Add MCP control server, live API-generation view, and repetition penalty

- scripts/jwash_mcp.py: MCP server (FastMCP/stdio), an HTTP client of the running
  J-Wash server so an external LLM can drive an already-loaded model. Tools:
  generate, find_token, list_layers, scale_token/replace_token (pure-weights,
  layers required), set_intensity, list_edits/reset_edits.
- api/app.py + ui: /api/generate now records the last exchange (surfaced in
  /api/status) and broadcasts on /ws when done; the UI shows a "generated via
  API/MCP" panel at the top of the chat and an Options "API monitor" toggle that
  swaps the 2s status poll for an event-driven refresh.
- sampling: repetition penalty (default 1.0, applied in model_manager._sample),
  exposed as a "rep" field in the chat controls; intentionally not exposed
  through the MCP.
- ui: remove the redundant "md" chat toggle (already available in Options).

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

config.py

@@ -30,6 +30,7 @@ DEFAULT_SAMPLING = {
     "top_k": 40,
     "max_tokens": 512,
     "seed": -1,  # -1 = random
+    "repetition_penalty": 1.0,  # 1.0 = off
 }