feat: add canvas compatibility checking for connection validation

action/canvas_compatibility.go

@@ -0,0 +1,295 @@
+package action
+
+import (
+	"encoding/json"
+	"fmt"
+	"regexp"
+	"strings"
+
+	"github.com/rockliang/poimen/workflows/pkg/db"
+)
+
+// IncompatibilityWarning explains why two activities can't be connected
+type IncompatibilityWarning struct {
+	Source       string `json:"source"`        // Source node ID
+	Target       string `json:"target"`        // Target node ID
+	Reason       string `json:"reason"`        // Why they can't connect
+	SourceNeeds  string `json:"source_needs"`  // What source would need to output
+	TargetNeeds  string `json:"target_needs"`  // What target requires as input
+	Suggestion   string `json:"suggestion"`    // Suggestion to make it work
+}
+
+// ActivitySchema describes what an activity needs/provides
+type ActivitySchema struct {
+	ActivityType string                 `json:"activity_type"`
+	Inputs       map[string]InputField  `json:"inputs"`
+	Outputs      map[string]OutputField `json:"outputs"`
+}
+
+type InputField struct {
+	Type        string   `json:"type"`
+	Description string   `json:"description"`
+	Required    bool     `json:"required"`
+	Enum        []string `json:"enum,omitempty"`
+}
+
+type OutputField struct {
+	Type        string `json:"type"`
+	Description string `json:"description"`
+}
+
+// getActivitySchema returns schema from knowledge base
+func getActivitySchema(activityType string) (*ActivitySchema, error) {
+	kb := knowledgeBaseData()
+	if kb == nil {
+		return nil, fmt.Errorf("knowledge base not loaded")
+	}
+
+	var activities []map[string]interface{}
+	if err := json.Unmarshal([]byte(kb), &activities); err != nil {
+		// Try to extract activities from full KB structure
+		var fullKB map[string]interface{}
+		if err := json.Unmarshal([]byte(kb), &fullKB); err != nil {
+			return nil, fmt.Errorf("failed to parse knowledge base")
+		}
+		if activitiesRaw, ok := fullKB["activities"]; ok {
+			if b, err := json.Marshal(activitiesRaw); err == nil {
+				if err := json.Unmarshal(b, &activities); err != nil {
+					return nil, fmt.Errorf("failed to extract activities from KB")
+				}
+			}
+		}
+	}
+
+	// Find matching activity
+	for _, act := range activities {
+		if name, ok := act["name"].(string); ok {
+			if toActivityName(activityType) == name {
+				// Convert to ActivitySchema
+				schema := &ActivitySchema{
+					ActivityType: activityType,
+					Inputs:       make(map[string]InputField),
+					Outputs:      make(map[string]OutputField),
+				}
+
+				if inputs, ok := act["inputs"].(map[string]interface{}); ok {
+					for key, val := range inputs {
+						if field, ok := val.(map[string]interface{}); ok {
+							schema.Inputs[key] = parseInputField(field)
+						}
+					}
+				}
+
+				if outputs, ok := act["outputs"].(map[string]interface{}); ok {
+					for key, val := range outputs {
+						if field, ok := val.(map[string]interface{}); ok {
+							schema.Outputs[key] = parseOutputField(field)
+						}
+					}
+				}
+
+				return schema, nil
+			}
+		}
+	}
+
+	return nil, fmt.Errorf("activity %s not found in knowledge base", activityType)
+}
+
+func parseInputField(data map[string]interface{}) InputField {
+	field := InputField{}
+	if t, ok := data["type"].(string); ok {
+		field.Type = t
+	}
+	if d, ok := data["description"].(string); ok {
+		field.Description = d
+	}
+	if r, ok := data["required"].(bool); ok {
+		field.Required = r
+	}
+	return field
+}
+
+func parseOutputField(data map[string]interface{}) OutputField {
+	field := OutputField{}
+	if t, ok := data["type"].(string); ok {
+		field.Type = t
+	}
+	if d, ok := data["description"].(string); ok {
+		field.Description = d
+	}
+	return field
+}
+
+// CheckConnectionCompatibility validates if source can connect to target
+func CheckConnectionCompatibility(sourceNode, targetNode db.WorkflowNode) []IncompatibilityWarning {
+	warnings := []IncompatibilityWarning{}
+
+	sourceSchema, err := getActivitySchema(sourceNode.Type)
+	if err != nil {
+		warnings = append(warnings, IncompatibilityWarning{
+			Source:     sourceNode.ID,
+			Target:     targetNode.ID,
+			Reason:     fmt.Sprintf("Source activity schema not found: %v", err),
+			Suggestion: "Ensure source activity type is registered in knowledge base",
+		})
+		return warnings
+	}
+
+	targetSchema, err := getActivitySchema(targetNode.Type)
+	if err != nil {
+		warnings = append(warnings, IncompatibilityWarning{
+			Source:     sourceNode.ID,
+			Target:     targetNode.ID,
+			Reason:     fmt.Sprintf("Target activity schema not found: %v", err),
+			Suggestion: "Ensure target activity type is registered in knowledge base",
+		})
+		return warnings
+	}
+
+	// Check if source produces outputs that target can consume
+	if len(sourceSchema.Outputs) == 0 {
+		warnings = append(warnings, IncompatibilityWarning{
+			Source:     sourceNode.ID,
+			Target:     targetNode.ID,
+			Reason:     fmt.Sprintf("%s produces no outputs", sourceNode.Type),
+			SourceNeeds: "any output",
+			Suggestion: "Source activity must produce outputs",
+		})
+		return warnings
+	}
+
+	if len(targetSchema.Inputs) == 0 {
+		warnings = append(warnings, IncompatibilityWarning{
+			Source:     sourceNode.ID,
+			Target:     targetNode.ID,
+			Reason:     fmt.Sprintf("%s accepts no inputs", targetNode.Type),
+			TargetNeeds: "no input",
+			Suggestion: "Target activity must accept inputs. Check if it's a terminal activity.",
+		})
+		return warnings
+	}
+
+	// Match outputs to inputs
+	sourceOutputs := getOutputNames(sourceSchema.Outputs)
+	targetInputs := getInputNames(targetSchema.Inputs)
+
+	if len(sourceOutputs) == 0 || len(targetInputs) == 0 {
+		warnings = append(warnings, IncompatibilityWarning{
+			Source:       sourceNode.ID,
+			Target:       targetNode.ID,
+			Reason:       "No compatible output/input fields found",
+			SourceNeeds:  strings.Join(sourceOutputs, ", "),
+			TargetNeeds:  strings.Join(targetInputs, ", "),
+			Suggestion:   "Use LLM transformation to map outputs to inputs",
+		})
+	}
+
+	return warnings
+}
+
+// CheckCanvasConnectivity analyzes all suggested edges for compatibility
+func CheckCanvasConnectivity(nodes []db.WorkflowNode, suggestedEdges []db.WorkflowEdge) []IncompatibilityWarning {
+	warnings := []IncompatibilityWarning{}
+	nodeMap := make(map[string]db.WorkflowNode)
+	for _, n := range nodes {
+		nodeMap[n.ID] = n
+	}
+
+	for _, edge := range suggestedEdges {
+		sourceNode, ok := nodeMap[edge.Source]
+		if !ok {
+			continue
+		}
+		targetNode, ok := nodeMap[edge.Target]
+		if !ok {
+			continue
+		}
+
+		edgeWarnings := CheckConnectionCompatibility(sourceNode, targetNode)
+		warnings = append(warnings, edgeWarnings...)
+	}
+
+	return warnings
+}
+
+// IdentifyDisconnectedNodes finds nodes that can't connect to anything
+func IdentifyDisconnectedNodes(nodes []db.WorkflowNode, suggestedEdges []db.WorkflowEdge) []string {
+	edgeMap := make(map[string]bool)
+	for _, edge := range suggestedEdges {
+		edgeMap[edge.Source] = true
+		edgeMap[edge.Target] = true
+	}
+
+	var disconnected []string
+	for _, node := range nodes {
+		if !edgeMap[node.ID] {
+			disconnected = append(disconnected, node.ID)
+		}
+	}
+	return disconnected
+}
+
+// toActivityName converts canvas type to activity name (e.g., "clone-repo" -> "CloneRepoActivity")
+func toActivityName(canvasType string) string {
+	parts := strings.Split(canvasType, "-")
+	var result string
+	for _, part := range parts {
+		if part != "" {
+			result += strings.ToUpper(part[:1]) + strings.ToLower(part[1:])
+		}
+	}
+	return result + "Activity"
+}
+
+// getOutputNames extracts output field names
+func getOutputNames(outputs map[string]OutputField) []string {
+	var names []string
+	for name := range outputs {
+		names = append(names, name)
+	}
+	return names
+}
+
+// getInputNames extracts input field names (required ones highlighted)
+func getInputNames(inputs map[string]InputField) []string {
+	var names []string
+	for name, field := range inputs {
+		if field.Required {
+			names = append(names, name+"*")
+		} else {
+			names = append(names, name)
+		}
+	}
+	return names
+}
+
+// SuggestDataTransformation proposes how to connect incompatible activities
+func SuggestDataTransformation(sourceNode, targetNode db.WorkflowNode) string {
+	sourceSchema, _ := getActivitySchema(sourceNode.Type)
+	targetSchema, _ := getActivitySchema(targetNode.Type)
+
+	if sourceSchema == nil || targetSchema == nil {
+		return "Cannot analyze compatibility without schemas"
+	}
+
+	sourceOuts := getOutputNames(sourceSchema.Outputs)
+	targetIns := getInputNames(targetSchema.Inputs)
+
+	return fmt.Sprintf(
+		"To connect %s → %s:\n"+
+			"  %s outputs: %s\n"+
+			"  %s needs: %s\n"+
+			"  Solution: Use LLM transformation node to map outputs to inputs",
+		sourceNode.Label, targetNode.Label,
+		sourceNode.Type, strings.Join(sourceOuts, ", "),
+		targetNode.Type, strings.Join(targetIns, ", "),
+	)
+}
+
+// knowledgeBaseData returns raw KB JSON (stub - implement with actual KB loading)
+func knowledgeBaseData() string {
+	// This would load from activity_knowledge_base.json
+	// For now, return empty - real implementation loads from file
+	return ""
+}

action/canvas_reasoner.go

@@ -25,6 +25,9 @@ type CanvasReasonerOutput struct {
 	RemovedEdges          []db.WorkflowEdge             `json:"removed_edges,omitempty"` // Edges to remove (if redesign)
 	Reasoning             string                        `json:"reasoning"`               // LLM explanation
 	Confidence            float64                       `json:"confidence"`              // 0.0-1.0
+	IncompatibleEdges     []IncompatibilityWarning      `json:"incompatible_edges,omitempty"` // Edges that can't be created
+	DisconnectedNodes     []string                      `json:"disconnected_nodes,omitempty"` // Nodes with no connections
+	UserAlerts            []string                      `json:"user_alerts,omitempty"`        // Human-readable warnings
 }
 
 // CanvasReasonerActivity uses LLM to infer connections between workflow activities
@@ -45,23 +48,29 @@ func CanvasReasonerActivity(ctx context.Context, in CanvasReasonerInput) (Canvas
 	nodeDesc := buildNodeDescriptions(in.Nodes)
 	edgeDesc := buildEdgeDescriptions(in.Edges)
 
-	// Create prompt for LLM reasoning
+	// Create prompt for LLM reasoning with compatibility guidance
 	systemPrompt := `You are a workflow automation expert. Analyze the following activities and suggest logical connections (edges) between them based on:
-1. Activity input/output compatibility
+1. Activity input/output compatibility (CRITICAL - only connect if outputs match inputs)
-2. Logical execution order
+2. Logical execution order and data flow
-3. Data flow requirements
+3. Required dependencies
 4. Common workflow patterns
 
+IMPORTANT: Only suggest edges where:
+- Source activity has outputs (check "outputs" fields)
+- Target activity has inputs (check "inputs" fields)
+- Data types are compatible (string→string, object→object, etc)
+- Connection makes semantic sense (don't connect a notifier to an analyzer)
+
 Respond with JSON containing:
 {
   "edges": [{"source": "node-1", "target": "node-2"}, ...],
-  "reasoning": "explanation of why these connections make sense",
+  "reasoning": "explanation of why these connections make sense and any type mismatches noted",
   "confidence": 0.85
 }`
 
 	userPrompt := fmt.Sprintf(`Canvas Analysis:
 
-Nodes:
+Nodes (including inputs/outputs):
 %s
 
 Current Edges:
@@ -69,8 +78,12 @@ Current Edges:
 
 Task: %s
 
-Preserve existing edges and suggest only NEW edges to add.
+KEY RULES:
-If any existing edges don't make sense, note them but keep them unless explicitly wrong.
+- Preserve existing edges and suggest only NEW edges to add
+- SKIP any connections where input/output types don't match
+- If an activity has no outputs, it cannot be a source
+- If an activity has no inputs, it cannot be a target
+- Note any activities that are hard to connect (terminal activities, generators, etc)
 
 Return ONLY valid JSON, no markdown code blocks.`, nodeDesc, edgeDesc, getReasoningTask(in.PreserveExisting))
 
@@ -143,20 +156,75 @@ Return ONLY valid JSON, no markdown code blocks.`, nodeDesc, edgeDesc, getReason
 	output.Reasoning = reasonerResp.Reasoning
 	output.Confidence = reasonerResp.Confidence
 
-	logger.logf("info", "LLM suggested %d edges with confidence %.2f", len(validEdges), output.Confidence)
+	// Check compatibility of suggested edges
+	incompatibilities := CheckCanvasConnectivity(in.Nodes, validEdges)
+	if len(incompatibilities) > 0 {
+		output.IncompatibleEdges = incompatibilities
+		logger.logf("warn", "Found %d incompatible edge connections", len(incompatibilities))
+
+		// Generate user-friendly alerts
+		for i, incompat := range incompatibilities {
+			if i < 5 { // Limit to 5 alerts to avoid spam
+				alert := fmt.Sprintf(
+					"⚠️  %s → %s: %s. %s",
+					incompat.Source, incompat.Target, incompat.Reason, incompat.Suggestion,
+				)
+				output.UserAlerts = append(output.UserAlerts, alert)
+			}
+		}
+	}
+
+	// Identify disconnected nodes
+	disconnected := IdentifyDisconnectedNodes(in.Nodes, validEdges)
+	if len(disconnected) > 0 {
+		output.DisconnectedNodes = disconnected
+		logger.logf("warn", "Found %d disconnected nodes", len(disconnected))
+
+		for _, nodeID := range disconnected {
+			var label string
+			for _, node := range in.Nodes {
+				if node.ID == nodeID {
+					label = node.Label
+					break
+				}
+			}
+			alert := fmt.Sprintf(
+				"🔌 Node '%s' has no connections. Consider adding edges or removing it.",
+				label,
+			)
+			output.UserAlerts = append(output.UserAlerts, alert)
+		}
+	}
+
+	logger.logf("info", "LLM suggested %d edges with confidence %.2f | %d incompatibilities | %d disconnected",
+		len(validEdges), output.Confidence, len(incompatibilities), len(disconnected))
 
 	return output, nil
 }
 
-// buildNodeDescriptions creates readable node descriptions for LLM
+// buildNodeDescriptions creates readable node descriptions for LLM (including schemas)
 func buildNodeDescriptions(nodes []db.WorkflowNode) string {
 	var desc string
 	for i, node := range nodes {
-		desc += fmt.Sprintf("%d. %s (type: %s)\n", i+1, node.ID, node.Type)
+		desc += fmt.Sprintf("%d. [%s] %s (type: %s)\n", i+1, node.ID, node.Label, node.Type)
-		desc += fmt.Sprintf("   Label: %s\n", node.Label)
+
+		// Add input/output schema info
+		if schema, err := getActivitySchema(node.Type); err == nil {
+			if len(schema.Inputs) > 0 {
+				desc += fmt.Sprintf("   INPUTS: %v\n", getInputNames(schema.Inputs))
+			} else {
+				desc += fmt.Sprintf("   INPUTS: none (generator/trigger)\n")
+			}
+			if len(schema.Outputs) > 0 {
+				desc += fmt.Sprintf("   OUTPUTS: %v\n", getOutputNames(schema.Outputs))
+			} else {
+				desc += fmt.Sprintf("   OUTPUTS: none (terminal/sink)\n")
+			}
+		}
+
 		if node.Data != nil {
 			if b, err := json.MarshalIndent(node.Data, "   ", "  "); err == nil {
-				desc += fmt.Sprintf("   Config: %s\n", string(b))
+				desc += fmt.Sprintf("   CONFIG: %s\n", string(b))
 			}
 		}
 	}

docs/CANVAS_REASONER_LOGIC.md

@@ -0,0 +1,322 @@
+# Canvas Reasoner: Auto-Inferring Workflow Connections
+
+## Overview
+
+The **CanvasReasonerActivity** uses LLM reasoning to automatically suggest connections between workflow activities when users drop new nodes onto the canvas. It analyzes input/output compatibility and detects connection problems.
+
+## Connection Logic
+
+### How It Works
+
+1. **Analyze Node Schemas**
+   - Get each activity's input/output fields from knowledge base
+   - Activities are classified as:
+     - **Generators**: No inputs, has outputs (e.g., API call, trigger)
+     - **Processors**: Has inputs and outputs (e.g., analyze code, security scan)
+     - **Sinks/Terminals**: Has inputs, no outputs (e.g., notification, approval)
+
+2. **LLM Reasoning**
+   - Pass all nodes + their schemas to reasoning model
+   - Ask LLM to suggest edges based on:
+     - Type compatibility (string→string, object→object)
+     - Logical execution order
+     - Data flow requirements
+     - Common workflow patterns
+
+3. **Validate Suggestions**
+   - Check all suggested edges exist in node map
+   - Skip self-loops
+   - Remove duplicates
+
+4. **Compatibility Checking**
+   - For each suggested edge: `source → target`
+   - Verify source produces outputs
+   - Verify target accepts inputs
+   - Check output/input type compatibility
+   - Flag incompatible connections
+
+5. **Identify Issues**
+   - Collect all incompatible edges
+   - Identify disconnected nodes (no edges in/out)
+   - Generate user alerts for problems
+
+## Connection Impossibility Detection
+
+### Why Connections Fail
+
+1. **Missing Outputs**
+   ```
+   NotifyStatusActivity → AnalyzeCodeActivity
+   ⚠️ NotifyStatusActivity produces no outputs
+   Reason: Notification is terminal activity (sink)
+   Solution: Add an intermediate processor that has outputs
+   ```
+
+2. **Missing Inputs**
+   ```
+   CloneRepoActivity → ApproveWorkflowActivity
+   ⚠️ ApproveWorkflowActivity accepts no inputs
+   Reason: Approval is a terminal activity (sink)
+   Solution: ApproveWorkflowActivity only works as final step
+   ```
+
+3. **Type Mismatch**
+   ```
+   LLMInferenceActivity (output: string) → DeploymentPreCheckActivity (input: object)
+   ⚠️ String output cannot satisfy object input requirement
+   Reason: Incompatible data types
+   Solution: Use LLM transformation node to convert string→object
+   ```
+
+4. **Semantic Incompatibility**
+   ```
+   NotifyStatusActivity → CloneRepoActivity
+   ⚠️ No logical connection between these activities
+   Reason: Notification cannot be input to clone operation
+   Solution: Ensure data flow makes semantic sense
+   ```
+
+### Incompatibility Data Structure
+
+```json
+{
+  "incompatible_edges": [
+    {
+      "source": "node-1",
+      "target": "node-2",
+      "reason": "Source activity produces no outputs",
+      "source_needs": "any output",
+      "target_needs": "path, depth",
+      "suggestion": "Use LLM transformation to map outputs to inputs"
+    }
+  ],
+  "disconnected_nodes": ["node-5", "node-8"],
+  "user_alerts": [
+    "⚠️  node-1 → node-2: Source activity produces no outputs. Use LLM transformation to map outputs to inputs",
+    "🔌 Node 'NotifyStatus-1' has no connections. Consider adding edges or removing it."
+  ]
+}
+```
+
+## User Alerts
+
+### Alert Types
+
+1. **Incompatibility Warnings** (⚠️)
+   ```
+   ⚠️  source → target: reason. suggestion.
+   ```
+   - Highlighted in red on canvas
+   - Shows in error sidebar
+   - Prevents workflow execution until fixed
+
+2. **Disconnection Warnings** (🔌)
+   ```
+   🔌 Node 'label' has no connections. Consider adding edges or removing it.
+   ```
+   - Highlighted in yellow
+   - Nodes with no input/output edges
+   - May be valid (first step, last step) or indicate design error
+
+3. **Type Mismatch Info** (ℹ️)
+   ```
+   ℹ️  To connect source → target, use transformer to map: {source_outputs} → {target_inputs}
+   ```
+   - Suggestion to use intermediate LLM node
+   - Provides mapping information
+
+## Frontend Integration
+
+### Canvas UI Feedback
+
+When CanvasReasonerActivity returns incompatibilities:
+
+1. **Visual Markers**
+   - Incompatible suggested edges: ❌ red dashed line (don't auto-add)
+   - Disconnected nodes: ⚠️ yellow border
+
+2. **Sidebar Alerts**
+   ```
+   🚨 Connection Issues (3)
+   
+   ⚠️  CloneRepo → ApproveWorkflow
+      Reason: ApproveWorkflow is terminal (no outputs)
+      Suggestion: Place ApproveWorkflow at end of workflow
+   
+   ⚠️  LLMInference → DeploymentPreCheck
+      Reason: Type mismatch (string ≠ object)
+      Suggestion: Add LLM transformation node
+   
+   🔌 SecurityScan-1 has no incoming edges
+      Suggestion: Connect CloneRepo → SecurityScan
+   ```
+
+3. **User Actions**
+   - ✅ Accept suggestions (green edges)
+   - ❌ Reject incompatible edges
+   - 🔧 Add transformer nodes
+   - 🗑️ Remove disconnected nodes
+
+### API Response Example
+
+```json
+{
+  "suggested_edges": [
+    {"source": "clone-1", "target": "analyze-1"},
+    {"source": "analyze-1", "target": "security-1"},
+    {"source": "security-1", "target": "report-1"}
+  ],
+  "reasoning": "Standard code review workflow: clone → analyze → scan → report",
+  "confidence": 0.92,
+  "incompatible_edges": [
+    {
+      "source": "report-1",
+      "target": "approve-1",
+      "reason": "ReportGenerator has no outputs (terminal activity)",
+      "suggestion": "ApproveWorkflow can only be a final step"
+    }
+  ],
+  "disconnected_nodes": [],
+  "user_alerts": [
+    "⚠️  report-1 → approve-1: ReportGenerator has no outputs (terminal activity). ApproveWorkflow can only be a final step"
+  ]
+}
+```
+
+## Knowledge Base Schema
+
+Each activity in `activity_knowledge_base.json` defines:
+
+```json
+{
+  "name": "CloneRepoActivity",
+  "inputs": {
+    "repo": {"type": "string", "required": true},
+    "branch": {"type": "string", "required": false}
+  },
+  "outputs": {
+    "path": {"type": "string"},
+    "commit": {"type": "string"}
+  }
+}
+```
+
+### Classification Rules
+
+- **Generator** (0 inputs): trigger, API call, schedule
+- **Processor** (1+ inputs, 1+ outputs): analysis, transformation, scan
+- **Sink** (1+ inputs, 0 outputs): notification, approval, archive
+- **Bypass** (0 inputs, 0 outputs): rare - usually error
+
+## Common Patterns
+
+### ✅ Valid Chains
+
+```
+CloneRepo → Analyze → SecurityScan → Report
+(generator) → (processor) → (processor) → (sink)
+```
+
+```
+Trigger → LLMInference → Decision → (Branch: Notify OR Approve)
+(gen) → (processor) → (processor) → (sink)
+```
+
+### ❌ Invalid Chains
+
+```
+Notify → CloneRepo  ❌
+(sink) → (generator) - backward flow
+
+CloneRepo → CloneRepo → Analyze  ❌
+self-loop - no benefit
+
+Analyze → Approve → Notify  ❌
+Approve is terminal (sink), can't output to Notify
+```
+
+## Edge Cases
+
+### Multiple Outputs → Single Input
+```
+SecurityScan → Report
+SecurityScan outputs: [issues, metrics, severity]
+Report inputs: [report_data]
+
+LLM must infer: bundle all outputs into single report_data object
+Confidence: 0.7 (requires transformation)
+```
+
+### Terminal Activities
+- **ApproveWorkflowActivity**: Must be last (blocks workflow)
+- **NotifyStatusActivity**: Can be mid-workflow (async notify)
+- **ArchiveResultsActivity**: Should be last (persistence)
+
+### Data Transformation
+When source outputs don't match target inputs:
+
+```python
+# User can insert transformer node:
+LLMInference → [LLMTransformer] → DeploymentPreCheck
+
+# Transformer:
+# - Input: LLMInference.output (string)
+# - Output: DeploymentPreCheck.requirements (object)
+# - Action: Call LLM to convert format
+```
+
+## Testing Incompatibility Detection
+
+### Test Case 1: Terminal Activity as Source
+```go
+source := db.WorkflowNode{ID: "n1", Type: "notify-status", Label: "Notify"}
+target := db.WorkflowNode{ID: "n2", Type: "clone-repo", Label: "Clone"}
+
+warnings := CheckConnectionCompatibility(source, target)
+// Should warn: NotifyStatusActivity produces no outputs
+```
+
+### Test Case 2: Type Mismatch
+```go
+source := db.WorkflowNode{ID: "n1", Type: "llm-inference", ...}
+target := db.WorkflowNode{ID: "n2", Type: "deployment-check", ...}
+
+warnings := CheckConnectionCompatibility(source, target)
+// Should warn: string output ≠ object input
+```
+
+### Test Case 3: Disconnected Node
+```go
+nodes := []db.WorkflowNode{n1, n2, n3}
+edges := []db.WorkflowEdge{{Source: "n1", Target: "n2"}}
+
+disconnected := IdentifyDisconnectedNodes(nodes, edges)
+// Should return ["n3"]
+```
+
+## Future Enhancements
+
+1. **Automatic Transformer Insertion**
+   - Detect incompatibilities
+   - Auto-suggest LLM transformer nodes
+   - Chain transformers if needed
+
+2. **Confidence Scoring**
+   - Increase when types match perfectly
+   - Decrease for semantic mismatches
+   - Factor in activity dependencies
+
+3. **Learning from History**
+   - Track successful workflows
+   - Remember user edits to suggestions
+   - Improve LLM prompts over time
+
+4. **Multi-Path Analysis**
+   - Suggest multiple connection topologies
+   - Show cost/efficiency of each
+   - Rank by execution time/cost
+
+5. **Dry-Run Validation**
+   - Execute suggested workflow in simulation
+   - Catch runtime errors early
+   - Show data flow through each node

k8s/git-commit.yaml

@@ -9,6 +9,6 @@ metadata:
     app.kubernetes.io/name: poimen
     app.kubernetes.io/component: orchestrator
 data:
-  GIT_COMMIT: "5342bb51"  # Updated automatically by CI/CD
+  GIT_COMMIT: "8cfa23e5d"  # Updated automatically by CI/CD
   GIT_BRANCH: "main"
   DEPLOYMENT_DATE: "2026-09-05"

k8s/worker-deployment.yaml

@@ -13,7 +13,7 @@ spec:
       labels:
         app: poimen-worker
       annotations:
-        git-commit: "5342bb51"  # ✅ Updated on each push, triggers rolling restart
+        git-commit: "8cfa23e5d"  # ✅ Updated on each push, triggers rolling restart
         deployment-date: "2026-09-05"
     spec:
       containers: