ai-inference-stepper 1.0.0

package/.env.example

@@ -0,0 +1,169 @@
+# Node environment
+NODE_ENV=development
+
+# Server configuration
+PORT=3001
+LOG_LEVEL=debug
+# Trust proxy for proper IP detection (1=single proxy, true=any, or specific IPs)
+# Required when behind nginx, ELB, Cloudflare, etc.
+TRUST_PROXY=1
+
+# Redis configuration
+REDIS_URL=redis://localhost:6379
+REDIS_KEY_PREFIX=stepper:
+
+# Cache configuration
+CACHE_TTL_SECONDS=604800
+CACHE_STALE_THRESHOLD=86400
+CACHE_STALE_WHILE_REVALIDATE=true
+
+# Queue configuration
+QUEUE_NAME=report-generation
+QUEUE_CONCURRENCY=5
+
+# Webhook configuration
+WEBHOOK_ENABLED=true
+# Must match API's WEBHOOK_SECRET - Generate with: openssl rand -hex 32
+WEBHOOK_SECRET=your-webhook-secret-here
+WEBHOOK_MAX_RETRIES=3
+WEBHOOK_RETRY_DELAY_MS=5000
+
+# Retry configuration
+RETRY_MAX_ATTEMPTS=3
+RETRY_BASE_DELAY_MS=500
+RETRY_MAX_JITTER_MS=300
+RETRY_RATE_LIMIT_FALLBACK=7200
+
+# Circuit breaker configuration
+CIRCUIT_FAILURE_THRESHOLD=5
+CIRCUIT_WINDOW_SECONDS=300
+CIRCUIT_COOLDOWN_SECONDS=300
+
+# Security - Sensitive Data Redaction
+REDACT_BEFORE_SEND=true
+
+# Security - CORS (Cross-Origin Resource Sharing)
+CORS_ENABLED=true
+CORS_ALLOWED_ORIGINS=https://yourdomain.com,https://app.yourdomain.com
+CORS_ALLOW_CREDENTIALS=false
+
+# Security - Rate Limiting
+RATE_LIMIT_ENABLED=true
+RATE_LIMIT_WINDOW_MS=900000
+RATE_LIMIT_MAX_REQUESTS=100
+RATE_LIMIT_MAX_PER_USER=50
+RATE_LIMIT_SKIP_HEALTH=true
+
+# Security - Helmet (Security Headers)
+HELMET_ENABLED=true
+
+# Security - API Key Authentication
+API_KEY_ENABLED=false
+API_KEY_HEADER=x-api-key
+STEPPER_API_KEY=your_secret_api_key_here
+API_KEY_SKIP_HEALTH=true
+
+# Alerts (optional)
+DISCORD_WEBHOOK_URL=https://discord.com/api/webhooks/your_webhook_url
+
+# --- Provider Configurations ---
+
+# Hugging Face Space
+HF_SPACE_ENABLED=false
+HF_SPACE_URL=https://your-space-name.hf.space
+HF_SPACE_API_KEY=your_hf_api_key_here
+HF_SPACE_RPS=3
+HF_SPACE_CONCURRENCY=1
+HF_SPACE_TIMEOUT=30000
+
+# Google Gemini
+GEMINI_ENABLED=false
+GEMINI_API_KEY=your_gemini_api_key_here
+GEMINI_BASE_URL=https://generativelanguage.googleapis.com
+GEMINI_MODEL=gemini-pro
+GEMINI_RPS=10
+GEMINI_CONCURRENCY=4
+GEMINI_TIMEOUT=15000
+
+# OpenAI
+OPENAI_ENABLED=false
+OPENAI_API_KEY=your_openai_key_here
+OPENAI_BASE_URL=https://api.openai.com
+OPENAI_MODEL=gpt-4-turbo-preview
+OPENAI_TIMEOUT=30000
+OPENAI_RPS=5
+OPENAI_CONCURRENCY=2
+
+# Anthropic Claude
+ANTHROPIC_ENABLED=false
+ANTHROPIC_API_KEY=your_anthropic_key_here
+ANTHROPIC_BASE_URL=https://api.anthropic.com
+ANTHROPIC_MODEL=claude-3-5-sonnet-20241022
+ANTHROPIC_TIMEOUT=30000
+ANTHROPIC_RPS=5
+ANTHROPIC_CONCURRENCY=2
+
+# Cohere
+COHERE_ENABLED=false
+COHERE_API_KEY=your_cohere_key_here
+COHERE_BASE_URL=https://api.cohere.ai
+COHERE_MODEL=command-r-plus
+COHERE_TIMEOUT=20000
+COHERE_RPS=5
+COHERE_CONCURRENCY=2
+
+# DeepSeek
+DEEPSEEK_ENABLED=false
+DEEPSEEK_API_KEY=your_deepseek_key_here
+DEEPSEEK_BASE_URL=https://api.deepseek.com
+DEEPSEEK_MODEL=deepseek-chat
+DEEPSEEK_TIMEOUT=20000
+DEEPSEEK_RPS=5
+DEEPSEEK_CONCURRENCY=2
+
+# Groq
+GROQ_ENABLED=false
+GROQ_API_KEY=your_groq_key_here
+GROQ_BASE_URL=https://api.groq.com/openai
+GROQ_MODEL=mixtral-8x7b-32768
+GROQ_TIMEOUT=10000
+GROQ_RPS=10
+GROQ_CONCURRENCY=4
+
+# OpenRouter
+OPENROUTER_ENABLED=false
+OPENROUTER_API_KEY=your_openrouter_key_here
+OPENROUTER_BASE_URL=https://openrouter.ai/api
+OPENROUTER_MODEL=anthropic/claude-3.5-sonnet
+OPENROUTER_TIMEOUT=30000
+OPENROUTER_RPS=5
+OPENROUTER_CONCURRENCY=2
+OPENROUTER_REFERER=https://commitdiary.com
+OPENROUTER_TITLE=CommitDiary Stepper
+
+# Mistral AI
+MISTRAL_ENABLED=false
+MISTRAL_API_KEY=your_key
+MISTRAL_BASE_URL=https://api.mistral.ai
+MISTRAL_MODEL=mistral-large-latest
+MISTRAL_TIMEOUT=15000
+MISTRAL_RPS=5
+MISTRAL_CONCURRENCY=2
+
+# Perplexity AI
+PERPLEXITY_ENABLED=false
+PERPLEXITY_API_KEY=your_key
+PERPLEXITY_BASE_URL=https://api.perplexity.ai
+PERPLEXITY_MODEL=llama-3.1-sonar-large-128k-online
+PERPLEXITY_TIMEOUT=20000
+PERPLEXITY_RPS=5
+PERPLEXITY_CONCURRENCY=2
+
+# Together AI
+TOGETHER_ENABLED=false
+TOGETHER_API_KEY=your_key
+TOGETHER_BASE_URL=https://api.together.xyz
+TOGETHER_MODEL=meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
+TOGETHER_TIMEOUT=20000
+TOGETHER_RPS=5
+TOGETHER_CONCURRENCY=2

package/.eslintrc.cjs

@@ -0,0 +1,23 @@
+module.exports = {
+  parser: '@typescript-eslint/parser',
+  parserOptions: {
+    ecmaVersion: 2022,
+    sourceType: 'module',
+    project: './tsconfig.json',
+  },
+  plugins: ['@typescript-eslint'],
+  extends: [
+    'eslint:recommended',
+    'plugin:@typescript-eslint/recommended',
+  ],
+  rules: {
+    '@typescript-eslint/no-unused-vars': ['error', { argsIgnorePattern: '^_' }],
+    '@typescript-eslint/explicit-function-return-type': 'off',
+    '@typescript-eslint/no-explicit-any': 'error',
+    'no-console': 'warn',
+  },
+  env: {
+    node: true,
+    es2022: true,
+  },
+};

package/.github/workflows/ci.yml

@@ -0,0 +1,51 @@
+name: CI
+
+on:
+  push:
+    branches: [main, develop]
+  pull_request:
+    branches: [main, develop]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    services:
+      redis:
+        image: redis:7-alpine
+        ports:
+          - 6379:6379
+        options: >-
+          --health-cmd "redis-cli ping"
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 5
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '18'
+
+      - name: Install pnpm
+        run: npm install -g pnpm
+
+      - name: Install dependencies
+        run: pnpm install # Removed --frozen-lockfile until you push a fresh lockfile
+
+      - name: Lint
+        run: pnpm lint
+
+      - name: Type check
+        run: pnpm typecheck
+
+      - name: Build
+        run: pnpm build
+
+      - name: Test
+        run: pnpm test
+        env:
+          REDIS_URL: redis://localhost:6379
+          NODE_ENV: test

package/.github/workflows/keep-alive.yml

@@ -0,0 +1,22 @@
+name: Render Keep-Alive
+
+on:
+  schedule:
+    # Run every 10 minutes to prevent Render free tier from sleeping
+    - cron: "*/10 * * * *"
+  workflow_dispatch: # Allows manual triggering for testing
+
+jobs:
+  ping:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Ping Render Service
+        run: |
+          URL="${{ secrets.RENDER_APP_URL }}"
+          if [ -z "$URL" ]; then
+            echo "Error: RENDER_APP_URL secret is not set."
+            echo "Please go to Settings > Secrets and variables > Actions and add RENDER_APP_URL (e.g., https://your-app.onrender.com)"
+            exit 1
+          fi
+          echo "Pinging $URL/health..."
+          curl -f -s "$URL/health" || echo "Ping failed, but that's okay (server might be starting up)."

package/.github/workflows/publish.yml

@@ -0,0 +1,34 @@
+name: Publish
+
+on:
+  workflow_dispatch:
+  release:
+    types: [published]
+
+permissions:
+  contents: read
+  id-token: write
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Node
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20
+          registry-url: https://registry.npmjs.org/
+
+      - name: Install
+        run: npm install
+
+      - name: Build
+        run: npm run build
+
+      - name: Publish
+        run: npm publish --access public
+        env:
+          NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}