step B.2 complete: all 23 tools use execute_on_client(); add embed() to llm

app/core/llm.py

@@ -17,6 +17,8 @@ Switch providers by changing **LLM_MODEL** / **LLM_ROUTER_MODEL** in ``.env``
 
 from __future__ import annotations
 
+from openai import AsyncOpenAI
+
 from langchain_openai import ChatOpenAI
 from litellm import get_supported_openai_params  # noqa: F401 – validates install
 
@@ -66,3 +68,13 @@ def get_router_llm(
 ) -> ChatOpenAI:
     """Return the lighter model used for intent classification / routing."""
     return get_llm(model=settings.LLM_ROUTER_MODEL, temperature=temperature)
+
+
+async def embed(text: str) -> list[float]:
+    """Return a 1536-dim embedding vector for *text* using text-embedding-3-small."""
+    client = AsyncOpenAI(api_key=settings.OPENAI_API_KEY)
+    response = await client.embeddings.create(
+        model="text-embedding-3-small",
+        input=text,
+    )
+    return response.data[0].embedding