data/_catalog/views/candidates_safe.json

@@ -0,0 +1,24 @@
+{
+  "name": "candidates_safe",
+  "base_dataset": "candidates",
+  "columns": [
+    "candidate_id",
+    "first_name",
+    "city",
+    "state",
+    "skills",
+    "years_experience",
+    "status"
+  ],
+  "row_filter": "status != 'blocked'",
+  "column_redactions": {
+    "candidate_id": {
+      "kind": "mask",
+      "keep_prefix": 3,
+      "keep_suffix": 2
+    }
+  },
+  "created_at": "2026-04-27T15:42:00Z",
+  "created_by": "j",
+  "description": "PII-free candidate projection — drops last_name, email, phone, hourly_rate_usd. candidate_id masked (keep first 3, last 2). Visible to recruiter / mode-runner agents."
+}

data/_catalog/views/jobs_safe.json

@@ -0,0 +1,26 @@
+{
+  "name": "jobs_safe",
+  "base_dataset": "job_orders",
+  "columns": [
+    "job_order_id",
+    "client_id",
+    "title",
+    "vertical",
+    "status",
+    "city",
+    "state",
+    "zip",
+    "bill_rate",
+    "pay_rate"
+  ],
+  "column_redactions": {
+    "client_id": {
+      "kind": "mask",
+      "keep_prefix": 3,
+      "keep_suffix": 2
+    }
+  },
+  "created_at": "2026-04-27T15:42:00Z",
+  "created_by": "j",
+  "description": "Job-order projection with client_id masked. Drops description (often quotes client names verbatim, no text-scrubber available). bill_rate / pay_rate kept — commercial info, not PII per staffing PRD."
+}

data/_catalog/views/workers_safe.json

@@ -0,0 +1,22 @@
+{
+  "name": "workers_safe",
+  "base_dataset": "workers_500k",
+  "columns": [
+    "worker_id",
+    "role",
+    "city",
+    "state",
+    "skills",
+    "certifications",
+    "archetype",
+    "reliability",
+    "responsiveness",
+    "engagement",
+    "compliance",
+    "availability"
+  ],
+  "column_redactions": {},
+  "created_at": "2026-04-27T15:42:00Z",
+  "created_by": "j",
+  "description": "PII-free worker projection — drops name, email, phone, zip, communications, resume_text. resume_text + communications carry verbatim PII (full names) and there's no in-view text scrubber, so they're dropped wholesale. Skills + certifications + scores carry the matching signal for staffing inference. Source for workers_500k_v9 vector corpus rebuild."
+}

scripts/staffing/build_workers_v9.sh

@@ -0,0 +1,53 @@
+#!/usr/bin/env bash
+# build_workers_v9.sh — Decision B (corpus rebuild side).
+#
+# Rebuilds workers_500k_v9 vector corpus from workers_safe view rather
+# than the raw workers_500k table. Closes the PII enforcement gap
+# (verified 2026-04-27 that v8 was built directly from raw — LLM saw
+# names/emails/phones/resume_text for every staffing query).
+#
+# Run as a background job — embedding 500K chunks took ~4 min for v8
+# of 50K rows; v9 of 500K rows will be 30+ min. Do not block on this.
+#
+# Usage:
+#     ./scripts/staffing/build_workers_v9.sh
+#     LH_GATEWAY=http://localhost:3100 ./scripts/staffing/build_workers_v9.sh
+#
+# After it completes:
+#   - Verify via: curl /vectors/indexes/workers_500k_v9 | jq
+#   - Flip config/modes.toml `staffing_inference` matrix_corpus to v9
+#   - Restart gateway to pick up the modes.toml change
+
+set -euo pipefail
+
+GATEWAY="${LH_GATEWAY:-http://localhost:3100}"
+
+# The /vectors/index endpoint accepts {name, sql, embed_model, ...}.
+# SQL pulls from workers_safe (see data/_catalog/views/workers_safe.json)
+# so the embedded text never contained raw PII by construction.
+#
+# Concatenated text is what gets embedded — keep it short enough that
+# 500K rows × N chunks fits in disk + memory budgets but still carries
+# the match signal (role, location, skills, scores).
+
+BODY=$(cat <<'JSON'
+{
+  "name": "workers_500k_v9",
+  "sql": "SELECT CAST(worker_id AS VARCHAR) AS doc_id, CONCAT(role, ' in ', city, ', ', state, '. Skills: ', COALESCE(skills, ''), '. Certifications: ', COALESCE(certifications, ''), '. Archetype: ', COALESCE(archetype, ''), '. Scores — reliability ', CAST(reliability AS VARCHAR), ', responsiveness ', CAST(responsiveness AS VARCHAR), ', availability ', CAST(availability AS VARCHAR), '.') AS text FROM workers_safe",
+  "embed_model": "nomic-embed-text",
+  "chunk_size": 500,
+  "overlap": 50,
+  "source_dataset": "workers_safe",
+  "bucket": "primary"
+}
+JSON
+)
+
+echo "POSTing /vectors/index → workers_500k_v9 (background job)..."
+curl -sS -X POST "${GATEWAY}/vectors/index" \
+  -H 'content-type: application/json' \
+  -d "$BODY"
+echo
+echo "Job started. Monitor progress:"
+echo "  curl ${GATEWAY}/vectors/indexes/workers_500k_v9 | jq"
+echo "  watch -n 5 'curl -s ${GATEWAY}/vectors/jobs | jq'"