chat/llm/client.py

@@ -12,3 +12,11 @@ class Message:
 class LLMClient(Protocol):
     async def generate(self, messages: Sequence[Message], *, model: str, **params) -> str: ...
     def stream(self, messages: Sequence[Message], *, model: str, **params) -> AsyncIterator[str]: ...
+    # T112 (Phase 4.5): real-embedding seam. Implementations either call a
+    # provider's ``/v1/embeddings`` endpoint or, when the provider doesn't
+    # expose embeddings (e.g. Featherless today), raise ``NotImplementedError``
+    # so ``generate_embedding`` can catch it and degrade to the zero-vector
+    # fallback. The Protocol is structural, so this method only needs to
+    # exist on implementations; existing callers that don't use it are
+    # unaffected.
+    async def embed(self, text: str, *, model: str) -> list[float]: ...