"""Tests for FeatherlessClient (Phase 4.5+).

Phase 4.5 adds an ``embed()`` method to the LLMClient Protocol (T112).
Featherless does not expose an OpenAI-compatible ``/v1/embeddings``
endpoint, so its implementation deliberately raises
``NotImplementedError`` to surface the gap clearly. The
``generate_embedding`` wrapper catches this and degrades to the
zero-vector fallback (the existing T107 warning path).

If/when Featherless ships embeddings, swap the body for a real call to
``/v1/embeddings`` and update this test to mock the HTTP layer.
"""

from __future__ import annotations

import pytest

from chat.llm.featherless import FeatherlessClient


@pytest.mark.asyncio
async def test_featherless_embed_raises_not_implemented():
    """Featherless does not expose ``/v1/embeddings`` — embed() must
    raise ``NotImplementedError`` so callers (``generate_embedding``)
    can degrade to the fallback zero vector + warning rather than
    silently producing useless output."""
    client = FeatherlessClient(api_key="test-key")
    with pytest.raises(NotImplementedError) as excinfo:
        await client.embed("hello world", model="bge-small-en-v1.5")
    # Message should hint at the cause so operators see why their
    # real-model swap fell back.
    assert "embeddings" in str(excinfo.value).lower()