docs: update AI Pipeline spec to use OpenRouter instead of OpenAI direct

Migrated from OpenAI direct API to OpenRouter for multiple advantages:

Cost Optimization:
- Reduced cost by ~25%: /bin/bash.00015/call (vs /bin/bash.0002/call OpenAI)
- Monthly estimate: ~/bin/bash.15 for 1000 calls (vs /bin/bash.20)

Provider Benefits:
- Access to 300+ AI models (OpenAI, Anthropic, Google, etc.)
- Automatic fallback between providers for 99.9% uptime
- Single API key for all providers
- Unified API interface

Technical Changes:
- Updated endpoint: api.openai.com → openrouter.ai/api/v1
- Model format: gpt-4o-mini → openai/gpt-4o-mini
- Added required headers: HTTP-Referer, X-Title
- Environment variables: OPENAI_API_KEY → OPENROUTER_API_KEY
  + OPENROUTER_SITE_URL (for OpenRouter ranking)
  + OPENROUTER_APP_NAME

Added Sections:
- 3.1 Why OpenRouter? (benefits comparison)
- 3.5 Model Fallback (automatic provider switching)
- Updated all code examples with OpenRouter integration
- Updated test cases (openai_client → openrouter_client)
- Updated cost estimates throughout document

References updated to OpenRouter documentation.

Refs: OpenRouter docs https://openrouter.ai/docs

CHANGELOG.md

@@ -34,6 +34,23 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   - n8n_automation_mastery: n8n workflow best practices
   - context7_documentation_retrivial: Context-aware documentation lookup
 - docs: Add requirements.txt with Python dependencies (pytest, requests)
+- docs: Add AI Pipeline technical specification
+  - System prompt with Metodo Sacchi integration (Safety First, Little Often, Double Check)
+  - OpenRouter configuration (migrated from OpenAI direct)
+    - 25% cost savings (~$0.00015/call vs ~$0.0002/call)
+    - Multi-provider fallback (300+ models available)
+    - Automatic failover if primary provider down
+  - Complete n8n Code Node JavaScript implementation
+    - OpenRouter endpoint: https://openrouter.ai/api/v1
+    - Required headers: HTTP-Referer, X-Title for ranking
+    - Model format: provider/model (e.g., openai/gpt-4o-mini)
+  - JSON output schema with severity mapping (critical/medium/low)
+  - Error handling with circuit breaker pattern
+  - Security guidelines (data sanitization, rate limiting)
+  - 10 acceptance criteria defined
+  - 5 test scenarios with expected input/output
+  - 5 real-world examples (OOM, disk full, connection refused, etc.)
+  - Implementation checklist for developers
 
 ### Changed