Add character detail, markdown rendering, wider layout, and LLM provider switch

- Character sheets gain structured combat_stats, abilities (name +
  plain-language explanation), and equipment fields, populated by the
  upsert_character_sheet tool; the detail page renders them as their
  own sections instead of one prose block, with a player-card-style
  attribute grid (full ability names + modifiers).
- Fix double-escaped unicode occasionally left in tool-call JSON
  arguments (a model quirk) and stop the app's own json.dumps calls
  from re-introducing it (ensure_ascii=False).
- Render chat messages as markdown (react-markdown + Tailwind
  typography) instead of raw text, and widen the games/characters/
  chat layout to use more of the screen on desktop.
- Sharpen the DM system prompt: state the ability + DC for each
  offered action option before the player commits, and narrate rolls
  as DC → result → pass/fail before the story consequence; also stop
  re-asking Session-0 questions already answered in the game's
  name/description.
- Make the DM's LLM provider configurable (xai default, lmstudio for
  a local OpenAI-compatible server via host.docker.internal) instead
  of hardcoded to x.ai.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

.env.example

@@ -1,7 +1,19 @@
 # Copy this file to .env and fill in real values. Never commit .env.
 
-# x.ai API (Grok) — DM model. Get a key at https://console.x.ai
+# DM model provider: "xai" (default, cloud) or "lmstudio" (local, free, no API cost)
+LLM_PROVIDER=xai
+
+# x.ai API (Grok) — used when LLM_PROVIDER=xai. Get a key at https://console.x.ai
 XAI_API_KEY=
+DM_MODEL=grok-4.6
+
+# LM Studio local server — used when LLM_PROVIDER=lmstudio. Use host.docker.internal, not a
+# LAN IP — the backend runs inside Docker and can't necessarily reach the host's LAN address
+# (e.g. a WSL2-internal IP the host itself sees but containers can't route to).
+LMSTUDIO_BASE_URL=http://host.docker.internal:1234/v1
+LMSTUDIO_API_KEY=
+# When LLM_PROVIDER=lmstudio, also set DM_MODEL above to the model id LM Studio reports at
+# GET /v1/models, e.g. DM_MODEL=qwen2.5-14b-instruct
 
 # Auth secrets — generate with: python -c "import secrets; print(secrets.token_urlsafe(32))"
 JWT_SECRET=