feat: decouple embeddings from the local-chat backend (EMBED_BASE_URL)

Embeddings shared LOCAL_BASE_URL with the local chat backend (the 3090's Ollama),
so the 3090 being powered off killed all chat (every turn embeds to recall + to
store). Add a separate EMBED_BASE_URL (defaults to LOCAL_BASE_URL, so existing
setups are unchanged) and use it in llm.embed.

Deployed: a user-level Ollama (CPU) now runs nomic-embed-text on lyra-cortex
itself; EMBED_BASE_URL points at 127.0.0.1:11434 while LOCAL_BASE_URL still points
the local chat backend at the 3090. Local embeddings verified identical to the
3090's (cosine 0.999994, 768-dim) so existing vectors stay valid — no re-embed.

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

.env.example

@@ -22,3 +22,7 @@ SUMMARY_BACKEND=local
 
 # Where Lyra stores her memory.
 LYRA_DB_PATH=data/lyra.db
+
+# Optional: run embeddings on a separate always-on Ollama (decoupled from
+# LOCAL_BASE_URL, which serves local chat). Defaults to LOCAL_BASE_URL if unset.
+# EMBED_BASE_URL=http://127.0.0.1:11434

lyra/config.py

@@ -22,6 +22,7 @@ class Config:
     embed_backend: str  # "cloud" (OpenAI) or "local" (Ollama)
     embed_model: str  # OpenAI embedding model
     local_embed_model: str  # Ollama embedding model
+    embed_base_url: str  # Ollama endpoint for embeddings (own box, decoupled from local chat)
     summary_backend: str  # "local" or "cloud" — backend used to compact memory
     db_path: Path
 
@@ -38,6 +39,9 @@ def load() -> Config:
         embed_backend=os.getenv("EMBED_BACKEND", "cloud").lower(),
         embed_model=os.getenv("EMBED_MODEL", "text-embedding-3-small"),
         local_embed_model=os.getenv("LOCAL_EMBED_MODEL", "nomic-embed-text"),
+        # Embeddings can live on their own always-on box, separate from the local
+        # chat backend. Defaults to LOCAL_BASE_URL so existing setups are unchanged.
+        embed_base_url=os.getenv("EMBED_BASE_URL", os.getenv("LOCAL_BASE_URL", "http://localhost:11434")),
         summary_backend=os.getenv("SUMMARY_BACKEND", "local").lower(),
         db_path=Path(os.getenv("LYRA_DB_PATH", "data/lyra.db")),
     )

lyra/llm.py

@@ -173,7 +173,7 @@ def embed(texts: list[str]) -> list[list[float]]:
     cfg = load()
     if cfg.embed_backend == "local":
         resp = httpx.post(
-            f"{cfg.local_base_url}/api/embed",
+            f"{cfg.embed_base_url}/api/embed",
             json={"model": cfg.local_embed_model, "input": texts},
             timeout=120,
         )