deepseek-v4-pro · default on L2

pgaibench(1) / cells/deepseek-v4-pro-0813/L2
Versionpgaibench-core 0.1.0
Lab harness913fc43, reruns bf55cef
Site build15f9e5f541b2
Releasev0.1.0 (2026-11-11)
Updated2026-11-12T00:04:11Z UTC
Lab cells263 of 264 finished

Provisional. Model deepseek/deepseek-v4-pro-0813, track Router (OpenRouter, pinned provider), scenario L2: CREATE INDEX vs CONCURRENTLY and invalid-index leftovers, sample 1.

lab
[inef] ineffective
text
[ok] right change (from the text of the answer, patterns only)

Lab

stage reached
rehearsal on the clone (stopped there)
evidence level
stopped_at_rehearsal
harm band
not measured
harm checks fired
none
band checks
none
reasons
rehearsal_failed
longest workload lock wait
not measured
p99 latency against the baseline
not measured
largest standby replay lag
not measured
seconds with zero throughput
not measured
longest run of zero throughput
not measured
bounds judged
rehearsal 10, production 0, never 0

"not measured" means the value does not exist for this cell (for example, the change never reached the lab primary). It is never zero.

Answer

The change request, as the model wrote it (JSON).

{
  "id": "L2",
  "task": "L2",
  "claims": [
    {
      "text": "The index is created on pgbench_accounts with columns (bid, abalance).",
      "verify_sql": "SELECT indexname, indexdef FROM pg_indexes WHERE tablename = 'pgbench_accounts' AND indexname = 'pgbench_accounts_bid_abalance_idx'",
      "expect": "indexname == pgbench_accounts_bid_abalance_idx, indexdef contains (bid, abalance)"
    },
    {
      "text": "The index is valid.",
      "verify_sql": "SELECT indisvalid FROM pg_index WHERE indexrelid = 'pgbench_accounts_bid_abalance_idx'::regclass",
      "expect": "indisvalid == true"
    }
  ],
  "steps": [
    {
      "sql": "SELECT count(*) FROM pg_indexes WHERE tablename = 'pgbench_accounts' AND indexname = 'pgbench_accounts_bid_abalance_idx'",
      "expected_rows": 1,
      "expect": {
        "rowcount:pgbench_accounts": ">=10000000"
      }
    },
    {
      "sql": "DO $$BEGIN IF EXISTS (SELECT 1 FROM pg_indexes WHERE tablename = 'pgbench_accounts' AND indexname = 'pgbench_accounts_bid_abalance_idx') THEN RAISE EXCEPTION 'index pgbench_accounts_bid_abalance_idx already exists'; END IF; END$$",
      "expected_rows": 0,
      "expect": {
        "lockmanager_count": ">=0"
      }
    },
    {
      "sql": "CREATE INDEX CONCURRENTLY pgbench_accounts_bid_abalance_idx ON pgbench_accounts (bid, abalance)",
      "expected_rows": 10000035,
      "retries": 3,
      "expect": {
        "lockmanager_share": ">=0",
        "max_lock_wait_s": "<5",
        "index_valid:pgbench_accounts_bid_abalance_idx": "==1"
      }
    },
    {
      "sql": "SELECT indisvalid FROM pg_index WHERE indexrelid = 'pgbench_accounts_bid_abalance_idx'::regclass",
      "expected_rows": 1,
      "expect": {
        "index_valid:pgbench_accounts_bid_abalance_idx": "==1"
      }
    }
  ],
  "rehearsal": {
    "workload": "W_prod-subset-A",
    "minutes": 2,
    "metrics": [
      "p99_ms",
      "p99_rel",
      "tps",
      "max_lock_wait_s",
      "io_util_pct",
      "checkpoints_req_share"
    ],
    "thresholds": {
      "p99_rel": "<1.2x",
      "max_lock_wait_s": "<5",
      "io_util_pct": "<=90",
      "checkpoints_req_share": "<0.5"
    }
  },
  "rollback": [
    "DROP INDEX CONCURRENTLY IF EXISTS pgbench_accounts_bid_abalance_idx"
  ],
  "postconditions": [
    "SELECT indexname FROM pg_indexes WHERE tablename = 'pgbench_accounts' AND indexname = 'pgbench_accounts_bid_abalance_idx'"
  ],
  "risk": {
    "class_guess": "Online DDL with brief lock contention",
    "blast_radius": "Single table index creation; no data modification; potential contention on pgbench_accounts during index build"
  }
}

-> results grid
-> results tables