5b1fcf6d27
Accumulated since a6f12e2 (Phase 21 Rust port + Phase 27 versioning): - Phase 36: embed_semaphore on VectorState (permits=1) serializes seed embed calls — prevents sidecar socket collisions under concurrent /seed stress load - Phase 31+: run_stress.ts 6-task diverse stress scaffolding; run_e2e_rated.ts + orchestrator.ts tightening - Catalog dedupe cleanup: 16 duplicate manifests removed; canonical candidates.parquet (10.5MB -> 76KB) + placements.parquet (1.2MB -> 11KB) regenerated post-dedupe; fresh manifests for active datasets - vectord: harness EvalSet refinements (+181), agent portfolio rotation + ingest triggers (+158), autotune + rag adjustments - catalogd/storaged/ingestd/mcp-server: misc tightening - docs: Phase 28-36 PRD entries + DECISIONS ADR additions; control-plane pivot banner added to top of docs/PRD.md (pointing at docs/CONTROL_PLANE_PRD.md which lands in next commit) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
159 lines
3.4 KiB
JSON
159 lines
3.4 KiB
JSON
{
|
|
"id": "33544879-fcfa-4458-b782-a4ca8dafed08",
|
|
"name": "workers_100k",
|
|
"schema_fingerprint": "1cc2a0caf174aa9bf67b1e2cb7858a312a0c94d604d906f807eb5610864ff70e",
|
|
"objects": [
|
|
{
|
|
"bucket": "primary",
|
|
"key": "datasets/workers_100k.parquet",
|
|
"size_bytes": 65225188,
|
|
"created_at": "2026-04-17T04:54:03.306737596Z"
|
|
}
|
|
],
|
|
"created_at": "2026-04-17T04:54:03.306740279Z",
|
|
"updated_at": "2026-04-17T04:54:03.306927852Z",
|
|
"description": "",
|
|
"owner": "",
|
|
"sensitivity": "pii",
|
|
"columns": [
|
|
{
|
|
"name": "worker_id",
|
|
"data_type": "Int64",
|
|
"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": "email",
|
|
"data_type": "Utf8",
|
|
"sensitivity": "pii",
|
|
"description": "",
|
|
"is_pii": true
|
|
},
|
|
{
|
|
"name": "phone",
|
|
"data_type": "Int64",
|
|
"sensitivity": "pii",
|
|
"description": "",
|
|
"is_pii": true
|
|
},
|
|
{
|
|
"name": "city",
|
|
"data_type": "Utf8",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "state",
|
|
"data_type": "Utf8",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "zip",
|
|
"data_type": "Int64",
|
|
"sensitivity": "pii",
|
|
"description": "",
|
|
"is_pii": true
|
|
},
|
|
{
|
|
"name": "skills",
|
|
"data_type": "Utf8",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "certifications",
|
|
"data_type": "Utf8",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "archetype",
|
|
"data_type": "Utf8",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "reliability",
|
|
"data_type": "Float64",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "responsiveness",
|
|
"data_type": "Float64",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "engagement",
|
|
"data_type": "Float64",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "compliance",
|
|
"data_type": "Float64",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "availability",
|
|
"data_type": "Float64",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "communications",
|
|
"data_type": "Utf8",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "resume_text",
|
|
"data_type": "Utf8",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
}
|
|
],
|
|
"lineage": {
|
|
"source_system": "csv",
|
|
"source_file": "workers_100k.csv",
|
|
"ingest_job": "ingest-1776401643306",
|
|
"ingest_timestamp": "2026-04-17T04:54:03.306737596Z",
|
|
"parent_datasets": []
|
|
},
|
|
"freshness": null,
|
|
"tags": [],
|
|
"row_count": 100000,
|
|
"last_embedded_at": null,
|
|
"embedding_stale_since": null,
|
|
"embedding_refresh_policy": null
|
|
} |