@tangle-network/agent-eval 0.129.0 → 0.130.0

package/dist/chunk-M4YBQKIJ.js.map

@@ -1 +0,0 @@
-{"version":3,"sources":["../src/contamination-guard.ts","../src/contract/analyze-runs.ts"],"sourcesContent":["/**\n * ContaminationGuard — ensures held-out scenarios don't leak into\n * training/prompt paths, and flags model memorization.\n *\n * Three probes:\n *   1. `checkCanaries(output, scenario)` — if the scenario carries a\n *      canary token, it MUST NOT appear in the agent's output.\n *      Canaries are strings that are statistically impossible to\n *      reconstruct from the scenario description alone — so if they\n *      echo back, the model memorized them.\n *   2. `canaryLeakView(store)` — cross-corpus view of every run whose\n *      output contained a canary, with the offending scenario + run.\n *   3. `HoldoutAuditor` — wraps a Dataset and emits a structured error\n *      on any code path that reads holdout scenarios but doesn't flag\n *      `purpose: 'evaluation'`. Keeps engineers honest.\n */\n\nimport type { DatasetScenario } from './dataset'\nimport { llmSpans } from './trace/query'\nimport type { TraceStore } from './trace/store'\n\nexport interface CanaryLeak {\n  scenarioId: string\n  canary: string\n  runId?: string\n  evidence: string\n}\n\nexport function checkCanaries(output: string, scenarios: DatasetScenario[]): CanaryLeak[] {\n  const leaks: CanaryLeak[] = []\n  for (const s of scenarios) {\n    if (!s.canary) continue\n    if (output.includes(s.canary)) {\n      leaks.push({ scenarioId: s.id, canary: s.canary, evidence: excerpt(output, s.canary) })\n    }\n  }\n  return leaks\n}\n\n/**\n * Behavioral canary: tests the AGENT, not the eval grep.\n *\n *   - `forbiddenPattern` PRESENT in output ⇒ AGENT EMITTED BAD CONTENT ⇒ LEAK.\n *   - `forbiddenPattern` ABSENT from output ⇒ AGENT HELD THE LINE       ⇒ PASS.\n *\n * Use when running known-bad-prompt scenarios against the agent under\n * test and you want to know if the agent misbehaved. The classical\n * {@link checkCanaries} / {@link import('./canary').runCanaries | runCanaries}\n * test whether the eval check fires when the bad output is forced\n * into the eval flow — different question, different answer.\n *\n * Pattern resolution order (first match wins):\n *   1. `scenario.forbiddenPattern` — if it parses as `/body/flags`,\n *      treated as a regex; otherwise a literal substring.\n *   2. `scenario.canary` — literal substring fallback so the helper\n *      works on existing scenario fixtures.\n *\n * Returns `null` when nothing forbidden was found OR the scenario\n * declared no pattern.\n */\nexport function checkBehavioralCanary(\n  output: string,\n  scenario: DatasetScenario,\n): CanaryLeak | null {\n  const pattern = scenario.forbiddenPattern ?? scenario.canary\n  if (!pattern) return null\n  const hit = matchForbidden(output, pattern)\n  if (!hit) return null\n  return {\n    scenarioId: scenario.id,\n    canary: pattern,\n    evidence: excerpt(output, hit),\n  }\n}\n\n/**\n * Behavioral canary over many (scenario, output) pairs. Sibling to\n * {@link import('./canary').runCanaries | runCanaries} — same idea\n * (run-many → report) but the question being answered is \"did the\n * AGENT misbehave?\" rather than \"did the EVAL grep fire?\".\n *\n * Returns one `CanaryLeak` per pair where the agent's output\n * contained its scenario's `forbiddenPattern` (or `canary` fallback).\n */\nexport function runBehavioralCanaries(\n  cases: Array<{ scenario: DatasetScenario; output: string; runId?: string }>,\n): CanaryLeak[] {\n  const leaks: CanaryLeak[] = []\n  for (const c of cases) {\n    const leak = checkBehavioralCanary(c.output, c.scenario)\n    if (leak) leaks.push({ ...leak, runId: c.runId ?? leak.runId })\n  }\n  return leaks\n}\n\n/**\n * Resolve a forbidden-pattern string to the matched substring inside\n * `output`. `/body/flags` notation is interpreted as a regex; anything\n * else is a literal substring.\n */\nfunction matchForbidden(output: string, pattern: string): string | null {\n  const re = tryParseRegex(pattern)\n  if (re) {\n    const m = output.match(re)\n    return m && m[0].length > 0 ? m[0] : null\n  }\n  return output.includes(pattern) ? pattern : null\n}\n\nfunction tryParseRegex(pattern: string): RegExp | null {\n  if (pattern.length < 2 || pattern[0] !== '/') return null\n  const last = pattern.lastIndexOf('/')\n  if (last <= 0) return null\n  const body = pattern.slice(1, last)\n  const flags = pattern.slice(last + 1)\n  if (!/^[gimsuy]*$/.test(flags)) return null\n  try {\n    return new RegExp(body, flags)\n  } catch {\n    return null\n  }\n}\n\n/**\n * Scan the LLM-output history in a corpus; returns every case where a\n * canary from a known scenario appeared in agent output. Pass the full\n * set of scenarios whose canaries you care about (typically the whole\n * held-out slice).\n */\nexport async function canaryLeakView(\n  store: TraceStore,\n  scenarios: DatasetScenario[],\n): Promise<CanaryLeak[]> {\n  const targets = scenarios.filter((s) => !!s.canary)\n  if (targets.length === 0) return []\n  const spans = await llmSpans(store)\n  const leaks: CanaryLeak[] = []\n  for (const span of spans) {\n    const output = span.output ?? ''\n    for (const s of targets) {\n      if (s.canary && output.includes(s.canary)) {\n        leaks.push({\n          scenarioId: s.id,\n          canary: s.canary,\n          runId: span.runId,\n          evidence: excerpt(output, s.canary),\n        })\n      }\n    }\n  }\n  return leaks\n}\n\nexport class HoldoutAuditor {\n  private scenarios: DatasetScenario[]\n  private accessLog: Array<{ scenarioId: string; purpose: string; at: number }> = []\n\n  constructor(scenarios: DatasetScenario[]) {\n    this.scenarios = scenarios\n  }\n\n  /** Retrieve a holdout scenario for a declared purpose. Non-'evaluation' throws. */\n  get(scenarioId: string, purpose: 'evaluation' | 'debugging'): DatasetScenario {\n    if (purpose !== 'evaluation' && purpose !== 'debugging') {\n      throw new Error(\n        `HoldoutAuditor.get: purpose must be 'evaluation' or 'debugging', got ${purpose}`,\n      )\n    }\n    const s = this.scenarios.find((x) => x.id === scenarioId)\n    if (!s) throw new Error(`holdout scenario \"${scenarioId}\" not found`)\n    this.accessLog.push({ scenarioId, purpose, at: Date.now() })\n    return s\n  }\n\n  getAccessLog(): ReadonlyArray<{ scenarioId: string; purpose: string; at: number }> {\n    return this.accessLog\n  }\n}\n\nfunction excerpt(source: string, needle: string): string {\n  const at = source.indexOf(needle)\n  if (at < 0) return ''\n  const start = Math.max(0, at - 30)\n  const end = Math.min(source.length, at + needle.length + 30)\n  return (start > 0 ? '…' : '') + source.slice(start, end) + (end < source.length ? '…' : '')\n}\n","/**\n * # `analyzeRuns()` — turn a set of agent runs into an actionable decision packet.\n *\n * Wires the substrate's statistical, calibration, clustering, Pareto, and\n * release-confidence primitives into one `InsightReport`. Two top-level\n * entry points use this function:\n *\n *   - `selfImprove()` calls it on the campaign output to attach a packet\n *     to every run.\n *   - Consumers with observed `RunRecord[]` (production traces, gold\n *     corpora, approve/reject tables) call it directly via `analyzeRuns()`\n *     for analysis without a closed loop.\n *\n * Every section is opt-in based on what the input data supports — the\n * function never invents signal. If runs carry no judge scores, `judges`\n * is empty. If there's no baseline/candidate split, `lift` is undefined.\n * If no `analyst` is wired, `failureClusters` is undefined.\n *\n * The `recommendations` array is the human-readable layer; everything\n * else is the evidence backing each recommendation.\n */\n\nimport type { AnalystRegistry } from '../analyst/registry'\nimport type { AnalystFinding } from '../analyst/types'\nimport { checkCanaries } from '../contamination-guard'\nimport type { DatasetScenario } from '../dataset'\nimport { continuousAgreement } from '../judge-calibration'\nimport { pairRunRecords } from '../paired-arms'\nimport { observedSplitScore } from '../rollout/reward'\nimport {\n  type RunRecord,\n  type RunTerminalOutcome,\n  type RunTokenUsage,\n  validateRunRecord,\n} from '../run-record'\nimport {\n  pairedBootstrap,\n  pairedCohensDz,\n  pairedMde,\n  pairedTTest,\n  pearsonR,\n  requiredPairedSampleSize,\n  spearmanR,\n} from '../statistics'\nimport { type ParetoFigureSpec, paretoChart } from '../summary-report'\nimport type { FailureClass } from '../trace/schema'\n\nimport type {\n  CostProvenanceSummary,\n  ExecutionInsight,\n  FailureClassTally,\n  FailureClusterInsight,\n  InsightReport,\n  InterRaterInsight,\n  JudgeInsight,\n  LiftInsight,\n  MetricDelta,\n  OutcomeCorrelationInsight,\n  PriorPeriodComparison,\n  Recommendation,\n  ScalarDistribution,\n  TokenUsageInsight,\n} from './insight-report'\n\n// ── Public API ───────────────────────────────────────────────────────\n\nexport interface AnalyzeRunsOptions {\n  /** The runs to analyze. */\n  runs: RunRecord[]\n  /** Which split to score against when reading composite from RunOutcome.\n   *  Default: holdout when ANY run has a `holdoutScore`, else search. */\n  split?: 'search' | 'holdout' | 'auto'\n  /** Pairwise analysis configuration. When both `baselineCandidateId` and\n   *  `candidateCandidateId` are present, lift is computed on paired\n   *  (experimentId, scenarioId, seed) identities shared between the two sides.\n   *  Unmatched rows remain visible in the lift result. */\n  baselineCandidateId?: string\n  candidateCandidateId?: string\n  /** Canary scenarios — checked against every run's raw output for\n   *  holdout contamination. */\n  canaryScenarios?: DatasetScenario[]\n  /** Analyst registry for failure clustering. When omitted, the\n   *  `failureClusters` section is left undefined. */\n  analyst?: AnalystRegistry\n  /** Downstream outcome metric per run (e.g. engagement rate, approval\n   *  rate, downstream pass rate). When present, the report includes\n   *  `outcomeCorrelation` + a simple linear reward model fit. */\n  outcomeSignal?: {\n    metric: string\n    valueByRunId: Record<string, number>\n  }\n  /** Multi-rater feedback for inter-rater agreement. Each entry is one\n   *  rater's score for one run. Two or more raters → kappa + disagreement\n   *  triage list. */\n  raterScores?: Array<{ runId: string; rater: string; score: number }>\n  /** Number of histogram bins for distributional summaries. Default 12. */\n  histogramBins?: number\n  /** Decision threshold — the smallest composite lift the caller cares\n   *  about. Used by the recommendations engine to call ship vs hold.\n   *  Default 0.02. */\n  decisionThreshold?: number\n  /** Optional prior-period runs. When set, the report includes\n   *  `priorPeriodComparison` with per-metric Welch-CI deltas and\n   *  recommendations fire on statistically significant regressions.\n   *  The two windows do NOT have to share scenarios — the comparison\n   *  is two-sample unpaired (the substrate's `lift` field uses paired\n   *  bootstrap on shared (experimentId, scenarioId, seed) identities; this is the\n   *  shape for \"this week vs last week\" rather than \"candidate vs\n   *  baseline within a campaign\"). */\n  baselineRuns?: RunRecord[]\n  /** Human-readable label for the baseline window, e.g. \"vs prior 7\n   *  days\", \"vs v3.1 release\". Surfaces in recommendations + UI. */\n  baselineLabel?: string\n}\n\nexport interface SummarizeExecutionOptions {\n  runs: RunRecord[]\n  histogramBins?: number\n}\n\nexport interface ExecutionReport {\n  execution: ExecutionInsight\n  costProvenance: CostProvenanceSummary\n}\n\n/** Summarize runtime facts without interpreting task quality or promotion readiness. */\nexport function summarizeExecution(opts: SummarizeExecutionOptions): ExecutionReport {\n  const runs = opts.runs.map(validateRunRecord)\n  const bins = opts.histogramBins ?? 12\n  return {\n    execution: computeExecutionInsight(runs, bins),\n    costProvenance: summarizeCostProvenance(runs),\n  }\n}\n\nexport async function analyzeRuns(opts: AnalyzeRunsOptions): Promise<InsightReport> {\n  const runs = opts.runs.map(validateRunRecord)\n  const bins = opts.histogramBins ?? 12\n  const threshold = opts.decisionThreshold ?? 0.02\n  const split = resolveSplit(runs, opts.split ?? 'auto')\n\n  const compositeWithIds = runs\n    .map((r) => ({ runId: r.runId, score: compositeOf(r, split) }))\n    .filter((p) => Number.isFinite(p.score))\n  const composite = distributionOf(\n    compositeWithIds.map((p) => p.score),\n    bins,\n    compositeWithIds,\n  )\n\n  const perDimension = computePerDimension(runs, bins)\n  const { execution, costProvenance: provenance } = summarizeExecution({\n    runs,\n    histogramBins: bins,\n  })\n  const knownCostRuns = runs.filter((run) => run.costProvenance.kind !== 'uncaptured')\n  const costs = knownCostRuns.map((r) => r.costUsd).filter(isFiniteNumber)\n  const costDist = distributionOf(costs, bins)\n  const pareto = paretoChart(knownCostRuns, { split })\n  const degraded: { cost?: string; pareto?: string } = {}\n  if (provenance.uncaptured.n > 0) {\n    degraded.cost = diagnoseCostCoverage(runs, provenance)\n  } else if (costs.length === 0 || costs.every((c) => c === 0)) {\n    degraded.cost = `all ${runs.length} explicitly observed or estimated USD values are $0`\n  }\n  if (pareto.points.length < 2) {\n    degraded.pareto =\n      pareto.points.length === 0\n        ? 'no candidates — Pareto unavailable'\n        : 'single candidate — Pareto is a single point, not a frontier'\n  }\n  const costQuality = {\n    cost: costDist,\n    pareto,\n    provenance,\n    ...(degraded.cost || degraded.pareto ? { degraded } : {}),\n  }\n\n  const judges = computeJudgeInsights(runs)\n\n  const interRater = opts.raterScores ? computeInterRater(opts.raterScores) : undefined\n\n  const lift = computeLift(runs, opts.baselineCandidateId, opts.candidateCandidateId, split)\n\n  const failureClusters = opts.analyst\n    ? await computeFailureClusters(runs, opts.analyst, split)\n    : undefined\n\n  const failureClasses = computeFailureClasses(runs, split)\n\n  const contamination = opts.canaryScenarios\n    ? computeContamination(runs, opts.canaryScenarios)\n    : undefined\n\n  const outcomeCorrelation = opts.outcomeSignal\n    ? computeOutcomeCorrelation(runs, opts.outcomeSignal, split)\n    : undefined\n\n  const release = buildReleaseScorecard(composite, lift, contamination)\n\n  const priorPeriodComparison = opts.baselineRuns\n    ? computePriorPeriodComparison(runs, opts.baselineRuns, split, opts.baselineLabel)\n    : undefined\n\n  const recommendations = buildRecommendations({\n    composite,\n    judges,\n    interRater,\n    lift,\n    failureClusters,\n    failureClasses,\n    contamination,\n    outcomeCorrelation,\n    priorPeriodComparison,\n    threshold,\n  })\n\n  return {\n    n: runs.length,\n    execution,\n    composite,\n    perDimension,\n    costQuality,\n    judges,\n    interRater,\n    lift,\n    failureClusters,\n    contamination,\n    outcomeCorrelation,\n    release,\n    ...(failureClasses ? { failureClasses } : {}),\n    ...(priorPeriodComparison ? { priorPeriodComparison } : {}),\n    recommendations,\n  }\n}\n\nfunction computeExecutionInsight(runs: RunRecord[], bins: number): ExecutionInsight {\n  const aggregateRows = runs.flatMap((run) => {\n    const usage = aggregateTokenUsage(run)\n    return usage ? [{ usage, costUsd: finiteRaw(run, 'aggregate_cost_usd') }] : []\n  })\n  const aggregateCosts = aggregateRows.flatMap((row) =>\n    row.costUsd !== undefined ? [row.costUsd] : [],\n  )\n  const modelCounts = new Map<string, number>()\n  let executionErrorRuns = 0\n  let executionErrorEvents = 0\n  let errorReportingRuns = 0\n  let errorSpanEvents = 0\n  let errorSpanReportingRuns = 0\n  const terminalOutcomes: Record<RunTerminalOutcome, number> = {\n    succeeded: 0,\n    failed: 0,\n    cancelled: 0,\n    incomplete: 0,\n    unknown: 0,\n  }\n  const errorsByTerminalOutcome: ExecutionInsight['executionErrors']['byTerminalOutcome'] = {\n    succeeded: { withErrors: 0, withoutErrors: 0, unreported: 0 },\n    failed: { withErrors: 0, withoutErrors: 0, unreported: 0 },\n    cancelled: { withErrors: 0, withoutErrors: 0, unreported: 0 },\n    incomplete: { withErrors: 0, withoutErrors: 0, unreported: 0 },\n    unknown: { withErrors: 0, withoutErrors: 0, unreported: 0 },\n  }\n  let modelCallRuns = 0\n  let modelCallEvents = 0\n  let modelCallReportingRuns = 0\n\n  for (const run of runs) {\n    modelCounts.set(run.model, (modelCounts.get(run.model) ?? 0) + 1)\n    const terminalOutcome = run.terminalOutcome\n    terminalOutcomes[terminalOutcome] += 1\n    const modelCalls = nonNegativeCountRaw(run, 'llm_span_count')\n    if (modelCalls !== undefined) {\n      modelCallEvents += modelCalls\n      modelCallReportingRuns += 1\n    }\n    const usage = run.tokenUsage\n    if (\n      (modelCalls ?? 0) > 0 ||\n      usage.input > 0 ||\n      usage.output > 0 ||\n      (usage.cached ?? 0) > 0 ||\n      (usage.cacheWrite ?? 0) > 0\n    ) {\n      modelCallRuns += 1\n    }\n    const errorEvents = reportedExecutionErrorEvents(run)\n    if (errorEvents !== undefined) {\n      executionErrorEvents += errorEvents\n      errorReportingRuns += 1\n      if (errorEvents > 0) {\n        executionErrorRuns += 1\n        errorsByTerminalOutcome[terminalOutcome].withErrors += 1\n      } else errorsByTerminalOutcome[terminalOutcome].withoutErrors += 1\n    } else errorsByTerminalOutcome[terminalOutcome].unreported += 1\n    const reportedErrorSpans = nonNegativeCountRaw(run, 'error_span_count')\n    if (reportedErrorSpans !== undefined) {\n      errorSpanEvents += reportedErrorSpans\n      errorSpanReportingRuns += 1\n    }\n  }\n\n  return {\n    durationMs: distributionOf(\n      runs.map((run) => run.wallMs),\n      bins,\n    ),\n    queueMs: distributionOf(\n      runs.filter((run) => run.queueMs !== undefined).map((run) => run.queueMs!),\n      bins,\n    ),\n    tokenUsage: summarizeTokenUsage(\n      runs.map((run) => run.tokenUsage),\n      bins,\n    ),\n    aggregateUsage: {\n      runs: aggregateRows.length,\n      tokenUsage: summarizeTokenUsage(\n        aggregateRows.map((row) => row.usage),\n        bins,\n      ),\n      costUsd: distributionOf(aggregateCosts, bins),\n      totalCostUsd: aggregateCosts.reduce((total, value) => total + value, 0),\n    },\n    models: [...modelCounts.entries()]\n      .map(([model, count]) => ({ model, runs: count }))\n      .sort((left, right) => right.runs - left.runs || left.model.localeCompare(right.model)),\n    modelCalls: {\n      runs: modelCallRuns,\n      events: modelCallEvents,\n      reportingRuns: modelCallReportingRuns,\n    },\n    executionErrors: {\n      runs: executionErrorRuns,\n      fraction: errorReportingRuns > 0 ? executionErrorRuns / errorReportingRuns : null,\n      events: executionErrorEvents,\n      reportingRuns: errorReportingRuns,\n      errorSpanEvents,\n      errorSpanReportingRuns,\n      byTerminalOutcome: errorsByTerminalOutcome,\n    },\n    terminalOutcomes,\n  }\n}\n\nfunction reportedExecutionErrorEvents(run: RunRecord): number | undefined {\n  return nonNegativeCountRaw(run, 'execution_error_count')\n}\n\nfunction nonNegativeCountRaw(run: RunRecord, key: string): number | undefined {\n  const value = finiteRaw(run, key)\n  return value !== undefined && Number.isInteger(value) && value >= 0 ? value : undefined\n}\n\nfunction summarizeTokenUsage(usages: RunTokenUsage[], bins: number): TokenUsageInsight {\n  const reasoning = usages.flatMap((usage) =>\n    usage.reasoning !== undefined ? [usage.reasoning] : [],\n  )\n  const cached = usages.flatMap((usage) => (usage.cached !== undefined ? [usage.cached] : []))\n  const cacheWrite = usages.flatMap((usage) =>\n    usage.cacheWrite !== undefined ? [usage.cacheWrite] : [],\n  )\n  return {\n    input: distributionOf(\n      usages.map((usage) => usage.input),\n      bins,\n    ),\n    output: distributionOf(\n      usages.map((usage) => usage.output),\n      bins,\n    ),\n    reasoning: distributionOf(reasoning, bins),\n    cached: distributionOf(cached, bins),\n    cacheWrite: distributionOf(cacheWrite, bins),\n    totals: {\n      input: usages.reduce((total, usage) => total + usage.input, 0),\n      output: usages.reduce((total, usage) => total + usage.output, 0),\n      reasoning: reasoning.reduce((total, value) => total + value, 0),\n      cached: cached.reduce((total, value) => total + value, 0),\n      cacheWrite: cacheWrite.reduce((total, value) => total + value, 0),\n    },\n  }\n}\n\nfunction aggregateTokenUsage(run: RunRecord): RunTokenUsage | undefined {\n  const input = finiteRaw(run, 'aggregate_prompt_tokens')\n  const output = finiteRaw(run, 'aggregate_completion_tokens')\n  const reasoning = finiteRaw(run, 'aggregate_reasoning_tokens')\n  const cached = finiteRaw(run, 'aggregate_cached_tokens')\n  const cacheWrite = finiteRaw(run, 'aggregate_cache_write_tokens')\n  if (\n    input === undefined &&\n    output === undefined &&\n    reasoning === undefined &&\n    cached === undefined &&\n    cacheWrite === undefined\n  )\n    return undefined\n  return {\n    input: input ?? 0,\n    output: output ?? 0,\n    ...(reasoning !== undefined ? { reasoning } : {}),\n    ...(cached !== undefined ? { cached } : {}),\n    ...(cacheWrite !== undefined ? { cacheWrite } : {}),\n  }\n}\n\nfunction finiteRaw(run: RunRecord, key: string): number | undefined {\n  const value = run.outcome.raw[key]\n  return typeof value === 'number' && Number.isFinite(value) && value >= 0 ? value : undefined\n}\n\nfunction summarizeCostProvenance(runs: RunRecord[]): CostProvenanceSummary {\n  const summary: CostProvenanceSummary = {\n    observed: { n: 0, totalUsd: 0 },\n    estimated: { n: 0, totalUsd: 0 },\n    uncaptured: { n: 0 },\n    knownFraction: 0,\n  }\n  for (const run of runs) {\n    const cost = run.costProvenance\n    if (cost.kind === 'uncaptured') {\n      summary.uncaptured.n += 1\n    } else {\n      summary[cost.kind].n += 1\n      summary[cost.kind].totalUsd += cost.usd\n    }\n  }\n  const known = summary.observed.n + summary.estimated.n\n  summary.knownFraction = runs.length > 0 ? known / runs.length : 0\n  return summary\n}\n\nfunction diagnoseCostCoverage(runs: RunRecord[], provenance: CostProvenanceSummary): string {\n  const uncaptured = provenance.uncaptured.n\n  const known = provenance.observed.n + provenance.estimated.n\n  if (uncaptured === runs.length) {\n    return `USD cost uncaptured for all ${runs.length} runs — no observed or estimated USD values; token and wall-time metrics remain available.`\n  }\n  return `USD cost uncaptured for ${uncaptured}/${runs.length} runs; excluded those rows from cost statistics (${known}/${runs.length} retained: ${provenance.observed.n} observed, ${provenance.estimated.n} estimated).`\n}\n\n/**\n * Model-free task-failure tally.\n *\n * Explicit non-success classes are task-failure evidence.\n * A low task score without a class is counted as `unknown`.\n */\nfunction computeFailureClasses(\n  runs: RunRecord[],\n  split: 'search' | 'holdout',\n): FailureClassTally[] | undefined {\n  const counts = new Map<FailureClass, number>()\n  for (const r of runs) {\n    if (!isTaskFailure(r, split)) continue\n    const key =\n      r.failureClass !== undefined && r.failureClass !== 'success' ? r.failureClass : 'unknown'\n    counts.set(key, (counts.get(key) ?? 0) + 1)\n  }\n  if (counts.size === 0) return undefined\n  const n = runs.length\n  return [...counts.entries()]\n    .map(([failureClass, count]) => ({\n      failureClass,\n      count,\n      share: n > 0 ? count / n : 0,\n    }))\n    .sort((a, b) => b.count - a.count || a.failureClass.localeCompare(b.failureClass))\n}\n\n// ── Prior-period comparison ─────────────────────────────────────────\n\n/** Direction of the metric — does \"higher current\" mean better or worse?\n *  Composite + judge dimensions: higher is better. Cost + duration: lower\n *  is better. The recommendations engine flips the sign before judging\n *  regressed vs improved. */\ntype MetricDirection = 'higher-is-better' | 'lower-is-better'\n\nfunction computePriorPeriodComparison(\n  current: RunRecord[],\n  baseline: RunRecord[],\n  split: 'search' | 'holdout',\n  windowLabel: string | undefined,\n): PriorPeriodComparison | undefined {\n  if (current.length === 0 || baseline.length === 0) return undefined\n\n  const metrics: Record<string, MetricDelta> = {}\n  const directions: Record<string, MetricDirection> = {}\n\n  const compositeCurrent = current\n    .map((r) => compositeOf(r, split))\n    .filter(Number.isFinite) as number[]\n  const compositeBaseline = baseline\n    .map((r) => compositeOf(r, split))\n    .filter(Number.isFinite) as number[]\n  if (compositeCurrent.length > 0 && compositeBaseline.length > 0) {\n    metrics.composite = welchCompare(compositeBaseline, compositeCurrent)\n    directions.composite = 'higher-is-better'\n  }\n\n  const costCurrent = knownCostValues(current)\n  const costBaseline = knownCostValues(baseline)\n  if (costCurrent.length > 0 && costBaseline.length > 0) {\n    metrics.cost = welchCompare(costBaseline, costCurrent)\n    directions.cost = 'lower-is-better'\n  }\n\n  const durCurrent = current.map((r) => r.wallMs).filter(Number.isFinite)\n  const durBaseline = baseline.map((r) => r.wallMs).filter(Number.isFinite)\n  if (durCurrent.length > 0 && durBaseline.length > 0) {\n    metrics.duration = welchCompare(durBaseline, durCurrent)\n    directions.duration = 'lower-is-better'\n  }\n\n  const tokCurrent = current\n    .map((r) => (r.tokenUsage.input ?? 0) + (r.tokenUsage.output ?? 0))\n    .filter(Number.isFinite)\n  const tokBaseline = baseline\n    .map((r) => (r.tokenUsage.input ?? 0) + (r.tokenUsage.output ?? 0))\n    .filter(Number.isFinite)\n  if (tokCurrent.length > 0 && tokBaseline.length > 0) {\n    metrics.tokenUsage = welchCompare(tokBaseline, tokCurrent)\n    directions.tokenUsage = 'lower-is-better'\n  }\n\n  // Per-dimension judge comparisons — only for dimensions present in BOTH\n  // windows. We use perDimMean since per-judge nesting is finicky for\n  // two-sample comparisons across different judge configurations.\n  const dimsCurrent = collectPerDimension(current)\n  const dimsBaseline = collectPerDimension(baseline)\n  for (const dim of Object.keys(dimsCurrent)) {\n    const b = dimsBaseline[dim]\n    const c = dimsCurrent[dim]\n    if (!b || b.length === 0 || !c || c.length === 0) continue\n    metrics[`dim.${dim}`] = welchCompare(b, c)\n    directions[`dim.${dim}`] = 'higher-is-better'\n  }\n\n  const regressedMetrics: string[] = []\n  const improvedMetrics: string[] = []\n  for (const [name, delta] of Object.entries(metrics)) {\n    if (!delta.significant) continue\n    const dir = directions[name] ?? 'higher-is-better'\n    const better = dir === 'higher-is-better' ? delta.delta > 0 : delta.delta < 0\n    if (better) improvedMetrics.push(name)\n    else regressedMetrics.push(name)\n  }\n\n  return {\n    baselineN: baseline.length,\n    currentN: current.length,\n    ...(windowLabel ? { windowLabel } : {}),\n    metrics,\n    regressedMetrics,\n    improvedMetrics,\n  }\n}\n\nfunction knownCostValues(runs: RunRecord[]): number[] {\n  return runs\n    .filter((run) => run.costProvenance.kind !== 'uncaptured')\n    .map((run) => run.costUsd)\n    .filter(isFiniteNumber)\n}\n\nfunction isFiniteNumber(value: unknown): value is number {\n  return typeof value === 'number' && Number.isFinite(value)\n}\n\n/** Collect per-dimension values across runs (from outcome.judgeScores.perDimMean). */\nfunction collectPerDimension(runs: RunRecord[]): Record<string, number[]> {\n  const out: Record<string, number[]> = {}\n  for (const r of runs) {\n    const perDim = r.outcome.judgeScores?.perDimMean\n    if (!perDim) continue\n    for (const [dim, value] of Object.entries(perDim)) {\n      if (!Number.isFinite(value)) continue\n      if (!out[dim]) out[dim] = []\n      out[dim].push(value as number)\n    }\n  }\n  return out\n}\n\n/** Two-sample Welch comparison: unequal-variance t-test + CI on the delta\n *  + Cohen's d (pooled stddev). Significance = p < 0.05 AND |d| >= 0.2. */\nfunction welchCompare(baseline: number[], current: number[]): MetricDelta {\n  const baselineMean = mean(baseline)\n  const currentMean = mean(current)\n  const baselineVar = sampleVariance(baseline, baselineMean)\n  const currentVar = sampleVariance(current, currentMean)\n  const baselineN = baseline.length\n  const currentN = current.length\n  const delta = currentMean - baselineMean\n\n  // Welch standard error\n  const se = Math.sqrt(baselineVar / baselineN + currentVar / currentN)\n  // For 95% CI we use z=1.96 (large-n approximation). Customers running\n  // analyzeRuns will typically have n >= 30; the t-correction is\n  // negligible vs the practical noise floor.\n  const halfWidth = 1.96 * (se > 0 ? se : 0)\n  const ci95: [number, number] = [delta - halfWidth, delta + halfWidth]\n\n  // p-value via normal approximation to the t-statistic.\n  const t = se > 0 ? delta / se : 0\n  const pValue = se > 0 ? 2 * (1 - standardNormalCdf(Math.abs(t))) : 1\n\n  // Cohen's d — pooled stddev.\n  const pooledStddev = Math.sqrt(\n    ((baselineN - 1) * baselineVar + (currentN - 1) * currentVar) /\n      Math.max(1, baselineN + currentN - 2),\n  )\n  const cohensD = pooledStddev > 0 ? delta / pooledStddev : 0\n\n  // Significance: BOTH p < 0.05 AND |d| >= 0.2 (small-effect threshold).\n  const significant = pValue < 0.05 && Math.abs(cohensD) >= 0.2\n\n  return {\n    current: currentMean,\n    baseline: baselineMean,\n    delta,\n    ci95,\n    pValue,\n    cohensD,\n    baselineN,\n    currentN,\n    significant,\n  }\n}\n\nfunction sampleVariance(xs: number[], xsMean: number): number {\n  if (xs.length < 2) return 0\n  let s = 0\n  for (const x of xs) s += (x - xsMean) ** 2\n  return s / (xs.length - 1)\n}\n\n/** Abramowitz & Stegun approximation to Φ(z). Maximum error ~7.5e-8. */\nfunction standardNormalCdf(z: number): number {\n  const a1 = 0.254829592\n  const a2 = -0.284496736\n  const a3 = 1.421413741\n  const a4 = -1.453152027\n  const a5 = 1.061405429\n  const p = 0.3275911\n  const sign = z < 0 ? -1 : 1\n  const x = Math.abs(z) / Math.SQRT2\n  const t = 1 / (1 + p * x)\n  const y = 1 - ((((a5 * t + a4) * t + a3) * t + a2) * t + a1) * t * Math.exp(-x * x)\n  return 0.5 * (1 + sign * y)\n}\n\n// ── Composite + split selection ─────────────────────────────────────\n\nfunction resolveSplit(\n  runs: RunRecord[],\n  pref: 'search' | 'holdout' | 'auto',\n): 'search' | 'holdout' {\n  if (pref !== 'auto') return pref\n  const hasHoldout = runs.some((r) => Number.isFinite(observedSplitScore(r, 'holdout')))\n  return hasHoldout ? 'holdout' : 'search'\n}\n\n/**\n * RAW (`observedSplitScore`): `analyzeRuns` describes what a set of runs\n * reported, and every downstream reader of this composite — distributions,\n * per-candidate summaries, the reward-hacking correlation — needs the ungated\n * number to see an inflated run at all.\n */\nfunction compositeOf(run: RunRecord, split: 'search' | 'holdout'): number {\n  // Split-exact, no cross-split fallthrough: answering \"what did this run\n  // score on the split I am summarising\" with the other split's number\n  // silently mixes populations.\n  const score = observedSplitScore(run, split)\n  return Number.isFinite(score) ? (score as number) : Number.NaN\n}\n\n// ── Distribution helpers ────────────────────────────────────────────\n\nfunction distributionOf(\n  values: number[],\n  bins: number,\n  withIds?: Array<{ runId: string; score: number }>,\n): ScalarDistribution {\n  if (values.length === 0) {\n    return {\n      n: 0,\n      mean: null,\n      p50: null,\n      p95: null,\n      stddev: null,\n      min: null,\n      max: null,\n      histogram: [],\n    }\n  }\n  const sorted = [...values].sort((a, b) => a - b)\n  const n = sorted.length\n  const mean = sorted.reduce((s, v) => s + v, 0) / n\n  const variance = sorted.reduce((s, v) => s + (v - mean) ** 2, 0) / n\n  const stddev = Math.sqrt(variance)\n  const tailRuns = withIds\n    ? [...withIds].sort((a, b) => a.score - b.score).slice(0, Math.min(5, withIds.length))\n    : undefined\n  return {\n    n,\n    mean,\n    p50: percentile(sorted, 0.5),\n    p95: percentile(sorted, 0.95),\n    stddev,\n    min: sorted[0]!,\n    max: sorted[n - 1]!,\n    histogram: histogram(sorted, bins),\n    ...(tailRuns ? { tailRuns } : {}),\n  }\n}\n\nfunction percentile(sorted: number[], q: number): number {\n  if (sorted.length === 0) return 0\n  if (sorted.length === 1) return sorted[0]!\n  const idx = (sorted.length - 1) * q\n  const lo = Math.floor(idx)\n  const hi = Math.ceil(idx)\n  if (lo === hi) return sorted[lo]!\n  const w = idx - lo\n  return sorted[lo]! * (1 - w) + sorted[hi]! * w\n}\n\n/** Even-width histogram over the value range. Returns inclusive-lo /\n *  exclusive-hi bins (closed on right for the last bin) compatible with\n *  the substrate's `GainDistributionBin` shape. */\nfunction histogram(sorted: number[], bins: number): ScalarDistribution['histogram'] {\n  if (sorted.length === 0 || bins < 1) return []\n  const min = sorted[0]!\n  const max = sorted[sorted.length - 1]!\n  if (min === max) return [{ lo: min, hi: max, count: sorted.length }]\n  const width = (max - min) / bins\n  const out: ScalarDistribution['histogram'] = []\n  for (let i = 0; i < bins; i++) {\n    const lo = min + i * width\n    const hi = i === bins - 1 ? max : lo + width\n    out.push({ lo, hi, count: 0 })\n  }\n  for (const v of sorted) {\n    const idx = Math.min(bins - 1, Math.floor((v - min) / width))\n    out[idx]!.count++\n  }\n  return out\n}\n\nfunction computePerDimension(runs: RunRecord[], bins: number): Record<string, ScalarDistribution> {\n  // JudgeScoresRecord pre-aggregates `perDimMean` (mean across judges per\n  // dimension). We collect those means across runs to produce a per-dim\n  // distribution at the corpus level. Consumers who want per-judge\n  // dimension values reach into `perJudge[judgeId][dim]` themselves.\n  const byDim = new Map<string, number[]>()\n  for (const run of runs) {\n    const scores = run.outcome.judgeScores\n    if (!scores) continue\n    for (const [dim, value] of Object.entries(scores.perDimMean ?? {})) {\n      if (!Number.isFinite(value)) continue\n      const arr = byDim.get(dim) ?? []\n      arr.push(value)\n      byDim.set(dim, arr)\n    }\n  }\n  const out: Record<string, ScalarDistribution> = {}\n  for (const [dim, values] of byDim) out[dim] = distributionOf(values, bins)\n  return out\n}\n\n// ── Judge insights ──────────────────────────────────────────────────\n\nfunction computeJudgeInsights(runs: RunRecord[]): Record<string, JudgeInsight> {\n  // Each judge's per-run mean is the average of its per-dimension scores\n  // for that run. We aggregate those means across all runs each judge\n  // scored — giving consumers a \"this judge's typical verdict\" reading.\n  const out: Record<string, JudgeInsight> = {}\n  const byJudge = new Map<string, number[]>()\n  for (const run of runs) {\n    const scores = run.outcome.judgeScores\n    if (!scores?.perJudge) continue\n    for (const [judgeId, dims] of Object.entries(scores.perJudge)) {\n      const dimValues = Object.values(dims).filter(Number.isFinite) as number[]\n      if (dimValues.length === 0) continue\n      const judgeMean = dimValues.reduce((s, v) => s + v, 0) / dimValues.length\n      const arr = byJudge.get(judgeId) ?? []\n      arr.push(judgeMean)\n      byJudge.set(judgeId, arr)\n    }\n  }\n  for (const [judgeId, values] of byJudge) {\n    out[judgeId] = {\n      n: values.length,\n      meanScore: values.reduce((s, v) => s + v, 0) / values.length,\n    }\n  }\n  return out\n}\n\n// ── Inter-rater agreement ───────────────────────────────────────────\n\nfunction computeInterRater(\n  ratings: Array<{ runId: string; rater: string; score: number }>,\n): InterRaterInsight | undefined {\n  const byRun = new Map<string, Array<{ rater: string; score: number }>>()\n  for (const r of ratings) {\n    if (!Number.isFinite(r.score)) continue\n    const list = byRun.get(r.runId) ?? []\n    list.push({ rater: r.rater, score: r.score })\n    byRun.set(r.runId, list)\n  }\n  const raters = new Set(ratings.map((r) => r.rater))\n  const jointlyRated: string[] = []\n  for (const [runId, ratersForRun] of byRun) {\n    const seen = new Set(ratersForRun.map((r) => r.rater))\n    let all = true\n    for (const r of raters) if (!seen.has(r)) all = false\n    if (all) jointlyRated.push(runId)\n  }\n  if (raters.size < 2 || jointlyRated.length === 0) return undefined\n\n  const raterList = [...raters].sort()\n  const perPair: Record<string, number> = {}\n  for (let i = 0; i < raterList.length; i++) {\n    for (let j = i + 1; j < raterList.length; j++) {\n      const a = raterList[i]!\n      const b = raterList[j]!\n      const aScores: number[] = []\n      const bScores: number[] = []\n      for (const runId of jointlyRated) {\n        const ratersForRun = byRun.get(runId)!\n        const sa = ratersForRun.find((r) => r.rater === a)?.score\n        const sb = ratersForRun.find((r) => r.rater === b)?.score\n        if (sa !== undefined && sb !== undefined) {\n          aScores.push(sa)\n          bScores.push(sb)\n        }\n      }\n      const agreement = continuousAgreement(\n        aScores.map((score, index) => [score, bScores[index]!]),\n        { bootstrap: 0 },\n      )\n      perPair[`${a}::${b}`] = agreement.weightedKappa\n    }\n  }\n  const matrix = jointlyRated.map((runId) => {\n    const ratingsByRater = new Map(byRun.get(runId)!.map((rating) => [rating.rater, rating.score]))\n    return raterList.map((rater) => ratingsByRater.get(rater)!)\n  })\n  const agreement = continuousAgreement(matrix, { bootstrap: 0 })\n\n  const disagreementCases = jointlyRated\n    .map((runId) => {\n      const ratersForRun = byRun.get(runId)!\n      const scores = ratersForRun.map((r) => r.score)\n      const range = Math.max(...scores) - Math.min(...scores)\n      return { runId, ratings: ratersForRun, range }\n    })\n    .sort((a, b) => b.range - a.range)\n    .slice(0, 20)\n\n  return {\n    raters: raters.size,\n    jointlyRated: jointlyRated.length,\n    kappa: Number.isFinite(agreement.weightedKappa) ? agreement.weightedKappa : 0,\n    icc: agreement.icc,\n    pearson: agreement.pearson,\n    spearman: agreement.spearman,\n    perPair,\n    disagreementCases,\n  }\n}\n\n// ── Lift ────────────────────────────────────────────────────────────\n\nfunction computeLift(\n  runs: RunRecord[],\n  baselineId: string | undefined,\n  candidateId: string | undefined,\n  split: 'search' | 'holdout',\n): LiftInsight | undefined {\n  let bId = baselineId\n  let cId = candidateId\n  if (!bId || !cId) {\n    // Auto-detect: when exactly two distinct candidateIds appear, treat the\n    // lower-mean side as baseline.\n    const ids = [...new Set(runs.map((r) => r.candidateId))]\n    if (ids.length !== 2) return undefined\n    const [idA, idB] = ids as [string, string]\n    const scoresA = finiteCompositeScores(\n      runs.filter((run) => run.candidateId === idA),\n      split,\n    )\n    const scoresB = finiteCompositeScores(\n      runs.filter((run) => run.candidateId === idB),\n      split,\n    )\n    if (scoresA.length === 0 || scoresB.length === 0) return undefined\n    const meanA = mean(scoresA)\n    const meanB = mean(scoresB)\n    bId = meanA <= meanB ? idA : idB\n    cId = meanA <= meanB ? idB : idA\n  }\n\n  const baseline = runs.filter((r) => r.candidateId === bId)\n  const candidate = runs.filter((r) => r.candidateId === cId)\n  if (baseline.length === 0 || candidate.length === 0) return undefined\n\n  const scoredBaseline = baseline.filter((run) => Number.isFinite(compositeOf(run, split)))\n  const scoredCandidate = candidate.filter((run) => Number.isFinite(compositeOf(run, split)))\n  const pairing = pairRunRecords(scoredBaseline, scoredCandidate)\n  const pairedBaseline = pairing.pairs.map((pair) => compositeOf(pair.baseline, split))\n  const pairedCandidate = pairing.pairs.map((pair) => compositeOf(pair.treatment, split))\n  if (pairedBaseline.length === 0) return undefined\n\n  const baselineMean = mean(pairedBaseline)\n  const candidateMean = mean(pairedCandidate)\n  const delta = candidateMean - baselineMean\n\n  const bootstrap = pairedBootstrap(pairedBaseline, pairedCandidate, {\n    confidence: 0.95,\n    resamples: 2000,\n    statistic: 'mean',\n  })\n  const tTest = pairedTTest(pairedBaseline, pairedCandidate)\n  const d = pairedCohensDz(pairedBaseline, pairedCandidate)\n  const mde = pairedMde({ nPaired: pairedBaseline.length, power: 0.8, alpha: 0.05 })\n  const requiredN =\n    d === null || d === 0\n      ? null\n      : requiredPairedSampleSize({\n          effect: Math.abs(d),\n          power: 0.8,\n          alpha: 0.05,\n        })\n\n  return {\n    baselineMean,\n    candidateMean,\n    delta,\n    ci95: [bootstrap.low, bootstrap.high],\n    pValue: tTest.p,\n    n: pairedBaseline.length,\n    unpairedBaseline: pairing.unpairedBaseline.length,\n    unpairedCandidate: pairing.unpairedTreatment.length,\n    cohensD: d,\n    mde,\n    requiredN,\n  }\n}\n\nfunction mean(arr: number[]): number {\n  return arr.length === 0 ? 0 : arr.reduce((s, v) => s + v, 0) / arr.length\n}\n\n// ── Failure clustering ──────────────────────────────────────────────\n\nasync function computeFailureClusters(\n  runs: RunRecord[],\n  analyst: AnalystRegistry,\n  split: 'search' | 'holdout',\n): Promise<FailureClusterInsight | undefined> {\n  const failed = runs.filter((run) => isTaskFailure(run, split))\n  if (failed.length === 0) return { clusters: [], totalFailures: 0 }\n\n  const clusters = new Map<string, { exemplars: string[]; share: number }>()\n  for (const run of failed) {\n    try {\n      // AnalystRunInputs routes by field name: run-record analysts read\n      // `runRecord`. Any other shape makes every analyst skip with\n      // \"missing input\" and the clusters come back silently empty.\n      const result = await analyst.run(run.runId, { runRecord: run })\n      for (const finding of result.findings as AnalystFinding[]) {\n        const key = finding.area || finding.analyst_id || 'unclassified'\n        const c = clusters.get(key) ?? { exemplars: [], share: 0 }\n        if (c.exemplars.length < 5) c.exemplars.push(run.runId)\n        clusters.set(key, c)\n      }\n    } catch {\n      const c = clusters.get('analyst-error') ?? { exemplars: [], share: 0 }\n      if (c.exemplars.length < 5) c.exemplars.push(run.runId)\n      clusters.set('analyst-error', c)\n    }\n  }\n  const clusterList = [...clusters.entries()].map(([id, c]) => ({\n    id,\n    name: id,\n    share: c.exemplars.length / failed.length,\n    exemplars: c.exemplars,\n  }))\n  clusterList.sort((a, b) => b.share - a.share)\n  return { clusters: clusterList, totalFailures: failed.length }\n}\n\nfunction finiteCompositeScores(runs: readonly RunRecord[], split: 'search' | 'holdout'): number[] {\n  return runs.map((run) => compositeOf(run, split)).filter(Number.isFinite)\n}\n\nfunction isTaskFailure(run: RunRecord, split: 'search' | 'holdout'): boolean {\n  if (run.failureClass !== undefined && run.failureClass !== 'success') return true\n  const score = compositeOf(run, split)\n  return Number.isFinite(score) && score < 0.5\n}\n\n// ── Contamination ──────────────────────────────────────────────────\n\nfunction computeContamination(\n  runs: RunRecord[],\n  canaries: DatasetScenario[],\n): InsightReport['contamination'] {\n  let leaks = 0\n  const details: Array<{ runId: string; canary: string; matched: string }> = []\n  for (const run of runs) {\n    const output = stringifyOutput(run)\n    if (!output) continue\n    const leaksHere = checkCanaries(output, canaries)\n    for (const leak of leaksHere) {\n      leaks++\n      details.push({ runId: run.runId, canary: leak.canary, matched: leak.evidence })\n    }\n  }\n  return { leaks, holdoutAuditPassed: leaks === 0, details }\n}\n\nfunction stringifyOutput(run: RunRecord): string | undefined {\n  // RunRecord doesn't fix where \"the agent's output\" lives — different\n  // consumers stash it differently. We probe the common shapes: the\n  // outcome.raw map (numeric only by design — unlikely to contain text),\n  // and any string-valued fields tucked under metadata via type casting.\n  // Consumers with bespoke shapes pass canaryScenarios only when they\n  // know their runs carry a stringifiable surface.\n  const metadata = (run as unknown as { metadata?: Record<string, unknown> }).metadata\n  if (typeof metadata?.output === 'string') return metadata.output\n  if (typeof metadata?.text === 'string') return metadata.text\n  return undefined\n}\n\n// ── Outcome correlation + linear reward model ──────────────────────\n\nfunction computeOutcomeCorrelation(\n  runs: RunRecord[],\n  outcome: { metric: string; valueByRunId: Record<string, number> },\n  split: 'search' | 'holdout',\n): OutcomeCorrelationInsight | undefined {\n  const xs: number[] = []\n  const ys: number[] = []\n  for (const run of runs) {\n    const y = outcome.valueByRunId[run.runId]\n    if (y === undefined || !Number.isFinite(y)) continue\n    const x = compositeOf(run, split)\n    if (!Number.isFinite(x)) continue\n    xs.push(x)\n    ys.push(y)\n  }\n  if (xs.length < 3) return undefined\n\n  const p = pearsonR(xs, ys)\n  const s = spearmanR(xs, ys)\n  const meanX = mean(xs)\n  const meanY = mean(ys)\n  let num = 0\n  let denom = 0\n  for (let i = 0; i < xs.length; i++) {\n    num += (xs[i]! - meanX) * (ys[i]! - meanY)\n    denom += (xs[i]! - meanX) ** 2\n  }\n  const slope = denom === 0 ? 0 : num / denom\n  const intercept = meanY - slope * meanX\n  const ssTot = ys.reduce((a, y) => a + (y - meanY) ** 2, 0)\n  const ssRes = ys.reduce((a, y, i) => a + (y - (intercept + slope * xs[i]!)) ** 2, 0)\n  const r2 = ssTot === 0 ? 0 : 1 - ssRes / ssTot\n\n  return {\n    metric: outcome.metric,\n    n: xs.length,\n    pearson: p,\n    spearman: s,\n    rewardModel: { intercept, slope, r2 },\n  }\n}\n\n// ── Release confidence scorecard ───────────────────────────────────\n\nfunction buildReleaseScorecard(\n  composite: ScalarDistribution,\n  lift: LiftInsight | undefined,\n  contamination: InsightReport['contamination'],\n): InsightReport['release'] {\n  // Synthesise a minimal scorecard from the rolled-up signal. The\n  // substrate's `evaluateReleaseConfidence` primitive consumes a richer\n  // input shape that callers can produce by wiring SLO definitions; the\n  // shape here is the contract `selfImprove`/`analyzeRuns` consumers\n  // receive automatically. They can call `evaluateReleaseConfidence`\n  // directly when they want SLO-based axis evaluation.\n  const axes: InsightReport['release']['axes'] = []\n  const liftPass =\n    lift === undefined\n      ? ('not_evaluated' as const)\n      : lift.ci95[0] > 0\n        ? ('pass' as const)\n        : lift.delta > 0\n          ? ('warn' as const)\n          : ('fail' as const)\n  axes.push({\n    name: 'quality-lift',\n    status: liftPass,\n    detail: lift\n      ? `delta=${lift.delta.toFixed(3)}, CI95=[${lift.ci95[0].toFixed(3)}, ${lift.ci95[1].toFixed(3)}], n=${lift.n}`\n      : 'no baseline/candidate pair available',\n  })\n  const contamPass =\n    contamination === undefined\n      ? ('not_evaluated' as const)\n      : contamination.leaks === 0\n        ? ('pass' as const)\n        : ('fail' as const)\n  axes.push({\n    name: 'contamination',\n    status: contamPass,\n    detail: contamination ? `${contamination.leaks} canary leak(s)` : 'no canaries supplied',\n  })\n  axes.push(\n    composite.n === 0\n      ? {\n          name: 'composite-distribution',\n          status: 'not_evaluated',\n          detail: 'no task-quality scores available',\n        }\n      : {\n          name: 'composite-distribution',\n          status:\n            composite.mean !== null && composite.mean >= 0.5\n              ? 'pass'\n              : composite.mean !== null && composite.mean >= 0.3\n                ? 'warn'\n                : 'fail',\n          detail:\n            composite.mean === null || composite.p50 === null || composite.p95 === null\n              ? 'task-quality distribution is internally incomplete'\n              : `mean=${composite.mean.toFixed(3)}, p50=${composite.p50.toFixed(3)}, p95=${composite.p95.toFixed(3)} over n=${composite.n}`,\n        },\n  )\n  const status = axes.some((a) => a.status === 'fail')\n    ? 'fail'\n    : axes.some((a) => a.status === 'warn' || a.status === 'not_evaluated')\n      ? 'warn'\n      : 'pass'\n  return {\n    status,\n    axes,\n    issues: [],\n  }\n}\n\n// ── Recommendations engine ─────────────────────────────────────────\n\ninterface RecommendationContext {\n  composite: ScalarDistribution\n  judges: Record<string, JudgeInsight>\n  interRater?: InterRaterInsight\n  lift?: LiftInsight\n  failureClusters?: FailureClusterInsight\n  failureClasses?: FailureClassTally[]\n  contamination?: InsightReport['contamination']\n  outcomeCorrelation?: OutcomeCorrelationInsight\n  priorPeriodComparison?: PriorPeriodComparison\n  threshold: number\n}\n\nfunction buildRecommendations(ctx: RecommendationContext): Recommendation[] {\n  const out: Recommendation[] = []\n\n  // Prior-period regressions — highest customer-impact signal when present.\n  // \"Did my last change help?\" with a falsifiable answer.\n  if (ctx.priorPeriodComparison) {\n    const ppc = ctx.priorPeriodComparison\n    const label = ppc.windowLabel ?? 'baseline period'\n    for (const name of ppc.regressedMetrics) {\n      const d = ppc.metrics[name]\n      if (!d) continue\n      out.push({\n        priority: 'critical',\n        kind: 'investigate',\n        title: `${name} regressed from ${d.baseline.toFixed(3)} → ${d.current.toFixed(3)} vs ${label}`,\n        detail: `Welch CI95 = [${d.ci95[0].toFixed(3)}, ${d.ci95[1].toFixed(3)}], p=${d.pValue.toFixed(4)}, Cohen's d=${d.cohensD.toFixed(2)} (n_current=${d.currentN}, n_baseline=${d.baselineN}). The regression is statistically significant at p<0.05 with at-least-small effect size.`,\n        evidencePath: `priorPeriodComparison.metrics.${name}`,\n      })\n    }\n    for (const name of ppc.improvedMetrics) {\n      const d = ppc.metrics[name]\n      if (!d) continue\n      out.push({\n        priority: 'low',\n        kind: 'ship',\n        title: `${name} improved from ${d.baseline.toFixed(3)} → ${d.current.toFixed(3)} vs ${label}`,\n        detail: `Welch CI95 = [${d.ci95[0].toFixed(3)}, ${d.ci95[1].toFixed(3)}], p=${d.pValue.toFixed(4)}, Cohen's d=${d.cohensD.toFixed(2)} (n_current=${d.currentN}, n_baseline=${d.baselineN}). Statistically significant improvement worth flagging.`,\n        evidencePath: `priorPeriodComparison.metrics.${name}`,\n      })\n    }\n  }\n\n  // Composite-distribution branch. Fires when the overall quality signal is\n  // poor regardless of lift / contamination / clusters — the customer needs\n  // to know they have a problem AND which specific runs to inspect.\n  if (\n    ctx.composite.n > 0 &&\n    ctx.composite.mean !== null &&\n    ctx.composite.p50 !== null &&\n    ctx.composite.p95 !== null\n  ) {\n    if (ctx.composite.mean < 0.3) {\n      const tail = ctx.composite.tailRuns ?? []\n      const names = tail\n        .slice(0, 5)\n        .map((t) => `${t.runId}=${t.score.toFixed(3)}`)\n        .join(', ')\n      out.push({\n        priority: 'critical',\n        kind: 'investigate',\n        title: `Composite mean ${ctx.composite.mean.toFixed(3)} is below the 0.3 floor — the agent is broken on this corpus`,\n        detail:\n          tail.length > 0\n            ? `Worst ${tail.length} run${tail.length === 1 ? '' : 's'} to inspect first: ${names}. Histogram p50=${ctx.composite.p50.toFixed(3)}, p95=${ctx.composite.p95.toFixed(3)}.`\n            : `Histogram p50=${ctx.composite.p50.toFixed(3)}, p95=${ctx.composite.p95.toFixed(3)}.`,\n        evidencePath: 'composite.tailRuns',\n      })\n    } else if (ctx.composite.mean < 0.5) {\n      const tail = ctx.composite.tailRuns ?? []\n      const names = tail\n        .slice(0, 3)\n        .map((t) => `${t.runId}=${t.score.toFixed(3)}`)\n        .join(', ')\n      out.push({\n        priority: 'high',\n        kind: 'investigate',\n        title: `Composite mean ${ctx.composite.mean.toFixed(3)} is below 0.5 — investigate the lower tail before claiming the agent is healthy`,\n        detail:\n          tail.length > 0\n            ? `Worst ${tail.length} run${tail.length === 1 ? '' : 's'}: ${names}. Histogram p50=${ctx.composite.p50.toFixed(3)}, p95=${ctx.composite.p95.toFixed(3)}.`\n            : `Histogram p50=${ctx.composite.p50.toFixed(3)}, p95=${ctx.composite.p95.toFixed(3)}.`,\n        evidencePath: 'composite.tailRuns',\n      })\n    }\n  }\n\n  // A healthy-looking mean can hide a group of failed tasks sharing one\n  // producer-reported cause. This path does not require an analyst.\n  if (ctx.failureClasses && ctx.failureClasses.length > 0) {\n    const top = ctx.failureClasses[0]!\n    if (top.count >= 3 && top.share >= 0.15) {\n      out.push({\n        priority: top.share >= 0.25 ? 'high' : 'medium',\n        kind: 'investigate',\n        title: `'${top.failureClass}' is the dominant failure class — ${top.count} runs (${(top.share * 100).toFixed(0)}% of the corpus)`,\n        detail: `The mean composite can look acceptable while one failure class dominates the lower tail. ${top.count} of ${ctx.composite.n} runs failed with '${top.failureClass}'${ctx.failureClasses.length > 1 ? ` (next: '${ctx.failureClasses[1]!.failureClass}' ×${ctx.failureClasses[1]!.count})` : ''}. Fix this cause first.`,\n        evidencePath: 'failureClasses',\n      })\n    }\n  }\n\n  // Missing-judges branch. The report can't surface per-dimension or\n  // calibration signal when `outcome.judgeScores` is empty across the\n  // corpus. Tell the customer how to enrich.\n  if (Object.keys(ctx.judges).length === 0 && ctx.composite.n > 0) {\n    out.push({\n      priority: 'medium',\n      kind: 'expand-corpus',\n      title: 'No judge scores recorded — per-dimension + calibration insights unavailable',\n      detail:\n        'Records have no `outcome.judgeScores`. To unlock perDimension, judges, and calibration, attach a Judge run during your eval pass and populate `outcome.judgeScores.perJudge[judgeName][dimension] = score`. See `docs/insight-report.md` for the expected shape.',\n      evidencePath: 'judges',\n    })\n  }\n\n  if (ctx.lift) {\n    const pairedEffect =\n      ctx.lift.cohensD === null ? 'undefined (zero delta variance)' : ctx.lift.cohensD.toFixed(2)\n    const requiredRuns =\n      ctx.lift.requiredN === null ? 'not estimable' : `~${ctx.lift.requiredN} paired runs`\n    const decisive = ctx.lift.ci95[0] > ctx.threshold\n    const inconclusive = ctx.lift.ci95[0] <= ctx.threshold && ctx.lift.ci95[1] > ctx.threshold\n    if (decisive) {\n      out.push({\n        priority: 'critical',\n        kind: 'ship',\n        title: `Ship — lift ${ctx.lift.delta.toFixed(3)} (95% CI ${ctx.lift.ci95[0].toFixed(3)}..${ctx.lift.ci95[1].toFixed(3)})`,\n        detail: `Holdout lift exceeds threshold ${ctx.threshold} with 95% bootstrap confidence (n=${ctx.lift.n}, p=${ctx.lift.pValue.toFixed(4)}, paired d=${pairedEffect}).`,\n        evidencePath: 'lift',\n      })\n    } else if (inconclusive) {\n      out.push({\n        priority: 'high',\n        kind: 'expand-corpus',\n        title: `Inconclusive — required sample is ${requiredRuns} (have ${ctx.lift.n}) at current effect size`,\n        detail: `CI straddles threshold. Current MDE at 80% power is ${ctx.lift.mde.toFixed(3)}; observed delta is ${ctx.lift.delta.toFixed(3)}.`,\n        evidencePath: 'lift',\n      })\n    } else {\n      out.push({\n        priority: 'critical',\n        kind: 'hold',\n        title: `Hold — lift CI lower bound ${ctx.lift.ci95[0].toFixed(3)} is at or below threshold ${ctx.threshold}`,\n        detail: `Bootstrap CI provides no statistical evidence the candidate is better. Consider tightening the mutation or expanding the holdout.`,\n        evidencePath: 'lift',\n      })\n    }\n  }\n\n  if (ctx.contamination && ctx.contamination.leaks > 0) {\n    out.push({\n      priority: 'critical',\n      kind: 'fix',\n      title: `${ctx.contamination.leaks} canary leak${ctx.contamination.leaks === 1 ? '' : 's'} detected`,\n      detail: `Holdout integrity is compromised. The lift number is unreliable until you investigate.`,\n      evidencePath: 'contamination',\n    })\n  }\n\n  if (ctx.interRater && ctx.interRater.kappa < 0.5) {\n    out.push({\n      priority: 'high',\n      kind: 'recalibrate',\n      title: `Inter-rater weighted kappa ${ctx.interRater.kappa.toFixed(2)} is below 0.5`,\n      detail:\n        'Raters disagree on what good looks like. Review the largest disagreement cases and refine the rubric before automating these decisions.',\n      evidencePath: 'interRater',\n    })\n  }\n\n  if (ctx.failureClusters && ctx.failureClusters.clusters.length > 0) {\n    const top = ctx.failureClusters.clusters[0]!\n    out.push({\n      priority: 'high',\n      kind: 'investigate',\n      title: `Top failure cluster: ${top.name} (${(top.share * 100).toFixed(0)}% of failures)`,\n      detail: `${ctx.failureClusters.totalFailures} runs failed. The largest cluster groups ${top.exemplars.length} exemplars under '${top.name}'.`,\n      evidencePath: 'failureClusters.clusters[0]',\n    })\n  }\n\n  if (ctx.outcomeCorrelation && Math.abs(ctx.outcomeCorrelation.spearman) < 0.3) {\n    out.push({\n      priority: 'medium',\n      kind: 'recalibrate',\n      title: `Judge scores decoupled from ${ctx.outcomeCorrelation.metric} (Spearman ρ=${ctx.outcomeCorrelation.spearman.toFixed(2)})`,\n      detail: `Your judges score what they were trained to score, but it isn't predicting downstream ${ctx.outcomeCorrelation.metric}. Consider retraining the judge against ${ctx.outcomeCorrelation.metric} as the gold signal.`,\n      evidencePath: 'outcomeCorrelation',\n    })\n  }\n\n  return out\n}\n\n// ── Re-export pareto figure spec for hosted-side rendering ─────────\n\nexport type { ParetoFigureSpec }\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;AA4BO,SAAS,cAAc,QAAgB,WAA4C;AACxF,QAAM,QAAsB,CAAC;AAC7B,aAAW,KAAK,WAAW;AACzB,QAAI,CAAC,EAAE,OAAQ;AACf,QAAI,OAAO,SAAS,EAAE,MAAM,GAAG;AAC7B,YAAM,KAAK,EAAE,YAAY,EAAE,IAAI,QAAQ,EAAE,QAAQ,UAAU,QAAQ,QAAQ,EAAE,MAAM,EAAE,CAAC;AAAA,IACxF;AAAA,EACF;AACA,SAAO;AACT;AAuBO,SAAS,sBACd,QACA,UACmB;AACnB,QAAM,UAAU,SAAS,oBAAoB,SAAS;AACtD,MAAI,CAAC,QAAS,QAAO;AACrB,QAAM,MAAM,eAAe,QAAQ,OAAO;AAC1C,MAAI,CAAC,IAAK,QAAO;AACjB,SAAO;AAAA,IACL,YAAY,SAAS;AAAA,IACrB,QAAQ;AAAA,IACR,UAAU,QAAQ,QAAQ,GAAG;AAAA,EAC/B;AACF;AAWO,SAAS,sBACd,OACc;AACd,QAAM,QAAsB,CAAC;AAC7B,aAAW,KAAK,OAAO;AACrB,UAAM,OAAO,sBAAsB,EAAE,QAAQ,EAAE,QAAQ;AACvD,QAAI,KAAM,OAAM,KAAK,EAAE,GAAG,MAAM,OAAO,EAAE,SAAS,KAAK,MAAM,CAAC;AAAA,EAChE;AACA,SAAO;AACT;AAOA,SAAS,eAAe,QAAgB,SAAgC;AACtE,QAAM,KAAK,cAAc,OAAO;AAChC,MAAI,IAAI;AACN,UAAM,IAAI,OAAO,MAAM,EAAE;AACzB,WAAO,KAAK,EAAE,CAAC,EAAE,SAAS,IAAI,EAAE,CAAC,IAAI;AAAA,EACvC;AACA,SAAO,OAAO,SAAS,OAAO,IAAI,UAAU;AAC9C;AAEA,SAAS,cAAc,SAAgC;AACrD,MAAI,QAAQ,SAAS,KAAK,QAAQ,CAAC,MAAM,IAAK,QAAO;AACrD,QAAM,OAAO,QAAQ,YAAY,GAAG;AACpC,MAAI,QAAQ,EAAG,QAAO;AACtB,QAAM,OAAO,QAAQ,MAAM,GAAG,IAAI;AAClC,QAAM,QAAQ,QAAQ,MAAM,OAAO,CAAC;AACpC,MAAI,CAAC,cAAc,KAAK,KAAK,EAAG,QAAO;AACvC,MAAI;AACF,WAAO,IAAI,OAAO,MAAM,KAAK;AAAA,EAC/B,QAAQ;AACN,WAAO;AAAA,EACT;AACF;AAQA,eAAsB,eACpB,OACA,WACuB;AACvB,QAAM,UAAU,UAAU,OAAO,CAAC,MAAM,CAAC,CAAC,EAAE,MAAM;AAClD,MAAI,QAAQ,WAAW,EAAG,QAAO,CAAC;AAClC,QAAM,QAAQ,MAAM,SAAS,KAAK;AAClC,QAAM,QAAsB,CAAC;AAC7B,aAAW,QAAQ,OAAO;AACxB,UAAM,SAAS,KAAK,UAAU;AAC9B,eAAW,KAAK,SAAS;AACvB,UAAI,EAAE,UAAU,OAAO,SAAS,EAAE,MAAM,GAAG;AACzC,cAAM,KAAK;AAAA,UACT,YAAY,EAAE;AAAA,UACd,QAAQ,EAAE;AAAA,UACV,OAAO,KAAK;AAAA,UACZ,UAAU,QAAQ,QAAQ,EAAE,MAAM;AAAA,QACpC,CAAC;AAAA,MACH;AAAA,IACF;AAAA,EACF;AACA,SAAO;AACT;AAEO,IAAM,iBAAN,MAAqB;AAAA,EAClB;AAAA,EACA,YAAwE,CAAC;AAAA,EAEjF,YAAY,WAA8B;AACxC,SAAK,YAAY;AAAA,EACnB;AAAA;AAAA,EAGA,IAAI,YAAoB,SAAsD;AAC5E,QAAI,YAAY,gBAAgB,YAAY,aAAa;AACvD,YAAM,IAAI;AAAA,QACR,wEAAwE,OAAO;AAAA,MACjF;AAAA,IACF;AACA,UAAM,IAAI,KAAK,UAAU,KAAK,CAAC,MAAM,EAAE,OAAO,UAAU;AACxD,QAAI,CAAC,EAAG,OAAM,IAAI,MAAM,qBAAqB,UAAU,aAAa;AACpE,SAAK,UAAU,KAAK,EAAE,YAAY,SAAS,IAAI,KAAK,IAAI,EAAE,CAAC;AAC3D,WAAO;AAAA,EACT;AAAA,EAEA,eAAmF;AACjF,WAAO,KAAK;AAAA,EACd;AACF;AAEA,SAAS,QAAQ,QAAgB,QAAwB;AACvD,QAAM,KAAK,OAAO,QAAQ,MAAM;AAChC,MAAI,KAAK,EAAG,QAAO;AACnB,QAAM,QAAQ,KAAK,IAAI,GAAG,KAAK,EAAE;AACjC,QAAM,MAAM,KAAK,IAAI,OAAO,QAAQ,KAAK,OAAO,SAAS,EAAE;AAC3D,UAAQ,QAAQ,IAAI,WAAM,MAAM,OAAO,MAAM,OAAO,GAAG,KAAK,MAAM,OAAO,SAAS,WAAM;AAC1F;;;AC3DO,SAAS,mBAAmB,MAAkD;AACnF,QAAM,OAAO,KAAK,KAAK,IAAI,iBAAiB;AAC5C,QAAM,OAAO,KAAK,iBAAiB;AACnC,SAAO;AAAA,IACL,WAAW,wBAAwB,MAAM,IAAI;AAAA,IAC7C,gBAAgB,wBAAwB,IAAI;AAAA,EAC9C;AACF;AAEA,eAAsB,YAAY,MAAkD;AAClF,QAAM,OAAO,KAAK,KAAK,IAAI,iBAAiB;AAC5C,QAAM,OAAO,KAAK,iBAAiB;AACnC,QAAM,YAAY,KAAK,qBAAqB;AAC5C,QAAM,QAAQ,aAAa,MAAM,KAAK,SAAS,MAAM;AAErD,QAAM,mBAAmB,KACtB,IAAI,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,OAAO,YAAY,GAAG,KAAK,EAAE,EAAE,EAC7D,OAAO,CAAC,MAAM,OAAO,SAAS,EAAE,KAAK,CAAC;AACzC,QAAM,YAAY;AAAA,IAChB,iBAAiB,IAAI,CAAC,MAAM,EAAE,KAAK;AAAA,IACnC;AAAA,IACA;AAAA,EACF;AAEA,QAAM,eAAe,oBAAoB,MAAM,IAAI;AACnD,QAAM,EAAE,WAAW,gBAAgB,WAAW,IAAI,mBAAmB;AAAA,IACnE;AAAA,IACA,eAAe;AAAA,EACjB,CAAC;AACD,QAAM,gBAAgB,KAAK,OAAO,CAAC,QAAQ,IAAI,eAAe,SAAS,YAAY;AACnF,QAAM,QAAQ,cAAc,IAAI,CAAC,MAAM,EAAE,OAAO,EAAE,OAAO,cAAc;AACvE,QAAM,WAAW,eAAe,OAAO,IAAI;AAC3C,QAAM,SAAS,YAAY,eAAe,EAAE,MAAM,CAAC;AACnD,QAAM,WAA+C,CAAC;AACtD,MAAI,WAAW,WAAW,IAAI,GAAG;AAC/B,aAAS,OAAO,qBAAqB,MAAM,UAAU;AAAA,EACvD,WAAW,MAAM,WAAW,KAAK,MAAM,MAAM,CAAC,MAAM,MAAM,CAAC,GAAG;AAC5D,aAAS,OAAO,OAAO,KAAK,MAAM;AAAA,EACpC;AACA,MAAI,OAAO,OAAO,SAAS,GAAG;AAC5B,aAAS,SACP,OAAO,OAAO,WAAW,IACrB,4CACA;AAAA,EACR;AACA,QAAM,cAAc;AAAA,IAClB,MAAM;AAAA,IACN;AAAA,IACA;AAAA,IACA,GAAI,SAAS,QAAQ,SAAS,SAAS,EAAE,SAAS,IAAI,CAAC;AAAA,EACzD;AAEA,QAAM,SAAS,qBAAqB,IAAI;AAExC,QAAM,aAAa,KAAK,cAAc,kBAAkB,KAAK,WAAW,IAAI;AAE5E,QAAM,OAAO,YAAY,MAAM,KAAK,qBAAqB,KAAK,sBAAsB,KAAK;AAEzF,QAAM,kBAAkB,KAAK,UACzB,MAAM,uBAAuB,MAAM,KAAK,SAAS,KAAK,IACtD;AAEJ,QAAM,iBAAiB,sBAAsB,MAAM,KAAK;AAExD,QAAM,gBAAgB,KAAK,kBACvB,qBAAqB,MAAM,KAAK,eAAe,IAC/C;AAEJ,QAAM,qBAAqB,KAAK,gBAC5B,0BAA0B,MAAM,KAAK,eAAe,KAAK,IACzD;AAEJ,QAAM,UAAU,sBAAsB,WAAW,MAAM,aAAa;AAEpE,QAAM,wBAAwB,KAAK,eAC/B,6BAA6B,MAAM,KAAK,cAAc,OAAO,KAAK,aAAa,IAC/E;AAEJ,QAAM,kBAAkB,qBAAqB;AAAA,IAC3C;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,EACF,CAAC;AAED,SAAO;AAAA,IACL,GAAG,KAAK;AAAA,IACR;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA,GAAI,iBAAiB,EAAE,eAAe,IAAI,CAAC;AAAA,IAC3C,GAAI,wBAAwB,EAAE,sBAAsB,IAAI,CAAC;AAAA,IACzD;AAAA,EACF;AACF;AAEA,SAAS,wBAAwB,MAAmB,MAAgC;AAClF,QAAM,gBAAgB,KAAK,QAAQ,CAAC,QAAQ;AAC1C,UAAM,QAAQ,oBAAoB,GAAG;AACrC,WAAO,QAAQ,CAAC,EAAE,OAAO,SAAS,UAAU,KAAK,oBAAoB,EAAE,CAAC,IAAI,CAAC;AAAA,EAC/E,CAAC;AACD,QAAM,iBAAiB,cAAc;AAAA,IAAQ,CAAC,QAC5C,IAAI,YAAY,SAAY,CAAC,IAAI,OAAO,IAAI,CAAC;AAAA,EAC/C;AACA,QAAM,cAAc,oBAAI,IAAoB;AAC5C,MAAI,qBAAqB;AACzB,MAAI,uBAAuB;AAC3B,MAAI,qBAAqB;AACzB,MAAI,kBAAkB;AACtB,MAAI,yBAAyB;AAC7B,QAAM,mBAAuD;AAAA,IAC3D,WAAW;AAAA,IACX,QAAQ;AAAA,IACR,WAAW;AAAA,IACX,YAAY;AAAA,IACZ,SAAS;AAAA,EACX;AACA,QAAM,0BAAoF;AAAA,IACxF,WAAW,EAAE,YAAY,GAAG,eAAe,GAAG,YAAY,EAAE;AAAA,IAC5D,QAAQ,EAAE,YAAY,GAAG,eAAe,GAAG,YAAY,EAAE;AAAA,IACzD,WAAW,EAAE,YAAY,GAAG,eAAe,GAAG,YAAY,EAAE;AAAA,IAC5D,YAAY,EAAE,YAAY,GAAG,eAAe,GAAG,YAAY,EAAE;AAAA,IAC7D,SAAS,EAAE,YAAY,GAAG,eAAe,GAAG,YAAY,EAAE;AAAA,EAC5D;AACA,MAAI,gBAAgB;AACpB,MAAI,kBAAkB;AACtB,MAAI,yBAAyB;AAE7B,aAAW,OAAO,MAAM;AACtB,gBAAY,IAAI,IAAI,QAAQ,YAAY,IAAI,IAAI,KAAK,KAAK,KAAK,CAAC;AAChE,UAAM,kBAAkB,IAAI;AAC5B,qBAAiB,eAAe,KAAK;AACrC,UAAM,aAAa,oBAAoB,KAAK,gBAAgB;AAC5D,QAAI,eAAe,QAAW;AAC5B,yBAAmB;AACnB,gCAA0B;AAAA,IAC5B;AACA,UAAM,QAAQ,IAAI;AAClB,SACG,cAAc,KAAK,KACpB,MAAM,QAAQ,KACd,MAAM,SAAS,MACd,MAAM,UAAU,KAAK,MACrB,MAAM,cAAc,KAAK,GAC1B;AACA,uBAAiB;AAAA,IACnB;AACA,UAAM,cAAc,6BAA6B,GAAG;AACpD,QAAI,gBAAgB,QAAW;AAC7B,8BAAwB;AACxB,4BAAsB;AACtB,UAAI,cAAc,GAAG;AACnB,8BAAsB;AACtB,gCAAwB,eAAe,EAAE,cAAc;AAAA,MACzD,MAAO,yBAAwB,eAAe,EAAE,iBAAiB;AAAA,IACnE,MAAO,yBAAwB,eAAe,EAAE,cAAc;AAC9D,UAAM,qBAAqB,oBAAoB,KAAK,kBAAkB;AACtE,QAAI,uBAAuB,QAAW;AACpC,yBAAmB;AACnB,gCAA0B;AAAA,IAC5B;AAAA,EACF;AAEA,SAAO;AAAA,IACL,YAAY;AAAA,MACV,KAAK,IAAI,CAAC,QAAQ,IAAI,MAAM;AAAA,MAC5B;AAAA,IACF;AAAA,IACA,SAAS;AAAA,MACP,KAAK,OAAO,CAAC,QAAQ,IAAI,YAAY,MAAS,EAAE,IAAI,CAAC,QAAQ,IAAI,OAAQ;AAAA,MACzE;AAAA,IACF;AAAA,IACA,YAAY;AAAA,MACV,KAAK,IAAI,CAAC,QAAQ,IAAI,UAAU;AAAA,MAChC;AAAA,IACF;AAAA,IACA,gBAAgB;AAAA,MACd,MAAM,cAAc;AAAA,MACpB,YAAY;AAAA,QACV,cAAc,IAAI,CAAC,QAAQ,IAAI,KAAK;AAAA,QACpC;AAAA,MACF;AAAA,MACA,SAAS,eAAe,gBAAgB,IAAI;AAAA,MAC5C,cAAc,eAAe,OAAO,CAAC,OAAO,UAAU,QAAQ,OAAO,CAAC;AAAA,IACxE;AAAA,IACA,QAAQ,CAAC,GAAG,YAAY,QAAQ,CAAC,EAC9B,IAAI,CAAC,CAAC,OAAO,KAAK,OAAO,EAAE,OAAO,MAAM,MAAM,EAAE,EAChD,KAAK,CAAC,MAAM,UAAU,MAAM,OAAO,KAAK,QAAQ,KAAK,MAAM,cAAc,MAAM,KAAK,CAAC;AAAA,IACxF,YAAY;AAAA,MACV,MAAM;AAAA,MACN,QAAQ;AAAA,MACR,eAAe;AAAA,IACjB;AAAA,IACA,iBAAiB;AAAA,MACf,MAAM;AAAA,MACN,UAAU,qBAAqB,IAAI,qBAAqB,qBAAqB;AAAA,MAC7E,QAAQ;AAAA,MACR,eAAe;AAAA,MACf;AAAA,MACA;AAAA,MACA,mBAAmB;AAAA,IACrB;AAAA,IACA;AAAA,EACF;AACF;AAEA,SAAS,6BAA6B,KAAoC;AACxE,SAAO,oBAAoB,KAAK,uBAAuB;AACzD;AAEA,SAAS,oBAAoB,KAAgB,KAAiC;AAC5E,QAAM,QAAQ,UAAU,KAAK,GAAG;AAChC,SAAO,UAAU,UAAa,OAAO,UAAU,KAAK,KAAK,SAAS,IAAI,QAAQ;AAChF;AAEA,SAAS,oBAAoB,QAAyB,MAAiC;AACrF,QAAM,YAAY,OAAO;AAAA,IAAQ,CAAC,UAChC,MAAM,cAAc,SAAY,CAAC,MAAM,SAAS,IAAI,CAAC;AAAA,EACvD;AACA,QAAM,SAAS,OAAO,QAAQ,CAAC,UAAW,MAAM,WAAW,SAAY,CAAC,MAAM,MAAM,IAAI,CAAC,CAAE;AAC3F,QAAM,aAAa,OAAO;AAAA,IAAQ,CAAC,UACjC,MAAM,eAAe,SAAY,CAAC,MAAM,UAAU,IAAI,CAAC;AAAA,EACzD;AACA,SAAO;AAAA,IACL,OAAO;AAAA,MACL,OAAO,IAAI,CAAC,UAAU,MAAM,KAAK;AAAA,MACjC;AAAA,IACF;AAAA,IACA,QAAQ;AAAA,MACN,OAAO,IAAI,CAAC,UAAU,MAAM,MAAM;AAAA,MAClC;AAAA,IACF;AAAA,IACA,WAAW,eAAe,WAAW,IAAI;AAAA,IACzC,QAAQ,eAAe,QAAQ,IAAI;AAAA,IACnC,YAAY,eAAe,YAAY,IAAI;AAAA,IAC3C,QAAQ;AAAA,MACN,OAAO,OAAO,OAAO,CAAC,OAAO,UAAU,QAAQ,MAAM,OAAO,CAAC;AAAA,MAC7D,QAAQ,OAAO,OAAO,CAAC,OAAO,UAAU,QAAQ,MAAM,QAAQ,CAAC;AAAA,MAC/D,WAAW,UAAU,OAAO,CAAC,OAAO,UAAU,QAAQ,OAAO,CAAC;AAAA,MAC9D,QAAQ,OAAO,OAAO,CAAC,OAAO,UAAU,QAAQ,OAAO,CAAC;AAAA,MACxD,YAAY,WAAW,OAAO,CAAC,OAAO,UAAU,QAAQ,OAAO,CAAC;AAAA,IAClE;AAAA,EACF;AACF;AAEA,SAAS,oBAAoB,KAA2C;AACtE,QAAM,QAAQ,UAAU,KAAK,yBAAyB;AACtD,QAAM,SAAS,UAAU,KAAK,6BAA6B;AAC3D,QAAM,YAAY,UAAU,KAAK,4BAA4B;AAC7D,QAAM,SAAS,UAAU,KAAK,yBAAyB;AACvD,QAAM,aAAa,UAAU,KAAK,8BAA8B;AAChE,MACE,UAAU,UACV,WAAW,UACX,cAAc,UACd,WAAW,UACX,eAAe;AAEf,WAAO;AACT,SAAO;AAAA,IACL,OAAO,SAAS;AAAA,IAChB,QAAQ,UAAU;AAAA,IAClB,GAAI,cAAc,SAAY,EAAE,UAAU,IAAI,CAAC;AAAA,IAC/C,GAAI,WAAW,SAAY,EAAE,OAAO,IAAI,CAAC;AAAA,IACzC,GAAI,eAAe,SAAY,EAAE,WAAW,IAAI,CAAC;AAAA,EACnD;AACF;AAEA,SAAS,UAAU,KAAgB,KAAiC;AAClE,QAAM,QAAQ,IAAI,QAAQ,IAAI,GAAG;AACjC,SAAO,OAAO,UAAU,YAAY,OAAO,SAAS,KAAK,KAAK,SAAS,IAAI,QAAQ;AACrF;AAEA,SAAS,wBAAwB,MAA0C;AACzE,QAAM,UAAiC;AAAA,IACrC,UAAU,EAAE,GAAG,GAAG,UAAU,EAAE;AAAA,IAC9B,WAAW,EAAE,GAAG,GAAG,UAAU,EAAE;AAAA,IAC/B,YAAY,EAAE,GAAG,EAAE;AAAA,IACnB,eAAe;AAAA,EACjB;AACA,aAAW,OAAO,MAAM;AACtB,UAAM,OAAO,IAAI;AACjB,QAAI,KAAK,SAAS,cAAc;AAC9B,cAAQ,WAAW,KAAK;AAAA,IAC1B,OAAO;AACL,cAAQ,KAAK,IAAI,EAAE,KAAK;AACxB,cAAQ,KAAK,IAAI,EAAE,YAAY,KAAK;AAAA,IACtC;AAAA,EACF;AACA,QAAM,QAAQ,QAAQ,SAAS,IAAI,QAAQ,UAAU;AACrD,UAAQ,gBAAgB,KAAK,SAAS,IAAI,QAAQ,KAAK,SAAS;AAChE,SAAO;AACT;AAEA,SAAS,qBAAqB,MAAmB,YAA2C;AAC1F,QAAM,aAAa,WAAW,WAAW;AACzC,QAAM,QAAQ,WAAW,SAAS,IAAI,WAAW,UAAU;AAC3D,MAAI,eAAe,KAAK,QAAQ;AAC9B,WAAO,+BAA+B,KAAK,MAAM;AAAA,EACnD;AACA,SAAO,2BAA2B,UAAU,IAAI,KAAK,MAAM,oDAAoD,KAAK,IAAI,KAAK,MAAM,cAAc,WAAW,SAAS,CAAC,cAAc,WAAW,UAAU,CAAC;AAC5M;AAQA,SAAS,sBACP,MACA,OACiC;AACjC,QAAM,SAAS,oBAAI,IAA0B;AAC7C,aAAW,KAAK,MAAM;AACpB,QAAI,CAAC,cAAc,GAAG,KAAK,EAAG;AAC9B,UAAM,MACJ,EAAE,iBAAiB,UAAa,EAAE,iBAAiB,YAAY,EAAE,eAAe;AAClF,WAAO,IAAI,MAAM,OAAO,IAAI,GAAG,KAAK,KAAK,CAAC;AAAA,EAC5C;AACA,MAAI,OAAO,SAAS,EAAG,QAAO;AAC9B,QAAM,IAAI,KAAK;AACf,SAAO,CAAC,GAAG,OAAO,QAAQ,CAAC,EACxB,IAAI,CAAC,CAAC,cAAc,KAAK,OAAO;AAAA,IAC/B;AAAA,IACA;AAAA,IACA,OAAO,IAAI,IAAI,QAAQ,IAAI;AAAA,EAC7B,EAAE,EACD,KAAK,CAAC,GAAG,MAAM,EAAE,QAAQ,EAAE,SAAS,EAAE,aAAa,cAAc,EAAE,YAAY,CAAC;AACrF;AAUA,SAAS,6BACP,SACA,UACA,OACA,aACmC;AACnC,MAAI,QAAQ,WAAW,KAAK,SAAS,WAAW,EAAG,QAAO;AAE1D,QAAM,UAAuC,CAAC;AAC9C,QAAM,aAA8C,CAAC;AAErD,QAAM,mBAAmB,QACtB,IAAI,CAAC,MAAM,YAAY,GAAG,KAAK,CAAC,EAChC,OAAO,OAAO,QAAQ;AACzB,QAAM,oBAAoB,SACvB,IAAI,CAAC,MAAM,YAAY,GAAG,KAAK,CAAC,EAChC,OAAO,OAAO,QAAQ;AACzB,MAAI,iBAAiB,SAAS,KAAK,kBAAkB,SAAS,GAAG;AAC/D,YAAQ,YAAY,aAAa,mBAAmB,gBAAgB;AACpE,eAAW,YAAY;AAAA,EACzB;AAEA,QAAM,cAAc,gBAAgB,OAAO;AAC3C,QAAM,eAAe,gBAAgB,QAAQ;AAC7C,MAAI,YAAY,SAAS,KAAK,aAAa,SAAS,GAAG;AACrD,YAAQ,OAAO,aAAa,cAAc,WAAW;AACrD,eAAW,OAAO;AAAA,EACpB;AAEA,QAAM,aAAa,QAAQ,IAAI,CAAC,MAAM,EAAE,MAAM,EAAE,OAAO,OAAO,QAAQ;AACtE,QAAM,cAAc,SAAS,IAAI,CAAC,MAAM,EAAE,MAAM,EAAE,OAAO,OAAO,QAAQ;AACxE,MAAI,WAAW,SAAS,KAAK,YAAY,SAAS,GAAG;AACnD,YAAQ,WAAW,aAAa,aAAa,UAAU;AACvD,eAAW,WAAW;AAAA,EACxB;AAEA,QAAM,aAAa,QAChB,IAAI,CAAC,OAAO,EAAE,WAAW,SAAS,MAAM,EAAE,WAAW,UAAU,EAAE,EACjE,OAAO,OAAO,QAAQ;AACzB,QAAM,cAAc,SACjB,IAAI,CAAC,OAAO,EAAE,WAAW,SAAS,MAAM,EAAE,WAAW,UAAU,EAAE,EACjE,OAAO,OAAO,QAAQ;AACzB,MAAI,WAAW,SAAS,KAAK,YAAY,SAAS,GAAG;AACnD,YAAQ,aAAa,aAAa,aAAa,UAAU;AACzD,eAAW,aAAa;AAAA,EAC1B;AAKA,QAAM,cAAc,oBAAoB,OAAO;AAC/C,QAAM,eAAe,oBAAoB,QAAQ;AACjD,aAAW,OAAO,OAAO,KAAK,WAAW,GAAG;AAC1C,UAAM,IAAI,aAAa,GAAG;AAC1B,UAAM,IAAI,YAAY,GAAG;AACzB,QAAI,CAAC,KAAK,EAAE,WAAW,KAAK,CAAC,KAAK,EAAE,WAAW,EAAG;AAClD,YAAQ,OAAO,GAAG,EAAE,IAAI,aAAa,GAAG,CAAC;AACzC,eAAW,OAAO,GAAG,EAAE,IAAI;AAAA,EAC7B;AAEA,QAAM,mBAA6B,CAAC;AACpC,QAAM,kBAA4B,CAAC;AACnC,aAAW,CAAC,MAAM,KAAK,KAAK,OAAO,QAAQ,OAAO,GAAG;AACnD,QAAI,CAAC,MAAM,YAAa;AACxB,UAAM,MAAM,WAAW,IAAI,KAAK;AAChC,UAAM,SAAS,QAAQ,qBAAqB,MAAM,QAAQ,IAAI,MAAM,QAAQ;AAC5E,QAAI,OAAQ,iBAAgB,KAAK,IAAI;AAAA,QAChC,kBAAiB,KAAK,IAAI;AAAA,EACjC;AAEA,SAAO;AAAA,IACL,WAAW,SAAS;AAAA,IACpB,UAAU,QAAQ;AAAA,IAClB,GAAI,cAAc,EAAE,YAAY,IAAI,CAAC;AAAA,IACrC;AAAA,IACA;AAAA,IACA;AAAA,EACF;AACF;AAEA,SAAS,gBAAgB,MAA6B;AACpD,SAAO,KACJ,OAAO,CAAC,QAAQ,IAAI,eAAe,SAAS,YAAY,EACxD,IAAI,CAAC,QAAQ,IAAI,OAAO,EACxB,OAAO,cAAc;AAC1B;AAEA,SAAS,eAAe,OAAiC;AACvD,SAAO,OAAO,UAAU,YAAY,OAAO,SAAS,KAAK;AAC3D;AAGA,SAAS,oBAAoB,MAA6C;AACxE,QAAM,MAAgC,CAAC;AACvC,aAAW,KAAK,MAAM;AACpB,UAAM,SAAS,EAAE,QAAQ,aAAa;AACtC,QAAI,CAAC,OAAQ;AACb,eAAW,CAAC,KAAK,KAAK,KAAK,OAAO,QAAQ,MAAM,GAAG;AACjD,UAAI,CAAC,OAAO,SAAS,KAAK,EAAG;AAC7B,UAAI,CAAC,IAAI,GAAG,EAAG,KAAI,GAAG,IAAI,CAAC;AAC3B,UAAI,GAAG,EAAE,KAAK,KAAe;AAAA,IAC/B;AAAA,EACF;AACA,SAAO;AACT;AAIA,SAAS,aAAa,UAAoB,SAAgC;AACxE,QAAM,eAAe,KAAK,QAAQ;AAClC,QAAM,cAAc,KAAK,OAAO;AAChC,QAAM,cAAc,eAAe,UAAU,YAAY;AACzD,QAAM,aAAa,eAAe,SAAS,WAAW;AACtD,QAAM,YAAY,SAAS;AAC3B,QAAM,WAAW,QAAQ;AACzB,QAAM,QAAQ,cAAc;AAG5B,QAAM,KAAK,KAAK,KAAK,cAAc,YAAY,aAAa,QAAQ;AAIpE,QAAM,YAAY,QAAQ,KAAK,IAAI,KAAK;AACxC,QAAM,OAAyB,CAAC,QAAQ,WAAW,QAAQ,SAAS;AAGpE,QAAM,IAAI,KAAK,IAAI,QAAQ,KAAK;AAChC,QAAM,SAAS,KAAK,IAAI,KAAK,IAAI,kBAAkB,KAAK,IAAI,CAAC,CAAC,KAAK;AAGnE,QAAM,eAAe,KAAK;AAAA,MACtB,YAAY,KAAK,eAAe,WAAW,KAAK,cAChD,KAAK,IAAI,GAAG,YAAY,WAAW,CAAC;AAAA,EACxC;AACA,QAAM,UAAU,eAAe,IAAI,QAAQ,eAAe;AAG1D,QAAM,cAAc,SAAS,QAAQ,KAAK,IAAI,OAAO,KAAK;AAE1D,SAAO;AAAA,IACL,SAAS;AAAA,IACT,UAAU;AAAA,IACV;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,EACF;AACF;AAEA,SAAS,eAAe,IAAc,QAAwB;AAC5D,MAAI,GAAG,SAAS,EAAG,QAAO;AAC1B,MAAI,IAAI;AACR,aAAW,KAAK,GAAI,OAAM,IAAI,WAAW;AACzC,SAAO,KAAK,GAAG,SAAS;AAC1B;AAGA,SAAS,kBAAkB,GAAmB;AAC5C,QAAM,KAAK;AACX,QAAM,KAAK;AACX,QAAM,KAAK;AACX,QAAM,KAAK;AACX,QAAM,KAAK;AACX,QAAM,IAAI;AACV,QAAM,OAAO,IAAI,IAAI,KAAK;AAC1B,QAAM,IAAI,KAAK,IAAI,CAAC,IAAI,KAAK;AAC7B,QAAM,IAAI,KAAK,IAAI,IAAI;AACvB,QAAM,IAAI,QAAQ,KAAK,IAAI,MAAM,IAAI,MAAM,IAAI,MAAM,IAAI,MAAM,IAAI,KAAK,IAAI,CAAC,IAAI,CAAC;AAClF,SAAO,OAAO,IAAI,OAAO;AAC3B;AAIA,SAAS,aACP,MACA,MACsB;AACtB,MAAI,SAAS,OAAQ,QAAO;AAC5B,QAAM,aAAa,KAAK,KAAK,CAAC,MAAM,OAAO,SAAS,mBAAmB,GAAG,SAAS,CAAC,CAAC;AACrF,SAAO,aAAa,YAAY;AAClC;AAQA,SAAS,YAAY,KAAgB,OAAqC;AAIxE,QAAM,QAAQ,mBAAmB,KAAK,KAAK;AAC3C,SAAO,OAAO,SAAS,KAAK,IAAK,QAAmB,OAAO;AAC7D;AAIA,SAAS,eACP,QACA,MACA,SACoB;AACpB,MAAI,OAAO,WAAW,GAAG;AACvB,WAAO;AAAA,MACL,GAAG;AAAA,MACH,MAAM;AAAA,MACN,KAAK;AAAA,MACL,KAAK;AAAA,MACL,QAAQ;AAAA,MACR,KAAK;AAAA,MACL,KAAK;AAAA,MACL,WAAW,CAAC;AAAA,IACd;AAAA,EACF;AACA,QAAM,SAAS,CAAC,GAAG,MAAM,EAAE,KAAK,CAAC,GAAG,MAAM,IAAI,CAAC;AAC/C,QAAM,IAAI,OAAO;AACjB,QAAMA,QAAO,OAAO,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI;AACjD,QAAM,WAAW,OAAO,OAAO,CAAC,GAAG,MAAM,KAAK,IAAIA,UAAS,GAAG,CAAC,IAAI;AACnE,QAAM,SAAS,KAAK,KAAK,QAAQ;AACjC,QAAM,WAAW,UACb,CAAC,GAAG,OAAO,EAAE,KAAK,CAAC,GAAG,MAAM,EAAE,QAAQ,EAAE,KAAK,EAAE,MAAM,GAAG,KAAK,IAAI,GAAG,QAAQ,MAAM,CAAC,IACnF;AACJ,SAAO;AAAA,IACL;AAAA,IACA,MAAAA;AAAA,IACA,KAAK,WAAW,QAAQ,GAAG;AAAA,IAC3B,KAAK,WAAW,QAAQ,IAAI;AAAA,IAC5B;AAAA,IACA,KAAK,OAAO,CAAC;AAAA,IACb,KAAK,OAAO,IAAI,CAAC;AAAA,IACjB,WAAW,UAAU,QAAQ,IAAI;AAAA,IACjC,GAAI,WAAW,EAAE,SAAS,IAAI,CAAC;AAAA,EACjC;AACF;AAEA,SAAS,WAAW,QAAkB,GAAmB;AACvD,MAAI,OAAO,WAAW,EAAG,QAAO;AAChC,MAAI,OAAO,WAAW,EAAG,QAAO,OAAO,CAAC;AACxC,QAAM,OAAO,OAAO,SAAS,KAAK;AAClC,QAAM,KAAK,KAAK,MAAM,GAAG;AACzB,QAAM,KAAK,KAAK,KAAK,GAAG;AACxB,MAAI,OAAO,GAAI,QAAO,OAAO,EAAE;AAC/B,QAAM,IAAI,MAAM;AAChB,SAAO,OAAO,EAAE,KAAM,IAAI,KAAK,OAAO,EAAE,IAAK;AAC/C;AAKA,SAAS,UAAU,QAAkB,MAA+C;AAClF,MAAI,OAAO,WAAW,KAAK,OAAO,EAAG,QAAO,CAAC;AAC7C,QAAM,MAAM,OAAO,CAAC;AACpB,QAAM,MAAM,OAAO,OAAO,SAAS,CAAC;AACpC,MAAI,QAAQ,IAAK,QAAO,CAAC,EAAE,IAAI,KAAK,IAAI,KAAK,OAAO,OAAO,OAAO,CAAC;AACnE,QAAM,SAAS,MAAM,OAAO;AAC5B,QAAM,MAAuC,CAAC;AAC9C,WAAS,IAAI,GAAG,IAAI,MAAM,KAAK;AAC7B,UAAM,KAAK,MAAM,IAAI;AACrB,UAAM,KAAK,MAAM,OAAO,IAAI,MAAM,KAAK;AACvC,QAAI,KAAK,EAAE,IAAI,IAAI,OAAO,EAAE,CAAC;AAAA,EAC/B;AACA,aAAW,KAAK,QAAQ;AACtB,UAAM,MAAM,KAAK,IAAI,OAAO,GAAG,KAAK,OAAO,IAAI,OAAO,KAAK,CAAC;AAC5D,QAAI,GAAG,EAAG;AAAA,EACZ;AACA,SAAO;AACT;AAEA,SAAS,oBAAoB,MAAmB,MAAkD;AAKhG,QAAM,QAAQ,oBAAI,IAAsB;AACxC,aAAW,OAAO,MAAM;AACtB,UAAM,SAAS,IAAI,QAAQ;AAC3B,QAAI,CAAC,OAAQ;AACb,eAAW,CAAC,KAAK,KAAK,KAAK,OAAO,QAAQ,OAAO,cAAc,CAAC,CAAC,GAAG;AAClE,UAAI,CAAC,OAAO,SAAS,KAAK,EAAG;AAC7B,YAAM,MAAM,MAAM,IAAI,GAAG,KAAK,CAAC;AAC/B,UAAI,KAAK,KAAK;AACd,YAAM,IAAI,KAAK,GAAG;AAAA,IACpB;AAAA,EACF;AACA,QAAM,MAA0C,CAAC;AACjD,aAAW,CAAC,KAAK,MAAM,KAAK,MAAO,KAAI,GAAG,IAAI,eAAe,QAAQ,IAAI;AACzE,SAAO;AACT;AAIA,SAAS,qBAAqB,MAAiD;AAI7E,QAAM,MAAoC,CAAC;AAC3C,QAAM,UAAU,oBAAI,IAAsB;AAC1C,aAAW,OAAO,MAAM;AACtB,UAAM,SAAS,IAAI,QAAQ;AAC3B,QAAI,CAAC,QAAQ,SAAU;AACvB,eAAW,CAAC,SAAS,IAAI,KAAK,OAAO,QAAQ,OAAO,QAAQ,GAAG;AAC7D,YAAM,YAAY,OAAO,OAAO,IAAI,EAAE,OAAO,OAAO,QAAQ;AAC5D,UAAI,UAAU,WAAW,EAAG;AAC5B,YAAM,YAAY,UAAU,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,UAAU;AACnE,YAAM,MAAM,QAAQ,IAAI,OAAO,KAAK,CAAC;AACrC,UAAI,KAAK,SAAS;AAClB,cAAQ,IAAI,SAAS,GAAG;AAAA,IAC1B;AAAA,EACF;AACA,aAAW,CAAC,SAAS,MAAM,KAAK,SAAS;AACvC,QAAI,OAAO,IAAI;AAAA,MACb,GAAG,OAAO;AAAA,MACV,WAAW,OAAO,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,OAAO;AAAA,IACxD;AAAA,EACF;AACA,SAAO;AACT;AAIA,SAAS,kBACP,SAC+B;AAC/B,QAAM,QAAQ,oBAAI,IAAqD;AACvE,aAAW,KAAK,SAAS;AACvB,QAAI,CAAC,OAAO,SAAS,EAAE,KAAK,EAAG;AAC/B,UAAM,OAAO,MAAM,IAAI,EAAE,KAAK,KAAK,CAAC;AACpC,SAAK,KAAK,EAAE,OAAO,EAAE,OAAO,OAAO,EAAE,MAAM,CAAC;AAC5C,UAAM,IAAI,EAAE,OAAO,IAAI;AAAA,EACzB;AACA,QAAM,SAAS,IAAI,IAAI,QAAQ,IAAI,CAAC,MAAM,EAAE,KAAK,CAAC;AAClD,QAAM,eAAyB,CAAC;AAChC,aAAW,CAAC,OAAO,YAAY,KAAK,OAAO;AACzC,UAAM,OAAO,IAAI,IAAI,aAAa,IAAI,CAAC,MAAM,EAAE,KAAK,CAAC;AACrD,QAAI,MAAM;AACV,eAAW,KAAK,OAAQ,KAAI,CAAC,KAAK,IAAI,CAAC,EAAG,OAAM;AAChD,QAAI,IAAK,cAAa,KAAK,KAAK;AAAA,EAClC;AACA,MAAI,OAAO,OAAO,KAAK,aAAa,WAAW,EAAG,QAAO;AAEzD,QAAM,YAAY,CAAC,GAAG,MAAM,EAAE,KAAK;AACnC,QAAM,UAAkC,CAAC;AACzC,WAAS,IAAI,GAAG,IAAI,UAAU,QAAQ,KAAK;AACzC,aAAS,IAAI,IAAI,GAAG,IAAI,UAAU,QAAQ,KAAK;AAC7C,YAAM,IAAI,UAAU,CAAC;AACrB,YAAM,IAAI,UAAU,CAAC;AACrB,YAAM,UAAoB,CAAC;AAC3B,YAAM,UAAoB,CAAC;AAC3B,iBAAW,SAAS,cAAc;AAChC,cAAM,eAAe,MAAM,IAAI,KAAK;AACpC,cAAM,KAAK,aAAa,KAAK,CAAC,MAAM,EAAE,UAAU,CAAC,GAAG;AACpD,cAAM,KAAK,aAAa,KAAK,CAAC,MAAM,EAAE,UAAU,CAAC,GAAG;AACpD,YAAI,OAAO,UAAa,OAAO,QAAW;AACxC,kBAAQ,KAAK,EAAE;AACf,kBAAQ,KAAK,EAAE;AAAA,QACjB;AAAA,MACF;AACA,YAAMC,aAAY;AAAA,QAChB,QAAQ,IAAI,CAAC,OAAO,UAAU,CAAC,OAAO,QAAQ,KAAK,CAAE,CAAC;AAAA,QACtD,EAAE,WAAW,EAAE;AAAA,MACjB;AACA,cAAQ,GAAG,CAAC,KAAK,CAAC,EAAE,IAAIA,WAAU;AAAA,IACpC;AAAA,EACF;AACA,QAAM,SAAS,aAAa,IAAI,CAAC,UAAU;AACzC,UAAM,iBAAiB,IAAI,IAAI,MAAM,IAAI,KAAK,EAAG,IAAI,CAAC,WAAW,CAAC,OAAO,OAAO,OAAO,KAAK,CAAC,CAAC;AAC9F,WAAO,UAAU,IAAI,CAAC,UAAU,eAAe,IAAI,KAAK,CAAE;AAAA,EAC5D,CAAC;AACD,QAAM,YAAY,oBAAoB,QAAQ,EAAE,WAAW,EAAE,CAAC;AAE9D,QAAM,oBAAoB,aACvB,IAAI,CAAC,UAAU;AACd,UAAM,eAAe,MAAM,IAAI,KAAK;AACpC,UAAM,SAAS,aAAa,IAAI,CAAC,MAAM,EAAE,KAAK;AAC9C,UAAM,QAAQ,KAAK,IAAI,GAAG,MAAM,IAAI,KAAK,IAAI,GAAG,MAAM;AACtD,WAAO,EAAE,OAAO,SAAS,cAAc,MAAM;AAAA,EAC/C,CAAC,EACA,KAAK,CAAC,GAAG,MAAM,EAAE,QAAQ,EAAE,KAAK,EAChC,MAAM,GAAG,EAAE;AAEd,SAAO;AAAA,IACL,QAAQ,OAAO;AAAA,IACf,cAAc,aAAa;AAAA,IAC3B,OAAO,OAAO,SAAS,UAAU,aAAa,IAAI,UAAU,gBAAgB;AAAA,IAC5E,KAAK,UAAU;AAAA,IACf,SAAS,UAAU;AAAA,IACnB,UAAU,UAAU;AAAA,IACpB;AAAA,IACA;AAAA,EACF;AACF;AAIA,SAAS,YACP,MACA,YACA,aACA,OACyB;AACzB,MAAI,MAAM;AACV,MAAI,MAAM;AACV,MAAI,CAAC,OAAO,CAAC,KAAK;AAGhB,UAAM,MAAM,CAAC,GAAG,IAAI,IAAI,KAAK,IAAI,CAAC,MAAM,EAAE,WAAW,CAAC,CAAC;AACvD,QAAI,IAAI,WAAW,EAAG,QAAO;AAC7B,UAAM,CAAC,KAAK,GAAG,IAAI;AACnB,UAAM,UAAU;AAAA,MACd,KAAK,OAAO,CAAC,QAAQ,IAAI,gBAAgB,GAAG;AAAA,MAC5C;AAAA,IACF;AACA,UAAM,UAAU;AAAA,MACd,KAAK,OAAO,CAAC,QAAQ,IAAI,gBAAgB,GAAG;AAAA,MAC5C;AAAA,IACF;AACA,QAAI,QAAQ,WAAW,KAAK,QAAQ,WAAW,EAAG,QAAO;AACzD,UAAM,QAAQ,KAAK,OAAO;AAC1B,UAAM,QAAQ,KAAK,OAAO;AAC1B,UAAM,SAAS,QAAQ,MAAM;AAC7B,UAAM,SAAS,QAAQ,MAAM;AAAA,EAC/B;AAEA,QAAM,WAAW,KAAK,OAAO,CAAC,MAAM,EAAE,gBAAgB,GAAG;AACzD,QAAM,YAAY,KAAK,OAAO,CAAC,MAAM,EAAE,gBAAgB,GAAG;AAC1D,MAAI,SAAS,WAAW,KAAK,UAAU,WAAW,EAAG,QAAO;AAE5D,QAAM,iBAAiB,SAAS,OAAO,CAAC,QAAQ,OAAO,SAAS,YAAY,KAAK,KAAK,CAAC,CAAC;AACxF,QAAM,kBAAkB,UAAU,OAAO,CAAC,QAAQ,OAAO,SAAS,YAAY,KAAK,KAAK,CAAC,CAAC;AAC1F,QAAM,UAAU,eAAe,gBAAgB,eAAe;AAC9D,QAAM,iBAAiB,QAAQ,MAAM,IAAI,CAAC,SAAS,YAAY,KAAK,UAAU,KAAK,CAAC;AACpF,QAAM,kBAAkB,QAAQ,MAAM,IAAI,CAAC,SAAS,YAAY,KAAK,WAAW,KAAK,CAAC;AACtF,MAAI,eAAe,WAAW,EAAG,QAAO;AAExC,QAAM,eAAe,KAAK,cAAc;AACxC,QAAM,gBAAgB,KAAK,eAAe;AAC1C,QAAM,QAAQ,gBAAgB;AAE9B,QAAM,YAAY,gBAAgB,gBAAgB,iBAAiB;AAAA,IACjE,YAAY;AAAA,IACZ,WAAW;AAAA,IACX,WAAW;AAAA,EACb,CAAC;AACD,QAAM,QAAQ,YAAY,gBAAgB,eAAe;AACzD,QAAM,IAAI,eAAe,gBAAgB,eAAe;AACxD,QAAM,MAAM,UAAU,EAAE,SAAS,eAAe,QAAQ,OAAO,KAAK,OAAO,KAAK,CAAC;AACjF,QAAM,YACJ,MAAM,QAAQ,MAAM,IAChB,OACA,yBAAyB;AAAA,IACvB,QAAQ,KAAK,IAAI,CAAC;AAAA,IAClB,OAAO;AAAA,IACP,OAAO;AAAA,EACT,CAAC;AAEP,SAAO;AAAA,IACL;AAAA,IACA;AAAA,IACA;AAAA,IACA,MAAM,CAAC,UAAU,KAAK,UAAU,IAAI;AAAA,IACpC,QAAQ,MAAM;AAAA,IACd,GAAG,eAAe;AAAA,IAClB,kBAAkB,QAAQ,iBAAiB;AAAA,IAC3C,mBAAmB,QAAQ,kBAAkB;AAAA,IAC7C,SAAS;AAAA,IACT;AAAA,IACA;AAAA,EACF;AACF;AAEA,SAAS,KAAK,KAAuB;AACnC,SAAO,IAAI,WAAW,IAAI,IAAI,IAAI,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,IAAI;AACrE;AAIA,eAAe,uBACb,MACA,SACA,OAC4C;AAC5C,QAAM,SAAS,KAAK,OAAO,CAAC,QAAQ,cAAc,KAAK,KAAK,CAAC;AAC7D,MAAI,OAAO,WAAW,EAAG,QAAO,EAAE,UAAU,CAAC,GAAG,eAAe,EAAE;AAEjE,QAAM,WAAW,oBAAI,IAAoD;AACzE,aAAW,OAAO,QAAQ;AACxB,QAAI;AAIF,YAAM,SAAS,MAAM,QAAQ,IAAI,IAAI,OAAO,EAAE,WAAW,IAAI,CAAC;AAC9D,iBAAW,WAAW,OAAO,UAA8B;AACzD,cAAM,MAAM,QAAQ,QAAQ,QAAQ,cAAc;AAClD,cAAM,IAAI,SAAS,IAAI,GAAG,KAAK,EAAE,WAAW,CAAC,GAAG,OAAO,EAAE;AACzD,YAAI,EAAE,UAAU,SAAS,EAAG,GAAE,UAAU,KAAK,IAAI,KAAK;AACtD,iBAAS,IAAI,KAAK,CAAC;AAAA,MACrB;AAAA,IACF,QAAQ;AACN,YAAM,IAAI,SAAS,IAAI,eAAe,KAAK,EAAE,WAAW,CAAC,GAAG,OAAO,EAAE;AACrE,UAAI,EAAE,UAAU,SAAS,EAAG,GAAE,UAAU,KAAK,IAAI,KAAK;AACtD,eAAS,IAAI,iBAAiB,CAAC;AAAA,IACjC;AAAA,EACF;AACA,QAAM,cAAc,CAAC,GAAG,SAAS,QAAQ,CAAC,EAAE,IAAI,CAAC,CAAC,IAAI,CAAC,OAAO;AAAA,IAC5D;AAAA,IACA,MAAM;AAAA,IACN,OAAO,EAAE,UAAU,SAAS,OAAO;AAAA,IACnC,WAAW,EAAE;AAAA,EACf,EAAE;AACF,cAAY,KAAK,CAAC,GAAG,MAAM,EAAE,QAAQ,EAAE,KAAK;AAC5C,SAAO,EAAE,UAAU,aAAa,eAAe,OAAO,OAAO;AAC/D;AAEA,SAAS,sBAAsB,MAA4B,OAAuC;AAChG,SAAO,KAAK,IAAI,CAAC,QAAQ,YAAY,KAAK,KAAK,CAAC,EAAE,OAAO,OAAO,QAAQ;AAC1E;AAEA,SAAS,cAAc,KAAgB,OAAsC;AAC3E,MAAI,IAAI,iBAAiB,UAAa,IAAI,iBAAiB,UAAW,QAAO;AAC7E,QAAM,QAAQ,YAAY,KAAK,KAAK;AACpC,SAAO,OAAO,SAAS,KAAK,KAAK,QAAQ;AAC3C;AAIA,SAAS,qBACP,MACA,UACgC;AAChC,MAAI,QAAQ;AACZ,QAAM,UAAqE,CAAC;AAC5E,aAAW,OAAO,MAAM;AACtB,UAAM,SAAS,gBAAgB,GAAG;AAClC,QAAI,CAAC,OAAQ;AACb,UAAM,YAAY,cAAc,QAAQ,QAAQ;AAChD,eAAW,QAAQ,WAAW;AAC5B;AACA,cAAQ,KAAK,EAAE,OAAO,IAAI,OAAO,QAAQ,KAAK,QAAQ,SAAS,KAAK,SAAS,CAAC;AAAA,IAChF;AAAA,EACF;AACA,SAAO,EAAE,OAAO,oBAAoB,UAAU,GAAG,QAAQ;AAC3D;AAEA,SAAS,gBAAgB,KAAoC;AAO3D,QAAM,WAAY,IAA0D;AAC5E,MAAI,OAAO,UAAU,WAAW,SAAU,QAAO,SAAS;AAC1D,MAAI,OAAO,UAAU,SAAS,SAAU,QAAO,SAAS;AACxD,SAAO;AACT;AAIA,SAAS,0BACP,MACA,SACA,OACuC;AACvC,QAAM,KAAe,CAAC;AACtB,QAAM,KAAe,CAAC;AACtB,aAAW,OAAO,MAAM;AACtB,UAAM,IAAI,QAAQ,aAAa,IAAI,KAAK;AACxC,QAAI,MAAM,UAAa,CAAC,OAAO,SAAS,CAAC,EAAG;AAC5C,UAAM,IAAI,YAAY,KAAK,KAAK;AAChC,QAAI,CAAC,OAAO,SAAS,CAAC,EAAG;AACzB,OAAG,KAAK,CAAC;AACT,OAAG,KAAK,CAAC;AAAA,EACX;AACA,MAAI,GAAG,SAAS,EAAG,QAAO;AAE1B,QAAM,IAAI,SAAS,IAAI,EAAE;AACzB,QAAM,IAAI,UAAU,IAAI,EAAE;AAC1B,QAAM,QAAQ,KAAK,EAAE;AACrB,QAAM,QAAQ,KAAK,EAAE;AACrB,MAAI,MAAM;AACV,MAAI,QAAQ;AACZ,WAAS,IAAI,GAAG,IAAI,GAAG,QAAQ,KAAK;AAClC,YAAQ,GAAG,CAAC,IAAK,UAAU,GAAG,CAAC,IAAK;AACpC,cAAU,GAAG,CAAC,IAAK,UAAU;AAAA,EAC/B;AACA,QAAM,QAAQ,UAAU,IAAI,IAAI,MAAM;AACtC,QAAM,YAAY,QAAQ,QAAQ;AAClC,QAAM,QAAQ,GAAG,OAAO,CAAC,GAAG,MAAM,KAAK,IAAI,UAAU,GAAG,CAAC;AACzD,QAAM,QAAQ,GAAG,OAAO,CAAC,GAAG,GAAG,MAAM,KAAK,KAAK,YAAY,QAAQ,GAAG,CAAC,OAAQ,GAAG,CAAC;AACnF,QAAM,KAAK,UAAU,IAAI,IAAI,IAAI,QAAQ;AAEzC,SAAO;AAAA,IACL,QAAQ,QAAQ;AAAA,IAChB,GAAG,GAAG;AAAA,IACN,SAAS;AAAA,IACT,UAAU;AAAA,IACV,aAAa,EAAE,WAAW,OAAO,GAAG;AAAA,EACtC;AACF;AAIA,SAAS,sBACP,WACA,MACA,eAC0B;AAO1B,QAAM,OAAyC,CAAC;AAChD,QAAM,WACJ,SAAS,SACJ,kBACD,KAAK,KAAK,CAAC,IAAI,IACZ,SACD,KAAK,QAAQ,IACV,SACA;AACX,OAAK,KAAK;AAAA,IACR,MAAM;AAAA,IACN,QAAQ;AAAA,IACR,QAAQ,OACJ,SAAS,KAAK,MAAM,QAAQ,CAAC,CAAC,WAAW,KAAK,KAAK,CAAC,EAAE,QAAQ,CAAC,CAAC,KAAK,KAAK,KAAK,CAAC,EAAE,QAAQ,CAAC,CAAC,QAAQ,KAAK,CAAC,KAC1G;AAAA,EACN,CAAC;AACD,QAAM,aACJ,kBAAkB,SACb,kBACD,cAAc,UAAU,IACrB,SACA;AACT,OAAK,KAAK;AAAA,IACR,MAAM;AAAA,IACN,QAAQ;AAAA,IACR,QAAQ,gBAAgB,GAAG,cAAc,KAAK,oBAAoB;AAAA,EACpE,CAAC;AACD,OAAK;AAAA,IACH,UAAU,MAAM,IACZ;AAAA,MACE,MAAM;AAAA,MACN,QAAQ;AAAA,MACR,QAAQ;AAAA,IACV,IACA;AAAA,MACE,MAAM;AAAA,MACN,QACE,UAAU,SAAS,QAAQ,UAAU,QAAQ,MACzC,SACA,UAAU,SAAS,QAAQ,UAAU,QAAQ,MAC3C,SACA;AAAA,MACR,QACE,UAAU,SAAS,QAAQ,UAAU,QAAQ,QAAQ,UAAU,QAAQ,OACnE,uDACA,QAAQ,UAAU,KAAK,QAAQ,CAAC,CAAC,SAAS,UAAU,IAAI,QAAQ,CAAC,CAAC,SAAS,UAAU,IAAI,QAAQ,CAAC,CAAC,WAAW,UAAU,CAAC;AAAA,IACjI;AAAA,EACN;AACA,QAAM,SAAS,KAAK,KAAK,CAAC,MAAM,EAAE,WAAW,MAAM,IAC/C,SACA,KAAK,KAAK,CAAC,MAAM,EAAE,WAAW,UAAU,EAAE,WAAW,eAAe,IAClE,SACA;AACN,SAAO;AAAA,IACL;AAAA,IACA;AAAA,IACA,QAAQ,CAAC;AAAA,EACX;AACF;AAiBA,SAAS,qBAAqB,KAA8C;AAC1E,QAAM,MAAwB,CAAC;AAI/B,MAAI,IAAI,uBAAuB;AAC7B,UAAM,MAAM,IAAI;AAChB,UAAM,QAAQ,IAAI,eAAe;AACjC,eAAW,QAAQ,IAAI,kBAAkB;AACvC,YAAM,IAAI,IAAI,QAAQ,IAAI;AAC1B,UAAI,CAAC,EAAG;AACR,UAAI,KAAK;AAAA,QACP,UAAU;AAAA,QACV,MAAM;AAAA,QACN,OAAO,GAAG,IAAI,mBAAmB,EAAE,SAAS,QAAQ,CAAC,CAAC,WAAM,EAAE,QAAQ,QAAQ,CAAC,CAAC,OAAO,KAAK;AAAA,QAC5F,QAAQ,iBAAiB,EAAE,KAAK,CAAC,EAAE,QAAQ,CAAC,CAAC,KAAK,EAAE,KAAK,CAAC,EAAE,QAAQ,CAAC,CAAC,QAAQ,EAAE,OAAO,QAAQ,CAAC,CAAC,eAAe,EAAE,QAAQ,QAAQ,CAAC,CAAC,eAAe,EAAE,QAAQ,gBAAgB,EAAE,SAAS;AAAA,QACxL,cAAc,iCAAiC,IAAI;AAAA,MACrD,CAAC;AAAA,IACH;AACA,eAAW,QAAQ,IAAI,iBAAiB;AACtC,YAAM,IAAI,IAAI,QAAQ,IAAI;AAC1B,UAAI,CAAC,EAAG;AACR,UAAI,KAAK;AAAA,QACP,UAAU;AAAA,QACV,MAAM;AAAA,QACN,OAAO,GAAG,IAAI,kBAAkB,EAAE,SAAS,QAAQ,CAAC,CAAC,WAAM,EAAE,QAAQ,QAAQ,CAAC,CAAC,OAAO,KAAK;AAAA,QAC3F,QAAQ,iBAAiB,EAAE,KAAK,CAAC,EAAE,QAAQ,CAAC,CAAC,KAAK,EAAE,KAAK,CAAC,EAAE,QAAQ,CAAC,CAAC,QAAQ,EAAE,OAAO,QAAQ,CAAC,CAAC,eAAe,EAAE,QAAQ,QAAQ,CAAC,CAAC,eAAe,EAAE,QAAQ,gBAAgB,EAAE,SAAS;AAAA,QACxL,cAAc,iCAAiC,IAAI;AAAA,MACrD,CAAC;AAAA,IACH;AAAA,EACF;AAKA,MACE,IAAI,UAAU,IAAI,KAClB,IAAI,UAAU,SAAS,QACvB,IAAI,UAAU,QAAQ,QACtB,IAAI,UAAU,QAAQ,MACtB;AACA,QAAI,IAAI,UAAU,OAAO,KAAK;AAC5B,YAAM,OAAO,IAAI,UAAU,YAAY,CAAC;AACxC,YAAM,QAAQ,KACX,MAAM,GAAG,CAAC,EACV,IAAI,CAAC,MAAM,GAAG,EAAE,KAAK,IAAI,EAAE,MAAM,QAAQ,CAAC,CAAC,EAAE,EAC7C,KAAK,IAAI;AACZ,UAAI,KAAK;AAAA,QACP,UAAU;AAAA,QACV,MAAM;AAAA,QACN,OAAO,kBAAkB,IAAI,UAAU,KAAK,QAAQ,CAAC,CAAC;AAAA,QACtD,QACE,KAAK,SAAS,IACV,SAAS,KAAK,MAAM,OAAO,KAAK,WAAW,IAAI,KAAK,GAAG,sBAAsB,KAAK,mBAAmB,IAAI,UAAU,IAAI,QAAQ,CAAC,CAAC,SAAS,IAAI,UAAU,IAAI,QAAQ,CAAC,CAAC,MACtK,iBAAiB,IAAI,UAAU,IAAI,QAAQ,CAAC,CAAC,SAAS,IAAI,UAAU,IAAI,QAAQ,CAAC,CAAC;AAAA,QACxF,cAAc;AAAA,MAChB,CAAC;AAAA,IACH,WAAW,IAAI,UAAU,OAAO,KAAK;AACnC,YAAM,OAAO,IAAI,UAAU,YAAY,CAAC;AACxC,YAAM,QAAQ,KACX,MAAM,GAAG,CAAC,EACV,IAAI,CAAC,MAAM,GAAG,EAAE,KAAK,IAAI,EAAE,MAAM,QAAQ,CAAC,CAAC,EAAE,EAC7C,KAAK,IAAI;AACZ,UAAI,KAAK;AAAA,QACP,UAAU;AAAA,QACV,MAAM;AAAA,QACN,OAAO,kBAAkB,IAAI,UAAU,KAAK,QAAQ,CAAC,CAAC;AAAA,QACtD,QACE,KAAK,SAAS,IACV,SAAS,KAAK,MAAM,OAAO,KAAK,WAAW,IAAI,KAAK,GAAG,KAAK,KAAK,mBAAmB,IAAI,UAAU,IAAI,QAAQ,CAAC,CAAC,SAAS,IAAI,UAAU,IAAI,QAAQ,CAAC,CAAC,MACrJ,iBAAiB,IAAI,UAAU,IAAI,QAAQ,CAAC,CAAC,SAAS,IAAI,UAAU,IAAI,QAAQ,CAAC,CAAC;AAAA,QACxF,cAAc;AAAA,MAChB,CAAC;AAAA,IACH;AAAA,EACF;AAIA,MAAI,IAAI,kBAAkB,IAAI,eAAe,SAAS,GAAG;AACvD,UAAM,MAAM,IAAI,eAAe,CAAC;AAChC,QAAI,IAAI,SAAS,KAAK,IAAI,SAAS,MAAM;AACvC,UAAI,KAAK;AAAA,QACP,UAAU,IAAI,SAAS,OAAO,SAAS;AAAA,QACvC,MAAM;AAAA,QACN,OAAO,IAAI,IAAI,YAAY,0CAAqC,IAAI,KAAK,WAAW,IAAI,QAAQ,KAAK,QAAQ,CAAC,CAAC;AAAA,QAC/G,QAAQ,4FAA4F,IAAI,KAAK,OAAO,IAAI,UAAU,CAAC,sBAAsB,IAAI,YAAY,IAAI,IAAI,eAAe,SAAS,IAAI,YAAY,IAAI,eAAe,CAAC,EAAG,YAAY,SAAM,IAAI,eAAe,CAAC,EAAG,KAAK,MAAM,EAAE;AAAA,QACtS,cAAc;AAAA,MAChB,CAAC;AAAA,IACH;AAAA,EACF;AAKA,MAAI,OAAO,KAAK,IAAI,MAAM,EAAE,WAAW,KAAK,IAAI,UAAU,IAAI,GAAG;AAC/D,QAAI,KAAK;AAAA,MACP,UAAU;AAAA,MACV,MAAM;AAAA,MACN,OAAO;AAAA,MACP,QACE;AAAA,MACF,cAAc;AAAA,IAChB,CAAC;AAAA,EACH;AAEA,MAAI,IAAI,MAAM;AACZ,UAAM,eACJ,IAAI,KAAK,YAAY,OAAO,oCAAoC,IAAI,KAAK,QAAQ,QAAQ,CAAC;AAC5F,UAAM,eACJ,IAAI,KAAK,cAAc,OAAO,kBAAkB,IAAI,IAAI,KAAK,SAAS;AACxE,UAAM,WAAW,IAAI,KAAK,KAAK,CAAC,IAAI,IAAI;AACxC,UAAM,eAAe,IAAI,KAAK,KAAK,CAAC,KAAK,IAAI,aAAa,IAAI,KAAK,KAAK,CAAC,IAAI,IAAI;AACjF,QAAI,UAAU;AACZ,UAAI,KAAK;AAAA,QACP,UAAU;AAAA,QACV,MAAM;AAAA,QACN,OAAO,oBAAe,IAAI,KAAK,MAAM,QAAQ,CAAC,CAAC,YAAY,IAAI,KAAK,KAAK,CAAC,EAAE,QAAQ,CAAC,CAAC,KAAK,IAAI,KAAK,KAAK,CAAC,EAAE,QAAQ,CAAC,CAAC;AAAA,QACtH,QAAQ,kCAAkC,IAAI,SAAS,qCAAqC,IAAI,KAAK,CAAC,OAAO,IAAI,KAAK,OAAO,QAAQ,CAAC,CAAC,cAAc,YAAY;AAAA,QACjK,cAAc;AAAA,MAChB,CAAC;AAAA,IACH,WAAW,cAAc;AACvB,UAAI,KAAK;AAAA,QACP,UAAU;AAAA,QACV,MAAM;AAAA,QACN,OAAO,0CAAqC,YAAY,UAAU,IAAI,KAAK,CAAC;AAAA,QAC5E,QAAQ,uDAAuD,IAAI,KAAK,IAAI,QAAQ,CAAC,CAAC,uBAAuB,IAAI,KAAK,MAAM,QAAQ,CAAC,CAAC;AAAA,QACtI,cAAc;AAAA,MAChB,CAAC;AAAA,IACH,OAAO;AACL,UAAI,KAAK;AAAA,QACP,UAAU;AAAA,QACV,MAAM;AAAA,QACN,OAAO,mCAA8B,IAAI,KAAK,KAAK,CAAC,EAAE,QAAQ,CAAC,CAAC,6BAA6B,IAAI,SAAS;AAAA,QAC1G,QAAQ;AAAA,QACR,cAAc;AAAA,MAChB,CAAC;AAAA,IACH;AAAA,EACF;AAEA,MAAI,IAAI,iBAAiB,IAAI,cAAc,QAAQ,GAAG;AACpD,QAAI,KAAK;AAAA,MACP,UAAU;AAAA,MACV,MAAM;AAAA,MACN,OAAO,GAAG,IAAI,cAAc,KAAK,eAAe,IAAI,cAAc,UAAU,IAAI,KAAK,GAAG;AAAA,MACxF,QAAQ;AAAA,MACR,cAAc;AAAA,IAChB,CAAC;AAAA,EACH;AAEA,MAAI,IAAI,cAAc,IAAI,WAAW,QAAQ,KAAK;AAChD,QAAI,KAAK;AAAA,MACP,UAAU;AAAA,MACV,MAAM;AAAA,MACN,OAAO,8BAA8B,IAAI,WAAW,MAAM,QAAQ,CAAC,CAAC;AAAA,MACpE,QACE;AAAA,MACF,cAAc;AAAA,IAChB,CAAC;AAAA,EACH;AAEA,MAAI,IAAI,mBAAmB,IAAI,gBAAgB,SAAS,SAAS,GAAG;AAClE,UAAM,MAAM,IAAI,gBAAgB,SAAS,CAAC;AAC1C,QAAI,KAAK;AAAA,MACP,UAAU;AAAA,MACV,MAAM;AAAA,MACN,OAAO,wBAAwB,IAAI,IAAI,MAAM,IAAI,QAAQ,KAAK,QAAQ,CAAC,CAAC;AAAA,MACxE,QAAQ,GAAG,IAAI,gBAAgB,aAAa,4CAA4C,IAAI,UAAU,MAAM,qBAAqB,IAAI,IAAI;AAAA,MACzI,cAAc;AAAA,IAChB,CAAC;AAAA,EACH;AAEA,MAAI,IAAI,sBAAsB,KAAK,IAAI,IAAI,mBAAmB,QAAQ,IAAI,KAAK;AAC7E,QAAI,KAAK;AAAA,MACP,UAAU;AAAA,MACV,MAAM;AAAA,MACN,OAAO,+BAA+B,IAAI,mBAAmB,MAAM,qBAAgB,IAAI,mBAAmB,SAAS,QAAQ,CAAC,CAAC;AAAA,MAC7H,QAAQ,yFAAyF,IAAI,mBAAmB,MAAM,2CAA2C,IAAI,mBAAmB,MAAM;AAAA,MACtM,cAAc;AAAA,IAChB,CAAC;AAAA,EACH;AAEA,SAAO;AACT;","names":["mean","agreement"]}

package/dist/chunk-MA6HLL3S.js

@@ -1,65 +0,0 @@
-// src/trace/schema.ts
-var TRACE_SCHEMA_VERSION = "1.0.0";
-var FAILURE_CLASSES = [
-  "success",
-  "reasoning_error",
-  "tool_selection_error",
-  "tool_argument_error",
-  "tool_recovery_failure",
-  "hallucination",
-  "instruction_following",
-  "safety_refusal_miss",
-  "policy_violation",
-  "budget_exceeded",
-  "format_drift",
-  "permission_escalation",
-  "pii_leak",
-  "cost_overrun",
-  "timeout",
-  "sandbox_failure",
-  "missing_user_data",
-  "missing_domain_data",
-  "missing_codebase_context",
-  "missing_runtime_context",
-  "missing_credentials",
-  "missing_integration_connection",
-  "missing_integration_scope",
-  "integration_approval_required",
-  "integration_auth_expired",
-  "integration_provider_failure",
-  "bad_integration_manifest",
-  "unsafe_integration_write_denied",
-  "stale_external_data",
-  "bad_retrieval",
-  "insufficient_evidence",
-  "contradictory_evidence",
-  "ambiguous_user_intent",
-  "knowledge_readiness_blocked",
-  "unknown"
-];
-function isLlmSpan(s) {
-  return s.kind === "llm";
-}
-function isToolSpan(s) {
-  return s.kind === "tool";
-}
-function isRetrievalSpan(s) {
-  return s.kind === "retrieval";
-}
-function isJudgeSpan(s) {
-  return s.kind === "judge";
-}
-function isSandboxSpan(s) {
-  return s.kind === "sandbox";
-}
-
-export {
-  TRACE_SCHEMA_VERSION,
-  FAILURE_CLASSES,
-  isLlmSpan,
-  isToolSpan,
-  isRetrievalSpan,
-  isJudgeSpan,
-  isSandboxSpan
-};
-//# sourceMappingURL=chunk-MA6HLL3S.js.map

package/dist/chunk-MA6HLL3S.js.map

@@ -1 +0,0 @@
-{"version":3,"sources":["../src/trace/schema.ts"],"sourcesContent":["/**\n * TraceSchema v1 — the canonical data model for agent-eval.\n *\n * Every score, every failure class, every pipeline in the framework is\n * a view over this data. Shape it once, live with it.\n *\n * Wire-compatible with OpenTelemetry span semantics (see trace/otel.ts)\n * but extended with agent-specific span kinds (llm, tool, retrieval,\n * judge, sandbox) and first-class BudgetLedger / Artifact / JudgeVerdict\n * entities that OTEL leaves as free-form attributes.\n */\n\nexport const TRACE_SCHEMA_VERSION = '1.0.0'\n\n// ── Run ──────────────────────────────────────────────────────────────\n\nexport type RunStatus = 'running' | 'completed' | 'failed' | 'aborted'\n\nexport interface BudgetSpec {\n  tokens?: number\n  wallMs?: number\n  calls?: number\n  usd?: number\n}\n\nexport interface RunOutcome {\n  score?: number\n  pass?: boolean\n  failureClass?: FailureClass\n  notes?: string\n}\n\n/**\n * Layer — optional classification in a nested build workflow.\n * `builder`: the meta-agent editing a project (e.g. agent-builder Forge chat).\n * `app-build`: sandbox harness that compiled + tested the generated scaffold.\n * `app-runtime`: a run of the generated agent against a domain scenario.\n * `meta`: any meta-eval (judge replay, correlation analysis).\n */\nexport type RunLayer = 'builder' | 'app-build' | 'app-runtime' | 'meta' | 'custom'\n\nexport interface Run {\n  runId: string\n  /**\n   * Stable identifier of the scenario being executed.\n   *\n   * Always populated on the persisted Run — but `TraceEmitter.startRun` accepts\n   * input WITHOUT this field, substituting a sensible default\n   * (`run.layer ?? run.tags?.['kind'] ?? 'runtime'`) when the caller has no\n   * curated scenario to anchor to (runtime / operator / meta-eval runs). This\n   * keeps the persisted shape unambiguous for downstream filters + aggregations\n   * while removing the boilerplate of inventing placeholder ids at the call site.\n   */\n  scenarioId: string\n  variantId?: string\n  datasetVersion?: string\n  /** Git SHA of agent code at run time. */\n  codeSha?: string\n  /** Hash of the prompt template + any system prompt. */\n  promptSha?: string\n  /** Model id + date + system-prompt hash, concatenated. */\n  modelFingerprint?: string\n  seed?: number\n  /** Arbitrary environment markers (shell, docker version, tz). */\n  envFingerprint?: Record<string, string>\n  /** Version of the redaction rules applied to this run. */\n  redactionVersion?: string\n  /** Parent run in a nested build workflow. A builder run's children are\n   *  app-build runs; those children are app-runtime runs. */\n  parentRunId?: string\n  /** Stable project identifier — groups runs across chats + sessions. */\n  projectId?: string\n  /** Chat/conversation identifier within a project. */\n  chatId?: string\n  /** Layer classification — hint for aggregation; not enforced. */\n  layer?: RunLayer\n  startedAt: number\n  endedAt?: number\n  status: RunStatus\n  outcome?: RunOutcome\n  budget?: BudgetSpec\n  /** Free-form labels for downstream grouping. */\n  tags?: Record<string, string>\n}\n\n// ── Spans (hierarchical work units) ──────────────────────────────────\n\nexport type SpanKind = 'agent' | 'llm' | 'tool' | 'retrieval' | 'judge' | 'sandbox' | 'custom'\n\nexport type SpanStatus = 'ok' | 'error'\n\nexport interface SpanBase {\n  spanId: string\n  parentSpanId?: string\n  runId: string\n  kind: SpanKind\n  name: string\n  startedAt: number\n  endedAt?: number\n  status?: SpanStatus\n  error?: string\n  /** Anything not covered by typed fields. Kept deliberately free-form. */\n  attributes?: Record<string, unknown>\n}\n\nexport interface Message {\n  role: 'system' | 'user' | 'assistant' | 'tool'\n  content: string\n  tokens?: number\n  /** Multi-modal content descriptors; blobs themselves live in Artifacts. */\n  images?: Array<{ artifactId?: string; url?: string; mime?: string }>\n}\n\nexport interface LlmSpan extends SpanBase {\n  kind: 'llm'\n  model: string\n  messages: Message[]\n  output?: string\n  inputTokens?: number\n  /** All generated tokens, including the reasoning subset when present. */\n  outputTokens?: number\n  cachedTokens?: number\n  cacheWriteTokens?: number\n  /** Reasoning-token subset of `outputTokens`. */\n  reasoningTokens?: number\n  costUsd?: number\n  finishReason?: string\n}\n\nexport interface ToolSpan extends SpanBase {\n  kind: 'tool'\n  toolName: string\n  args: unknown\n  /** False when the source observed the call but did not capture its arguments. */\n  argsCaptured?: boolean\n  result?: unknown\n  latencyMs?: number\n}\n\nexport interface RetrievalSpan extends SpanBase {\n  kind: 'retrieval'\n  query: string\n  hits: Array<{ docId: string; score: number; content?: string }>\n}\n\nexport interface JudgeSpan extends SpanBase {\n  kind: 'judge'\n  judgeId: string\n  /** Span this judgment applies to. */\n  targetSpanId: string\n  dimension: string\n  /** Numeric score (free-range; interpretation up to the judge). */\n  score: number\n  rationale?: string\n  evidence?: string\n}\n\nexport interface SandboxSpan extends SpanBase {\n  kind: 'sandbox'\n  image?: string\n  command?: string\n  exitCode?: number\n  testsTotal?: number\n  testsPassed?: number\n  stdoutHash?: string\n  stderrHash?: string\n  /** Duration in ms; the harness fills this explicitly (endedAt - startedAt may miss setup). */\n  wallMs?: number\n}\n\nexport interface GenericSpan extends SpanBase {\n  kind: 'agent' | 'custom'\n}\n\nexport type Span = LlmSpan | ToolSpan | RetrievalSpan | JudgeSpan | SandboxSpan | GenericSpan\n\n// ── Events (point-in-time occurrences within a span) ─────────────────\n\nexport type EventKind =\n  | 'log'\n  | 'error'\n  | 'budget_decrement'\n  | 'budget_breach'\n  | 'state_mutation'\n  | 'policy_violation'\n  | 'redaction_applied'\n  | 'custom'\n\nexport interface TraceEvent {\n  eventId: string\n  runId: string\n  spanId?: string\n  kind: EventKind\n  timestamp: number\n  payload: Record<string, unknown>\n}\n\n// ── Budget ledger (running token/wall/call/$ accounting) ─────────────\n\nexport interface BudgetLedgerEntry {\n  runId: string\n  dimension: keyof BudgetSpec\n  limit: number\n  consumed: number\n  remaining: number\n  timestamp: number\n  breached: boolean\n  /** Span that triggered this entry, if any. */\n  spanId?: string\n}\n\n// ── Artifacts (blobs addressed by hash) ──────────────────────────────\n\nexport interface Artifact {\n  artifactId: string\n  runId: string\n  spanId?: string\n  contentType: string\n  sizeBytes: number\n  /** sha256 in hex. */\n  hash: string\n  /** External storage URL (R2, S3, filesystem path). */\n  storageUrl?: string\n  /** Inline content for small blobs — keep under ~64KB. */\n  inlineContent?: string\n}\n\n// ── Failure taxonomy ─────────────────────────────────────────────────\n\nexport type FailureClass =\n  | 'success'\n  | 'reasoning_error'\n  | 'tool_selection_error'\n  | 'tool_argument_error'\n  | 'tool_recovery_failure'\n  | 'hallucination'\n  | 'instruction_following'\n  | 'safety_refusal_miss'\n  | 'policy_violation'\n  | 'budget_exceeded'\n  | 'format_drift'\n  | 'permission_escalation'\n  | 'pii_leak'\n  | 'cost_overrun'\n  | 'timeout'\n  | 'sandbox_failure'\n  | 'missing_user_data'\n  | 'missing_domain_data'\n  | 'missing_codebase_context'\n  | 'missing_runtime_context'\n  | 'missing_credentials'\n  | 'missing_integration_connection'\n  | 'missing_integration_scope'\n  | 'integration_approval_required'\n  | 'integration_auth_expired'\n  | 'integration_provider_failure'\n  | 'bad_integration_manifest'\n  | 'unsafe_integration_write_denied'\n  | 'stale_external_data'\n  | 'bad_retrieval'\n  | 'insufficient_evidence'\n  | 'contradictory_evidence'\n  | 'ambiguous_user_intent'\n  | 'knowledge_readiness_blocked'\n  | 'unknown'\n\nexport const FAILURE_CLASSES: readonly FailureClass[] = [\n  'success',\n  'reasoning_error',\n  'tool_selection_error',\n  'tool_argument_error',\n  'tool_recovery_failure',\n  'hallucination',\n  'instruction_following',\n  'safety_refusal_miss',\n  'policy_violation',\n  'budget_exceeded',\n  'format_drift',\n  'permission_escalation',\n  'pii_leak',\n  'cost_overrun',\n  'timeout',\n  'sandbox_failure',\n  'missing_user_data',\n  'missing_domain_data',\n  'missing_codebase_context',\n  'missing_runtime_context',\n  'missing_credentials',\n  'missing_integration_connection',\n  'missing_integration_scope',\n  'integration_approval_required',\n  'integration_auth_expired',\n  'integration_provider_failure',\n  'bad_integration_manifest',\n  'unsafe_integration_write_denied',\n  'stale_external_data',\n  'bad_retrieval',\n  'insufficient_evidence',\n  'contradictory_evidence',\n  'ambiguous_user_intent',\n  'knowledge_readiness_blocked',\n  'unknown',\n] as const\n\n// ── Helpers ──────────────────────────────────────────────────────────\n\nexport function isLlmSpan(s: Span): s is LlmSpan {\n  return s.kind === 'llm'\n}\nexport function isToolSpan(s: Span): s is ToolSpan {\n  return s.kind === 'tool'\n}\nexport function isRetrievalSpan(s: Span): s is RetrievalSpan {\n  return s.kind === 'retrieval'\n}\nexport function isJudgeSpan(s: Span): s is JudgeSpan {\n  return s.kind === 'judge'\n}\nexport function isSandboxSpan(s: Span): s is SandboxSpan {\n  return s.kind === 'sandbox'\n}\n"],"mappings":";AAYO,IAAM,uBAAuB;AA8P7B,IAAM,kBAA2C;AAAA,EACtD;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AACF;AAIO,SAAS,UAAU,GAAuB;AAC/C,SAAO,EAAE,SAAS;AACpB;AACO,SAAS,WAAW,GAAwB;AACjD,SAAO,EAAE,SAAS;AACpB;AACO,SAAS,gBAAgB,GAA6B;AAC3D,SAAO,EAAE,SAAS;AACpB;AACO,SAAS,YAAY,GAAyB;AACnD,SAAO,EAAE,SAAS;AACpB;AACO,SAAS,cAAc,GAA2B;AACvD,SAAO,EAAE,SAAS;AACpB;","names":[]}

package/dist/chunk-MAZ26DC7.js

@@ -1,99 +0,0 @@
-// src/sequential.ts
-function pairedEvalueSequence(deltas, opts = {}) {
-  const c = opts.bound ?? 1;
-  const alpha = opts.alpha ?? 0.05;
-  const initialShrink = opts.initialBetShrinkage ?? 0.5;
-  const rope = opts.rope ?? null;
-  if (c <= 0) throw new Error("pairedEvalueSequence: bound must be > 0");
-  if (alpha <= 0 || alpha >= 1) throw new Error("pairedEvalueSequence: alpha must be in (0,1)");
-  if (rope && !(Number.isFinite(rope.low) && Number.isFinite(rope.high) && rope.low <= rope.high)) {
-    throw new Error("pairedEvalueSequence: rope must satisfy low \u2264 high");
-  }
-  const steps = [];
-  let clipped = false;
-  let evalue = 1;
-  let decisionFiredAt = null;
-  let sum = 0;
-  let sumSq = 0;
-  let count = 0;
-  for (let i = 0; i < deltas.length; i++) {
-    let d = deltas[i];
-    if (d < -c || d > c) {
-      d = Math.max(-c, Math.min(c, d));
-      clipped = true;
-    }
-    const muHat = count === 0 ? 0 : sum / count;
-    const varHat = count === 0 ? c * c : Math.max(1e-12, sumSq / count - muHat * muHat);
-    const t = i + 1;
-    const shrink = initialShrink * Math.min(1, count / 32);
-    let lambda = muHat / (varHat + c * c) * shrink;
-    const lambdaMax = 0.99 / c;
-    if (lambda > lambdaMax) lambda = lambdaMax;
-    if (lambda < -lambdaMax) lambda = -lambdaMax;
-    evalue = evalue * (1 + lambda * d);
-    if (!Number.isFinite(evalue) || evalue < 0) evalue = 0;
-    sum += d;
-    sumSq += d * d;
-    count += 1;
-    const pValue = Math.min(1, 1 / Math.max(evalue, 1e-300));
-    const cs = empiricalBernsteinCs(sum, sumSq, count, c, alpha);
-    let decision = "continue";
-    if (rope && cs.low >= rope.low && cs.high <= rope.high) decision = "equivalent";
-    else if (evalue >= 2 / alpha && muHat > 0) decision = "promote_now";
-    else if (evalue >= 2 / alpha && muHat < 0) decision = "reject_now";
-    else if (rope && cs.high < rope.low) decision = "reject_now";
-    if (decision !== "continue" && decisionFiredAt === null) decisionFiredAt = t;
-    steps.push({ t, delta: d, evalue, pValue, csLow: cs.low, csHigh: cs.high, decision });
-  }
-  const finalDecision = steps.length === 0 ? "continue" : steps[steps.length - 1].decision;
-  return { steps, finalDecision, decisionFiredAt, clipped };
-}
-function evaluateInterimReleaseConfidence(input) {
-  const candidates = input.deltaSeries.map((s) => {
-    const seq = pairedEvalueSequence(s.deltas, {
-      alpha: input.alpha,
-      bound: input.bound,
-      rope: input.rope
-    });
-    const last = seq.steps[seq.steps.length - 1];
-    return {
-      candidateId: s.candidateId,
-      decision: seq.finalDecision,
-      decisionFiredAt: seq.decisionFiredAt,
-      finalEvalue: last?.evalue ?? 1,
-      finalPValue: last?.pValue ?? 1,
-      pairs: seq.steps.length,
-      csLow: last?.csLow ?? Number.NEGATIVE_INFINITY,
-      csHigh: last?.csHigh ?? Number.POSITIVE_INFINITY
-    };
-  });
-  const promote = candidates.find((c) => c.decision === "promote_now");
-  if (promote)
-    return {
-      candidates,
-      recommendation: { decision: "promote_now", candidateId: promote.candidateId }
-    };
-  const live = candidates.find((c) => c.decision === "continue");
-  if (live) return { candidates, recommendation: { decision: "continue", candidateId: null } };
-  const equiv = candidates.find((c) => c.decision === "equivalent");
-  if (equiv)
-    return {
-      candidates,
-      recommendation: { decision: "equivalent", candidateId: equiv.candidateId }
-    };
-  return { candidates, recommendation: { decision: "reject_now", candidateId: null } };
-}
-function empiricalBernsteinCs(sum, sumSq, n, bound, alpha) {
-  if (n === 0) return { low: -bound, high: bound };
-  const mean = sum / n;
-  const variance = Math.max(0, sumSq / n - mean * mean);
-  const psi = Math.log(2 / alpha) + 1.7 * Math.log(Math.log(Math.max(Math.E, n)) + 1);
-  const radius = Math.sqrt(2 * variance * psi / n) + 3 * bound * psi / n;
-  return { low: mean - radius, high: mean + radius };
-}
-
-export {
-  pairedEvalueSequence,
-  evaluateInterimReleaseConfidence
-};
-//# sourceMappingURL=chunk-MAZ26DC7.js.map

package/dist/chunk-MAZ26DC7.js.map

@@ -1 +0,0 @@
-{"version":3,"sources":["../src/sequential.ts"],"sourcesContent":["/**\n * Always-valid sequential evaluation.\n *\n * `researchReport` assumes a single pre-specified analysis. Real\n * consumers run campaigns weekly / nightly / per-PR; each new run silently\n * inflates the false-discovery rate, because the BH-FDR guarantee is for\n * the *first* look, not the 47th. Without time-uniform inference,\n * launch-decision teams either (a) don't peek, which forfeits the cost\n * advantage of stop-when-decisive, or (b) peek and pretend they didn't,\n * which forfeits scientific validity.\n *\n * This module ships **e-value-based confidence sequences** for paired\n * bounded outcomes. The methodology is the predictable plug-in betting\n * martingale of Waudby-Smith & Ramdas (2024) — provably valid at *any*\n * stopping time. Concretely:\n *\n *   For paired deltas D_1, D_2, … ∈ [-c, c] with the null H_0: E[D] ≤ 0,\n *   a betting fraction λ_i is chosen using only D_{1..i-1} (predictable\n *   plug-in), and the running e-value is\n *\n *     E_t = ∏_{i=1}^{t} (1 + λ_i · D_i)\n *\n *   E_t is a non-negative martingale under H_0 with E[E_t] ≤ 1, so by\n *   Ville's inequality, P(∃ t : E_t ≥ 1/α) ≤ α — we can reject the null\n *   at any time without inflating the type-I error.\n *\n * Combined with `runEvalCampaign`, every consumer running rolling\n * campaigns gains the ability to ship the moment evidence is decisive,\n * stop-early on dead-on-arrival variants, and accumulate evidence across\n * partial runs without spending the FDR budget. No new sweep is wasted.\n *\n * References:\n *   - Howard, S. R., Ramdas, A., McAuliffe, J., Sekhon, J. (2021).\n *     Time-uniform, nonparametric, nonasymptotic confidence sequences.\n *     Annals of Statistics, 49(2), 1055–1080.\n *   - Waudby-Smith, I., Ramdas, A. (2024). Estimating means of bounded\n *     random variables by betting. JRSS B, 86(1), 1–27.\n */\n\nexport type SequentialDecision = 'promote_now' | 'continue' | 'reject_now' | 'equivalent'\n\nexport interface PairedEvalueOptions {\n  /**\n   * Bound on |delta|. Default 1 (matching most score scales). Must satisfy\n   * c > 0; deltas outside [-c, c] are clipped with a warning attached to\n   * the return value.\n   */\n  bound?: number\n  /** Target Type-I error. Default 0.05. */\n  alpha?: number\n  /**\n   * Region of Practical Equivalence on the *mean* paired delta. When\n   * supplied, the verdict can return `'equivalent'` once the running\n   * confidence sequence on the mean is fully contained in [low, high].\n   */\n  rope?: { low: number; high: number }\n  /** Initial bet shrinkage (0 < scale ≤ 1). Default 0.5 — empirically robust. */\n  initialBetShrinkage?: number\n}\n\nexport interface PairedEvalueStep {\n  /** 1-indexed observation count. */\n  t: number\n  delta: number\n  /** Running e-value E_t = ∏ (1 + λ_i · D_i). */\n  evalue: number\n  /** Time-uniform p-value at stopping time t. */\n  pValue: number\n  /** Lower bound of the empirical Bernstein confidence sequence at level 1-α. */\n  csLow: number\n  csHigh: number\n  /** Verdict at this stopping time. */\n  decision: SequentialDecision\n}\n\nexport interface PairedEvalueSequence {\n  steps: PairedEvalueStep[]\n  /** The decision at the final step. */\n  finalDecision: SequentialDecision\n  /** Index (1-based) at which a non-`continue` decision first fired, or null. */\n  decisionFiredAt: number | null\n  /** True if any deltas were clipped to [-bound, bound]. */\n  clipped: boolean\n}\n\n/**\n * Run the paired e-value sequence over an in-order delta stream.\n *\n * Use for *streaming* / interim analyses: pass the deltas you have so\n * far, get the verdict at every prefix length. The decision is\n * monotone-stable in the sense that once `'reject_now'` or `'promote_now'`\n * fires, the verdict at later steps remains decisive (the e-value is a\n * non-negative martingale; once it crosses the threshold, it's crossed).\n */\nexport function pairedEvalueSequence(\n  deltas: number[],\n  opts: PairedEvalueOptions = {},\n): PairedEvalueSequence {\n  const c = opts.bound ?? 1\n  const alpha = opts.alpha ?? 0.05\n  const initialShrink = opts.initialBetShrinkage ?? 0.5\n  const rope = opts.rope ?? null\n  if (c <= 0) throw new Error('pairedEvalueSequence: bound must be > 0')\n  if (alpha <= 0 || alpha >= 1) throw new Error('pairedEvalueSequence: alpha must be in (0,1)')\n  if (rope && !(Number.isFinite(rope.low) && Number.isFinite(rope.high) && rope.low <= rope.high)) {\n    throw new Error('pairedEvalueSequence: rope must satisfy low ≤ high')\n  }\n\n  const steps: PairedEvalueStep[] = []\n  let clipped = false\n  let evalue = 1\n  let decisionFiredAt: number | null = null\n\n  // Running statistics (using only D_{1..i-1} for the bet → predictable plug-in).\n  let sum = 0\n  let sumSq = 0\n  let count = 0\n\n  for (let i = 0; i < deltas.length; i++) {\n    let d = deltas[i]!\n    if (d < -c || d > c) {\n      d = Math.max(-c, Math.min(c, d))\n      clipped = true\n    }\n\n    // Predictable plug-in bet (positive λ tests for E[D] > 0; we run a two-sided\n    // test by tracking the symmetric e-value via |bet|).\n    // λ_i ∝ mean / (variance + bound^2). Shrink early to avoid overbetting.\n    const muHat = count === 0 ? 0 : sum / count\n    const varHat = count === 0 ? c * c : Math.max(1e-12, sumSq / count - muHat * muHat)\n    const t = i + 1\n    const shrink = initialShrink * Math.min(1, count / 32) // anneal toward 1\n    let lambda = (muHat / (varHat + c * c)) * shrink\n    // Clip to ensure 1 + λ·D > 0 for all |D| ≤ c (so the e-value stays non-negative).\n    const lambdaMax = 0.99 / c\n    if (lambda > lambdaMax) lambda = lambdaMax\n    if (lambda < -lambdaMax) lambda = -lambdaMax\n\n    evalue = evalue * (1 + lambda * d)\n    if (!Number.isFinite(evalue) || evalue < 0) evalue = 0\n\n    sum += d\n    sumSq += d * d\n    count += 1\n\n    const pValue = Math.min(1, 1 / Math.max(evalue, 1e-300))\n\n    // Empirical Bernstein confidence sequence on the mean. Howard et al.\n    // (2021), Theorem 4.4 with σ̂² the running sample variance and a\n    // calibration constant tuned for two-sided coverage at level 1 - α.\n    const cs = empiricalBernsteinCs(sum, sumSq, count, c, alpha)\n\n    let decision: SequentialDecision = 'continue'\n    if (rope && cs.low >= rope.low && cs.high <= rope.high) decision = 'equivalent'\n    else if (evalue >= 2 / alpha && muHat > 0) decision = 'promote_now'\n    else if (evalue >= 2 / alpha && muHat < 0) decision = 'reject_now'\n    else if (rope && cs.high < rope.low) decision = 'reject_now'\n\n    if (decision !== 'continue' && decisionFiredAt === null) decisionFiredAt = t\n\n    steps.push({ t, delta: d, evalue, pValue, csLow: cs.low, csHigh: cs.high, decision })\n  }\n\n  const finalDecision = steps.length === 0 ? 'continue' : steps[steps.length - 1]!.decision\n  return { steps, finalDecision, decisionFiredAt, clipped }\n}\n\nexport interface InterimReleaseConfidenceInput {\n  /**\n   * One delta series per candidate (paired deltas vs comparator). Order\n   * within a series is the order the campaigns were run.\n   */\n  deltaSeries: Array<{ candidateId: string; deltas: number[] }>\n  alpha?: number\n  bound?: number\n  rope?: { low: number; high: number }\n}\n\nexport interface InterimReleaseConfidence {\n  candidates: Array<{\n    candidateId: string\n    decision: SequentialDecision\n    decisionFiredAt: number | null\n    finalEvalue: number\n    finalPValue: number\n    pairs: number\n    csLow: number\n    csHigh: number\n  }>\n  /**\n   * Campaign-level recommendation: pick the strongest 'promote_now', else\n   * 'continue' if any candidate is still live, else 'reject_now' if every\n   * candidate is dead, else 'equivalent'.\n   */\n  recommendation: { decision: SequentialDecision; candidateId: string | null }\n}\n\n/**\n * Run interim sequential analyses across many candidates at once,\n * preserving the time-uniform α guarantee for each candidate's series and\n * synthesising a campaign-level recommendation. Designed to be called on\n * every campaign tick — the recommendation is anytime-valid.\n */\nexport function evaluateInterimReleaseConfidence(\n  input: InterimReleaseConfidenceInput,\n): InterimReleaseConfidence {\n  const candidates = input.deltaSeries.map((s) => {\n    const seq = pairedEvalueSequence(s.deltas, {\n      alpha: input.alpha,\n      bound: input.bound,\n      rope: input.rope,\n    })\n    const last = seq.steps[seq.steps.length - 1]\n    return {\n      candidateId: s.candidateId,\n      decision: seq.finalDecision,\n      decisionFiredAt: seq.decisionFiredAt,\n      finalEvalue: last?.evalue ?? 1,\n      finalPValue: last?.pValue ?? 1,\n      pairs: seq.steps.length,\n      csLow: last?.csLow ?? Number.NEGATIVE_INFINITY,\n      csHigh: last?.csHigh ?? Number.POSITIVE_INFINITY,\n    }\n  })\n\n  const promote = candidates.find((c) => c.decision === 'promote_now')\n  if (promote)\n    return {\n      candidates,\n      recommendation: { decision: 'promote_now', candidateId: promote.candidateId },\n    }\n  const live = candidates.find((c) => c.decision === 'continue')\n  if (live) return { candidates, recommendation: { decision: 'continue', candidateId: null } }\n  const equiv = candidates.find((c) => c.decision === 'equivalent')\n  if (equiv)\n    return {\n      candidates,\n      recommendation: { decision: 'equivalent', candidateId: equiv.candidateId },\n    }\n  return { candidates, recommendation: { decision: 'reject_now', candidateId: null } }\n}\n\n// ── Internals ────────────────────────────────────────────────────────────\n\n/**\n * Empirical Bernstein confidence sequence on the mean of bounded variables.\n * Adapted from Howard et al. (2021) §4.4. Provides a time-uniform CI on\n * the running mean; valid at every stopping time.\n */\nfunction empiricalBernsteinCs(\n  sum: number,\n  sumSq: number,\n  n: number,\n  bound: number,\n  alpha: number,\n): { low: number; high: number } {\n  if (n === 0) return { low: -bound, high: bound }\n  const mean = sum / n\n  const variance = Math.max(0, sumSq / n - mean * mean)\n  // Iterated-log calibration constant. The 1.7 exponent matches the\n  // recommended choice in Howard et al. for two-sided coverage at level\n  // 1 - α with mild log-corrections; tightening further requires a\n  // tuned mixture and is out of scope.\n  const psi = Math.log(2 / alpha) + 1.7 * Math.log(Math.log(Math.max(Math.E, n)) + 1)\n  const radius = Math.sqrt((2 * variance * psi) / n) + (3 * bound * psi) / n\n  return { low: mean - radius, high: mean + radius }\n}\n"],"mappings":";AA8FO,SAAS,qBACd,QACA,OAA4B,CAAC,GACP;AACtB,QAAM,IAAI,KAAK,SAAS;AACxB,QAAM,QAAQ,KAAK,SAAS;AAC5B,QAAM,gBAAgB,KAAK,uBAAuB;AAClD,QAAM,OAAO,KAAK,QAAQ;AAC1B,MAAI,KAAK,EAAG,OAAM,IAAI,MAAM,yCAAyC;AACrE,MAAI,SAAS,KAAK,SAAS,EAAG,OAAM,IAAI,MAAM,8CAA8C;AAC5F,MAAI,QAAQ,EAAE,OAAO,SAAS,KAAK,GAAG,KAAK,OAAO,SAAS,KAAK,IAAI,KAAK,KAAK,OAAO,KAAK,OAAO;AAC/F,UAAM,IAAI,MAAM,yDAAoD;AAAA,EACtE;AAEA,QAAM,QAA4B,CAAC;AACnC,MAAI,UAAU;AACd,MAAI,SAAS;AACb,MAAI,kBAAiC;AAGrC,MAAI,MAAM;AACV,MAAI,QAAQ;AACZ,MAAI,QAAQ;AAEZ,WAAS,IAAI,GAAG,IAAI,OAAO,QAAQ,KAAK;AACtC,QAAI,IAAI,OAAO,CAAC;AAChB,QAAI,IAAI,CAAC,KAAK,IAAI,GAAG;AACnB,UAAI,KAAK,IAAI,CAAC,GAAG,KAAK,IAAI,GAAG,CAAC,CAAC;AAC/B,gBAAU;AAAA,IACZ;AAKA,UAAM,QAAQ,UAAU,IAAI,IAAI,MAAM;AACtC,UAAM,SAAS,UAAU,IAAI,IAAI,IAAI,KAAK,IAAI,OAAO,QAAQ,QAAQ,QAAQ,KAAK;AAClF,UAAM,IAAI,IAAI;AACd,UAAM,SAAS,gBAAgB,KAAK,IAAI,GAAG,QAAQ,EAAE;AACrD,QAAI,SAAU,SAAS,SAAS,IAAI,KAAM;AAE1C,UAAM,YAAY,OAAO;AACzB,QAAI,SAAS,UAAW,UAAS;AACjC,QAAI,SAAS,CAAC,UAAW,UAAS,CAAC;AAEnC,aAAS,UAAU,IAAI,SAAS;AAChC,QAAI,CAAC,OAAO,SAAS,MAAM,KAAK,SAAS,EAAG,UAAS;AAErD,WAAO;AACP,aAAS,IAAI;AACb,aAAS;AAET,UAAM,SAAS,KAAK,IAAI,GAAG,IAAI,KAAK,IAAI,QAAQ,MAAM,CAAC;AAKvD,UAAM,KAAK,qBAAqB,KAAK,OAAO,OAAO,GAAG,KAAK;AAE3D,QAAI,WAA+B;AACnC,QAAI,QAAQ,GAAG,OAAO,KAAK,OAAO,GAAG,QAAQ,KAAK,KAAM,YAAW;AAAA,aAC1D,UAAU,IAAI,SAAS,QAAQ,EAAG,YAAW;AAAA,aAC7C,UAAU,IAAI,SAAS,QAAQ,EAAG,YAAW;AAAA,aAC7C,QAAQ,GAAG,OAAO,KAAK,IAAK,YAAW;AAEhD,QAAI,aAAa,cAAc,oBAAoB,KAAM,mBAAkB;AAE3E,UAAM,KAAK,EAAE,GAAG,OAAO,GAAG,QAAQ,QAAQ,OAAO,GAAG,KAAK,QAAQ,GAAG,MAAM,SAAS,CAAC;AAAA,EACtF;AAEA,QAAM,gBAAgB,MAAM,WAAW,IAAI,aAAa,MAAM,MAAM,SAAS,CAAC,EAAG;AACjF,SAAO,EAAE,OAAO,eAAe,iBAAiB,QAAQ;AAC1D;AAsCO,SAAS,iCACd,OAC0B;AAC1B,QAAM,aAAa,MAAM,YAAY,IAAI,CAAC,MAAM;AAC9C,UAAM,MAAM,qBAAqB,EAAE,QAAQ;AAAA,MACzC,OAAO,MAAM;AAAA,MACb,OAAO,MAAM;AAAA,MACb,MAAM,MAAM;AAAA,IACd,CAAC;AACD,UAAM,OAAO,IAAI,MAAM,IAAI,MAAM,SAAS,CAAC;AAC3C,WAAO;AAAA,MACL,aAAa,EAAE;AAAA,MACf,UAAU,IAAI;AAAA,MACd,iBAAiB,IAAI;AAAA,MACrB,aAAa,MAAM,UAAU;AAAA,MAC7B,aAAa,MAAM,UAAU;AAAA,MAC7B,OAAO,IAAI,MAAM;AAAA,MACjB,OAAO,MAAM,SAAS,OAAO;AAAA,MAC7B,QAAQ,MAAM,UAAU,OAAO;AAAA,IACjC;AAAA,EACF,CAAC;AAED,QAAM,UAAU,WAAW,KAAK,CAAC,MAAM,EAAE,aAAa,aAAa;AACnE,MAAI;AACF,WAAO;AAAA,MACL;AAAA,MACA,gBAAgB,EAAE,UAAU,eAAe,aAAa,QAAQ,YAAY;AAAA,IAC9E;AACF,QAAM,OAAO,WAAW,KAAK,CAAC,MAAM,EAAE,aAAa,UAAU;AAC7D,MAAI,KAAM,QAAO,EAAE,YAAY,gBAAgB,EAAE,UAAU,YAAY,aAAa,KAAK,EAAE;AAC3F,QAAM,QAAQ,WAAW,KAAK,CAAC,MAAM,EAAE,aAAa,YAAY;AAChE,MAAI;AACF,WAAO;AAAA,MACL;AAAA,MACA,gBAAgB,EAAE,UAAU,cAAc,aAAa,MAAM,YAAY;AAAA,IAC3E;AACF,SAAO,EAAE,YAAY,gBAAgB,EAAE,UAAU,cAAc,aAAa,KAAK,EAAE;AACrF;AASA,SAAS,qBACP,KACA,OACA,GACA,OACA,OAC+B;AAC/B,MAAI,MAAM,EAAG,QAAO,EAAE,KAAK,CAAC,OAAO,MAAM,MAAM;AAC/C,QAAM,OAAO,MAAM;AACnB,QAAM,WAAW,KAAK,IAAI,GAAG,QAAQ,IAAI,OAAO,IAAI;AAKpD,QAAM,MAAM,KAAK,IAAI,IAAI,KAAK,IAAI,MAAM,KAAK,IAAI,KAAK,IAAI,KAAK,IAAI,KAAK,GAAG,CAAC,CAAC,IAAI,CAAC;AAClF,QAAM,SAAS,KAAK,KAAM,IAAI,WAAW,MAAO,CAAC,IAAK,IAAI,QAAQ,MAAO;AACzE,SAAO,EAAE,KAAK,OAAO,QAAQ,MAAM,OAAO,OAAO;AACnD;","names":[]}

package/dist/chunk-NPCTHQIO.js

@@ -1,91 +0,0 @@
-// src/meta-eval/calibration.ts
-async function calibrationCurve(traceStore, outcomeStore, evalMetric, outcomeMetric, options = {}) {
-  const runs = await traceStore.listRuns();
-  const outcomes = await outcomeStore.list();
-  const byRun = /* @__PURE__ */ new Map();
-  for (const o of outcomes) {
-    const arr = byRun.get(o.runId) ?? [];
-    arr.push(o);
-    byRun.set(o.runId, arr);
-  }
-  const extract = evalMetric.extract ?? defaultExtract(evalMetric.id);
-  const pairs = [];
-  for (const run of runs) {
-    const os = byRun.get(run.runId);
-    if (!os?.length) continue;
-    const x = await extract(run, traceStore);
-    if (x === null || !Number.isFinite(x)) continue;
-    const latest = [...os].sort((a, b) => b.capturedAt - a.capturedAt)[0];
-    const y = latest.metrics[outcomeMetric];
-    if (typeof y !== "number" || !Number.isFinite(y)) continue;
-    pairs.push({ x, y });
-  }
-  if (pairs.length < 2) return null;
-  return calibrationFromPairs(
-    pairs.map((p) => ({ evalScore: p.x, outcome: p.y })),
-    evalMetric.id,
-    outcomeMetric,
-    options
-  );
-}
-function calibrationFromPairs(inputPairs, evalMetric, outcomeMetric, options = {}) {
-  const pairs = inputPairs.filter(
-    (pair) => Number.isFinite(pair.evalScore) && Number.isFinite(pair.outcome)
-  );
-  if (pairs.length < 2) return null;
-  const numBins = options.bins ?? 10;
-  const binning = options.binning ?? "equal-width";
-  const xs = pairs.map((p) => p.evalScore);
-  const lo = options.range?.lo ?? Math.min(...xs);
-  const hi = options.range?.hi ?? Math.max(...xs);
-  const bins = [];
-  if (binning === "equal-frequency") {
-    const sorted = [...pairs].sort((a, b) => a.evalScore - b.evalScore);
-    const perBin = Math.max(1, Math.floor(sorted.length / numBins));
-    for (let i = 0; i < sorted.length; i += perBin) {
-      const chunk = sorted.slice(i, i + perBin);
-      if (chunk.length === 0) continue;
-      bins.push(toBin(chunk));
-    }
-  } else {
-    const width = (hi - lo) / numBins;
-    if (width === 0) return null;
-    for (let i = 0; i < numBins; i++) {
-      const binLo = lo + i * width;
-      const binHi = i === numBins - 1 ? hi + 1e-9 : lo + (i + 1) * width;
-      const chunk = pairs.filter((p) => p.evalScore >= binLo && p.evalScore < binHi);
-      if (chunk.length === 0) continue;
-      bins.push(toBin(chunk, binLo, binHi));
-    }
-  }
-  const total = bins.reduce((a, b) => a + b.n, 0);
-  const ece = bins.reduce((a, b) => a + b.n / total * b.gap, 0);
-  const maxGap = bins.reduce((a, b) => Math.max(a, b.gap), 0);
-  return { evalMetric, outcomeMetric, n: pairs.length, bins, ece, maxGap };
-}
-function toBin(chunk, lower, upper) {
-  const xs = chunk.map((c) => c.evalScore);
-  const ys = chunk.map((c) => c.outcome);
-  const evalMean = mean(xs);
-  const outcomeMean = mean(ys);
-  return {
-    lower: lower ?? Math.min(...xs),
-    upper: upper ?? Math.max(...xs),
-    n: chunk.length,
-    evalMean,
-    outcomeMean,
-    gap: Math.abs(outcomeMean - evalMean)
-  };
-}
-function mean(xs) {
-  return xs.reduce((a, b) => a + b, 0) / xs.length;
-}
-function defaultExtract(metric) {
-  return async (run) => run.outcome?.score ?? (metric === "pass" ? run.outcome?.pass === true ? 1 : 0 : null);
-}
-
-export {
-  calibrationCurve,
-  calibrationFromPairs
-};
-//# sourceMappingURL=chunk-NPCTHQIO.js.map

package/dist/chunk-NPCTHQIO.js.map

@@ -1 +0,0 @@
-{"version":3,"sources":["../src/meta-eval/calibration.ts"],"sourcesContent":["/**\n * Calibration curve — binned \"if eval says X, what does reality show?\"\n *\n * Companion to correlationStudy. Raw correlation is a single number;\n * the calibration curve shows *where* the eval is well-calibrated vs\n * overconfident / underconfident. Buckets the eval metric, computes\n * mean outcome per bucket, reports expected-calibration-error (ECE).\n */\n\nimport type { Run } from '../trace/schema'\nimport type { TraceStore } from '../trace/store'\nimport type { EvalMetricSpec } from './correlation-study'\nimport type { DeploymentOutcome, OutcomeStore } from './outcome-store'\n\nexport interface CalibrationBin {\n  lower: number\n  upper: number\n  n: number\n  evalMean: number\n  outcomeMean: number\n  /** |outcomeMean − evalMean|; contributes to ECE weighted by n/total. */\n  gap: number\n}\n\nexport interface CalibrationReport {\n  evalMetric: string\n  outcomeMetric: string\n  n: number\n  bins: CalibrationBin[]\n  /** Expected Calibration Error — Σ (n_i/N) × |outcomeMean_i − evalMean_i|. */\n  ece: number\n  /** Max bin gap — upper bound on miscalibration. */\n  maxGap: number\n}\n\nexport interface CalibrationOptions {\n  bins?: number\n  /** Equal-width (fixed bin edges) or equal-frequency (quantile bins). */\n  binning?: 'equal-width' | 'equal-frequency'\n  /** Clip eval values to [lo, hi] before binning. */\n  range?: { lo: number; hi: number }\n}\n\nexport interface CalibrationPair {\n  evalScore: number\n  outcome: number\n}\n\nexport async function calibrationCurve(\n  traceStore: TraceStore,\n  outcomeStore: OutcomeStore,\n  evalMetric: EvalMetricSpec,\n  outcomeMetric: string,\n  options: CalibrationOptions = {},\n): Promise<CalibrationReport | null> {\n  const runs = await traceStore.listRuns()\n  const outcomes = await outcomeStore.list()\n  const byRun = new Map<string, DeploymentOutcome[]>()\n  for (const o of outcomes) {\n    const arr = byRun.get(o.runId) ?? []\n    arr.push(o)\n    byRun.set(o.runId, arr)\n  }\n\n  const extract = evalMetric.extract ?? defaultExtract(evalMetric.id)\n  const pairs: Array<{ x: number; y: number }> = []\n  for (const run of runs) {\n    const os = byRun.get(run.runId)\n    if (!os?.length) continue\n    const x = await extract(run, traceStore)\n    if (x === null || !Number.isFinite(x)) continue\n    const latest = [...os].sort((a, b) => b.capturedAt - a.capturedAt)[0]!\n    const y = latest.metrics[outcomeMetric]\n    if (typeof y !== 'number' || !Number.isFinite(y)) continue\n    pairs.push({ x, y })\n  }\n  if (pairs.length < 2) return null\n\n  return calibrationFromPairs(\n    pairs.map((p) => ({ evalScore: p.x, outcome: p.y })),\n    evalMetric.id,\n    outcomeMetric,\n    options,\n  )\n}\n\nexport function calibrationFromPairs(\n  inputPairs: CalibrationPair[],\n  evalMetric: string,\n  outcomeMetric: string,\n  options: CalibrationOptions = {},\n): CalibrationReport | null {\n  const pairs = inputPairs.filter(\n    (pair) => Number.isFinite(pair.evalScore) && Number.isFinite(pair.outcome),\n  )\n  if (pairs.length < 2) return null\n\n  const numBins = options.bins ?? 10\n  const binning = options.binning ?? 'equal-width'\n  const xs = pairs.map((p) => p.evalScore)\n  const lo = options.range?.lo ?? Math.min(...xs)\n  const hi = options.range?.hi ?? Math.max(...xs)\n\n  const bins: CalibrationBin[] = []\n  if (binning === 'equal-frequency') {\n    const sorted = [...pairs].sort((a, b) => a.evalScore - b.evalScore)\n    const perBin = Math.max(1, Math.floor(sorted.length / numBins))\n    for (let i = 0; i < sorted.length; i += perBin) {\n      const chunk = sorted.slice(i, i + perBin)\n      if (chunk.length === 0) continue\n      bins.push(toBin(chunk))\n    }\n  } else {\n    const width = (hi - lo) / numBins\n    if (width === 0) return null\n    for (let i = 0; i < numBins; i++) {\n      const binLo = lo + i * width\n      const binHi = i === numBins - 1 ? hi + 1e-9 : lo + (i + 1) * width\n      const chunk = pairs.filter((p) => p.evalScore >= binLo && p.evalScore < binHi)\n      if (chunk.length === 0) continue\n      bins.push(toBin(chunk, binLo, binHi))\n    }\n  }\n\n  const total = bins.reduce((a, b) => a + b.n, 0)\n  const ece = bins.reduce((a, b) => a + (b.n / total) * b.gap, 0)\n  const maxGap = bins.reduce((a, b) => Math.max(a, b.gap), 0)\n\n  return { evalMetric, outcomeMetric, n: pairs.length, bins, ece, maxGap }\n}\n\nfunction toBin(chunk: CalibrationPair[], lower?: number, upper?: number): CalibrationBin {\n  const xs = chunk.map((c) => c.evalScore)\n  const ys = chunk.map((c) => c.outcome)\n  const evalMean = mean(xs)\n  const outcomeMean = mean(ys)\n  return {\n    lower: lower ?? Math.min(...xs),\n    upper: upper ?? Math.max(...xs),\n    n: chunk.length,\n    evalMean,\n    outcomeMean,\n    gap: Math.abs(outcomeMean - evalMean),\n  }\n}\n\nfunction mean(xs: number[]): number {\n  return xs.reduce((a, b) => a + b, 0) / xs.length\n}\n\nfunction defaultExtract(metric: string): (run: Run, store: TraceStore) => Promise<number | null> {\n  return async (run) =>\n    run.outcome?.score ?? (metric === 'pass' ? (run.outcome?.pass === true ? 1 : 0) : null)\n}\n"],"mappings":";AAgDA,eAAsB,iBACpB,YACA,cACA,YACA,eACA,UAA8B,CAAC,GACI;AACnC,QAAM,OAAO,MAAM,WAAW,SAAS;AACvC,QAAM,WAAW,MAAM,aAAa,KAAK;AACzC,QAAM,QAAQ,oBAAI,IAAiC;AACnD,aAAW,KAAK,UAAU;AACxB,UAAM,MAAM,MAAM,IAAI,EAAE,KAAK,KAAK,CAAC;AACnC,QAAI,KAAK,CAAC;AACV,UAAM,IAAI,EAAE,OAAO,GAAG;AAAA,EACxB;AAEA,QAAM,UAAU,WAAW,WAAW,eAAe,WAAW,EAAE;AAClE,QAAM,QAAyC,CAAC;AAChD,aAAW,OAAO,MAAM;AACtB,UAAM,KAAK,MAAM,IAAI,IAAI,KAAK;AAC9B,QAAI,CAAC,IAAI,OAAQ;AACjB,UAAM,IAAI,MAAM,QAAQ,KAAK,UAAU;AACvC,QAAI,MAAM,QAAQ,CAAC,OAAO,SAAS,CAAC,EAAG;AACvC,UAAM,SAAS,CAAC,GAAG,EAAE,EAAE,KAAK,CAAC,GAAG,MAAM,EAAE,aAAa,EAAE,UAAU,EAAE,CAAC;AACpE,UAAM,IAAI,OAAO,QAAQ,aAAa;AACtC,QAAI,OAAO,MAAM,YAAY,CAAC,OAAO,SAAS,CAAC,EAAG;AAClD,UAAM,KAAK,EAAE,GAAG,EAAE,CAAC;AAAA,EACrB;AACA,MAAI,MAAM,SAAS,EAAG,QAAO;AAE7B,SAAO;AAAA,IACL,MAAM,IAAI,CAAC,OAAO,EAAE,WAAW,EAAE,GAAG,SAAS,EAAE,EAAE,EAAE;AAAA,IACnD,WAAW;AAAA,IACX;AAAA,IACA;AAAA,EACF;AACF;AAEO,SAAS,qBACd,YACA,YACA,eACA,UAA8B,CAAC,GACL;AAC1B,QAAM,QAAQ,WAAW;AAAA,IACvB,CAAC,SAAS,OAAO,SAAS,KAAK,SAAS,KAAK,OAAO,SAAS,KAAK,OAAO;AAAA,EAC3E;AACA,MAAI,MAAM,SAAS,EAAG,QAAO;AAE7B,QAAM,UAAU,QAAQ,QAAQ;AAChC,QAAM,UAAU,QAAQ,WAAW;AACnC,QAAM,KAAK,MAAM,IAAI,CAAC,MAAM,EAAE,SAAS;AACvC,QAAM,KAAK,QAAQ,OAAO,MAAM,KAAK,IAAI,GAAG,EAAE;AAC9C,QAAM,KAAK,QAAQ,OAAO,MAAM,KAAK,IAAI,GAAG,EAAE;AAE9C,QAAM,OAAyB,CAAC;AAChC,MAAI,YAAY,mBAAmB;AACjC,UAAM,SAAS,CAAC,GAAG,KAAK,EAAE,KAAK,CAAC,GAAG,MAAM,EAAE,YAAY,EAAE,SAAS;AAClE,UAAM,SAAS,KAAK,IAAI,GAAG,KAAK,MAAM,OAAO,SAAS,OAAO,CAAC;AAC9D,aAAS,IAAI,GAAG,IAAI,OAAO,QAAQ,KAAK,QAAQ;AAC9C,YAAM,QAAQ,OAAO,MAAM,GAAG,IAAI,MAAM;AACxC,UAAI,MAAM,WAAW,EAAG;AACxB,WAAK,KAAK,MAAM,KAAK,CAAC;AAAA,IACxB;AAAA,EACF,OAAO;AACL,UAAM,SAAS,KAAK,MAAM;AAC1B,QAAI,UAAU,EAAG,QAAO;AACxB,aAAS,IAAI,GAAG,IAAI,SAAS,KAAK;AAChC,YAAM,QAAQ,KAAK,IAAI;AACvB,YAAM,QAAQ,MAAM,UAAU,IAAI,KAAK,OAAO,MAAM,IAAI,KAAK;AAC7D,YAAM,QAAQ,MAAM,OAAO,CAAC,MAAM,EAAE,aAAa,SAAS,EAAE,YAAY,KAAK;AAC7E,UAAI,MAAM,WAAW,EAAG;AACxB,WAAK,KAAK,MAAM,OAAO,OAAO,KAAK,CAAC;AAAA,IACtC;AAAA,EACF;AAEA,QAAM,QAAQ,KAAK,OAAO,CAAC,GAAG,MAAM,IAAI,EAAE,GAAG,CAAC;AAC9C,QAAM,MAAM,KAAK,OAAO,CAAC,GAAG,MAAM,IAAK,EAAE,IAAI,QAAS,EAAE,KAAK,CAAC;AAC9D,QAAM,SAAS,KAAK,OAAO,CAAC,GAAG,MAAM,KAAK,IAAI,GAAG,EAAE,GAAG,GAAG,CAAC;AAE1D,SAAO,EAAE,YAAY,eAAe,GAAG,MAAM,QAAQ,MAAM,KAAK,OAAO;AACzE;AAEA,SAAS,MAAM,OAA0B,OAAgB,OAAgC;AACvF,QAAM,KAAK,MAAM,IAAI,CAAC,MAAM,EAAE,SAAS;AACvC,QAAM,KAAK,MAAM,IAAI,CAAC,MAAM,EAAE,OAAO;AACrC,QAAM,WAAW,KAAK,EAAE;AACxB,QAAM,cAAc,KAAK,EAAE;AAC3B,SAAO;AAAA,IACL,OAAO,SAAS,KAAK,IAAI,GAAG,EAAE;AAAA,IAC9B,OAAO,SAAS,KAAK,IAAI,GAAG,EAAE;AAAA,IAC9B,GAAG,MAAM;AAAA,IACT;AAAA,IACA;AAAA,IACA,KAAK,KAAK,IAAI,cAAc,QAAQ;AAAA,EACtC;AACF;AAEA,SAAS,KAAK,IAAsB;AAClC,SAAO,GAAG,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,GAAG;AAC5C;AAEA,SAAS,eAAe,QAAyE;AAC/F,SAAO,OAAO,QACZ,IAAI,SAAS,UAAU,WAAW,SAAU,IAAI,SAAS,SAAS,OAAO,IAAI,IAAK;AACtF;","names":[]}