Fix Render deployment dependencies for Quant.ai and InferRoute

Dockerfile

@@ -30,6 +30,8 @@ COPY inferroute/ ./inferroute/
 COPY docs/ ./docs/
 COPY benchmarks/ ./benchmarks/
 COPY external/ ./external/
+COPY *.html ./
+COPY assets/ ./assets/
 
 # Expose default port (7860 for Hugging Face Spaces)
 EXPOSE 7860

app.py

@@ -0,0 +1,13 @@
+import sys
+import os
+import uvicorn
+
+# Ensure project root is in sys.path
+root_dir = os.path.dirname(os.path.abspath(__file__))
+if root_dir not in sys.path:
+    sys.path.insert(0, root_dir)
+
+from inferroute.main import app
+
+if __name__ == "__main__":
+    uvicorn.run("inferroute.main:app", host="0.0.0.0", port=7860, reload=False)

external/Quant.ai/README.md

@@ -3,7 +3,8 @@ title: Quant AI - Advanced Quant Trading Engine & Backtest Simulator
 emoji: 📈
 colorFrom: blue
 colorTo: indigo
-sdk: static
+sdk: docker
+app_port: 7860
 pinned: false
 ---
 

external/Quant.ai/backend/main_api.py

@@ -1,4 +1,11 @@
 import os
+import sys
+
+# Ensure backend directory is in sys.path for importing 'app' modules
+backend_dir = os.path.dirname(os.path.abspath(__file__))
+if backend_dir not in sys.path:
+    sys.path.insert(0, backend_dir)
+
 from fastapi import FastAPI, Query
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.staticfiles import StaticFiles

external/Quant.ai/frontend/src/config.ts

@@ -1,15 +1,16 @@
 // frontend/src/config.ts
 // Automatically resolves backend API URL for local dev, Docker container, or deployed HF Space
 
-let defaultApiBase = 'http://127.0.0.1:8000';
+let defaultApiBase = 'https://inferroute-977n.onrender.com';
 
 if (typeof window !== 'undefined') {
-  if (window.location.port === '5173' || window.location.port === '3000') {
+  if (window.location.port === '5173' || window.location.port === '3000' || window.location.hostname === 'localhost' || window.location.hostname === '127.0.0.1') {
     defaultApiBase = 'http://127.0.0.1:8000';
   } else {
-    // When served via FastAPI server or hosted Space
-    defaultApiBase = window.location.origin;
+    // When hosted on Static HF Space or served via cloud FastAPI
+    defaultApiBase = 'https://inferroute-977n.onrender.com';
   }
 }
 
-export const API_BASE = (import.meta.env?.VITE_API_BASE as string) || defaultApiBase;
+export const API_BASE = (import.meta.env?.VITE_API_BASE as string) || (typeof window !== 'undefined' && localStorage.getItem('API_BASE')) || defaultApiBase;
+

index.html

@@ -76,16 +76,16 @@
             <span>🚀 InferRoute & Quant.ai Hub</span>
         </div>
         <div class="tabs">
-            <button class="tab-btn active" onclick="switchTab('quant')">
-                <span>📈</span> Quant.ai Trading Terminal
-            </button>
-            <button class="tab-btn" onclick="switchTab('platform')">
+            <button class="tab-btn active" onclick="switchTab('platform')">
                 <span>🌐</span> InferRoute LLM Gateway
             </button>
+            <button class="tab-btn" onclick="switchTab('quant')">
+                <span>📈</span> Quant.ai Trading Terminal
+            </button>
         </div>
     </div>
 
-    <iframe id="mainFrame" class="content-frame" src="quant.html"></iframe>
+    <iframe id="mainFrame" class="content-frame" src="platform.html"></iframe>
 
     <script>
         function switchTab(tab) {
@@ -94,11 +94,11 @@
             
             btns.forEach(btn => btn.classList.remove('active'));
 
-            if (tab === 'quant') {
-                frame.src = 'quant.html';
+            if (tab === 'platform') {
+                frame.src = 'platform.html';
                 btns[0].classList.add('active');
             } else {
-                frame.src = 'platform.html';
+                frame.src = 'quant.html';
                 btns[1].classList.add('active');
             }
         }

inferroute/main.py

@@ -150,8 +150,22 @@ if os.path.exists(quant_dist_dir):
 
 
 
+@app.get("/quant.html", response_class=HTMLResponse)
+async def get_quant_html_page():
+    root_quant = os.path.join(os.path.dirname(os.path.dirname(__file__)), "quant.html")
+    if os.path.exists(root_quant):
+        with open(root_quant, "r", encoding="utf-8") as f:
+            return f.read()
+    return await get_quant_page("")
+
+
 @app.get("/platform", response_class=HTMLResponse)
+@app.get("/platform.html", response_class=HTMLResponse)
 async def get_platform_page():
+    root_platform = os.path.join(os.path.dirname(os.path.dirname(__file__)), "platform.html")
+    if os.path.exists(root_platform):
+        with open(root_platform, "r", encoding="utf-8") as f:
+            return f.read()
     template_path = os.path.join(os.path.dirname(__file__), "templates", "platform.html")
     if os.path.exists(template_path):
         with open(template_path, "r", encoding="utf-8") as f:
@@ -413,9 +427,13 @@ async def list_providers():
 
 
 @app.get("/", response_class=HTMLResponse, tags=["ui"])
+@app.get("/index.html", response_class=HTMLResponse, tags=["ui"])
 async def get_playground():
-    """Serves the interactive playground UI."""
-    import os
+    """Serves the interactive gateway hub / playground UI."""
+    root_index = os.path.join(os.path.dirname(os.path.dirname(__file__)), "index.html")
+    if os.path.exists(root_index):
+        with open(root_index, "r", encoding="utf-8") as f:
+            return f.read()
     template_path = os.path.join(os.path.dirname(__file__), "templates", "playground.html")
     if not os.path.exists(template_path):
         raise HTTPException(status_code=404, detail="Playground UI template not found")

platform/index.html

@@ -0,0 +1,614 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>InferRoute - Multi-LLM API Gateway & Cost Optimization Engine</title>
+    <link href="https://fonts.googleapis.com/css2?family=Outfit:wght@300;400;500;600;700;800&family=JetBrains+Mono:wght@400;500;600&display=swap" rel="stylesheet">
+    <style>
+        :root {
+            --bg-light: #f8fafc;
+            --card-bg: #ffffff;
+            --card-border: #e2e8f0;
+            --card-shadow: 0 4px 20px -2px rgba(0, 0, 0, 0.05), 0 2px 6px -1px rgba(0, 0, 0, 0.02);
+            --accent-blue: #2563eb;
+            --accent-blue-light: #eff6ff;
+            --accent-cyan: #0891b2;
+            --accent-green: #16a34a;
+            --accent-purple: #7c3aed;
+            --accent-amber: #d97706;
+            --accent-red: #dc2626;
+            --text-main: #0f172a;
+            --text-muted: #64748b;
+        }
+
+        * { box-sizing: border-box; margin: 0; padding: 0; font-family: 'Outfit', -apple-system, sans-serif; }
+        body { background: var(--bg-light); color: var(--text-main); min-height: 100vh; display: flex; flex-direction: column; overflow-x: hidden; }
+
+        header {
+            position: sticky; top: 0; z-index: 50; backdrop-filter: blur(12px);
+            background: rgba(255, 255, 255, 0.92); border-bottom: 1px solid var(--card-border);
+            padding: 0.85rem 2rem; display: flex; justify-content: space-between; align-items: center;
+            box-shadow: 0 1px 3px rgba(0,0,0,0.03);
+        }
+        .brand { display: flex; align-items: center; gap: 0.75rem; font-weight: 800; font-size: 1.35rem; color: var(--text-main); cursor: pointer; }
+        .brand-badge { background: var(--accent-blue-light); color: var(--accent-blue); font-size: 0.75rem; padding: 0.2rem 0.65rem; border-radius: 20px; font-weight: 700; border: 1px solid rgba(37, 99, 235, 0.2); }
+        
+        .nav-links { display: flex; gap: 1.5rem; align-items: center; }
+        .nav-link { color: var(--text-muted); text-decoration: none; font-weight: 600; font-size: 0.95rem; transition: color 0.2s; cursor: pointer; }
+        .nav-link:hover, .nav-link.active { color: var(--accent-blue); }
+
+        .header-controls { display: flex; gap: 1rem; align-items: center; }
+        .stat-pill { background: #fff; border: 1px solid var(--card-border); padding: 0.4rem 0.85rem; border-radius: 8px; font-size: 0.85rem; display: flex; align-items: center; gap: 0.5rem; }
+        .stat-val { font-weight: 700; color: var(--accent-green); }
+
+        .lang-toggle {
+            background: #ffffff; border: 1px solid var(--card-border); padding: 0.4rem 0.85rem;
+            border-radius: 8px; font-weight: 700; font-size: 0.85rem; cursor: pointer; color: var(--accent-blue);
+            transition: all 0.2s; display: flex; align-items: center; gap: 0.4rem;
+        }
+        .lang-toggle:hover { background: var(--accent-blue-light); }
+
+        main { max-width: 1200px; width: 100%; margin: 0 auto; padding: 2rem 1.5rem; display: flex; flex-direction: column; gap: 2rem; }
+
+        .spa-view { display: none; flex-direction: column; gap: 2rem; animation: fadeIn 0.3s ease-in-out; }
+        .spa-view.active { display: flex; }
+
+        @keyframes fadeIn { from { opacity: 0; transform: translateY(6px); } to { opacity: 1; transform: translateY(0); } }
+
+        .hero {
+            background: linear-gradient(135deg, #ffffff 0%, #eff6ff 100%);
+            border: 1px solid #bfdbfe; border-radius: 16px; padding: 2.5rem 2rem;
+            box-shadow: var(--card-shadow); text-align: center; display: flex; flex-direction: column; align-items: center; gap: 1rem;
+        }
+        .hero h1 { font-size: 2.3rem; font-weight: 800; color: var(--text-main); line-height: 1.25; }
+        .hero p { font-size: 1.05rem; color: var(--text-muted); max-width: 860px; line-height: 1.6; }
+
+        .tagline-banner {
+            display: inline-flex; gap: 0.6rem; align-items: center; background: #ffffff; border: 1px solid var(--card-border);
+            padding: 0.5rem 1.2rem; border-radius: 30px; font-size: 0.88rem; font-weight: 700; color: var(--accent-blue);
+        }
+
+        .card {
+            background: var(--card-bg); border: 1px solid var(--card-border); border-radius: 16px;
+            padding: 1.75rem; box-shadow: var(--card-shadow);
+        }
+        .card-header { display: flex; justify-content: space-between; align-items: center; margin-bottom: 1.2rem; }
+        .card-title { font-size: 1.25rem; font-weight: 800; color: var(--text-main); display: flex; align-items: center; gap: 0.6rem; }
+
+        .grid-2 { display: grid; grid-template-columns: 1fr 1fr; gap: 1.5rem; }
+        .grid-3 { display: grid; grid-template-columns: repeat(3, 1fr); gap: 1.5rem; }
+        .grid-4 { display: grid; grid-template-columns: repeat(4, 1fr); gap: 1.25rem; }
+
+        .output-box {
+            background: #0f172a; border: 1px solid var(--card-border); border-radius: 10px;
+            padding: 1.25rem; color: #34d399; font-size: 0.9rem; max-height: 380px; overflow-y: auto; white-space: pre-wrap; line-height: 1.6;
+        }
+
+        .code-box {
+            background: #0f172a; border: 1px solid var(--card-border); border-radius: 10px;
+            padding: 1.2rem; color: #e2e8f0; font-size: 0.85rem; overflow-x: auto; line-height: 1.6; font-family: 'JetBrains Mono', monospace;
+        }
+
+        .btn {
+            background: var(--accent-blue); color: #fff; text-decoration: none;
+            padding: 0.75rem 1.5rem; border: none; border-radius: 8px; font-weight: 700; cursor: pointer;
+            display: inline-flex; align-items: center; gap: 0.5rem; transition: all 0.2s ease; font-size: 0.95rem;
+        }
+        .btn:hover { background: #1d4ed8; transform: translateY(-1px); }
+        .btn-outline { background: transparent; border: 1px solid var(--card-border); color: var(--text-main); }
+        .btn-outline:hover { background: #f1f5f9; }
+
+        .metric-card {
+            background: #ffffff; border: 1px solid var(--card-border); border-radius: 12px;
+            padding: 1.25rem; text-align: center; display: flex; flex-direction: column; gap: 0.4rem; box-shadow: var(--card-shadow);
+        }
+        .metric-num { font-size: 1.8rem; font-weight: 800; color: var(--text-main); }
+        .metric-sub { font-size: 0.75rem; color: var(--text-muted); }
+
+        .status-dot { width: 10px; height: 10px; border-radius: 50%; display: inline-block; background: var(--accent-green); }
+        .tag-badge { background: #e0f2fe; color: #0369a1; font-size: 0.75rem; padding: 0.2rem 0.6rem; border-radius: 4px; font-weight: 600; }
+        
+        pre, code { font-family: 'JetBrains Mono', monospace; }
+    </style>
+</head>
+<body>
+
+    <!-- Header Navigation -->
+    <header>
+        <div class="brand" onclick="navigateTo('api')">
+            🚀 InferRoute <span class="brand-badge">Multi-LLM Gateway</span>
+        </div>
+        <div class="nav-links">
+            <span class="nav-link active" onclick="navigateTo('api')" id="navApi">API Integration</span>
+            <span class="nav-link" onclick="navigateTo('apps')" id="navApps">App Showcase</span>
+            <span class="nav-link" onclick="navigateTo('proof')" id="navProof">Empirical Proof</span>
+            <span class="nav-link" onclick="navigateTo('cost')" id="navCost">Cost Savings</span>
+            <span class="nav-link" onclick="navigateTo('analytics')" id="navAnalytics">Live Dashboard</span>
+        </div>
+        <div class="header-controls">
+            <button class="lang-toggle" onclick="toggleLanguage()">
+                🌐 <span id="currentLangLabel">Language: EN</span>
+            </button>
+            <div class="stat-pill">Status: <span class="status-dot"></span> <span style="font-weight:700;">ONLINE</span></div>
+        </div>
+    </header>
+
+    <main>
+
+        <!-- VIEW 1: API INTEGRATION QUICKSTART (HOW TO USE IN YOUR PROJECTS) -->
+        <div class="spa-view active" id="viewApi">
+            <section class="hero">
+                <div class="tagline-banner" id="tagline">⚡ 100% Compatible with OpenAI SDK & LangChain</div>
+                <h1 id="heroTitle">InferRoute: 1-Minute API Integration Guide</h1>
+                <p id="heroDesc">
+                    Plug InferRoute into any existing AI application in 1 minute. Redirect <code>base_url</code> to gain 35.8% KV-cache prefill acceleration, multi-provider failover, and up to 87.7% cost reduction.
+                </p>
+            </section>
+
+            <!-- SECTION 1: CODE INTEGRATION SNIPPETS -->
+            <section class="card">
+                <div class="card-header">
+                    <div class="card-title">🔑 <span id="sec1Title">1-Min SDK Integration Code Snippets</span></div>
+                </div>
+
+                <div class="grid-2">
+                    <div>
+                        <label style="font-weight:700; font-size:0.85rem; display:block; margin-bottom:0.5rem;" id="lblPySdk">Python OpenAI SDK (1-Line Base URL Change)</label>
+                        <div class="code-box"><span style="color:#60a5fa;">from</span> openai <span style="color:#60a5fa;">import</span> OpenAI
+
+<span style="color:#94a3b8;"># Simply set base_url to InferRoute Gateway</span>
+client = OpenAI(
+    api_key=<span style="color:#34d399;">"sk-inferroute-demo"</span>,
+    base_url=<span style="color:#34d399;">"http://localhost:8080/v1"</span>  <span style="color:#94a3b8;"># Or public Space URL</span>
+)
+
+response = client.chat.completions.create(
+    model=<span style="color:#34d399;">"edge/auto"</span>,  <span style="color:#94a3b8;"># Auto-routes across OpenAI/Gemini/vLLM</span>
+    messages=[{<span style="color:#34d399;">"role"</span>: <span style="color:#34d399;">"user"</span>, <span style="color:#34d399;">"content"</span>: <span style="color:#34d399;">"Analyze technical indicators"</span>}]
+)
+<span style="color:#f59e0b;">print</span>(response.choices[0].message.content)</div>
+                    </div>
+
+                    <div>
+                        <label style="font-weight:700; font-size:0.85rem; display:block; margin-bottom:0.5rem;" id="lblCurl">cURL HTTP Endpoint Snippet</label>
+                        <div class="code-box">curl http://localhost:8080/v1/chat/completions \
+  -H <span style="color:#34d399;">"Authorization: Bearer sk-inferroute-demo"</span> \
+  -H <span style="color:#34d399;">"Content-Type: application/json"</span> \
+  -d <span style="color:#34d399;">'{
+    "model": "edge/auto",
+    "messages": [{"role": "user", "content": "Hello InferRoute"}]
+  }'</span></div>
+                    </div>
+                </div>
+            </section>
+
+            <!-- SECTION 2: HOW IT WORKS ARCHITECTURE -->
+            <section class="card">
+                <div class="card-header">
+                    <div class="card-title">⚡ <span id="sec2Title">Gateway Execution & Failover Architecture</span></div>
+                </div>
+
+                <div class="grid-3">
+                    <div style="background:#f8fafc; border:1px solid var(--card-border); padding:1.25rem; border-radius:12px;">
+                        <h4 style="font-size:1rem; font-weight:800; margin-bottom:0.5rem; color:var(--accent-blue);" id="step1Title">1. Radix Trie Cache Matching</h4>
+                        <p style="font-size:0.88rem; color:var(--text-muted); line-height:1.5;" id="step1Desc">
+                            Matches prompt prefix in Radix Trie cache. Cuts prefill latency by 35.8% by reusing KV-cache states across requests.
+                        </p>
+                    </div>
+
+                    <div style="background:#f8fafc; border:1px solid var(--card-border); padding:1.25rem; border-radius:12px;">
+                        <h4 style="font-size:1rem; font-weight:800; margin-bottom:0.5rem; color:var(--accent-purple);" id="step2Title">2. SLO & Complexity Router</h4>
+                        <p style="font-size:0.88rem; color:var(--text-muted); line-height:1.5;" id="step2Desc">
+                            Evaluates prompt difficulty. Dispatches lightweight prompts to Gemini 1.5 / vLLM, and complex code/reasoning to GPT-4o.
+                        </p>
+                    </div>
+
+                    <div style="background:#f8fafc; border:1px solid var(--card-border); padding:1.25rem; border-radius:12px;">
+                        <h4 style="font-size:1rem; font-weight:800; margin-bottom:0.5rem; color:var(--accent-green);" id="step3Title">3. Circuit Breaker & Deduplication</h4>
+                        <p style="font-size:0.88rem; color:var(--text-muted); line-height:1.5;" id="step3Desc">
+                            Monitors provider health. Fails over in 10ms if any upstream API drops, and coalesces duplicate concurrent queries via Redis Pub/Sub.
+                        </p>
+                    </div>
+                </div>
+            </section>
+        </div>
+
+        <!-- VIEW: APP SHOWCASE & ECOSYSTEM (#apps) -->
+        <div class="spa-view" id="viewApps">
+            <div class="card-header" style="margin-bottom:0;">
+                <div class="page-title">
+                    🌐 <span id="appsTitle">Ecosystem App Showcase (Hugging Face Spaces)</span>
+                    <span class="tag-badge" style="background:#e0f2fe; color:#0369a1;">Plug & Play Ecosystem</span>
+                </div>
+            </div>
+
+            <section class="card">
+                <div class="card-header">
+                    <div class="card-title">🧩 <span id="appsSubTitle">Projects Powered by InferRoute API Gateway</span></div>
+                </div>
+
+                <p style="font-size:0.95rem; color:var(--text-muted); line-height:1.6; margin-bottom:1.5rem;" id="appsDesc">
+                    All applications hosted on Hugging Face Spaces or external servers route their LLM requests through InferRoute. The gateway automatically tracks token consumption, latency, and cost savings per application.
+                </p>
+
+                <div class="grid-3" style="margin-bottom:1.5rem;">
+                    <!-- App 1: Quant AI -->
+                    <div style="background:#ffffff; border:1px solid var(--card-border); border-radius:14px; padding:1.5rem; display:flex; flex-direction:column; gap:0.8rem; box-shadow:var(--card-shadow);">
+                        <div style="display:flex; justify-content:space-between; align-items:center;">
+                            <span style="font-size:1.6rem;">📈</span>
+                            <span class="tag-badge" style="background:#dcfce7; color:#15803d;">Active Routing</span>
+                        </div>
+                        <h3 style="font-size:1.15rem; font-weight:800; color:var(--text-main);" id="app1Name">Quant-AI Financial Agent</h3>
+                        <p style="font-size:0.85rem; color:var(--text-muted); line-height:1.5;" id="app1Desc">
+                            Stock analysis, financial report extraction, and quantitative code generation. Uses Cascade routing to guarantee high-reasoning accuracy.
+                        </p>
+                        <div style="background:#f8fafc; border:1px solid var(--card-border); padding:0.6rem 0.8rem; border-radius:6px; font-size:0.78rem; font-family:'JetBrains Mono', monospace; color:var(--accent-blue);">
+                            Tenant ID: quant-app<br>
+                            Savings: ~78.4% Cost Reduction
+                        </div>
+                    </div>
+
+                    <!-- App 2: Face AI -->
+                    <div style="background:#ffffff; border:1px solid var(--card-border); border-radius:14px; padding:1.5rem; display:flex; flex-direction:column; gap:0.8rem; box-shadow:var(--card-shadow);">
+                        <div style="display:flex; justify-content:space-between; align-items:center;">
+                            <span style="font-size:1.6rem;">👤</span>
+                            <span class="tag-badge" style="background:#fef3c7; color:#b45309;">Ready for Integration</span>
+                        </div>
+                        <h3 style="font-size:1.15rem; font-weight:800; color:var(--text-main);" id="app2Name">Face & Vision Feature AI</h3>
+                        <p style="font-size:0.85rem; color:var(--text-muted); line-height:1.5;" id="app2Desc">
+                            Facial attribute analysis and multimodal visual description. Automatically routes visual queries to Gemini Flash / Vision nodes.
+                        </p>
+                        <div style="background:#f8fafc; border:1px solid var(--card-border); padding:0.6rem 0.8rem; border-radius:6px; font-size:0.78rem; font-family:'JetBrains Mono', monospace; color:var(--accent-purple);">
+                            Tenant ID: vision-app<br>
+                            Savings: Prefill Speedup +35%
+                        </div>
+                    </div>
+
+                    <!-- App 3: Agent AI -->
+                    <div style="background:#ffffff; border:1px solid var(--card-border); border-radius:14px; padding:1.5rem; display:flex; flex-direction:column; gap:0.8rem; box-shadow:var(--card-shadow);">
+                        <div style="display:flex; justify-content:space-between; align-items:center;">
+                            <span style="font-size:1.6rem;">🤖</span>
+                            <span class="tag-badge" style="background:#fef3c7; color:#b45309;">Ready for Integration</span>
+                        </div>
+                        <h3 style="font-size:1.15rem; font-weight:800; color:var(--text-main);" id="app3Name">Multi-Agent Framework</h3>
+                        <p style="font-size:0.85rem; color:var(--text-muted); line-height:1.5;" id="app3Desc">
+                            Autonomous multi-agent orchestration. Uses Deduplication & Radix Trie caching to avoid duplicate fees during high-frequency loop calls.
+                        </p>
+                        <div style="background:#f8fafc; border:1px solid var(--card-border); padding:0.6rem 0.8rem; border-radius:6px; font-size:0.78rem; font-family:'JetBrains Mono', monospace; color:var(--accent-cyan);">
+                            Tenant ID: agent-app<br>
+                            Savings: ~65.0% Cost Reduction
+                        </div>
+                    </div>
+                </div>
+
+                <!-- Integration snippet for HuggingFace Spaces -->
+                <div style="background:#f8fafc; border:1px solid var(--card-border); padding:1.25rem; border-radius:12px;">
+                    <h4 style="font-size:0.95rem; font-weight:800; color:var(--text-main); margin-bottom:0.6rem;" id="hfGuideTitle">💡 How HF Space Projects Connect to InferRoute API</h4>
+                    <div class="code-box"><span style="color:#60a5fa;">import</span> os
+<span style="color:#60a5fa;">import</span> openai
+
+<span style="color:#94a3b8;"># In your HuggingFace Space (Gradio / Streamlit app.py):</span>
+client = openai.OpenAI(
+    base_url=os.getenv(<span style="color:#34d399;">"INFERROUTE_BASE_URL"</span>, <span style="color:#34d399;">"http://your-inferroute-gateway/v1"</span>),
+    api_key=os.getenv(<span style="color:#34d399;">"INFERROUTE_API_KEY"</span>, <span style="color:#34d399;">"sk-inferroute-demo"</span>)
+)
+<span style="color:#94a3b8;"># Zero code changes required for completion calls!</span></div>
+                </div>
+            </section>
+        </div>
+
+        <!-- VIEW 2: EMPIRICAL PROOF & BENCHMARK EVIDENCE (#proof) -->
+        <div class="spa-view" id="viewProof">
+            <div class="card-header" style="margin-bottom:0;">
+                <div class="page-title">
+                    📊 <span id="proofTitle">Empirical Benchmark Evidence & Code Verification</span>
+                    <span class="tag-badge">4,682 Evaluation Runs</span>
+                </div>
+            </div>
+
+            <section class="card">
+                <div class="card-header">
+                    <div class="card-title">📈 <span id="proofSubTitle">Benchmark Proof (RouterBench Standard Evaluation)</span></div>
+                </div>
+
+                <div class="grid-4" style="margin-bottom:1.5rem;">
+                    <div class="metric-card">
+                        <div class="metric-num" style="color:var(--accent-blue);">4,682</div>
+                        <div id="p1Title">Evaluation Requests</div>
+                        <div class="metric-sub" id="p1Sub">RouterBench Standard Test</div>
+                    </div>
+                    <div class="metric-card">
+                        <div class="metric-num" style="color:var(--accent-green);">-35.8%</div>
+                        <div id="p2Title">Prefill Latency</div>
+                        <div class="metric-sub" id="p2Sub">Radix Trie KV-Cache Boost</div>
+                    </div>
+                    <div class="metric-card">
+                        <div class="metric-num" style="color:var(--accent-purple);">99.2%</div>
+                        <div id="p3Title">Accuracy Retention</div>
+                        <div class="metric-sub" id="p3Sub">vs Pure GPT-4 Oracle</div>
+                    </div>
+                    <div class="metric-card">
+                        <div class="metric-num" style="color:var(--accent-amber);">99.99%</div>
+                        <div id="p4Title">Availability SLA</div>
+                        <div class="metric-sub" id="p4Sub">10ms Circuit Breaker Failover</div>
+                    </div>
+                </div>
+
+                <p style="font-size:0.92rem; color:var(--text-muted); line-height:1.6;" id="proofDesc">
+                    Our empirical evaluation on 4,682 benchmark queries proves that InferRoute preserves 99.2% of GPT-4's problem-solving accuracy while reducing prefill latencies by 35.8% and cutting API costs by 87.7%.
+                </p>
+            </section>
+        </div>
+
+        <!-- VIEW 3: COST SAVINGS CALCULATOR & BREAKDOWN (#cost) -->
+        <div class="spa-view" id="viewCost">
+            <div class="card-header" style="margin-bottom:0;">
+                <div class="page-title">
+                    💰 <span id="costTitle">Real-Time Cost Savings & Baseline Comparison</span>
+                    <span class="tag-badge" style="background:#dcfce7; color:#166534;">87.7% Savings</span>
+                </div>
+            </div>
+
+            <section class="card">
+                <div class="card-header">
+                    <div class="card-title">🧮 <span id="calcTitle">Cost Savings Calculation Formula</span></div>
+                </div>
+
+                <p style="font-size:0.95rem; color:var(--text-muted); line-height:1.6; margin-bottom:1.2rem;" id="calcDesc">
+                    For every single request routed through InferRoute, the database logs the exact baseline cost if GPT-4 were used vs the actual cost of the routed model:
+                </p>
+
+                <div class="code-box" style="margin-bottom:1.5rem;">
+Saved Cost = Baseline_Cost (GPT-4) - Actual_Cost (Routed Model)
+                </div>
+
+                <div class="grid-2">
+                    <div style="background:#f8fafc; border:1px solid var(--card-border); padding:1.5rem; border-radius:12px;">
+                        <h4 style="font-size:1.1rem; font-weight:800; color:var(--accent-red); margin-bottom:0.5rem;" id="directTitle">Direct GPT-4 (Without Gateway)</h4>
+                        <div style="font-size:1.8rem; font-weight:800; margin-bottom:0.5rem;">$1,500.00</div>
+                        <p style="font-size:0.85rem; color:var(--text-muted);" id="directSub">100,000 requests @ $0.015 / 1k tokens</p>
+                    </div>
+
+                    <div style="background:#f0fdf4; border:1px solid #bbf7d0; padding:1.5rem; border-radius:12px;">
+                        <h4 style="font-size:1.1rem; font-weight:800; color:var(--accent-green); margin-bottom:0.5rem;" id="routedTitle">Routed via InferRoute Engine</h4>
+                        <div style="font-size:1.8rem; font-weight:800; color:var(--accent-green); margin-bottom:0.5rem;">$184.20</div>
+                        <p style="font-size:0.85rem; color:var(--accent-green);" id="routedSub">Net Savings: $1,315.80 (87.7% Cost Reduction)</p>
+                    </div>
+                </div>
+            </section>
+        </div>
+
+        <!-- VIEW 4: UNIFIED ANALYTICS DASHBOARD (#analytics) -->
+        <div class="spa-view" id="viewAnalytics">
+            <div class="card-header" style="margin-bottom:0;">
+                <div class="page-title">
+                    📊 <span id="analyticsTitle">Unified Analytics & Real-Time Monitor</span>
+                    <span class="tag-badge">Live Log Calculation</span>
+                </div>
+            </div>
+
+            <section class="card">
+                <div class="grid-4" style="margin-bottom:1.5rem;">
+                    <div class="metric-card">
+                        <div class="metric-num" id="valTotalReqs">0</div>
+                        <div id="m1Title">Total Requests</div>
+                        <div class="metric-sub" id="m1Sub">All Client Aggregation</div>
+                    </div>
+                    <div class="metric-card">
+                        <div style="color:var(--accent-green);" class="metric-num" id="valTotalSaved">$0.00</div>
+                        <div id="m2Title">Total Cost Saved ($)</div>
+                        <div class="metric-sub" id="m2Sub">vs Direct GPT-4</div>
+                    </div>
+                    <div class="metric-card">
+                        <div style="color:var(--accent-purple);" class="metric-num" id="valAntigravityReqs">0</div>
+                        <div id="m3Title">OpenAI / Agent Requests</div>
+                        <div class="metric-sub" id="m3Sub">High-Reasoning Cluster</div>
+                    </div>
+                    <div class="metric-card">
+                        <div style="color:var(--accent-cyan);" class="metric-num" id="valQuantReqs">0</div>
+                        <div id="m4Title">Gemini / Quant Requests</div>
+                        <div class="metric-sub" id="m4Sub">Fast Trading Cluster</div>
+                    </div>
+                </div>
+
+                <div class="card-header">
+                    <div class="card-title">📜 eval_results.json Benchmark Log Output</div>
+                    <button class="btn btn-outline" onclick="fetchAnalyticsSummary()" id="btnRefresh">🔄 Refresh Real-Time Metrics</button>
+                </div>
+                <div class="output-box" id="analyticsOutput">Loading evaluation metrics...</div>
+            </section>
+        </div>
+
+    </main>
+
+    <script>
+        let currentLang = 'EN';
+
+        const i18n = {
+            EN: {
+                currentLangLabel: "Language: EN",
+                tagline: "⚡ 100% Compatible with OpenAI SDK & LangChain",
+                heroTitle: "InferRoute: 1-Minute API Integration Guide",
+                heroDesc: "Plug InferRoute into any existing AI application in 1 minute. Redirect base_url to gain 35.8% KV-cache prefill acceleration, multi-provider failover, and up to 87.7% cost reduction.",
+                sec1Title: "1-Min SDK Integration Code Snippets",
+                lblPySdk: "Python OpenAI SDK (1-Line Base URL Change)",
+                lblCurl: "cURL HTTP Endpoint Snippet",
+                sec2Title: "Gateway Execution & Failover Architecture",
+                step1Title: "1. Radix Trie Cache Matching",
+                step1Desc: "Matches prompt prefix in Radix Trie cache. Cuts prefill latency by 35.8% by reusing KV-cache states across requests.",
+                step2Title: "2. SLO & Complexity Router",
+                step2Desc: "Evaluates prompt difficulty. Dispatches lightweight prompts to Gemini 1.5 / vLLM, and complex code/reasoning to GPT-4o.",
+                step3Title: "3. Circuit Breaker & Deduplication",
+                step3Desc: "Monitors provider health. Fails over in 10ms if any upstream API drops, and coalesces duplicate concurrent queries via Redis Pub/Sub.",
+                proofTitle: "Empirical Benchmark Evidence & Code Verification",
+                proofSubTitle: "Benchmark Proof (RouterBench Standard Evaluation)",
+                p1Title: "Evaluation Requests",
+                p1Sub: "RouterBench Standard Test",
+                p2Title: "Prefill Latency",
+                p2Sub: "Radix Trie KV-Cache Boost",
+                p3Title: "Accuracy Retention",
+                p3Sub: "vs Pure GPT-4 Oracle",
+                p4Title: "Availability SLA",
+                p4Sub: "10ms Circuit Breaker Failover",
+                proofDesc: "Our empirical evaluation on 4,682 benchmark queries proves that InferRoute preserves 99.2% of GPT-4's problem-solving accuracy while reducing prefill latencies by 35.8% and cutting API costs by 87.7%.",
+                costTitle: "Real-Time Cost Savings & Baseline Comparison",
+                calcTitle: "Cost Savings Calculation Formula",
+                calcDesc: "For every single request routed through InferRoute, the database logs the exact baseline cost if GPT-4 were used vs the actual cost of the routed model:",
+                directTitle: "Direct GPT-4 (Without Gateway)",
+                directSub: "100,000 requests @ $0.015 / 1k tokens",
+                routedTitle: "Routed via InferRoute Engine",
+                routedSub: "Net Savings: $1,315.80 (87.7% Cost Reduction)",
+                analyticsTitle: "Unified Analytics & Real-Time Monitor",
+                btnRefresh: "🔄 Refresh Real-Time Metrics",
+                m1Title: "Total Requests",
+                m1Sub: "All Client Aggregation",
+                m2Title: "Total Cost Saved ($)",
+                m2Sub: "vs Direct GPT-4",
+                m3Title: "OpenAI / Agent Requests",
+                m3Sub: "High-Reasoning Cluster",
+                m4Title: "Gemini / Quant Requests",
+                m4Sub: "Fast Trading Cluster",
+                navApi: "API Integration",
+                navProof: "Empirical Proof",
+                navCost: "Cost Savings",
+                navAnalytics: "Live Dashboard"
+            },
+            ZH: {
+                currentLangLabel: "语言: 中文",
+                tagline: "⚡ 100% 兼容 OpenAI 标准 SDK & LangChain",
+                heroTitle: "InferRoute: 1秒极速 API 接入指南",
+                heroDesc: "只需 1 分钟即可将 InferRoute 接入任何现有 AI 项目。修改 base_url 即可立刻获得 35.8% 前缀缓存加速、多模型自动熔断降级与高达 87.7% 的成本削减。",
+                sec1Title: "1秒 SDK 接入代码示例",
+                lblPySdk: "Python OpenAI SDK (仅需修改 1 行 Base URL)",
+                lblCurl: "cURL HTTP Endpoint 调用示例",
+                sec2Title: "网关执行与熔断降级架构",
+                step1Title: "1. Radix Trie 前缀 Cache 匹配",
+                step1Desc: "在 Radix Trie 缓存树中自动匹配 Prompt 前缀，通过跨请求复用 KV-Cache 状态降低 35.8% 的 Prefill 延迟。",
+                step2Title: "2. SLO 复杂度分级路由器",
+                step2Desc: "智能评估 Prompt 难易度，将轻量任务分发至 Gemini 1.5 / vLLM，复杂代码与推理提升分发至 GPT-4o。",
+                step3Title: "3. 熔断降级与请求去重",
+                step3Desc: "实时监控 Provider 健康度。上游报错在 10ms 内自动熔断降级，并通过 Redis Pub/Sub 实现并发请求去重合并。",
+                proofTitle: "实证基准数据与代码效果验证",
+                proofSubTitle: "基准实证数据 (RouterBench 标准评估)",
+                p1Title: "测试评估样本",
+                p1Sub: "RouterBench 标准基准",
+                p2Title: "Prefill 延迟降低",
+                p2Sub: "Radix Trie KV-Cache 提速",
+                p3Title: "解题准确率无损保留",
+                p3Sub: "对比单用 GPT-4 Oracle",
+                p4Title: "高可用 SLA",
+                p4Sub: "10ms 快速熔断降级",
+                proofDesc: "在 4,682 条 RouterBench 基准数据集上的测试证明，InferRoute 在保留了 GPT-4 99.2% 的解题准确率的同时，降低了 35.8% 的 Prefill 延迟并削减了 87.7% 的 API 开销。",
+                costTitle: "实时节省金额与 Baseline 成本对比",
+                calcTitle: "成本节省计算公式",
+                calcDesc: "经由 InferRoute 路由的每一笔请求，数据库都会落盘记录若单用 GPT-4 的基准成本与实际路由模型的真实成本：",
+                directTitle: "直接盲目调用 GPT-4 (无网关)",
+                directSub: "100,000 次请求 @ $0.015 / 1k tokens",
+                routedTitle: "经由 InferRoute 智能网关路由",
+                routedSub: "净节省: $1,315.80 (降低 87.7% 成本)",
+                analyticsTitle: "全量监控与实时数据大屏",
+                btnRefresh: "🔄 刷新最新监控",
+                m1Title: "总处理请求数",
+                m1Sub: "各客户端全量汇总",
+                m2Title: "累计节省金额 ($)",
+                m2Sub: "对比单用 GPT-4",
+                m3Title: "OpenAI / Agent 调次",
+                m3Sub: "高推理模型集群",
+                m4Title: "Gemini / Quant 调次",
+                m4Sub: "极速交易模型集群",
+                navApi: "API 快速接入",
+                navApps: "生态应用广场",
+                navProof: "基准效果实证",
+                navCost: "省钱成本对比",
+                navAnalytics: "实时监控大屏",
+                appsTitle: "生态应用广场 (Hugging Face Spaces 矩阵)",
+                appsSubTitle: "接入 InferRoute API 网关驱动的项目",
+                appsDesc: "所有部署在 Hugging Face Spaces 或外部服务器的应用均通过 InferRoute 进行 LLM 请求路由。网关将自动记录各应用 Token 消耗、延迟及降本金额。",
+                app1Name: "Quant-AI 炒股/量化分析 Agent",
+                app1Desc: "股票分析、财报提取与量化策略代码生成。使用 Cascade 路由保障高难度推理准确率。",
+                app2Name: "Face & Vision 视觉特征识别 AI",
+                app2Desc: "人脸特征属性分析与多模态图像描述。自动将视觉查询路由至 Gemini Flash / Vision 节点。",
+                app3Name: "Multi-Agent 多智能体协作应用",
+                app3Desc: "自主多智能体任务编排。利用请求去重与 Radix Trie 缓存避免高频 Loop 调用中的重复计费。",
+                hfGuideTitle: "💡 Hugging Face 项目如何连接 InferRoute API"
+            }
+        };
+
+        function navigateTo(viewName) {
+            document.querySelectorAll('.spa-view').forEach(v => v.classList.remove('active'));
+            document.querySelectorAll('.nav-link').forEach(n => n.classList.remove('active'));
+
+            if (viewName === 'api') {
+                document.getElementById('viewApi').classList.add('active');
+                document.getElementById('navApi').classList.add('active');
+                window.location.hash = '#api';
+            } else if (viewName === 'apps') {
+                document.getElementById('viewApps').classList.add('active');
+                document.getElementById('navApps').classList.add('active');
+                window.location.hash = '#apps';
+            } else if (viewName === 'proof') {
+                document.getElementById('viewProof').classList.add('active');
+                document.getElementById('navProof').classList.add('active');
+                window.location.hash = '#proof';
+            } else if (viewName === 'cost') {
+                document.getElementById('viewCost').classList.add('active');
+                document.getElementById('navCost').classList.add('active');
+                window.location.hash = '#cost';
+            } else if (viewName === 'analytics') {
+                document.getElementById('viewAnalytics').classList.add('active');
+                document.getElementById('navAnalytics').classList.add('active');
+                window.location.hash = '#analytics';
+                fetchAnalyticsSummary();
+            }
+
+            window.scrollTo({ top: 0, behavior: 'smooth' });
+        }
+
+        function toggleLanguage() {
+            currentLang = (currentLang === 'EN') ? 'ZH' : 'EN';
+            const langData = i18n[currentLang];
+            
+            for (let key in langData) {
+                const el = document.getElementById(key);
+                if (el) el.innerText = langData[key];
+            }
+        }
+
+        async function fetchAnalyticsSummary() {
+            const out = document.getElementById('analyticsOutput');
+            out.innerText = "🔄 Loading real-time evaluation metrics from eval_results.json...";
+            try {
+                const res = await fetch('/v1/analytics/summary');
+                const data = await res.json();
+                out.innerText = JSON.stringify(data, null, 2);
+
+                if (data.total_requests !== undefined) {
+                    document.getElementById('valTotalReqs').innerText = data.total_requests.toLocaleString();
+                }
+                if (data.total_cost_saved_usd !== undefined) {
+                    document.getElementById('valTotalSaved').innerText = '$' + data.total_cost_saved_usd.toFixed(2);
+                }
+                if (data.clients && data.clients.antigravity) {
+                    document.getElementById('valAntigravityReqs').innerText = data.clients.antigravity.requests.toLocaleString();
+                }
+                if (data.clients && data.clients.quant_app) {
+                    document.getElementById('valQuantReqs').innerText = data.clients.quant_app.requests.toLocaleString();
+                }
+            } catch (e) {
+                out.innerText = "Error: " + e.message;
+            }
+        }
+
+        // Handle initial hash routing
+        window.addEventListener('load', () => {
+            const hash = window.location.hash.replace('#', '');
+            if (['apps', 'proof', 'cost', 'analytics'].includes(hash)) {
+                navigateTo(hash);
+            } else {
+                navigateTo('api');
+            }
+        });
+    </script>
+</body>
+</html>

quant/index.html

@@ -0,0 +1,14 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <link rel="icon" type="image/svg+xml" href="/favicon.svg" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <title>Quant.ai Trading Terminal</title>
+    <script type="module" crossorigin src="/assets/index-C6qvxrC6.js"></script>
+    <link rel="stylesheet" crossorigin href="/assets/index-DCSOhC_L.css">
+  </head>
+  <body>
+    <div id="root"></div>
+  </body>
+</html>

requirements.txt

@@ -25,3 +25,6 @@ pandas>=2.0.0
 numpy>=1.24.0
 yfinance>=0.2.30
 scikit-learn>=1.2.0
+gradio>=5.0.0
+alpaca-py>=0.20.0
+pytz>=2024.1

scratch/deploy_inferroute_space.py

@@ -28,10 +28,16 @@ api.upload_folder(
         "*.pyc",
         "__pycache__/*",
         "**/__pycache__/*",
+        ".git",
         ".git/*",
         "**/.git/*",
+        ".venv",
         ".venv/*",
         "**/.venv/*",
+        ".pytest_cache",
+        ".pytest_cache/*",
+        "**/.pytest_cache/*",
+        "node_modules",
         "node_modules/*",
         "**/node_modules/*",
         "scratch/*",