2 Commits

Author	SHA1	Message	Date
yusyus	0573ef24f9	fix: Add cloud storage test dependencies and proper skipping (Kimi's issues #2 & #3) ... Fixed cloud storage test failures and missing test dependencies: Issue #2: Cloud Storage Test Failures (16 tests) - Added availability checks for boto3, google-cloud-storage, azure-storage-blob - Added @pytest.mark.skipif decorators to all 16 cloud storage tests - Tests now skip gracefully when dependencies not installed - Result: 4 passed, 16 skipped (instead of 16 failed) Issue #3: Missing Test Dependencies Added to [dependency-groups] dev: - boto3>=1.26.0 (AWS S3 testing) - google-cloud-storage>=2.10.0 (Google Cloud Storage testing) - azure-storage-blob>=12.17.0 (Azure Blob Storage testing) - psutil>=5.9.0 (process utilities) - numpy>=1.24.0 (numerical operations) - starlette>=0.31.0 (HTTP transport testing) - httpx>=0.24.0 (HTTP client) Test Results: - Before: 16 failed (AttributeError on missing modules) - After: 4 passed, 16 skipped (clean skip with reason) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>	2026-02-08 12:45:48 +03:00
yusyus	8b3f31409e	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	2026-02-07 20:59:03 +03:00