#!/usr/bin/env bash
# Quickstart step 5 — build the leakage-gated training dataset.
set -euo pipefail

: "${TESSERA_API_BASE:?e.g. https://api.staging.tessera.zone/v1}"
: "${TESSERA_API_KEY:?your tsk_test_… key}"
: "${TESSERA_STATE_DIR:=.}"
AUTH=(-H "Authorization: Bearer $TESSERA_API_KEY")
LABEL_ID="$(cat "$TESSERA_STATE_DIR/label_id")"

# Small windows keep the tutorial models CPU-friendly: each training example
# is a user's last 8 events inside the sample's fixed time range.
BUILD="$(curl -sS -X POST "$TESSERA_API_BASE/datasets" "${AUTH[@]}" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: quickstart-dataset" \
  -d '{
    "entity_type": "user",
    "labels": ["'"$LABEL_ID"'"],
    "window": {
      "max_events_per_entity": 8,
      "time_range": {"start": "2025-01-01T00:00:00Z", "end": "2025-07-01T00:00:00Z"}
    },
    "split": {"method": "entity_hash", "train": 0.7, "val": 0.1, "test": 0.2, "seed": 7}
  }')"
DATASET_ID="$(printf '%s' "$BUILD" | python3 -c 'import json,sys; print(json.load(sys.stdin)["dataset_id"])')"

for _ in $(seq 1 600); do
  DATASET="$(curl -sS "$TESSERA_API_BASE/datasets/$DATASET_ID" "${AUTH[@]}")"
  STATUS="$(printf '%s' "$DATASET" | python3 -c 'import json,sys; print(json.load(sys.stdin)["status"])')"
  case "$STATUS" in succeeded|failed|aborted_leakage) break ;; esac
  sleep 2
done

# The manifest is the build's receipt: row counts per split, per-label
# supervision accounting, the (empty) violation report, and every pinned
# fingerprint.
printf '%s' "$DATASET" | python3 -c '
import json, sys
dataset = json.load(sys.stdin)
manifest = dataset.get("manifest") or {}
print(json.dumps({
    "dataset_id": dataset["dataset_id"],
    "status": dataset["status"],
    "row_counts": manifest.get("row_counts"),
    "violations": (dataset.get("violation_report") or {}).get("violations"),
    "contract_version": manifest.get("contract_version"),
}, indent=2))
'
printf '%s' "$DATASET_ID" > "$TESSERA_STATE_DIR/dataset_id"