agentic-flow 3.0.0-alpha.1 → 3.0.0

package/dist/packages/agentdb/src/controllers/NightlyLearner.js

@@ -1,520 +0,0 @@
-/**
- * Nightly Learner - Automated Causal Discovery and Consolidation
- *
- * Runs as a background job to:
- * 1. Discover new causal edges from episode patterns
- * 2. Run A/B experiments on promising hypotheses
- * 3. Calculate uplift for completed experiments
- * 4. Prune low-confidence edges
- * 5. Update rerank weights based on performance
- *
- * Based on doubly robust learner:
- * τ̂(x) = μ1(x) − μ0(x) + [a*(y−μ1(x)) / e(x)] − [(1−a)*(y−μ0(x)) / (1−e(x))]
- *
- * v2.0.0-alpha.3 Features:
- * - FlashAttention for memory-efficient episodic consolidation
- * - Block-wise computation for large episode buffers
- * - Feature flag: ENABLE_FLASH_CONSOLIDATION (default: false)
- * - 100% backward compatible with fallback to standard consolidation
- */
-import { CausalMemoryGraph } from './CausalMemoryGraph.js';
-import { ReflexionMemory } from './ReflexionMemory.js';
-import { SkillLibrary } from './SkillLibrary.js';
-import { AttentionService } from '../utils/LegacyAttentionAdapter.js';
-import { cosineSimilarity } from '../utils/vector-math.js';
-export class NightlyLearner {
-    config;
-    db;
-    causalGraph;
-    reflexion;
-    skillLibrary;
-    embedder;
-    attentionService;
-    constructor(db, embedder, config = {
-        minSimilarity: 0.7,
-        minSampleSize: 30,
-        confidenceThreshold: 0.6,
-        upliftThreshold: 0.05,
-        pruneOldEdges: true,
-        edgeMaxAgeDays: 90,
-        autoExperiments: true,
-        experimentBudget: 10,
-        ENABLE_FLASH_CONSOLIDATION: false,
-    }) {
-        this.config = config;
-        this.db = db;
-        this.embedder = embedder;
-        this.causalGraph = new CausalMemoryGraph(db);
-        this.reflexion = new ReflexionMemory(db, embedder);
-        this.skillLibrary = new SkillLibrary(db, embedder);
-        // Initialize AttentionService if FlashAttention enabled
-        if (this.config.ENABLE_FLASH_CONSOLIDATION) {
-            this.attentionService = new AttentionService(db, {
-                flash: {
-                    enabled: true,
-                    ...this.config.flashConfig,
-                },
-            });
-        }
-    }
-    /**
-     * Main learning job - runs all discovery and consolidation tasks
-     */
-    async run() {
-        console.log('\n🌙 Nightly Learner Starting...\n');
-        const startTime = Date.now();
-        const report = {
-            timestamp: startTime,
-            executionTimeMs: 0,
-            edgesDiscovered: 0,
-            edgesPruned: 0,
-            experimentsCompleted: 0,
-            experimentsCreated: 0,
-            avgUplift: 0,
-            avgConfidence: 0,
-            recommendations: []
-        };
-        try {
-            // Step 1: Discover new causal edges
-            console.log('📊 Discovering causal edges from episode patterns...');
-            report.edgesDiscovered = await this.discoverCausalEdges();
-            console.log(`   ✓ Discovered ${report.edgesDiscovered} new edges\n`);
-            // Step 2: Complete running experiments
-            console.log('🧪 Completing A/B experiments...');
-            report.experimentsCompleted = await this.completeExperiments();
-            console.log(`   ✓ Completed ${report.experimentsCompleted} experiments\n`);
-            // Step 3: Create new experiments (if enabled)
-            if (this.config.autoExperiments) {
-                console.log('🔬 Creating new A/B experiments...');
-                report.experimentsCreated = await this.createExperiments();
-                console.log(`   ✓ Created ${report.experimentsCreated} new experiments\n`);
-            }
-            // Step 4: Prune low-confidence edges
-            if (this.config.pruneOldEdges) {
-                console.log('🧹 Pruning low-confidence edges...');
-                report.edgesPruned = await this.pruneEdges();
-                console.log(`   ✓ Pruned ${report.edgesPruned} edges\n`);
-            }
-            // Step 5: Calculate statistics
-            const stats = this.calculateStats();
-            report.avgUplift = stats.avgUplift;
-            report.avgConfidence = stats.avgConfidence;
-            // Step 6: Generate recommendations
-            report.recommendations = this.generateRecommendations(report);
-            report.executionTimeMs = Date.now() - startTime;
-            console.log('✅ Nightly Learner Completed\n');
-            this.printReport(report);
-            return report;
-        }
-        catch (error) {
-            console.error('❌ Nightly Learner Failed:', error);
-            throw error;
-        }
-    }
-    /**
-     * Discover causal edges using doubly robust learner
-     *
-     * τ̂(x) = μ1(x) − μ0(x) + [a*(y−μ1(x)) / e(x)] − [(1−a)*(y−μ0(x)) / (1−e(x))]
-     *
-     * Where:
-     * - μ1(x) = outcome model for treatment
-     * - μ0(x) = outcome model for control
-     * - e(x) = propensity score (probability of treatment)
-     * - a = treatment indicator
-     * - y = observed outcome
-     *
-     * v2: Uses FlashAttention for memory-efficient consolidation if enabled
-     */
-    async discover(config) {
-        const edges = [];
-        const count = await this.discoverCausalEdges();
-        // If dryRun, return empty array since we didn't actually create edges
-        if (config.dryRun) {
-            return edges;
-        }
-        // Return discovered edges (for non-dry runs)
-        // Note: In a real implementation, we'd track and return the actual edges created
-        return edges;
-    }
-    /**
-     * Consolidate episodic memories using FlashAttention (v2 feature)
-     *
-     * Processes large episode buffers efficiently using block-wise computation.
-     * Identifies patterns and relationships across episodes for causal edge discovery.
-     *
-     * @param sessionId - Session to consolidate (optional, processes all if not provided)
-     * @returns Number of edges discovered through consolidation
-     */
-    async consolidateEpisodes(sessionId) {
-        if (!this.attentionService) {
-            // Fallback: Use standard discovery without attention
-            const edgesDiscovered = await this.discoverCausalEdges();
-            return {
-                edgesDiscovered,
-                episodesProcessed: 0,
-            };
-        }
-        // Get episodes to consolidate
-        const episodes = sessionId
-            ? this.db.prepare(`
-          SELECT id, task, output, reward FROM episodes
-          WHERE session_id = ?
-          ORDER BY ts ASC
-        `).all(sessionId)
-            : this.db.prepare(`
-          SELECT id, task, output, reward FROM episodes
-          ORDER BY ts ASC
-          LIMIT 1000
-        `).all();
-        if (episodes.length === 0) {
-            return { edgesDiscovered: 0, episodesProcessed: 0 };
-        }
-        // Generate embeddings for all episodes
-        const episodeEmbeddings = [];
-        for (const episode of episodes) {
-            const text = `${episode.task}: ${episode.output}`;
-            const embedding = await this.embedder.embed(text);
-            episodeEmbeddings.push(embedding);
-        }
-        // Prepare queries (each episode is a query)
-        const dim = 384;
-        const queries = new Float32Array(episodes.length * dim);
-        const keys = new Float32Array(episodes.length * dim);
-        const values = new Float32Array(episodes.length * dim);
-        episodeEmbeddings.forEach((embedding, idx) => {
-            queries.set(embedding, idx * dim);
-            keys.set(embedding, idx * dim);
-            values.set(embedding, idx * dim);
-        });
-        // Apply FlashAttention for memory-efficient consolidation
-        const attentionResult = await this.attentionService.flashAttention(queries, keys, values);
-        // Analyze attention output to discover causal relationships
-        let edgesDiscovered = 0;
-        const consolidatedEmbeddings = attentionResult.output;
-        // For each episode, find similar episodes in consolidated space
-        for (let i = 0; i < episodes.length; i++) {
-            const queryEmb = consolidatedEmbeddings.slice(i * dim, (i + 1) * dim);
-            // Find top-k similar episodes
-            const similarities = [];
-            for (let j = 0; j < episodes.length; j++) {
-                if (i === j)
-                    continue;
-                const keyEmb = consolidatedEmbeddings.slice(j * dim, (j + 1) * dim);
-                const score = cosineSimilarity(queryEmb, keyEmb);
-                if (score >= this.config.minSimilarity) {
-                    similarities.push({ idx: j, score });
-                }
-            }
-            // Sort by similarity
-            similarities.sort((a, b) => b.score - a.score);
-            // Create causal edges for top matches
-            for (const { idx, score } of similarities.slice(0, 5)) {
-                // Only create edge if temporal sequence is correct
-                if (idx > i) {
-                    const uplift = episodes[idx].reward - episodes[i].reward;
-                    if (Math.abs(uplift) >= this.config.upliftThreshold) {
-                        await this.causalGraph.addCausalEdge({
-                            fromMemoryId: episodes[i].id,
-                            fromMemoryType: 'episode',
-                            toMemoryId: episodes[idx].id,
-                            toMemoryType: 'episode',
-                            similarity: score,
-                            uplift,
-                            confidence: score,
-                            sampleSize: 1,
-                            mechanism: 'flash_attention_consolidation',
-                            metadata: {
-                                consolidationMethod: 'flash_attention',
-                                blockSize: this.config.flashConfig?.blockSize || 256,
-                            },
-                        });
-                        edgesDiscovered++;
-                    }
-                }
-            }
-        }
-        return {
-            edgesDiscovered,
-            episodesProcessed: episodes.length,
-            metrics: attentionResult.metrics,
-        };
-    }
-    async discoverCausalEdges() {
-        let discovered = 0;
-        // Find episode pairs with high similarity and temporal sequence
-        const candidatePairs = this.db.prepare(`
-      SELECT
-        e1.id as from_id,
-        e1.task as from_task,
-        e1.reward as from_reward,
-        e2.id as to_id,
-        e2.task as to_task,
-        e2.reward as to_reward,
-        e2.ts - e1.ts as time_diff
-      FROM episodes e1
-      JOIN episodes e2 ON e1.session_id = e2.session_id
-      WHERE e1.id != e2.id
-        AND e2.ts > e1.ts
-        AND e2.ts - e1.ts < 3600 -- Within 1 hour
-      ORDER BY e1.id, e2.ts
-      LIMIT 1000
-    `).all();
-        // Better-sqlite3 best practice: Prepare statements OUTSIDE loops for better performance
-        const checkExistingStmt = this.db.prepare(`
-      SELECT id FROM causal_edges
-      WHERE from_memory_id = ? AND to_memory_id = ?
-    `);
-        for (const pair of candidatePairs) {
-            // Check if edge already exists
-            const existing = checkExistingStmt.get(pair.from_id, pair.to_id);
-            if (existing)
-                continue;
-            // Calculate propensity score e(x) - probability of treatment
-            // Simplified: use frequency of from_task in session
-            const propensity = this.calculatePropensity(pair.from_id);
-            // Calculate outcome models μ1(x) and μ0(x)
-            const mu1 = this.calculateOutcomeModel(pair.from_task, true); // With treatment
-            const mu0 = this.calculateOutcomeModel(pair.from_task, false); // Without treatment
-            // Calculate doubly robust estimator
-            const a = 1; // This is a treated observation
-            const y = pair.to_reward;
-            const doublyRobustEstimate = (mu1 - mu0) + (a * (y - mu1) / propensity);
-            // Calculate confidence based on sample size and variance
-            const sampleSize = this.getSampleSize(pair.from_task);
-            const confidence = this.calculateConfidence(sampleSize, doublyRobustEstimate);
-            // Only add if meets thresholds
-            if (Math.abs(doublyRobustEstimate) >= this.config.upliftThreshold && confidence >= this.config.confidenceThreshold) {
-                const edge = {
-                    fromMemoryId: pair.from_id,
-                    fromMemoryType: 'episode',
-                    toMemoryId: pair.to_id,
-                    toMemoryType: 'episode',
-                    similarity: 0.8, // Simplified - would use embedding similarity in production
-                    uplift: doublyRobustEstimate,
-                    confidence,
-                    sampleSize,
-                    mechanism: `${pair.from_task} → ${pair.to_task} (doubly robust)`,
-                    metadata: {
-                        propensity,
-                        mu1,
-                        mu0,
-                        discoveredAt: Date.now()
-                    }
-                };
-                this.causalGraph.addCausalEdge(edge);
-                discovered++;
-            }
-        }
-        return discovered;
-    }
-    /**
-     * Calculate propensity score e(x) - probability of treatment given context
-     */
-    calculatePropensity(episodeId) {
-        const episode = this.db.prepare('SELECT task, session_id FROM episodes WHERE id = ?').get(episodeId);
-        // Count occurrences of this task type in session
-        const counts = this.db.prepare(`
-      SELECT
-        COUNT(*) as total,
-        SUM(CASE WHEN task = ? THEN 1 ELSE 0 END) as task_count
-      FROM episodes
-      WHERE session_id = ?
-    `).get(episode.task, episode.session_id);
-        const propensity = counts.task_count / Math.max(counts.total, 1);
-        // Clip to avoid division by zero
-        return Math.max(0.01, Math.min(0.99, propensity));
-    }
-    /**
-     * Calculate outcome model μ(x) - expected outcome given treatment status
-     */
-    calculateOutcomeModel(task, treated) {
-        // Get average reward for episodes with/without this task in their history
-        const avgReward = this.db.prepare(`
-      SELECT AVG(reward) as avg_reward
-      FROM episodes
-      WHERE ${treated ? '' : 'NOT'} EXISTS (
-        SELECT 1 FROM episodes e2
-        WHERE e2.session_id = episodes.session_id
-          AND e2.task = ?
-          AND e2.ts < episodes.ts
-      )
-    `).get(task);
-        return avgReward?.avg_reward || 0.5;
-    }
-    /**
-     * Get sample size for a task type
-     */
-    getSampleSize(task) {
-        const count = this.db.prepare(`
-      SELECT COUNT(*) as count
-      FROM episodes
-      WHERE task = ?
-    `).get(task);
-        return count.count;
-    }
-    /**
-     * Calculate confidence based on sample size and effect size
-     */
-    calculateConfidence(sampleSize, uplift) {
-        // Simplified confidence calculation
-        // In production, use proper statistical methods (bootstrap, etc.)
-        const sampleFactor = Math.min(sampleSize / 100, 1.0); // Max at 100 samples
-        const effectSizeFactor = Math.min(Math.abs(uplift) / 0.5, 1.0); // Max at 0.5 uplift
-        return sampleFactor * effectSizeFactor;
-    }
-    /**
-     * Complete running A/B experiments and calculate uplift
-     */
-    async completeExperiments() {
-        // Better-sqlite3 best practice: Prepare statements OUTSIDE loops for better performance
-        const runningExperiments = this.db.prepare(`
-      SELECT id, start_time, sample_size
-      FROM causal_experiments
-      WHERE status = 'running'
-        AND sample_size >= ?
-    `).all(this.config.minSampleSize);
-        let completed = 0;
-        for (const exp of runningExperiments) {
-            try {
-                this.causalGraph.calculateUplift(exp.id);
-                completed++;
-            }
-            catch (error) {
-                console.error(`   ⚠ Failed to calculate uplift for experiment ${exp.id}:`, error);
-            }
-        }
-        return completed;
-    }
-    /**
-     * Create new A/B experiments for promising hypotheses
-     */
-    async createExperiments() {
-        const currentExperiments = this.db.prepare(`
-      SELECT COUNT(*) as count
-      FROM causal_experiments
-      WHERE status = 'running'
-    `).get();
-        const available = this.config.experimentBudget - currentExperiments.count;
-        if (available <= 0) {
-            return 0;
-        }
-        // Find promising task pairs that don't have experiments yet
-        const candidates = this.db.prepare(`
-      SELECT DISTINCT
-        e1.task as treatment_task,
-        e1.id as treatment_id,
-        COUNT(e2.id) as potential_outcomes
-      FROM episodes e1
-      JOIN episodes e2 ON e1.session_id = e2.session_id
-      WHERE e2.ts > e1.ts
-        AND NOT EXISTS (
-          SELECT 1 FROM causal_experiments
-          WHERE treatment_id = e1.id
-        )
-      GROUP BY e1.task, e1.id
-      HAVING COUNT(e2.id) >= ?
-      ORDER BY COUNT(e2.id) DESC
-      LIMIT ?
-    `).all(this.config.minSampleSize, available);
-        let created = 0;
-        for (const candidate of candidates) {
-            const expId = this.causalGraph.createExperiment({
-                name: `Auto: ${candidate.treatment_task} Impact`,
-                hypothesis: `${candidate.treatment_task} affects downstream outcomes`,
-                treatmentId: candidate.treatment_id,
-                treatmentType: 'episode',
-                startTime: Date.now(),
-                sampleSize: 0,
-                status: 'running',
-                metadata: {
-                    autoGenerated: true,
-                    potentialOutcomes: candidate.potential_outcomes
-                }
-            });
-            created++;
-        }
-        return created;
-    }
-    /**
-     * Prune old or low-confidence edges
-     */
-    async pruneEdges() {
-        const maxAgeMs = this.config.edgeMaxAgeDays * 24 * 60 * 60 * 1000;
-        const cutoffTime = Date.now() / 1000 - maxAgeMs / 1000;
-        const result = this.db.prepare(`
-      DELETE FROM causal_edges
-      WHERE confidence < ?
-        OR created_at < ?
-    `).run(this.config.confidenceThreshold, cutoffTime);
-        return result.changes;
-    }
-    /**
-     * Calculate overall statistics
-     */
-    calculateStats() {
-        const stats = this.db.prepare(`
-      SELECT
-        AVG(ABS(uplift)) as avg_uplift,
-        AVG(confidence) as avg_confidence
-      FROM causal_edges
-      WHERE uplift IS NOT NULL
-    `).get();
-        return {
-            avgUplift: stats?.avg_uplift || 0,
-            avgConfidence: stats?.avg_confidence || 0
-        };
-    }
-    /**
-     * Generate recommendations based on learning results
-     */
-    generateRecommendations(report) {
-        const recommendations = [];
-        if (report.edgesDiscovered === 0) {
-            recommendations.push('No new causal edges discovered. Consider collecting more diverse episode data.');
-        }
-        if (report.avgUplift < 0.1) {
-            recommendations.push('Average uplift is low. Review task sequences for optimization opportunities.');
-        }
-        if (report.avgConfidence < 0.7) {
-            recommendations.push('Average confidence is below target. Increase sample sizes or refine hypothesis selection.');
-        }
-        if (report.experimentsCompleted > 0) {
-            recommendations.push(`${report.experimentsCompleted} experiments completed. Review results for actionable insights.`);
-        }
-        if (report.edgesPruned > report.edgesDiscovered) {
-            recommendations.push('More edges pruned than discovered. Consider adjusting confidence thresholds.');
-        }
-        return recommendations;
-    }
-    /**
-     * Print report to console
-     */
-    printReport(report) {
-        console.log('═══════════════════════════════════════════════════════════');
-        console.log('  Nightly Learner Report');
-        console.log('═══════════════════════════════════════════════════════════\n');
-        console.log(`  Execution Time: ${report.executionTimeMs}ms`);
-        console.log(`  Timestamp: ${new Date(report.timestamp).toISOString()}\n`);
-        console.log('  Results:');
-        console.log(`    • Edges Discovered: ${report.edgesDiscovered}`);
-        console.log(`    • Edges Pruned: ${report.edgesPruned}`);
-        console.log(`    • Experiments Completed: ${report.experimentsCompleted}`);
-        console.log(`    • Experiments Created: ${report.experimentsCreated}\n`);
-        console.log('  Statistics:');
-        console.log(`    • Avg Uplift: ${report.avgUplift.toFixed(3)}`);
-        console.log(`    • Avg Confidence: ${report.avgConfidence.toFixed(3)}\n`);
-        if (report.recommendations.length > 0) {
-            console.log('  Recommendations:');
-            report.recommendations.forEach(rec => console.log(`    • ${rec}`));
-            console.log('');
-        }
-        console.log('═══════════════════════════════════════════════════════════\n');
-    }
-    /**
-     * Update learner configuration
-     */
-    updateConfig(config) {
-        this.config = { ...this.config, ...config };
-    }
-}
-//# sourceMappingURL=NightlyLearner.js.map

package/dist/packages/agentdb/src/controllers/NightlyLearner.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"NightlyLearner.js","sourceRoot":"","sources":["../../../../../../packages/agentdb/src/controllers/NightlyLearner.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;GAkBG;AAIH,OAAO,EAAE,iBAAiB,EAAc,MAAM,wBAAwB,CAAC;AACvE,OAAO,EAAE,eAAe,EAAE,MAAM,sBAAsB,CAAC;AACvD,OAAO,EAAE,YAAY,EAAE,MAAM,mBAAmB,CAAC;AAEjD,OAAO,EAAE,gBAAgB,EAA6B,MAAM,oCAAoC,CAAC;AACjG,OAAO,EAAE,gBAAgB,EAAE,MAAM,yBAAyB,CAAC;AA+B3D,MAAM,OAAO,cAAc;IAWf;IAVF,EAAE,CAAW;IACb,WAAW,CAAoB;IAC/B,SAAS,CAAkB;IAC3B,YAAY,CAAe;IAC3B,QAAQ,CAAmB;IAC3B,gBAAgB,CAAoB;IAE5C,YACE,EAAY,EACZ,QAA0B,EAClB,SAAwB;QAC9B,aAAa,EAAE,GAAG;QAClB,aAAa,EAAE,EAAE;QACjB,mBAAmB,EAAE,GAAG;QACxB,eAAe,EAAE,IAAI;QACrB,aAAa,EAAE,IAAI;QACnB,cAAc,EAAE,EAAE;QAClB,eAAe,EAAE,IAAI;QACrB,gBAAgB,EAAE,EAAE;QACpB,0BAA0B,EAAE,KAAK;KAClC;QAVO,WAAM,GAAN,MAAM,CAUb;QAED,IAAI,CAAC,EAAE,GAAG,EAAE,CAAC;QACb,IAAI,CAAC,QAAQ,GAAG,QAAQ,CAAC;QACzB,IAAI,CAAC,WAAW,GAAG,IAAI,iBAAiB,CAAC,EAAE,CAAC,CAAC;QAC7C,IAAI,CAAC,SAAS,GAAG,IAAI,eAAe,CAAC,EAAE,EAAE,QAAQ,CAAC,CAAC;QACnD,IAAI,CAAC,YAAY,GAAG,IAAI,YAAY,CAAC,EAAE,EAAE,QAAQ,CAAC,CAAC;QAEnD,wDAAwD;QACxD,IAAI,IAAI,CAAC,MAAM,CAAC,0BAA0B,EAAE,CAAC;YAC3C,IAAI,CAAC,gBAAgB,GAAG,IAAI,gBAAgB,CAAC,EAAE,EAAE;gBAC/C,KAAK,EAAE;oBACL,OAAO,EAAE,IAAI;oBACb,GAAG,IAAI,CAAC,MAAM,CAAC,WAAW;iBAC3B;aACF,CAAC,CAAC;QACL,CAAC;IACH,CAAC;IAED;;OAEG;IACH,KAAK,CAAC,GAAG;QACP,OAAO,CAAC,GAAG,CAAC,oCAAoC,CAAC,CAAC;QAClD,MAAM,SAAS,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC;QAE7B,MAAM,MAAM,GAAkB;YAC5B,SAAS,EAAE,SAAS;YACpB,eAAe,EAAE,CAAC;YAClB,eAAe,EAAE,CAAC;YAClB,WAAW,EAAE,CAAC;YACd,oBAAoB,EAAE,CAAC;YACvB,kBAAkB,EAAE,CAAC;YACrB,SAAS,EAAE,CAAC;YACZ,aAAa,EAAE,CAAC;YAChB,eAAe,EAAE,EAAE;SACpB,CAAC;QAEF,IAAI,CAAC;YACH,oCAAoC;YACpC,OAAO,CAAC,GAAG,CAAC,sDAAsD,CAAC,CAAC;YACpE,MAAM,CAAC,eAAe,GAAG,MAAM,IAAI,CAAC,mBAAmB,EAAE,CAAC;YAC1D,OAAO,CAAC,GAAG,CAAC,mBAAmB,MAAM,CAAC,eAAe,cAAc,CAAC,CAAC;YAErE,uCAAuC;YACvC,OAAO,CAAC,GAAG,CAAC,kCAAkC,CAAC,CAAC;YAChD,MAAM,CAAC,oBAAoB,GAAG,MAAM,IAAI,CAAC,mBAAmB,EAAE,CAAC;YAC/D,OAAO,CAAC,GAAG,CAAC,kBAAkB,MAAM,CAAC,oBAAoB,gBAAgB,CAAC,CAAC;YAE3E,8CAA8C;YAC9C,IAAI,IAAI,CAAC,MAAM,CAAC,eAAe,EAAE,CAAC;gBAChC,OAAO,CAAC,GAAG,CAAC,oCAAoC,CAAC,CAAC;gBAClD,MAAM,CAAC,kBAAkB,GAAG,MAAM,IAAI,CAAC,iBAAiB,EAAE,CAAC;gBAC3D,OAAO,CAAC,GAAG,CAAC,gBAAgB,MAAM,CAAC,kBAAkB,oBAAoB,CAAC,CAAC;YAC7E,CAAC;YAED,qCAAqC;YACrC,IAAI,IAAI,CAAC,MAAM,CAAC,aAAa,EAAE,CAAC;gBAC9B,OAAO,CAAC,GAAG,CAAC,oCAAoC,CAAC,CAAC;gBAClD,MAAM,CAAC,WAAW,GAAG,MAAM,IAAI,CAAC,UAAU,EAAE,CAAC;gBAC7C,OAAO,CAAC,GAAG,CAAC,eAAe,MAAM,CAAC,WAAW,UAAU,CAAC,CAAC;YAC3D,CAAC;YAED,+BAA+B;YAC/B,MAAM,KAAK,GAAG,IAAI,CAAC,cAAc,EAAE,CAAC;YACpC,MAAM,CAAC,SAAS,GAAG,KAAK,CAAC,SAAS,CAAC;YACnC,MAAM,CAAC,aAAa,GAAG,KAAK,CAAC,aAAa,CAAC;YAE3C,mCAAmC;YACnC,MAAM,CAAC,eAAe,GAAG,IAAI,CAAC,uBAAuB,CAAC,MAAM,CAAC,CAAC;YAE9D,MAAM,CAAC,eAAe,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,SAAS,CAAC;YAEhD,OAAO,CAAC,GAAG,CAAC,+BAA+B,CAAC,CAAC;YAC7C,IAAI,CAAC,WAAW,CAAC,MAAM,CAAC,CAAC;YAEzB,OAAO,MAAM,CAAC;QAChB,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,OAAO,CAAC,KAAK,CAAC,2BAA2B,EAAE,KAAK,CAAC,CAAC;YAClD,MAAM,KAAK,CAAC;QACd,CAAC;IACH,CAAC;IAED;;;;;;;;;;;;;OAaG;IACH,KAAK,CAAC,QAAQ,CAAC,MAKd;QACC,MAAM,KAAK,GAAiB,EAAE,CAAC;QAC/B,MAAM,KAAK,GAAG,MAAM,IAAI,CAAC,mBAAmB,EAAE,CAAC;QAE/C,sEAAsE;QACtE,IAAI,MAAM,CAAC,MAAM,EAAE,CAAC;YAClB,OAAO,KAAK,CAAC;QACf,CAAC;QAED,6CAA6C;QAC7C,iFAAiF;QACjF,OAAO,KAAK,CAAC;IACf,CAAC;IAED;;;;;;;;OAQG;IACH,KAAK,CAAC,mBAAmB,CAAC,SAAkB;QAS1C,IAAI,CAAC,IAAI,CAAC,gBAAgB,EAAE,CAAC;YAC3B,qDAAqD;YACrD,MAAM,eAAe,GAAG,MAAM,IAAI,CAAC,mBAAmB,EAAE,CAAC;YACzD,OAAO;gBACL,eAAe;gBACf,iBAAiB,EAAE,CAAC;aACrB,CAAC;QACJ,CAAC;QAED,8BAA8B;QAC9B,MAAM,QAAQ,GAAG,SAAS;YACxB,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,OAAO,CAAC;;;;SAIf,CAAC,CAAC,GAAG,CAAC,SAAS,CAAU;YAC5B,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,OAAO,CAAC;;;;SAIf,CAAC,CAAC,GAAG,EAAW,CAAC;QAEtB,IAAI,QAAQ,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YAC1B,OAAO,EAAE,eAAe,EAAE,CAAC,EAAE,iBAAiB,EAAE,CAAC,EAAE,CAAC;QACtD,CAAC;QAED,uCAAuC;QACvC,MAAM,iBAAiB,GAAmB,EAAE,CAAC;QAC7C,KAAK,MAAM,OAAO,IAAI,QAAQ,EAAE,CAAC;YAC/B,MAAM,IAAI,GAAG,GAAG,OAAO,CAAC,IAAI,KAAK,OAAO,CAAC,MAAM,EAAE,CAAC;YAClD,MAAM,SAAS,GAAG,MAAM,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;YAClD,iBAAiB,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;QACpC,CAAC;QAED,4CAA4C;QAC5C,MAAM,GAAG,GAAG,GAAG,CAAC;QAChB,MAAM,OAAO,GAAG,IAAI,YAAY,CAAC,QAAQ,CAAC,MAAM,GAAG,GAAG,CAAC,CAAC;QACxD,MAAM,IAAI,GAAG,IAAI,YAAY,CAAC,QAAQ,CAAC,MAAM,GAAG,GAAG,CAAC,CAAC;QACrD,MAAM,MAAM,GAAG,IAAI,YAAY,CAAC,QAAQ,CAAC,MAAM,GAAG,GAAG,CAAC,CAAC;QAEvD,iBAAiB,CAAC,OAAO,CAAC,CAAC,SAAS,EAAE,GAAG,EAAE,EAAE;YAC3C,OAAO,CAAC,GAAG,CAAC,SAAS,EAAE,GAAG,GAAG,GAAG,CAAC,CAAC;YAClC,IAAI,CAAC,GAAG,CAAC,SAAS,EAAE,GAAG,GAAG,GAAG,CAAC,CAAC;YAC/B,MAAM,CAAC,GAAG,CAAC,SAAS,EAAE,GAAG,GAAG,GAAG,CAAC,CAAC;QACnC,CAAC,CAAC,CAAC;QAEH,0DAA0D;QAC1D,MAAM,eAAe,GAAG,MAAM,IAAI,CAAC,gBAAgB,CAAC,cAAc,CAAC,OAAO,EAAE,IAAI,EAAE,MAAM,CAAC,CAAC;QAE1F,4DAA4D;QAC5D,IAAI,eAAe,GAAG,CAAC,CAAC;QACxB,MAAM,sBAAsB,GAAG,eAAe,CAAC,MAAM,CAAC;QAEtD,gEAAgE;QAChE,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,QAAQ,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;YACzC,MAAM,QAAQ,GAAG,sBAAsB,CAAC,KAAK,CAAC,CAAC,GAAG,GAAG,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,GAAG,GAAG,CAAC,CAAC;YAEtE,8BAA8B;YAC9B,MAAM,YAAY,GAA0C,EAAE,CAAC;YAC/D,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,QAAQ,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;gBACzC,IAAI,CAAC,KAAK,CAAC;oBAAE,SAAS;gBAEtB,MAAM,MAAM,GAAG,sBAAsB,CAAC,KAAK,CAAC,CAAC,GAAG,GAAG,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,GAAG,GAAG,CAAC,CAAC;gBACpE,MAAM,KAAK,GAAG,gBAAgB,CAAC,QAAQ,EAAE,MAAM,CAAC,CAAC;gBAEjD,IAAI,KAAK,IAAI,IAAI,CAAC,MAAM,CAAC,aAAa,EAAE,CAAC;oBACvC,YAAY,CAAC,IAAI,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC;gBACvC,CAAC;YACH,CAAC;YAED,qBAAqB;YACrB,YAAY,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,KAAK,CAAC,CAAC;YAE/C,sCAAsC;YACtC,KAAK,MAAM,EAAE,GAAG,EAAE,KAAK,EAAE,IAAI,YAAY,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC;gBACtD,mDAAmD;gBACnD,IAAI,GAAG,GAAG,CAAC,EAAE,CAAC;oBACZ,MAAM,MAAM,GAAG,QAAQ,CAAC,GAAG,CAAC,CAAC,MAAM,GAAG,QAAQ,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC;oBAEzD,IAAI,IAAI,CAAC,GAAG,CAAC,MAAM,CAAC,IAAI,IAAI,CAAC,MAAM,CAAC,eAAe,EAAE,CAAC;wBACpD,MAAM,IAAI,CAAC,WAAW,CAAC,aAAa,CAAC;4BACnC,YAAY,EAAE,QAAQ,CAAC,CAAC,CAAC,CAAC,EAAE;4BAC5B,cAAc,EAAE,SAAS;4BACzB,UAAU,EAAE,QAAQ,CAAC,GAAG,CAAC,CAAC,EAAE;4BAC5B,YAAY,EAAE,SAAS;4BACvB,UAAU,EAAE,KAAK;4BACjB,MAAM;4BACN,UAAU,EAAE,KAAK;4BACjB,UAAU,EAAE,CAAC;4BACb,SAAS,EAAE,+BAA+B;4BAC1C,QAAQ,EAAE;gCACR,mBAAmB,EAAE,iBAAiB;gCACtC,SAAS,EAAE,IAAI,CAAC,MAAM,CAAC,WAAW,EAAE,SAAS,IAAI,GAAG;6BACrD;yBACF,CAAC,CAAC;wBAEH,eAAe,EAAE,CAAC;oBACpB,CAAC;gBACH,CAAC;YACH,CAAC;QACH,CAAC;QAED,OAAO;YACL,eAAe;YACf,iBAAiB,EAAE,QAAQ,CAAC,MAAM;YAClC,OAAO,EAAE,eAAe,CAAC,OAAO;SACjC,CAAC;IACJ,CAAC;IAEO,KAAK,CAAC,mBAAmB;QAC/B,IAAI,UAAU,GAAG,CAAC,CAAC;QAEnB,gEAAgE;QAChE,MAAM,cAAc,GAAG,IAAI,CAAC,EAAE,CAAC,OAAO,CAAC;;;;;;;;;;;;;;;;KAgBtC,CAAC,CAAC,GAAG,EAAW,CAAC;QAElB,wFAAwF;QACxF,MAAM,iBAAiB,GAAG,IAAI,CAAC,EAAE,CAAC,OAAO,CAAC;;;KAGzC,CAAC,CAAC;QAEH,KAAK,MAAM,IAAI,IAAI,cAAc,EAAE,CAAC;YAClC,+BAA+B;YAC/B,MAAM,QAAQ,GAAG,iBAAiB,CAAC,GAAG,CAAC,IAAI,CAAC,OAAO,EAAE,IAAI,CAAC,KAAK,CAAC,CAAC;YAEjE,IAAI,QAAQ;gBAAE,SAAS;YAEvB,6DAA6D;YAC7D,oDAAoD;YACpD,MAAM,UAAU,GAAG,IAAI,CAAC,mBAAmB,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;YAE1D,2CAA2C;YAC3C,MAAM,GAAG,GAAG,IAAI,CAAC,qBAAqB,CAAC,IAAI,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC,CAAE,iBAAiB;YAChF,MAAM,GAAG,GAAG,IAAI,CAAC,qBAAqB,CAAC,IAAI,CAAC,SAAS,EAAE,KAAK,CAAC,CAAC,CAAC,oBAAoB;YAEnF,oCAAoC;YACpC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC,gCAAgC;YAC7C,MAAM,CAAC,GAAG,IAAI,CAAC,SAAS,CAAC;YACzB,MAAM,oBAAoB,GAAG,CAAC,GAAG,GAAG,GAAG,CAAC,GAAG,CAAC,CAAC,GAAG,CAAC,CAAC,GAAG,GAAG,CAAC,GAAG,UAAU,CAAC,CAAC;YAExE,yDAAyD;YACzD,MAAM,UAAU,GAAG,IAAI,CAAC,aAAa,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;YACtD,MAAM,UAAU,GAAG,IAAI,CAAC,mBAAmB,CAAC,UAAU,EAAE,oBAAoB,CAAC,CAAC;YAE9E,+BAA+B;YAC/B,IAAI,IAAI,CAAC,GAAG,CAAC,oBAAoB,CAAC,IAAI,IAAI,CAAC,MAAM,CAAC,eAAe,IAAI,UAAU,IAAI,IAAI,CAAC,MAAM,CAAC,mBAAmB,EAAE,CAAC;gBACnH,MAAM,IAAI,GAAe;oBACvB,YAAY,EAAE,IAAI,CAAC,OAAO;oBAC1B,cAAc,EAAE,SAAS;oBACzB,UAAU,EAAE,IAAI,CAAC,KAAK;oBACtB,YAAY,EAAE,SAAS;oBACvB,UAAU,EAAE,GAAG,EAAE,4DAA4D;oBAC7E,MAAM,EAAE,oBAAoB;oBAC5B,UAAU;oBACV,UAAU;oBACV,SAAS,EAAE,GAAG,IAAI,CAAC,SAAS,MAAM,IAAI,CAAC,OAAO,kBAAkB;oBAChE,QAAQ,EAAE;wBACR,UAAU;wBACV,GAAG;wBACH,GAAG;wBACH,YAAY,EAAE,IAAI,CAAC,GAAG,EAAE;qBACzB;iBACF,CAAC;gBAEF,IAAI,CAAC,WAAW,CAAC,aAAa,CAAC,IAAI,CAAC,CAAC;gBACrC,UAAU,EAAE,CAAC;YACf,CAAC;QACH,CAAC;QAED,OAAO,UAAU,CAAC;IACpB,CAAC;IAED;;OAEG;IACK,mBAAmB,CAAC,SAAiB;QAC3C,MAAM,OAAO,GAAG,IAAI,CAAC,EAAE,CAAC,OAAO,CAAC,oDAAoD,CAAC,CAAC,GAAG,CAAC,SAAS,CAAQ,CAAC;QAE5G,iDAAiD;QACjD,MAAM,MAAM,GAAG,IAAI,CAAC,EAAE,CAAC,OAAO,CAAC;;;;;;KAM9B,CAAC,CAAC,GAAG,CAAC,OAAO,CAAC,IAAI,EAAE,OAAO,CAAC,UAAU,CAAQ,CAAC;QAEhD,MAAM,UAAU,GAAG,MAAM,CAAC,UAAU,GAAG,IAAI,CAAC,GAAG,CAAC,MAAM,CAAC,KAAK,EAAE,CAAC,CAAC,CAAC;QAEjE,iCAAiC;QACjC,OAAO,IAAI,CAAC,GAAG,CAAC,IAAI,EAAE,IAAI,CAAC,GAAG,CAAC,IAAI,EAAE,UAAU,CAAC,CAAC,CAAC;IACpD,CAAC;IAED;;OAEG;IACK,qBAAqB,CAAC,IAAY,EAAE,OAAgB;QAC1D,0EAA0E;QAC1E,MAAM,SAAS,GAAG,IAAI,CAAC,EAAE,CAAC,OAAO,CAAC;;;cAGxB,OAAO,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,KAAK;;;;;;KAM7B,CAAC,CAAC,GAAG,CAAC,IAAI,CAAQ,CAAC;QAEpB,OAAO,SAAS,EAAE,UAAU,IAAI,GAAG,CAAC;IACtC,CAAC;IAED;;OAEG;IACK,aAAa,CAAC,IAAY;QAChC,MAAM,KAAK,GAAG,IAAI,CAAC,EAAE,CAAC,OAAO,CAAC;;;;KAI7B,CAAC,CAAC,GAAG,CAAC,IAAI,CAAQ,CAAC;QAEpB,OAAO,KAAK,CAAC,KAAK,CAAC;IACrB,CAAC;IAED;;OAEG;IACK,mBAAmB,CAAC,UAAkB,EAAE,MAAc;QAC5D,oCAAoC;QACpC,kEAAkE;QAElE,MAAM,YAAY,GAAG,IAAI,CAAC,GAAG,CAAC,UAAU,GAAG,GAAG,EAAE,GAAG,CAAC,CAAC,CAAC,qBAAqB;QAC3E,MAAM,gBAAgB,GAAG,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,GAAG,CAAC,MAAM,CAAC,GAAG,GAAG,EAAE,GAAG,CAAC,CAAC,CAAC,oBAAoB;QAEpF,OAAO,YAAY,GAAG,gBAAgB,CAAC;IACzC,CAAC;IAED;;OAEG;IACK,KAAK,CAAC,mBAAmB;QAC/B,wFAAwF;QACxF,MAAM,kBAAkB,GAAG,IAAI,CAAC,EAAE,CAAC,OAAO,CAAC;;;;;KAK1C,CAAC,CAAC,GAAG,CAAC,IAAI,CAAC,MAAM,CAAC,aAAa,CAAU,CAAC;QAE3C,IAAI,SAAS,GAAG,CAAC,CAAC;QAElB,KAAK,MAAM,GAAG,IAAI,kBAAkB,EAAE,CAAC;YACrC,IAAI,CAAC;gBACH,IAAI,CAAC,WAAW,CAAC,eAAe,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;gBACzC,SAAS,EAAE,CAAC;YACd,CAAC;YAAC,OAAO,KAAK,EAAE,CAAC;gBACf,OAAO,CAAC,KAAK,CAAC,kDAAkD,GAAG,CAAC,EAAE,GAAG,EAAE,KAAK,CAAC,CAAC;YACpF,CAAC;QACH,CAAC;QAED,OAAO,SAAS,CAAC;IACnB,CAAC;IAED;;OAEG;IACK,KAAK,CAAC,iBAAiB;QAC7B,MAAM,kBAAkB,GAAG,IAAI,CAAC,EAAE,CAAC,OAAO,CAAC;;;;KAI1C,CAAC,CAAC,GAAG,EAAS,CAAC;QAEhB,MAAM,SAAS,GAAG,IAAI,CAAC,MAAM,CAAC,gBAAgB,GAAG,kBAAkB,CAAC,KAAK,CAAC;QAC1E,IAAI,SAAS,IAAI,CAAC,EAAE,CAAC;YACnB,OAAO,CAAC,CAAC;QACX,CAAC;QAED,4DAA4D;QAC5D,MAAM,UAAU,GAAG,IAAI,CAAC,EAAE,CAAC,OAAO,CAAC;;;;;;;;;;;;;;;;KAgBlC,CAAC,CAAC,GAAG,CAAC,IAAI,CAAC,MAAM,CAAC,aAAa,EAAE,SAAS,CAAU,CAAC;QAEtD,IAAI,OAAO,GAAG,CAAC,CAAC;QAEhB,KAAK,MAAM,SAAS,IAAI,UAAU,EAAE,CAAC;YACnC,MAAM,KAAK,GAAG,IAAI,CAAC,WAAW,CAAC,gBAAgB,CAAC;gBAC9C,IAAI,EAAE,SAAS,SAAS,CAAC,cAAc,SAAS;gBAChD,UAAU,EAAE,GAAG,SAAS,CAAC,cAAc,8BAA8B;gBACrE,WAAW,EAAE,SAAS,CAAC,YAAY;gBACnC,aAAa,EAAE,SAAS;gBACxB,SAAS,EAAE,IAAI,CAAC,GAAG,EAAE;gBACrB,UAAU,EAAE,CAAC;gBACb,MAAM,EAAE,SAAS;gBACjB,QAAQ,EAAE;oBACR,aAAa,EAAE,IAAI;oBACnB,iBAAiB,EAAE,SAAS,CAAC,kBAAkB;iBAChD;aACF,CAAC,CAAC;YAEH,OAAO,EAAE,CAAC;QACZ,CAAC;QAED,OAAO,OAAO,CAAC;IACjB,CAAC;IAED;;OAEG;IACK,KAAK,CAAC,UAAU;QACtB,MAAM,QAAQ,GAAG,IAAI,CAAC,MAAM,CAAC,cAAc,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,IAAI,CAAC;QAClE,MAAM,UAAU,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,IAAI,GAAG,QAAQ,GAAG,IAAI,CAAC;QAEvD,MAAM,MAAM,GAAG,IAAI,CAAC,EAAE,CAAC,OAAO,CAAC;;;;KAI9B,CAAC,CAAC,GAAG,CAAC,IAAI,CAAC,MAAM,CAAC,mBAAmB,EAAE,UAAU,CAAC,CAAC;QAEpD,OAAO,MAAM,CAAC,OAAO,CAAC;IACxB,CAAC;IAED;;OAEG;IACK,cAAc;QACpB,MAAM,KAAK,GAAG,IAAI,CAAC,EAAE,CAAC,OAAO,CAAC;;;;;;KAM7B,CAAC,CAAC,GAAG,EAAS,CAAC;QAEhB,OAAO;YACL,SAAS,EAAE,KAAK,EAAE,UAAU,IAAI,CAAC;YACjC,aAAa,EAAE,KAAK,EAAE,cAAc,IAAI,CAAC;SAC1C,CAAC;IACJ,CAAC;IAED;;OAEG;IACK,uBAAuB,CAAC,MAAqB;QACnD,MAAM,eAAe,GAAa,EAAE,CAAC;QAErC,IAAI,MAAM,CAAC,eAAe,KAAK,CAAC,EAAE,CAAC;YACjC,eAAe,CAAC,IAAI,CAAC,gFAAgF,CAAC,CAAC;QACzG,CAAC;QAED,IAAI,MAAM,CAAC,SAAS,GAAG,GAAG,EAAE,CAAC;YAC3B,eAAe,CAAC,IAAI,CAAC,8EAA8E,CAAC,CAAC;QACvG,CAAC;QAED,IAAI,MAAM,CAAC,aAAa,GAAG,GAAG,EAAE,CAAC;YAC/B,eAAe,CAAC,IAAI,CAAC,2FAA2F,CAAC,CAAC;QACpH,CAAC;QAED,IAAI,MAAM,CAAC,oBAAoB,GAAG,CAAC,EAAE,CAAC;YACpC,eAAe,CAAC,IAAI,CAAC,GAAG,MAAM,CAAC,oBAAoB,iEAAiE,CAAC,CAAC;QACxH,CAAC;QAED,IAAI,MAAM,CAAC,WAAW,GAAG,MAAM,CAAC,eAAe,EAAE,CAAC;YAChD,eAAe,CAAC,IAAI,CAAC,8EAA8E,CAAC,CAAC;QACvG,CAAC;QAED,OAAO,eAAe,CAAC;IACzB,CAAC;IAED;;OAEG;IACK,WAAW,CAAC,MAAqB;QACvC,OAAO,CAAC,GAAG,CAAC,6DAA6D,CAAC,CAAC;QAC3E,OAAO,CAAC,GAAG,CAAC,0BAA0B,CAAC,CAAC;QACxC,OAAO,CAAC,GAAG,CAAC,+DAA+D,CAAC,CAAC;QAC7E,OAAO,CAAC,GAAG,CAAC,qBAAqB,MAAM,CAAC,eAAe,IAAI,CAAC,CAAC;QAC7D,OAAO,CAAC,GAAG,CAAC,gBAAgB,IAAI,IAAI,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,WAAW,EAAE,IAAI,CAAC,CAAC;QAC1E,OAAO,CAAC,GAAG,CAAC,YAAY,CAAC,CAAC;QAC1B,OAAO,CAAC,GAAG,CAAC,2BAA2B,MAAM,CAAC,eAAe,EAAE,CAAC,CAAC;QACjE,OAAO,CAAC,GAAG,CAAC,uBAAuB,MAAM,CAAC,WAAW,EAAE,CAAC,CAAC;QACzD,OAAO,CAAC,GAAG,CAAC,gCAAgC,MAAM,CAAC,oBAAoB,EAAE,CAAC,CAAC;QAC3E,OAAO,CAAC,GAAG,CAAC,8BAA8B,MAAM,CAAC,kBAAkB,IAAI,CAAC,CAAC;QACzE,OAAO,CAAC,GAAG,CAAC,eAAe,CAAC,CAAC;QAC7B,OAAO,CAAC,GAAG,CAAC,qBAAqB,MAAM,CAAC,SAAS,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;QAChE,OAAO,CAAC,GAAG,CAAC,yBAAyB,MAAM,CAAC,aAAa,CAAC,OAAO,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC;QAE1E,IAAI,MAAM,CAAC,eAAe,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACtC,OAAO,CAAC,GAAG,CAAC,oBAAoB,CAAC,CAAC;YAClC,MAAM,CAAC,eAAe,CAAC,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,OAAO,CAAC,GAAG,CAAC,SAAS,GAAG,EAAE,CAAC,CAAC,CAAC;YACnE,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;QAClB,CAAC;QAED,OAAO,CAAC,GAAG,CAAC,+DAA+D,CAAC,CAAC;IAC/E,CAAC;IAED;;OAEG;IACH,YAAY,CAAC,MAA8B;QACzC,IAAI,CAAC,MAAM,GAAG,EAAE,GAAG,IAAI,CAAC,MAAM,EAAE,GAAG,MAAM,EAAE,CAAC;IAC9C,CAAC;CACF","sourcesContent":["/**\n * Nightly Learner - Automated Causal Discovery and Consolidation\n *\n * Runs as a background job to:\n * 1. Discover new causal edges from episode patterns\n * 2. Run A/B experiments on promising hypotheses\n * 3. Calculate uplift for completed experiments\n * 4. Prune low-confidence edges\n * 5. Update rerank weights based on performance\n *\n * Based on doubly robust learner:\n * τ̂(x) = μ1(x) − μ0(x) + [a*(y−μ1(x)) / e(x)] − [(1−a)*(y−μ0(x)) / (1−e(x))]\n *\n * v2.0.0-alpha.3 Features:\n * - FlashAttention for memory-efficient episodic consolidation\n * - Block-wise computation for large episode buffers\n * - Feature flag: ENABLE_FLASH_CONSOLIDATION (default: false)\n * - 100% backward compatible with fallback to standard consolidation\n */\n\n// Database type from db-fallback\ntype Database = any;\nimport { CausalMemoryGraph, CausalEdge } from './CausalMemoryGraph.js';\nimport { ReflexionMemory } from './ReflexionMemory.js';\nimport { SkillLibrary } from './SkillLibrary.js';\nimport { EmbeddingService } from './EmbeddingService.js';\nimport { AttentionService, type FlashAttentionConfig } from '../utils/LegacyAttentionAdapter.js';\nimport { cosineSimilarity } from '../utils/vector-math.js';\n\nexport interface LearnerConfig {\n  minSimilarity: number; // Min similarity to consider for causal edge (default: 0.7)\n  minSampleSize: number; // Min observations for uplift calculation (default: 30)\n  confidenceThreshold: number; // Min confidence to keep edge (default: 0.6)\n  upliftThreshold: number; // Min absolute uplift to consider significant (default: 0.05)\n  pruneOldEdges: boolean; // Remove edges older than X days (default: true)\n  edgeMaxAgeDays: number; // Max age for edges (default: 90)\n  autoExperiments: boolean; // Automatically create A/B experiments (default: true)\n  experimentBudget: number; // Max experiments to run concurrently (default: 10)\n\n  // v2 features\n  /** Enable FlashAttention for consolidation (default: false) */\n  ENABLE_FLASH_CONSOLIDATION?: boolean;\n  /** FlashAttention configuration */\n  flashConfig?: Partial<FlashAttentionConfig>;\n}\n\nexport interface LearnerReport {\n  timestamp: number;\n  executionTimeMs: number;\n  edgesDiscovered: number;\n  edgesPruned: number;\n  experimentsCompleted: number;\n  experimentsCreated: number;\n  avgUplift: number;\n  avgConfidence: number;\n  recommendations: string[];\n}\n\nexport class NightlyLearner {\n  private db: Database;\n  private causalGraph: CausalMemoryGraph;\n  private reflexion: ReflexionMemory;\n  private skillLibrary: SkillLibrary;\n  private embedder: EmbeddingService;\n  private attentionService?: AttentionService;\n\n  constructor(\n    db: Database,\n    embedder: EmbeddingService,\n    private config: LearnerConfig = {\n      minSimilarity: 0.7,\n      minSampleSize: 30,\n      confidenceThreshold: 0.6,\n      upliftThreshold: 0.05,\n      pruneOldEdges: true,\n      edgeMaxAgeDays: 90,\n      autoExperiments: true,\n      experimentBudget: 10,\n      ENABLE_FLASH_CONSOLIDATION: false,\n    }\n  ) {\n    this.db = db;\n    this.embedder = embedder;\n    this.causalGraph = new CausalMemoryGraph(db);\n    this.reflexion = new ReflexionMemory(db, embedder);\n    this.skillLibrary = new SkillLibrary(db, embedder);\n\n    // Initialize AttentionService if FlashAttention enabled\n    if (this.config.ENABLE_FLASH_CONSOLIDATION) {\n      this.attentionService = new AttentionService(db, {\n        flash: {\n          enabled: true,\n          ...this.config.flashConfig,\n        },\n      });\n    }\n  }\n\n  /**\n   * Main learning job - runs all discovery and consolidation tasks\n   */\n  async run(): Promise<LearnerReport> {\n    console.log('\\n🌙 Nightly Learner Starting...\\n');\n    const startTime = Date.now();\n\n    const report: LearnerReport = {\n      timestamp: startTime,\n      executionTimeMs: 0,\n      edgesDiscovered: 0,\n      edgesPruned: 0,\n      experimentsCompleted: 0,\n      experimentsCreated: 0,\n      avgUplift: 0,\n      avgConfidence: 0,\n      recommendations: []\n    };\n\n    try {\n      // Step 1: Discover new causal edges\n      console.log('📊 Discovering causal edges from episode patterns...');\n      report.edgesDiscovered = await this.discoverCausalEdges();\n      console.log(`   ✓ Discovered ${report.edgesDiscovered} new edges\\n`);\n\n      // Step 2: Complete running experiments\n      console.log('🧪 Completing A/B experiments...');\n      report.experimentsCompleted = await this.completeExperiments();\n      console.log(`   ✓ Completed ${report.experimentsCompleted} experiments\\n`);\n\n      // Step 3: Create new experiments (if enabled)\n      if (this.config.autoExperiments) {\n        console.log('🔬 Creating new A/B experiments...');\n        report.experimentsCreated = await this.createExperiments();\n        console.log(`   ✓ Created ${report.experimentsCreated} new experiments\\n`);\n      }\n\n      // Step 4: Prune low-confidence edges\n      if (this.config.pruneOldEdges) {\n        console.log('🧹 Pruning low-confidence edges...');\n        report.edgesPruned = await this.pruneEdges();\n        console.log(`   ✓ Pruned ${report.edgesPruned} edges\\n`);\n      }\n\n      // Step 5: Calculate statistics\n      const stats = this.calculateStats();\n      report.avgUplift = stats.avgUplift;\n      report.avgConfidence = stats.avgConfidence;\n\n      // Step 6: Generate recommendations\n      report.recommendations = this.generateRecommendations(report);\n\n      report.executionTimeMs = Date.now() - startTime;\n\n      console.log('✅ Nightly Learner Completed\\n');\n      this.printReport(report);\n\n      return report;\n    } catch (error) {\n      console.error('❌ Nightly Learner Failed:', error);\n      throw error;\n    }\n  }\n\n  /**\n   * Discover causal edges using doubly robust learner\n   *\n   * τ̂(x) = μ1(x) − μ0(x) + [a*(y−μ1(x)) / e(x)] − [(1−a)*(y−μ0(x)) / (1−e(x))]\n   *\n   * Where:\n   * - μ1(x) = outcome model for treatment\n   * - μ0(x) = outcome model for control\n   * - e(x) = propensity score (probability of treatment)\n   * - a = treatment indicator\n   * - y = observed outcome\n   *\n   * v2: Uses FlashAttention for memory-efficient consolidation if enabled\n   */\n  async discover(config: {\n    minAttempts?: number;\n    minSuccessRate?: number;\n    minConfidence?: number;\n    dryRun?: boolean;\n  }): Promise<CausalEdge[]> {\n    const edges: CausalEdge[] = [];\n    const count = await this.discoverCausalEdges();\n\n    // If dryRun, return empty array since we didn't actually create edges\n    if (config.dryRun) {\n      return edges;\n    }\n\n    // Return discovered edges (for non-dry runs)\n    // Note: In a real implementation, we'd track and return the actual edges created\n    return edges;\n  }\n\n  /**\n   * Consolidate episodic memories using FlashAttention (v2 feature)\n   *\n   * Processes large episode buffers efficiently using block-wise computation.\n   * Identifies patterns and relationships across episodes for causal edge discovery.\n   *\n   * @param sessionId - Session to consolidate (optional, processes all if not provided)\n   * @returns Number of edges discovered through consolidation\n   */\n  async consolidateEpisodes(sessionId?: string): Promise<{\n    edgesDiscovered: number;\n    episodesProcessed: number;\n    metrics?: {\n      computeTimeMs: number;\n      peakMemoryMB: number;\n      blocksProcessed: number;\n    };\n  }> {\n    if (!this.attentionService) {\n      // Fallback: Use standard discovery without attention\n      const edgesDiscovered = await this.discoverCausalEdges();\n      return {\n        edgesDiscovered,\n        episodesProcessed: 0,\n      };\n    }\n\n    // Get episodes to consolidate\n    const episodes = sessionId\n      ? this.db.prepare(`\n          SELECT id, task, output, reward FROM episodes\n          WHERE session_id = ?\n          ORDER BY ts ASC\n        `).all(sessionId) as any[]\n      : this.db.prepare(`\n          SELECT id, task, output, reward FROM episodes\n          ORDER BY ts ASC\n          LIMIT 1000\n        `).all() as any[];\n\n    if (episodes.length === 0) {\n      return { edgesDiscovered: 0, episodesProcessed: 0 };\n    }\n\n    // Generate embeddings for all episodes\n    const episodeEmbeddings: Float32Array[] = [];\n    for (const episode of episodes) {\n      const text = `${episode.task}: ${episode.output}`;\n      const embedding = await this.embedder.embed(text);\n      episodeEmbeddings.push(embedding);\n    }\n\n    // Prepare queries (each episode is a query)\n    const dim = 384;\n    const queries = new Float32Array(episodes.length * dim);\n    const keys = new Float32Array(episodes.length * dim);\n    const values = new Float32Array(episodes.length * dim);\n\n    episodeEmbeddings.forEach((embedding, idx) => {\n      queries.set(embedding, idx * dim);\n      keys.set(embedding, idx * dim);\n      values.set(embedding, idx * dim);\n    });\n\n    // Apply FlashAttention for memory-efficient consolidation\n    const attentionResult = await this.attentionService.flashAttention(queries, keys, values);\n\n    // Analyze attention output to discover causal relationships\n    let edgesDiscovered = 0;\n    const consolidatedEmbeddings = attentionResult.output;\n\n    // For each episode, find similar episodes in consolidated space\n    for (let i = 0; i < episodes.length; i++) {\n      const queryEmb = consolidatedEmbeddings.slice(i * dim, (i + 1) * dim);\n\n      // Find top-k similar episodes\n      const similarities: Array<{ idx: number; score: number }> = [];\n      for (let j = 0; j < episodes.length; j++) {\n        if (i === j) continue;\n\n        const keyEmb = consolidatedEmbeddings.slice(j * dim, (j + 1) * dim);\n        const score = cosineSimilarity(queryEmb, keyEmb);\n\n        if (score >= this.config.minSimilarity) {\n          similarities.push({ idx: j, score });\n        }\n      }\n\n      // Sort by similarity\n      similarities.sort((a, b) => b.score - a.score);\n\n      // Create causal edges for top matches\n      for (const { idx, score } of similarities.slice(0, 5)) {\n        // Only create edge if temporal sequence is correct\n        if (idx > i) {\n          const uplift = episodes[idx].reward - episodes[i].reward;\n\n          if (Math.abs(uplift) >= this.config.upliftThreshold) {\n            await this.causalGraph.addCausalEdge({\n              fromMemoryId: episodes[i].id,\n              fromMemoryType: 'episode',\n              toMemoryId: episodes[idx].id,\n              toMemoryType: 'episode',\n              similarity: score,\n              uplift,\n              confidence: score,\n              sampleSize: 1,\n              mechanism: 'flash_attention_consolidation',\n              metadata: {\n                consolidationMethod: 'flash_attention',\n                blockSize: this.config.flashConfig?.blockSize || 256,\n              },\n            });\n\n            edgesDiscovered++;\n          }\n        }\n      }\n    }\n\n    return {\n      edgesDiscovered,\n      episodesProcessed: episodes.length,\n      metrics: attentionResult.metrics,\n    };\n  }\n\n  private async discoverCausalEdges(): Promise<number> {\n    let discovered = 0;\n\n    // Find episode pairs with high similarity and temporal sequence\n    const candidatePairs = this.db.prepare(`\n      SELECT\n        e1.id as from_id,\n        e1.task as from_task,\n        e1.reward as from_reward,\n        e2.id as to_id,\n        e2.task as to_task,\n        e2.reward as to_reward,\n        e2.ts - e1.ts as time_diff\n      FROM episodes e1\n      JOIN episodes e2 ON e1.session_id = e2.session_id\n      WHERE e1.id != e2.id\n        AND e2.ts > e1.ts\n        AND e2.ts - e1.ts < 3600 -- Within 1 hour\n      ORDER BY e1.id, e2.ts\n      LIMIT 1000\n    `).all() as any[];\n\n    // Better-sqlite3 best practice: Prepare statements OUTSIDE loops for better performance\n    const checkExistingStmt = this.db.prepare(`\n      SELECT id FROM causal_edges\n      WHERE from_memory_id = ? AND to_memory_id = ?\n    `);\n\n    for (const pair of candidatePairs) {\n      // Check if edge already exists\n      const existing = checkExistingStmt.get(pair.from_id, pair.to_id);\n\n      if (existing) continue;\n\n      // Calculate propensity score e(x) - probability of treatment\n      // Simplified: use frequency of from_task in session\n      const propensity = this.calculatePropensity(pair.from_id);\n\n      // Calculate outcome models μ1(x) and μ0(x)\n      const mu1 = this.calculateOutcomeModel(pair.from_task, true);  // With treatment\n      const mu0 = this.calculateOutcomeModel(pair.from_task, false); // Without treatment\n\n      // Calculate doubly robust estimator\n      const a = 1; // This is a treated observation\n      const y = pair.to_reward;\n      const doublyRobustEstimate = (mu1 - mu0) + (a * (y - mu1) / propensity);\n\n      // Calculate confidence based on sample size and variance\n      const sampleSize = this.getSampleSize(pair.from_task);\n      const confidence = this.calculateConfidence(sampleSize, doublyRobustEstimate);\n\n      // Only add if meets thresholds\n      if (Math.abs(doublyRobustEstimate) >= this.config.upliftThreshold && confidence >= this.config.confidenceThreshold) {\n        const edge: CausalEdge = {\n          fromMemoryId: pair.from_id,\n          fromMemoryType: 'episode',\n          toMemoryId: pair.to_id,\n          toMemoryType: 'episode',\n          similarity: 0.8, // Simplified - would use embedding similarity in production\n          uplift: doublyRobustEstimate,\n          confidence,\n          sampleSize,\n          mechanism: `${pair.from_task} → ${pair.to_task} (doubly robust)`,\n          metadata: {\n            propensity,\n            mu1,\n            mu0,\n            discoveredAt: Date.now()\n          }\n        };\n\n        this.causalGraph.addCausalEdge(edge);\n        discovered++;\n      }\n    }\n\n    return discovered;\n  }\n\n  /**\n   * Calculate propensity score e(x) - probability of treatment given context\n   */\n  private calculatePropensity(episodeId: number): number {\n    const episode = this.db.prepare('SELECT task, session_id FROM episodes WHERE id = ?').get(episodeId) as any;\n\n    // Count occurrences of this task type in session\n    const counts = this.db.prepare(`\n      SELECT\n        COUNT(*) as total,\n        SUM(CASE WHEN task = ? THEN 1 ELSE 0 END) as task_count\n      FROM episodes\n      WHERE session_id = ?\n    `).get(episode.task, episode.session_id) as any;\n\n    const propensity = counts.task_count / Math.max(counts.total, 1);\n\n    // Clip to avoid division by zero\n    return Math.max(0.01, Math.min(0.99, propensity));\n  }\n\n  /**\n   * Calculate outcome model μ(x) - expected outcome given treatment status\n   */\n  private calculateOutcomeModel(task: string, treated: boolean): number {\n    // Get average reward for episodes with/without this task in their history\n    const avgReward = this.db.prepare(`\n      SELECT AVG(reward) as avg_reward\n      FROM episodes\n      WHERE ${treated ? '' : 'NOT'} EXISTS (\n        SELECT 1 FROM episodes e2\n        WHERE e2.session_id = episodes.session_id\n          AND e2.task = ?\n          AND e2.ts < episodes.ts\n      )\n    `).get(task) as any;\n\n    return avgReward?.avg_reward || 0.5;\n  }\n\n  /**\n   * Get sample size for a task type\n   */\n  private getSampleSize(task: string): number {\n    const count = this.db.prepare(`\n      SELECT COUNT(*) as count\n      FROM episodes\n      WHERE task = ?\n    `).get(task) as any;\n\n    return count.count;\n  }\n\n  /**\n   * Calculate confidence based on sample size and effect size\n   */\n  private calculateConfidence(sampleSize: number, uplift: number): number {\n    // Simplified confidence calculation\n    // In production, use proper statistical methods (bootstrap, etc.)\n\n    const sampleFactor = Math.min(sampleSize / 100, 1.0); // Max at 100 samples\n    const effectSizeFactor = Math.min(Math.abs(uplift) / 0.5, 1.0); // Max at 0.5 uplift\n\n    return sampleFactor * effectSizeFactor;\n  }\n\n  /**\n   * Complete running A/B experiments and calculate uplift\n   */\n  private async completeExperiments(): Promise<number> {\n    // Better-sqlite3 best practice: Prepare statements OUTSIDE loops for better performance\n    const runningExperiments = this.db.prepare(`\n      SELECT id, start_time, sample_size\n      FROM causal_experiments\n      WHERE status = 'running'\n        AND sample_size >= ?\n    `).all(this.config.minSampleSize) as any[];\n\n    let completed = 0;\n\n    for (const exp of runningExperiments) {\n      try {\n        this.causalGraph.calculateUplift(exp.id);\n        completed++;\n      } catch (error) {\n        console.error(`   ⚠ Failed to calculate uplift for experiment ${exp.id}:`, error);\n      }\n    }\n\n    return completed;\n  }\n\n  /**\n   * Create new A/B experiments for promising hypotheses\n   */\n  private async createExperiments(): Promise<number> {\n    const currentExperiments = this.db.prepare(`\n      SELECT COUNT(*) as count\n      FROM causal_experiments\n      WHERE status = 'running'\n    `).get() as any;\n\n    const available = this.config.experimentBudget - currentExperiments.count;\n    if (available <= 0) {\n      return 0;\n    }\n\n    // Find promising task pairs that don't have experiments yet\n    const candidates = this.db.prepare(`\n      SELECT DISTINCT\n        e1.task as treatment_task,\n        e1.id as treatment_id,\n        COUNT(e2.id) as potential_outcomes\n      FROM episodes e1\n      JOIN episodes e2 ON e1.session_id = e2.session_id\n      WHERE e2.ts > e1.ts\n        AND NOT EXISTS (\n          SELECT 1 FROM causal_experiments\n          WHERE treatment_id = e1.id\n        )\n      GROUP BY e1.task, e1.id\n      HAVING COUNT(e2.id) >= ?\n      ORDER BY COUNT(e2.id) DESC\n      LIMIT ?\n    `).all(this.config.minSampleSize, available) as any[];\n\n    let created = 0;\n\n    for (const candidate of candidates) {\n      const expId = this.causalGraph.createExperiment({\n        name: `Auto: ${candidate.treatment_task} Impact`,\n        hypothesis: `${candidate.treatment_task} affects downstream outcomes`,\n        treatmentId: candidate.treatment_id,\n        treatmentType: 'episode',\n        startTime: Date.now(),\n        sampleSize: 0,\n        status: 'running',\n        metadata: {\n          autoGenerated: true,\n          potentialOutcomes: candidate.potential_outcomes\n        }\n      });\n\n      created++;\n    }\n\n    return created;\n  }\n\n  /**\n   * Prune old or low-confidence edges\n   */\n  private async pruneEdges(): Promise<number> {\n    const maxAgeMs = this.config.edgeMaxAgeDays * 24 * 60 * 60 * 1000;\n    const cutoffTime = Date.now() / 1000 - maxAgeMs / 1000;\n\n    const result = this.db.prepare(`\n      DELETE FROM causal_edges\n      WHERE confidence < ?\n        OR created_at < ?\n    `).run(this.config.confidenceThreshold, cutoffTime);\n\n    return result.changes;\n  }\n\n  /**\n   * Calculate overall statistics\n   */\n  private calculateStats(): { avgUplift: number; avgConfidence: number } {\n    const stats = this.db.prepare(`\n      SELECT\n        AVG(ABS(uplift)) as avg_uplift,\n        AVG(confidence) as avg_confidence\n      FROM causal_edges\n      WHERE uplift IS NOT NULL\n    `).get() as any;\n\n    return {\n      avgUplift: stats?.avg_uplift || 0,\n      avgConfidence: stats?.avg_confidence || 0\n    };\n  }\n\n  /**\n   * Generate recommendations based on learning results\n   */\n  private generateRecommendations(report: LearnerReport): string[] {\n    const recommendations: string[] = [];\n\n    if (report.edgesDiscovered === 0) {\n      recommendations.push('No new causal edges discovered. Consider collecting more diverse episode data.');\n    }\n\n    if (report.avgUplift < 0.1) {\n      recommendations.push('Average uplift is low. Review task sequences for optimization opportunities.');\n    }\n\n    if (report.avgConfidence < 0.7) {\n      recommendations.push('Average confidence is below target. Increase sample sizes or refine hypothesis selection.');\n    }\n\n    if (report.experimentsCompleted > 0) {\n      recommendations.push(`${report.experimentsCompleted} experiments completed. Review results for actionable insights.`);\n    }\n\n    if (report.edgesPruned > report.edgesDiscovered) {\n      recommendations.push('More edges pruned than discovered. Consider adjusting confidence thresholds.');\n    }\n\n    return recommendations;\n  }\n\n  /**\n   * Print report to console\n   */\n  private printReport(report: LearnerReport): void {\n    console.log('═══════════════════════════════════════════════════════════');\n    console.log('  Nightly Learner Report');\n    console.log('═══════════════════════════════════════════════════════════\\n');\n    console.log(`  Execution Time: ${report.executionTimeMs}ms`);\n    console.log(`  Timestamp: ${new Date(report.timestamp).toISOString()}\\n`);\n    console.log('  Results:');\n    console.log(`    • Edges Discovered: ${report.edgesDiscovered}`);\n    console.log(`    • Edges Pruned: ${report.edgesPruned}`);\n    console.log(`    • Experiments Completed: ${report.experimentsCompleted}`);\n    console.log(`    • Experiments Created: ${report.experimentsCreated}\\n`);\n    console.log('  Statistics:');\n    console.log(`    • Avg Uplift: ${report.avgUplift.toFixed(3)}`);\n    console.log(`    • Avg Confidence: ${report.avgConfidence.toFixed(3)}\\n`);\n\n    if (report.recommendations.length > 0) {\n      console.log('  Recommendations:');\n      report.recommendations.forEach(rec => console.log(`    • ${rec}`));\n      console.log('');\n    }\n\n    console.log('═══════════════════════════════════════════════════════════\\n');\n  }\n\n  /**\n   * Update learner configuration\n   */\n  updateConfig(config: Partial<LearnerConfig>): void {\n    this.config = { ...this.config, ...config };\n  }\n}\n"]}