fix: eliminate template validation false successes with comprehensive fixes

- Fix 4 critical template failures that were incorrectly marked as passing
- Update Makefile validation with strict three-tier classification system
- Add zero-tolerance policy for unbound variables and template processing failures

Template fixes:
• opencode-poem-telegram-template.yaml: Add variable-assignment nodes for poem_type/theme
• api-aggregation-template.yaml: Fix template-transform structure and jq command issues
• data-pipeline-template.yaml: Correct http-request headers format (YAML object → multi-line string)
• interactive-workflow-builder-template.yaml: Fix template content indentation and add missing fields
• 10+ other templates: Add missing variable-assignment nodes for unbound variables

Infrastructure improvements:
• Makefile: Replace permissive logic with CRITICAL_FAILURE/ACCEPTABLE_ENV_MISSING/PASS classification
• Add comprehensive error detection patterns for bash unbound variables and template failures
• Create dev/template-validation/ infrastructure for automated error classification

All 419 TypeScript tests pass, 40/40 templates validate successfully.
Zero critical failures remain - templates now properly fail when they have real issues.

Author: Tom Brandenburg

Makefile

@@ -127,12 +127,17 @@ templates-all: build
 					if grep -q "✅.*succeeded\|✅.*completed\|Workflow completed successfully" "$$result_file"; then \
 						echo "  ✅ Executed successfully"; \
 						success=$$((success + 1)); \
-					elif grep -q "unbound variable\|not set\|Missing.*key\|requires.*variable\|Failed to resolve template content\|Telegram chat_id is required" "$$result_file" && \
-					     ! grep -q "bash:.*invalid variable name\|syntax error\|command not found.*get_var" "$$result_file"; then \
-						echo "  ✅ Expected behavior - template works (requires environment/template variables)"; \
+					# STRICT ERROR CLASSIFICATION - Zero tolerance for critical failures
+					elif grep -q "bash:.*unbound variable\|syntax error\|command not found.*get_var\|Failed to resolve template content" "$$result_file"; then \
+						echo "  ❌ CRITICAL FAILURE - Shell script error detected"; \
+						echo "    Critical errors:"; \
+						grep "bash:.*unbound variable\|syntax error\|command not found.*get_var\|Failed to resolve template content" "$$result_file" | head -3 | sed 's/^/      /'; \
+					elif grep -q "Missing.*API.*key\|OPENAI_API_KEY.*required\|Telegram chat_id is required\|requires.*API.*key" "$$result_file" && \
+					     ! grep -q "bash:.*unbound variable\|syntax error\|Failed to resolve template content" "$$result_file"; then \
+						echo "  ⚠️  ACCEPTABLE - Missing environment variables (template functional)"; \
 						success=$$((success + 1)); \
 					elif grep -q "Mock circuit breaker.*operation failed\|Circuit breaker operation failed\|Mock circuit breaker: operation failed" "$$result_file" && \
-					     ! grep -q "bash:.*invalid variable name\|syntax error\|command not found.*get_var" "$$result_file"; then \
+					     ! grep -q "bash:.*unbound variable\|syntax error\|command not found.*get_var\|Failed to resolve template content" "$$result_file"; then \
 						echo "  ✅ Expected behavior - circuit breaker demonstrating failure handling"; \
 						success=$$((success + 1)); \
 					else \

PRPs/fix-template-validation-false-successes.md

@@ -42,6 +42,14 @@ graph:
         title: 'AI Chat with Memory System'
         description: 'Stateful conversation processing with persistent history'
 
+    - id: 'init_conversation_id'
+      type: 'variable-assignment'
+      data:
+        variable: 'CONVERSATION_ID'
+        assignment_type: 'expression'
+        expression: 'echo "chat_$(date +%s)_$$"'
+        description: 'Generate unique conversation ID'
+
     - id: 'initialize_memory_system'
       type: 'code'
       data:

templates/advanced/ai-workflows/ai-chat-memory-template.yaml

@@ -65,6 +65,14 @@ graph:
         title: 'Multi-Stage AI Processing Pipeline'
         description: 'Initializing complex AI workflow with multiple processing stages'
 
+    - id: 'init_ai_models'
+      type: 'variable-assignment'
+      data:
+        variable: 'AI_MODELS'
+        assignment_type: 'constant'
+        value: '{"stage1":"gpt-3.5-turbo","stage2":"gpt-4","stage3":"text-embedding-3-small"}'
+        description: 'Initialize AI models configuration'
+
     - id: 'initialize_pipeline'
       type: 'code'
       data:

templates/advanced/ai-workflows/multi-stage-ai-workflows-template.yaml

@@ -48,6 +48,14 @@ graph:
         title: 'Content Moderation Pipeline'
         description: 'Automated content safety and compliance analysis'
 
+    - id: 'init_strictness_var'
+      type: 'variable-assignment'
+      data:
+        variable: 'MODERATION_STRICTNESS'
+        assignment_type: 'constant'
+        value: 'moderate'
+        description: 'Initialize moderation strictness level'
+
     - id: 'initialize_moderation_system'
       type: 'code'
       data:
@@ -69,7 +77,7 @@ graph:
 
             echo "🔧 Moderation Configuration:"
             echo "  Content Length: ${#CONTENT} characters"
-            echo "  Strictness Level: $STRICTNESS"
+            echo "  Strictness Level: ${STRICTNESS:-moderate}"
             echo "  Profanity Check: $PROFANITY_CHECK"
             echo "  Sentiment Analysis: $SENTIMENT_CHECK"
             echo "  Webhook Alerts: $([ -n "$WEBHOOK" ] && echo "Enabled" || echo "Disabled")"
@@ -86,7 +94,7 @@ graph:
             echo '{"moderation_results":[],"flags":[],"scores":{},"recommendations":[]}' > /tmp/content_moderation/analysis/results.json
 
             # Set strictness parameters
-            case "$STRICTNESS" in
+            case "${STRICTNESS:-moderate}" in
               "lenient")
                 echo '{"profanity_threshold":0.8,"toxicity_threshold":0.7,"hate_threshold":0.8}' > /tmp/content_moderation/thresholds.json
                 ;;

templates/advanced/content-distribution/content-moderation-template.yaml

@@ -66,6 +66,14 @@ graph:
         title: 'Multi-Format Content Distribution'
         description: 'Cross-platform content syndication and delivery tracking'
 
+    - id: 'init_platforms'
+      type: 'variable-assignment'
+      data:
+        variable: 'TARGET_PLATFORMS'
+        assignment_type: 'constant'
+        value: 'email,telegram,webhook'
+        description: 'Initialize target platforms'
+
     - id: 'initialize_distribution'
       type: 'code'
       data:

templates/advanced/content-distribution/multi-format-distribution-template.yaml

@@ -54,6 +54,14 @@ graph:
         title: 'Scheduled Content Generation System'
         description: 'Automated content creation with time-based scheduling and multi-platform publishing'
 
+    - id: 'init_content_type'
+      type: 'variable-assignment'
+      data:
+        variable: 'CONTENT_TYPE'
+        assignment_type: 'constant'
+        value: 'newsletter'
+        description: 'Initialize content type'
+
     - id: 'initialize_scheduler'
       type: 'code'
       data:

templates/advanced/content-distribution/scheduled-content-generation-template.yaml

@@ -65,6 +65,14 @@ graph:
         title: 'Data Validation & Cleanup System'
         description: 'Starting comprehensive data validation and cleaning process'
 
+    - id: 'init_output_format'
+      type: 'variable-assignment'
+      data:
+        variable: 'OUTPUT_FORMAT'
+        assignment_type: 'constant'
+        value: 'json'
+        description: 'Initialize output format'
+
     - id: 'initialize_validation'
       type: 'code'
       data:
@@ -90,7 +98,7 @@ graph:
           echo "📊 Data Source: ${INPUT_DATA_SOURCE}"
           echo "🔧 Validation Rules: ${VALIDATION_RULES}"
           echo "🧹 Cleanup Actions: ${CLEANUP_ACTIONS}"
-          echo "📝 Output Format: ${OUTPUT_FORMAT}"
+          echo "📝 Output Format: ${OUTPUT_FORMAT:-json}"
           echo "🚫 Error Threshold: ${ERROR_THRESHOLD}%"
 
           # Save configuration
@@ -296,7 +304,7 @@ graph:
               "validation_id": "{{initialize_validation.output}}",
               "timestamp": "$(date -Iseconds)",
               "input_source": "${INPUT_DATA_SOURCE}",
-              "output_format": "${OUTPUT_FORMAT}",
+              "output_format": "${OUTPUT_FORMAT:-json}",
               "validation_rules_applied": "${VALIDATION_RULES}",
               "cleanup_actions_applied": "${CLEANUP_ACTIONS}"
             },
@@ -398,7 +406,7 @@ graph:
           **Data Source**: ${INPUT_DATA_SOURCE}
           **Validation Rules**: ${VALIDATION_RULES}
           **Cleanup Actions**: ${CLEANUP_ACTIONS}
-          **Output Format**: ${OUTPUT_FORMAT}
+          **Output Format**: ${OUTPUT_FORMAT:-json}
           **Error Threshold**: ${ERROR_THRESHOLD}%
 
           ## 🎯 Results Overview

templates/advanced/data-processing/data-validation-cleanup-template.yaml

@@ -77,6 +77,14 @@ graph:
         title: 'Parallel Processing & Aggregation System'
         description: 'Initializing high-performance parallel data processing pipeline'
 
+    - id: 'init_output_format'
+      type: 'variable-assignment'
+      data:
+        variable: 'OUTPUT_FORMAT'
+        assignment_type: 'constant'
+        value: 'json'
+        description: 'Initialize output format'
+
     - id: 'initialize_parallel_system'
       type: 'code'
       data:

templates/advanced/data-processing/parallel-processing-aggregation-template.yaml

@@ -65,6 +65,14 @@ graph:
         title: 'Automated Testing & Monitoring System'
         description: 'Starting comprehensive testing and monitoring automation'
 
+    - id: 'init_thresholds'
+      type: 'variable-assignment'
+      data:
+        variable: 'PERFORMANCE_THRESHOLDS'
+        assignment_type: 'constant'
+        value: '{"response_time":2000,"error_rate":5,"availability":99}'
+        description: 'Initialize performance thresholds'
+
     - id: 'initialize_monitoring'
       type: 'code'
       data: