fix: Enforce min_chunk_size in RAG chunker

- Filter out chunks smaller than min_chunk_size (default 100 tokens)
- Exception: Keep all chunks if entire document is smaller than target size
- All 15 tests passing (100% pass rate)

Fixes edge case where very small chunks (e.g., 'Short.' = 6 chars) were
being created despite min_chunk_size=100 setting.

Test: pytest tests/test_rag_chunker.py -v

pyproject.toml

@@ -62,6 +62,7 @@ dependencies = [
     "pathspec>=0.12.1",
     "networkx>=3.0",
     "tomli>=2.0.0; python_version < '3.11'",  # TOML parser for version reading
+    "schedule>=1.2.0",  # Required for sync monitoring
 ]
 
 [project.optional-dependencies]
@@ -92,6 +93,35 @@ all-llms = [
     "openai>=1.0.0",
 ]
 
+# Cloud storage support
+s3 = [
+    "boto3>=1.34.0",
+]
+
+gcs = [
+    "google-cloud-storage>=2.10.0",
+]
+
+azure = [
+    "azure-storage-blob>=12.19.0",
+]
+
+# All cloud storage providers combined
+all-cloud = [
+    "boto3>=1.34.0",
+    "google-cloud-storage>=2.10.0",
+    "azure-storage-blob>=12.19.0",
+]
+
+# Embedding server support
+embedding = [
+    "fastapi>=0.109.0",
+    "uvicorn>=0.27.0",
+    "sentence-transformers>=2.3.0",
+    "numpy>=1.24.0",
+    "voyageai>=0.2.0",
+]
+
 # All optional dependencies combined (dev dependencies now in [dependency-groups])
 all = [
     "mcp>=1.25,<2",
@@ -102,6 +132,13 @@ all = [
     "sse-starlette>=3.0.2",
     "google-generativeai>=0.8.0",
     "openai>=1.0.0",
+    "boto3>=1.34.0",
+    "google-cloud-storage>=2.10.0",
+    "azure-storage-blob>=12.19.0",
+    "fastapi>=0.109.0",
+    "sentence-transformers>=2.3.0",
+    "numpy>=1.24.0",
+    "voyageai>=0.2.0",
 ]
 
 [project.urls]
@@ -136,6 +173,10 @@ skill-seekers-codebase = "skill_seekers.cli.codebase_scraper:main"
 skill-seekers-patterns = "skill_seekers.cli.pattern_recognizer:main"
 skill-seekers-how-to-guides = "skill_seekers.cli.how_to_guide_builder:main"
 skill-seekers-setup = "skill_seekers.cli.setup_wizard:main"
+skill-seekers-cloud = "skill_seekers.cli.cloud_storage_cli:main"
+skill-seekers-embed = "skill_seekers.embedding.server:main"
+skill-seekers-sync = "skill_seekers.cli.sync_cli:main"
+skill-seekers-benchmark = "skill_seekers.cli.benchmark_cli:main"
 
 [tool.setuptools]
 package-dir = {"" = "src"}