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>

synapse/playbooks/store.py

@@ -22,6 +22,8 @@ class PlaybookItem(BaseModel):
     goal: str
     instructions: str
     tags: List[str] = []
+    tools: List[str] = []
+    model: str = ""
     order: int = 0
 
 
@@ -43,6 +45,8 @@ class PlaybookFileStore:
                 goal=data.get("goal", ""),
                 instructions=data.get("instructions", ""),
                 tags=data.get("tags", []),
+                tools=data.get("tools", []),
+                model=data.get("model", ""),
                 order=data.get("order", 0),
             )
         except Exception:
@@ -58,6 +62,8 @@ class PlaybookFileStore:
             "title": item.title,
             "goal": item.goal,
             "tags": item.tags,
+            "tools": item.tools,
+            "model": item.model,
             "order": item.order,
             "instructions": self._clean(item.instructions),
         }