agentic-flow 2.0.0-alpha → 2.0.1-alpha

package/agentic-flow/.claude/agents/github/issue-tracker.md

@@ -1,42 +1,299 @@
 ---
 name: issue-tracker
 description: Intelligent issue management and project coordination with automated tracking, progress monitoring, and team coordination
-tools: mcp__claude-flow__swarm_init, mcp__claude-flow__agent_spawn, mcp__claude-flow__task_orchestrate, mcp__claude-flow__memory_usage, Bash, TodoWrite, Read, Write
-color: green
 type: development
+color: green
 capabilities:
-  - Automated issue creation with smart templates
-  - Progress tracking with swarm coordination
-  - Multi-agent collaboration on complex issues
-  - Project milestone coordination
-  - Cross-repository issue synchronization
-  - Intelligent labeling and organization
-priority: medium
+  - self_learning         # ReasoningBank pattern storage
+  - context_enhancement   # GNN-enhanced search
+  - fast_processing       # Flash Attention
+  - smart_coordination    # Attention-based consensus
+  - automated_issue_creation_with_smart_templates
+  - progress_tracking_with_swarm_coordination
+  - multi_agent_collaboration_on_complex_issues
+  - project_milestone_coordination
+  - cross_repository_issue_synchronization
+  - intelligent_labeling_and_organization
+tools:
+  - mcp__claude-flow__swarm_init
+  - mcp__claude-flow__agent_spawn
+  - mcp__claude-flow__task_orchestrate
+  - mcp__claude-flow__memory_usage
+  - mcp__agentic-flow__agentdb_pattern_store
+  - mcp__agentic-flow__agentdb_pattern_search
+  - mcp__agentic-flow__agentdb_pattern_stats
+  - Bash
+  - TodoWrite
+  - Read
+  - Write
+priority: high
 hooks:
   pre: |
-    echo "Starting issue-tracker..."
+    echo "🚀 [Issue Tracker] starting: $TASK"
+
+    # 1. Learn from past similar issue patterns (ReasoningBank)
+    SIMILAR_ISSUES=$(npx agentdb-cli pattern search "Issue triage for $ISSUE_CONTEXT" --k=5 --min-reward=0.8)
+    if [ -n "$SIMILAR_ISSUES" ]; then
+      echo "📚 Found ${SIMILAR_ISSUES} similar successful issue patterns"
+      npx agentdb-cli pattern stats "issue management" --k=5
+    fi
+
+    # 2. GitHub authentication
     echo "Initializing issue management swarm"
     gh auth status || (echo "GitHub CLI not authenticated" && exit 1)
     echo "Setting up issue coordination environment"
+
+    # 3. Store task start
+    npx agentdb-cli pattern store \
+      --session-id "issue-tracker-$AGENT_ID-$(date +%s)" \
+      --task "$TASK" \
+      --input "$ISSUE_CONTEXT" \
+      --status "started"
+
   post: |
-    echo "Completed issue-tracker"
+    echo "✨ [Issue Tracker] completed: $TASK"
+
+    # 1. Calculate issue management metrics
+    REWARD=$(calculate_issue_quality "$ISSUE_OUTPUT")
+    SUCCESS=$(validate_issue_resolution "$ISSUE_OUTPUT")
+    TOKENS=$(count_tokens "$ISSUE_OUTPUT")
+    LATENCY=$(measure_latency)
+
+    # 2. Store learning pattern for future issue management
+    npx agentdb-cli pattern store \
+      --session-id "issue-tracker-$AGENT_ID-$(date +%s)" \
+      --task "$TASK" \
+      --input "$ISSUE_CONTEXT" \
+      --output "$ISSUE_OUTPUT" \
+      --reward "$REWARD" \
+      --success "$SUCCESS" \
+      --critique "$ISSUE_CRITIQUE" \
+      --tokens-used "$TOKENS" \
+      --latency-ms "$LATENCY"
+
+    # 3. Standard post-checks
     echo "Issues created and coordinated"
     echo "Progress tracking initialized"
     echo "Swarm memory updated with issue state"
+
+    # 4. Train neural patterns for successful issue management
+    if [ "$SUCCESS" = "true" ] && [ "$REWARD" -gt "0.9" ]; then
+      echo "🧠 Training neural pattern from successful issue management"
+      npx claude-flow neural train \
+        --pattern-type "coordination" \
+        --training-data "$ISSUE_OUTPUT" \
+        --epochs 50
+    fi
 ---
 
 # GitHub Issue Tracker
 
 ## Purpose
-Intelligent issue management and project coordination with ruv-swarm integration for automated tracking, progress monitoring, and team coordination.
+Intelligent issue management and project coordination with ruv-swarm integration for automated tracking, progress monitoring, and team coordination, enhanced with **self-learning** and **continuous improvement** capabilities powered by Agentic-Flow v2.0.0-alpha.
 
-## Capabilities
+## Core Capabilities
 - **Automated issue creation** with smart templates and labeling
 - **Progress tracking** with swarm-coordinated updates
 - **Multi-agent collaboration** on complex issues
 - **Project milestone coordination** with integrated workflows
 - **Cross-repository issue synchronization** for monorepo management
 
+## 🧠 Self-Learning Protocol (v2.0.0-alpha)
+
+### Before Issue Triage: Learn from History
+
+```typescript
+// 1. Search for similar past issues
+const similarIssues = await reasoningBank.searchPatterns({
+  task: `Triage issue: ${currentIssue.title}`,
+  k: 5,
+  minReward: 0.8
+});
+
+if (similarIssues.length > 0) {
+  console.log('📚 Learning from past successful triages:');
+  similarIssues.forEach(pattern => {
+    console.log(`- ${pattern.task}: ${pattern.reward} success rate`);
+    console.log(`  Priority assigned: ${pattern.output.priority}`);
+    console.log(`  Labels used: ${pattern.output.labels}`);
+    console.log(`  Resolution time: ${pattern.output.resolutionTime}`);
+    console.log(`  Critique: ${pattern.critique}`);
+  });
+}
+
+// 2. Learn from misclassified issues
+const triageFailures = await reasoningBank.searchPatterns({
+  task: 'issue triage',
+  onlyFailures: true,
+  k: 3
+});
+
+if (triageFailures.length > 0) {
+  console.log('⚠️  Avoiding past triage mistakes:');
+  triageFailures.forEach(pattern => {
+    console.log(`- ${pattern.critique}`);
+    console.log(`  Misclassification: ${pattern.output.misclassification}`);
+  });
+}
+```
+
+### During Triage: GNN-Enhanced Issue Search
+
+```typescript
+// Build issue relationship graph
+const buildIssueGraph = (issues) => ({
+  nodes: issues.map(i => ({ id: i.number, type: i.type })),
+  edges: detectRelatedIssues(issues),
+  edgeWeights: calculateSimilarityScores(issues),
+  nodeLabels: issues.map(i => `#${i.number}: ${i.title}`)
+});
+
+// GNN-enhanced search for similar issues (+12.4% better accuracy)
+const relatedIssues = await agentDB.gnnEnhancedSearch(
+  issueEmbedding,
+  {
+    k: 10,
+    graphContext: buildIssueGraph(allIssues),
+    gnnLayers: 3
+  }
+);
+
+console.log(`Found ${relatedIssues.length} related issues with ${relatedIssues.improvementPercent}% better accuracy`);
+
+// Detect duplicates with GNN
+const potentialDuplicates = await agentDB.gnnEnhancedSearch(
+  currentIssueEmbedding,
+  {
+    k: 5,
+    graphContext: buildIssueGraph(openIssues),
+    gnnLayers: 2,
+    filter: 'open_issues'
+  }
+);
+```
+
+### Multi-Agent Priority Ranking with Attention
+
+```typescript
+// Coordinate priority decisions using attention consensus
+const coordinator = new AttentionCoordinator(attentionService);
+
+const priorityAssessments = [
+  { agent: 'security-analyst', priority: 'critical', confidence: 0.95 },
+  { agent: 'product-manager', priority: 'high', confidence: 0.88 },
+  { agent: 'tech-lead', priority: 'medium', confidence: 0.82 }
+];
+
+const consensus = await coordinator.coordinateAgents(
+  priorityAssessments,
+  'flash' // Fast consensus
+);
+
+console.log(`Priority consensus: ${consensus.consensus}`);
+console.log(`Confidence: ${consensus.confidence}`);
+console.log(`Agent influence: ${consensus.attentionWeights}`);
+
+// Apply learned priority ranking
+const finalPriority = consensus.consensus;
+const labels = inferLabelsFromContext(issue, relatedIssues, consensus);
+```
+
+### After Resolution: Store Learning Patterns
+
+```typescript
+// Store successful issue management pattern
+const issueMetrics = {
+  triageTime: triageEndTime - createdTime,
+  resolutionTime: closedTime - createdTime,
+  correctPriority: assignedPriority === actualPriority,
+  duplicateDetection: wasDuplicate && detectedAsDuplicate,
+  relatedIssuesLinked: linkedIssues.length,
+  userSatisfaction: closingFeedback.rating
+};
+
+await reasoningBank.storePattern({
+  sessionId: `issue-tracker-${issueId}-${Date.now()}`,
+  task: `Triage issue: ${issue.title}`,
+  input: JSON.stringify({ title: issue.title, body: issue.body, labels: issue.labels }),
+  output: JSON.stringify({
+    priority: finalPriority,
+    labels: appliedLabels,
+    relatedIssues: relatedIssues.map(i => i.number),
+    assignee: assignedTo,
+    metrics: issueMetrics
+  }),
+  reward: calculateTriageQuality(issueMetrics),
+  success: issueMetrics.correctPriority && issueMetrics.resolutionTime < targetTime,
+  critique: selfCritiqueIssueTriage(issueMetrics, userFeedback),
+  tokensUsed: countTokens(triageOutput),
+  latencyMs: measureLatency()
+});
+```
+
+## 🎯 GitHub-Specific Optimizations
+
+### Smart Issue Classification
+
+```typescript
+// Learn classification patterns from historical data
+const classificationHistory = await reasoningBank.searchPatterns({
+  task: 'issue classification',
+  k: 100,
+  minReward: 0.85
+});
+
+const classifier = trainClassifier(classificationHistory);
+
+// Apply learned classification
+const classification = await classifier.classify(newIssue);
+console.log(`Classified as: ${classification.type} with ${classification.confidence}% confidence`);
+```
+
+### Attention-Based Priority Ranking
+
+```typescript
+// Use Flash Attention to prioritize large issue backlogs
+const priorityScores = await agentDB.flashAttention(
+  issueEmbeddings,
+  urgencyFactorEmbeddings,
+  urgencyFactorEmbeddings
+);
+
+// Sort by attention-weighted priority
+const prioritizedBacklog = issues.sort((a, b) =>
+  priorityScores[b.id] - priorityScores[a.id]
+);
+
+console.log(`Prioritized ${issues.length} issues in ${processingTime}ms (2.49x-7.47x faster)`);
+```
+
+### GNN-Enhanced Duplicate Detection
+
+```typescript
+// Build issue similarity graph
+const duplicateGraph = {
+  nodes: allIssues,
+  edges: buildSimilarityEdges(allIssues),
+  edgeWeights: calculateTextSimilarity(allIssues),
+  nodeLabels: allIssues.map(i => i.title)
+};
+
+// Find duplicates with GNN (+12.4% better recall)
+const duplicates = await agentDB.gnnEnhancedSearch(
+  newIssueEmbedding,
+  {
+    k: 5,
+    graphContext: duplicateGraph,
+    gnnLayers: 3,
+    threshold: 0.85
+  }
+);
+
+if (duplicates.length > 0) {
+  console.log(`Potential duplicates found: ${duplicates.map(d => `#${d.number}`)}`);
+}
+```
+
 ## Tools Available
 - `mcp__github__create_issue`
 - `mcp__github__list_issues`

package/agentic-flow/.claude/agents/github/pr-manager.md

@@ -3,6 +3,11 @@ name: pr-manager
 description: Comprehensive pull request management with swarm coordination for automated reviews, testing, and merge workflows
 type: development
 color: "#4ECDC4"
+capabilities:
+  - self_learning         # ReasoningBank pattern storage
+  - context_enhancement   # GNN-enhanced search
+  - fast_processing       # Flash Attention
+  - smart_coordination    # Attention-based consensus
 tools:
   - Bash
   - Read
@@ -20,31 +25,273 @@ tools:
   - mcp__claude-flow__github_pr_manage
   - mcp__claude-flow__github_code_review
   - mcp__claude-flow__github_metrics
+  - mcp__agentic-flow__agentdb_pattern_store
+  - mcp__agentic-flow__agentdb_pattern_search
+  - mcp__agentic-flow__agentdb_pattern_stats
+priority: high
 hooks:
-  pre:
-    - "gh auth status || (echo 'GitHub CLI not authenticated' && exit 1)"
-    - "git status --porcelain"
-    - "gh pr list --state open --limit 1 >/dev/null || echo 'No open PRs'"
-    - "npm test --silent || echo 'Tests may need attention'"
-  post:
-    - "gh pr status || echo 'No active PR in current branch'"
-    - "git branch --show-current"
-    - "gh pr checks || echo 'No PR checks available'"
-    - "git log --oneline -3"
+  pre: |
+    echo "🚀 [PR Manager] starting: $TASK"
+
+    # 1. Learn from past similar PR patterns (ReasoningBank)
+    SIMILAR_PATTERNS=$(npx agentdb-cli pattern search "Manage pull request for $PR_CONTEXT" --k=5 --min-reward=0.8)
+    if [ -n "$SIMILAR_PATTERNS" ]; then
+      echo "📚 Found ${SIMILAR_PATTERNS} similar successful PR patterns"
+      npx agentdb-cli pattern stats "PR management" --k=5
+    fi
+
+    # 2. GitHub authentication and status
+    gh auth status || (echo 'GitHub CLI not authenticated' && exit 1)
+    git status --porcelain
+    gh pr list --state open --limit 1 >/dev/null || echo 'No open PRs'
+    npm test --silent || echo 'Tests may need attention'
+
+    # 3. Store task start
+    npx agentdb-cli pattern store \
+      --session-id "pr-manager-$AGENT_ID-$(date +%s)" \
+      --task "$TASK" \
+      --input "$PR_CONTEXT" \
+      --status "started"
+
+  post: |
+    echo "✨ [PR Manager] completed: $TASK"
+
+    # 1. Calculate success metrics
+    REWARD=$(calculate_pr_success "$PR_OUTPUT")
+    SUCCESS=$(validate_pr_merge "$PR_OUTPUT")
+    TOKENS=$(count_tokens "$PR_OUTPUT")
+    LATENCY=$(measure_latency)
+
+    # 2. Store learning pattern for future PR management
+    npx agentdb-cli pattern store \
+      --session-id "pr-manager-$AGENT_ID-$(date +%s)" \
+      --task "$TASK" \
+      --input "$PR_CONTEXT" \
+      --output "$PR_OUTPUT" \
+      --reward "$REWARD" \
+      --success "$SUCCESS" \
+      --critique "$PR_CRITIQUE" \
+      --tokens-used "$TOKENS" \
+      --latency-ms "$LATENCY"
+
+    # 3. Standard post-checks
+    gh pr status || echo 'No active PR in current branch'
+    git branch --show-current
+    gh pr checks || echo 'No PR checks available'
+    git log --oneline -3
+
+    # 4. Train neural patterns for successful PRs (optional)
+    if [ "$SUCCESS" = "true" ] && [ "$REWARD" -gt "0.9" ]; then
+      echo "🧠 Training neural pattern from successful PR management"
+      npx claude-flow neural train \
+        --pattern-type "coordination" \
+        --training-data "$PR_OUTPUT" \
+        --epochs 50
+    fi
 ---
 
 # GitHub PR Manager
 
 ## Purpose
-Comprehensive pull request management with swarm coordination for automated reviews, testing, and merge workflows.
+Comprehensive pull request management with swarm coordination for automated reviews, testing, and merge workflows, enhanced with **self-learning** and **continuous improvement** capabilities powered by Agentic-Flow v2.0.0-alpha.
 
-## Capabilities
+## Core Capabilities
 - **Multi-reviewer coordination** with swarm agents
 - **Automated conflict resolution** and merge strategies
 - **Comprehensive testing** integration and validation
 - **Real-time progress tracking** with GitHub issue coordination
 - **Intelligent branch management** and synchronization
 
+## 🧠 Self-Learning Protocol (v2.0.0-alpha)
+
+### Before Each PR Task: Learn from History
+
+```typescript
+// 1. Search for similar past PR solutions
+const similarPRs = await reasoningBank.searchPatterns({
+  task: `Manage PR for ${currentPR.title}`,
+  k: 5,
+  minReward: 0.8
+});
+
+if (similarPRs.length > 0) {
+  console.log('📚 Learning from past successful PRs:');
+  similarPRs.forEach(pattern => {
+    console.log(`- ${pattern.task}: ${pattern.reward} success rate`);
+    console.log(`  Merge strategy: ${pattern.output.mergeStrategy}`);
+    console.log(`  Conflicts resolved: ${pattern.output.conflictsResolved}`);
+    console.log(`  Critique: ${pattern.critique}`);
+  });
+
+  // Apply best practices from successful PR patterns
+  const bestPractices = similarPRs
+    .filter(p => p.reward > 0.9)
+    .map(p => p.output);
+}
+
+// 2. Learn from past PR failures
+const failedPRs = await reasoningBank.searchPatterns({
+  task: 'PR management',
+  onlyFailures: true,
+  k: 3
+});
+
+if (failedPRs.length > 0) {
+  console.log('⚠️  Avoiding past PR mistakes:');
+  failedPRs.forEach(pattern => {
+    console.log(`- ${pattern.critique}`);
+    console.log(`  Failure reason: ${pattern.output.failureReason}`);
+  });
+}
+```
+
+### During PR Management: GNN-Enhanced Code Search
+
+```typescript
+// Use GNN to find related code changes (+12.4% better accuracy)
+const buildPRGraph = (prFiles) => ({
+  nodes: prFiles.map(f => f.filename),
+  edges: detectDependencies(prFiles),
+  edgeWeights: calculateChangeImpact(prFiles),
+  nodeLabels: prFiles.map(f => f.path)
+});
+
+const relatedChanges = await agentDB.gnnEnhancedSearch(
+  prEmbedding,
+  {
+    k: 10,
+    graphContext: buildPRGraph(pr.files),
+    gnnLayers: 3
+  }
+);
+
+console.log(`Found related code with ${relatedChanges.improvementPercent}% better accuracy`);
+
+// Smart conflict detection with GNN
+const potentialConflicts = await agentDB.gnnEnhancedSearch(
+  currentChangesEmbedding,
+  {
+    k: 5,
+    graphContext: buildConflictGraph(),
+    gnnLayers: 2
+  }
+);
+```
+
+### Multi-Agent Coordination with Attention
+
+```typescript
+// Coordinate review decisions using attention consensus (better than voting)
+const coordinator = new AttentionCoordinator(attentionService);
+
+const reviewDecisions = [
+  { agent: 'security-reviewer', decision: 'approve', confidence: 0.95 },
+  { agent: 'code-quality-reviewer', decision: 'request-changes', confidence: 0.85 },
+  { agent: 'performance-reviewer', decision: 'approve', confidence: 0.90 }
+];
+
+const consensus = await coordinator.coordinateAgents(
+  reviewDecisions,
+  'flash' // 2.49x-7.47x faster
+);
+
+console.log(`Review consensus: ${consensus.consensus}`);
+console.log(`Confidence: ${consensus.confidence}`);
+console.log(`Agent influence: ${consensus.attentionWeights}`);
+
+// Intelligent merge decision based on attention consensus
+if (consensus.consensus === 'approve' && consensus.confidence > 0.85) {
+  await mergePR(pr, consensus.suggestedStrategy);
+}
+```
+
+### After PR Completion: Store Learning Patterns
+
+```typescript
+// Store successful PR pattern for future learning
+const prMetrics = {
+  filesChanged: pr.files.length,
+  linesAdded: pr.additions,
+  linesDeleted: pr.deletions,
+  conflictsResolved: conflicts.length,
+  reviewRounds: reviews.length,
+  mergeTime: mergeTimestamp - createTimestamp,
+  testsPassed: allTestsPass,
+  securityChecksPass: securityPass
+};
+
+await reasoningBank.storePattern({
+  sessionId: `pr-manager-${prId}-${Date.now()}`,
+  task: `Manage PR: ${pr.title}`,
+  input: JSON.stringify({ title: pr.title, files: pr.files, context: pr.description }),
+  output: JSON.stringify({
+    mergeStrategy: mergeStrategy,
+    conflictsResolved: conflicts,
+    reviewerConsensus: consensus,
+    metrics: prMetrics
+  }),
+  reward: calculatePRSuccess(prMetrics),
+  success: pr.merged && allTestsPass,
+  critique: selfCritiquePRManagement(pr, reviews),
+  tokensUsed: countTokens(prOutput),
+  latencyMs: measureLatency()
+});
+```
+
+## 🎯 GitHub-Specific Optimizations
+
+### Smart Merge Decision Making
+
+```typescript
+// Learn optimal merge strategies from past PRs
+const mergeHistory = await reasoningBank.searchPatterns({
+  task: 'PR merge strategy',
+  k: 20,
+  minReward: 0.85
+});
+
+const strategy = analyzeMergePatterns(mergeHistory, currentPR);
+// Returns: 'squash', 'merge', 'rebase' based on learned patterns
+```
+
+### Attention-Based Conflict Resolution
+
+```typescript
+// Use attention to focus on most impactful conflicts
+const conflictPriorities = await agentDB.flashAttention(
+  conflictEmbeddings,
+  codeContextEmbeddings,
+  codeContextEmbeddings
+);
+
+// Resolve conflicts in order of attention scores
+const sortedConflicts = conflicts.sort((a, b) =>
+  conflictPriorities[b.id] - conflictPriorities[a.id]
+);
+```
+
+### GNN-Enhanced Review Coordination
+
+```typescript
+// Build PR review graph
+const reviewGraph = {
+  nodes: reviewers.concat(prFiles),
+  edges: buildReviewerFileRelations(),
+  edgeWeights: calculateExpertiseScores(),
+  nodeLabels: [...reviewers.map(r => r.name), ...prFiles.map(f => f.path)]
+};
+
+// Find optimal reviewer assignments with GNN
+const assignments = await agentDB.gnnEnhancedSearch(
+  prEmbedding,
+  {
+    k: 3, // Top 3 reviewers
+    graphContext: reviewGraph,
+    gnnLayers: 2
+  }
+);
+```
+
 ## Usage Patterns
 
 ### 1. Create and Manage PR with Swarm Coordination