Observer KB: 477 pages from 8 ChatGPT PDFs indexed and searchable

- Fixed Unicode crash in chunker (ligatures like fi causing byte boundary panic)
- Chunker now works with char indices, not byte indices
- 8 PDFs ingested: hybrid_ai_data_lake (133p), spark_vs_flink_iceberg (124p),
  code_sorting (70p), hybrid_indexing (69p), rust_in_tech_stack (49p), etc.
- 477 chunks embedded via supervisor (43/sec)
- HNSW index built in 0.44s
- Search results <200ms, finding correct conversations by meaning
- Tested: "S3 architecture", "CRM WordPress", "Rust vs Python" — all correct

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

data/vectors/meta/quick_test.json

@@ -0,0 +1,15 @@
+{
+  "index_name": "quick_test",
+  "source": "test",
+  "model_name": "nomic-embed-text",
+  "model_version": "latest",
+  "dimensions": 768,
+  "chunk_count": 5,
+  "doc_count": 5,
+  "chunk_size": 500,
+  "overlap": 50,
+  "storage_key": "vectors/quick_test.parquet",
+  "created_at": "2026-03-28T03:51:49.689474954Z",
+  "build_time_secs": 1.3572433,
+  "chunks_per_sec": 3.6839378
+}