@tangle-network/agent-eval 0.145.22 → 0.147.0

package/dist/types-B3jzCp0p.js

@@ -0,0 +1,108 @@
+//#region src/multishot/types.ts
+var MultishotDriverEmptyError = class extends Error {
+	turn;
+	constructor(turn) {
+		super(`multishot: driver returned empty content twice at turn ${turn} — failing loud`);
+		this.turn = turn;
+		this.name = "MultishotDriverEmptyError";
+	}
+};
+var MultishotFatalToolError = class extends Error {
+	constructor(message) {
+		super(message);
+		this.name = "MultishotFatalToolError";
+	}
+};
+var MultishotShotResultError = class extends Error {
+	constructor(reason) {
+		super(`multishot: shot returned an invalid MultishotResult — ${reason}`);
+		this.name = "MultishotShotResultError";
+	}
+};
+const MULTISHOT_ROLES = /* @__PURE__ */ new Set([
+	"user",
+	"assistant",
+	"tool"
+]);
+/** Contract guard for the value a caller-supplied shot resolves with. The
+*  matrix writes per-cell artifacts, builds judge inputs, and meters cost from
+*  this value, so a malformed result must stop the cell instead of scoring a
+*  degraded one. Two silent degradations this closes: an artifact with no
+*  `type` matches neither the code nor the content artifact set, so the cell
+*  scores as though the artifact was never produced; a non-finite `costUsd`
+*  reaches `summary.totalCostUsd` and makes every cost number NaN.
+*
+*  A rejected cell is still billed: the matrix cell reads the shot's own
+*  `costUsd` when it is a usable amount and declares that spend on the throw,
+*  so money the shot spent before returning a malformed result stays in the
+*  cumulative sum the cost ceiling reads. A result whose `costUsd` is itself
+*  malformed carries no usable amount, and the cell records as `uncaptured`.
+*
+*  Every required field of `MultishotMessage` and `MultishotArtifact` is
+*  checked, including `toolCalls` elements and `invocation.args`. Optional
+*  fields are checked only when present. */
+function assertMultishotShotResult(value) {
+	if (typeof value !== "object" || value === null) throw new MultishotShotResultError(`expected an object, received ${describeValue(value)}`);
+	const result = value;
+	if (!Array.isArray(result.transcript)) throw new MultishotShotResultError(`transcript must be an array, received ${describeValue(result.transcript)}`);
+	if (!Array.isArray(result.artifacts)) throw new MultishotShotResultError(`artifacts must be an array, received ${describeValue(result.artifacts)}`);
+	result.transcript.forEach(assertMessage);
+	result.artifacts.forEach(assertArtifact);
+	assertFiniteCount(result.toolCalls, "toolCalls");
+	assertFiniteCount(result.durationMs, "durationMs");
+	assertFiniteCount(result.costUsd, "costUsd");
+	if (result.costProvenance !== void 0) assertCostProvenance(result.costProvenance);
+}
+function assertCostProvenance(value) {
+	const row = requireRow(value, "costProvenance");
+	if (row.kind !== "observed" && row.kind !== "estimated" && row.kind !== "uncaptured") throw new MultishotShotResultError(`costProvenance.kind must be observed, estimated or uncaptured, received ${describeValue(row.kind)}`);
+	if (row.kind === "uncaptured") {
+		if (row.usd !== null) throw new MultishotShotResultError(`uncaptured costProvenance.usd must be null, received ${describeValue(row.usd)}`);
+		return;
+	}
+	assertFiniteCount(row.usd, "costProvenance.usd");
+}
+function assertMessage(value, index) {
+	const row = requireRow(value, `transcript[${index}]`);
+	if (typeof row.role !== "string" || !MULTISHOT_ROLES.has(row.role)) throw new MultishotShotResultError(`transcript[${index}].role must be user, assistant or tool, received ${describeValue(row.role)}`);
+	assertString(row.content, `transcript[${index}].content`);
+	if (row.toolCallId !== void 0) assertString(row.toolCallId, `transcript[${index}].toolCallId`);
+	if (row.toolCalls === void 0) return;
+	if (!Array.isArray(row.toolCalls)) throw new MultishotShotResultError(`transcript[${index}].toolCalls must be an array when present, received ${describeValue(row.toolCalls)}`);
+	row.toolCalls.forEach((call, callIndex) => {
+		const field = `transcript[${index}].toolCalls[${callIndex}]`;
+		const row = requireRow(call, field);
+		assertString(row.id, `${field}.id`);
+		assertString(row.name, `${field}.name`);
+		requireRow(row.args, `${field}.args`);
+	});
+}
+function assertArtifact(value, index) {
+	const row = requireRow(value, `artifacts[${index}]`);
+	assertString(row.type, `artifacts[${index}].type`);
+	assertString(row.content, `artifacts[${index}].content`);
+	assertFiniteCount(row.turn, `artifacts[${index}].turn`);
+	const invocation = requireRow(row.invocation, `artifacts[${index}].invocation`);
+	assertString(invocation.name, `artifacts[${index}].invocation.name`);
+	requireRow(invocation.args, `artifacts[${index}].invocation.args`);
+}
+function requireRow(value, field) {
+	if (typeof value !== "object" || value === null || Array.isArray(value)) throw new MultishotShotResultError(`${field} must be an object, received ${describeValue(value)}`);
+	return value;
+}
+function assertString(value, field) {
+	if (typeof value !== "string") throw new MultishotShotResultError(`${field} must be a string, received ${describeValue(value)}`);
+}
+function assertFiniteCount(value, field) {
+	if (typeof value !== "number" || !Number.isFinite(value) || value < 0) throw new MultishotShotResultError(`${field} must be a finite number >= 0, received ${describeValue(value)}`);
+}
+function describeValue(value) {
+	if (value === null) return "null";
+	if (Array.isArray(value)) return "an array";
+	if (typeof value === "object") return "an object";
+	return `${typeof value} ${String(value)}`;
+}
+//#endregion
+export { assertMultishotShotResult as i, MultishotFatalToolError as n, MultishotShotResultError as r, MultishotDriverEmptyError as t };
+
+//# sourceMappingURL=types-B3jzCp0p.js.map

package/dist/types-B3jzCp0p.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"types-B3jzCp0p.js","names":[],"sources":["../src/multishot/types.ts"],"sourcesContent":["// Public types for the multishot substrate.\n\nimport type { CostProvenance } from '../cost-ledger'\n\nexport interface MultishotMessage {\n  role: 'user' | 'assistant' | 'tool'\n  content: string\n  toolCallId?: string\n  toolCalls?: Array<{ id: string; name: string; args: Record<string, unknown> }>\n}\n\nexport interface MultishotArtifact {\n  type: string\n  turn: number\n  invocation: { name: string; args: Record<string, unknown> }\n  content: string\n}\n\nexport interface MultishotResult {\n  transcript: MultishotMessage[]\n  artifacts: MultishotArtifact[]\n  toolCalls: number\n  durationMs: number\n  /** Known spend. A subtotal, not a total, when `costProvenance.kind` is\n   *  `uncaptured`. */\n  costUsd: number\n  /** Origin of `costUsd`. A shot that priced every call reports `estimated`\n   *  or `observed`; a shot with a call the router priced at nothing reports\n   *  `uncaptured`, and the matrix records the cell as under-counted instead of\n   *  presenting the subtotal as a complete estimate.\n   *\n   *  Optional so an engine written before this field keeps working; the matrix\n   *  then judges the cell on judge receipts alone, as it did before. */\n  costProvenance?: CostProvenance\n}\n\nexport interface MultishotToolDefinition {\n  type: 'function'\n  function: {\n    name: string\n    description: string\n    parameters: Record<string, unknown>\n  }\n}\n\n/** One chat-completion request the multishot loop issues for a single agent\n *  (or driver) inference step. Mirrors the OpenAI-compat body the loop would\n *  otherwise POST to the Tangle router. */\nexport interface MultishotTransportRequest {\n  model: string\n  messages: Array<Record<string, unknown>>\n  tools?: MultishotToolDefinition[]\n  temperature?: number\n  maxTokens?: number\n  signal?: AbortSignal\n}\n\nexport interface MultishotTransportToolCall {\n  id: string\n  type: 'function'\n  function: { name: string; arguments: string }\n}\n\nexport interface MultishotTransportResponse {\n  message: { content?: string | null; tool_calls?: MultishotTransportToolCall[] }\n  usage?: { prompt_tokens?: number; completion_tokens?: number }\n  /** Actual spend for this call. When omitted, the loop meters cost from\n   *  `usage` via the per-model router estimator (estimateRouterCost). */\n  costUsd?: number\n}\n\n/** Execution seam for one leg of the multishot loop. When provided, it\n *  replaces the internal router HTTP call for that leg — the loop still owns\n *  turn scheduling, tool dispatch, transcript capture, and cost metering.\n *  agent-eval has no dependency on agent-runtime; adapt agent-runtime's\n *  resolveAgentBackend (or any sandbox/cli-bridge/router client) into this\n *  signature product-side. */\nexport type MultishotTransport = (\n  req: MultishotTransportRequest,\n) => Promise<MultishotTransportResponse>\n\nexport type MultishotToolExecutor = (\n  args: Record<string, unknown>,\n  ctx: { apiKey: string; baseUrl: string; signal?: AbortSignal },\n) => Promise<{ content: string; costUsd: number }>\n\nexport interface MultishotPersona {\n  /** Stable identifier — used for per-cell artifact paths + matrix axis keys. */\n  id: string\n  /** Per-domain payload (income/profile/voice/etc.) shaped by the consumer. */\n  [k: string]: unknown\n}\n\n/**\n * Persona-shaping callbacks. Both are OPTIONAL: when omitted, the loop derives\n * them from the `AgentProfile` + persona payload (see `defaultShapeFromProfile`)\n * so a pure-profile call — `runMultishot({ profile, persona })` — works with no\n * role-builder functions. Provide callbacks only to override the derived shape.\n */\nexport interface MultishotShape<TPersona extends MultishotPersona> {\n  /** Opening user message (turn 0) — the persona's first ask. */\n  buildOpener?: (persona: TPersona) => string\n  /** System prompt the driver LLM uses to roleplay the persona. Should set\n   *  voice, goals, constraints, time-pressure, and the \"never go silent\" rule. */\n  buildDriverSystemPrompt?: (persona: TPersona) => string\n}\n\nexport class MultishotDriverEmptyError extends Error {\n  constructor(public readonly turn: number) {\n    super(`multishot: driver returned empty content twice at turn ${turn} — failing loud`)\n    this.name = 'MultishotDriverEmptyError'\n  }\n}\n\nexport class MultishotFatalToolError extends Error {\n  constructor(message: string) {\n    super(message)\n    this.name = 'MultishotFatalToolError'\n  }\n}\n\nexport class MultishotShotResultError extends Error {\n  constructor(reason: string) {\n    super(`multishot: shot returned an invalid MultishotResult — ${reason}`)\n    this.name = 'MultishotShotResultError'\n  }\n}\n\nconst MULTISHOT_ROLES = new Set(['user', 'assistant', 'tool'])\n\n/** Contract guard for the value a caller-supplied shot resolves with. The\n *  matrix writes per-cell artifacts, builds judge inputs, and meters cost from\n *  this value, so a malformed result must stop the cell instead of scoring a\n *  degraded one. Two silent degradations this closes: an artifact with no\n *  `type` matches neither the code nor the content artifact set, so the cell\n *  scores as though the artifact was never produced; a non-finite `costUsd`\n *  reaches `summary.totalCostUsd` and makes every cost number NaN.\n *\n *  A rejected cell is still billed: the matrix cell reads the shot's own\n *  `costUsd` when it is a usable amount and declares that spend on the throw,\n *  so money the shot spent before returning a malformed result stays in the\n *  cumulative sum the cost ceiling reads. A result whose `costUsd` is itself\n *  malformed carries no usable amount, and the cell records as `uncaptured`.\n *\n *  Every required field of `MultishotMessage` and `MultishotArtifact` is\n *  checked, including `toolCalls` elements and `invocation.args`. Optional\n *  fields are checked only when present. */\nexport function assertMultishotShotResult(value: unknown): asserts value is MultishotResult {\n  if (typeof value !== 'object' || value === null) {\n    throw new MultishotShotResultError(`expected an object, received ${describeValue(value)}`)\n  }\n  const result = value as Record<string, unknown>\n  if (!Array.isArray(result.transcript)) {\n    throw new MultishotShotResultError(\n      `transcript must be an array, received ${describeValue(result.transcript)}`,\n    )\n  }\n  if (!Array.isArray(result.artifacts)) {\n    throw new MultishotShotResultError(\n      `artifacts must be an array, received ${describeValue(result.artifacts)}`,\n    )\n  }\n  result.transcript.forEach(assertMessage)\n  result.artifacts.forEach(assertArtifact)\n  assertFiniteCount(result.toolCalls, 'toolCalls')\n  assertFiniteCount(result.durationMs, 'durationMs')\n  assertFiniteCount(result.costUsd, 'costUsd')\n  if (result.costProvenance !== undefined) assertCostProvenance(result.costProvenance)\n}\n\nfunction assertCostProvenance(value: unknown): void {\n  const row = requireRow(value, 'costProvenance')\n  if (row.kind !== 'observed' && row.kind !== 'estimated' && row.kind !== 'uncaptured') {\n    throw new MultishotShotResultError(\n      `costProvenance.kind must be observed, estimated or uncaptured, received ${describeValue(row.kind)}`,\n    )\n  }\n  // The matrix reads the amount from `costUsd`; `usd` only has to agree with\n  // the kind, so an uncaptured provenance cannot smuggle in a total.\n  if (row.kind === 'uncaptured') {\n    if (row.usd !== null) {\n      throw new MultishotShotResultError(\n        `uncaptured costProvenance.usd must be null, received ${describeValue(row.usd)}`,\n      )\n    }\n    return\n  }\n  assertFiniteCount(row.usd, 'costProvenance.usd')\n}\n\nfunction assertMessage(value: unknown, index: number): void {\n  const row = requireRow(value, `transcript[${index}]`)\n  if (typeof row.role !== 'string' || !MULTISHOT_ROLES.has(row.role)) {\n    throw new MultishotShotResultError(\n      `transcript[${index}].role must be user, assistant or tool, received ${describeValue(row.role)}`,\n    )\n  }\n  assertString(row.content, `transcript[${index}].content`)\n  if (row.toolCallId !== undefined) {\n    assertString(row.toolCallId, `transcript[${index}].toolCallId`)\n  }\n  if (row.toolCalls === undefined) return\n  if (!Array.isArray(row.toolCalls)) {\n    throw new MultishotShotResultError(\n      `transcript[${index}].toolCalls must be an array when present, received ${describeValue(row.toolCalls)}`,\n    )\n  }\n  row.toolCalls.forEach((call, callIndex) => {\n    const field = `transcript[${index}].toolCalls[${callIndex}]`\n    const row = requireRow(call, field)\n    assertString(row.id, `${field}.id`)\n    assertString(row.name, `${field}.name`)\n    requireRow(row.args, `${field}.args`)\n  })\n}\n\nfunction assertArtifact(value: unknown, index: number): void {\n  const row = requireRow(value, `artifacts[${index}]`)\n  assertString(row.type, `artifacts[${index}].type`)\n  assertString(row.content, `artifacts[${index}].content`)\n  assertFiniteCount(row.turn, `artifacts[${index}].turn`)\n  const invocation = requireRow(row.invocation, `artifacts[${index}].invocation`)\n  assertString(invocation.name, `artifacts[${index}].invocation.name`)\n  requireRow(invocation.args, `artifacts[${index}].invocation.args`)\n}\n\nfunction requireRow(value: unknown, field: string): Record<string, unknown> {\n  if (typeof value !== 'object' || value === null || Array.isArray(value)) {\n    throw new MultishotShotResultError(\n      `${field} must be an object, received ${describeValue(value)}`,\n    )\n  }\n  return value as Record<string, unknown>\n}\n\nfunction assertString(value: unknown, field: string): void {\n  if (typeof value !== 'string') {\n    throw new MultishotShotResultError(\n      `${field} must be a string, received ${describeValue(value)}`,\n    )\n  }\n}\n\nfunction assertFiniteCount(value: unknown, field: string): void {\n  if (typeof value !== 'number' || !Number.isFinite(value) || value < 0) {\n    throw new MultishotShotResultError(\n      `${field} must be a finite number >= 0, received ${describeValue(value)}`,\n    )\n  }\n}\n\nfunction describeValue(value: unknown): string {\n  if (value === null) return 'null'\n  if (Array.isArray(value)) return 'an array'\n  if (typeof value === 'object') return 'an object'\n  return `${typeof value} ${String(value)}`\n}\n"],"mappings":";AA2GA,IAAa,4BAAb,cAA+C,MAAM;CACvB;CAA5B,YAAY,MAA8B;EACxC,MAAM,0DAA0D,KAAK,gBAAgB;EAD3D,KAAA,OAAA;EAE1B,KAAK,OAAO;CACd;AACF;AAEA,IAAa,0BAAb,cAA6C,MAAM;CACjD,YAAY,SAAiB;EAC3B,MAAM,OAAO;EACb,KAAK,OAAO;CACd;AACF;AAEA,IAAa,2BAAb,cAA8C,MAAM;CAClD,YAAY,QAAgB;EAC1B,MAAM,yDAAyD,QAAQ;EACvE,KAAK,OAAO;CACd;AACF;AAEA,MAAM,kCAAkB,IAAI,IAAI;CAAC;CAAQ;CAAa;AAAM,CAAC;;;;;;;;;;;;;;;;;;AAmB7D,SAAgB,0BAA0B,OAAkD;CAC1F,IAAI,OAAO,UAAU,YAAY,UAAU,MACzC,MAAM,IAAI,yBAAyB,gCAAgC,cAAc,KAAK,GAAG;CAE3F,MAAM,SAAS;CACf,IAAI,CAAC,MAAM,QAAQ,OAAO,UAAU,GAClC,MAAM,IAAI,yBACR,yCAAyC,cAAc,OAAO,UAAU,GAC1E;CAEF,IAAI,CAAC,MAAM,QAAQ,OAAO,SAAS,GACjC,MAAM,IAAI,yBACR,wCAAwC,cAAc,OAAO,SAAS,GACxE;CAEF,OAAO,WAAW,QAAQ,aAAa;CACvC,OAAO,UAAU,QAAQ,cAAc;CACvC,kBAAkB,OAAO,WAAW,WAAW;CAC/C,kBAAkB,OAAO,YAAY,YAAY;CACjD,kBAAkB,OAAO,SAAS,SAAS;CAC3C,IAAI,OAAO,mBAAmB,KAAA,GAAW,qBAAqB,OAAO,cAAc;AACrF;AAEA,SAAS,qBAAqB,OAAsB;CAClD,MAAM,MAAM,WAAW,OAAO,gBAAgB;CAC9C,IAAI,IAAI,SAAS,cAAc,IAAI,SAAS,eAAe,IAAI,SAAS,cACtE,MAAM,IAAI,yBACR,2EAA2E,cAAc,IAAI,IAAI,GACnG;CAIF,IAAI,IAAI,SAAS,cAAc;EAC7B,IAAI,IAAI,QAAQ,MACd,MAAM,IAAI,yBACR,wDAAwD,cAAc,IAAI,GAAG,GAC/E;EAEF;CACF;CACA,kBAAkB,IAAI,KAAK,oBAAoB;AACjD;AAEA,SAAS,cAAc,OAAgB,OAAqB;CAC1D,MAAM,MAAM,WAAW,OAAO,cAAc,MAAM,EAAE;CACpD,IAAI,OAAO,IAAI,SAAS,YAAY,CAAC,gBAAgB,IAAI,IAAI,IAAI,GAC/D,MAAM,IAAI,yBACR,cAAc,MAAM,mDAAmD,cAAc,IAAI,IAAI,GAC/F;CAEF,aAAa,IAAI,SAAS,cAAc,MAAM,UAAU;CACxD,IAAI,IAAI,eAAe,KAAA,GACrB,aAAa,IAAI,YAAY,cAAc,MAAM,aAAa;CAEhE,IAAI,IAAI,cAAc,KAAA,GAAW;CACjC,IAAI,CAAC,MAAM,QAAQ,IAAI,SAAS,GAC9B,MAAM,IAAI,yBACR,cAAc,MAAM,sDAAsD,cAAc,IAAI,SAAS,GACvG;CAEF,IAAI,UAAU,SAAS,MAAM,cAAc;EACzC,MAAM,QAAQ,cAAc,MAAM,cAAc,UAAU;EAC1D,MAAM,MAAM,WAAW,MAAM,KAAK;EAClC,aAAa,IAAI,IAAI,GAAG,MAAM,IAAI;EAClC,aAAa,IAAI,MAAM,GAAG,MAAM,MAAM;EACtC,WAAW,IAAI,MAAM,GAAG,MAAM,MAAM;CACtC,CAAC;AACH;AAEA,SAAS,eAAe,OAAgB,OAAqB;CAC3D,MAAM,MAAM,WAAW,OAAO,aAAa,MAAM,EAAE;CACnD,aAAa,IAAI,MAAM,aAAa,MAAM,OAAO;CACjD,aAAa,IAAI,SAAS,aAAa,MAAM,UAAU;CACvD,kBAAkB,IAAI,MAAM,aAAa,MAAM,OAAO;CACtD,MAAM,aAAa,WAAW,IAAI,YAAY,aAAa,MAAM,aAAa;CAC9E,aAAa,WAAW,MAAM,aAAa,MAAM,kBAAkB;CACnE,WAAW,WAAW,MAAM,aAAa,MAAM,kBAAkB;AACnE;AAEA,SAAS,WAAW,OAAgB,OAAwC;CAC1E,IAAI,OAAO,UAAU,YAAY,UAAU,QAAQ,MAAM,QAAQ,KAAK,GACpE,MAAM,IAAI,yBACR,GAAG,MAAM,+BAA+B,cAAc,KAAK,GAC7D;CAEF,OAAO;AACT;AAEA,SAAS,aAAa,OAAgB,OAAqB;CACzD,IAAI,OAAO,UAAU,UACnB,MAAM,IAAI,yBACR,GAAG,MAAM,8BAA8B,cAAc,KAAK,GAC5D;AAEJ;AAEA,SAAS,kBAAkB,OAAgB,OAAqB;CAC9D,IAAI,OAAO,UAAU,YAAY,CAAC,OAAO,SAAS,KAAK,KAAK,QAAQ,GAClE,MAAM,IAAI,yBACR,GAAG,MAAM,0CAA0C,cAAc,KAAK,GACxE;AAEJ;AAEA,SAAS,cAAc,OAAwB;CAC7C,IAAI,UAAU,MAAM,OAAO;CAC3B,IAAI,MAAM,QAAQ,KAAK,GAAG,OAAO;CACjC,IAAI,OAAO,UAAU,UAAU,OAAO;CACtC,OAAO,GAAG,OAAO,MAAM,GAAG,OAAO,KAAK;AACxC"}

package/dist/{types-oAsa-fs4.d.ts → types-BohHewKK.d.ts}

@@ -1,6 +1,6 @@
 import { c as CostLedgerHandle } from "./cost-ledger-DbQdN3nO.js";
 import { a as RunRecord, n as RunCostProvenance, u as RunTokenUsage } from "./run-record-DVV82Gwh.js";
-import { a as JudgeInput, p as ChatClient } from "./types-XBRdmbj8.js";
+import { a as JudgeInput, p as ChatClient } from "./types-DOhGq4S1.js";
 import { RE2JS } from "re2js";
 //#region src/trace-analyst/types.d.ts
 /**
@@ -594,4 +594,4 @@ type AnalystRunEvent = {
 };
 //#endregion
 export { SearchSpanResult as A, ViewSpansResult as B, TRACE_ANALYSIS_LIMITS as C, DatasetOverview as D, DEFAULT_TRACE_ANALYST_BUDGETS as E, TraceAnalystFilters as F, ViewTraceResult as H, TraceAnalystSpan as I, TraceAnalystSpanKind as L, SpanMatchRecord as M, TRACE_ANALYST_TRUNCATION_MARKER_PREFIX as N, ErrorCluster as O, TraceAnalystByteBudgets as P, TraceAnalystSpanStatus as R, BoundedTraceAnalysisStoreOptions as S, TraceAnalysisStoreContext as T, ViewTraceOversized as V, ProposalFinding as _, AnalystInputKind as a, makeFinding as b, AnalystRunInputs as c, AnalystSeverity as d, AnalystUsageReceipt as f, ExecutionProbeRequest as g, ExecutionProbeOutcome as h, AnalystFinding as i, SearchTraceResult as j, QueryTracesPage as k, AnalystRunResult as l, ExecutionProbe as m, AnalystContext as n, AnalystRequirements as o, EvidenceRef as p, AnalystCost as r, AnalystRunEvent as s, Analyst as t, AnalystRunSummary as u, ProposalFindingOrigin as v, TraceAnalysisStore as w, makeProposalFinding as x, computeFindingId as y, TraceAnalystTraceSummary as z };
-//# sourceMappingURL=types-oAsa-fs4.d.ts.map
+//# sourceMappingURL=types-BohHewKK.d.ts.map

package/dist/{types-oAsa-fs4.d.ts.map → types-BohHewKK.d.ts.map}

@@ -1 +1 @@
-{"version":3,"file":"types-oAsa-fs4.d.ts","names":[],"sources":["../src/trace-analyst/types.ts","../src/trace-analyst/store-contract.ts","../src/analyst/types.ts"],"mappings":";;;;;;;;;;;;;;;;;;;;KAgBY;KAUA;;;;UAKK;EACf;EACA;EACA;EACA;EACA,MAAM;EACN;EACA;EACA;EACA,QAAQ;EACR;EACA;EACA;EACA;EACA;;;EAGA,YAAY;;UAGG;EACf;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;;UAGe;;EAEf;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;;EAGA;;;;;;;UAQe;;EAEf;;EAEA;;EAEA;;EAEA;EACA;EACA;;EAEA;;EAEA;;EAEA;;UAGe;EACf;EACA;EACA;EACA;EACA;EACA;;EAEA;EACA;IAAU;IAAqB;;;;;;EAK/B,gBAAgB;EAChB;IAAc;IAAkB;;;UAGjB;EACf,QAAQ;EACR;EACA;;;;;UAMe;EACf;EACA,QAAQ;EACR,YAAY;;UAGG;EACf;;EAEA,gBAAgB;;EAEhB;EACA;;UAGe;EACf;EACA,OAAO;;EAEP;;EAEA;;EAEA;;EAEA;;UAGe;EACf;EACA;EACA;EACA,WAAW;;;EAGX;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA,MAAM;EACN;;UAGe;EACf;EACA;EACA,MAAM;EACN;;;UAIe;;;EAGf;;;EAGA;;;EAGA;;;EAGA;;cAGW,+BAA+B;;;cAS/B;;;cC7MA;WACX;WACA;WACA;WACA;WACA;WACA;WACA;WACA;;UAGe;EACf,SAAS;;;;;;;;;UAUM;EACf,SAAS,kBAAkB,UAAU,4BAA4B;EAEjE,SACE;IAAS;IAAkB;KAC3B,UAAU,4BACT;EAEH,YACE,UAAU,qBACV,UAAU,4BACT,QAAQ;EAEX,YACE;IAAS,UAAU;IAAqB;IAAe;KACvD,UAAU,4BACT,QAAQ;EAEX,YAAY,UAAU,qBAAqB,UAAU,4BAA4B;EAEjF,UACE;IACE;IACA;KAEF,UAAU,4BACT,QAAQ;EAEX,UACE;IACE;IACA;IACA;KAEF,UAAU,4BACT,QAAQ;EAEX,YACE;IACE;IACA;IACA;KAEF,UAAU,4BACT,QAAQ;EAEX,WACE;IACE;IACA;IACA;IACA;KAEF,UAAU,4BACT,QAAQ;;UAGI;EACf,UAAU,QAAQ;;;;;;;;UC/DH;EACf;;;;;;;EAOA;EACA;EACA;EACA,UAAU;;;;;;;EAOV;EACA;EACA;EACA,eAAe;EACf;EACA;;EAEA;;;;;;EAMA;;;;EAIA;;EAEA,WAAW;;KAGD;;KAGA;;KAGA,kBAAkB;WACnB,iBAAiB;;UAGX;;;;;;;EAOf;EACA;EACA;;;;;;;;KAWU;UAOK;;EAEf;;EAEA;;EAEA;;EAEA;;UAGe;;EAEf;;EAEA;;;;;;UAOe;EACf,aAAa;EACb;EACA,YAAY;EACZ,aAAa;;EAEb,SAAS;;UAGM;EACf;;EAEA;;EAEA;;EAEA;;EAEA,aAAa;;EAEb;;;;;;;EAOA,OAAO;;;;;;;;;;EAUP,gBAAgB,cAAc;;;;;;;EAO9B,mBAAmB,cAAc;;;;;EAKjC,eAAe,SAAS;;EAExB,OAAO;;EAEP,OAAO,aAAa,SAAS;;EAE7B,SAAS;;;;;;;;EAQT,QAAQ;;;UAMO;EACf;;EAEA;;EAEA;;EAEA;EACA,SAAS;;;;;;;KAQC;EAEN;EACA;EACA;EACA;EACA;;EAEA;;EAEA;EAAkB;IAAS;IAAe;;;;;;;;UAO/B;;WAEN;EACT,QAAQ,SAAS,wBAAwB,QAAQ;;;;;;;;UASlC,QAAQ;;WAEd;;WAEA;WACA,WAAW;WACX,MAAM;WACN,WAAW;;WAEX;EACT,QAAQ,OAAO,QAAQ,KAAK,iBAAiB,QAAQ;;;UAItC;;EAEf;;EAEA,QAAQ;;EAER,MAAM;;EAEN;;;;;;;;EAQA;IAAkB;IAAsB;;;;;;;;EAOxC;;;;;;;;;;iBAac,iBAAiB;EAC/B;EACA;EACA;EACA;;EAEA;;;;;;iBAyBc,YACd,MAAM,KAAK;EACT;EACA;IAED;;iBAiBa,oBACd,MAAM,KAAK;EACT;EACA;IAED;UAOc;EACf;EACA;;EAEA;EACA;EACA;;EAEA,OAAO;;EAEP;IAAU;IAAe;;;UAGV;EACf;EACA;EACA;EACA;EACA,UAAU;EACV,aAAa;;EAEb;;;;;EAKA,wBAAwB;;;;;;;;;;;;;;;KAkBd;EAEN;EACA;EACA;EACA;;EAEA,aAAa;;EAGb;EACA,SAAS;;EAGT;EACA;EACA;;EAGA;;EAEA,SAAS;EACT,UAAU,cAAc;;EAGxB;EACA,QAAQ"}
+{"version":3,"file":"types-BohHewKK.d.ts","names":[],"sources":["../src/trace-analyst/types.ts","../src/trace-analyst/store-contract.ts","../src/analyst/types.ts"],"mappings":";;;;;;;;;;;;;;;;;;;;KAgBY;KAUA;;;;UAKK;EACf;EACA;EACA;EACA;EACA,MAAM;EACN;EACA;EACA;EACA,QAAQ;EACR;EACA;EACA;EACA;EACA;;;EAGA,YAAY;;UAGG;EACf;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;;UAGe;;EAEf;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;;EAGA;;;;;;;UAQe;;EAEf;;EAEA;;EAEA;;EAEA;EACA;EACA;;EAEA;;EAEA;;EAEA;;UAGe;EACf;EACA;EACA;EACA;EACA;EACA;;EAEA;EACA;IAAU;IAAqB;;;;;;EAK/B,gBAAgB;EAChB;IAAc;IAAkB;;;UAGjB;EACf,QAAQ;EACR;EACA;;;;;UAMe;EACf;EACA,QAAQ;EACR,YAAY;;UAGG;EACf;;EAEA,gBAAgB;;EAEhB;EACA;;UAGe;EACf;EACA,OAAO;;EAEP;;EAEA;;EAEA;;EAEA;;UAGe;EACf;EACA;EACA;EACA,WAAW;;;EAGX;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA,MAAM;EACN;;UAGe;EACf;EACA;EACA,MAAM;EACN;;;UAIe;;;EAGf;;;EAGA;;;EAGA;;;EAGA;;cAGW,+BAA+B;;;cAS/B;;;cC7MA;WACX;WACA;WACA;WACA;WACA;WACA;WACA;WACA;;UAGe;EACf,SAAS;;;;;;;;;UAUM;EACf,SAAS,kBAAkB,UAAU,4BAA4B;EAEjE,SACE;IAAS;IAAkB;KAC3B,UAAU,4BACT;EAEH,YACE,UAAU,qBACV,UAAU,4BACT,QAAQ;EAEX,YACE;IAAS,UAAU;IAAqB;IAAe;KACvD,UAAU,4BACT,QAAQ;EAEX,YAAY,UAAU,qBAAqB,UAAU,4BAA4B;EAEjF,UACE;IACE;IACA;KAEF,UAAU,4BACT,QAAQ;EAEX,UACE;IACE;IACA;IACA;KAEF,UAAU,4BACT,QAAQ;EAEX,YACE;IACE;IACA;IACA;KAEF,UAAU,4BACT,QAAQ;EAEX,WACE;IACE;IACA;IACA;IACA;KAEF,UAAU,4BACT,QAAQ;;UAGI;EACf,UAAU,QAAQ;;;;;;;;UC/DH;EACf;;;;;;;EAOA;EACA;EACA;EACA,UAAU;;;;;;;EAOV;EACA;EACA;EACA,eAAe;EACf;EACA;;EAEA;;;;;;EAMA;;;;EAIA;;EAEA,WAAW;;KAGD;;KAGA;;KAGA,kBAAkB;WACnB,iBAAiB;;UAGX;;;;;;;EAOf;EACA;EACA;;;;;;;;KAWU;UAOK;;EAEf;;EAEA;;EAEA;;EAEA;;UAGe;;EAEf;;EAEA;;;;;;UAOe;EACf,aAAa;EACb;EACA,YAAY;EACZ,aAAa;;EAEb,SAAS;;UAGM;EACf;;EAEA;;EAEA;;EAEA;;EAEA,aAAa;;EAEb;;;;;;;EAOA,OAAO;;;;;;;;;;EAUP,gBAAgB,cAAc;;;;;;;EAO9B,mBAAmB,cAAc;;;;;EAKjC,eAAe,SAAS;;EAExB,OAAO;;EAEP,OAAO,aAAa,SAAS;;EAE7B,SAAS;;;;;;;;EAQT,QAAQ;;;UAMO;EACf;;EAEA;;EAEA;;EAEA;EACA,SAAS;;;;;;;KAQC;EAEN;EACA;EACA;EACA;EACA;;EAEA;;EAEA;EAAkB;IAAS;IAAe;;;;;;;;UAO/B;;WAEN;EACT,QAAQ,SAAS,wBAAwB,QAAQ;;;;;;;;UASlC,QAAQ;;WAEd;;WAEA;WACA,WAAW;WACX,MAAM;WACN,WAAW;;WAEX;EACT,QAAQ,OAAO,QAAQ,KAAK,iBAAiB,QAAQ;;;UAItC;;EAEf;;EAEA,QAAQ;;EAER,MAAM;;EAEN;;;;;;;;EAQA;IAAkB;IAAsB;;;;;;;;EAOxC;;;;;;;;;;iBAac,iBAAiB;EAC/B;EACA;EACA;EACA;;EAEA;;;;;;iBAyBc,YACd,MAAM,KAAK;EACT;EACA;IAED;;iBAiBa,oBACd,MAAM,KAAK;EACT;EACA;IAED;UAOc;EACf;EACA;;EAEA;EACA;EACA;;EAEA,OAAO;;EAEP;IAAU;IAAe;;;UAGV;EACf;EACA;EACA;EACA;EACA,UAAU;EACV,aAAa;;EAEb;;;;;EAKA,wBAAwB;;;;;;;;;;;;;;;KAkBd;EAEN;EACA;EACA;EACA;;EAEA,aAAa;;EAGb;EACA,SAAS;;EAGT;EACA;EACA;;EAGA;;EAEA,SAAS;EACT,UAAU,cAAc;;EAGxB;EACA,QAAQ"}

package/dist/{types-DABZgDGV.d.ts → types-C1Bmeb8X.d.ts}

@@ -1,7 +1,7 @@
 import { S as PaidCallResult, T as RunPaidCallInput, a as CostChannel, c as CostLedgerHandle, f as CostLedgerSummary, p as CostProvenance } from "./cost-ledger-DbQdN3nO.js";
 import { u as RunTokenUsage } from "./run-record-DVV82Gwh.js";
-import { E as LlmCallMetadata } from "./types-XBRdmbj8.js";
-import { _ as ProposalFinding } from "./types-oAsa-fs4.js";
+import { E as LlmCallMetadata } from "./types-DOhGq4S1.js";
+import { _ as ProposalFinding } from "./types-BohHewKK.js";
 //#region src/campaign/types.d.ts
 /** Stable identifier + kind tag for any scenario. Consumers
  *  extend with their per-domain payload (persona, task, requirement, ...). */
@@ -626,4 +626,4 @@ interface CampaignResult<TArtifact = unknown, TScenario extends Scenario = Scena
 }
 //#endregion
 export { LabeledScenarioWrite as A, ScoredSurfaceOutcome as B, JudgeDimension as C, LabeledScenarioSampleArgs as D, LabeledScenarioRecord as E, ProposeContext as F, labelTrustRank as G, SurfaceProposer as H, ProposedCandidate as I, RedactionStatus as L, OptimizerConfig as M, ParetoParent as N, LabeledScenarioSource as O, ProposalTrackContext as P, Scenario as R, JudgeConfig as S, LabelTrust as T, TraceSpan as U, SessionScript as V, isProposedCandidate as W, GateDecision as _, CampaignResult as a, GenerationRecord as b, CampaignTraceWriter as c, DispatchContext as d, DispatchFn as f, GateContribution as g, GateContext as h, CampaignCostMeter as i, MutableSurface as j, LabeledScenarioStore as k, CodeSurface as l, GateCheckStatus as m, CampaignArtifactWriter as n, CampaignScenarioIdentity as o, Gate as p, CampaignCellResult as r, CampaignTokenUsage as s, CampaignAggregates as t, ComponentSurface as u, GateResult as v, JudgeScore as w, JudgeAggregate as x, GenerationCandidate as y, ScenarioAggregate as z };
-//# sourceMappingURL=types-DABZgDGV.d.ts.map
+//# sourceMappingURL=types-C1Bmeb8X.d.ts.map

package/dist/{types-DABZgDGV.d.ts.map → types-C1Bmeb8X.d.ts.map}

@@ -1 +1 @@
-{"version":3,"file":"types-DABZgDGV.d.ts","names":[],"sources":["../src/campaign/types.ts"],"mappings":";;;;;;;UAgCiB;EACf;EACA;EACA;;;;;EAKA;;;UAIe,iCAAiC,KAAK;EACrD;;;;;UAMe;EACf;;EAEA;EACA;EACA;EACA;EACA,QAAQ;EACR,OAAO;EACP,WAAW;EACX,MAAM;;EAEN;;EAEA;;;;;;;;EAQA;;;;KAKU,WAAW,kBAAkB,UAAU,cACjD,UAAU,WACV,KAAK,oBACF,QAAQ;;;;UAOI,cAAc,WAAW;EACxC;EACA;EACA;;EAEA;;;EAGA,sBAAsB,UAAU,WAAW,sBAAsB,UAAU,cAAc;;UAK1E;;EAEf;;EAEA;;;;;;;;;UAUe,YAAY,WAAW,kBAAkB,WAAW;EACnE;EACA,YAAY;;;;EAIZ;;;EAGA,MAAM;IACJ,UAAU;IACV,UAAU;IACV,QAAQ;;IAER,aAAa;IACb;IACA,WAAW;MACT,aAAa,QAAQ;EACzB,aAAa,UAAU;;;;;;;;;;;UAYR;EACf,YAAY;EACZ;EACA;;EAEA,UAAU;;;;EAIV;;;EAGA;;EAEA;;EAEA,WAAW,eAAe;;;;;;;UAUX;WACN;;;WAGA;;WAEA;;WAEA;;WAEA;;WAEA;;WAEA;;;WAGA;aACE;aACA;aACA;;;WAGF;;;UAIM;WACN;WACA,YAAY,SAAS;;;;;;;;;;;KAYpB,0BAA0B,mBAAmB;;;;;;;UAQxC;EACf,SAAS;;EAET;;;;EAIA;;;;iBAKc,oBACd,OAAO,iBAAiB,oBACvB,SAAS;;;;;;;;;UAkBK;EACf,SAAS;EACT;;;EAGA,YAAY;;;EAGZ;;EAEA;EACA;EACA;;;UAIe;EACf;EACA;EACA;EACA;EACA;;;;;UAMe;;;EAGf;;EAEA;EACA;EACA;EACA,YAAY;;;;;EAKZ,WAAW;IAAQ;IAAoB;IAAmB;IAAgB;;EAC1E;IACE;IACA;;;;;UAMa,eAAe,YAAY;WACjC,gBAAgB;WAChB,SAAS,cAAc;WACvB,UAAU,cAAc;;WAExB;WACA;WACA,QAAQ;;WAER,QAAQ;;;WAGR,kBAAkB;;;WAGlB,mBAAmB;;;;WAInB;;;;;;;WAOA,gBAAgB,cAAc;;WAE9B,aAAa;WACb;;;;;;;;;;;;;;UAeM,gBAAgB,YAAY;EAC3C;;;;;EAKA,QAAQ,KAAK,eAAe,aAAa,QAAQ,MAAM,iBAAiB;;;EAGxE,QAAQ;IAAQ,SAAS,cAAc;;IAAwB;IAAe;;;UAG/D;EACf;EACA;EACA,mBAAmB,qBAAqB;;UAGzB,wBAAwB;EACvC,UAAU;;;KAMA;;KAGA;UAEK;EACf;EACA,QAAQ;EACR;;UAGe,YAAY,WAAW,kBAAkB;EACxD,oBAAoB,YAAY;EAChC,oBAAoB,YAAY;;EAEhC,aAAa,YAAY,eAAe;;;;;EAKxC,sBAAsB,YAAY,eAAe;;;;;;;EAOjD,yBAAyB,YAAY,eAAe;;;EAGpD,uBAAuB,YAAY;EACnC,WAAW;EACX;IAAQ;IAAmB;;;EAE3B,aAAa;EACb;EACA,QAAQ;;UAGO;EACf,UAAU;EACV;EACA,mBAAmB;EACnB;;;UAIe,KAAK,qBAAqB,kBAAkB,WAAW;EACtE;EACA,OAAO,KAAK,YAAY,WAAW,aAAa,QAAQ;;;;UAOzC;EACf,KAAK,cAAc,aAAa,0BAA0B;EAC1D,SAAS;;UAGM;EACf,IAAI,aAAa;EACjB,aAAa,aAAa;;;;UAKX;EACf,MAAM,cAAc,kBAAkB,aAAa;EACnD,UAAU,cAAc,iBAAiB;;;;;;KAO/B,qBAAqB;;;;;UAMhB;;EAEf,YAAY,GACV,OAAO,KAAK,iBAAiB;IAC3B,UAAU;MAEX,QAAQ,eAAe;;;;;KAQhB;KAOA;;;;;;;;;;;;;;;KAgBA;;iBASI,eAAe,OAAO;;;;UAOrB,qBAAqB,kBAAkB,WAAW,UAAU;EAC3E,UAAU;EACV,UAAU;EACV,aAAa,eAAe;EAC5B,QAAQ;EACR;EACA;EACA,iBAAiB;;;;;EAKjB,aAAa;;EAEb;;UAGe,sBAAsB,kBAAkB,WAAW,UAAU,6BACpE,qBAAqB,WAAW;;EAExC;;;EAGA;;UAGe;EACf;;EAEA;;;;EAIA;EACA;IACE;IACA,SAAS,wBAAwB;IACjC;IACA;;;;;IAKA,WAAW;;;UAIE;EACf,QAAQ,OAAO,uBAAuB;EACtC,OAAO,MAAM,4BAA4B,QAAQ;EACjD,QAAQ;IACN;IACA;IACA,UAAU;;;IAGV,SAAS,OAAO;;;UAMH,mBAAmB;;;EAGlC;EACA;EACA;EACA;EACA;EACA,UAAU;EACV,aAAa,eAAe;;;EAG5B;;EAEA,gBAAgB;;EAEhB;;;EAGA,YAAY;;;EAGZ;;;EAGA;EACA;EACA;EACA;;EAEA;;EAEA;EACA;;UAGe;EACf;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;;UAGe;EACf;EACA,YAAY;EACZ;;;;;;UAOe;EACf;;EAEA;;EAEA;;EAEA;;EAEA;;;EAGA;;;;EAIA;;;;EAIA;IACE;IACA;IACA,iBAAiB;MAAQ;MAAgB;;;;;EAI3C,YAAY;;;;;;;;;;EAUZ,WAAW;IAAQ;IAAoB;IAAmB;IAAgB;;;;EAG1E;;;;EAIA;;UAGe;EACf,SAAS,eAAe;EACxB,YAAY,eAAe;;EAE3B,MAAM;;EAEN;EACA;EACA;;EAEA;;EAEA;;EAEA;;EAEA;;UAGe,eAAe,qBAAqB,kBAAkB,WAAW;;EAEhF;;EAEA;EACA;;EAEA;EACA;EACA;EACA;EACA,OAAO,MAAM,mBAAmB;EAChC,YAAY;EACZ;IACE,aAAa;IACb;;EAEF,OAAO;EACP;EACA;EACA,iBAAiB;;;EAGjB,WAAW,MAAM,2BAA2B,KAAK"}
+{"version":3,"file":"types-C1Bmeb8X.d.ts","names":[],"sources":["../src/campaign/types.ts"],"mappings":";;;;;;;UAgCiB;EACf;EACA;EACA;;;;;EAKA;;;UAIe,iCAAiC,KAAK;EACrD;;;;;UAMe;EACf;;EAEA;EACA;EACA;EACA;EACA,QAAQ;EACR,OAAO;EACP,WAAW;EACX,MAAM;;EAEN;;EAEA;;;;;;;;EAQA;;;;KAKU,WAAW,kBAAkB,UAAU,cACjD,UAAU,WACV,KAAK,oBACF,QAAQ;;;;UAOI,cAAc,WAAW;EACxC;EACA;EACA;;EAEA;;;EAGA,sBAAsB,UAAU,WAAW,sBAAsB,UAAU,cAAc;;UAK1E;;EAEf;;EAEA;;;;;;;;;UAUe,YAAY,WAAW,kBAAkB,WAAW;EACnE;EACA,YAAY;;;;EAIZ;;;EAGA,MAAM;IACJ,UAAU;IACV,UAAU;IACV,QAAQ;;IAER,aAAa;IACb;IACA,WAAW;MACT,aAAa,QAAQ;EACzB,aAAa,UAAU;;;;;;;;;;;UAYR;EACf,YAAY;EACZ;EACA;;EAEA,UAAU;;;;EAIV;;;EAGA;;EAEA;;EAEA,WAAW,eAAe;;;;;;;UAUX;WACN;;;WAGA;;WAEA;;WAEA;;WAEA;;WAEA;;WAEA;;;WAGA;aACE;aACA;aACA;;;WAGF;;;UAIM;WACN;WACA,YAAY,SAAS;;;;;;;;;;;KAYpB,0BAA0B,mBAAmB;;;;;;;UAQxC;EACf,SAAS;;EAET;;;;EAIA;;;;iBAKc,oBACd,OAAO,iBAAiB,oBACvB,SAAS;;;;;;;;;UAkBK;EACf,SAAS;EACT;;;EAGA,YAAY;;;EAGZ;;EAEA;EACA;EACA;;;UAIe;EACf;EACA;EACA;EACA;EACA;;;;;UAMe;;;EAGf;;EAEA;EACA;EACA;EACA,YAAY;;;;;EAKZ,WAAW;IAAQ;IAAoB;IAAmB;IAAgB;;EAC1E;IACE;IACA;;;;;UAMa,eAAe,YAAY;WACjC,gBAAgB;WAChB,SAAS,cAAc;WACvB,UAAU,cAAc;;WAExB;WACA;WACA,QAAQ;;WAER,QAAQ;;;WAGR,kBAAkB;;;WAGlB,mBAAmB;;;;WAInB;;;;;;;WAOA,gBAAgB,cAAc;;WAE9B,aAAa;WACb;;;;;;;;;;;;;;UAeM,gBAAgB,YAAY;EAC3C;;;;;EAKA,QAAQ,KAAK,eAAe,aAAa,QAAQ,MAAM,iBAAiB;;;EAGxE,QAAQ;IAAQ,SAAS,cAAc;;IAAwB;IAAe;;;UAG/D;EACf;EACA;EACA,mBAAmB,qBAAqB;;UAGzB,wBAAwB;EACvC,UAAU;;;KAMA;;KAGA;UAEK;EACf;EACA,QAAQ;EACR;;UAGe,YAAY,WAAW,kBAAkB;EACxD,oBAAoB,YAAY;EAChC,oBAAoB,YAAY;;EAEhC,aAAa,YAAY,eAAe;;;;;EAKxC,sBAAsB,YAAY,eAAe;;;;;;;EAOjD,yBAAyB,YAAY,eAAe;;;EAGpD,uBAAuB,YAAY;EACnC,WAAW;EACX;IAAQ;IAAmB;;;EAE3B,aAAa;EACb;EACA,QAAQ;;UAGO;EACf,UAAU;EACV;EACA,mBAAmB;EACnB;;;UAIe,KAAK,qBAAqB,kBAAkB,WAAW;EACtE;EACA,OAAO,KAAK,YAAY,WAAW,aAAa,QAAQ;;;;UAOzC;EACf,KAAK,cAAc,aAAa,0BAA0B;EAC1D,SAAS;;UAGM;EACf,IAAI,aAAa;EACjB,aAAa,aAAa;;;;UAKX;EACf,MAAM,cAAc,kBAAkB,aAAa;EACnD,UAAU,cAAc,iBAAiB;;;;;;KAO/B,qBAAqB;;;;;UAMhB;;EAEf,YAAY,GACV,OAAO,KAAK,iBAAiB;IAC3B,UAAU;MAEX,QAAQ,eAAe;;;;;KAQhB;KAOA;;;;;;;;;;;;;;;KAgBA;;iBASI,eAAe,OAAO;;;;UAOrB,qBAAqB,kBAAkB,WAAW,UAAU;EAC3E,UAAU;EACV,UAAU;EACV,aAAa,eAAe;EAC5B,QAAQ;EACR;EACA;EACA,iBAAiB;;;;;EAKjB,aAAa;;EAEb;;UAGe,sBAAsB,kBAAkB,WAAW,UAAU,6BACpE,qBAAqB,WAAW;;EAExC;;;EAGA;;UAGe;EACf;;EAEA;;;;EAIA;EACA;IACE;IACA,SAAS,wBAAwB;IACjC;IACA;;;;;IAKA,WAAW;;;UAIE;EACf,QAAQ,OAAO,uBAAuB;EACtC,OAAO,MAAM,4BAA4B,QAAQ;EACjD,QAAQ;IACN;IACA;IACA,UAAU;;;IAGV,SAAS,OAAO;;;UAMH,mBAAmB;;;EAGlC;EACA;EACA;EACA;EACA;EACA,UAAU;EACV,aAAa,eAAe;;;EAG5B;;EAEA,gBAAgB;;EAEhB;;;EAGA,YAAY;;;EAGZ;;;EAGA;EACA;EACA;EACA;;EAEA;;EAEA;EACA;;UAGe;EACf;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;;UAGe;EACf;EACA,YAAY;EACZ;;;;;;UAOe;EACf;;EAEA;;EAEA;;EAEA;;EAEA;;;EAGA;;;;EAIA;;;;EAIA;IACE;IACA;IACA,iBAAiB;MAAQ;MAAgB;;;;;EAI3C,YAAY;;;;;;;;;;EAUZ,WAAW;IAAQ;IAAoB;IAAmB;IAAgB;;;;EAG1E;;;;EAIA;;UAGe;EACf,SAAS,eAAe;EACxB,YAAY,eAAe;;EAE3B,MAAM;;EAEN;EACA;EACA;;EAEA;;EAEA;;EAEA;;EAEA;;UAGe,eAAe,qBAAqB,kBAAkB,WAAW;;EAEhF;;EAEA;EACA;;EAEA;EACA;EACA;EACA;EACA,OAAO,MAAM,mBAAmB;EAChC,YAAY;EACZ;IACE,aAAa;IACb;;EAEF,OAAO;EACP;EACA;EACA,iBAAiB;;;EAGjB,WAAW,MAAM,2BAA2B,KAAK"}

package/dist/{types-CWcPguwd.d.ts → types-ColZlZtc.d.ts}

@@ -1,5 +1,5 @@
 import { s as RunSplitTag } from "./run-record-DVV82Gwh.js";
-import { R as Scenario, d as DispatchContext } from "./types-DABZgDGV.js";
+import { R as Scenario, d as DispatchContext } from "./types-C1Bmeb8X.js";
 //#region src/benchmarks/types.d.ts
 type BenchmarkTaskKind = 'retrieval' | 'rag-answer' | 'hallucination' | 'kb-improvement' | 'routing' | 'custom';
 type BenchmarkFamily = 'beir' | 'mteb-retrieval' | 'msmarco' | 'trec-dl' | 'miracl' | 'lotte' | 'bright' | 'crag' | 'hotpotqa' | 'kilt' | 'ragtruth' | 'faithbench' | 'first-party' | 'custom';
@@ -90,4 +90,4 @@ declare const BENCHMARK_SPLIT_SEED = "agent-eval-v1";
 declare function deterministicSplit(itemId: string, seed?: string): RunSplitTag;
 //#endregion
 export { BenchmarkFamily as a, BenchmarkSource as c, BenchmarkEvaluation as i, BenchmarkTaskKind as l, BenchmarkAdapter as n, BenchmarkResponder as o, BenchmarkDatasetItem as r, BenchmarkScenario as s, BENCHMARK_SPLIT_SEED as t, deterministicSplit as u };
-//# sourceMappingURL=types-CWcPguwd.d.ts.map
+//# sourceMappingURL=types-ColZlZtc.d.ts.map

package/dist/{types-CWcPguwd.d.ts.map → types-ColZlZtc.d.ts.map}

@@ -1 +1 @@
-{"version":3,"file":"types-CWcPguwd.d.ts","names":[],"sources":["../src/benchmarks/types.ts"],"mappings":";;;KASY;KAQA;UAgBK,qBAAqB;;;EAGpC;;EAEA,SAAS;;EAET,QAAQ;;EAER,SAAS;;EAET,WAAW;;EAEX;;EAEA,SAAS;EACT,WAAW;;UAGI;;;;EAIf;;EAEA;;EAEA,aAAa;;;EAGb,KAAK;EACL;;UAGe;EACf;EACA;EACA;EACA;EACA;;;UAQe,iBAAiB,kBAAkB,oBAAoB;;EAEtE;EACA,SAAS;EACT,WAAW;EACX;EACA,SAAS;EACT;;;;;EAKA,YAAY,OAAO,cAAc,QAAQ,qBAAqB;;EAE9D,SAAS,MAAM,qBAAqB,WAAW,UAAU,YAAY,QAAQ;;;;EAI7E,YAAY,iBAAiB;;UAGd,kBAAkB,4BAA4B;EAC7D;EACA;EACA,QAAQ;EACR,UAAU;EACV,UAAU;EACV,MAAM,qBAAqB;;KAGjB,mBAAmB,oBAAoB,uBAAuB;EACxE,UAAU,kBAAkB;EAC5B,MAAM,qBAAqB;EAC3B,SAAS;MACL,QAAQ,aAAa;;;cAoBd;;;;;;;;;iBAUG,mBACd,gBACA,gBACC"}
+{"version":3,"file":"types-ColZlZtc.d.ts","names":[],"sources":["../src/benchmarks/types.ts"],"mappings":";;;KASY;KAQA;UAgBK,qBAAqB;;;EAGpC;;EAEA,SAAS;;EAET,QAAQ;;EAER,SAAS;;EAET,WAAW;;EAEX;;EAEA,SAAS;EACT,WAAW;;UAGI;;;;EAIf;;EAEA;;EAEA,aAAa;;;EAGb,KAAK;EACL;;UAGe;EACf;EACA;EACA;EACA;EACA;;;UAQe,iBAAiB,kBAAkB,oBAAoB;;EAEtE;EACA,SAAS;EACT,WAAW;EACX;EACA,SAAS;EACT;;;;;EAKA,YAAY,OAAO,cAAc,QAAQ,qBAAqB;;EAE9D,SAAS,MAAM,qBAAqB,WAAW,UAAU,YAAY,QAAQ;;;;EAI7E,YAAY,iBAAiB;;UAGd,kBAAkB,4BAA4B;EAC7D;EACA;EACA,QAAQ;EACR,UAAU;EACV,UAAU;EACV,MAAM,qBAAqB;;KAGjB,mBAAmB,oBAAoB,uBAAuB;EACxE,UAAU,kBAAkB;EAC5B,MAAM,qBAAqB;EAC3B,SAAS;MACL,QAAQ,aAAa;;;cAoBd;;;;;;;;;iBAUG,mBACd,gBACA,gBACC"}

package/dist/{types-XBRdmbj8.d.ts → types-DOhGq4S1.d.ts}

@@ -767,10 +767,6 @@ interface CompletionCriterion {
   check: (state: DriverState) => boolean;
   progress?: (state: DriverState) => number;
 }
-interface FeedbackPattern {
-  trigger: string;
-  response: string;
-}
 /**
  * How hard the simulated user pushes back. The driver LLM scales its tone
  * and follow-up aggression to this:
@@ -785,9 +781,7 @@ interface PersonaConfig {
   role: string;
   goal: string;
   completionCriteria: CompletionCriterion[];
-  feedbackPatterns?: FeedbackPattern[];
   maxTurns: number;
-  driverModel?: string;
   /** How adversarial the simulated user is. Defaults to 'demanding'. */
   rigor?: PersonaRigor;
   /**
@@ -842,4 +836,4 @@ interface CheckResult {
 }
 //#endregion
 export { checkServedModel as $, LlmClientOptions as A, isTransientLlmError as B, SandboxSdkTransportOpts as C, LlmCallRequest as D, LlmCallMetadata as E, assertLlmRoute as F, AssertServedModelOptions as G, probeLlm as H, callLlm as I, ServedModelCheck as J, ModelSubstitutionError as K, callLlmJson as L, LlmResponseError as M, LlmRouteRequirements as N, LlmCallResult as O, LlmUsage as P, assertServedModels as Q, costReceiptFromLlm as R, RouterTransportOpts as S, LlmCallError as T, stripFencedJson as U, maximumChargeForLlmRequest as V, AssertCrossFamilyServedOptions as W, assertCrossFamilyServed as X, ServedModelVerdict as Y, assertServedModel as Z, CliBridgeTransportOpts as _, providerFromBaseUrl as _t, JudgeInput as a, judgeFamily as at, DirectProviderTransportOpts as b, PersonaConfig as c, InMemoryRawProviderSink as ct, Scenario as d, ProviderRedactor as dt, servedModelAcceptable as et, ChatCallOpts as f, RawProviderDirection as ft, ChatTransport as g, defaultProviderRedactor as gt, ChatResponse as h, RawProviderSinkFilter as ht, JudgeFn as i, assertCrossFamily as it, LlmMessage as j, LlmClient as k, ProductClientConfig as l, InMemoryRawProviderSinkOptions as lt, ChatRequest as m, RawProviderSink as mt, CompletionCriterion as n, CrossFamilyError as nt, JudgeRubric as o, FileSystemRawProviderSink as ot, ChatClient as p, RawProviderEvent as pt, ServedCrossFamilyError as q, DriverState as r, JudgeFamily as rt, JudgeScore as s, FileSystemRawProviderSinkOptions as st, CheckResult as t, AssertCrossFamilyOptions as tt, RouteMap as u, NoopRawProviderSink as ut, CreateChatClientOpts as v, createChatClient as w, MockTransportOpts as x, CustomTransportOpts as y, costReceiptFromLlmError as z };
-//# sourceMappingURL=types-XBRdmbj8.d.ts.map
+//# sourceMappingURL=types-DOhGq4S1.d.ts.map

package/dist/{types-XBRdmbj8.d.ts.map → types-DOhGq4S1.d.ts.map}

@@ -1 +1 @@
-{"version":3,"file":"types-XBRdmbj8.d.ts","names":[],"sources":["../src/trace/raw-provider-sink.ts","../src/judge-families.ts","../src/integrity/served-model.ts","../src/llm-client.ts","../src/analyst/chat-client.ts","../src/types.ts"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;KA8BY;UAEK;;EAEf;;EAEA;EACA;;;;;;EAMA;EACA;;EAEA;;EAEA;;EAEA;EACA,WAAW;;EAEX;;EAEA;EACA;EACA,iBAAiB;EACjB;EACA,kBAAkB;EAClB;;EAEA;;EAEA;;UAGe;EACf;EACA;EACA,YAAY;EACZ;;UAGe;EACf,OAAO,OAAO,mBAAmB;;EAEjC,MAAM,SAAS,wBAAwB,QAAQ;;EAE/C,UAAU;;KAGA,oBAAoB,OAAO,qBAAqB;;;;;;iBAmB5C,wBAAwB,OAAO,mBAAmB;UA8CjD;EACf,WAAW;;cAGA,mCAAmC;UACtC;UACA;EAER,YAAY,OAAM;EAIZ,OAAO,OAAO,mBAAmB;EAIjC,KAAK,SAAQ,wBAA6B,QAAQ;EAUxD;;cAKW,+BAA+B;EACpC,UAAU;;;;;;;EASV,QAAQ,QAAQ;;UAOP;;EAEf;;EAEA;;EAEA;EACA,WAAW;;cAGA,qCAAqC;UACxC;UACA;UACA;UACA;UACA;UACA;UACA;EAER,YAAY,MAAM;UAOJ;UAON;EAKF,OAAO,OAAO,mBAAmB;EAYjC,KAAK,SAAQ,wBAA6B,QAAQ;;;;;;iBAkC1C,oBAAoB;;;;;;;;;;;;;KC5QxB;;;;;;;iBAkEI,YAAY,kBAAkB;UAc7B;;EAEf;;;;EAIA;;cAGW,yBAAyB;WAGlB,UAAU;WACV;EAHlB,YACE,iBACgB,UAAU,eACV;;;;;;;;;;;;;;;iBAoBJ,kBACd,kBACA,OAAM,2BACL;;;;KCnFS;;;;;;;;;;;UAYK;;EAEf;;EAEA;EACA,iBAAiB;;EAEjB,cAAc;EACd,SAAS;;EAET;;;;;;;;;;;;iBA4Cc,iBACd,mBACA,oCACC;cA4CU,+BAA+B;WAGxB,QAAQ,cAAc;EAFxC,YACE,iBACgB,QAAQ,cAAc;;UAOzB;;;;;;EAMf;;;;;EAKA;;EAEA;;;;;;;iBAQc,sBACd,OAAO,kBACP,OAAM;;;;;;iBA6BQ,kBACd,mBACA,mCACA,OAAM,2BACL;;;;;iBAea,mBACd,OAAO;EAAgB;EAAmB;IAC1C,OAAM,2BACL;UAec,uCAAuC;;EAEtD;;EAEA;;cAGW,+BAA+B;WAGxB,UAAU;WACV,QAAQ,cAAc;EAHxC,YACE,iBACgB,UAAU,eACV,QAAQ,cAAc;;;;;;;;;;;iBAgB1B,wBACd,OAAO;EAAgB;EAAmB;IAC1C,OAAM,iCACL;;;UCjPc;EACf;;;;;EAKA,kBAEI;IACM;IAAc;;IACd;IAAmB;MAAa;MAAa;;;;KAI7C;UAEK;EACf;EACA,UAAU;;EAEV;;EAEA;IAAe;IAAc,QAAQ;;EACrC;EACA;;EAEA,WAAW;;EAEX;;;;;;iBAOc,2BACd,SAAS,KAAK,iFACd,UAAS,mBACR;UAgCc;EACf;EACA;EACA;;EAEA;;EAEA;;EAEA;;UAGe;;EAEf;EACA,OAAO;;;;;EAKP;;;;;;;;;EASA;;;;;;;;;;;;EAYA;;EAEA;;;;;;;;;EASA;;;;;;;EAOA;;EAEA,KAAK;;KAGK,kBAAkB,KAAK;;iBAGnB,mBACd,QAAQ,eACR,qBAAqB,qBACpB;;iBA2Ba,wBACd,OAAO,OACP,qBAAqB,qBACpB;cAMU,qBAAqB;WAGd;WACA;WACA;EAJlB,YACE,iBACgB,gBACA,cACA;;;;;cASP,yBAAyB;WAGlB,QAAQ;EAF1B,YACE,iBACgB,QAAQ,eACxB;IAAY;;;UAMC;;EAEf;;EAEA;EACA;;EAEA;IAAe;IAAc;;;EAE7B;;EAEA;;;;;;;EAOA,SAAS;;;;;;;;EAQT;;EAEA;;EAEA,qBAAqB;;;;;;;EAOrB;;;;;;EAMA;;EAEA,WAAW;;EAEX,eAAe;;;;;;;;EAQf,UAAU;;;;;EAKV;;EAEA;IAAiB;IAAgB;;;EAEjC,WAAW;;;;;;;;;;EAUX,8BAA8B;;;;;;;;;;;;;iBAsEhB,oBAAoB;;;;;;iBA6IpB,gBAAgB;;;;;;iBA6EV,QACpB,KAAK,gBACL,OAAM,mBACL,QAAQ;;;;;;;iBAoVW,YAAY,aAChC,KAAK,gBACL,OAAM,mBACL;EAAU,OAAO;EAAG,QAAQ;;UA6Ed;;;;;;;EAOf;;;;;EAKA,kBAAkB,eAAe;;EAEjC,kBAAkB,eAAe;;EAEjC;;;;;EAKA;;;;;;;;;;;iBAYc,eAAe,MAAM,kBAAkB,MAAK;;;;;;;;;;;;;;;;;;iBA6EtC,SACpB,eACA,OAAM;EAAqB;IAC1B;EACD;EACA;EACA;;EAEA;;EAEA;;;;;;;cAoCW;WACF;mBACQ;EAEjB,YAAY,OAAM;EAKlB,KAAK,KAAK,gBAAgB,MAAM,mBAAmB,QAAQ;EAK3D,SAAS,aACP,KAAK,gBACL,MAAM,mBACL;IAAU,OAAO;IAAG,QAAQ;;;;;;;;UCjqChB;;WAEN,WAAW;;WAEX;;WAEA;;EAGT,KAAK,KAAK,aAAa,OAAO,eAAe,QAAQ;;KAG3C;UAQK,oBAAoB,KAAK;;EAExC;;KAGU,eAAe;UAEV;;EAEf,SAAS;;EAET;;EAEA;;EAEA;;KAKU,uBACR,sBACA,yBACA,8BACA,0BACA,sBACA;UAEM;EACR;;EAEA;;UAGe,4BAA4B;EAC3C;EACA;EACA;;UAGe,+BAA+B;EAC9C;EACA;EACA;;UAGe,oCAAoC;EACnD;EACA;EACA;;;;;;UAOe,gCAAgC;EAC/C;EACA,OAAO,KAAK,aAAa,OAAO,iBAAiB,QAAQ;;;UAI1C,4BAA4B;EAC3C;EACA,OAAO,KAAK,aAAa,OAAO,iBAAiB,QAAQ;;;;;;UAO1C,0BAA0B;EACzC;EACA,UAAU,KAAK,aAAa,OAAO,iBAAiB,QAAQ;;;;;;iBAO9C,iBAAiB,MAAM,uBAAuB;;;UCjH7C;EACf;EACA;EACA;EACA;EACA;EACA,OAAO;EACP,gBAAgB;EAChB;;UAGe;EACf;EACA;EACA;EACA;;UAKe;EACf;EAQA;EACA;EACA;EACA;;UAKe;EACf;EACA;EACA,YAAY;;UAGG;EACf;EACA;EACA;EACA;EACA;;UAmBe;EACf;EACA;EACA;EACA;EACA;IAAmB;IAAc;;EACjC;EACA;;UASe;EACf;EACA;EACA;EACA;EACA;;UAGe;EACf;IAAc;IAAc;;EAC5B;IAAmB;IAAc,QAAQ;;EACzC;IAAc;IAAkB;;EAChC;;UAKe;EACf;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;GACC;;UAGc;EACf;EACA,QAAQ;;EAER;;UAyBe;EACf;EACA,QAAQ,OAAO;EACf,YAAY,OAAO;;UAGJ;EACf;EACA;;;;;;;;;;KAWU;UAEK;EACf;EACA;EACA;EACA,oBAAoB;EACpB,mBAAmB;EACnB;EACA;;EAEA,QAAQ;;;;;;;EAOR;;;;;;;EAOA;;;;;;EAMA;;UAGe;EACf;EACA;EACA;IAAa;IAAiB;IAAkB;;EAChD;EACA;EACA;;UAGe;EACf,UAAU;EACV,OAAO;EACP,WAAW;;EAEX,aAAa;EACb;EACA,WAAW;EACX,SAAS;;KAGC,WAAW,MAAM,YAAY,OAAO,eAAe,QAAQ;UAYtD;EACf;EACA;EACA;EACA"}
+{"version":3,"file":"types-DOhGq4S1.d.ts","names":[],"sources":["../src/trace/raw-provider-sink.ts","../src/judge-families.ts","../src/integrity/served-model.ts","../src/llm-client.ts","../src/analyst/chat-client.ts","../src/types.ts"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;KA8BY;UAEK;;EAEf;;EAEA;EACA;;;;;;EAMA;EACA;;EAEA;;EAEA;;EAEA;EACA,WAAW;;EAEX;;EAEA;EACA;EACA,iBAAiB;EACjB;EACA,kBAAkB;EAClB;;EAEA;;EAEA;;UAGe;EACf;EACA;EACA,YAAY;EACZ;;UAGe;EACf,OAAO,OAAO,mBAAmB;;EAEjC,MAAM,SAAS,wBAAwB,QAAQ;;EAE/C,UAAU;;KAGA,oBAAoB,OAAO,qBAAqB;;;;;;iBAmB5C,wBAAwB,OAAO,mBAAmB;UA8CjD;EACf,WAAW;;cAGA,mCAAmC;UACtC;UACA;EAER,YAAY,OAAM;EAIZ,OAAO,OAAO,mBAAmB;EAIjC,KAAK,SAAQ,wBAA6B,QAAQ;EAUxD;;cAKW,+BAA+B;EACpC,UAAU;;;;;;;EASV,QAAQ,QAAQ;;UAOP;;EAEf;;EAEA;;EAEA;EACA,WAAW;;cAGA,qCAAqC;UACxC;UACA;UACA;UACA;UACA;UACA;UACA;EAER,YAAY,MAAM;UAOJ;UAON;EAKF,OAAO,OAAO,mBAAmB;EAYjC,KAAK,SAAQ,wBAA6B,QAAQ;;;;;;iBAkC1C,oBAAoB;;;;;;;;;;;;;KC5QxB;;;;;;;iBAkEI,YAAY,kBAAkB;UAc7B;;EAEf;;;;EAIA;;cAGW,yBAAyB;WAGlB,UAAU;WACV;EAHlB,YACE,iBACgB,UAAU,eACV;;;;;;;;;;;;;;;iBAoBJ,kBACd,kBACA,OAAM,2BACL;;;;KCnFS;;;;;;;;;;;UAYK;;EAEf;;EAEA;EACA,iBAAiB;;EAEjB,cAAc;EACd,SAAS;;EAET;;;;;;;;;;;;iBA4Cc,iBACd,mBACA,oCACC;cA4CU,+BAA+B;WAGxB,QAAQ,cAAc;EAFxC,YACE,iBACgB,QAAQ,cAAc;;UAOzB;;;;;;EAMf;;;;;EAKA;;EAEA;;;;;;;iBAQc,sBACd,OAAO,kBACP,OAAM;;;;;;iBA6BQ,kBACd,mBACA,mCACA,OAAM,2BACL;;;;;iBAea,mBACd,OAAO;EAAgB;EAAmB;IAC1C,OAAM,2BACL;UAec,uCAAuC;;EAEtD;;EAEA;;cAGW,+BAA+B;WAGxB,UAAU;WACV,QAAQ,cAAc;EAHxC,YACE,iBACgB,UAAU,eACV,QAAQ,cAAc;;;;;;;;;;;iBAgB1B,wBACd,OAAO;EAAgB;EAAmB;IAC1C,OAAM,iCACL;;;UCjPc;EACf;;;;;EAKA,kBAEI;IACM;IAAc;;IACd;IAAmB;MAAa;MAAa;;;;KAI7C;UAEK;EACf;EACA,UAAU;;EAEV;;EAEA;IAAe;IAAc,QAAQ;;EACrC;EACA;;EAEA,WAAW;;EAEX;;;;;;iBAOc,2BACd,SAAS,KAAK,iFACd,UAAS,mBACR;UAgCc;EACf;EACA;EACA;;EAEA;;EAEA;;EAEA;;UAGe;;EAEf;EACA,OAAO;;;;;EAKP;;;;;;;;;EASA;;;;;;;;;;;;EAYA;;EAEA;;;;;;;;;EASA;;;;;;;EAOA;;EAEA,KAAK;;KAGK,kBAAkB,KAAK;;iBAGnB,mBACd,QAAQ,eACR,qBAAqB,qBACpB;;iBA2Ba,wBACd,OAAO,OACP,qBAAqB,qBACpB;cAMU,qBAAqB;WAGd;WACA;WACA;EAJlB,YACE,iBACgB,gBACA,cACA;;;;;cASP,yBAAyB;WAGlB,QAAQ;EAF1B,YACE,iBACgB,QAAQ,eACxB;IAAY;;;UAMC;;EAEf;;EAEA;EACA;;EAEA;IAAe;IAAc;;;EAE7B;;EAEA;;;;;;;EAOA,SAAS;;;;;;;;EAQT;;EAEA;;EAEA,qBAAqB;;;;;;;EAOrB;;;;;;EAMA;;EAEA,WAAW;;EAEX,eAAe;;;;;;;;EAQf,UAAU;;;;;EAKV;;EAEA;IAAiB;IAAgB;;;EAEjC,WAAW;;;;;;;;;;EAUX,8BAA8B;;;;;;;;;;;;;iBAsEhB,oBAAoB;;;;;;iBA6IpB,gBAAgB;;;;;;iBA6EV,QACpB,KAAK,gBACL,OAAM,mBACL,QAAQ;;;;;;;iBAoVW,YAAY,aAChC,KAAK,gBACL,OAAM,mBACL;EAAU,OAAO;EAAG,QAAQ;;UA6Ed;;;;;;;EAOf;;;;;EAKA,kBAAkB,eAAe;;EAEjC,kBAAkB,eAAe;;EAEjC;;;;;EAKA;;;;;;;;;;;iBAYc,eAAe,MAAM,kBAAkB,MAAK;;;;;;;;;;;;;;;;;;iBA6EtC,SACpB,eACA,OAAM;EAAqB;IAC1B;EACD;EACA;EACA;;EAEA;;EAEA;;;;;;;cAoCW;WACF;mBACQ;EAEjB,YAAY,OAAM;EAKlB,KAAK,KAAK,gBAAgB,MAAM,mBAAmB,QAAQ;EAK3D,SAAS,aACP,KAAK,gBACL,MAAM,mBACL;IAAU,OAAO;IAAG,QAAQ;;;;;;;;UCjqChB;;WAEN,WAAW;;WAEX;;WAEA;;EAGT,KAAK,KAAK,aAAa,OAAO,eAAe,QAAQ;;KAG3C;UAQK,oBAAoB,KAAK;;EAExC;;KAGU,eAAe;UAEV;;EAEf,SAAS;;EAET;;EAEA;;EAEA;;KAKU,uBACR,sBACA,yBACA,8BACA,0BACA,sBACA;UAEM;EACR;;EAEA;;UAGe,4BAA4B;EAC3C;EACA;EACA;;UAGe,+BAA+B;EAC9C;EACA;EACA;;UAGe,oCAAoC;EACnD;EACA;EACA;;;;;;UAOe,gCAAgC;EAC/C;EACA,OAAO,KAAK,aAAa,OAAO,iBAAiB,QAAQ;;;UAI1C,4BAA4B;EAC3C;EACA,OAAO,KAAK,aAAa,OAAO,iBAAiB,QAAQ;;;;;;UAO1C,0BAA0B;EACzC;EACA,UAAU,KAAK,aAAa,OAAO,iBAAiB,QAAQ;;;;;;iBAO9C,iBAAiB,MAAM,uBAAuB;;;UCjH7C;EACf;EACA;EACA;EACA;EACA;EACA,OAAO;EACP,gBAAgB;EAChB;;UAGe;EACf;EACA;EACA;EACA;;UAKe;EACf;EAQA;EACA;EACA;EACA;;UAKe;EACf;EACA;EACA,YAAY;;UAGG;EACf;EACA;EACA;EACA;EACA;;UAmBe;EACf;EACA;EACA;EACA;EACA;IAAmB;IAAc;;EACjC;EACA;;UASe;EACf;EACA;EACA;EACA;EACA;;UAGe;EACf;IAAc;IAAc;;EAC5B;IAAmB;IAAc,QAAQ;;EACzC;IAAc;IAAkB;;EAChC;;UAKe;EACf;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;GACC;;UAGc;EACf;EACA,QAAQ;;EAER;;UAyBe;EACf;EACA,QAAQ,OAAO;EACf,YAAY,OAAO;;;;;;;;;;KAWT;UAEK;EACf;EACA;EACA;EACA,oBAAoB;EACpB;;EAEA,QAAQ;;;;;;;EAOR;;;;;;;EAOA;;;;;;EAMA;;UAGe;EACf;EACA;EACA;IAAa;IAAiB;IAAkB;;EAChD;EACA;EACA;;UAGe;EACf,UAAU;EACV,OAAO;EACP,WAAW;;EAEX,aAAa;EACb;EACA,WAAW;EACX,SAAS;;KAGC,WAAW,MAAM,YAAY,OAAO,eAAe,QAAQ;UAYtD;EACf;EACA;EACA;EACA"}

package/dist/wire/index.d.ts

@@ -1,7 +1,7 @@
 import { c as CostLedgerHandle } from "../cost-ledger-DbQdN3nO.js";
-import { A as LlmClientOptions, N as LlmRouteRequirements } from "../types-XBRdmbj8.js";
+import { A as LlmClientOptions, N as LlmRouteRequirements } from "../types-DOhGq4S1.js";
 import { s as TraceStore } from "../store-CT9YIIve.js";
-import { m as FeedbackTrajectoryStore } from "../feedback-trajectory-Cg9EDxKB.js";
+import { m as FeedbackTrajectoryStore } from "../feedback-trajectory-niGeR6uJ.js";
 import { z } from "zod";
 import { ServerType } from "@hono/node-server";
 import { Hono } from "hono";

package/dist/wire/index.js

@@ -1,2 +1,2 @@
-import { A as TraceEventSchema, C as HealthResponseSchema, D as RubricDimensionSchema, E as ListRubricsResponseSchema, F as hashRubric, M as TracesIngestResponseSchema, N as VersionResponseSchema, O as RubricInfoSchema, P as WIRE_VERSION, S as FeedbackTrajectorySchema, T as JudgeResultSchema, _ as ErrorResponseSchema, a as runRpcBatch, b as FeedbackIngestResponseSchema, c as WireError, d as handleListRubrics, f as handleTracesIngest, g as listBuiltinRubrics, h as getBuiltinRubric, i as dispatchRpc, j as TracesIngestRequestSchema, k as RubricSchema, l as handleFeedbackIngest, m as BUILTIN_RUBRICS, n as startServer, o as runRpcOnce, p as handleVersion, r as startServerAsync, s as buildOpenApi, t as createApp, u as handleJudge, v as FailureModeSchema, w as JudgeRequestSchema, x as FeedbackLabelSchema, y as FeedbackAttemptSchema } from "../server-cQXve8i4.js";
+import { A as TraceEventSchema, C as HealthResponseSchema, D as RubricDimensionSchema, E as ListRubricsResponseSchema, F as hashRubric, M as TracesIngestResponseSchema, N as VersionResponseSchema, O as RubricInfoSchema, P as WIRE_VERSION, S as FeedbackTrajectorySchema, T as JudgeResultSchema, _ as ErrorResponseSchema, a as runRpcBatch, b as FeedbackIngestResponseSchema, c as WireError, d as handleListRubrics, f as handleTracesIngest, g as listBuiltinRubrics, h as getBuiltinRubric, i as dispatchRpc, j as TracesIngestRequestSchema, k as RubricSchema, l as handleFeedbackIngest, m as BUILTIN_RUBRICS, n as startServer, o as runRpcOnce, p as handleVersion, r as startServerAsync, s as buildOpenApi, t as createApp, u as handleJudge, v as FailureModeSchema, w as JudgeRequestSchema, x as FeedbackLabelSchema, y as FeedbackAttemptSchema } from "../server-D9wQclzG.js";
 export { BUILTIN_RUBRICS, ErrorResponseSchema, FailureModeSchema, FeedbackAttemptSchema, FeedbackIngestResponseSchema, FeedbackLabelSchema, FeedbackTrajectorySchema, HealthResponseSchema, JudgeRequestSchema, JudgeResultSchema, ListRubricsResponseSchema, RubricDimensionSchema, RubricInfoSchema, RubricSchema, TraceEventSchema, TracesIngestRequestSchema, TracesIngestResponseSchema, VersionResponseSchema, WIRE_VERSION, WireError, buildOpenApi, createApp, dispatchRpc, getBuiltinRubric, handleFeedbackIngest, handleJudge, handleListRubrics, handleTracesIngest, handleVersion, hashRubric, listBuiltinRubrics, runRpcBatch, runRpcOnce, startServer, startServerAsync };

package/docs/multishot-golden-records.md

@@ -0,0 +1,102 @@
+# Multishot golden records
+
+`@tangle-network/agent-eval/multishot/golden` holds frozen recordings of what a multishot conversation engine produces on a closed set of deterministic scenarios.
+Point your engine at them and any orchestration drift surfaces as a named field.
+
+## What a record holds
+
+Each scenario records two things.
+
+**The request ledger** — every transport call each leg received, in issue order: the model, the temperature, the token budget, the advertised tool definitions, and the full message log.
+Tools are compared by value, not by array identity: an engine may rebuild the array, but a changed name, description or parameter schema changes what the agent is offered.
+This is where two orchestrators diverge without their return value changing: a wrong follow-up token budget, a driver rotation that stops one model early, a point-of-view translation that drops a tool row from the driver's view.
+
+**The outcome** — either the `MultishotResult` without its wall-clock `durationMs`, or the throw reduced to its constructor name, its message, and the cell spend it declares for the cost ceiling.
+
+The matrix scenarios add the returned `MatrixResult`, the judge calls, and every file the run persisted under its run directory.
+
+Wall-clock and run-identity keys (`durationMs`, `meanDurationMs`, `matrixId`, `runId`) are removed before comparison — no two runs agree on them.
+The summary Markdown keeps its text with the rendered duration masked.
+
+## Use it
+
+```ts
+import { describe, it } from 'vitest'
+import {
+  assertMultishotGoldenScenario,
+  multishotGoldenScenarios,
+} from '@tangle-network/agent-eval/multishot/golden'
+import { runMyEngine } from './my-engine'
+
+describe('my engine reproduces the multishot golden records', () => {
+  for (const scenario of multishotGoldenScenarios()) {
+    it(scenario.description, async () => {
+      await assertMultishotGoldenScenario({ engine: runMyEngine, scenario })
+    })
+  }
+})
+```
+
+`assertMultishotGoldenScenario` throws `MultishotGoldenMismatchError` listing every field that moved.
+`checkMultishotGoldenScenario` returns the same report without throwing, for a caller that wants to inspect it.
+`checkMultishotGolden` runs every SHOT scenario in one call; the matrix scenarios have their own pair below.
+It refuses an `only` id the catalog does not hold, so a stale id after a rename stops the check instead of greening a run of zero scenarios.
+
+The matrix pair is `assertMultishotMatrixGoldenScenario` / `checkMultishotMatrixGoldenScenario`; both take a `runDir` the engine may write into, and both install a deterministic judge wire on `globalThis.fetch` for the duration of the run.
+That wire is process-wide, so run matrix checks serially within one process and keep other fetch traffic out of it.
+Both rules are enforced, not just documented: a second concurrent install throws, and the wire fails loud on any request it does not recognise rather than answering it.
+
+## Determinism rules
+
+Every scenario is a closed system: scripted transports, scripted tool executors, a fixed persona and profile, fixed token budgets.
+No network, no random number, and no clock in a COMPARED field — the fixture envelope carries a `recordedAt` stamp as provenance, and nothing compares it.
+Matrix cells run one at a time, so the request ledger is a property of the conversation engine rather than of how two engines interleave their microtasks.
+
+Judge calls fan out across three slots through `Promise.all`, so their issue order is a detail of the cell body rather than observable behaviour.
+Their content is behaviour, so they are compared as a set with a stable order.
+
+## Records are frozen
+
+A version file is written once and never edited.
+A golden record that can be regenerated over itself proves nothing: a regression would simply be re-recorded as the new truth.
+
+`scripts/record-multishot-golden.ts` refuses to overwrite an existing version.
+A deliberate behaviour change mints a NEW version file, registers it in `src/multishot/golden/records/index.ts` beside the old one, and moves `CURRENT_MULTISHOT_GOLDEN_VERSION`.
+The diff between the two files is the reviewable evidence of what moved, and the previous contract stays runnable through `goldenRecords('v1')`.
+
+## Regenerate
+
+The recorder never picks an engine for you: the reference has to be named.
+Once the loop leaves this package there is no engine here to default to, and a script that silently picked one would record the wrong thing.
+
+```bash
+pnpm tsx scripts/record-multishot-golden.ts \
+  --version v2 \
+  --engine <module>#<export> \
+  --matrix-engine <module>#<export>
+```
+
+`<module>` resolves from the repository root and may point outside it, so a reference engine that lives in a consumer works:
+
+```bash
+pnpm tsx scripts/record-multishot-golden.ts \
+  --version v2 \
+  --engine ../gtm-agent/eval/lib/multishot-graph.ts#runMultishotGraph \
+  --matrix-engine ../gtm-agent/eval/lib/multishot-matrix-graph.ts#runMultishotMatrixGraph
+```
+
+Then register the new file in `src/multishot/golden/records/index.ts` and move `CURRENT_MULTISHOT_GOLDEN_VERSION` to it.
+The recorder writes the file and nothing else; until it is registered, `goldenRecords()` still resolves the old version and the new file is inert.
+
+Every scenario is captured twice and the two captures must agree.
+A scenario that is not reproducible cannot detect a regression, so an unstable capture fails the run instead of freezing a coin flip.
+Captures run with the network refused and with the same `durationMs` contract the check enforces, so the recorder cannot freeze a record its own reference engine would fail.
+
+## Adding a scenario
+
+Add it to `multishotGoldenScenarios()` in `src/multishot/golden/scenarios.ts`, then mint a new version.
+The record-set integrity test requires one record per catalog scenario in catalog order, so a scenario with no record fails the suite rather than passing silently.
+
+A version may be dropped once no supported consumer checks against it and its behaviour is fully covered by a later version. Until then every version stays: an old record is how a consumer still on an older engine keeps a runnable contract.
+
+`v1` was captured from the `./multishot` loop at agent-eval 0.145.21 — the engine the merged loop-to-graph parity proofs compared against.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tangle-network/agent-eval",
-  "version": "0.145.22",
+  "version": "0.147.0",
   "description": "Evaluate and improve AI agents from runs, traces, judges, and feedback. Compare candidates, cluster failures, measure lift, and gate releases.",
   "homepage": "https://github.com/tangle-network/agent-eval#readme",
   "repository": {
@@ -89,6 +89,11 @@
       "import": "./dist/multishot/index.js",
       "default": "./dist/multishot/index.js"
     },
+    "./multishot/golden": {
+      "types": "./dist/multishot/golden/index.d.ts",
+      "import": "./dist/multishot/golden/index.js",
+      "default": "./dist/multishot/golden/index.js"
+    },
     "./campaign": {
       "types": "./dist/campaign/index.d.ts",
       "import": "./dist/campaign/index.js",
@@ -180,7 +185,7 @@
   "dependencies": {
     "@asteasolutions/zod-to-openapi": "^9.1.0",
     "@hono/node-server": "^2.0.12",
-    "@tangle-network/agent-core": "0.9.4",
+    "@tangle-network/agent-core": "^0.9.4",
     "@tangle-network/agent-interface": "^1.0.0",
     "@tangle-network/agent-trace-contract": "^1.0.2",
     "hono": "^4.12.32",

package/dist/experiment-tracker-C29gXM4B.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"experiment-tracker-C29gXM4B.js","names":[],"sources":["../src/experiment-tracker.ts"],"sourcesContent":["/**\n * Experiment tracker — git-provenanced experiment log with N-rep stats and a\n * KEEP / REGRESSION / NOISE verdict against a parent.\n *\n * Every loop the fleet runs reduces to the same question: \"I ran the candidate\n * N times — is the median measurably better than the parent, or is the delta\n * inside the noise band?\" The hand-rolled copies bake a fixed score scale\n * (percentage points), a fixed store path (`.evolve/experiments-v2.json`), and\n * `execSync('git …')` straight into the module. This is the canonical version:\n * provenance and persistence are injected, thresholds are configurable, and the\n * stats + verdict are pure functions you can unit-test without a git repo or a\n * filesystem.\n *\n * Stats per experiment: median / mean / min / max / iqr / stddev / passRate /\n * n, plus a `stable` flag (`iqr < iqrUnstableAbove && stddev < stddevUnstableAbove`).\n *\n * Verdict against a parent (both must have `n >= minRepsForVerdict`):\n *   - NOISE       — the candidate is too unstable to judge (`!stable`)\n *   - KEEP        — `medianDelta >  keepThreshold`\n *   - REGRESSION  — `medianDelta < -regressionThreshold`\n *   - NOISE       — otherwise (delta inside the band)\n * With no parent (or insufficient reps) the verdict is the neutral ITERATE.\n */\n\nimport { execSync } from 'node:child_process'\nimport { iqr } from './baseline'\nimport { ValidationError } from './errors'\n\n/** Verdict for one experiment relative to its parent. ITERATE is the neutral\n *  \"keep collecting reps / no parent to compare against\" state. */\nexport type ExperimentVerdict = 'KEEP' | 'ITERATE' | 'NOISE' | 'REGRESSION'\n\n/** Git provenance for the working tree an experiment was run from. */\nexport interface ExperimentProvenance {\n  /** Commit sha (short or full — the tracker does not interpret it). */\n  commit: string\n  /** First line of the commit message. */\n  message: string\n  /** Files changed vs the parent commit, or a marker like 'uncommitted'. */\n  changedFiles: string[]\n}\n\n/** A single repetition of an experiment, carrying the score the verdict is\n *  computed on plus any free-form per-rep metrics the consumer wants kept. */\nexport interface ExperimentRep {\n  /** 0-indexed repetition number within the experiment. */\n  rep: number\n  /** The score this rep is judged on (same scale as the thresholds). */\n  score: number\n  /** ISO timestamp the rep completed. */\n  timestamp: string\n  /** Whether this rep passed the consumer's own gate — folded into `passRate`. */\n  passed?: boolean\n  /** Free-form numeric metrics retained for later analysis. */\n  metrics?: Record<string, number>\n}\n\nexport interface ExperimentStats {\n  median: number\n  mean: number\n  min: number\n  max: number\n  /** Inter-quartile range of the rep scores. */\n  iqr: number\n  /** Population standard deviation of the rep scores. */\n  stddev: number\n  /** Fraction of reps with `passed === true`, over reps that set `passed`.\n   *  null when no rep declared a pass/fail outcome. */\n  passRate: number | null\n  /** Number of reps. */\n  n: number\n  /** True when the sample is tight enough to trust for a verdict. */\n  stable: boolean\n}\n\nexport interface Experiment {\n  /** Stable id for the experiment. */\n  id: string\n  /** Free-form label / config descriptor. */\n  label: string\n  /** Git provenance captured when the experiment was created. */\n  provenance: ExperimentProvenance\n  /** Parent experiment id this candidate is compared against, if any. */\n  parentId?: string\n  /** One-line summary of what changed from the parent. */\n  changeSummary: string\n  reps: ExperimentRep[]\n  stats: ExperimentStats\n  verdict: ExperimentVerdict\n  /** ISO timestamp the experiment was created. */\n  createdAt: string\n}\n\nexport interface ImprovementThresholds {\n  /** medianDelta strictly above this ⇒ KEEP. Default 5. */\n  keepThreshold?: number\n  /** medianDelta strictly below the negative of this ⇒ REGRESSION. Default 5. */\n  regressionThreshold?: number\n  /** iqr at or above this ⇒ unstable. Default 10. */\n  iqrUnstableAbove?: number\n  /** stddev at or above this ⇒ unstable. Default Infinity (iqr-only stability). */\n  stddevUnstableAbove?: number\n  /** Reps required on BOTH candidate and parent before a verdict is rendered.\n   *  Default 3. */\n  minRepsForVerdict?: number\n}\n\nexport interface ImprovementVerdictResult {\n  verdict: ExperimentVerdict\n  /** candidate.median − parent.median; null when no parent or insufficient reps. */\n  medianDelta: number | null\n  /** Human-readable reason for the verdict — for dashboards and logs. */\n  reason: string\n}\n\nconst DEFAULTS: Required<ImprovementThresholds> = {\n  keepThreshold: 5,\n  regressionThreshold: 5,\n  iqrUnstableAbove: 10,\n  stddevUnstableAbove: Number.POSITIVE_INFINITY,\n  minRepsForVerdict: 3,\n}\n\nfunction resolveThresholds(t: ImprovementThresholds | undefined): Required<ImprovementThresholds> {\n  const r = { ...DEFAULTS, ...(t ?? {}) }\n  if (r.keepThreshold < 0) {\n    throw new ValidationError(\n      `experiment-tracker: keepThreshold must be >= 0, got ${r.keepThreshold}`,\n    )\n  }\n  if (r.regressionThreshold < 0) {\n    throw new ValidationError(\n      `experiment-tracker: regressionThreshold must be >= 0, got ${r.regressionThreshold}`,\n    )\n  }\n  if (r.minRepsForVerdict < 1) {\n    throw new ValidationError(\n      `experiment-tracker: minRepsForVerdict must be >= 1, got ${r.minRepsForVerdict}`,\n    )\n  }\n  return r\n}\n\nfunction median(sorted: number[]): number {\n  const n = sorted.length\n  if (n === 0) return 0\n  const mid = Math.floor(n / 2)\n  return n % 2 === 0 ? (sorted[mid - 1]! + sorted[mid]!) / 2 : sorted[mid]!\n}\n\n/** Population standard deviation (÷n). 0 for fewer than 2 values. */\nfunction stddev(values: number[], mean: number): number {\n  if (values.length < 2) return 0\n  const variance = values.reduce((acc, v) => acc + (v - mean) ** 2, 0) / values.length\n  return Math.sqrt(variance)\n}\n\n/**\n * Compute the N-rep statistics for a set of reps. Pure — no I/O. The `stable`\n * flag is the trust gate the verdict depends on: a sample whose spread exceeds\n * the configured bounds can't distinguish a real delta from run-to-run noise.\n */\nexport function computeExperimentStats(\n  reps: ExperimentRep[],\n  thresholds?: ImprovementThresholds,\n): ExperimentStats {\n  const t = resolveThresholds(thresholds)\n  const n = reps.length\n  if (n === 0) {\n    return {\n      median: 0,\n      mean: 0,\n      min: 0,\n      max: 0,\n      iqr: 0,\n      stddev: 0,\n      passRate: null,\n      n: 0,\n      stable: false,\n    }\n  }\n  const scores = reps.map((r) => {\n    if (!Number.isFinite(r.score)) {\n      throw new ValidationError(`experiment-tracker: rep ${r.rep} has non-finite score ${r.score}`)\n    }\n    return r.score\n  })\n  const sorted = [...scores].sort((a, b) => a - b)\n  const mean = scores.reduce((s, v) => s + v, 0) / n\n  const sd = stddev(scores, mean)\n  const spread = iqr(scores)\n  const rated = reps.filter((r) => typeof r.passed === 'boolean')\n  const passRate = rated.length === 0 ? null : rated.filter((r) => r.passed).length / rated.length\n  const stable = spread < t.iqrUnstableAbove && sd < t.stddevUnstableAbove\n  return {\n    median: median(sorted),\n    mean,\n    min: sorted[0]!,\n    max: sorted[n - 1]!,\n    iqr: spread,\n    stddev: sd,\n    passRate,\n    n,\n    stable,\n  }\n}\n\n/**\n * Verdict for a candidate against its parent. Pure — operates on already-computed\n * stats. KEEP/REGRESSION require both sides to have `>= minRepsForVerdict` reps\n * AND the candidate to be `stable`; otherwise the result is NOISE (unstable) or\n * ITERATE (not enough reps / no parent).\n */\nexport function improvementVerdict(\n  candidate: ExperimentStats,\n  parent: ExperimentStats | null,\n  thresholds?: ImprovementThresholds,\n): ImprovementVerdictResult {\n  const t = resolveThresholds(thresholds)\n  if (!parent) {\n    return {\n      verdict: 'ITERATE',\n      medianDelta: null,\n      reason: 'no parent experiment to compare against',\n    }\n  }\n  if (candidate.n < t.minRepsForVerdict || parent.n < t.minRepsForVerdict) {\n    return {\n      verdict: 'ITERATE',\n      medianDelta: null,\n      reason: `need >= ${t.minRepsForVerdict} reps on both sides (candidate n=${candidate.n}, parent n=${parent.n})`,\n    }\n  }\n  if (!candidate.stable) {\n    return {\n      verdict: 'NOISE',\n      medianDelta: candidate.median - parent.median,\n      reason: `candidate unstable (iqr=${candidate.iqr}, stddev=${candidate.stddev.toFixed(2)})`,\n    }\n  }\n  const medianDelta = candidate.median - parent.median\n  if (medianDelta > t.keepThreshold) {\n    return { verdict: 'KEEP', medianDelta, reason: `median +${medianDelta} > +${t.keepThreshold}` }\n  }\n  if (medianDelta < -t.regressionThreshold) {\n    return {\n      verdict: 'REGRESSION',\n      medianDelta,\n      reason: `median ${medianDelta} < -${t.regressionThreshold}`,\n    }\n  }\n  return {\n    verdict: 'NOISE',\n    medianDelta,\n    reason: `median delta ${medianDelta} inside noise band [-${t.regressionThreshold}, +${t.keepThreshold}]`,\n  }\n}\n\n// ── Provenance + persistence seams ───────────────────────────────────\n\n/** Reads git provenance for the working tree. Inject a fake in tests; the\n *  default implementation shells out to `git`. */\nexport type ProvenanceReader = () => ExperimentProvenance | Promise<ExperimentProvenance>\n\n/** Persistence seam for the experiment log. Inject in-memory in tests; the\n *  filesystem implementation is `fileExperimentStore`. */\nexport interface ExperimentStore {\n  load(): Promise<Experiment[]>\n  save(experiments: Experiment[]): Promise<void>\n}\n\n/**\n * Default provenance reader: `git rev-parse HEAD`, the subject line, and the\n * files changed vs `HEAD~1`. Fail-loud — a tracker that silently logs\n * `commit: 'unknown'` corrupts the provenance the whole point of the log is to\n * carry. When the working tree genuinely has no parent commit, pass an override.\n */\nexport const gitProvenanceReader: ProvenanceReader = () => {\n  const run = (cmd: string): string => execSync(cmd, { encoding: 'utf8' }).trim()\n  const commit = run('git rev-parse --short HEAD')\n  const message = run('git log -1 --format=%s')\n  const changedRaw = run('git diff --name-only HEAD~1')\n  const changedFiles = changedRaw.length === 0 ? [] : changedRaw.split('\\n').filter(Boolean)\n  return { commit, message, changedFiles }\n}\n\n/** In-memory store — the default when no persistence is wanted (tests, ephemeral\n *  runs). State lives on the instance. */\nexport function inMemoryExperimentStore(initial: Experiment[] = []): ExperimentStore {\n  let state = initial.map((e) => structuredClone(e))\n  return {\n    async load() {\n      return state.map((e) => structuredClone(e))\n    },\n    async save(experiments) {\n      state = experiments.map((e) => structuredClone(e))\n    },\n  }\n}\n\n/** Filesystem store — a single JSON array at `path`, created on first save. */\nexport function fileExperimentStore(path: string): ExperimentStore {\n  return {\n    async load() {\n      const fs = await import('node:fs/promises')\n      try {\n        const raw = await fs.readFile(path, 'utf8')\n        const parsed = JSON.parse(raw)\n        if (!Array.isArray(parsed)) {\n          throw new ValidationError(`experiment-tracker: store at ${path} is not a JSON array`)\n        }\n        return parsed as Experiment[]\n      } catch (err) {\n        if ((err as NodeJS.ErrnoException).code === 'ENOENT') return []\n        throw err\n      }\n    },\n    async save(experiments) {\n      const fs = await import('node:fs/promises')\n      const pathMod = await import('node:path')\n      await fs.mkdir(pathMod.dirname(path), { recursive: true })\n      await fs.writeFile(path, JSON.stringify(experiments, null, 2), 'utf8')\n    },\n  }\n}\n\nexport interface ExperimentTrackerOptions {\n  store?: ExperimentStore\n  provenanceReader?: ProvenanceReader\n  thresholds?: ImprovementThresholds\n  /** Clock seam for deterministic timestamps in tests. Default `Date.now`. */\n  now?: () => number\n}\n\nexport interface CreateExperimentInput {\n  id: string\n  label: string\n  changeSummary: string\n  parentId?: string\n  /** Override provenance instead of reading from git (e.g. CI metadata). */\n  provenance?: ExperimentProvenance\n}\n\n/**\n * Stateful tracker over an `ExperimentStore`. Create an experiment (provenance\n * is captured once), append reps as they complete (stats + verdict recompute on\n * every append), and read the log back for a dashboard. All persistence and git\n * access flow through the injected seams, so the tracker is fully testable\n * without a repo or disk.\n */\nexport class ExperimentTracker {\n  private readonly store: ExperimentStore\n  private readonly provenanceReader: ProvenanceReader\n  private readonly thresholds: Required<ImprovementThresholds>\n  private readonly now: () => number\n\n  constructor(options: ExperimentTrackerOptions = {}) {\n    this.store = options.store ?? inMemoryExperimentStore()\n    this.provenanceReader = options.provenanceReader ?? gitProvenanceReader\n    this.thresholds = resolveThresholds(options.thresholds)\n    this.now = options.now ?? Date.now\n  }\n\n  async create(input: CreateExperimentInput): Promise<Experiment> {\n    const experiments = await this.store.load()\n    if (experiments.some((e) => e.id === input.id)) {\n      throw new ValidationError(`experiment-tracker: experiment id \"${input.id}\" already exists`)\n    }\n    if (input.parentId && !experiments.some((e) => e.id === input.parentId)) {\n      throw new ValidationError(\n        `experiment-tracker: parent experiment \"${input.parentId}\" not found`,\n      )\n    }\n    const provenance = input.provenance ?? (await this.provenanceReader())\n    const experiment: Experiment = {\n      id: input.id,\n      label: input.label,\n      provenance,\n      parentId: input.parentId,\n      changeSummary: input.changeSummary,\n      reps: [],\n      stats: computeExperimentStats([], this.thresholds),\n      verdict: 'ITERATE',\n      createdAt: new Date(this.now()).toISOString(),\n    }\n    experiments.push(experiment)\n    await this.store.save(experiments)\n    return structuredClone(experiment)\n  }\n\n  /** Append a rep (its `rep` index defaults to the current rep count) and\n   *  recompute stats + verdict. Returns the updated experiment. */\n  async addRep(\n    experimentId: string,\n    rep: Omit<ExperimentRep, 'rep' | 'timestamp'> & { rep?: number; timestamp?: string },\n  ): Promise<Experiment> {\n    const experiments = await this.store.load()\n    const exp = experiments.find((e) => e.id === experimentId)\n    if (!exp)\n      throw new ValidationError(`experiment-tracker: experiment \"${experimentId}\" not found`)\n    const fullRep: ExperimentRep = {\n      rep: rep.rep ?? exp.reps.length,\n      score: rep.score,\n      passed: rep.passed,\n      metrics: rep.metrics,\n      timestamp: rep.timestamp ?? new Date(this.now()).toISOString(),\n    }\n    exp.reps.push(fullRep)\n    exp.stats = computeExperimentStats(exp.reps, this.thresholds)\n    const parent = exp.parentId ? experiments.find((e) => e.id === exp.parentId) : undefined\n    exp.verdict = improvementVerdict(exp.stats, parent?.stats ?? null, this.thresholds).verdict\n    await this.store.save(experiments)\n    return structuredClone(exp)\n  }\n\n  async get(experimentId: string): Promise<Experiment | undefined> {\n    const experiments = await this.store.load()\n    const found = experiments.find((e) => e.id === experimentId)\n    return found ? structuredClone(found) : undefined\n  }\n\n  async list(): Promise<Experiment[]> {\n    return this.store.load()\n  }\n\n  /** Full verdict (not just the enum) for an experiment vs its parent. */\n  async verdictFor(experimentId: string): Promise<ImprovementVerdictResult> {\n    const experiments = await this.store.load()\n    const exp = experiments.find((e) => e.id === experimentId)\n    if (!exp)\n      throw new ValidationError(`experiment-tracker: experiment \"${experimentId}\" not found`)\n    const parent = exp.parentId ? experiments.find((e) => e.id === exp.parentId) : undefined\n    return improvementVerdict(exp.stats, parent?.stats ?? null, this.thresholds)\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;AAmHA,MAAM,WAA4C;CAChD,eAAe;CACf,qBAAqB;CACrB,kBAAkB;CAClB,qBAAqB,OAAO;CAC5B,mBAAmB;AACrB;AAEA,SAAS,kBAAkB,GAAuE;CAChG,MAAM,IAAI;EAAE,GAAG;EAAU,GAAI,KAAK,CAAC;CAAG;CACtC,IAAI,EAAE,gBAAgB,GACpB,MAAM,IAAI,gBACR,uDAAuD,EAAE,eAC3D;CAEF,IAAI,EAAE,sBAAsB,GAC1B,MAAM,IAAI,gBACR,6DAA6D,EAAE,qBACjE;CAEF,IAAI,EAAE,oBAAoB,GACxB,MAAM,IAAI,gBACR,2DAA2D,EAAE,mBAC/D;CAEF,OAAO;AACT;AAEA,SAAS,OAAO,QAA0B;CACxC,MAAM,IAAI,OAAO;CACjB,IAAI,MAAM,GAAG,OAAO;CACpB,MAAM,MAAM,KAAK,MAAM,IAAI,CAAC;CAC5B,OAAO,IAAI,MAAM,KAAK,OAAO,MAAM,KAAM,OAAO,QAAS,IAAI,OAAO;AACtE;;AAGA,SAAS,OAAO,QAAkB,MAAsB;CACtD,IAAI,OAAO,SAAS,GAAG,OAAO;CAC9B,MAAM,WAAW,OAAO,QAAQ,KAAK,MAAM,OAAO,IAAI,SAAS,GAAG,CAAC,IAAI,OAAO;CAC9E,OAAO,KAAK,KAAK,QAAQ;AAC3B;;;;;;AAOA,SAAgB,uBACd,MACA,YACiB;CACjB,MAAM,IAAI,kBAAkB,UAAU;CACtC,MAAM,IAAI,KAAK;CACf,IAAI,MAAM,GACR,OAAO;EACL,QAAQ;EACR,MAAM;EACN,KAAK;EACL,KAAK;EACL,KAAK;EACL,QAAQ;EACR,UAAU;EACV,GAAG;EACH,QAAQ;CACV;CAEF,MAAM,SAAS,KAAK,KAAK,MAAM;EAC7B,IAAI,CAAC,OAAO,SAAS,EAAE,KAAK,GAC1B,MAAM,IAAI,gBAAgB,2BAA2B,EAAE,IAAI,wBAAwB,EAAE,OAAO;EAE9F,OAAO,EAAE;CACX,CAAC;CACD,MAAM,SAAS,CAAC,GAAG,MAAM,CAAC,CAAC,MAAM,GAAG,MAAM,IAAI,CAAC;CAC/C,MAAM,OAAO,OAAO,QAAQ,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI;CACjD,MAAM,KAAK,OAAO,QAAQ,IAAI;CAC9B,MAAM,SAAS,IAAI,MAAM;CACzB,MAAM,QAAQ,KAAK,QAAQ,MAAM,OAAO,EAAE,WAAW,SAAS;CAC9D,MAAM,WAAW,MAAM,WAAW,IAAI,OAAO,MAAM,QAAQ,MAAM,EAAE,MAAM,CAAC,CAAC,SAAS,MAAM;CAC1F,MAAM,SAAS,SAAS,EAAE,oBAAoB,KAAK,EAAE;CACrD,OAAO;EACL,QAAQ,OAAO,MAAM;EACrB;EACA,KAAK,OAAO;EACZ,KAAK,OAAO,IAAI;EAChB,KAAK;EACL,QAAQ;EACR;EACA;EACA;CACF;AACF;;;;;;;AAQA,SAAgB,mBACd,WACA,QACA,YAC0B;CAC1B,MAAM,IAAI,kBAAkB,UAAU;CACtC,IAAI,CAAC,QACH,OAAO;EACL,SAAS;EACT,aAAa;EACb,QAAQ;CACV;CAEF,IAAI,UAAU,IAAI,EAAE,qBAAqB,OAAO,IAAI,EAAE,mBACpD,OAAO;EACL,SAAS;EACT,aAAa;EACb,QAAQ,WAAW,EAAE,kBAAkB,mCAAmC,UAAU,EAAE,aAAa,OAAO,EAAE;CAC9G;CAEF,IAAI,CAAC,UAAU,QACb,OAAO;EACL,SAAS;EACT,aAAa,UAAU,SAAS,OAAO;EACvC,QAAQ,2BAA2B,UAAU,IAAI,WAAW,UAAU,OAAO,QAAQ,CAAC,EAAE;CAC1F;CAEF,MAAM,cAAc,UAAU,SAAS,OAAO;CAC9C,IAAI,cAAc,EAAE,eAClB,OAAO;EAAE,SAAS;EAAQ;EAAa,QAAQ,WAAW,YAAY,MAAM,EAAE;CAAgB;CAEhG,IAAI,cAAc,CAAC,EAAE,qBACnB,OAAO;EACL,SAAS;EACT;EACA,QAAQ,UAAU,YAAY,MAAM,EAAE;CACxC;CAEF,OAAO;EACL,SAAS;EACT;EACA,QAAQ,gBAAgB,YAAY,uBAAuB,EAAE,oBAAoB,KAAK,EAAE,cAAc;CACxG;AACF;;;;;;;AAqBA,MAAa,4BAA8C;CACzD,MAAM,OAAO,QAAwB,SAAS,KAAK,EAAE,UAAU,OAAO,CAAC,CAAC,CAAC,KAAK;CAC9E,MAAM,SAAS,IAAI,4BAA4B;CAC/C,MAAM,UAAU,IAAI,wBAAwB;CAC5C,MAAM,aAAa,IAAI,6BAA6B;CAEpD,OAAO;EAAE;EAAQ;EAAS,cADL,WAAW,WAAW,IAAI,CAAC,IAAI,WAAW,MAAM,IAAI,CAAC,CAAC,OAAO,OAAO;CAClD;AACzC;;;AAIA,SAAgB,wBAAwB,UAAwB,CAAC,GAAoB;CACnF,IAAI,QAAQ,QAAQ,KAAK,MAAM,gBAAgB,CAAC,CAAC;CACjD,OAAO;EACL,MAAM,OAAO;GACX,OAAO,MAAM,KAAK,MAAM,gBAAgB,CAAC,CAAC;EAC5C;EACA,MAAM,KAAK,aAAa;GACtB,QAAQ,YAAY,KAAK,MAAM,gBAAgB,CAAC,CAAC;EACnD;CACF;AACF;;AAGA,SAAgB,oBAAoB,MAA+B;CACjE,OAAO;EACL,MAAM,OAAO;GACX,MAAM,KAAK,MAAM,OAAO;GACxB,IAAI;IACF,MAAM,MAAM,MAAM,GAAG,SAAS,MAAM,MAAM;IAC1C,MAAM,SAAS,KAAK,MAAM,GAAG;IAC7B,IAAI,CAAC,MAAM,QAAQ,MAAM,GACvB,MAAM,IAAI,gBAAgB,gCAAgC,KAAK,qBAAqB;IAEtF,OAAO;GACT,SAAS,KAAK;IACZ,IAAK,IAA8B,SAAS,UAAU,OAAO,CAAC;IAC9D,MAAM;GACR;EACF;EACA,MAAM,KAAK,aAAa;GACtB,MAAM,KAAK,MAAM,OAAO;GACxB,MAAM,UAAU,MAAM,OAAO;GAC7B,MAAM,GAAG,MAAM,QAAQ,QAAQ,IAAI,GAAG,EAAE,WAAW,KAAK,CAAC;GACzD,MAAM,GAAG,UAAU,MAAM,KAAK,UAAU,aAAa,MAAM,CAAC,GAAG,MAAM;EACvE;CACF;AACF;;;;;;;;AA0BA,IAAa,oBAAb,MAA+B;CAC7B;CACA;CACA;CACA;CAEA,YAAY,UAAoC,CAAC,GAAG;EAClD,KAAK,QAAQ,QAAQ,SAAS,wBAAwB;EACtD,KAAK,mBAAmB,QAAQ,oBAAoB;EACpD,KAAK,aAAa,kBAAkB,QAAQ,UAAU;EACtD,KAAK,MAAM,QAAQ,OAAO,KAAK;CACjC;CAEA,MAAM,OAAO,OAAmD;EAC9D,MAAM,cAAc,MAAM,KAAK,MAAM,KAAK;EAC1C,IAAI,YAAY,MAAM,MAAM,EAAE,OAAO,MAAM,EAAE,GAC3C,MAAM,IAAI,gBAAgB,sCAAsC,MAAM,GAAG,iBAAiB;EAE5F,IAAI,MAAM,YAAY,CAAC,YAAY,MAAM,MAAM,EAAE,OAAO,MAAM,QAAQ,GACpE,MAAM,IAAI,gBACR,0CAA0C,MAAM,SAAS,YAC3D;EAEF,MAAM,aAAa,MAAM,cAAe,MAAM,KAAK,iBAAiB;EACpE,MAAM,aAAyB;GAC7B,IAAI,MAAM;GACV,OAAO,MAAM;GACb;GACA,UAAU,MAAM;GAChB,eAAe,MAAM;GACrB,MAAM,CAAC;GACP,OAAO,uBAAuB,CAAC,GAAG,KAAK,UAAU;GACjD,SAAS;GACT,WAAW,IAAI,KAAK,KAAK,IAAI,CAAC,CAAC,CAAC,YAAY;EAC9C;EACA,YAAY,KAAK,UAAU;EAC3B,MAAM,KAAK,MAAM,KAAK,WAAW;EACjC,OAAO,gBAAgB,UAAU;CACnC;;;CAIA,MAAM,OACJ,cACA,KACqB;EACrB,MAAM,cAAc,MAAM,KAAK,MAAM,KAAK;EAC1C,MAAM,MAAM,YAAY,MAAM,MAAM,EAAE,OAAO,YAAY;EACzD,IAAI,CAAC,KACH,MAAM,IAAI,gBAAgB,mCAAmC,aAAa,YAAY;EACxF,MAAM,UAAyB;GAC7B,KAAK,IAAI,OAAO,IAAI,KAAK;GACzB,OAAO,IAAI;GACX,QAAQ,IAAI;GACZ,SAAS,IAAI;GACb,WAAW,IAAI,aAAa,IAAI,KAAK,KAAK,IAAI,CAAC,CAAC,CAAC,YAAY;EAC/D;EACA,IAAI,KAAK,KAAK,OAAO;EACrB,IAAI,QAAQ,uBAAuB,IAAI,MAAM,KAAK,UAAU;EAC5D,MAAM,SAAS,IAAI,WAAW,YAAY,MAAM,MAAM,EAAE,OAAO,IAAI,QAAQ,IAAI,KAAA;EAC/E,IAAI,UAAU,mBAAmB,IAAI,OAAO,QAAQ,SAAS,MAAM,KAAK,UAAU,CAAC,CAAC;EACpF,MAAM,KAAK,MAAM,KAAK,WAAW;EACjC,OAAO,gBAAgB,GAAG;CAC5B;CAEA,MAAM,IAAI,cAAuD;EAE/D,MAAM,SAAQ,MADY,KAAK,MAAM,KAAK,EAAA,CAChB,MAAM,MAAM,EAAE,OAAO,YAAY;EAC3D,OAAO,QAAQ,gBAAgB,KAAK,IAAI,KAAA;CAC1C;CAEA,MAAM,OAA8B;EAClC,OAAO,KAAK,MAAM,KAAK;CACzB;;CAGA,MAAM,WAAW,cAAyD;EACxE,MAAM,cAAc,MAAM,KAAK,MAAM,KAAK;EAC1C,MAAM,MAAM,YAAY,MAAM,MAAM,EAAE,OAAO,YAAY;EACzD,IAAI,CAAC,KACH,MAAM,IAAI,gBAAgB,mCAAmC,aAAa,YAAY;EACxF,MAAM,SAAS,IAAI,WAAW,YAAY,MAAM,MAAM,EAAE,OAAO,IAAI,QAAQ,IAAI,KAAA;EAC/E,OAAO,mBAAmB,IAAI,OAAO,QAAQ,SAAS,MAAM,KAAK,UAAU;CAC7E;AACF"}

package/dist/experiment-tracker-DWHZBAYL.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"experiment-tracker-DWHZBAYL.d.ts","names":[],"sources":["../src/statistics/power-and-mde.ts","../src/statistics/random.ts","../src/experiment-tracker.ts"],"mappings":";;;;;;;iBAWgB,mBAAmB;EACjC;EACA;EACA;EACA;;;;;;;;;;;iBAsBc,yBAAyB;EACvC;EACA;EACA;EACA;;;;;;;;iBAkBc,UAAU;EACxB;EACA;EACA;EACA;;;;;;;;;;;;;;;;iBAyBc,iBAAiB;EAC/B;EACA;EACA;EACA;EACA;;;;;;;iBAyBc,aAAa;EAC3B;EACA;EACA;EACA;EACA;;;;;;;;iBCrHc,WAAW;;;;;;;;;;;;;;;;;;;;;;;;;;;;KCwBf;;UAGK;;EAEf;;EAEA;;EAEA;;;;UAKe;;EAEf;;EAEA;;EAEA;;EAEA;;EAEA,UAAU;;UAGK;EACf;EACA;EACA;EACA;;EAEA;;EAEA;;;EAGA;;EAEA;;EAEA;;UAGe;;EAEf;;EAEA;;EAEA,YAAY;;EAEZ;;EAEA;EACA,MAAM;EACN,OAAO;EACP,SAAS;;EAET;;UAGe;;EAEf;;EAEA;;EAEA;;EAEA;;;EAGA;;UAGe;EACf,SAAS;;EAET;;EAEA;;;;;;;iBAkDc,uBACd,MAAM,iBACN,aAAa,wBACZ;;;;;;;iBAgDa,mBACd,WAAW,iBACX,QAAQ,wBACR,aAAa,wBACZ;;;KA6CS,yBAAyB,uBAAuB,QAAQ;;;UAInD;EACf,QAAQ,QAAQ;EAChB,KAAK,aAAa,eAAe;;;;iBAoBnB,wBAAwB,UAAS,eAAoB;;iBAarD,oBAAoB,eAAe;UAyBlC;EACf,QAAQ;EACR,mBAAmB;EACnB,aAAa;;EAEb;;UAGe;EACf;EACA;EACA;EACA;;EAEA,aAAa;;;;;;;;;cAUF;mBACM;mBACA;mBACA;mBACA;EAEjB,YAAY,UAAS;EAOf,OAAO,OAAO,wBAAwB,QAAQ;;;EA6B9C,OACJ,sBACA,KAAK,KAAK;IAAwC;IAAc;MAC/D,QAAQ;EAoBL,IAAI,uBAAuB,QAAQ;EAMnC,QAAQ,QAAQ;;EAKhB,WAAW,uBAAuB,QAAQ"}

package/dist/index-BgHYx1QG.d.ts

@@ -1 +0,0 @@
-import "./capture-fetch-BZiO2cEH.js";