feat(docker): implement smart browser pool with 10x memory efficiency

Major refactoring to eliminate memory leaks and enable high-scale crawling:

- **Smart 3-Tier Browser Pool**:
  - Permanent browser (always-ready default config)
  - Hot pool (configs used 3+ times, longer TTL)
  - Cold pool (new/rare configs, short TTL)
  - Auto-promotion: cold → hot after 3 uses
  - 100% pool reuse achieved in tests

- **Container-Aware Memory Detection**:
  - Read cgroup v1/v2 memory limits (not host metrics)
  - Accurate memory pressure detection in Docker
  - Memory-based browser creation blocking

- **Adaptive Janitor**:
  - Dynamic cleanup intervals (10s/30s/60s based on memory)
  - Tiered TTLs: cold 30-300s, hot 120-600s
  - Aggressive cleanup at high memory pressure

- **Unified Pool Usage**:
  - All endpoints now use pool (/html, /screenshot, /pdf, /execute_js, /md, /llm)
  - Fixed config signature mismatch (permanent browser matches endpoints)
  - get_default_browser_config() helper for consistency

- **Configuration**:
  - Reduced idle_ttl: 1800s → 300s (30min → 5min)
  - Fixed port: 11234 → 11235 (match Gunicorn)

**Performance Results** (from stress tests):
- Memory: 10x reduction (500-700MB × N → 270MB permanent)
- Latency: 30-50x faster (<100ms pool hits vs 3-5s startup)
- Reuse: 100% for default config, 60%+ for variants
- Capacity: 100+ concurrent requests (vs ~20 before)
- Leak: 0 MB/cycle (stable across tests)

**Test Infrastructure**:
- 7-phase sequential test suite (tests/)
- Docker stats integration + log analysis
- Pool promotion verification
- Memory leak detection
- Full endpoint coverage

Fixes memory issues reported in production deployments.

deploy/docker/crawler_pool.py

@@ -1,60 +1,146 @@
-# crawler_pool.py  (new file)
-import asyncio, json, hashlib, time, psutil
+# crawler_pool.py - Smart browser pool with tiered management
+import asyncio, json, hashlib, time
 from contextlib import suppress
-from typing import Dict
+from typing import Dict, Optional
 from crawl4ai import AsyncWebCrawler, BrowserConfig
-from typing import Dict
-from utils import load_config 
+from utils import load_config, get_container_memory_percent
+import logging
 
+logger = logging.getLogger(__name__)
 CONFIG = load_config()
 
-POOL: Dict[str, AsyncWebCrawler] = {}
+# Pool tiers
+PERMANENT: Optional[AsyncWebCrawler] = None  # Always-ready default browser
+HOT_POOL: Dict[str, AsyncWebCrawler] = {}    # Frequent configs
+COLD_POOL: Dict[str, AsyncWebCrawler] = {}   # Rare configs
 LAST_USED: Dict[str, float] = {}
+USAGE_COUNT: Dict[str, int] = {}
 LOCK = asyncio.Lock()
 
-MEM_LIMIT  = CONFIG.get("crawler", {}).get("memory_threshold_percent", 95.0)   # % RAM – refuse new browsers above this
-IDLE_TTL  = CONFIG.get("crawler", {}).get("pool", {}).get("idle_ttl_sec", 1800)   # close if unused for 30 min
+# Config
+MEM_LIMIT = CONFIG.get("crawler", {}).get("memory_threshold_percent", 95.0)
+BASE_IDLE_TTL = CONFIG.get("crawler", {}).get("pool", {}).get("idle_ttl_sec", 300)
+DEFAULT_CONFIG_SIG = None  # Cached sig for default config
 
 def _sig(cfg: BrowserConfig) -> str:
+    """Generate config signature."""
     payload = json.dumps(cfg.to_dict(), sort_keys=True, separators=(",",":"))
     return hashlib.sha1(payload.encode()).hexdigest()
 
+def _is_default_config(sig: str) -> bool:
+    """Check if config matches default."""
+    return sig == DEFAULT_CONFIG_SIG
+
 async def get_crawler(cfg: BrowserConfig) -> AsyncWebCrawler:
-    try:
-        sig = _sig(cfg)
-        async with LOCK:
-            if sig in POOL:
-                LAST_USED[sig] = time.time();  
-                return POOL[sig]
-            if psutil.virtual_memory().percent >= MEM_LIMIT:
-                raise MemoryError("RAM pressure – new browser denied")
-            crawler = AsyncWebCrawler(config=cfg, thread_safe=False)
-            await crawler.start()
-            POOL[sig] = crawler; LAST_USED[sig] = time.time()
-            return crawler
-    except MemoryError as e:
-        raise MemoryError(f"RAM pressure – new browser denied: {e}")
-    except Exception as e:
-        raise RuntimeError(f"Failed to start browser: {e}")
-    finally:
-        if sig in POOL:
-            LAST_USED[sig] = time.time()
-        else:
-            # If we failed to start the browser, we should remove it from the pool
-            POOL.pop(sig, None)
-            LAST_USED.pop(sig, None)
-        # If we failed to start the browser, we should remove it from the pool
-async def close_all():
+    """Get crawler from pool with tiered strategy."""
+    sig = _sig(cfg)
     async with LOCK:
-        await asyncio.gather(*(c.close() for c in POOL.values()), return_exceptions=True)
-        POOL.clear(); LAST_USED.clear()
+        # Check permanent browser for default config
+        if PERMANENT and _is_default_config(sig):
+            LAST_USED[sig] = time.time()
+            USAGE_COUNT[sig] = USAGE_COUNT.get(sig, 0) + 1
+            logger.info("🔥 Using permanent browser")
+            return PERMANENT
+
+        # Check hot pool
+        if sig in HOT_POOL:
+            LAST_USED[sig] = time.time()
+            USAGE_COUNT[sig] = USAGE_COUNT.get(sig, 0) + 1
+            logger.info(f"♨️  Using hot pool browser (sig={sig[:8]})")
+            return HOT_POOL[sig]
+
+        # Check cold pool (promote to hot if used 3+ times)
+        if sig in COLD_POOL:
+            LAST_USED[sig] = time.time()
+            USAGE_COUNT[sig] = USAGE_COUNT.get(sig, 0) + 1
+
+            if USAGE_COUNT[sig] >= 3:
+                logger.info(f"⬆️  Promoting to hot pool (sig={sig[:8]}, count={USAGE_COUNT[sig]})")
+                HOT_POOL[sig] = COLD_POOL.pop(sig)
+                return HOT_POOL[sig]
+
+            logger.info(f"❄️  Using cold pool browser (sig={sig[:8]})")
+            return COLD_POOL[sig]
+
+        # Memory check before creating new
+        mem_pct = get_container_memory_percent()
+        if mem_pct >= MEM_LIMIT:
+            logger.error(f"💥 Memory pressure: {mem_pct:.1f}% >= {MEM_LIMIT}%")
+            raise MemoryError(f"Memory at {mem_pct:.1f}%, refusing new browser")
+
+        # Create new in cold pool
+        logger.info(f"🆕 Creating new browser in cold pool (sig={sig[:8]}, mem={mem_pct:.1f}%)")
+        crawler = AsyncWebCrawler(config=cfg, thread_safe=False)
+        await crawler.start()
+        COLD_POOL[sig] = crawler
+        LAST_USED[sig] = time.time()
+        USAGE_COUNT[sig] = 1
+        return crawler
+
+async def init_permanent(cfg: BrowserConfig):
+    """Initialize permanent default browser."""
+    global PERMANENT, DEFAULT_CONFIG_SIG
+    async with LOCK:
+        if PERMANENT:
+            return
+        DEFAULT_CONFIG_SIG = _sig(cfg)
+        logger.info("🔥 Creating permanent default browser")
+        PERMANENT = AsyncWebCrawler(config=cfg, thread_safe=False)
+        await PERMANENT.start()
+        LAST_USED[DEFAULT_CONFIG_SIG] = time.time()
+        USAGE_COUNT[DEFAULT_CONFIG_SIG] = 0
+
+async def close_all():
+    """Close all browsers."""
+    async with LOCK:
+        tasks = []
+        if PERMANENT:
+            tasks.append(PERMANENT.close())
+        tasks.extend([c.close() for c in HOT_POOL.values()])
+        tasks.extend([c.close() for c in COLD_POOL.values()])
+        await asyncio.gather(*tasks, return_exceptions=True)
+        HOT_POOL.clear()
+        COLD_POOL.clear()
+        LAST_USED.clear()
+        USAGE_COUNT.clear()
 
 async def janitor():
+    """Adaptive cleanup based on memory pressure."""
     while True:
-        await asyncio.sleep(60)
+        mem_pct = get_container_memory_percent()
+
+        # Adaptive intervals and TTLs
+        if mem_pct > 80:
+            interval, cold_ttl, hot_ttl = 10, 30, 120
+        elif mem_pct > 60:
+            interval, cold_ttl, hot_ttl = 30, 60, 300
+        else:
+            interval, cold_ttl, hot_ttl = 60, BASE_IDLE_TTL, BASE_IDLE_TTL * 2
+
+        await asyncio.sleep(interval)
+
         now = time.time()
         async with LOCK:
-            for sig, crawler in list(POOL.items()):
-                if now - LAST_USED[sig] > IDLE_TTL:
-                    with suppress(Exception): await crawler.close()
-                    POOL.pop(sig, None); LAST_USED.pop(sig, None)
+            # Clean cold pool
+            for sig in list(COLD_POOL.keys()):
+                if now - LAST_USED.get(sig, now) > cold_ttl:
+                    logger.info(f"🧹 Closing cold browser (sig={sig[:8]}, idle={now - LAST_USED[sig]:.0f}s)")
+                    with suppress(Exception):
+                        await COLD_POOL[sig].close()
+                    COLD_POOL.pop(sig, None)
+                    LAST_USED.pop(sig, None)
+                    USAGE_COUNT.pop(sig, None)
+
+            # Clean hot pool (more conservative)
+            for sig in list(HOT_POOL.keys()):
+                if now - LAST_USED.get(sig, now) > hot_ttl:
+                    logger.info(f"🧹 Closing hot browser (sig={sig[:8]}, idle={now - LAST_USED[sig]:.0f}s)")
+                    with suppress(Exception):
+                        await HOT_POOL[sig].close()
+                    HOT_POOL.pop(sig, None)
+                    LAST_USED.pop(sig, None)
+                    USAGE_COUNT.pop(sig, None)
+
+            # Log pool stats
+            if mem_pct > 60:
+                logger.info(f"📊 Pool: hot={len(HOT_POOL)}, cold={len(COLD_POOL)}, mem={mem_pct:.1f}%")