feat: LLMClient protocol with Featherless and mock implementations

chat/llm/featherless.py

@@ -0,0 +1,29 @@
+from __future__ import annotations
+from typing import AsyncIterator, Sequence
+from openai import AsyncOpenAI
+from .client import Message
+
+
+class FeatherlessClient:
+    def __init__(self, api_key: str, base_url: str = "https://api.featherless.ai/v1"):
+        self._client = AsyncOpenAI(api_key=api_key, base_url=base_url)
+
+    async def generate(self, messages: Sequence[Message], *, model: str, **params) -> str:
+        resp = await self._client.chat.completions.create(
+            model=model,
+            messages=[{"role": m.role, "content": m.content} for m in messages],
+            **params,
+        )
+        return resp.choices[0].message.content or ""
+
+    async def stream(self, messages: Sequence[Message], *, model: str, **params) -> AsyncIterator[str]:
+        stream = await self._client.chat.completions.create(
+            model=model,
+            messages=[{"role": m.role, "content": m.content} for m in messages],
+            stream=True,
+            **params,
+        )
+        async for chunk in stream:
+            delta = chunk.choices[0].delta.content or ""
+            if delta:
+                yield delta