.dracula.purple,};const labelMap: Record<string, string> = {workflow: 'Workflows',@@ -88,6 +90,7 @@ const ComponentPalette: React.FC<ComponentPaletteProps> = ({search: 'Search',google: 'Google Workspace',scheduler: 'Schedulers',+ proxy: 'Proxy',};return {icon: CATEGORY_ICONS[key] || '📦',diff --git a/client/src/nodeDefinitions.ts b/client/src/nodeDefinitions.tsindex b0630675..d307764f 100644--- a/client/src/nodeDefinitions.ts+++ b/client/src/nodeDefinitions.ts@@ -23,6 +23,7 @@ import { apifyNodes, APIFY_NODE_TYPES } from './nodeDefinitions/apifyNodes';import { searchNodes, SEARCH_NODE_TYPES } from './nodeDefinitions/searchNodes';// Consolidated Google Workspace nodes (replaces gmailNodes, calendarNodes, driveNodes, sheetsNodes, tasksNodes, contactsNodes)import { googleWorkspaceNodes, GOOGLE_WORKSPACE_NODE_TYPES } from './nodeDefinitions/googleWorkspaceNodes';+import { proxyNodes, PROXY_NODE_TYPES } from './nodeDefinitions/proxyNodes';// ============================================================================// MAIN NODE REGISTRY - Combining all modular definitions@@ -49,7 +50,8 @@ export const nodeDefinitions: Record<string, INodeTypeDescription> = {...twitterNodes,...apifyNodes,...searchNodes,- ...googleWorkspaceNodes+ ...googleWorkspaceNodes,+ ...proxyNodes};// ============================================================================@@ -142,5 +144,9 @@ export const SEARCH_NODES = [...SEARCH_NODE_TYPES];+export const PROXY_NODES = [+ ...PROXY_NODE_TYPES+];+// Re-export types and utilities from modular files for external accessexport { createBaseChatModel } from './nodeDefinitions/aiModelNodes';diff --git a/client/src/nodeDefinitions/documentNodes.ts b/client/src/nodeDefinitions/documentNodes.tsindex d5f249f7..d999c18a 100644--- a/client/src/nodeDefinitions/documentNodes.ts+++ b/client/src/nodeDefinitions/documentNodes.ts@@ -92,6 +92,31 @@ export const documentNodes: Record<string, INodeTypeDescription> = {default: '{}',typeOptions: { rows: 2 },placeholder: '{"Authorization": "Bearer token"}'+ },+ {+ displayName: 'Use Proxy',+ name: 'useProxy',+ type: 'boolean',+ default: false,+ description: 'Route requests through a configured proxy provider'+ },+ {+ displayName: 'Proxy Country',+ name: 'proxyCountry',+ type: 'string',+ default: '',+ placeholder: 'US',+ description: 'ISO country code for geo-targeting (e.g. US, GB, DE)',+ displayOptions: { show: { useProxy: [true] } }+ },+ {+ displayName: 'Proxy Provider',+ name: 'proxyProvider',+ type: 'string',+ default: '',+ placeholder: 'Auto-select',+ description: 'Specific provider name, or leave empty for auto-selection',+ displayOptions: { show: { useProxy: [true] } }}]},diff --git a/client/src/nodeDefinitions/proxyNodes.ts b/client/src/nodeDefinitions/proxyNodes.tsindex 86ab8b24..16a43439 100644--- a/client/src/nodeDefinitions/proxyNodes.ts+++ b/client/src/nodeDefinitions/proxyNodes.ts@@ -13,7 +13,7 @@ export const proxyNodes: Record<string, INodeTypeDescription> = {displayName: 'Proxy Request',name: 'proxyRequest',icon: '🛡',- group: ['proxy', 'api'],+ group: ['proxy', 'tool'],version: 1,description: 'Make HTTP requests through residential proxy providers with geo-targeting and failover',defaults: { name: 'Proxy Request', color: '#8B5CF6' },@@ -295,7 +295,7 @@ export const proxyNodes: Record<string, INodeTypeDescription> = {displayName: 'Proxy Status',name: 'proxyStatus',icon: '📊',- group: ['proxy', 'utility'],+ group: ['proxy', 'tool'],version: 1,description: 'View proxy provider health, scores, and usage statistics',defaults: { name: 'Proxy Status', color: '#6366F1' },diff --git a/client/src/nodeDefinitions/utilityNodes.ts b/client/src/nodeDefinitions/utilityNodes.tsindex 91befabb..f696708b 100644--- a/client/src/nodeDefinitions/utilityNodes.ts+++ b/client/src/nodeDefinitions/utilityNodes.ts@@ -64,6 +64,42 @@ export const utilityNodes: Record<string, INodeTypeDescription> = {name: 'timeout',type: 'number',default: 30+ },+ {+ displayName: 'Use Proxy',+ name: 'useProxy',+ type: 'boolean',+ default: false,+ description: 'Route request through a configured proxy provider'+ },+ {+ displayName: 'Proxy Country',+ name: 'proxyCountry',+ type: 'string',+ default: '',+ placeholder: 'US',+ description: 'ISO country code for geo-targeting (e.g. US, GB, DE)',+ displayOptions: { show: { useProxy: [true] } }+ },+ {+ displayName: 'Proxy Provider',+ name: 'proxyProvider',+ type: 'string',+ default: '',+ placeholder: 'Auto-select',+ description: 'Specific provider name, or leave empty for auto-selection',+ displayOptions: { show: { useProxy: [true] } }+ },+ {+ displayName: 'Session Type',+ name: 'sessionType',+ type: 'options',+ default: 'rotating',+ options: [+ { name: 'Rotating (new IP per request)', value: 'rotating' },+ { name: 'Sticky (same IP)', value: 'sticky' }+ ],+ displayOptions: { show: { useProxy: [true] } }}]},diff --git a/client/src/services/executionService.ts b/client/src/services/executionService.tsindex 76161919..ee33af92 100644--- a/client/src/services/executionService.ts+++ b/client/src/services/executionService.ts@@ -238,7 +238,11 @@ export class ExecutionService {// Search API nodes...SEARCH_NODE_TYPES,// Telegram Nodes- ...TELEGRAM_NODE_TYPES+ ...TELEGRAM_NODE_TYPES,+ // Proxy Nodes+ 'proxyRequest',+ 'proxyConfig',+ 'proxyStatus'];return supportedTypes.includes(nodeType);diff --git a/docs-internal/node_creation.md b/docs-internal/node_creation.mdindex 1a8f56d9..5ed6febb 100644--- a/docs-internal/node_creation.md+++ b/docs-internal/node_creation.md@@ -26,7 +26,7 @@ This guide explains how to create new nodes for MachinaOs, covering frontend def## Node Types Overview-MachinaOs supports 108 nodes across 18 categories:+MachinaOs supports 111 nodes across 19 categories:| Category | Visual Component | Example Nodes | Count ||----------|-----------------|---------------|-------|@@ -46,6 +46,7 @@ MachinaOs supports 108 nodes across 18 categories:| **Social** | SquareNode | socialReceive, socialSend | 2 || **Location/Maps** | SquareNode | createMap, addLocations, showNearbyPlaces | 3 || **Utility** | SquareNode | httpRequest, webhookTrigger, webhookResponse, chatTrigger, console | 5 |+| **Proxy** | SquareNode | proxyRequest, proxyConfig, proxyStatus | 3 || **Code** | SquareNode | pythonExecutor, javascriptExecutor | 2 || **Chat** | SquareNode | chatSend, chatHistory | 2 || **Document** | SquareNode | httpScraper, fileDownloader, documentParser, textChunker, embeddingGenerator, vectorStore | 6 |diff --git a/docs-internal/workflow-schema.md b/docs-internal/workflow-schema.mdindex 9e46abb4..9eb82835 100644--- a/docs-internal/workflow-schema.md+++ b/docs-internal/workflow-schema.md@@ -59,7 +59,7 @@ A workflow JSON document contains:}```-## Supported Node Types (64 Total)+## Supported Node Types (67 Total)### Workflow Nodes (1 node)- `start` - Workflow entry point with initial data@@ -149,12 +149,17 @@ Dual-purpose nodes (workflow + AI tool). Defined in `searchNodes.ts`:- `mediaControl` - Media playback, volume### Utility Nodes (5 nodes)-- `httpRequest` - HTTP requests (GET, POST, PUT, DELETE, PATCH)+- `httpRequest` - HTTP requests (GET, POST, PUT, DELETE, PATCH) with optional proxy support (`useProxy: true`)- `webhookTrigger` - Incoming HTTP webhook trigger at `/webhook/{path}`- `webhookResponse` - Custom response to webhook caller- `chatTrigger` - Console message input trigger- `console` - Debug logging output+### Proxy Nodes (3 nodes)+- `proxyRequest` - HTTP requests through residential proxy providers with geo-targeting and failover+- `proxyConfig` - Configure proxy providers, credentials, and routing rules+- `proxyStatus` - View proxy provider health, scores, and usage statistics+### Code Nodes (2 nodes)- `pythonExecutor` - Python code execution with input_data access- `javascriptExecutor` - JavaScript code executiondiff --git a/scripts/dev.js b/scripts/dev.jsindex 2049844e..76ace58b 100644--- a/scripts/dev.js+++ b/scripts/dev.js@@ -71,14 +71,13 @@ async function main() {}// Start services- log('Starting services...');- log('Press Ctrl+C to stop\n');+ log('Spawning services...');const clientDist = resolve(ROOT, 'client', 'dist', 'index.html');const hasVite = existsSync(resolve(ROOT, 'node_modules', 'vite'))|| existsSync(resolve(ROOT, 'client', 'node_modules', 'vite'));const isProduction = existsSync(clientDist) && !hasVite;- log(`Mode: ${isProduction ? 'Production' : 'Development'}`);+ log(`Client: ${isProduction ? 'Static server' : 'Vite dev server'}`);const services = [];if (isProduction) {@@ -90,13 +89,41 @@ async function main() {if (!skipWhatsApp) services.push('npm:whatsapp:api');if (config.temporalEnabled) services.push('npm:temporal:worker');+ // Ready-detection patterns for each service+ const readyPatterns = [+ { name: 'Client', pattern: /ready in|VITE.*ready|Client:\s*http/i },+ { name: 'Backend', pattern: /Application startup complete|Uvicorn running/i },+ ];+ if (!skipWhatsApp) {+ readyPatterns.push({ name: 'WhatsApp', pattern: /listening on|WhatsApp.*ready|API.*started|:9400/i });+ }+ const readySet = new Set();+ const totalExpected = readyPatterns.length;+const proc = spawn('npx', ['concurrently', '--raw', '--kill-others', ...services], {cwd: ROOT,- stdio: 'inherit',+ stdio: ['inherit', 'pipe', 'pipe'],shell: true,env: { ...process.env, FORCE_COLOR: '1' }});+ proc.stdout.on('data', (data) => {+ process.stdout.write(data);+ const text = data.toString();+ for (const { name, pattern } of readyPatterns) {+ if (!readySet.has(name) && pattern.test(text)) {+ readySet.add(name);+ log(`${name} ready`);+ if (readySet.size === totalExpected) {+ log(`All services ready -- http://localhost:${config.clientPort}`);+ console.log('');+ }+ }+ }+ });++ proc.stderr.on('data', (data) => process.stderr.write(data));+process.on('SIGINT', () => proc.kill('SIGINT'));process.on('SIGTERM', () => proc.kill('SIGTERM'));proc.on('close', (code) => {diff --git a/scripts/start.js b/scripts/start.jsindex f6d669cf..cdbe3b94 100755--- a/scripts/start.js+++ b/scripts/start.js@@ -14,8 +14,12 @@ import {loadEnvConfig,ensureEnvFile,killPort,+ createLogger,} from './utils.js';+const START_TIME = Date.now();+const log = createLogger(START_TIME);+const args = process.argv.slice(2);const isVerbose = args.includes('--verbose') || args.includes('-v');const skipWhatsApp = args.includes('--skip-whatsapp');@@ -45,9 +49,11 @@ async function main() {ensureEnvFile();// Free ports+ log('Freeing ports...');for (const port of config.allPorts) {await killPort(port);}+ log('Ports ready');// Services: static client, backend (uvicorn), whatsapp, temporalconst services = [];@@ -56,15 +62,44 @@ async function main() {if (!skipWhatsApp) services.push('npm:whatsapp:api');if (config.temporalEnabled) services.push('npm:temporal:worker');+ // Ready-detection patterns for each service+ const readyPatterns = [+ { name: 'Client', pattern: /ready in|VITE.*ready|Client:\s*http/i },+ { name: 'Backend', pattern: /Application startup complete|Uvicorn running/i },+ ];+ if (!skipWhatsApp) {+ readyPatterns.push({ name: 'WhatsApp', pattern: /listening on|WhatsApp.*ready|API.*started|:9400/i });+ }+ const readySet = new Set();+ const totalExpected = readyPatterns.length;++ function checkReady(text) {+ for (const { name, pattern } of readyPatterns) {+ if (!readySet.has(name) && pattern.test(text)) {+ readySet.add(name);+ log(`${name} ready`);+ if (readySet.size === totalExpected) {+ log(`All services ready`);+ }+ }+ }+ }+if (isVerbose) {console.log('\n=== MachinaOS Starting (verbose) ===\n');const proc = spawn('npx', ['concurrently', '--raw', '--kill-others', ...services], {cwd: ROOT,- stdio: 'inherit',+ stdio: ['inherit', 'pipe', 'pipe'],shell: true,env: { ...process.env, FORCE_COLOR: '1' },});+ proc.stdout.on('data', (data) => {+ process.stdout.write(data);+ checkReady(data.toString());+ });+ proc.stderr.on('data', (data) => process.stderr.write(data));+process.on('SIGINT', () => proc.kill('SIGINT'));process.on('SIGTERM', () => proc.kill('SIGTERM'));proc.on('close', (code) => process.exit(code || 0));@@ -96,7 +131,9 @@ async function main() {const essential = /error|fatal|exception|failed|started|ready|listening|running|address already in use|application startup complete/i;proc.stdout.on('data', (data) => {- for (const line of data.toString().split('\n')) {+ const text = data.toString();+ checkReady(text);+ for (const line of text.split('\n')) {const trimmed = line.trim();if (trimmed && essential.test(trimmed)) {process.stdout.write(line + '\n');diff --git a/scripts/utils.js b/scripts/utils.jsindex 5a71aed6..2bbe5653 100644--- a/scripts/utils.js+++ b/scripts/utils.js@@ -27,7 +27,9 @@ export const isWSL = !isWindows && process.platform === 'linux' && ();// True when we should use Windows-style venv paths (Scripts/python.exe)-export const useWindowsVenv = isWindows || isWSL;+// WSL excluded: even with a Windows venv, WSL should prefer system python3+// for port management (Windows python.exe via interop gives wrong process info)+export const useWindowsVenv = isWindows && !isWSL;// Cached Python path (undefined = not checked, null = unavailable, string = path)let _pythonCmd;diff --git a/server/constants.py b/server/constants.pyindex 802d573b..abd1c097 100644--- a/server/constants.py+++ b/server/constants.py@@ -80,6 +80,23 @@ CONFIG_NODE_TYPES: FrozenSet[str] = (SKILL_NODE_TYPES # Skill nodes (connect to Zeenie's input-skill))+# =============================================================================+# PROXY NODE TYPES+# =============================================================================++PROXY_NODE_TYPES: FrozenSet[str] = frozenset([+ 'proxyRequest',+ 'proxyConfig',+ 'proxyStatus',+])++# Dual-purpose proxy nodes (workflow node + AI tool)+PROXY_TOOL_TYPES: FrozenSet[str] = frozenset([+ 'proxyRequest',+ 'proxyConfig',+ 'proxyStatus',+])+# =============================================================================# SEARCH NODE TYPES# =============================================================================diff --git a/server/core/config.py b/server/core/config.pyindex e5083602..adcd8c4b 100644--- a/server/core/config.py+++ b/server/core/config.py@@ -67,6 +67,11 @@ class Settings(BaseSettings):# AI Proxy Configuration (Ollama-style proxy)ai_proxy_default_port: int = Field(default=11434, env="AI_PROXY_DEFAULT_PORT")+ # Residential Proxy Configuration+ proxy_enabled: bool = Field(default=False, env="PROXY_ENABLED")+ proxy_budget_daily_usd: float = Field(default=50.0, env="PROXY_BUDGET_DAILY_USD")+ proxy_default_country: str = Field(default="", env="PROXY_DEFAULT_COUNTRY")+# WebSocket Configurationwebsocket_url: str = Field(default="", env="WEBSOCKET_URL")websocket_api_key: Optional[str] = Field(default=None, env="WEBSOCKET_API_KEY")diff --git a/server/core/container.py b/server/core/container.pyindex 84661c81..90ba36b0 100644--- a/server/core/container.py+++ b/server/core/container.py@@ -1,5 +1,15 @@"""Dependency injection container for the application."""+import time as _time++_ct0 = _time.perf_counter()+++def _clog(msg):+ elapsed = (_time.perf_counter() - _ct0) * 1000+ print(f" container: {msg} ({elapsed:.0f}ms)", flush=True)++from dependency_injector import containers, providersfrom core.config import Settings@@ -7,14 +17,18 @@ from core.database import Databasefrom core.cache import CacheServicefrom core.encryption import EncryptionServicefrom core.credentials_database import CredentialsDatabase+_clog("core imports done")from services.ai import AIService+_clog("AIService imported")from services.maps import MapsServicefrom services.workflow import WorkflowService+_clog("WorkflowService imported")from services.auth import AuthServicefrom services.text import TextServicefrom services.android_service import AndroidServicefrom services.user_auth import UserAuthServicefrom services.compaction import init_compaction_service+_clog("all service imports done")# Temporal is optional - import with fallbacktry:diff --git a/server/core/database.py b/server/core/database.pyindex 67d46111..442338ae 100644--- a/server/core/database.py+++ b/server/core/database.py@@ -13,7 +13,8 @@ from models.database import (NodeParameter, Workflow, Execution, APIKey, APIKeyValidation, NodeOutput,ConversationMessage, ToolSchema, UserSkill, ChatMessage, UserSettings,TokenUsageMetric, CompactionEvent, SessionTokenState, ProviderDefaults,- AgentTeam, TeamMember, TeamTask, AgentMessage, GoogleConnection+ AgentTeam, TeamMember, TeamTask, AgentMessage, GoogleConnection,+ ProxyProviderConfig, ProxyRoutingRule)from models.cache import CacheEntry # SQLite-backed cache for Redis alternativefrom core.logging import get_logger@@ -2579,4 +2580,187 @@ class Database:return Falseexcept Exception as e:logger.error(f"Failed to update Google last used: {e}")+ return False++ # ============================================================================+ # Proxy Provider CRUD+ # ============================================================================++ async def save_proxy_provider(self, data: Dict[str, Any]) -> bool:+ """Save or update a proxy provider configuration (upsert by name)."""+ try:+ name = data.get("name")+ if not name:+ logger.error("Cannot save proxy provider without name")+ return False++ async with self.get_session() as session:+ stmt = select(ProxyProviderConfig).where(ProxyProviderConfig.name == name)+ result = await session.execute(stmt)+ existing = result.scalar_one_or_none()++ if existing:+ for field in ["enabled", "priority", "cost_per_gb", "gateway_host", "gateway_port", "url_template"]:+ if field in data:+ setattr(existing, field, data[field])+ existing.updated_at = datetime.now(timezone.utc)+ else:+ existing = ProxyProviderConfig(+ name=name,+ enabled=data.get("enabled", True),+ priority=data.get("priority", 50),+ cost_per_gb=data.get("cost_per_gb", 0.0),+ gateway_host=data.get("gateway_host", ""),+ gateway_port=data.get("gateway_port", 0),+ url_template=data.get("url_template", "{}"),+ )+ session.add(existing)++ await session.commit()+ logger.info(f"[DB] Proxy provider saved: {name}")+ return True++ except Exception as e:+ logger.error(f"Failed to save proxy provider: {e}")+ return False++ async def get_proxy_provider(self, name: str) -> Optional[Dict[str, Any]]:+ """Get a single proxy provider by name."""+ try:+ async with self.get_session() as session:+ stmt = select(ProxyProviderConfig).where(ProxyProviderConfig.name == name)+ result = await session.execute(stmt)+ p = result.scalar_one_or_none()++ if not p:+ return None++ return {+ "id": p.id,+ "name": p.name,+ "enabled": p.enabled,+ "priority": p.priority,+ "cost_per_gb": p.cost_per_gb,+ "gateway_host": p.gateway_host,+ "gateway_port": p.gateway_port,+ "url_template": p.url_template,+ "created_at": p.created_at.isoformat() if p.created_at else None,+ "updated_at": p.updated_at.isoformat() if p.updated_at else None,+ }++ except Exception as e:+ logger.error(f"Failed to get proxy provider: {e}")+ return None++ async def get_proxy_providers(self) -> List[Dict[str, Any]]:+ """Get all proxy provider configurations."""+ try:+ async with self.get_session() as session:+ stmt = select(ProxyProviderConfig).order_by(ProxyProviderConfig.priority)+ result = await session.execute(stmt)+ providers = result.scalars().all()++ return [+ {+ "id": p.id,+ "name": p.name,+ "enabled": p.enabled,+ "priority": p.priority,+ "cost_per_gb": p.cost_per_gb,+ "gateway_host": p.gateway_host,+ "gateway_port": p.gateway_port,+ "url_template": p.url_template,+ "created_at": p.created_at.isoformat() if p.created_at else None,+ "updated_at": p.updated_at.isoformat() if p.updated_at else None,+ }+ for p in providers+ ]++ except Exception as e:+ logger.error(f"Failed to get proxy providers: {e}")+ return []++ async def delete_proxy_provider(self, name: str) -> bool:+ """Delete a proxy provider by name."""+ try:+ async with self.get_session() as session:+ stmt = select(ProxyProviderConfig).where(ProxyProviderConfig.name == name)+ result = await session.execute(stmt)+ provider = result.scalar_one_or_none()++ if provider:+ await session.delete(provider)+ await session.commit()+ logger.info(f"[DB] Proxy provider deleted: {name}")++ return True++ except Exception as e:+ logger.error(f"Failed to delete proxy provider: {e}")+ return False++ # ============================================================================+ # Proxy Routing Rules CRUD+ # ============================================================================++ async def save_proxy_routing_rule(self, data: Dict[str, Any]) -> bool:+ """Save a new proxy routing rule."""+ try:+ async with self.get_session() as session:+ rule = ProxyRoutingRule(+ domain_pattern=data.get("domain_pattern", ""),+ preferred_providers=data.get("preferred_providers", "[]"),+ required_country=data.get("required_country", ""),+ session_type=data.get("session_type", "rotating"),+ )+ session.add(rule)+ await session.commit()+ logger.info(f"[DB] Proxy routing rule saved: {data.get('domain_pattern')}")+ return True++ except Exception as e:+ logger.error(f"Failed to save proxy routing rule: {e}")+ return False++ async def get_proxy_routing_rules(self) -> List[Dict[str, Any]]:+ """Get all proxy routing rules."""+ try:+ async with self.get_session() as session:+ stmt = select(ProxyRoutingRule).order_by(ProxyRoutingRule.id)+ result = await session.execute(stmt)+ rules = result.scalars().all()++ return [+ {+ "id": r.id,+ "domain_pattern": r.domain_pattern,+ "preferred_providers": r.preferred_providers,+ "required_country": r.required_country,+ "session_type": r.session_type,+ "created_at": r.created_at.isoformat() if r.created_at else None,+ }+ for r in rules+ ]++ except Exception as e:+ logger.error(f"Failed to get proxy routing rules: {e}")+ return []++ async def delete_proxy_routing_rule(self, rule_id: int) -> bool:+ """Delete a proxy routing rule by ID."""+ try:+ async with self.get_session() as session:+ stmt = select(ProxyRoutingRule).where(ProxyRoutingRule.id == rule_id)+ result = await session.execute(stmt)+ rule = result.scalar_one_or_none()++ if rule:+ await session.delete(rule)+ await session.commit()+ logger.info(f"[DB] Proxy routing rule deleted: {rule_id}")++ return True++ except Exception as e:+ logger.error(f"Failed to delete proxy routing rule: {e}")return False\ No newline at end of filediff --git a/server/main.py b/server/main.pyindex 3c7c7f88..5fc48a75 100644--- a/server/main.py+++ b/server/main.py@@ -4,6 +4,15 @@ Modern FastAPI backend for React Flow workflow automation platform.Refactored with dependency injection, modular services, and clean architecture."""+import time as _time+_t0 = _time.perf_counter()+++def _startup_log(msg):+ elapsed = _time.perf_counter() - _t0+ print(f" [{elapsed:6.2f}s] {msg}", flush=True)++# Performance: Install uvloop if available (Linux/macOS only)try:import uvloop@@ -19,14 +28,19 @@ from contextlib import asynccontextmanager# Adding custom handlers that raise KeyboardInterrupt causes cascading errors# during async operations (WebSocket handlers, logging, etc.).+_startup_log("Importing FastAPI...")from fastapi import FastAPIfrom fastapi.middleware.cors import CORSMiddlewarefrom fastapi.responses import ORJSONResponse+_startup_log("Importing DI container + all services...")from core.container import container+_startup_log("Importing settings + logging...")from core.config import Settingsfrom core.logging import configure_logging, get_logger, setup_websocket_logging, shutdown_websocket_logging+_startup_log("Importing routers...")from routers import workflow, database, maps, nodejs_compat, android, websocket, webhook, auth, twitter, google+_startup_log("All imports complete")# Initialize settings and loggingsettings = Settings()@@ -48,7 +62,7 @@ logging.getLogger("watchfiles").setLevel(logging.WARNING)async def lifespan(app: FastAPI):"""Application lifespan management."""# Startup- logger.info("Starting React Flow Python Services")+ _startup_log("Lifespan startup begin")# Wire dependency injectioncontainer.wire(modules=[@@ -68,6 +82,7 @@ async def lifespan(app: FastAPI):# Start servicesawait container.database().startup()await container.cache().startup()+ _startup_log("Database + cache started")# Initialize credentials database (creates tables if not exist)credentials_db = container.credentials_database()@@ -80,6 +95,7 @@ async def lifespan(app: FastAPI):if not encryption.is_initialized():encryption.initialize(settings.api_key_encryption_key, salt)logger.info("Encryption service initialized")+ _startup_log("Credentials + encryption initialized")# Initialize event waiter with cache service for Redis Streams supportfrom services import event_waiter@@ -133,6 +149,7 @@ async def lifespan(app: FastAPI):compaction_svc = container.compaction_service() # Trigger singleton initializationcompaction_svc.set_ai_service(container.ai_service())logger.info("Compaction service initialized")+ _startup_log("Compaction service ready")# Initialize model registry servicefrom services.model_registry import get_model_registry@@ -156,6 +173,16 @@ async def lifespan(app: FastAPI):init_agent_team_service(container.database(), get_status_broadcaster())logger.info("Agent team service initialized")+ # Initialize proxy service (loads providers from DB, reads credentials)+ from services.proxy.service import init_proxy_service+ proxy_svc = init_proxy_service(+ auth_service=container.auth_service(),+ database=container.database(),+ settings=settings,+ )+ await proxy_svc.startup()+ _startup_log("Proxy service initialized")+# Record startup time for health reportingset_startup_time()@@ -203,7 +230,8 @@ async def lifespan(app: FastAPI):logger.warning(f"Temporal not available (optional): {str(e)}")logger.info("Continuing without Temporal - using local parallel/sequential execution")- logger.info("Services started successfully")+ _startup_log("All services initialized")+ print("Application startup complete", flush=True)yield# Shutdown@@ -224,6 +252,12 @@ async def lifespan(app: FastAPI):except Exception:pass+ # Shutdown proxy service+ from services.proxy.service import get_proxy_service+ _proxy_svc = get_proxy_service()+ if _proxy_svc:+ await _proxy_svc.shutdown()+# Close Android relay client (prevents "Unclosed client session" warning)from services.android.manager import close_relay_clientawait close_relay_client(clear_stored_session=False)diff --git a/server/models/database.py b/server/models/database.pyindex 7eb05244..3a0fdb7a 100644--- a/server/models/database.py+++ b/server/models/database.py@@ -500,6 +500,53 @@ class AgentMessage(SQLModel, table=True):)+class ProxyProviderConfig(SQLModel, table=True):+ """Proxy provider configuration stored in database.++ Each row represents a configured residential proxy provider with+ gateway endpoint, url_template for parameter encoding, and metadata.+ """++ __tablename__ = "proxy_providers"++ id: Optional[int] = Field(default=None, primary_key=True)+ name: str = Field(unique=True, index=True, max_length=255)+ enabled: bool = Field(default=True)+ priority: int = Field(default=50) # Lower = preferred+ cost_per_gb: float = Field(default=0.0)+ gateway_host: str = Field(default="", max_length=500)+ gateway_port: int = Field(default=0)+ url_template: str = Field(default="{}", max_length=5000) # JSON template config+ created_at: datetime = Field(+ default_factory=lambda: datetime.now(timezone.utc),+ sa_column=Column(DateTime(timezone=True), server_default=func.now())+ )+ updated_at: datetime = Field(+ default_factory=lambda: datetime.now(timezone.utc),+ sa_column=Column(DateTime(timezone=True), onupdate=func.now())+ )+++class ProxyRoutingRule(SQLModel, table=True):+ """Domain-based routing rules for proxy providers.++ Routes specific domain patterns through preferred providers+ with optional geo-targeting and session type requirements.+ """++ __tablename__ = "proxy_routing_rules"++ id: Optional[int] = Field(default=None, primary_key=True)+ domain_pattern: str = Field(max_length=500) # e.g., *.linkedin.com+ preferred_providers: str = Field(default="[]", max_length=2000) # JSON array+ required_country: str = Field(default="", max_length=10)+ session_type: str = Field(default="rotating", max_length=20)+ created_at: datetime = Field(+ default_factory=lambda: datetime.now(timezone.utc),+ sa_column=Column(DateTime(timezone=True), server_default=func.now())+ )++class GoogleConnection(SQLModel, table=True):"""Google Workspace OAuth connections for customer access mode.diff --git a/server/services/ai.py b/server/services/ai.pyindex e3758a60..cf6f0b8e 100644--- a/server/services/ai.py+++ b/server/services/ai.py@@ -8,9 +8,21 @@ from datetime import datetimefrom typing import Dict, Any, List, Optional, Callable, Type, TypedDict, Annotated, Sequenceimport operator+_ai_t0 = time.perf_counter()+++def _ailog(msg):+ elapsed = (time.perf_counter() - _ai_t0) * 1000+ print(f" ai.py: {msg} ({elapsed:.0f}ms)", flush=True)+++_ailog("importing langchain_openai...")from langchain_openai import ChatOpenAI+_ailog("importing langchain_anthropic...")from langchain_anthropic import ChatAnthropic+_ailog("importing langchain_groq...")from langchain_groq import ChatGroq+_ailog("importing langchain_core.messages...")from langchain_core.messages import HumanMessage, SystemMessage, AIMessage, BaseMessage, ToolMessage# Lazy import for Google GenAI (google-generativeai init hangs on Windows/Python 3.13)@@ -26,15 +38,18 @@ def _get_google_genai_class():# Conditional import for Cerebras (requires Python <3.13)CEREBRAS_IMPORT_ERROR = Nonetry:+ _ailog("importing langchain_cerebras...")from langchain_cerebras import ChatCerebrasCEREBRAS_AVAILABLE = Trueexcept ImportError as e:ChatCerebras = NoneCEREBRAS_AVAILABLE = FalseCEREBRAS_IMPORT_ERROR = str(e)+_ailog("importing langgraph + pydantic...")from langchain_core.tools import StructuredToolfrom langgraph.graph import StateGraph, ENDfrom pydantic import BaseModel, Field, create_model+_ailog("all LangChain imports done")import jsonfrom core.config import Settings@@ -815,6 +830,64 @@ def build_agent_graph(chat_model, tools: List = None, tool_executor: Callable =return graph.compile()+def _build_skill_system_prompt(skill_data: List[Dict[str, Any]], log_prefix: str = "[Agent]") -> tuple:+ """Build skill injection text for the system message.++ Personality skills (names ending in '-personality') get their FULL SKILL.md+ instructions injected. All other skills get brief registry descriptions only.++ Args:+ skill_data: List of skill entries from _collect_agent_connections.+ log_prefix: Log prefix for debug messages.++ Returns:+ Tuple of (prompt_text, has_personality). prompt_text is the string to+ append to system_message. has_personality indicates whether any+ personality skills were found (used to drop the default system message).+ """+ if not skill_data:+ return "", False++ from services.skill_loader import get_skill_loader++ skill_loader = get_skill_loader()+ skill_loader.scan_skills()++ personality_blocks = []+ non_personality_names = []++ for skill_info in skill_data:+ skill_name = skill_info.get('skill_name') or skill_info.get('node_type', '').replace('Skill', '-skill').lower()+ if skill_name.endswith('skill') and '-' not in skill_name:+ skill_name = skill_name[:-5] + '-skill'++ if skill_name.endswith('-personality'):+ instructions = skill_info.get('parameters', {}).get('instructions', '')+ if instructions:+ personality_blocks.append(instructions)+ logger.debug(f"{log_prefix} Personality skill injected (full): {skill_name}")+ else:+ logger.warning(f"{log_prefix} Personality skill {skill_name} has no instructions")+ else:+ non_personality_names.append(skill_name)+ logger.debug(f"{log_prefix} Skill detected: {skill_name}")++ parts = []++ for block in personality_blocks:+ parts.append(block)++ if non_personality_names:+ registry_prompt = skill_loader.get_registry_prompt(non_personality_names)+ if registry_prompt:+ parts.append(registry_prompt)++ if parts:+ logger.debug(f"{log_prefix} Enhanced system message: {len(personality_blocks)} personality, {len(non_personality_names)} standard skills")++ return "\n\n".join(parts), len(personality_blocks) > 0++class AIService:"""AI model service for LangChain operations."""@@ -1493,29 +1566,13 @@ class AIService:prompt = parameters.get('prompt', 'Hello')system_message = parameters.get('systemMessage', 'You are a helpful assistant')- # Load skills and enhance system message with SKILL.md context- # Skills provide instructions/context - actual tools come from tool nodes- if skill_data:- from services.skill_loader import get_skill_loader-- skill_loader = get_skill_loader()- skill_loader.scan_skills()-- # Extract skill names from connected skill nodes- skill_names = []- for skill_info in skill_data:- skill_name = skill_info.get('skill_name') or skill_info.get('node_type', '').replace('Skill', '-skill').lower()- # Convert node type to skill name (e.g., 'whatsappSkill' -> 'whatsapp-skill')- if skill_name.endswith('skill') and '-' not in skill_name:- skill_name = skill_name[:-5] + '-skill' # whatsappskill -> whatsapp-skill- skill_names.append(skill_name)- logger.debug(f"[AIAgent] Skill detected: {skill_name}")-- # Add skill SKILL.md content to system message- skill_prompt = skill_loader.get_registry_prompt(skill_names)- if skill_prompt:+ # Inject skills: personality skills get full instructions, others get brief descriptions+ skill_prompt, has_personality = _build_skill_system_prompt(skill_data, log_prefix="[AIAgent]")+ if skill_prompt:+ if has_personality:+ system_message = skill_prompt+ else:system_message = f"{system_message}\n\n{skill_prompt}"- logger.debug(f"[AIAgent] Enhanced system message with {len(skill_names)} skill contexts")# Flatten options collection from frontendoptions = parameters.get('options', {})@@ -1656,6 +1713,15 @@ class AIService:tool_configs[check_tool.name] = check_configlogger.debug("[LangGraph] Auto-injected check_delegated_tasks tool")+ # Add delegation guidance to system message+ delegate_names = [n for n in tool_configs if n.startswith('delegate_to_')]+ system_message += (+ "\n\n## Agent Delegation\n"+ "When delegating to sub-agents, use 'task' for the mission directive "+ "(role and goal) and 'context' for input data the agent needs to work with.\n"+ f"Available agents: {', '.join(delegate_names)}"+ )+# Create tool executor callbackasync def tool_executor(tool_name: str, tool_args: Dict) -> Any:"""Execute a tool by name."""@@ -1947,29 +2013,13 @@ class AIService:prompt = parameters.get('prompt', 'Hello')system_message = parameters.get('systemMessage', 'You are a helpful assistant')- # Load skills and enhance system message with SKILL.md context- # Skills only provide instructions/context - actual tools come from direct tool nodes- if skill_data:- from services.skill_loader import get_skill_loader-- skill_loader = get_skill_loader()- skill_loader.scan_skills()-- # Extract skill names from connected skill nodes- skill_names = []- for skill_info in skill_data:- skill_name = skill_info.get('skill_name') or skill_info.get('node_type', '').replace('Skill', '-skill').lower()- # Convert node type to skill name (e.g., 'whatsappSkill' -> 'whatsapp-skill')- if skill_name.endswith('skill') and '-' not in skill_name:- skill_name = skill_name[:-5] + '-skill' # whatsappskill -> whatsapp-skill- skill_names.append(skill_name)- logger.debug(f"[ChatAgent] Skill detected: {skill_name}")-- # Add skill SKILL.md content to system message- skill_prompt = skill_loader.get_registry_prompt(skill_names)- if skill_prompt:+ # Inject skills: personality skills get full instructions, others get brief descriptions+ skill_prompt, has_personality = _build_skill_system_prompt(skill_data, log_prefix="[ChatAgent]")+ if skill_prompt:+ if has_personality:+ system_message = skill_prompt+ else:system_message = f"{system_message}\n\n{skill_prompt}"- logger.debug(f"[ChatAgent] Enhanced system message with {len(skill_names)} skill contexts")# Build tools from tool_data using same method as AI Agent# This supports ALL tool types: calculatorTool, currentTimeTool, duckduckgoSearch, androidTool, httpRequest@@ -2005,6 +2055,15 @@ class AIService:tool_node_configs[check_tool.name] = check_configlogger.debug("[ChatAgent] Auto-injected check_delegated_tasks tool")+ # Add delegation guidance to system message+ delegate_names = [n for n in tool_node_configs if n.startswith('delegate_to_')]+ system_message += (+ "\n\n## Agent Delegation\n"+ "When delegating to sub-agents, use 'task' for the mission directive "+ "(role and goal) and 'context' for input data the agent needs to work with.\n"+ f"Available agents: {', '.join(delegate_names)}"+ )+logger.debug(f"[ChatAgent] Total tools available: {len(all_tools)}")# Debug: log all tool schemas to verify they're correctfor t in all_tools:@@ -2436,6 +2495,10 @@ class AIService:'sheets': 'google_sheets','tasks': 'google_tasks','contacts': 'google_contacts',+ # Proxy (dual-purpose tools)+ 'proxyRequest': 'proxy_request',+ 'proxyConfig': 'proxy_config',+ 'proxyStatus': 'proxy_status',}DEFAULT_TOOL_DESCRIPTIONS = {'calculatorTool': 'Perform mathematical calculations. Operations: add, subtract, multiply, divide, power, sqrt, mod, abs',@@ -2495,6 +2558,10 @@ class AIService:'sheets': 'Read and write Google Sheets data. Operations: read (get range), write (set range), append (add rows).','tasks': 'Manage Google Tasks. Operations: create (new task), list (find tasks), complete (mark done), update (modify task), delete (remove task).','contacts': 'Manage Google Contacts. Operations: create (new contact), list (browse), search (find by name/email/phone), get (details by resource name), update (modify), delete (remove).',+ # Proxy (dual-purpose tools)+ 'proxyRequest': 'Make HTTP requests through residential proxy providers with geo-targeting, session control, and automatic failover. Supports GET, POST, PUT, DELETE, PATCH methods.',+ 'proxyConfig': 'Manage proxy providers and routing rules. Operations: list_providers, add_provider, update_provider, remove_provider, set_credentials, test_provider, get_stats, add_routing_rule, list_routing_rules, remove_routing_rule.',+ 'proxyStatus': 'Get proxy provider health stats, scores, and usage statistics. Returns enabled status, provider list with health scores, and aggregated stats.',}try:@@ -2633,6 +2700,7 @@ class AIService:url: str = Field(description="URL path or full URL to request")method: str = Field(default="GET", description="HTTP method: GET, POST, PUT, DELETE")body: Optional[Dict[str, Any]] = Field(default=None, description="Request body as JSON object")+ useProxy: bool = Field(default=False, description="Route request through a configured residential proxy")return HttpRequestSchema@@ -3292,15 +3360,17 @@ class AIService:"""Delegate a task to another AI Agent (non-blocking).The child agent works independently in the background.+ The 'task' becomes the agent's mission directive (system message).+ The 'context' becomes the agent's input data (user prompt).Returns a task_id immediately. Use 'check_delegated_tasks'tool to check status and retrieve results when ready."""task: str = Field(- description=f"The task/instruction to delegate to '{agent_label}'. Be specific about what you want done."+ description=f"The mission directive for '{agent_label}'. Describe the role and goal clearly, e.g. 'You are a coding assistant. Write a Python script that processes the given CSV data.'")context: Optional[str] = Field(default=None,- description="Additional context or data the child agent needs to complete the task"+ description="Input data or specific details the agent needs to work with, e.g. file contents, user requirements, or parameters")return DelegateToAgentSchema@@ -3333,6 +3403,129 @@ class AIService:return ApifyActorSchema+ # Proxy Request tool schema (dual-purpose: workflow node + AI tool)+ if node_type == 'proxyRequest':+ class ProxyRequestSchema(BaseModel):+ """Make HTTP requests through residential proxy providers with geo-targeting and failover."""+ url: str = Field(+ description="Target URL to request through the proxy"+ )+ method: Optional[str] = Field(+ default="GET",+ description="HTTP method: GET, POST, PUT, DELETE, PATCH"+ )+ headers: Optional[str] = Field(+ default=None,+ description="JSON string of HTTP headers (e.g. '{\"Authorization\": \"Bearer token\"}')"+ )+ body: Optional[str] = Field(+ default=None,+ description="Request body (for POST/PUT/PATCH). JSON string or plain text."+ )+ proxyProvider: Optional[str] = Field(+ default=None,+ description="Provider name to use, or omit for auto-selection (best health score)"+ )+ proxyCountry: Optional[str] = Field(+ default=None,+ description="ISO 3166-1 alpha-2 country code for geo-targeting (e.g. US, GB, DE)"+ )+ sessionType: Optional[str] = Field(+ default="rotating",+ description="Session type: 'rotating' (new IP per request) or 'sticky' (same IP)"+ )+ timeout: Optional[int] = Field(+ default=30,+ description="Request timeout in seconds (5-300)"+ )+ maxRetries: Optional[int] = Field(+ default=3,+ description="Max retry attempts with failover (0-10)"+ )++ return ProxyRequestSchema++ # Proxy Status tool schema (dual-purpose: workflow node + AI tool)+ if node_type == 'proxyStatus':+ class ProxyStatusSchema(BaseModel):+ """Get proxy provider health stats, scores, and usage statistics."""+ providerFilter: Optional[str] = Field(+ default=None,+ description="Filter by specific provider name, or omit for all providers"+ )++ return ProxyStatusSchema++ # Proxy Config tool schema (dual-purpose: workflow node + AI tool)+ if node_type == 'proxyConfig':+ class ProxyConfigSchema(BaseModel):+ """Manage proxy providers and routing rules.++ Operations: list_providers, add_provider, update_provider, remove_provider,+ set_credentials, test_provider, get_stats, add_routing_rule, list_routing_rules, remove_routing_rule.+ """+ operation: str = Field(+ description="Operation: list_providers, add_provider, update_provider, remove_provider, set_credentials, test_provider, get_stats, add_routing_rule, list_routing_rules, remove_routing_rule"+ )+ name: Optional[str] = Field(+ default=None,+ description="Provider name (required for add/update/remove/set_credentials/test_provider)"+ )+ gateway_host: Optional[str] = Field(+ default=None,+ description="Gateway hostname (for add_provider/update_provider)"+ )+ gateway_port: Optional[int] = Field(+ default=None,+ description="Gateway port (for add_provider/update_provider)"+ )+ url_template: Optional[str] = Field(+ default=None,+ description="JSON template config for proxy URL encoding (for add_provider/update_provider)"+ )+ username: Optional[str] = Field(+ default=None,+ description="Proxy username (for set_credentials)"+ )+ password: Optional[str] = Field(+ default=None,+ description="Proxy password (for set_credentials)"+ )+ enabled: Optional[bool] = Field(+ default=None,+ description="Enable/disable provider (for add_provider/update_provider)"+ )+ priority: Optional[int] = Field(+ default=None,+ description="Provider priority, lower=preferred (for add_provider/update_provider)"+ )+ cost_per_gb: Optional[float] = Field(+ default=None,+ description="Cost per GB in USD (for add_provider/update_provider)"+ )+ domain_pattern: Optional[str] = Field(+ default=None,+ description="Domain glob pattern (for add_routing_rule, e.g. '*.linkedin.com')"+ )+ preferred_providers: Optional[str] = Field(+ default=None,+ description="JSON array of provider names (for add_routing_rule)"+ )+ required_country: Optional[str] = Field(+ default=None,+ description="ISO country code (for add_routing_rule)"+ )+ session_type: Optional[str] = Field(+ default=None,+ description="Session type: 'rotating' or 'sticky' (for add_routing_rule)"+ )+ rule_id: Optional[int] = Field(+ default=None,+ description="Routing rule ID (for remove_routing_rule)"+ )++ return ProxyConfigSchema+# Generic schema for other nodesclass GenericToolSchema(BaseModel):"""Generic schema for tool arguments."""diff --git a/server/services/handlers/document.py b/server/services/handlers/document.pyindex 580d7a27..ff220742 100644--- a/server/services/handlers/document.py+++ b/server/services/handlers/document.py@@ -76,9 +76,25 @@ async def handle_http_scraper(else:urls_to_fetch.append((url, {}))- logger.info("[httpScraper] Starting", node_id=node_id, urls=len(urls_to_fetch))+ # Transparent proxy injection+ proxy_url = None+ if parameters.get('useProxy', False):+ try:+ from services.proxy.service import get_proxy_service+ proxy_svc = get_proxy_service()+ if proxy_svc and proxy_svc.is_enabled():+ proxy_url = await proxy_svc.get_proxy_url(url, parameters)+ except Exception as e:+ logger.warning("[httpScraper] Proxy lookup failed, proceeding without proxy", error=str(e))++ logger.info("[httpScraper] Starting", node_id=node_id, urls=len(urls_to_fetch),+ proxy=bool(proxy_url))++ client_kwargs: dict = {"timeout": 30, "follow_redirects": True}+ if proxy_url:+ client_kwargs["proxy"] = proxy_url- async with httpx.AsyncClient(timeout=30, follow_redirects=True) as client:+ async with httpx.AsyncClient(**client_kwargs) as client:for fetch_url, meta in urls_to_fetch:try:response = await client.get(fetch_url, headers=headers)diff --git a/server/services/handlers/http.py b/server/services/handlers/http.pyindex 181ab703..aac89edc 100644--- a/server/services/handlers/http.py+++ b/server/services/handlers/http.py@@ -3,12 +3,33 @@import jsonimport timefrom datetime import datetime-from typing import Dict, Any+from typing import Any, Dict, Optionalfrom core.logging import get_loggerlogger = get_logger(__name__)+async def _get_proxy_url_if_enabled(url: str, parameters: Dict[str, Any]) -> Optional[str]:+ """Return a proxy URL if useProxy is enabled and a provider is available.++ Returns None when proxy should not be used (disabled, no providers, etc.).+ Exceptions from the proxy service are logged and swallowed so that the+ request proceeds without a proxy rather than failing.+ """+ if not parameters.get('useProxy', False):+ return None++ try:+ from services.proxy.service import get_proxy_service+ proxy_svc = get_proxy_service()+ if not proxy_svc or not proxy_svc.is_enabled():+ return None+ return await proxy_svc.get_proxy_url(url, parameters)+ except Exception as e:+ logger.warning("Proxy URL lookup failed, proceeding without proxy", error=str(e))+ return None++async def handle_http_request(node_id: str,node_type: str,@@ -47,14 +68,20 @@ async def handle_http_request(except json.JSONDecodeError:headers = {}- logger.info("[HTTP Request] Executing", node_id=node_id, method=method, url=url)+ # Transparent proxy injection+ proxy_url = await _get_proxy_url_if_enabled(url, parameters)+ logger.info("[HTTP Request] Executing", node_id=node_id, method=method, url=url,+ proxy=bool(proxy_url))++ client_kwargs: Dict[str, Any] = {"timeout": timeout}+ if proxy_url:+ client_kwargs["proxy"] = proxy_url- async with httpx.AsyncClient() as client:+ async with httpx.AsyncClient(**client_kwargs) as client:kwargs = {'method': method,'url': url,'headers': headers,- 'timeout': timeout}# Add body for POST/PUT/PATCH@@ -77,7 +104,8 @@ async def handle_http_request("data": response_data,"headers": dict(response.headers),"url": str(response.url),- "method": method+ "method": method,+ "proxied": proxy_url is not None,}return {diff --git a/server/services/handlers/proxy.py b/server/services/handlers/proxy.pyindex 710a67d9..fe60e244 100644--- a/server/services/handlers/proxy.py+++ b/server/services/handlers/proxy.py@@ -91,7 +91,7 @@ async def handle_proxy_request("success": False,"node_id": node_id,"node_type": "proxyRequest",- "error": "Proxy service is not enabled. Set PROXY_ENABLED=true in .env",+ "error": "Proxy service not initialized. Use proxy_config tool to add a provider first.","execution_time": time.time() - start_time,"timestamp": datetime.now().isoformat(),}diff --git a/server/services/handlers/tools.py b/server/services/handlers/tools.pyindex d3512d7b..5e0ff7f6 100644--- a/server/services/handlers/tools.py+++ b/server/services/handlers/tools.py@@ -171,6 +171,14 @@ async def execute_tool(tool_name: str, tool_args: Dict[str, Any],if node_type == 'apifyActor':return await _execute_apify_actor(tool_args, config.get('parameters', {}))+ # Proxy nodes (dual-purpose: workflow node + AI tool)+ if node_type == 'proxyRequest':+ return await _execute_proxy_request(tool_args, config.get('parameters', {}), config)+ if node_type == 'proxyStatus':+ return await _execute_proxy_status(tool_args, config.get('parameters', {}))+ if node_type == 'proxyConfig':+ return await _execute_proxy_config(tool_args, config.get('parameters', {}))+# Built-in: Check delegated task results# Auto-injected when parent has delegation toolsif node_type == '_builtin_check_delegated_tasks':@@ -265,10 +273,27 @@ async def _execute_http_request(args: Dict[str, Any],except Exception:default_headers = {}- logger.debug(f"[HTTP Tool] {method} {full_url}")+ # Transparent proxy injection (useProxy from node params or LLM args)+ proxy_url = None+ use_proxy = args.get('useProxy', node_params.get('useProxy', False))+ if use_proxy:+ try:+ from services.proxy.service import get_proxy_service+ proxy_svc = get_proxy_service()+ if proxy_svc and proxy_svc.is_enabled():+ merged = {**node_params, **args}+ proxy_url = await proxy_svc.get_proxy_url(full_url, merged)+ except Exception as e:+ logger.warning(f"[HTTP Tool] Proxy lookup failed, proceeding without proxy: {e}")++ logger.debug(f"[HTTP Tool] {method} {full_url}", proxy=bool(proxy_url))try:- async with httpx.AsyncClient(timeout=30.0) as client:+ client_kwargs: dict = {"timeout": 30.0}+ if proxy_url:+ client_kwargs["proxy"] = proxy_url++ async with httpx.AsyncClient(**client_kwargs) as client:response = await client.request(method=method,url=full_url,@@ -286,7 +311,8 @@ async def _execute_http_request(args: Dict[str, Any],"status": response.status_code,"data": data,"url": full_url,- "method": method+ "method": method,+ "proxied": proxy_url is not None,}except httpx.TimeoutException:@@ -1358,6 +1384,251 @@ async def _execute_apify_actor(args: Dict[str, Any],)+async def _execute_proxy_request(args: Dict[str, Any],+ node_params: Dict[str, Any],+ config: Dict[str, Any]) -> Dict[str, Any]:+ """Execute proxy HTTP request as an AI tool.++ Delegates to the standalone proxy request handler.++ Args:+ args: LLM-provided arguments (url, method, headers, body, etc.)+ node_params: Node parameters+ config: Full tool config with context++ Returns:+ Request result dict+ """+ from services.handlers.proxy import handle_proxy_request++ # Merge LLM args over node params+ merged = {**node_params, **{k: v for k, v in args.items() if v is not None}}++ context = config.get('context', {})+ node_id = config.get('node_id', 'tool_proxy_request')++ result = await handle_proxy_request(node_id, 'proxyRequest', merged, context)+ return result.get('result', result)+++async def _execute_proxy_status(args: Dict[str, Any],+ node_params: Dict[str, Any]) -> Dict[str, Any]:+ """Execute proxy status check as an AI tool.++ Delegates to the standalone proxy status handler.++ Args:+ args: LLM-provided arguments (providerFilter)+ node_params: Node parameters++ Returns:+ Status result dict+ """+ from services.handlers.proxy import handle_proxy_status++ merged = {**node_params, **{k: v for k, v in args.items() if v is not None}}++ result = await handle_proxy_status('tool_proxy_status', 'proxyStatus', merged, {})+ return result.get('result', result)+++async def _execute_proxy_config(args: Dict[str, Any],+ node_params: Dict[str, Any]) -> Dict[str, Any]:+ """Execute proxy configuration operations.++ Manages proxy providers, credentials, and routing rules.++ Args:+ args: LLM-provided arguments (operation, name, etc.)+ node_params: Node parameters++ Returns:+ Operation result dict+ """+ import json as _json+ from core.container import container+ from services.proxy.service import get_proxy_service++ operation = args.get('operation', node_params.get('operation', ''))+ name = args.get('name', node_params.get('name', ''))+ proxy_svc = get_proxy_service()++ if operation == 'list_providers':+ providers = proxy_svc.get_providers() if proxy_svc else []+ return {"success": True, "operation": operation, "providers": [p.model_dump() for p in providers]}++ if operation == 'get_stats':+ stats = proxy_svc.get_stats() if proxy_svc else {}+ return {"success": True, "operation": operation, "stats": stats}++ if operation == 'list_routing_rules':+ rules = proxy_svc.get_routing_rules() if proxy_svc else []+ return {"success": True, "operation": operation, "rules": [r.model_dump() for r in rules]}++ if operation == 'add_provider':+ if not name:+ return {"success": False, "error": "Provider name is required"}+ gateway_host = args.get('gateway_host', node_params.get('gateway_host', ''))+ gateway_port = int(args.get('gateway_port', node_params.get('gateway_port', 0)))+ url_template_str = args.get('url_template', node_params.get('url_template', '{}'))+ cost_per_gb = float(args.get('cost_per_gb', node_params.get('cost_per_gb', 0)))+ enabled = args.get('enabled', node_params.get('enabled', True))+ priority = int(args.get('priority', node_params.get('priority', 50)))++ try:+ url_template = _json.loads(url_template_str) if isinstance(url_template_str, str) else url_template_str+ except _json.JSONDecodeError:+ return {"success": False, "error": f"Invalid url_template JSON: {url_template_str}"}++ db = container.database()+ await db.save_proxy_provider({+ "name": name,+ "enabled": enabled,+ "priority": priority,+ "cost_per_gb": cost_per_gb,+ "gateway_host": gateway_host,+ "gateway_port": gateway_port,+ "url_template": _json.dumps(url_template),+ })++ if proxy_svc:+ await proxy_svc.reload_providers()++ return {"success": True, "operation": operation, "name": name}++ if operation == 'update_provider':+ if not name:+ return {"success": False, "error": "Provider name is required"}+ db = container.database()+ existing = await db.get_proxy_provider(name)+ if not existing:+ return {"success": False, "error": f"Provider '{name}' not found"}++ updates = {}+ for field in ['gateway_host', 'gateway_port', 'cost_per_gb', 'enabled', 'priority']:+ val = args.get(field, node_params.get(field))+ if val is not None:+ updates[field] = val++ url_template_str = args.get('url_template', node_params.get('url_template'))+ if url_template_str:+ try:+ url_template = _json.loads(url_template_str) if isinstance(url_template_str, str) else url_template_str+ updates['url_template'] = _json.dumps(url_template)+ except _json.JSONDecodeError:+ return {"success": False, "error": f"Invalid url_template JSON"}++ if updates:+ merged = {**existing, **updates}+ await db.save_proxy_provider(merged)+ if proxy_svc:+ await proxy_svc.reload_providers()++ return {"success": True, "operation": operation, "name": name, "updated_fields": list(updates.keys())}++ if operation == 'remove_provider':+ if not name:+ return {"success": False, "error": "Provider name is required"}+ db = container.database()+ await db.delete_proxy_provider(name)+ if proxy_svc:+ await proxy_svc.reload_providers()+ return {"success": True, "operation": operation, "name": name}++ if operation == 'set_credentials':+ if not name:+ return {"success": False, "error": "Provider name is required"}+ username = args.get('username', node_params.get('username', ''))+ password = args.get('password', node_params.get('password', ''))+ if not username or not password:+ return {"success": False, "error": "Username and password are required"}++ auth_svc = container.auth_service()+ await auth_svc.store_api_key(f"proxy_{name}_username", username, [])+ await auth_svc.store_api_key(f"proxy_{name}_password", password, [])++ if proxy_svc:+ await proxy_svc.reload_providers()++ return {"success": True, "operation": operation, "name": name}++ if operation == 'test_provider':+ if not name:+ return {"success": False, "error": "Provider name is required"}+ if not proxy_svc:+ return {"success": False, "error": "Proxy service not enabled"}++ import time as _time+ import httpx++ try:+ proxy_url = await proxy_svc.get_proxy_url("https://httpbin.org/ip", {"proxyProvider": name})+ if not proxy_url:+ return {"success": False, "error": f"Could not get proxy URL for '{name}'"}++ start = _time.monotonic()+ async with httpx.AsyncClient(proxy=proxy_url, timeout=30) as client:+ resp = await client.get("https://httpbin.org/ip")+ latency_ms = (_time.monotonic() - start) * 1000++ try:+ data = resp.json()+ ip = data.get("origin", "unknown")+ except Exception:+ ip = "unknown"++ return {+ "success": resp.status_code == 200,+ "operation": operation,+ "name": name,+ "ip": ip,+ "latency_ms": round(latency_ms, 1),+ "status_code": resp.status_code,+ }+ except Exception as e:+ return {"success": False, "operation": operation, "name": name, "error": str(e)}++ if operation == 'add_routing_rule':+ domain_pattern = args.get('domain_pattern', node_params.get('domain_pattern', ''))+ if not domain_pattern:+ return {"success": False, "error": "domain_pattern is required"}++ preferred_str = args.get('preferred_providers', node_params.get('preferred_providers', '[]'))+ try:+ preferred = _json.loads(preferred_str) if isinstance(preferred_str, str) else preferred_str+ except _json.JSONDecodeError:+ preferred = []++ db = container.database()+ rule_data = {+ "domain_pattern": domain_pattern,+ "preferred_providers": _json.dumps(preferred),+ "required_country": args.get('required_country', node_params.get('required_country', '')),+ "session_type": args.get('session_type', node_params.get('session_type', 'rotating')),+ }+ await db.save_proxy_routing_rule(rule_data)++ if proxy_svc:+ await proxy_svc.reload_providers()++ return {"success": True, "operation": operation, "domain_pattern": domain_pattern}++ if operation == 'remove_routing_rule':+ rule_id = args.get('rule_id', node_params.get('rule_id'))+ if not rule_id:+ return {"success": False, "error": "rule_id is required"}++ db = container.database()+ await db.delete_proxy_routing_rule(int(rule_id))++ if proxy_svc:+ await proxy_svc.reload_providers()++ return {"success": True, "operation": operation, "rule_id": rule_id}++ return {"success": False, "error": f"Unknown operation: {operation}"}++async def _execute_generic(args: Dict[str, Any],config: Dict[str, Any]) -> Dict[str, Any]:"""Execute a generic tool (fallback handler).@@ -1464,11 +1735,9 @@ async def _execute_delegated_agent(args: Dict[str, Any],if models:child_params['model'] = models[0]- # Build prompt from task + context- full_prompt = task_description- if task_context:- full_prompt = f"{task_description}\n\nContext:\n{task_context}"- child_params['prompt'] = full_prompt+ # Task goes into systemMessage (directive), context data goes into prompt+ child_params['systemMessage'] = task_description+ child_params['prompt'] = task_context if task_context else task_description# Create execution context for child agentchild_context = {diff --git a/server/services/node_executor.py b/server/services/node_executor.pyindex ec201715..d8cd2ed3 100644--- a/server/services/node_executor.py+++ b/server/services/node_executor.py@@ -41,6 +41,7 @@ from services.handlers import ()from services.handlers.telegram import handle_telegram_send, handle_telegram_receivefrom services.handlers.apify import handle_apify_actor+from services.handlers.proxy import handle_proxy_request, handle_proxy_status, handle_proxy_config# Consolidated Google Workspace handlers (6 services with operation dispatchers)from services.handlers.gmail import handle_google_gmail, handle_gmail_receivefrom services.handlers.calendar import handle_google_calendar@@ -185,6 +186,10 @@ class NodeExecutor:'teamMonitor': handle_team_monitor,# Apify web scraping'apifyActor': handle_apify_actor,+ # Proxy nodes+ 'proxyRequest': handle_proxy_request,+ 'proxyStatus': handle_proxy_status,+ 'proxyConfig': handle_proxy_config,# Note: 'console' handled in _dispatch with connected_outputs}diff --git a/server/services/proxy/service.py b/server/services/proxy/service.pyindex 038fc881..6f753e98 100644--- a/server/services/proxy/service.py+++ b/server/services/proxy/service.py@@ -139,11 +139,11 @@ class ProxyService:self._initialized = Falseasync def startup(self) -> None:- """Load provider configs from DB and credentials from AuthService."""- if not self._settings.proxy_enabled:- logger.info("Proxy service disabled (PROXY_ENABLED=false)")- return+ """Load provider configs from DB and credentials from AuthService.+ Always initializes -- providers are managed dynamically by the LLM+ via proxy_config tool. PROXY_ENABLED is not a gate.+ """try:# Load provider configs from databasedb_providers = await self._database.get_proxy_providers()@@ -170,7 +170,7 @@ class ProxyService:logger.info("Proxy service stopped")def is_enabled(self) -> bool:- return self._settings.proxy_enabled and self._initialized+ return self._initializedasync def get_proxy_url(self,@@ -234,7 +234,7 @@ class ProxyService:)# Determine session type- session_type_str = parameters.get("proxySessionType", "rotating")+ session_type_str = parameters.get("sessionType") or parameters.get("proxySessionType", "rotating")session_type = SessionType(session_type_str) if session_type_str else SessionType.ROTATINGif rule:session_type = rule.session_typediff --git a/server/skills/web_agent/http-request-skill/SKILL.md b/server/skills/web_agent/http-request-skill/SKILL.mdindex a9876b44..cd32ccc1 100644--- a/server/skills/web_agent/http-request-skill/SKILL.md+++ b/server/skills/web_agent/http-request-skill/SKILL.md@@ -29,6 +29,7 @@ Make an HTTP request to any URL.| url | string | Yes | Full URL to request (e.g., `https://api.example.com/data`) || method | string | No | HTTP method: `GET`, `POST`, `PUT`, `DELETE`, `PATCH` (default: `GET`) || body | object | No | Request body as JSON object (for POST/PUT/PATCH) |+| useProxy | boolean | No | Route through proxy (default: `false`). The proxy service handles provider selection, geo-targeting, and session type automatically. |### Node Parameters@@ -46,7 +47,8 @@ Additional options can be configured on the node:"status": 200,"data": { "key": "value" },"url": "https://api.example.com/data",- "method": "GET"+ "method": "GET",+ "proxied": false}```@@ -188,6 +190,21 @@ Additional options can be configured on the node:| Health check | GET | Verify service availability || Webhook trigger | POST | Send events to services |+## Proxy Usage++To route a request through a residential proxy, just set `useProxy: true`. The proxy service automatically selects the best provider, geo-target, and session type from its configuration. A proxy provider must be configured first via the `proxy_config` tool (see proxy-config-skill).++**Proxied request:**+```json+{+ "url": "https://example.com/data",+ "method": "GET",+ "useProxy": true+}+```++If no proxy providers are configured or the proxy lookup fails, the request proceeds directly without a proxy and `"proxied": false` appears in the response.+## Guidelines1. **URLs**: Must be fully qualified with protocol (https://)@@ -195,6 +212,7 @@ Additional options can be configured on the node:3. **Timeout**: Default 30 seconds4. **JSON body**: Automatically serialized for POST/PUT/PATCH5. **Response**: JSON responses are automatically parsed+6. **Proxy**: Set `useProxy: true` to route through proxy -- the proxy service handles all routing details## Security Notes@@ -209,3 +227,4 @@ Additional options can be configured on the node:1. Connect the **HTTP Request** node to Zeenie's `input-tools` handle2. Configure authentication headers on the node if needed3. Ensure network access to target APIs+4. For proxy usage: configure a proxy provider via the proxy-config-skill firstdiff --git a/server/skills/web_agent/proxy-config-skill/SKILL.md b/server/skills/web_agent/proxy-config-skill/SKILL.mdindex 2e9d74c1..9fef1aec 100644--- a/server/skills/web_agent/proxy-config-skill/SKILL.md+++ b/server/skills/web_agent/proxy-config-skill/SKILL.md@@ -1,400 +1,228 @@---name: proxy-config-skill-description: Configure any residential proxy provider using template-driven URL encoding. Generate url_template JSON from provider docs, save providers, set credentials, manage routing rules.-allowed-tools: proxy_config python_code+description: Configure residential proxy providers and make proxied HTTP requests with geo-targeting.+allowed-tools: proxy_config proxy_request proxy_status python_codemetadata:author: machina- version: "1.0"+ version: "3.0"category: integrationicon: "🛡"color: "#8B5CF6"----# Proxy Config Skill+# Proxy Configuration Skill-Configure any residential proxy provider in the world using the template-driven proxy system. No provider-specific code exists -- you generate a `url_template` JSON config that tells the system how to format proxy URLs for that provider.+You manage residential proxy providers. Providers are configured with a JSON `url_template` that controls how geo/session parameters are encoded into the proxy URL.-## How It Works+## Setup Workflow-1. User tells you which proxy provider they want to configure-2. You use `python_code` to generate and validate the `url_template` JSON-3. You use `proxy_config` to save the provider, set credentials, and optionally add routing rules-4. You use `proxy_config(test_provider)` to verify the setup works+To add a new proxy provider, make these tool calls in order:-## Tools+### Step 1: Add the provider-- **proxy_config** -- Manage providers, credentials, and routing rules-- **python_code** -- Generate and validate url_template JSON configs+Call `proxy_config` with `operation: "add_provider"`. The `url_template` field is a **JSON string**.------## url_template JSON Schema+Most residential proxy providers use username-based parameter encoding with dash separators. Use this default template unless the provider docs show otherwise:-The `url_template` is a JSON object that tells the proxy system how to encode geo-targeting, session, and other parameters into the proxy URL. Every residential proxy provider uses one of three encoding strategies.--### Encoding Strategies (param_field)+```+proxy_config({+ "operation": "add_provider",+ "name": "smartproxy",+ "gateway_host": "gate.smartproxy.com",+ "gateway_port": 7777,+ "url_template": "{\"param_field\":\"username\",\"username_prefix\":\"{username}\",\"username_param_separator\":\"-\",\"param_separator\":\"-\",\"param_keys\":{\"country\":\"country-{v}\",\"city\":\"city-{v}\",\"state\":\"state-{v}\",\"session_id\":\"session-{v}\",\"session_duration\":\"sessTime-{v}\"},\"country_case\":\"lower\",\"city_separator\":\"_\"}"+})+```-| Strategy | param_field | How it works | Providers using this |-|----------|-------------|--------------|---------------------|-| Username encoding | `"username"` | Parameters appended to username string | ~80% of providers |-| Password encoding | `"password"` | Parameters appended to password string | A few providers |-| No encoding | `"none"` | Plain credentials, no parameter encoding | Generic/custom setups |+### Step 2: Set credentials-### Template Fields+```+proxy_config({+ "operation": "set_credentials",+ "name": "smartproxy",+ "username": "the_username",+ "password": "the_password"+})+```-| Field | Type | Default | Description |-|-------|------|---------|-------------|-| `param_field` | string | `"username"` | Where to encode params: `"username"`, `"password"`, or `"none"` |-| `username_prefix` | string | `"{username}"` | Template for the username base. `{username}` is replaced with the actual username |-| `username_param_separator` | string | `"-"` | Separator between username prefix and first parameter |-| `param_separator` | string | `"-"` | Separator between individual parameters |-| `param_keys` | object | `{}` | Map of parameter names to format strings. `{v}` is replaced with the value |-| `country_case` | string | `"lower"` | Case for country codes: `"lower"` or `"upper"` |-| `city_separator` | string | `"_"` | Character replacing spaces in city/state names |+### Step 3: Test-### param_keys Reference+```+proxy_config({+ "operation": "test_provider",+ "name": "smartproxy"+})+```-| Key | Purpose | Example format string |-|-----|---------|----------------------|-| `country` | ISO country code | `"country-{v}"`, `"_country-{v}"`, `"cc-{v}"` |-| `state` | State/region | `"state-{v}"`, `"_state-{v}"` |-| `city` | City name | `"city-{v}"`, `"_city-{v}"` |-| `session_id` | Sticky session ID | `"session-{v}"`, `"sessid-{v}"` |-| `session_duration` | Session duration | `"sessTime-{v}"`, `"_lifetime-{v}"` |+If test returns `"success": true`, the provider is ready. If it fails, check credentials and gateway host/port.-### How URL Formatting Works+## Making Proxied Requests-Given credentials `user123` / `pass456`, host `gate.example.com:7777`, country `US`:+Once a provider is configured:-**Username encoding** (`param_field: "username"`):```-http://user123-country-us:[email protected]:7777- ^^^^^^^^^^^^^^^^^^^^^^^- prefix + separator + params+proxy_request({+ "url": "https://example.com/page",+ "proxyCountry": "US"+})```-**Password encoding** (`param_field: "password"`):-```-http://user123:[email protected]:7777- ^^^^^^^^^^^^^^^^^^^^^- password + params (no separator usually)-```+The system auto-selects the best healthy provider. To force a specific one:-**No encoding** (`param_field: "none"`):```-http://user123:[email protected]:7777+proxy_request({+ "url": "https://example.com/page",+ "proxyProvider": "smartproxy",+ "proxyCountry": "US",+ "sessionType": "sticky"+})```------## Workflow: Configure a New Provider+## url_template Reference-### Step 1: Generate url_template with python_code+The `url_template` JSON controls how the system builds the proxy URL. It determines how username/password strings are constructed with geo and session parameters.-Read the provider's documentation to identify:-1. What the proxy gateway host and port are-2. How parameters are encoded (username-based or password-based)-3. What separator characters are used-4. What the parameter format strings look like--Then use `python_code` to generate and validate the template:--```python-import json--# Build the url_template based on provider docs-template = {- "param_field": "username",- "username_prefix": "{username}",- "username_param_separator": "-",- "param_separator": "-",- "param_keys": {- "country": "country-{v}",- "city": "city-{v}",- "session_id": "session-{v}",- "session_duration": "sessTime-{v}"- },- "country_case": "lower",- "city_separator": "_"-}+**Fields:**+- `param_field`: Where params go. `"username"` (80% of providers), `"password"`, or `"none"`.+- `username_prefix`: Template for username base. `{username}` is replaced with actual username.+- `username_param_separator`: Separator between username and first param (e.g. `"-"`).+- `param_separator`: Separator between params (e.g. `"-"`).+- `param_keys`: Object mapping param names to format strings. `{v}` is replaced with the value.+ - `country`: e.g. `"country-{v}"` produces `country-us`+ - `city`: e.g. `"city-{v}"` produces `city-new_york`+ - `state`: e.g. `"state-{v}"` produces `state-california`+ - `session_id`: e.g. `"session-{v}"` produces `session-abc123`+ - `session_duration`: e.g. `"sessTime-{v}"` produces `sessTime-10`+- `country_case`: `"lower"` or `"upper"` for country codes.+- `city_separator`: Replaces spaces in city/state names (e.g. `"_"` makes `new_york`).-# Validate: simulate what the proxy system does-username = "testuser"-password = "testpass"-country = "us"-city = "new_york"-session_id = "abc123"+**Result for username encoding with country US:**+`http://myuser-country-us:[email protected]:7777`-params = []-if "country" in template["param_keys"]:- cc = country.lower() if template.get("country_case") == "lower" else country.upper()- params.append(template["param_keys"]["country"].replace("{v}", cc))-if "city" in template["param_keys"]:- c = city.lower().replace(" ", template.get("city_separator", "_"))- params.append(template["param_keys"]["city"].replace("{v}", c))-if "session_id" in template["param_keys"]:- params.append(template["param_keys"]["session_id"].replace("{v}", session_id))--param_str = template.get("param_separator", "-").join(params)-prefix = template.get("username_prefix", "{username}").replace("{username}", username)--if template["param_field"] == "username" and param_str:- sep = template.get("username_param_separator", "-")- final_user = f"{prefix}{sep}{param_str}"- final_pass = password-elif template["param_field"] == "password" and param_str:- final_user = prefix- final_pass = f"{password}{param_str}"-else:- final_user = prefix- final_pass = password--url = f"http://{final_user}:{final_pass}@gate.example.com:7777"-print(f"Generated URL: {url}")--# Assert the URL matches expected format from provider docs-assert "country-us" in url, "Country encoding failed"-assert "city-new_york" in url, "City encoding failed"-assert "session-abc123" in url, "Session encoding failed"--# Output the validated template-result = json.dumps(template, indent=2)-print(f"\nValidated template:\n{result}")-output = result-```+**Result for password encoding with country US:**+`http://myuser:[email protected]:7777`-### Step 2: Save the provider with proxy_config+## Common Provider Templates+### DataImpulse (username-based, dash separator)+Gateway: `gw.dataimpulse.com:823````json-{- "operation": "add_provider",- "name": "my_provider",- "gateway_host": "gate.example.com",- "gateway_port": 7777,- "url_template": "{...the JSON template from step 1...}",- "cost_per_gb": 2.50,- "enabled": true,- "priority": 50-}+{"param_field":"username","username_prefix":"{username}","username_param_separator":"__","param_separator":"__","param_keys":{"country":"country-{v}","city":"city-{v}","session_id":"session-{v}","session_duration":"sessionduration-{v}"},"country_case":"lower","city_separator":"_"}```-### Step 3: Set credentials-+### Decodo/Smartproxy (username-based, dash separator)+Gateway: `gate.smartproxy.com:7777````json-{- "operation": "set_credentials",- "name": "my_provider",- "username": "actual_username",- "password": "actual_password"-}+{"param_field":"username","username_prefix":"{username}","username_param_separator":"-","param_separator":"-","param_keys":{"country":"country-{v}","city":"city-{v}","state":"state-{v}","session_id":"session-{v}","session_duration":"sessTime-{v}"},"country_case":"lower","city_separator":"_"}```-### Step 4: Test the provider-+### Bright Data (username-based, dash separator)+Gateway: `brd.superproxy.io:22225````json-{- "operation": "test_provider",- "name": "my_provider"-}+{"param_field":"username","username_prefix":"{username}","username_param_separator":"-","param_separator":"-","param_keys":{"country":"country-{v}","city":"city-{v}","state":"state-{v}","session_id":"session-{v}"},"country_case":"lower","city_separator":"_"}```-Expected response:+### IPRoyal (password-based)+Gateway: `geo.iproyal.com:12321````json-{- "success": true,- "ip": "203.0.113.42",- "latency_ms": 1250.3,- "status_code": 200-}+{"param_field":"password","username_prefix":"{username}","param_separator":"_","param_keys":{"country":"country-{v}","city":"city-{v}","session_id":"session-{v}","session_duration":"sessionduration-{v}"},"country_case":"lower","city_separator":"_"}```-### Step 5 (Optional): Add routing rules--Route specific domains through specific providers:-+### Custom/Generic (no encoding)+For providers that don't encode params in credentials:```json-{- "operation": "add_routing_rule",- "domain_pattern": "*.linkedin.com",- "preferred_providers": "[\"my_provider\"]",- "required_country": "US",- "session_type": "sticky"-}+{"param_field":"none"}```------## proxy_config Tool Reference--### Operations--| Operation | Description | Required Fields |-|-----------|-------------|-----------------|-| `list_providers` | List all configured providers | (none) |-| `add_provider` | Add a new provider | name, gateway_host, gateway_port, url_template |-| `update_provider` | Update provider settings | name, + fields to change |-| `remove_provider` | Remove a provider | name |-| `set_credentials` | Set provider username/password | name, username, password |-| `test_provider` | Health check via httpbin.org/ip | name |-| `get_stats` | Get usage statistics | (none) |-| `add_routing_rule` | Add domain routing rule | domain_pattern |-| `list_routing_rules` | List all routing rules | (none) |-| `remove_routing_rule` | Remove a routing rule | rule_id |--### add_provider Fields--| Field | Type | Required | Description |-|-------|------|----------|-------------|-| operation | string | Yes | `"add_provider"` |-| name | string | Yes | Unique provider name (e.g., `"smartproxy"`, `"brightdata"`) |-| gateway_host | string | Yes | Gateway hostname |-| gateway_port | integer | Yes | Gateway port |-| url_template | string | Yes | JSON string of template config |-| enabled | boolean | No | Active status (default: true) |-| priority | integer | No | Lower = preferred (default: 50) |-| cost_per_gb | float | No | USD per GB (default: 0) |-| geo_coverage | string | No | JSON array of ISO country codes |--### set_credentials Fields--| Field | Type | Required | Description |-|-------|------|----------|-------------|-| operation | string | Yes | `"set_credentials"` |-| name | string | Yes | Provider name |-| username | string | Yes | Proxy username from provider dashboard |-| password | string | Yes | Proxy password from provider dashboard |--### add_routing_rule Fields--| Field | Type | Required | Description |-|-------|------|----------|-------------|-| operation | string | Yes | `"add_routing_rule"` |-| domain_pattern | string | Yes | Glob pattern: `"*.example.com"`, `"*"` (catch-all) |-| preferred_providers | string | No | JSON array of provider names |-| required_country | string | No | ISO country code |-| session_type | string | No | `"rotating"` or `"sticky"` (default: rotating) |-------## Reading Provider Documentation--When the user gives you a provider name or documentation URL, look for these patterns:+## If Provider Uses Unfamiliar Format-### What to Extract+Use `python_code` to reverse-engineer the template from the provider's example URL:-1. **Gateway endpoint**: Usually formatted as `host:port` (e.g., `gate.smartproxy.com:7777`)-2. **Username format**: How parameters are appended (e.g., `user-country-us-session-abc123`)-3. **Separator characters**: Dash `-`, underscore `_`, dot `.`, or custom-4. **Parameter names**: What the provider calls country, city, session, etc.-5. **Country code format**: Lowercase `us` vs uppercase `US`--### Common Patterns to Recognize--**Pattern A: Dash-separated username params (most common)**-```-username: user-country-us-city-new_york-session-abc123-password: pass-```-Template: `param_field: "username"`, separators: `"-"`--**Pattern B: Underscore prefix params**-```-username: user_country-us_city-new_york_session-abc123-password: pass-```-Template: `username_param_separator: "_"`, keys use `"_country-{v}"`--**Pattern C: Password-based encoding**-```-username: user-password: pass_country-us_session-abc123-```-Template: `param_field: "password"`--**Pattern D: Custom prefix**-```-username: customer-user-zone-us-password: pass-```-Template: `username_prefix: "customer-{username}"`, keys: `"zone-{v}"`--### Validation Checklist--After generating a template, always verify with `python_code`:--1. Country code appears correctly in the URL-2. City names have spaces replaced with the right separator-3. Session IDs are properly formatted-4. The overall URL matches what the provider docs show-5. Both rotating (no session) and sticky (with session) modes work-------## Examples--### Example: User says "Set up Smartproxy"--1. Generate template with `python_code`:```pythonimport json++# Example from provider docs:+# Username: user123-cc-US-city-NewYork-sess-abc123+# Password: pass456+# Host: proxy.example.com:8080+template = {"param_field": "username","username_prefix": "{username}","username_param_separator": "-","param_separator": "-","param_keys": {- "country": "country-{v}",+ "country": "cc-{v}","city": "city-{v}",- "state": "state-{v}",- "session_id": "session-{v}",- "session_duration": "sessTime-{v}"+ "session_id": "sess-{v}"},- "country_case": "lower",- "city_separator": "_"+ "country_case": "upper",+ "city_separator": ""}++# Verify it produces the right URL+username = "user123"+params = []+params.append(template["param_keys"]["country"].replace("{v}", "US"))+params.append(template["param_keys"]["city"].replace("{v}", "NewYork"))+params.append(template["param_keys"]["session_id"].replace("{v}", "abc123"))+param_str = template["param_separator"].join(params)+result = f"{username}{template['username_param_separator']}{param_str}"+print(f"Built username: {result}")+assert result == "user123-cc-US-city-NewYork-sess-abc123", f"Mismatch: {result}"+output = json.dumps(template)+print(f"Template: {output}")```-2. Save: `proxy_config(add_provider, name="smartproxy", gateway_host="gate.smartproxy.com", gateway_port=7777, url_template=<template>, cost_per_gb=4.00)`-3. Credentials: `proxy_config(set_credentials, name="smartproxy", username="sp...", password="...")`-4. Test: `proxy_config(test_provider, name="smartproxy")`+Then pass the `output` as the `url_template` string to `proxy_config(add_provider)`.-### Example: User provides custom proxy docs+## All proxy_config Operations-If the user pastes documentation showing:-```-Proxy: proxy.example.com:8080-Username: your_key-Password: your_secret_cc-US_city-NewYork_sess-12345-```+| Operation | Required Parameters | Description |+|-----------|-------------------|-------------|+| `list_providers` | none | List all configured providers |+| `add_provider` | `name`, `gateway_host`, `gateway_port`, `url_template` | Add a new provider |+| `update_provider` | `name` + any fields to change | Update existing provider |+| `remove_provider` | `name` | Delete a provider |+| `set_credentials` | `name`, `username`, `password` | Store proxy credentials |+| `test_provider` | `name` | Test via httpbin.org/ip |+| `get_stats` | none | Usage statistics |+| `add_routing_rule` | `domain_pattern` | Route domains to specific providers |+| `list_routing_rules` | none | List all routing rules |+| `remove_routing_rule` | `rule_id` | Delete a routing rule |-You identify: password-based encoding, underscore prefix, dash key-value separator.+Optional fields for `add_provider`/`update_provider`: `enabled` (bool), `priority` (int, lower=preferred), `cost_per_gb` (float).-```python-import json-template = {- "param_field": "password",- "username_prefix": "{username}",- "param_separator": "_",- "param_keys": {- "country": "cc-{v}",- "city": "city-{v}",- "session_id": "sess-{v}"- },- "country_case": "upper",- "city_separator": ""-}-output = json.dumps(template)-```+## proxy_request Parameters----+| Parameter | Required | Default | Description |+|-----------|----------|---------|-------------|+| `url` | yes | | Target URL |+| `method` | no | GET | HTTP method |+| `headers` | no | | JSON string of headers |+| `body` | no | | Request body string |+| `proxyProvider` | no | auto | Provider name |+| `proxyCountry` | no | | ISO country code (US, GB, DE) |+| `sessionType` | no | rotating | `rotating` or `sticky` |+| `timeout` | no | 30 | Seconds |+| `maxRetries` | no | 3 | Retry with failover |++## Transparent Proxy on HTTP Nodes++The `httpRequest` and `httpScraper` nodes have built-in proxy support. Set `useProxy: true` and the proxy service handles everything -- provider selection, geo-targeting, and session type are all managed from the proxy service configuration (provider priorities, routing rules, default country).++When the AI Agent uses `http_request` as a tool, it can set `useProxy: true` in the tool arguments. No other proxy fields needed.++**When to use which:**+- Use **http_request with useProxy: true** for proxied requests (simple, proxy service handles routing)+- Use **proxy_request** tool only when you need explicit control over retries and failover-## Guidelines+## Notes-1. **Always validate** the template with `python_code` before saving-2. **Always test** the provider after setting credentials-3. **Never hardcode** provider-specific logic -- the template handles everything-4. If the user does not know their credentials, tell them to find username/password in their proxy provider's dashboard-5. If test fails, check: credentials correct? Gateway host/port correct? Template encoding matches docs?-6. Cost per GB is optional but helps the system prefer cheaper providers-7. Priority lower = preferred; use 10-30 for primary, 50 for default, 70-90 for fallback+- Always run `test_provider` after setting up a new provider+- If the user does not know their credentials, they need to get them from their proxy provider dashboard+- If test fails: check credentials, gateway host/port, and that the url_template matches the provider's format+- Use `proxy_status` to check provider health before making requests+- `sessionType: "sticky"` keeps the same IP across requests (good for scraping sessions)+- `sessionType: "rotating"` gets a new IP each request (good for anonymity)