v2-exece-docs

v2/V2-Execution-Docs/00F-self-hosted-ai-infra.md

@@ -1,10 +1,11 @@
 # IGNY8 Phase 0: Self-Hosted AI Infrastructure (00F)
 
 **Status:** Ready for Implementation
+**Version:** 1.1
 **Priority:** High (cost savings critical for unit economics)
 **Duration:** 5-7 days
 **Dependencies:** 00B (VPS provisioning) must be complete first
-**Version Reference:** See [00B Version Matrix](./00B-vps-provisioning.md) for authoritative version information
+**Source of Truth:** Codebase at `/data/app/igny8/`
 **Cost:** ~$200/month GPU rental + $0 software (open source)
 
 ---
@@ -12,14 +13,12 @@
 ## 1. Current State
 
 ### Existing AI Integration
-- **External providers:** OpenAI (GPT-4, GPT-3.5), Anthropic (Claude), Runware (image gen), Bria (image gen)
-- **Storage:** API keys stored in `GlobalIntegrationSettings` / `IntegrationProvider` models in database
+- **External providers (verified from `IntegrationProvider` model):** OpenAI (GPT-4, GPT-3.5), Anthropic (Claude), Runware (image gen)
+- **Storage:** API keys stored in `IntegrationProvider` model (table: `igny8_integration_providers`) with per-account overrides in `IntegrationSettings` (table: `igny8_integration_settings`). Global defaults in `GlobalIntegrationSettings`.
+- **Provider types in codebase:** `ai`, `payment`, `email`, `storage` (from `PROVIDER_TYPE_CHOICES`)
+- **Existing provider_ids:** `openai`, `runware`, `stripe`, `paypal`, `resend`
 - **Architecture:** Multi-provider AI engine with model selection capability
-- **Current usage:**
-  - Content generation: articles, product descriptions, blog posts
-  - Image generation: product images, covers, social media graphics
-  - Keyword research and SEO optimization
-  - Content enhancement and rewriting
+- **Current AI functions:** `auto_cluster`, `generate_ideas`, `generate_content`, `generate_images`, `generate_image_prompts`, `optimize_content`, `generate_site_structure`
 - **Async handling:** Celery workers process long-running AI tasks
 - **Cost impact:** External APIs constitute 15-30% of monthly operational costs
 
@@ -125,31 +124,35 @@
 
 ## 3. Data Models / APIs
 
-### Database Models (No Schema Changes Required)
+### Database Models (Minimal Schema Changes)
 
-Use existing `IntegrationProvider` and `GlobalIntegrationSettings` models:
+Use existing `IntegrationProvider` model — add a new row with `provider_type='ai'`:
 
 ```python
-# In GlobalIntegrationSettings
-INTEGRATION_PROVIDER_SELF_HOSTED = "self_hosted_ai"
+# New IntegrationProvider row (NO new provider_type needed)
+# provider_type='ai' already exists in PROVIDER_TYPE_CHOICES
 
-# Settings structure (stored as JSON)
-{
-    "provider": "self_hosted_ai",
-    "name": "Self-Hosted AI (LiteLLM)",
-    "base_url": "http://localhost:8000",
-    "api_key": "not_used",  # LiteLLM doesn't require auth (internal)
-    "enabled": True,
-    "priority": 10,  # Try self-hosted first
-    "models": {
-        "text_generation": "qwen3:32b",
-        "text_generation_fast": "qwen3:8b",
-        "image_generation": "flux.1-dev",
-        "image_generation_fast": "sdxl-lightning"
-    },
-    "timeout": 300,  # 5 minute timeout for slow models
-    "fallback_to": "openai"  # Fallback provider if self-hosted fails
-}
+# Create via admin or migration:
+IntegrationProvider.objects.create(
+    provider_id='self_hosted_ai',
+    display_name='Self-Hosted AI (LiteLLM)',
+    provider_type='ai',
+    api_key='',  # LiteLLM doesn't require auth (internal)
+    api_endpoint='http://localhost:8000',
+    is_active=True,
+    is_sandbox=False,
+    config={
+        "priority": 10,  # Try self-hosted first
+        "models": {
+            "text_generation": "qwen3:32b",
+            "text_generation_fast": "qwen3:8b",
+            "image_generation": "flux.1-dev",
+            "image_generation_fast": "sdxl-lightning"
+        },
+        "timeout": 300,  # 5 minute timeout for slow models
+        "fallback_to": "openai"  # Fallback provider if self-hosted fails
+    }
+)
 ```
 
 ### LiteLLM API Endpoints