feat: persona chat loop, web UI, and local (Ollama) embeddings

Phase 1 — persona + persistent memory chat loop:
- lyra/persona.py + personas/lyra.md: editable identity/voice (friend-first,
  honest, never invents poker math)
- lyra/chat.py: turn loop assembling persona + cross-session recall + recent
  context, persisting both sides to SQLite
- lyra/session.py, lyra/__main__.py: session lifecycle + `lyra` REPL

Phase 1.25 — reuse the old web UI:
- vendored the prior single-page UI into lyra/web/static, repointed to
  same-origin
- lyra/web/server.py (FastAPI): serves the UI and backs its endpoint contract
  (/v1/chat/completions, session CRUD, health, inert thinking-stream) with the
  new chat loop + memory; SQLite stays the single source of truth
- `lyra-web` console script

Local backends — test for free, no OpenAI key:
- llm.embed routes via EMBED_BACKEND (cloud=OpenAI, local=Ollama /api/embed)
- simplified UI backend selector to Local (Ollama) / Cloud (OpenAI), default local
- memory connection opened check_same_thread=False for the threaded server

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

lyra/persona.py

@@ -0,0 +1,20 @@
+"""Persona: Lyra's identity and voice, loaded from an editable markdown prompt.
+
+The prompt lives in `personas/<name>.md` so it can be tuned without touching
+code. `LYRA_PERSONA` selects which file to load (default: "lyra").
+"""
+from __future__ import annotations
+
+import os
+from functools import lru_cache
+from pathlib import Path
+
+_PERSONA_DIR = Path(__file__).parent / "personas"
+
+
+@lru_cache(maxsize=None)
+def system_prompt(name: str | None = None) -> str:
+    """Return the persona system prompt. Cached; pass a name to override env."""
+    name = name or os.getenv("LYRA_PERSONA", "lyra")
+    path = _PERSONA_DIR / f"{name}.md"
+    return path.read_text(encoding="utf-8").strip()