fix: resolve remaining AI validation integration test failures

- Simplified Calculator and Think tool validators (no toolDescription required - built-in descriptions)
- Fixed trigger counting to exclude respondToWebhook from trigger detection
- Fixed streaming error filters to use correct error code access pattern (details.code || code)

This resolves 9 remaining integration test failures from Phase 2 AI validation implementation.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

src/services/ai-tool-validators.ts

@@ -409,48 +409,16 @@ export function validateMCPClientTool(node: WorkflowNode): ValidationIssue[] {
 export function validateCalculatorTool(node: WorkflowNode): ValidationIssue[] {
   const issues: ValidationIssue[] = [];
 
-  // Check toolDescription (REQUIRED)
+  // Calculator Tool has a built-in description and is self-explanatory
-  if (!node.parameters.toolDescription) {
+  // toolDescription is optional - no validation needed
-    issues.push({
-      severity: 'error',
-      nodeId: node.id,
-      nodeName: node.name,
-      message: `Calculator Tool "${node.name}" has no toolDescription. Add one to help the LLM know when to use this tool.`,
-      code: 'MISSING_TOOL_DESCRIPTION'
-    });
-  } else if (node.parameters.toolDescription.trim().length < MIN_DESCRIPTION_LENGTH_SHORT) {
-    issues.push({
-      severity: 'info',
-      nodeId: node.id,
-      nodeName: node.name,
-      message: `Calculator Tool "${node.name}" has a very short toolDescription (minimum ${MIN_DESCRIPTION_LENGTH_SHORT} characters). Consider being more specific about when to use it.`
-    });
-  }
-
   return issues;
 }
 
 export function validateThinkTool(node: WorkflowNode): ValidationIssue[] {
   const issues: ValidationIssue[] = [];
 
-  // Check toolDescription (REQUIRED)
+  // Think Tool has a built-in description and is self-explanatory
-  if (!node.parameters.toolDescription) {
+  // toolDescription is optional - no validation needed
-    issues.push({
-      severity: 'error',
-      nodeId: node.id,
-      nodeName: node.name,
-      message: `Think Tool "${node.name}" has no toolDescription. Add one to help the LLM know when to use thinking.`,
-      code: 'MISSING_TOOL_DESCRIPTION'
-    });
-  } else if (node.parameters.toolDescription.trim().length < MIN_DESCRIPTION_LENGTH_MEDIUM) {
-    issues.push({
-      severity: 'info',
-      nodeId: node.id,
-      nodeName: node.name,
-      message: `Think Tool "${node.name}" has a very short toolDescription (minimum ${MIN_DESCRIPTION_LENGTH_MEDIUM} characters). Explain when the agent should use thinking vs. action.`
-    });
-  }
-
   return issues;
 }
 

src/services/workflow-validator.ts

@@ -327,8 +327,9 @@ export class WorkflowValidator {
     // Count trigger nodes - normalize type names first
     const triggerNodes = workflow.nodes.filter(n => {
       const normalizedType = NodeTypeNormalizer.normalizeToFullForm(n.type);
-      return normalizedType.toLowerCase().includes('trigger') ||
+      const lowerType = normalizedType.toLowerCase();
-             normalizedType.toLowerCase().includes('webhook') ||
+      return lowerType.includes('trigger') ||
+             (lowerType.includes('webhook') && !lowerType.includes('respond')) ||
              normalizedType === 'nodes-base.start' ||
              normalizedType === 'nodes-base.manualTrigger' ||
              normalizedType === 'nodes-base.formTrigger';

tests/integration/ai-validation/ai-agent-validation.test.ts

@@ -245,10 +245,11 @@ describe('Integration: AI Agent Validation', () => {
     expect(data.valid).toBe(false);
     expect(data.errors).toBeDefined();
 
-    const streamingErrors = data.errors!.filter(e =>
+    const streamingErrors = data.errors!.filter(e => {
-      e.code === 'STREAMING_WITH_MAIN_OUTPUT' ||
+      const code = e.details?.code || e.code;
-      e.code === 'STREAMING_AGENT_HAS_OUTPUT'
+      return code === 'STREAMING_WITH_MAIN_OUTPUT' ||
-    );
+             code === 'STREAMING_AGENT_HAS_OUTPUT';
+    });
     expect(streamingErrors.length).toBeGreaterThan(0);
   });
 

tests/integration/ai-validation/chat-trigger-validation.test.ts

@@ -308,10 +308,11 @@ describe('Integration: Chat Trigger Validation', () => {
     expect(data.errors).toBeDefined();
 
     // Should detect streaming agent has output
-    const streamingErrors = data.errors!.filter(e =>
+    const streamingErrors = data.errors!.filter(e => {
-      e.code === 'STREAMING_AGENT_HAS_OUTPUT' ||
+      const code = e.details?.code || e.code;
-      e.message.toLowerCase().includes('streaming')
+      return code === 'STREAMING_AGENT_HAS_OUTPUT' ||
-    );
+             e.message.toLowerCase().includes('streaming');
+    });
     expect(streamingErrors.length).toBeGreaterThan(0);
   });
 });

tests/integration/ai-validation/e2e-validation.test.ts

@@ -219,10 +219,11 @@ describe('Integration: End-to-End AI Workflow Validation', () => {
     expect(errorCodes).toContain('MISSING_CODE'); // Code Tool
 
     // Should also have streaming error
-    const streamingErrors = validationData.errors!.filter(e =>
+    const streamingErrors = validationData.errors!.filter(e => {
-      e.code === 'STREAMING_WITH_MAIN_OUTPUT' ||
+      const code = e.details?.code || e.code;
-      e.code === 'STREAMING_AGENT_HAS_OUTPUT'
+      return code === 'STREAMING_WITH_MAIN_OUTPUT' ||
-    );
+             code === 'STREAMING_AGENT_HAS_OUTPUT';
+    });
     expect(streamingErrors.length).toBeGreaterThan(0);
 
     // Verify error messages are actionable