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>

.env.example

@@ -1,11 +1,16 @@
-# Local backend (Ollama) — used by default for most calls.
+# Local backend (Ollama) — free, private. Point this at your home-lab Ollama.
 LOCAL_BASE_URL=http://localhost:11434
 LOCAL_MODEL=qwen2.5:7b-instruct
 
-# Cloud backend (OpenAI) — used for harder reasoning and embeddings.
+# Cloud backend (OpenAI) — higher quality, costs money.
 OPENAI_API_KEY=
 CLOUD_MODEL=gpt-4o-mini
+
+# Embeddings: "cloud" (OpenAI) or "local" (Ollama). A database is tied to whichever
+# backend created it — don't switch this against an existing DB (vector spaces differ).
+EMBED_BACKEND=cloud
 EMBED_MODEL=text-embedding-3-small
+LOCAL_EMBED_MODEL=nomic-embed-text
 
 # Where Lyra stores her memory.
 LYRA_DB_PATH=data/lyra.db