mirror of
https://github.com/czlonkowski/n8n-mcp.git
synced 2026-02-06 05:23:08 +00:00
feat: enhance workflow mutation telemetry for better AI responses (#419)
* feat: add comprehensive telemetry for partial workflow updates Implement telemetry infrastructure to track workflow mutations from partial update operations. This enables data-driven improvements to partial update tooling by capturing: - Workflow state before and after mutations - User intent and operation patterns - Validation results and improvements - Change metrics (nodes/connections modified) - Success/failure rates and error patterns New Components: - Intent classifier: Categorizes mutation patterns - Intent sanitizer: Removes PII from user instructions - Mutation validator: Ensures data quality before tracking - Mutation tracker: Coordinates validation and metric calculation Extended Components: - TelemetryManager: New trackWorkflowMutation() method - EventTracker: Mutation queue management - BatchProcessor: Mutation data flushing to Supabase MCP Tool Enhancements: - n8n_update_partial_workflow: Added optional 'intent' parameter - n8n_update_full_workflow: Added optional 'intent' parameter - Both tools now track mutations asynchronously Database Schema: - New workflow_mutations table with 20+ fields - Comprehensive indexes for efficient querying - Supports deduplication and data analysis This telemetry system is: - Privacy-focused (PII sanitization, anonymized users) - Non-blocking (async tracking, silent failures) - Production-ready (batching, retries, circuit breaker) - Backward compatible (all parameters optional) Conceived by Romuald Członkowski - https://www.aiadvisors.pl/en * fix: correct SQL syntax for expression index in workflow_mutations schema The expression index for significant changes needs double parentheses around the arithmetic expression to be valid PostgreSQL syntax. Conceived by Romuald Członkowski - https://www.aiadvisors.pl/en * fix: enable RLS policies for workflow_mutations table Enable Row-Level Security and add policies: - Allow anonymous (anon) inserts for telemetry data collection - Allow authenticated reads for data analysis and querying These policies are required for the telemetry system to function correctly with Supabase, as the MCP server uses the anon key to insert mutation data. Conceived by Romuald Członkowski - https://www.aiadvisors.pl/en * fix: reduce mutation auto-flush threshold from 5 to 2 Lower the auto-flush threshold for workflow mutations from 5 to 2 to ensure more timely data persistence. Since mutations are less frequent than regular telemetry events, a lower threshold provides: - Faster data persistence (don't wait for 5 mutations) - Better testing experience (easier to verify with fewer operations) - Reduced risk of data loss if process exits before threshold - More responsive telemetry for low-volume mutation scenarios This complements the existing 5-second periodic flush and process exit handlers, ensuring mutations are persisted promptly. Conceived by Romuald Członkowski - https://www.aiadvisors.pl/en * fix: improve mutation telemetry error logging and diagnostics Changes: - Upgrade error logging from debug to warn level for better visibility - Add diagnostic logging to track mutation processing - Log telemetry disabled state explicitly - Add context info (sessionId, intent, operationCount) to error logs - Remove 'await' from telemetry calls to make them truly non-blocking This will help identify why mutations aren't being persisted to the workflow_mutations table despite successful workflow operations. Conceived by Romuald Członkowski - https://www.aiadvisors.pl/en * feat: enhance workflow mutation telemetry for better AI responses Improve workflow mutation tracking to capture comprehensive data that helps provide better responses when users update workflows. This enhancement collects workflow state, user intent, and operation details to enable more context-aware assistance. Key improvements: - Reduce auto-flush threshold from 5 to 2 for more reliable mutation tracking - Add comprehensive workflow and credential sanitization to mutation tracker - Document intent parameter in workflow update tools for better UX - Fix mutation queue handling in telemetry manager (flush now handles 3 queues) - Add extensive unit tests for mutation tracking and validation (35 new tests) Technical changes: - mutation-tracker.ts: Multi-layer sanitization (workflow, node, parameter levels) - batch-processor.ts: Support mutation data flushing to Supabase - telemetry-manager.ts: Auto-flush mutations at threshold 2, track mutations queue - handlers-workflow-diff.ts: Track workflow mutations with sanitized data - Tests: 13 tests for mutation-tracker, 22 tests for mutation-validator The intent parameter messaging emphasizes user benefit ("helps to return better response") rather than technical implementation details. Conceived by Romuald Członkowski - https://www.aiadvisors.pl/en 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: bump version to 2.22.16 with telemetry changelog Updated package.json and package.runtime.json to version 2.22.16. Added comprehensive CHANGELOG entry documenting workflow mutation telemetry enhancements for better AI-powered workflow assistance. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Conceived by Romuald Członkowski - https://www.aiadvisors.pl/en Co-Authored-By: Claude <noreply@anthropic.com> * fix: resolve TypeScript lint errors in telemetry tests Fixed type issues in mutation-tracker and mutation-validator tests: - Import and use MutationToolName enum instead of string literals - Fix ValidationResult.errors to use proper object structure - Add UpdateNodeOperation type assertion for operation with nodeName All TypeScript errors resolved, lint now passes. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Conceived by Romuald Członkowski - https://www.aiadvisors.pl/en Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Romuald Członkowski
committed by
GitHub
GitHub
parent
77151e013e
commit
99c5907b71
243
src/telemetry/intent-classifier.ts
Normal file
243
src/telemetry/intent-classifier.ts
Normal file
@@ -0,0 +1,243 @@
|
||||
/**
|
||||
* Intent classifier for workflow mutations
|
||||
* Analyzes operations to determine the intent/pattern of the mutation
|
||||
*/
|
||||
|
||||
import { DiffOperation } from '../types/workflow-diff.js';
|
||||
import { IntentClassification } from './mutation-types.js';
|
||||
|
||||
/**
|
||||
* Classifies the intent of a workflow mutation based on operations performed
|
||||
*/
|
||||
export class IntentClassifier {
|
||||
/**
|
||||
* Classify mutation intent from operations and optional user intent text
|
||||
*/
|
||||
classify(operations: DiffOperation[], userIntent?: string): IntentClassification {
|
||||
if (operations.length === 0) {
|
||||
return IntentClassification.UNKNOWN;
|
||||
}
|
||||
|
||||
// First, try to classify from user intent text if provided
|
||||
if (userIntent) {
|
||||
const textClassification = this.classifyFromText(userIntent);
|
||||
if (textClassification !== IntentClassification.UNKNOWN) {
|
||||
return textClassification;
|
||||
}
|
||||
}
|
||||
|
||||
// Fall back to operation pattern analysis
|
||||
return this.classifyFromOperations(operations);
|
||||
}
|
||||
|
||||
/**
|
||||
* Classify from user intent text using keyword matching
|
||||
*/
|
||||
private classifyFromText(intent: string): IntentClassification {
|
||||
const lowerIntent = intent.toLowerCase();
|
||||
|
||||
// Fix validation errors
|
||||
if (
|
||||
lowerIntent.includes('fix') ||
|
||||
lowerIntent.includes('resolve') ||
|
||||
lowerIntent.includes('correct') ||
|
||||
lowerIntent.includes('repair') ||
|
||||
lowerIntent.includes('error')
|
||||
) {
|
||||
return IntentClassification.FIX_VALIDATION;
|
||||
}
|
||||
|
||||
// Add new functionality
|
||||
if (
|
||||
lowerIntent.includes('add') ||
|
||||
lowerIntent.includes('create') ||
|
||||
lowerIntent.includes('insert') ||
|
||||
lowerIntent.includes('new node')
|
||||
) {
|
||||
return IntentClassification.ADD_FUNCTIONALITY;
|
||||
}
|
||||
|
||||
// Modify configuration
|
||||
if (
|
||||
lowerIntent.includes('update') ||
|
||||
lowerIntent.includes('change') ||
|
||||
lowerIntent.includes('modify') ||
|
||||
lowerIntent.includes('configure') ||
|
||||
lowerIntent.includes('set')
|
||||
) {
|
||||
return IntentClassification.MODIFY_CONFIGURATION;
|
||||
}
|
||||
|
||||
// Rewire logic
|
||||
if (
|
||||
lowerIntent.includes('connect') ||
|
||||
lowerIntent.includes('reconnect') ||
|
||||
lowerIntent.includes('rewire') ||
|
||||
lowerIntent.includes('reroute') ||
|
||||
lowerIntent.includes('link')
|
||||
) {
|
||||
return IntentClassification.REWIRE_LOGIC;
|
||||
}
|
||||
|
||||
// Cleanup
|
||||
if (
|
||||
lowerIntent.includes('remove') ||
|
||||
lowerIntent.includes('delete') ||
|
||||
lowerIntent.includes('clean') ||
|
||||
lowerIntent.includes('disable')
|
||||
) {
|
||||
return IntentClassification.CLEANUP;
|
||||
}
|
||||
|
||||
return IntentClassification.UNKNOWN;
|
||||
}
|
||||
|
||||
/**
|
||||
* Classify from operation patterns
|
||||
*/
|
||||
private classifyFromOperations(operations: DiffOperation[]): IntentClassification {
|
||||
const opTypes = operations.map((op) => op.type);
|
||||
const opTypeSet = new Set(opTypes);
|
||||
|
||||
// Pattern: Adding nodes and connections (add functionality)
|
||||
if (opTypeSet.has('addNode') && opTypeSet.has('addConnection')) {
|
||||
return IntentClassification.ADD_FUNCTIONALITY;
|
||||
}
|
||||
|
||||
// Pattern: Only adding nodes (add functionality)
|
||||
if (opTypeSet.has('addNode') && !opTypeSet.has('removeNode')) {
|
||||
return IntentClassification.ADD_FUNCTIONALITY;
|
||||
}
|
||||
|
||||
// Pattern: Removing nodes or connections (cleanup)
|
||||
if (opTypeSet.has('removeNode') || opTypeSet.has('removeConnection')) {
|
||||
return IntentClassification.CLEANUP;
|
||||
}
|
||||
|
||||
// Pattern: Disabling nodes (cleanup)
|
||||
if (opTypeSet.has('disableNode')) {
|
||||
return IntentClassification.CLEANUP;
|
||||
}
|
||||
|
||||
// Pattern: Rewiring connections
|
||||
if (
|
||||
opTypeSet.has('rewireConnection') ||
|
||||
opTypeSet.has('replaceConnections') ||
|
||||
(opTypeSet.has('addConnection') && opTypeSet.has('removeConnection'))
|
||||
) {
|
||||
return IntentClassification.REWIRE_LOGIC;
|
||||
}
|
||||
|
||||
// Pattern: Only updating nodes (modify configuration)
|
||||
if (opTypeSet.has('updateNode') && opTypes.every((t) => t === 'updateNode')) {
|
||||
return IntentClassification.MODIFY_CONFIGURATION;
|
||||
}
|
||||
|
||||
// Pattern: Updating settings or metadata (modify configuration)
|
||||
if (
|
||||
opTypeSet.has('updateSettings') ||
|
||||
opTypeSet.has('updateName') ||
|
||||
opTypeSet.has('addTag') ||
|
||||
opTypeSet.has('removeTag')
|
||||
) {
|
||||
return IntentClassification.MODIFY_CONFIGURATION;
|
||||
}
|
||||
|
||||
// Pattern: Mix of updates with some additions/removals (modify configuration)
|
||||
if (opTypeSet.has('updateNode')) {
|
||||
return IntentClassification.MODIFY_CONFIGURATION;
|
||||
}
|
||||
|
||||
// Pattern: Moving nodes (modify configuration)
|
||||
if (opTypeSet.has('moveNode')) {
|
||||
return IntentClassification.MODIFY_CONFIGURATION;
|
||||
}
|
||||
|
||||
// Pattern: Enabling nodes (could be fixing)
|
||||
if (opTypeSet.has('enableNode')) {
|
||||
return IntentClassification.FIX_VALIDATION;
|
||||
}
|
||||
|
||||
// Pattern: Clean stale connections (cleanup)
|
||||
if (opTypeSet.has('cleanStaleConnections')) {
|
||||
return IntentClassification.CLEANUP;
|
||||
}
|
||||
|
||||
return IntentClassification.UNKNOWN;
|
||||
}
|
||||
|
||||
/**
|
||||
* Get confidence score for classification (0-1)
|
||||
* Higher score means more confident in the classification
|
||||
*/
|
||||
getConfidence(
|
||||
classification: IntentClassification,
|
||||
operations: DiffOperation[],
|
||||
userIntent?: string
|
||||
): number {
|
||||
// High confidence if user intent matches operation pattern
|
||||
if (userIntent && this.classifyFromText(userIntent) === classification) {
|
||||
return 0.9;
|
||||
}
|
||||
|
||||
// Medium-high confidence for clear operation patterns
|
||||
if (classification !== IntentClassification.UNKNOWN) {
|
||||
const opTypes = new Set(operations.map((op) => op.type));
|
||||
|
||||
// Very clear patterns get high confidence
|
||||
if (
|
||||
classification === IntentClassification.ADD_FUNCTIONALITY &&
|
||||
opTypes.has('addNode')
|
||||
) {
|
||||
return 0.8;
|
||||
}
|
||||
|
||||
if (
|
||||
classification === IntentClassification.CLEANUP &&
|
||||
(opTypes.has('removeNode') || opTypes.has('removeConnection'))
|
||||
) {
|
||||
return 0.8;
|
||||
}
|
||||
|
||||
if (
|
||||
classification === IntentClassification.REWIRE_LOGIC &&
|
||||
opTypes.has('rewireConnection')
|
||||
) {
|
||||
return 0.8;
|
||||
}
|
||||
|
||||
// Other patterns get medium confidence
|
||||
return 0.6;
|
||||
}
|
||||
|
||||
// Low confidence for unknown classification
|
||||
return 0.3;
|
||||
}
|
||||
|
||||
/**
|
||||
* Get human-readable description of the classification
|
||||
*/
|
||||
getDescription(classification: IntentClassification): string {
|
||||
switch (classification) {
|
||||
case IntentClassification.ADD_FUNCTIONALITY:
|
||||
return 'Adding new nodes or functionality to the workflow';
|
||||
case IntentClassification.MODIFY_CONFIGURATION:
|
||||
return 'Modifying configuration of existing nodes';
|
||||
case IntentClassification.REWIRE_LOGIC:
|
||||
return 'Changing workflow execution flow by rewiring connections';
|
||||
case IntentClassification.FIX_VALIDATION:
|
||||
return 'Fixing validation errors or issues';
|
||||
case IntentClassification.CLEANUP:
|
||||
return 'Removing or disabling nodes and connections';
|
||||
case IntentClassification.UNKNOWN:
|
||||
return 'Unknown or complex mutation pattern';
|
||||
default:
|
||||
return 'Unclassified mutation';
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Singleton instance for easy access
|
||||
*/
|
||||
export const intentClassifier = new IntentClassifier();
|
||||
Reference in New Issue
Block a user