feat: playbook tools, RAG, vision, voice, chat controls, faster boot

- Tool-using playbooks: read-only tool registry (search_memory,
  search_history, search_documents, list_models, get_time), per-playbook
  allowlist, agentic loop, and a "running tool" status indicator.
- Document ingest / RAG: documents table + chunker + embed/cosine retrieval
  reusing the existing stack; Documents page (upload/paste, viewer, delete);
  top-k chunks injected into the system prompt.
- Vision chat: attach images, base64 into /api/chat.
- Voice I/O: Web Speech dictation + read-aloud (browser-native, no backend).
- Chat controls: stop, regenerate, edit-and-resend; num_ctx knob in Settings.
- Per-playbook model override.
- History polish: per-conversation + bulk ShareGPT export.
- Faster ncp start: UI up first, Ollama warms in the background, with a
  per-phase timing readout.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

management/ncp.py

@@ -301,20 +301,23 @@ def stop_service(svc: Service) -> bool:
 
 # -- ollama --------------------------------------------------------------------
 
-def start_ollama() -> None:
+def start_ollama(background: bool = False) -> None:
     """Driven through the backend endpoint (the path the control panel uses)
     rather than launching the binary, because OllamaManager owns model and GPU
     selection. Requires the backend to be up.
 
-    Long timeout: the endpoint blocks until the model is warmed - weights read
-    off disk into RAM/VRAM - which the web UI's own "Loading model..." button
-    state calls out as routinely taking about a minute, not just the Ollama
-    process launching."""
+    background=True (`ncp start`): the endpoint returns as soon as `ollama serve`
+    is up and warms the model in a background task, so boot finishes in seconds
+    and the model loads concurrently into the first chat.
+    background=False (`ncp start --ai`): blocks until the model is warmed - weights
+    read off disk into RAM/VRAM, routinely about a minute - so "started" means the
+    AI can actually answer."""
     print("Starting OLLAMA...")
-    req = urllib.request.Request("http://localhost:8000/ollama/start", method="POST")
+    url = "http://localhost:8000/ollama/start" + ("?background=true" if background else "")
+    req = urllib.request.Request(url, method="POST")
     try:
         urllib.request.urlopen(req, timeout=180).read(1)
-        print("NEXUS OLLAMA STARTED")
+        print("NEXUS OLLAMA WARMING (background)" if background else "NEXUS OLLAMA STARTED")
     except Exception as e:
         print(f"  OLLAMA start failed: {e}")
 
@@ -350,14 +353,24 @@ def cmd_start(target) -> None:
     elif target in ("--ai", "-a"):
         start_ollama()
     elif target in (None, "", "all"):
-        # Memory + backend in parallel, both ready before the frontend starts.
+        # Bring the UI up first, then warm Ollama in the background — the model
+        # loads concurrently and into the first chat instead of blocking boot.
+        t0 = time.perf_counter()
         launch(SERVICES["memory"])
         launch(SERVICES["backend"])
         wait_for_port(SERVICES["memory"])
         wait_for_port(SERVICES["backend"])
-        start_ollama()
+        t_services = time.perf_counter()
         launch(SERVICES["frontend"])
         wait_for_port(SERVICES["frontend"])
+        t_frontend = time.perf_counter()
+        start_ollama(background=True)
+        t_ollama = time.perf_counter()
+        print("\nBoot timing:")
+        print(f"  services (memory+backend) : {t_services - t0:5.1f}s")
+        print(f"  frontend (UI ready)       : {t_frontend - t_services:5.1f}s")
+        print(f"  ollama kickoff (bg warm)  : {t_ollama - t_frontend:5.1f}s")
+        print(f"  total to interactive      : {t_ollama - t0:5.1f}s")
     else:
         show_help()