feat: configurable embedding infrastructure — local (fastembed) + API (OpenAI) (#675)

- Add agent/embeddings.py with Embedder protocol, FastEmbedEmbedder, OpenAIEmbedder
- Factory function get_embedder() reads provider from config.yaml embeddings section
- Lazy initialization — no startup impact, model loaded on first embed call
- cosine_similarity() and cosine_similarity_matrix() utility functions included
- Add fastembed as optional dependency in pyproject.toml
- 30 unit tests, all passing

Closes #675

pyproject.toml

@@ -51,6 +51,7 @@ pty = [
   "pywinpty>=2.0.0; sys_platform == 'win32'",
 ]
 honcho = ["honcho-ai>=2.0.1"]
+embeddings = ["fastembed>=0.3.0"]
 mcp = ["mcp>=1.2.0"]
 homeassistant = ["aiohttp>=3.9.0"]
 yc-bench = ["yc-bench @ git+https://github.com/collinear-ai/yc-bench.git"]
@@ -65,6 +66,7 @@ all = [
   "hermes-agent[slack]",
   "hermes-agent[pty]",
   "hermes-agent[honcho]",
+  "hermes-agent[embeddings]",
   "hermes-agent[mcp]",
   "hermes-agent[homeassistant]",
 ]