Luca Sacchi Ricciardi
|
d0f530f757
|
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
|
2026-04-02 19:31:04 +02:00 |
|
Luca Sacchi Ricciardi
|
96ba01b349
|
docs: add AI Pipeline technical specification
Create comprehensive spec for Sprint 2 Feature 2:
Content:
- System prompt with Metodo Sacchi integration (Safety First, Little Often, Double Check)
- OpenAI GPT-4o-mini configuration (cost: ~/bin/bash.0002/call)
- Complete n8n Code Node JavaScript implementation
- JSON output schema with severity mapping
- 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
Key Features:
- Safe command generation (destructive commands blacklisted)
- Incremental actions (Little Often principle)
- Confirmation required for uncertain situations (Double Check)
- Fallback when OpenAI unavailable
- Response time < 5s target
- Cost-optimized with GPT-4o-mini
Next: @python-developer implements OpenAI integration in n8n workflow
Refs: workflows/logwhisperer_ingest.json (already created)
|
2026-04-02 19:15:02 +02:00 |
|