RAG reranker + manifest bucket fix — quality improvements from eval

RAG pipeline now includes a cross-encoder rerank step between retrieval
and generation. The LLM re-sorts top-K results by relevance before
they become context. Falls back to original order if model output is
unparseable (~5% with 7B models). Also improved the generation prompt
to be domain-aware ("staffing database") and request specific citations.

Fixed 4 catalog manifests with bucket="data" (pre-federation leftover)
that poisoned the entire DataFusion query context on startup. The
"users", "lab_trials", "meta_runs", and "new_candidates" datasets
now correctly reference bucket="primary". This bug was surfaced by
the quality evaluation pipeline — wouldn't have been found by
structural tests alone.

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

data/_catalog/manifests/5a35646f-b357-4636-b88f-203aba0d7435.json

@@ -0,0 +1,61 @@
+{
+  "id": "5a35646f-b357-4636-b88f-203aba0d7435",
+  "name": "people_test",
+  "schema_fingerprint": "bba35b6cd1e399dc0504c760c767ab391f7ed81a41573c15b3bd4eb0e3bcc382",
+  "objects": [
+    {
+      "bucket": "testing",
+      "key": "datasets/people_test.parquet",
+      "size_bytes": 1402,
+      "created_at": "2026-04-16T13:47:32.669517398Z"
+    }
+  ],
+  "created_at": "2026-04-16T13:47:32.669518210Z",
+  "updated_at": "2026-04-16T13:47:32.669787451Z",
+  "description": "",
+  "owner": "",
+  "sensitivity": "pii",
+  "columns": [
+    {
+      "name": "person_id",
+      "data_type": "Utf8",
+      "sensitivity": null,
+      "description": "",
+      "is_pii": false
+    },
+    {
+      "name": "name",
+      "data_type": "Utf8",
+      "sensitivity": "pii",
+      "description": "",
+      "is_pii": true
+    },
+    {
+      "name": "role",
+      "data_type": "Utf8",
+      "sensitivity": null,
+      "description": "",
+      "is_pii": false
+    },
+    {
+      "name": "city",
+      "data_type": "Utf8",
+      "sensitivity": null,
+      "description": "",
+      "is_pii": false
+    }
+  ],
+  "lineage": {
+    "source_system": "csv",
+    "source_file": "people.csv",
+    "ingest_job": "ingest-1776347252669",
+    "ingest_timestamp": "2026-04-16T13:47:32.669517398Z",
+    "parent_datasets": []
+  },
+  "freshness": null,
+  "tags": [],
+  "row_count": 3,
+  "last_embedded_at": null,
+  "embedding_stale_since": null,
+  "embedding_refresh_policy": null
+}