merge: T107 embeddings.py fallback warning

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
     )