From 29b7c90b29aef99a8be7af644ee03f23c8336fcf Mon Sep 17 00:00:00 2001
From: Joseph Doherty <dohejw01@gmail.com>
Date: Mon, 27 Apr 2026 04:47:17 -0400
Subject: [PATCH] chore: embeddings.py warns on fallback for non-default models
 (T107)

---
 chat/services/embeddings.py | 13 ++++++++++++-
 tests/test_embeddings.py    | 31 +++++++++++++++++++++++++++++++
 2 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/chat/services/embeddings.py b/chat/services/embeddings.py
index ece6eae..44002ea 100644
--- a/chat/services/embeddings.py
+++ b/chat/services/embeddings.py
@@ -10,6 +10,7 @@ EmbeddingResult shape stays the same, only the generator changes.
 from __future__ import annotations
 
 import hashlib
+import logging
 import math
 import struct
 
@@ -18,6 +19,8 @@ from pydantic import BaseModel
 from chat.llm.client import LLMClient
 
 
+_log = logging.getLogger(__name__)
+
 DEFAULT_EMBEDDING_DIM = 384
 DEFAULT_EMBEDDING_MODEL = "pseudo-sha256-384"
 FALLBACK_EMBEDDING_MODEL = "fallback"
@@ -93,7 +96,15 @@ async def generate_embedding(
         return EmbeddingResult(vector=_pseudo_embed(text, dim), model=model, dim=dim)
 
     # Future: real embedding via client.embed(...). Phase 4.5 work.
-    # For Phase 4, any non-default model falls through to fallback.
+    # For Phase 4, any non-default model falls through to fallback —
+    # warn so misconfigured callers (e.g., a real-model swap that isn't
+    # wired up yet) don't silently degrade to a zero vector.
+    _log.warning(
+        "generate_embedding: non-default model %r returned fallback "
+        "(model client.embed() not yet implemented in Phase 4.5+); "
+        "downstream search will degrade silently. Configure a supported model.",
+        model,
+    )
     return EmbeddingResult(
         vector=[0.0] * dim, model=FALLBACK_EMBEDDING_MODEL, dim=dim
     )
diff --git a/tests/test_embeddings.py b/tests/test_embeddings.py
index b458681..4d1dc4b 100644
--- a/tests/test_embeddings.py
+++ b/tests/test_embeddings.py
@@ -20,6 +20,7 @@ The pseudo path doesn't touch the LLMClient, so we pass an empty
 
 from __future__ import annotations
 
+import logging
 import math
 
 import pytest
@@ -89,3 +90,33 @@ 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)
+
+
+@pytest.mark.asyncio
+async def test_generate_embedding_non_default_model_logs_warning(caplog):
+    """T107: non-default model falls through to fallback and must warn.
+
+    A Phase 4.5+ caller pointing at a real model that isn't yet wired
+    up would otherwise silently degrade (zero vector → useless cosine).
+    The warning surfaces the misconfiguration in logs.
+    """
+    caplog.set_level(logging.WARNING, logger="chat.services.embeddings")
+    result = await generate_embedding(_client(), text="hello", model="real-model")
+
+    # Behavior unchanged: still returns the fallback sentinel.
+    assert result.model == FALLBACK_EMBEDDING_MODEL == "fallback"
+    assert all(x == 0.0 for x in result.vector)
+
+    # Warning fired and names the offending model.
+    warnings = [r for r in caplog.records if r.levelno == logging.WARNING]
+    assert any("non-default model" in r.getMessage() for r in warnings)
+    assert any("real-model" in r.getMessage() for r in warnings)
+
+
+@pytest.mark.asyncio
+async def test_generate_embedding_default_model_does_not_warn(caplog):
+    """T107: the silent default path must stay silent."""
+    caplog.set_level(logging.WARNING, logger="chat.services.embeddings")
+    await generate_embedding(_client(), text="hello")
+    warnings = [r for r in caplog.records if r.levelno == logging.WARNING]
+    assert warnings == []