feat: embedding generation service (Phase 4 pseudo-embedding) (T91)

tests/test_embeddings.py

@@ -0,0 +1,91 @@
+"""Tests for the embedding generation service (T91, Phase 4).
+
+Phase 4's first cut ships a deterministic local pseudo-embedding so the
+vector retrieval pipeline can land without an external embeddings API
+or a heavy local model dependency. These tests pin the contract:
+
+* the result has the right shape (vector length, ``dim`` metadata),
+* the default ``model`` string is reported back unchanged,
+* output is byte-identical for the same input (deterministic),
+* distinct inputs produce distinct vectors (so cosine actually
+  discriminates),
+* empty / whitespace-only input collapses to the ``"fallback"`` sentinel
+  with a zero vector — callers detect this and skip indexing,
+* the vector is unit-normalized so cosine similarity behaves.
+
+The pseudo path doesn't touch the LLMClient, so we pass an empty
+``MockLLMClient`` — any accidental call into it would raise
+``IndexError`` and surface as a regression.
+"""
+
+from __future__ import annotations
+
+import math
+
+import pytest
+
+from chat.llm.mock import MockLLMClient
+from chat.services.embeddings import (
+    DEFAULT_EMBEDDING_DIM,
+    DEFAULT_EMBEDDING_MODEL,
+    FALLBACK_EMBEDDING_MODEL,
+    EmbeddingResult,
+    generate_embedding,
+)
+
+
+def _client() -> MockLLMClient:
+    # Pseudo path never calls the client — empty canned list ensures any
+    # accidental call raises and surfaces the regression loudly.
+    return MockLLMClient(canned=[])
+
+
+@pytest.mark.asyncio
+async def test_generate_embedding_returns_vector_of_correct_dim():
+    result = await generate_embedding(_client(), text="hello")
+    assert isinstance(result, EmbeddingResult)
+    assert isinstance(result.vector, list)
+    assert len(result.vector) == DEFAULT_EMBEDDING_DIM == 384
+    assert result.dim == 384
+    assert all(isinstance(x, float) for x in result.vector)
+
+
+@pytest.mark.asyncio
+async def test_generate_embedding_returns_correct_model_metadata():
+    result = await generate_embedding(_client(), text="hello")
+    assert result.model == DEFAULT_EMBEDDING_MODEL == "pseudo-sha256-384"
+
+
+@pytest.mark.asyncio
+async def test_generate_embedding_is_deterministic():
+    a = await generate_embedding(_client(), text="hello world")
+    b = await generate_embedding(_client(), text="hello world")
+    assert a.vector == b.vector
+
+
+@pytest.mark.asyncio
+async def test_generate_embedding_distinct_text_produces_distinct_vectors():
+    a = await generate_embedding(_client(), text="hello world")
+    b = await generate_embedding(_client(), text="totally different content")
+    assert a.vector != b.vector
+    # Sanity-check cosine similarity — both vectors are unit-normalized,
+    # so this reduces to a plain dot product.
+    cosine = sum(x * y for x, y in zip(a.vector, b.vector))
+    assert cosine < 0.99
+
+
+@pytest.mark.asyncio
+async def test_generate_embedding_empty_text_returns_fallback():
+    for empty in ("", "   ", "\n\t"):
+        result = await generate_embedding(_client(), text=empty)
+        assert result.model == FALLBACK_EMBEDDING_MODEL == "fallback"
+        assert result.dim == DEFAULT_EMBEDDING_DIM
+        assert len(result.vector) == DEFAULT_EMBEDDING_DIM
+        assert all(x == 0.0 for x in result.vector)
+
+
+@pytest.mark.asyncio
+async def test_generate_embedding_unit_normalized():
+    result = await generate_embedding(_client(), text="some non-empty text")
+    norm_sq = sum(x * x for x in result.vector)
+    assert math.isclose(norm_sq, 1.0, abs_tol=1e-6)