refactor(arch): modular package structure — split monolithic app.py into config/db/auth/memory/search/rag/gpu + routers/

- config.py: all constants, env vars, limits, skill registry, profiles
- db.py: schema init, connection factory, skill state helpers
- security.py: PIN hashing, audit logging, rate limiting, CSRF, request helpers
- auth.py: session management, PIN verify, auth routes
- memory.py: FTS5 CRUD + remember/forget command processing
- search.py: SearXNG integration, perplexity scoring, refusal/hedge detection
- gpu.py: rocm-smi stats
- rag.py: Qdrant vector search + system prompt assembly
- routers/: conversations, memories, models, presets, profile, settings, skills, chat, search
- app.py: slim entry point, middleware, router registration only

Bumps to v1.9.0

routers/models.py

@@ -0,0 +1,78 @@
+"""
+JarvisChat routers - Model listing, system stats.
+"""
+import logging
+from typing import Optional
+
+import httpx
+import psutil
+from fastapi import APIRouter, HTTPException, Request
+
+from config import OLLAMA_BASE
+from gpu import get_gpu_stats
+from security import read_json_body, BODY_LIMIT_DEFAULT_BYTES
+
+log = logging.getLogger("jarvischat")
+router = APIRouter()
+
+
+@router.get("/api/models")
+async def list_models():
+    async with httpx.AsyncClient() as client:
+        try:
+            resp = await client.get(f"{OLLAMA_BASE}/v1/models", timeout=10)
+            data = resp.json()
+            models = [{"name": m["id"], "model": m["id"]} for m in data.get("data", [])]
+            return {"models": models}
+        except httpx.ConnectError:
+            raise HTTPException(status_code=502, detail="Cannot connect to llama-server.")
+
+
+@router.get("/api/ps")
+async def running_models():
+    async with httpx.AsyncClient() as client:
+        try:
+            resp = await client.get(f"{OLLAMA_BASE}/api/ps", timeout=10)
+            return resp.json()
+        except httpx.ConnectError:
+            raise HTTPException(status_code=502, detail="Cannot connect to Ollama.")
+
+
+@router.post("/api/show")
+async def show_model(request: Request):
+    from security import BODY_LIMIT_DEFAULT_BYTES
+    body = await read_json_body(request, BODY_LIMIT_DEFAULT_BYTES)
+    async with httpx.AsyncClient() as client:
+        try:
+            resp = await client.post(f"{OLLAMA_BASE}/api/show", json=body, timeout=10)
+            return resp.json()
+        except httpx.ConnectError:
+            raise HTTPException(status_code=502, detail="Cannot connect to Ollama.")
+
+
+@router.get("/api/stats")
+async def system_stats():
+    cpu_percent = psutil.cpu_percent(interval=0.1)
+    memory = psutil.virtual_memory()
+    gpu = get_gpu_stats()
+    return {
+        "cpu_percent": round(cpu_percent, 1),
+        "memory_percent": round(memory.percent, 1),
+        "memory_used_gb": round(memory.used / (1024**3), 1),
+        "memory_total_gb": round(memory.total / (1024**3), 1),
+        "gpu_percent": gpu["gpu_percent"],
+        "vram_percent": gpu["vram_percent"],
+        "gpu_available": gpu["available"],
+    }
+
+
+@router.get("/api/search/status")
+async def search_status():
+    from config import SEARXNG_BASE
+    async with httpx.AsyncClient() as client:
+        try:
+            resp = await client.get(f"{SEARXNG_BASE}/search",
+                                    params={"q": "test", "format": "json"}, timeout=5)
+            return {"available": resp.status_code == 200}
+        except Exception:
+            return {"available": False}