improvements

.env.example

@@ -13,68 +13,60 @@ OIDC_ENDPOINT=https://your-oidc-provider.com
 OIDC_CLIENT_ID=your-client-id
 OIDC_CLIENT_SECRET=your-client-secret
 
-# === AI Configuration ===
+# ===================================================================
+# AI CONFIGURATION - Complete Reference for Improved Pipeline
+# ===================================================================
 
-# Selector AI (for selection stage, choode a good model) 
-AI_SELECTOR_ENDPOINT=https://llm.mikoshi.de
-AI_SELECTOR_API_KEY=sk-DzREDACTEDHA
-AI_SELECTOR_MODEL=mistral/mistral-medium-latest
+# === CORE AI ENDPOINTS & MODELS ===
+AI_API_ENDPOINT=https://llm.mikoshi.de
+AI_API_KEY=sREDACTED3w
+AI_MODEL='mistral/mistral-small-latest'
 
-# Analyzer AI (for analysis stage, choose a smaller model)
+# === IMPROVED PIPELINE: Use separate analyzer model (mistral-small is fine) ===
 AI_ANALYZER_ENDPOINT=https://llm.mikoshi.de
-AI_ANALYZER_API_KEY=sk-DzREDACTEDnHA
-AI_ANALYZER_MODEL=mistral/mistral-small-latest
+AI_ANALYZER_API_KEY=skREDACTEDw3w  
+AI_ANALYZER_MODEL='mistral/mistral-small-latest'
 
-# === Embeddings Configuration ===
-# Enable/disable semantic embeddings pre-selection
+# === EMBEDDINGS CONFIGURATION ===
 AI_EMBEDDINGS_ENABLED=true
-
-# Embeddings API (Mistral recommended)
 AI_EMBEDDINGS_ENDPOINT=https://api.mistral.ai/v1/embeddings
-AI_EMBEDDINGS_API_KEY=ZSpREDACTED3wL
+AI_EMBEDDINGS_API_KEY=ZREDACTED3wL
 AI_EMBEDDINGS_MODEL=mistral-embed
-
-# Embeddings performance settings
 AI_EMBEDDINGS_BATCH_SIZE=20
 AI_EMBEDDINGS_BATCH_DELAY_MS=1000
-AI_EMBEDDING_CANDIDATES=30
-AI_SIMILARITY_THRESHOLD=0.3
 
-# Delay between micro-tasks to respect rate limits (milliseconds)
-AI_MICRO_TASK_DELAY_MS=500
+# === PIPELINE: VectorIndex (HNSW) Configuration ===
+AI_MAX_SELECTED_ITEMS=60                    # Tools visible to each micro-task 
+AI_EMBEDDING_CANDIDATES=60                  # VectorIndex candidates (HNSW is more efficient)
+AI_SIMILARITY_THRESHOLD=0.3                # Not used by VectorIndex (uses cosine distance internally)
 
-# Micro-task specific rate limiting (requests per minute per user)
-AI_MICRO_TASK_RATE_LIMIT=30
+# === MICRO-TASK CONFIGURATION ===
+AI_MICRO_TASK_DELAY_MS=500                 # Delay between micro-tasks  
+AI_MICRO_TASK_TIMEOUT_MS=25000             # Timeout per micro-task (increased for full context)
 
-# Maximum parallel micro-tasks (for future parallel processing)
-AI_MAX_PARALLEL_TASKS=3
+# === RATE LIMITING ===
+AI_RATE_LIMIT_DELAY_MS=3000                # Main rate limit delay
+AI_RATE_LIMIT_MAX_REQUESTS=6               # Main requests per minute (reduced - fewer but richer calls)
+AI_MICRO_TASK_RATE_LIMIT=15                # Micro-task requests per minute (was 30)
 
-# Micro-task timeout settings (milliseconds)
-AI_MICRO_TASK_TIMEOUT_MS=15000
-
-# ENHANCED: Rate Limiting Configuration
-# Main query rate limiting (reduced due to micro-tasks)
-AI_RATE_LIMIT_DELAY_MS=3000
-AI_RATE_LIMIT_MAX_REQUESTS=8
-
-# Smart prompting rate limiting 
-AI_SMART_PROMPTING_RATE_LIMIT=5
-AI_SMART_PROMPTING_WINDOW_MS=60000
-
-# Queue management settings
+# === QUEUE MANAGEMENT ===
 AI_QUEUE_MAX_SIZE=50
 AI_QUEUE_CLEANUP_INTERVAL_MS=300000
 
-# === Performance & Monitoring ===
-# Enable detailed micro-task logging
-AI_MICRO_TASK_DEBUG=false
-
-# Enable performance metrics collection
+# === PERFORMANCE & MONITORING ===
+AI_MICRO_TASK_DEBUG=true
 AI_PERFORMANCE_METRICS=true
-
-# Cache settings for AI responses
 AI_RESPONSE_CACHE_TTL_MS=3600000
 
+# ===================================================================
+# LEGACY VARIABLES (still used but less important)
+# ===================================================================
+
+# These are still used by other parts of the system:
+AI_RESPONSE_CACHE_TTL_MS=3600000           # For caching responses
+AI_QUEUE_MAX_SIZE=50                       # Queue management
+AI_QUEUE_CLEANUP_INTERVAL_MS=300000       # Queue cleanup
+
 # === Application Configuration ===
 PUBLIC_BASE_URL=http://localhost:4321
 NODE_ENV=development