config/.env.example

# =============================================================================
# Design System Extractor v2 — Environment Variables
# =============================================================================
# Copy this file to .env and fill in your values
# NEVER commit .env to version control
# =============================================================================

# -----------------------------------------------------------------------------
# REQUIRED: Hugging Face Token (Pro recommended for best models)
# -----------------------------------------------------------------------------

# HuggingFace Token (for Spaces deployment and model access)
# Get yours at: https://huggingface.co/settings/tokens
# Pro subscription unlocks: Llama 3.1 405B, Qwen 72B, Command R+, etc.
HF_TOKEN=your_huggingface_token_here

# HuggingFace Space name (for deployment)
HF_SPACE_NAME=your-username/design-system-extractor

# -----------------------------------------------------------------------------
# MODEL CONFIGURATION — Diverse Models for Different Tasks
# -----------------------------------------------------------------------------

# === Agent 1 (Crawler/Extractor): NO LLM NEEDED ===
# Pure rule-based extraction using Playwright + CSS parsing

# === Agent 2 (Normalizer): FAST STRUCTURED OUTPUT ===
# Task: Token naming, duplicate detection, pattern inference
# Needs: Good instruction following, JSON output, SPEED
# 
# Options (pick one):
#   - microsoft/Phi-3.5-mini-instruct     (Fast, great for structured tasks)
#   - mistralai/Mistral-7B-Instruct-v0.3  (Fast, good JSON)
#   - google/gemma-2-9b-it                (Balanced speed/quality)
#   - Qwen/Qwen2.5-7B-Instruct            (Good all-rounder)
AGENT2_MODEL=microsoft/Phi-3.5-mini-instruct

# === Agent 3 (Advisor): STRONG REASONING — Most Important! ===
# Task: Design system analysis, best practice recommendations, trade-off analysis
# Needs: Deep reasoning, design knowledge, creative suggestions
#
# Options (pick one - Pro tier recommended):
#   - meta-llama/Llama-3.1-70B-Instruct   (Excellent reasoning, long context)
#   - CohereForAI/c4ai-command-r-plus     (Great for analysis & recommendations)
#   - Qwen/Qwen2.5-72B-Instruct           (Strong reasoning, good design knowledge)
#   - mistralai/Mixtral-8x22B-Instruct-v0.1 (Large MoE, good balance)
#   - meta-llama/Llama-3.1-405B-Instruct  (BEST - if you have Pro++)
AGENT3_MODEL=meta-llama/Llama-3.1-70B-Instruct

# === Agent 4 (Generator): CODE/JSON SPECIALIST ===
# Task: Generate Tokens Studio JSON, CSS variables, structured output
# Needs: Precise formatting, code generation, schema adherence
#
# Options (pick one):
#   - codellama/CodeLlama-34b-Instruct-hf (Code specialist)
#   - bigcode/starcoder2-15b-instruct-v0.1 (Code generation)
#   - mistralai/Codestral-22B-v0.1        (Mistral's code model)
#   - deepseek-ai/deepseek-coder-33b-instruct (Strong code model)
AGENT4_MODEL=mistralai/Codestral-22B-v0.1

# === Fallback Model (if primary fails) ===
FALLBACK_MODEL=mistralai/Mistral-7B-Instruct-v0.3

# -----------------------------------------------------------------------------
# PRESET CONFIGURATIONS
# -----------------------------------------------------------------------------

# Uncomment ONE preset below, or configure individually above

# --- PRESET: BUDGET (Free tier compatible) ---
# AGENT2_MODEL=microsoft/Phi-3.5-mini-instruct
# AGENT3_MODEL=mistralai/Mixtral-8x7B-Instruct-v0.1
# AGENT4_MODEL=mistralai/Mistral-7B-Instruct-v0.3

# --- PRESET: BALANCED (Pro tier) ---
# AGENT2_MODEL=google/gemma-2-9b-it
# AGENT3_MODEL=meta-llama/Llama-3.1-70B-Instruct
# AGENT4_MODEL=mistralai/Codestral-22B-v0.1

# --- PRESET: MAXIMUM QUALITY (Pro tier) ---
# AGENT2_MODEL=google/gemma-2-27b-it
# AGENT3_MODEL=meta-llama/Llama-3.1-405B-Instruct
# AGENT4_MODEL=deepseek-ai/deepseek-coder-33b-instruct

# -----------------------------------------------------------------------------
# OPTIONAL: Application Settings
# -----------------------------------------------------------------------------

DEBUG=false
LOG_LEVEL=INFO
MAX_PAGES=20
MIN_PAGES=10

# -----------------------------------------------------------------------------
# OPTIONAL: Browser Settings (Playwright)
# -----------------------------------------------------------------------------

BROWSER_TYPE=chromium
BROWSER_HEADLESS=true
BROWSER_TIMEOUT=30000
NETWORK_IDLE_TIMEOUT=5000

# -----------------------------------------------------------------------------
# OPTIONAL: Storage Settings
# -----------------------------------------------------------------------------

STORAGE_PATH=/data
ENABLE_PERSISTENCE=true
MAX_VERSIONS=10

# -----------------------------------------------------------------------------
# OPTIONAL: Rate Limiting
# -----------------------------------------------------------------------------

CRAWL_DELAY_MS=1000
MAX_CONCURRENT_CRAWLS=3
RESPECT_ROBOTS_TXT=true

# -----------------------------------------------------------------------------
# OPTIONAL: HuggingFace Inference Settings
# -----------------------------------------------------------------------------

USE_HF_INFERENCE_API=true
HF_INFERENCE_TIMEOUT=120
HF_MAX_NEW_TOKENS=2048
HF_TEMPERATURE=0.3

# -----------------------------------------------------------------------------
# OPTIONAL: UI Settings
# -----------------------------------------------------------------------------

SERVER_PORT=7860
SHARE=false
UI_THEME=soft

# -----------------------------------------------------------------------------
# OPTIONAL: Feature Flags
# -----------------------------------------------------------------------------

FEATURE_COLOR_RAMPS=true
FEATURE_TYPE_SCALES=true
FEATURE_A11Y_CHECKS=true
FEATURE_PARALLEL_EXTRACTION=true