feat: LLM router with local (Ollama) and cloud (OpenAI) backends

- lyra.config.load() reads env into a frozen Config dataclass
- lyra.llm.complete(messages, backend) routes to Ollama /api/chat or
  OpenAI chat completions
- lyra.llm.embed(texts) calls OpenAI embeddings
- .env.example switched from Anthropic to OpenAI to match available key

lyra/config.py

@@ -0,0 +1,31 @@
+"""Environment-driven configuration."""
+from __future__ import annotations
+
+import os
+from dataclasses import dataclass
+from pathlib import Path
+
+from dotenv import load_dotenv
+
+load_dotenv()
+
+
+@dataclass(frozen=True)
+class Config:
+    local_base_url: str
+    local_model: str
+    openai_api_key: str
+    cloud_model: str
+    embed_model: str
+    db_path: Path
+
+
+def load() -> Config:
+    return Config(
+        local_base_url=os.getenv("LOCAL_BASE_URL", "http://localhost:11434"),
+        local_model=os.getenv("LOCAL_MODEL", "qwen2.5:7b-instruct"),
+        openai_api_key=os.getenv("OPENAI_API_KEY", ""),
+        cloud_model=os.getenv("CLOUD_MODEL", "gpt-4o-mini"),
+        embed_model=os.getenv("EMBED_MODEL", "text-embedding-3-small"),
+        db_path=Path(os.getenv("LYRA_DB_PATH", "data/lyra.db")),
+    )

lyra/llm.py

@@ -0,0 +1,44 @@
+"""LLM router: local (Ollama) chat, cloud (OpenAI) chat + embeddings."""
+from __future__ import annotations
+
+from typing import Literal, TypedDict
+
+import httpx
+from openai import OpenAI
+
+from lyra.config import load
+
+
+class Message(TypedDict):
+    role: Literal["system", "user", "assistant"]
+    content: str
+
+
+Backend = Literal["local", "cloud"]
+
+
+def complete(messages: list[Message], backend: Backend = "local") -> str:
+    cfg = load()
+    if backend == "cloud":
+        if not cfg.openai_api_key:
+            raise RuntimeError("OPENAI_API_KEY is not set")
+        client = OpenAI(api_key=cfg.openai_api_key)
+        resp = client.chat.completions.create(model=cfg.cloud_model, messages=messages)
+        return resp.choices[0].message.content or ""
+
+    resp = httpx.post(
+        f"{cfg.local_base_url}/api/chat",
+        json={"model": cfg.local_model, "messages": messages, "stream": False},
+        timeout=120,
+    )
+    resp.raise_for_status()
+    return resp.json()["message"]["content"]
+
+
+def embed(texts: list[str]) -> list[list[float]]:
+    cfg = load()
+    if not cfg.openai_api_key:
+        raise RuntimeError("OPENAI_API_KEY is not set")
+    client = OpenAI(api_key=cfg.openai_api_key)
+    resp = client.embeddings.create(model=cfg.embed_model, input=texts)
+    return [d.embedding for d in resp.data]