@tangle-network/agent-runtime 0.50.0 → 0.52.0

package/dist/chunk-G3RGMA7C.js

@@ -0,0 +1,361 @@
+// src/otel-export.ts
+var SCOPE = { name: "@tangle-network/agent-runtime", version: "0.33.0" };
+var GEN_AI = {
+  operation: "gen_ai.operation.name",
+  agentName: "gen_ai.agent.name",
+  conversationId: "gen_ai.conversation.id",
+  inputTokens: "gen_ai.usage.input_tokens",
+  outputTokens: "gen_ai.usage.output_tokens"
+};
+function createOtelExporter(config) {
+  const resolvedEndpoint = config?.endpoint ?? (typeof process !== "undefined" ? process.env.OTEL_EXPORTER_OTLP_ENDPOINT : void 0);
+  if (!resolvedEndpoint) return void 0;
+  const endpoint = resolvedEndpoint;
+  const headers = config?.headers ?? parseHeadersFromEnv();
+  const batchSize = config?.batchSize ?? 64;
+  const flushIntervalMs = config?.flushIntervalMs ?? 5e3;
+  const serviceName = config?.serviceName ?? "agent-runtime";
+  const resourceAttrs = config?.resourceAttributes ?? {};
+  const pending = [];
+  let timer;
+  let stopped = false;
+  const exporter = {
+    exportSpan(span) {
+      if (stopped) return;
+      pending.push(span);
+      if (pending.length >= batchSize) {
+        void doFlush();
+      }
+    },
+    async flush() {
+      await doFlush();
+    },
+    async shutdown() {
+      stopped = true;
+      if (timer !== void 0) {
+        clearInterval(timer);
+        timer = void 0;
+      }
+      await doFlush();
+    }
+  };
+  timer = setInterval(() => {
+    if (pending.length > 0) void doFlush();
+  }, flushIntervalMs);
+  if (typeof timer === "object" && "unref" in timer) {
+    ;
+    timer.unref();
+  }
+  async function doFlush() {
+    if (pending.length === 0) return;
+    const batch = pending.splice(0);
+    const body = {
+      resourceSpans: [
+        {
+          resource: {
+            attributes: toAttributes({
+              "service.name": serviceName,
+              ...resourceAttrs
+            })
+          },
+          scopeSpans: [{ scope: SCOPE, spans: batch }]
+        }
+      ]
+    };
+    const url = `${endpoint.replace(/\/+$/, "")}/v1/traces`;
+    try {
+      await fetch(url, {
+        method: "POST",
+        headers: { "content-type": "application/json", ...headers },
+        body: JSON.stringify(body)
+      });
+    } catch {
+    }
+  }
+  return exporter;
+}
+function loopEventToOtelSpan(event, traceId, parentSpanId) {
+  const spanId = generateSpanId();
+  const attrs = {
+    "loop.event_kind": event.kind,
+    "loop.run_id": event.runId
+  };
+  for (const [k, v] of Object.entries(event.payload)) {
+    if (typeof v === "string" || typeof v === "number" || typeof v === "boolean") {
+      attrs[`loop.${k}`] = v;
+    }
+  }
+  const ts = msToNs(event.timestamp);
+  return {
+    traceId: padTraceId(traceId),
+    spanId,
+    parentSpanId: parentSpanId ? padSpanId(parentSpanId) : void 0,
+    name: event.kind,
+    kind: 1,
+    startTimeUnixNano: ts,
+    endTimeUnixNano: ts,
+    attributes: toAttributes(attrs),
+    status: { code: 1 }
+  };
+}
+function buildLoopOtelSpans(events, traceId, rootParentSpanId) {
+  const tid = padTraceId(traceId);
+  return buildLoopSpanNodes(events).map((node) => ({
+    traceId: tid,
+    spanId: node.spanId,
+    parentSpanId: node.parentSpanId ? padSpanId(node.parentSpanId) : rootParentSpanId ? padSpanId(rootParentSpanId) : void 0,
+    name: node.name,
+    kind: 1,
+    startTimeUnixNano: msToNs(node.startMs),
+    endTimeUnixNano: msToNs(node.endMs),
+    attributes: toAttributes(node.attrs),
+    status: { code: node.error ? 2 : 1 }
+  }));
+}
+function buildLoopSpanNodes(events) {
+  if (events.length === 0) return [];
+  const out = [];
+  const num = (v) => typeof v === "number" && Number.isFinite(v) ? v : void 0;
+  const str = (v) => typeof v === "string" && v.length > 0 ? v : void 0;
+  const rec = (v) => v && typeof v === "object" ? v : {};
+  const started = events.find((e) => e.kind === "loop.started");
+  const ended = events.find((e) => e.kind === "loop.ended");
+  const runId = events[0]?.runId ?? "";
+  const rootStart = started?.timestamp ?? events[0].timestamp;
+  const rootEnd = ended?.timestamp ?? events[events.length - 1].timestamp;
+  const rootId = generateSpanId();
+  const make = (spanId, parentSpanId, name, kind, startMs, endMs, attrs, error = false) => ({
+    spanId,
+    parentSpanId,
+    name,
+    kind,
+    startMs,
+    endMs,
+    attrs,
+    error
+  });
+  const sp = rec(started?.payload);
+  const rootAttrs = {
+    [GEN_AI.operation]: "invoke_workflow",
+    [GEN_AI.conversationId]: runId,
+    "tangle.loop.driver": str(sp.driver) ?? "driver"
+  };
+  if (Array.isArray(sp.agentRunNames) && sp.agentRunNames.length > 0) {
+    rootAttrs["tangle.loop.agents"] = sp.agentRunNames.map(String).join(",");
+  }
+  if (ended) {
+    const ep = rec(ended.payload);
+    const win = num(ep.winnerIterationIndex);
+    if (win !== void 0) rootAttrs["tangle.loop.winner.iteration_index"] = win;
+    const cost = num(ep.totalCostUsd);
+    if (cost !== void 0) rootAttrs["tangle.cost.usd"] = cost;
+    const dur = num(ep.durationMs);
+    if (dur !== void 0) rootAttrs["tangle.loop.duration_ms"] = dur;
+    const iters = num(ep.iterations);
+    if (iters !== void 0) rootAttrs["tangle.loop.iterations"] = iters;
+  }
+  out.push(make(rootId, void 0, "loop", "loop", rootStart, rootEnd, rootAttrs));
+  const iterStartTs = /* @__PURE__ */ new Map();
+  const placementByIdx = /* @__PURE__ */ new Map();
+  let currentRoundId;
+  let pendingRound;
+  const flushRound = (endMs) => {
+    if (!pendingRound) return;
+    out.push(
+      make(
+        pendingRound.id,
+        rootId,
+        "loop.round",
+        "round",
+        pendingRound.start,
+        endMs,
+        pendingRound.attrs
+      )
+    );
+    pendingRound = void 0;
+  };
+  for (const e of events) {
+    const p = rec(e.payload);
+    switch (e.kind) {
+      case "loop.plan": {
+        flushRound(e.timestamp);
+        const id = generateSpanId();
+        const roundIdx = num(p.roundIndex) ?? 0;
+        const attrs = {
+          [GEN_AI.operation]: "invoke_workflow",
+          "tangle.loop.round.index": roundIdx,
+          "tangle.loop.move.kind": str(p.moveKind) ?? "unknown",
+          "tangle.loop.move.round": roundIdx,
+          "tangle.loop.move.width": num(p.plannedCount) ?? 0
+        };
+        const r = str(p.rationale);
+        if (r) attrs["tangle.loop.move.rationale"] = r;
+        const parent = num(p.parentIndex);
+        if (parent !== void 0) attrs["tangle.loop.move.parent_index"] = parent;
+        if (Array.isArray(p.childIndices) && p.childIndices.length > 0) {
+          attrs["tangle.loop.move.child_indices"] = p.childIndices.map(String).join(",");
+        }
+        pendingRound = { id, start: e.timestamp, attrs };
+        currentRoundId = id;
+        break;
+      }
+      case "loop.iteration.started": {
+        const idx = num(p.iterationIndex);
+        if (idx !== void 0) iterStartTs.set(idx, e.timestamp);
+        break;
+      }
+      case "loop.iteration.dispatch": {
+        const idx = num(p.iterationIndex);
+        if (idx === void 0) break;
+        const place = {};
+        const kind = str(p.placement);
+        if (kind) place["tangle.loop.placement.kind"] = kind;
+        const sid = str(p.sandboxId);
+        if (sid) place["tangle.sandbox.id"] = sid;
+        const fid = str(p.fleetId);
+        if (fid) place["tangle.fleet.id"] = fid;
+        const mid = str(p.machineId);
+        if (mid) place["tangle.machine.id"] = mid;
+        placementByIdx.set(idx, place);
+        break;
+      }
+      case "loop.iteration.ended": {
+        const idx = num(p.iterationIndex) ?? 0;
+        const start = iterStartTs.get(idx) ?? e.timestamp;
+        const err = str(p.error);
+        const attrs = {
+          [GEN_AI.operation]: "invoke_agent",
+          "tangle.loop.iteration.index": idx
+        };
+        const agent = str(p.agentRunName);
+        if (agent) attrs[GEN_AI.agentName] = agent;
+        const tu = rec(p.tokenUsage);
+        const inTok = num(tu.input);
+        if (inTok !== void 0) attrs[GEN_AI.inputTokens] = inTok;
+        const outTok = num(tu.output);
+        if (outTok !== void 0) attrs[GEN_AI.outputTokens] = outTok;
+        const cost = num(p.costUsd);
+        if (cost !== void 0) attrs["tangle.cost.usd"] = cost;
+        const verdict = rec(p.verdict);
+        if (typeof verdict.valid === "boolean") attrs["tangle.loop.verdict.valid"] = verdict.valid;
+        const score = num(verdict.score);
+        if (score !== void 0) attrs["tangle.loop.verdict.score"] = score;
+        if (err) attrs["tangle.loop.error"] = err;
+        const gid = num(p.groupId);
+        if (gid !== void 0) attrs["tangle.loop.iteration.group_id"] = gid;
+        const par = num(p.parentIndex);
+        if (par !== void 0) attrs["tangle.loop.iteration.parent_index"] = par;
+        const dur = num(p.durationMs);
+        if (dur !== void 0) attrs["tangle.loop.iteration.duration_ms"] = dur;
+        const preview = str(p.outputPreview);
+        if (preview) attrs["tangle.loop.iteration.output_preview"] = preview;
+        Object.assign(attrs, placementByIdx.get(idx) ?? {});
+        out.push(
+          make(
+            generateSpanId(),
+            currentRoundId ?? rootId,
+            "loop.iteration",
+            "branch",
+            start,
+            e.timestamp,
+            attrs,
+            err !== void 0
+          )
+        );
+        break;
+      }
+      case "loop.decision": {
+        if (pendingRound) {
+          const dec = str(p.decision);
+          if (dec) pendingRound.attrs["tangle.loop.decision"] = dec;
+          flushRound(e.timestamp);
+        }
+        currentRoundId = void 0;
+        break;
+      }
+    }
+  }
+  flushRound(rootEnd);
+  return out;
+}
+function parseHeadersFromEnv() {
+  if (typeof process === "undefined") return {};
+  const raw = process.env.OTEL_EXPORTER_OTLP_HEADERS;
+  if (!raw) return {};
+  const out = {};
+  for (const pair of raw.split(",")) {
+    const eq = pair.indexOf("=");
+    if (eq < 0) continue;
+    const key = pair.slice(0, eq).trim();
+    const value = pair.slice(eq + 1).trim();
+    if (key) out[key] = value;
+  }
+  return out;
+}
+function toAttributes(record) {
+  return Object.entries(record).map(([key, value]) => ({
+    key,
+    value: typeof value === "number" ? Number.isInteger(value) ? { intValue: value.toString() } : { doubleValue: value } : typeof value === "boolean" ? { boolValue: value } : { stringValue: value }
+  }));
+}
+function msToNs(ms) {
+  return (BigInt(Math.floor(ms)) * 1000000n).toString();
+}
+function padSpanId(id) {
+  const cleaned = id.replace(/-/g, "");
+  return cleaned.slice(0, 16).padEnd(16, "0");
+}
+function padTraceId(id) {
+  const cleaned = id.replace(/-/g, "");
+  return cleaned.slice(0, 32).padEnd(32, "0");
+}
+function generateSpanId() {
+  const bytes = new Uint8Array(8);
+  if (typeof globalThis.crypto?.getRandomValues === "function") {
+    globalThis.crypto.getRandomValues(bytes);
+  } else {
+    for (let i = 0; i < 8; i++) bytes[i] = Math.floor(Math.random() * 256);
+  }
+  return Array.from(bytes).map((b) => b.toString(16).padStart(2, "0")).join("");
+}
+var INTELLIGENCE_WIRE_VERSION = "2026-05-26.v1";
+var DEFAULT_INTELLIGENCE_BASE = "https://intelligence.tangle.tools";
+async function exportEvalRuns(events, config) {
+  if (events.length === 0) return { ok: true, status: 0, accepted: 0, rejected: [] };
+  const apiKey = config?.apiKey ?? (typeof process !== "undefined" ? process.env.TANGLE_API_KEY : void 0);
+  if (!apiKey)
+    throw new Error("exportEvalRuns: apiKey required (pass config.apiKey or set TANGLE_API_KEY)");
+  const base = config?.base ?? (typeof process !== "undefined" ? process.env.INTELLIGENCE_BASE : void 0) ?? DEFAULT_INTELLIGENCE_BASE;
+  const url = `${base.replace(/\/+$/, "")}/v1/ingest/eval-runs`;
+  const res = await fetch(url, {
+    method: "POST",
+    headers: {
+      "content-type": "application/json",
+      authorization: `Bearer ${apiKey}`,
+      "X-Tangle-Wire-Version": INTELLIGENCE_WIRE_VERSION,
+      ...config?.idempotencyKey ? { "Idempotency-Key": config.idempotencyKey } : {}
+    },
+    body: JSON.stringify({ wireVersion: INTELLIGENCE_WIRE_VERSION, events })
+  });
+  let parsed = {};
+  try {
+    parsed = await res.json();
+  } catch {
+  }
+  return {
+    ok: res.ok,
+    status: res.status,
+    accepted: parsed.accepted ?? (res.ok ? events.length : 0),
+    rejected: parsed.rejected ?? []
+  };
+}
+
+export {
+  createOtelExporter,
+  loopEventToOtelSpan,
+  buildLoopOtelSpans,
+  buildLoopSpanNodes,
+  INTELLIGENCE_WIRE_VERSION,
+  exportEvalRuns
+};
+//# sourceMappingURL=chunk-G3RGMA7C.js.map

package/dist/chunk-G3RGMA7C.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/otel-export.ts"],"sourcesContent":["/**\n * OTEL span exporter — streams LoopTraceEvents to an OTLP/HTTP collector.\n *\n * Reads OTEL_EXPORTER_OTLP_ENDPOINT + OTEL_EXPORTER_OTLP_HEADERS from env\n * when no explicit config is given. Keeps the runtime dep-free from\n * @opentelemetry/sdk-trace-base — minimal OTLP/JSON serializer.\n *\n * The exporter accepts both raw OtelSpan objects and LoopTraceEvents\n * (which get converted to OTLP spans automatically).\n */\n\nexport interface OtelExportConfig {\n  /** OTLP endpoint. Reads OTEL_EXPORTER_OTLP_ENDPOINT env by default. */\n  endpoint?: string\n  /** OTLP headers. Reads OTEL_EXPORTER_OTLP_HEADERS env by default. */\n  headers?: Record<string, string>\n  /** Batch size before flush. Default 64. */\n  batchSize?: number\n  /** Flush interval ms. Default 5000. */\n  flushIntervalMs?: number\n  /** Resource attributes stamped on every export. */\n  resourceAttributes?: Record<string, string | number | boolean>\n  /** Service name. Default 'agent-runtime'. */\n  serviceName?: string\n}\n\nexport interface OtelExporter {\n  /** Export a span. */\n  exportSpan(span: OtelSpan): void\n  /** Force flush pending spans. */\n  flush(): Promise<void>\n  /** Shutdown cleanly. */\n  shutdown(): Promise<void>\n}\n\nexport interface OtelSpan {\n  traceId: string\n  spanId: string\n  parentSpanId?: string\n  name: string\n  kind?: number\n  startTimeUnixNano: string\n  endTimeUnixNano: string\n  attributes?: OtelAttribute[]\n  status?: { code: number; message?: string }\n}\n\nexport interface OtelAttribute {\n  key: string\n  value: { stringValue?: string; intValue?: string; doubleValue?: number; boolValue?: boolean }\n}\n\ninterface OtlpResourceSpans {\n  resource: { attributes: OtelAttribute[] }\n  scopeSpans: Array<{ scope: { name: string; version: string }; spans: OtelSpan[] }>\n}\n\ninterface OtlpExport {\n  resourceSpans: OtlpResourceSpans[]\n}\n\nconst SCOPE = { name: '@tangle-network/agent-runtime', version: '0.33.0' }\n\n/**\n * Current (non-deprecated) OpenTelemetry GenAI semantic-convention keys.\n * Registry: https://opentelemetry.io/docs/specs/semconv/registry/attributes/gen-ai/\n * NB: `gen_ai.system` / `gen_ai.usage.prompt_tokens` / `completion_tokens` are\n * DEPRECATED — do not emit them. We use `provider.name` + `input/output_tokens`.\n */\nconst GEN_AI = {\n  operation: 'gen_ai.operation.name',\n  agentName: 'gen_ai.agent.name',\n  conversationId: 'gen_ai.conversation.id',\n  inputTokens: 'gen_ai.usage.input_tokens',\n  outputTokens: 'gen_ai.usage.output_tokens',\n} as const\n\n/**\n * Create an OTEL exporter. Returns undefined when no endpoint is configured.\n */\nexport function createOtelExporter(config?: OtelExportConfig): OtelExporter | undefined {\n  const resolvedEndpoint =\n    config?.endpoint ??\n    (typeof process !== 'undefined' ? process.env.OTEL_EXPORTER_OTLP_ENDPOINT : undefined)\n  if (!resolvedEndpoint) return undefined\n  const endpoint: string = resolvedEndpoint\n\n  const headers = config?.headers ?? parseHeadersFromEnv()\n  const batchSize = config?.batchSize ?? 64\n  const flushIntervalMs = config?.flushIntervalMs ?? 5000\n  const serviceName = config?.serviceName ?? 'agent-runtime'\n  const resourceAttrs = config?.resourceAttributes ?? {}\n\n  const pending: OtelSpan[] = []\n  let timer: ReturnType<typeof setInterval> | undefined\n  let stopped = false\n\n  const exporter: OtelExporter = {\n    exportSpan(span: OtelSpan): void {\n      if (stopped) return\n      pending.push(span)\n      if (pending.length >= batchSize) {\n        void doFlush()\n      }\n    },\n\n    async flush(): Promise<void> {\n      await doFlush()\n    },\n\n    async shutdown(): Promise<void> {\n      stopped = true\n      if (timer !== undefined) {\n        clearInterval(timer)\n        timer = undefined\n      }\n      await doFlush()\n    },\n  }\n\n  timer = setInterval(() => {\n    if (pending.length > 0) void doFlush()\n  }, flushIntervalMs)\n  if (typeof timer === 'object' && 'unref' in timer) {\n    ;(timer as NodeJS.Timeout).unref()\n  }\n\n  async function doFlush(): Promise<void> {\n    if (pending.length === 0) return\n    const batch = pending.splice(0)\n    const body: OtlpExport = {\n      resourceSpans: [\n        {\n          resource: {\n            attributes: toAttributes({\n              'service.name': serviceName,\n              ...resourceAttrs,\n            }),\n          },\n          scopeSpans: [{ scope: SCOPE, spans: batch }],\n        },\n      ],\n    }\n    const url = `${endpoint.replace(/\\/+$/, '')}/v1/traces`\n    try {\n      await fetch(url, {\n        method: 'POST',\n        headers: { 'content-type': 'application/json', ...headers },\n        body: JSON.stringify(body),\n      })\n    } catch {\n      // Best-effort — telemetry export must not crash the runtime.\n    }\n  }\n\n  return exporter\n}\n\n/**\n * Convert a LoopTraceEvent into an OtelSpan for export.\n */\nexport function loopEventToOtelSpan(\n  event: {\n    kind: string\n    runId: string\n    timestamp: number\n    payload: object\n  },\n  traceId: string,\n  parentSpanId?: string,\n): OtelSpan {\n  const spanId = generateSpanId()\n  const attrs: Record<string, string | number | boolean> = {\n    'loop.event_kind': event.kind,\n    'loop.run_id': event.runId,\n  }\n  for (const [k, v] of Object.entries(event.payload)) {\n    if (typeof v === 'string' || typeof v === 'number' || typeof v === 'boolean') {\n      attrs[`loop.${k}`] = v\n    }\n  }\n  const ts = msToNs(event.timestamp)\n  return {\n    traceId: padTraceId(traceId),\n    spanId,\n    parentSpanId: parentSpanId ? padSpanId(parentSpanId) : undefined,\n    name: event.kind,\n    kind: 1,\n    startTimeUnixNano: ts,\n    endTimeUnixNano: ts,\n    attributes: toAttributes(attrs),\n    status: { code: 1 },\n  }\n}\n\n/**\n * Sink-neutral node in a reconstructed loop span tree. The root node's\n * `parentSpanId` is `undefined` — sinks decide how to parent it (the OTEL\n * mapper attaches the inherited delegation span; the delegation journal\n * leaves it as the tree root).\n */\nexport interface LoopSpanNode {\n  spanId: string\n  parentSpanId?: string\n  /** `'loop'` | `'loop.round'` | `'loop.iteration'`. */\n  name: string\n  /** Topology level: loop root, plan round, or iteration branch. */\n  kind: 'loop' | 'round' | 'branch'\n  startMs: number\n  endMs: number\n  attrs: Record<string, string | number | boolean>\n  /** True when the iteration carried an error — maps to OTEL status code 2. */\n  error: boolean\n}\n\n/**\n * Build a nested, real-duration OTLP span tree for ONE loop run from its full\n * ordered `LoopTraceEvent` stream. Unlike `loopEventToOtelSpan` (one flat,\n * zero-duration span per event), this reconstructs the topology hierarchy a\n * GenAI trace viewer renders natively:\n *\n *   loop (invoke_workflow)\n *     └─ loop.round[k] (invoke_workflow)   ← tangle.loop.move.{kind,width,rationale}\n *          ├─ loop.iteration[i] (invoke_agent)  ← gen_ai.agent.name + usage + verdict + placement\n *          └─ …\n *\n * Attributes follow the current GenAI semconv (`gen_ai.*`) where they apply and\n * a namespaced `tangle.loop.*` / `tangle.cost.usd` extension for topology /\n * verdict / placement / cost (not yet standardized). Pure: feed it a buffered\n * per-runId event array (e.g. flushed on `loop.ended`) and export the result.\n */\nexport function buildLoopOtelSpans(\n  events: ReadonlyArray<{ kind: string; runId: string; timestamp: number; payload: object }>,\n  traceId: string,\n  rootParentSpanId?: string,\n): OtelSpan[] {\n  const tid = padTraceId(traceId)\n  return buildLoopSpanNodes(events).map((node) => ({\n    traceId: tid,\n    spanId: node.spanId,\n    parentSpanId: node.parentSpanId\n      ? padSpanId(node.parentSpanId)\n      : rootParentSpanId\n        ? padSpanId(rootParentSpanId)\n        : undefined,\n    name: node.name,\n    kind: 1,\n    startTimeUnixNano: msToNs(node.startMs),\n    endTimeUnixNano: msToNs(node.endMs),\n    attributes: toAttributes(node.attrs),\n    status: { code: node.error ? 2 : 1 },\n  }))\n}\n\n/**\n * Sink-neutral core behind {@link buildLoopOtelSpans}: reconstruct the\n * loop → round → branch span tree from one run's ordered `LoopTraceEvent`\n * stream. Consumed by the OTEL mapper above and by the MCP delegation\n * journal's compact trace tee — one topology reconstruction, two sinks.\n * Tolerates partial streams (a run that never reached `loop.ended` closes\n * at the last observed event's timestamp).\n */\nexport function buildLoopSpanNodes(\n  events: ReadonlyArray<{ kind: string; runId: string; timestamp: number; payload: object }>,\n): LoopSpanNode[] {\n  if (events.length === 0) return []\n  const out: LoopSpanNode[] = []\n  const num = (v: unknown): number | undefined =>\n    typeof v === 'number' && Number.isFinite(v) ? v : undefined\n  const str = (v: unknown): string | undefined =>\n    typeof v === 'string' && v.length > 0 ? v : undefined\n  const rec = (v: unknown): Record<string, unknown> =>\n    v && typeof v === 'object' ? (v as Record<string, unknown>) : {}\n\n  const started = events.find((e) => e.kind === 'loop.started')\n  const ended = events.find((e) => e.kind === 'loop.ended')\n  const runId = events[0]?.runId ?? ''\n  const rootStart = started?.timestamp ?? events[0]!.timestamp\n  const rootEnd = ended?.timestamp ?? events[events.length - 1]!.timestamp\n  const rootId = generateSpanId()\n\n  const make = (\n    spanId: string,\n    parentSpanId: string | undefined,\n    name: string,\n    kind: LoopSpanNode['kind'],\n    startMs: number,\n    endMs: number,\n    attrs: Record<string, string | number | boolean>,\n    error = false,\n  ): LoopSpanNode => ({\n    spanId,\n    parentSpanId,\n    name,\n    kind,\n    startMs,\n    endMs,\n    attrs,\n    error,\n  })\n\n  // root\n  const sp = rec(started?.payload)\n  const rootAttrs: Record<string, string | number | boolean> = {\n    [GEN_AI.operation]: 'invoke_workflow',\n    [GEN_AI.conversationId]: runId,\n    'tangle.loop.driver': str(sp.driver) ?? 'driver',\n  }\n  if (Array.isArray(sp.agentRunNames) && sp.agentRunNames.length > 0) {\n    rootAttrs['tangle.loop.agents'] = sp.agentRunNames.map(String).join(',')\n  }\n  if (ended) {\n    const ep = rec(ended.payload)\n    const win = num(ep.winnerIterationIndex)\n    if (win !== undefined) rootAttrs['tangle.loop.winner.iteration_index'] = win\n    const cost = num(ep.totalCostUsd)\n    if (cost !== undefined) rootAttrs['tangle.cost.usd'] = cost\n    const dur = num(ep.durationMs)\n    if (dur !== undefined) rootAttrs['tangle.loop.duration_ms'] = dur\n    const iters = num(ep.iterations)\n    if (iters !== undefined) rootAttrs['tangle.loop.iterations'] = iters\n  }\n  out.push(make(rootId, undefined, 'loop', 'loop', rootStart, rootEnd, rootAttrs))\n\n  // rounds + iterations\n  const iterStartTs = new Map<number, number>()\n  const placementByIdx = new Map<number, Record<string, string>>()\n  let currentRoundId: string | undefined\n  let pendingRound:\n    | { id: string; start: number; attrs: Record<string, string | number | boolean> }\n    | undefined\n  const flushRound = (endMs: number) => {\n    if (!pendingRound) return\n    out.push(\n      make(\n        pendingRound.id,\n        rootId,\n        'loop.round',\n        'round',\n        pendingRound.start,\n        endMs,\n        pendingRound.attrs,\n      ),\n    )\n    pendingRound = undefined\n  }\n\n  for (const e of events) {\n    const p = rec(e.payload)\n    switch (e.kind) {\n      case 'loop.plan': {\n        flushRound(e.timestamp)\n        const id = generateSpanId()\n        const roundIdx = num(p.roundIndex) ?? 0\n        const attrs: Record<string, string | number | boolean> = {\n          [GEN_AI.operation]: 'invoke_workflow',\n          'tangle.loop.round.index': roundIdx,\n          'tangle.loop.move.kind': str(p.moveKind) ?? 'unknown',\n          'tangle.loop.move.round': roundIdx,\n          'tangle.loop.move.width': num(p.plannedCount) ?? 0,\n        }\n        const r = str(p.rationale)\n        if (r) attrs['tangle.loop.move.rationale'] = r\n        const parent = num(p.parentIndex)\n        if (parent !== undefined) attrs['tangle.loop.move.parent_index'] = parent\n        if (Array.isArray(p.childIndices) && p.childIndices.length > 0) {\n          attrs['tangle.loop.move.child_indices'] = p.childIndices.map(String).join(',')\n        }\n        pendingRound = { id, start: e.timestamp, attrs }\n        currentRoundId = id\n        break\n      }\n      case 'loop.iteration.started': {\n        const idx = num(p.iterationIndex)\n        if (idx !== undefined) iterStartTs.set(idx, e.timestamp)\n        break\n      }\n      case 'loop.iteration.dispatch': {\n        const idx = num(p.iterationIndex)\n        if (idx === undefined) break\n        const place: Record<string, string> = {}\n        const kind = str(p.placement)\n        if (kind) place['tangle.loop.placement.kind'] = kind\n        const sid = str(p.sandboxId)\n        if (sid) place['tangle.sandbox.id'] = sid\n        const fid = str(p.fleetId)\n        if (fid) place['tangle.fleet.id'] = fid\n        const mid = str(p.machineId)\n        if (mid) place['tangle.machine.id'] = mid\n        placementByIdx.set(idx, place)\n        break\n      }\n      case 'loop.iteration.ended': {\n        const idx = num(p.iterationIndex) ?? 0\n        const start = iterStartTs.get(idx) ?? e.timestamp\n        const err = str(p.error)\n        const attrs: Record<string, string | number | boolean> = {\n          [GEN_AI.operation]: 'invoke_agent',\n          'tangle.loop.iteration.index': idx,\n        }\n        const agent = str(p.agentRunName)\n        if (agent) attrs[GEN_AI.agentName] = agent\n        const tu = rec(p.tokenUsage)\n        const inTok = num(tu.input)\n        if (inTok !== undefined) attrs[GEN_AI.inputTokens] = inTok\n        const outTok = num(tu.output)\n        if (outTok !== undefined) attrs[GEN_AI.outputTokens] = outTok\n        const cost = num(p.costUsd)\n        if (cost !== undefined) attrs['tangle.cost.usd'] = cost\n        const verdict = rec(p.verdict)\n        if (typeof verdict.valid === 'boolean') attrs['tangle.loop.verdict.valid'] = verdict.valid\n        const score = num(verdict.score)\n        if (score !== undefined) attrs['tangle.loop.verdict.score'] = score\n        if (err) attrs['tangle.loop.error'] = err\n        const gid = num(p.groupId)\n        if (gid !== undefined) attrs['tangle.loop.iteration.group_id'] = gid\n        const par = num(p.parentIndex)\n        if (par !== undefined) attrs['tangle.loop.iteration.parent_index'] = par\n        const dur = num(p.durationMs)\n        if (dur !== undefined) attrs['tangle.loop.iteration.duration_ms'] = dur\n        const preview = str(p.outputPreview)\n        if (preview) attrs['tangle.loop.iteration.output_preview'] = preview\n        Object.assign(attrs, placementByIdx.get(idx) ?? {})\n        out.push(\n          make(\n            generateSpanId(),\n            currentRoundId ?? rootId,\n            'loop.iteration',\n            'branch',\n            start,\n            e.timestamp,\n            attrs,\n            err !== undefined,\n          ),\n        )\n        break\n      }\n      case 'loop.decision': {\n        if (pendingRound) {\n          const dec = str(p.decision)\n          if (dec) pendingRound.attrs['tangle.loop.decision'] = dec\n          flushRound(e.timestamp)\n        }\n        currentRoundId = undefined\n        break\n      }\n    }\n  }\n  flushRound(rootEnd)\n  return out\n}\n\nfunction parseHeadersFromEnv(): Record<string, string> {\n  if (typeof process === 'undefined') return {}\n  const raw = process.env.OTEL_EXPORTER_OTLP_HEADERS\n  if (!raw) return {}\n  const out: Record<string, string> = {}\n  for (const pair of raw.split(',')) {\n    const eq = pair.indexOf('=')\n    if (eq < 0) continue\n    const key = pair.slice(0, eq).trim()\n    const value = pair.slice(eq + 1).trim()\n    if (key) out[key] = value\n  }\n  return out\n}\n\nfunction toAttributes(record: Record<string, string | number | boolean>): OtelAttribute[] {\n  return Object.entries(record).map(([key, value]) => ({\n    key,\n    value:\n      typeof value === 'number'\n        ? Number.isInteger(value)\n          ? { intValue: value.toString() }\n          : { doubleValue: value }\n        : typeof value === 'boolean'\n          ? { boolValue: value }\n          : { stringValue: value },\n  }))\n}\n\nfunction msToNs(ms: number): string {\n  return (BigInt(Math.floor(ms)) * 1_000_000n).toString()\n}\n\nfunction padSpanId(id: string): string {\n  const cleaned = id.replace(/-/g, '')\n  return cleaned.slice(0, 16).padEnd(16, '0')\n}\n\nfunction padTraceId(id: string): string {\n  const cleaned = id.replace(/-/g, '')\n  return cleaned.slice(0, 32).padEnd(32, '0')\n}\n\nfunction generateSpanId(): string {\n  const bytes = new Uint8Array(8)\n  if (typeof globalThis.crypto?.getRandomValues === 'function') {\n    globalThis.crypto.getRandomValues(bytes)\n  } else {\n    for (let i = 0; i < 8; i++) bytes[i] = Math.floor(Math.random() * 256)\n  }\n  return Array.from(bytes)\n    .map((b) => b.toString(16).padStart(2, '0'))\n    .join('')\n}\n\n// ─── Eval-run ingest (self-improvement provenance) ───────────────────────────\n//\n// Tangle Intelligence has a first-class, non-trace record for self-improvement\n// runs: POST /v1/ingest/eval-runs (\"Mode D\"). Each generation carries a\n// `surfaceHash` (the proposed-change identity) + arbitrary `surface` provenance;\n// a later `gate-decided` event re-emits the same `runId` (idempotent upsert) with\n// a real `gateDecision` + `holdoutLift`, so proposal→verdict is one diffable\n// record. This is how a consumer's RSI loop records WHAT it changed, WHY, from\n// which evidence — the audit trail behind agentic self-improvement.\n\n/** Wire version the eval-runs ingest enforces (X-Tangle-Wire-Version + body). */\nexport const INTELLIGENCE_WIRE_VERSION = '2026-05-26.v1'\n\nexport interface EvalRunGeneration {\n  /** 0-based ordinal of this generation within the run (required by ingest). */\n  index: number\n  /** Identity of the proposed surface change (content-addressed hash). */\n  surfaceHash: string\n  /** Arbitrary provenance for this generation (rationale, evidence, source). */\n  surface?: unknown\n  /** Per-scenario results; empty until the generation is measured. */\n  cells?: unknown[]\n  /** Mean composite score (0 when unmeasured — pair with labels.measured). */\n  compositeMean: number\n  costUsd: number\n  durationMs: number\n}\n\nexport interface EvalRunEvent {\n  runId: string\n  runDir: string\n  /** ISO timestamp. */\n  timestamp: string\n  status:\n    | 'started'\n    | 'baseline-complete'\n    | 'generation-complete'\n    | 'gate-decided'\n    | 'finished'\n    | 'errored'\n  labels?: Record<string, string>\n  baseline?: EvalRunGeneration\n  generations?: EvalRunGeneration[]\n  gateDecision?: 'ship' | 'hold' | 'need_more_work' | 'model_ceiling' | 'arch_ceiling'\n  holdoutLift?: number\n  totalCostUsd: number\n  totalDurationMs: number\n  errorMessage?: string\n}\n\nexport interface EvalRunsExportConfig {\n  /** Bearer key — tenant is resolved server-side from it. Reads TANGLE_API_KEY. */\n  apiKey?: string\n  /** Intelligence base. Reads INTELLIGENCE_BASE env, else prod. */\n  base?: string\n  /** Idempotency-Key header (e.g. the runId) — safe retries + upsert. */\n  idempotencyKey?: string\n}\n\nexport interface EvalRunsExportResult {\n  ok: boolean\n  status: number\n  accepted: number\n  rejected: Array<{ index: number; reason: string }>\n}\n\nconst DEFAULT_INTELLIGENCE_BASE = 'https://intelligence.tangle.tools'\n\n/**\n * Ship self-improvement eval-run events to Tangle Intelligence. Unlike the\n * best-effort span exporter, this RESOLVES with the ingest verdict (accepted /\n * rejected per event) so a consumer's loop can assert its provenance landed.\n * Throws only on a missing key or network failure.\n */\nexport async function exportEvalRuns(\n  events: EvalRunEvent[],\n  config?: EvalRunsExportConfig,\n): Promise<EvalRunsExportResult> {\n  if (events.length === 0) return { ok: true, status: 0, accepted: 0, rejected: [] }\n  const apiKey =\n    config?.apiKey ?? (typeof process !== 'undefined' ? process.env.TANGLE_API_KEY : undefined)\n  if (!apiKey)\n    throw new Error('exportEvalRuns: apiKey required (pass config.apiKey or set TANGLE_API_KEY)')\n  const base =\n    config?.base ??\n    (typeof process !== 'undefined' ? process.env.INTELLIGENCE_BASE : undefined) ??\n    DEFAULT_INTELLIGENCE_BASE\n  const url = `${base.replace(/\\/+$/, '')}/v1/ingest/eval-runs`\n  const res = await fetch(url, {\n    method: 'POST',\n    headers: {\n      'content-type': 'application/json',\n      authorization: `Bearer ${apiKey}`,\n      'X-Tangle-Wire-Version': INTELLIGENCE_WIRE_VERSION,\n      ...(config?.idempotencyKey ? { 'Idempotency-Key': config.idempotencyKey } : {}),\n    },\n    body: JSON.stringify({ wireVersion: INTELLIGENCE_WIRE_VERSION, events }),\n  })\n  let parsed: { accepted?: number; rejected?: Array<{ index: number; reason: string }> } = {}\n  try {\n    parsed = (await res.json()) as typeof parsed\n  } catch {\n    // non-JSON body (e.g. 5xx HTML) — leave parsed empty\n  }\n  return {\n    ok: res.ok,\n    status: res.status,\n    accepted: parsed.accepted ?? (res.ok ? events.length : 0),\n    rejected: parsed.rejected ?? [],\n  }\n}\n"],"mappings":";AA6DA,IAAM,QAAQ,EAAE,MAAM,iCAAiC,SAAS,SAAS;AAQzE,IAAM,SAAS;AAAA,EACb,WAAW;AAAA,EACX,WAAW;AAAA,EACX,gBAAgB;AAAA,EAChB,aAAa;AAAA,EACb,cAAc;AAChB;AAKO,SAAS,mBAAmB,QAAqD;AACtF,QAAM,mBACJ,QAAQ,aACP,OAAO,YAAY,cAAc,QAAQ,IAAI,8BAA8B;AAC9E,MAAI,CAAC,iBAAkB,QAAO;AAC9B,QAAM,WAAmB;AAEzB,QAAM,UAAU,QAAQ,WAAW,oBAAoB;AACvD,QAAM,YAAY,QAAQ,aAAa;AACvC,QAAM,kBAAkB,QAAQ,mBAAmB;AACnD,QAAM,cAAc,QAAQ,eAAe;AAC3C,QAAM,gBAAgB,QAAQ,sBAAsB,CAAC;AAErD,QAAM,UAAsB,CAAC;AAC7B,MAAI;AACJ,MAAI,UAAU;AAEd,QAAM,WAAyB;AAAA,IAC7B,WAAW,MAAsB;AAC/B,UAAI,QAAS;AACb,cAAQ,KAAK,IAAI;AACjB,UAAI,QAAQ,UAAU,WAAW;AAC/B,aAAK,QAAQ;AAAA,MACf;AAAA,IACF;AAAA,IAEA,MAAM,QAAuB;AAC3B,YAAM,QAAQ;AAAA,IAChB;AAAA,IAEA,MAAM,WAA0B;AAC9B,gBAAU;AACV,UAAI,UAAU,QAAW;AACvB,sBAAc,KAAK;AACnB,gBAAQ;AAAA,MACV;AACA,YAAM,QAAQ;AAAA,IAChB;AAAA,EACF;AAEA,UAAQ,YAAY,MAAM;AACxB,QAAI,QAAQ,SAAS,EAAG,MAAK,QAAQ;AAAA,EACvC,GAAG,eAAe;AAClB,MAAI,OAAO,UAAU,YAAY,WAAW,OAAO;AACjD;AAAC,IAAC,MAAyB,MAAM;AAAA,EACnC;AAEA,iBAAe,UAAyB;AACtC,QAAI,QAAQ,WAAW,EAAG;AAC1B,UAAM,QAAQ,QAAQ,OAAO,CAAC;AAC9B,UAAM,OAAmB;AAAA,MACvB,eAAe;AAAA,QACb;AAAA,UACE,UAAU;AAAA,YACR,YAAY,aAAa;AAAA,cACvB,gBAAgB;AAAA,cAChB,GAAG;AAAA,YACL,CAAC;AAAA,UACH;AAAA,UACA,YAAY,CAAC,EAAE,OAAO,OAAO,OAAO,MAAM,CAAC;AAAA,QAC7C;AAAA,MACF;AAAA,IACF;AACA,UAAM,MAAM,GAAG,SAAS,QAAQ,QAAQ,EAAE,CAAC;AAC3C,QAAI;AACF,YAAM,MAAM,KAAK;AAAA,QACf,QAAQ;AAAA,QACR,SAAS,EAAE,gBAAgB,oBAAoB,GAAG,QAAQ;AAAA,QAC1D,MAAM,KAAK,UAAU,IAAI;AAAA,MAC3B,CAAC;AAAA,IACH,QAAQ;AAAA,IAER;AAAA,EACF;AAEA,SAAO;AACT;AAKO,SAAS,oBACd,OAMA,SACA,cACU;AACV,QAAM,SAAS,eAAe;AAC9B,QAAM,QAAmD;AAAA,IACvD,mBAAmB,MAAM;AAAA,IACzB,eAAe,MAAM;AAAA,EACvB;AACA,aAAW,CAAC,GAAG,CAAC,KAAK,OAAO,QAAQ,MAAM,OAAO,GAAG;AAClD,QAAI,OAAO,MAAM,YAAY,OAAO,MAAM,YAAY,OAAO,MAAM,WAAW;AAC5E,YAAM,QAAQ,CAAC,EAAE,IAAI;AAAA,IACvB;AAAA,EACF;AACA,QAAM,KAAK,OAAO,MAAM,SAAS;AACjC,SAAO;AAAA,IACL,SAAS,WAAW,OAAO;AAAA,IAC3B;AAAA,IACA,cAAc,eAAe,UAAU,YAAY,IAAI;AAAA,IACvD,MAAM,MAAM;AAAA,IACZ,MAAM;AAAA,IACN,mBAAmB;AAAA,IACnB,iBAAiB;AAAA,IACjB,YAAY,aAAa,KAAK;AAAA,IAC9B,QAAQ,EAAE,MAAM,EAAE;AAAA,EACpB;AACF;AAsCO,SAAS,mBACd,QACA,SACA,kBACY;AACZ,QAAM,MAAM,WAAW,OAAO;AAC9B,SAAO,mBAAmB,MAAM,EAAE,IAAI,CAAC,UAAU;AAAA,IAC/C,SAAS;AAAA,IACT,QAAQ,KAAK;AAAA,IACb,cAAc,KAAK,eACf,UAAU,KAAK,YAAY,IAC3B,mBACE,UAAU,gBAAgB,IAC1B;AAAA,IACN,MAAM,KAAK;AAAA,IACX,MAAM;AAAA,IACN,mBAAmB,OAAO,KAAK,OAAO;AAAA,IACtC,iBAAiB,OAAO,KAAK,KAAK;AAAA,IAClC,YAAY,aAAa,KAAK,KAAK;AAAA,IACnC,QAAQ,EAAE,MAAM,KAAK,QAAQ,IAAI,EAAE;AAAA,EACrC,EAAE;AACJ;AAUO,SAAS,mBACd,QACgB;AAChB,MAAI,OAAO,WAAW,EAAG,QAAO,CAAC;AACjC,QAAM,MAAsB,CAAC;AAC7B,QAAM,MAAM,CAAC,MACX,OAAO,MAAM,YAAY,OAAO,SAAS,CAAC,IAAI,IAAI;AACpD,QAAM,MAAM,CAAC,MACX,OAAO,MAAM,YAAY,EAAE,SAAS,IAAI,IAAI;AAC9C,QAAM,MAAM,CAAC,MACX,KAAK,OAAO,MAAM,WAAY,IAAgC,CAAC;AAEjE,QAAM,UAAU,OAAO,KAAK,CAAC,MAAM,EAAE,SAAS,cAAc;AAC5D,QAAM,QAAQ,OAAO,KAAK,CAAC,MAAM,EAAE,SAAS,YAAY;AACxD,QAAM,QAAQ,OAAO,CAAC,GAAG,SAAS;AAClC,QAAM,YAAY,SAAS,aAAa,OAAO,CAAC,EAAG;AACnD,QAAM,UAAU,OAAO,aAAa,OAAO,OAAO,SAAS,CAAC,EAAG;AAC/D,QAAM,SAAS,eAAe;AAE9B,QAAM,OAAO,CACX,QACA,cACA,MACA,MACA,SACA,OACA,OACA,QAAQ,WACU;AAAA,IAClB;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,EACF;AAGA,QAAM,KAAK,IAAI,SAAS,OAAO;AAC/B,QAAM,YAAuD;AAAA,IAC3D,CAAC,OAAO,SAAS,GAAG;AAAA,IACpB,CAAC,OAAO,cAAc,GAAG;AAAA,IACzB,sBAAsB,IAAI,GAAG,MAAM,KAAK;AAAA,EAC1C;AACA,MAAI,MAAM,QAAQ,GAAG,aAAa,KAAK,GAAG,cAAc,SAAS,GAAG;AAClE,cAAU,oBAAoB,IAAI,GAAG,cAAc,IAAI,MAAM,EAAE,KAAK,GAAG;AAAA,EACzE;AACA,MAAI,OAAO;AACT,UAAM,KAAK,IAAI,MAAM,OAAO;AAC5B,UAAM,MAAM,IAAI,GAAG,oBAAoB;AACvC,QAAI,QAAQ,OAAW,WAAU,oCAAoC,IAAI;AACzE,UAAM,OAAO,IAAI,GAAG,YAAY;AAChC,QAAI,SAAS,OAAW,WAAU,iBAAiB,IAAI;AACvD,UAAM,MAAM,IAAI,GAAG,UAAU;AAC7B,QAAI,QAAQ,OAAW,WAAU,yBAAyB,IAAI;AAC9D,UAAM,QAAQ,IAAI,GAAG,UAAU;AAC/B,QAAI,UAAU,OAAW,WAAU,wBAAwB,IAAI;AAAA,EACjE;AACA,MAAI,KAAK,KAAK,QAAQ,QAAW,QAAQ,QAAQ,WAAW,SAAS,SAAS,CAAC;AAG/E,QAAM,cAAc,oBAAI,IAAoB;AAC5C,QAAM,iBAAiB,oBAAI,IAAoC;AAC/D,MAAI;AACJ,MAAI;AAGJ,QAAM,aAAa,CAAC,UAAkB;AACpC,QAAI,CAAC,aAAc;AACnB,QAAI;AAAA,MACF;AAAA,QACE,aAAa;AAAA,QACb;AAAA,QACA;AAAA,QACA;AAAA,QACA,aAAa;AAAA,QACb;AAAA,QACA,aAAa;AAAA,MACf;AAAA,IACF;AACA,mBAAe;AAAA,EACjB;AAEA,aAAW,KAAK,QAAQ;AACtB,UAAM,IAAI,IAAI,EAAE,OAAO;AACvB,YAAQ,EAAE,MAAM;AAAA,MACd,KAAK,aAAa;AAChB,mBAAW,EAAE,SAAS;AACtB,cAAM,KAAK,eAAe;AAC1B,cAAM,WAAW,IAAI,EAAE,UAAU,KAAK;AACtC,cAAM,QAAmD;AAAA,UACvD,CAAC,OAAO,SAAS,GAAG;AAAA,UACpB,2BAA2B;AAAA,UAC3B,yBAAyB,IAAI,EAAE,QAAQ,KAAK;AAAA,UAC5C,0BAA0B;AAAA,UAC1B,0BAA0B,IAAI,EAAE,YAAY,KAAK;AAAA,QACnD;AACA,cAAM,IAAI,IAAI,EAAE,SAAS;AACzB,YAAI,EAAG,OAAM,4BAA4B,IAAI;AAC7C,cAAM,SAAS,IAAI,EAAE,WAAW;AAChC,YAAI,WAAW,OAAW,OAAM,+BAA+B,IAAI;AACnE,YAAI,MAAM,QAAQ,EAAE,YAAY,KAAK,EAAE,aAAa,SAAS,GAAG;AAC9D,gBAAM,gCAAgC,IAAI,EAAE,aAAa,IAAI,MAAM,EAAE,KAAK,GAAG;AAAA,QAC/E;AACA,uBAAe,EAAE,IAAI,OAAO,EAAE,WAAW,MAAM;AAC/C,yBAAiB;AACjB;AAAA,MACF;AAAA,MACA,KAAK,0BAA0B;AAC7B,cAAM,MAAM,IAAI,EAAE,cAAc;AAChC,YAAI,QAAQ,OAAW,aAAY,IAAI,KAAK,EAAE,SAAS;AACvD;AAAA,MACF;AAAA,MACA,KAAK,2BAA2B;AAC9B,cAAM,MAAM,IAAI,EAAE,cAAc;AAChC,YAAI,QAAQ,OAAW;AACvB,cAAM,QAAgC,CAAC;AACvC,cAAM,OAAO,IAAI,EAAE,SAAS;AAC5B,YAAI,KAAM,OAAM,4BAA4B,IAAI;AAChD,cAAM,MAAM,IAAI,EAAE,SAAS;AAC3B,YAAI,IAAK,OAAM,mBAAmB,IAAI;AACtC,cAAM,MAAM,IAAI,EAAE,OAAO;AACzB,YAAI,IAAK,OAAM,iBAAiB,IAAI;AACpC,cAAM,MAAM,IAAI,EAAE,SAAS;AAC3B,YAAI,IAAK,OAAM,mBAAmB,IAAI;AACtC,uBAAe,IAAI,KAAK,KAAK;AAC7B;AAAA,MACF;AAAA,MACA,KAAK,wBAAwB;AAC3B,cAAM,MAAM,IAAI,EAAE,cAAc,KAAK;AACrC,cAAM,QAAQ,YAAY,IAAI,GAAG,KAAK,EAAE;AACxC,cAAM,MAAM,IAAI,EAAE,KAAK;AACvB,cAAM,QAAmD;AAAA,UACvD,CAAC,OAAO,SAAS,GAAG;AAAA,UACpB,+BAA+B;AAAA,QACjC;AACA,cAAM,QAAQ,IAAI,EAAE,YAAY;AAChC,YAAI,MAAO,OAAM,OAAO,SAAS,IAAI;AACrC,cAAM,KAAK,IAAI,EAAE,UAAU;AAC3B,cAAM,QAAQ,IAAI,GAAG,KAAK;AAC1B,YAAI,UAAU,OAAW,OAAM,OAAO,WAAW,IAAI;AACrD,cAAM,SAAS,IAAI,GAAG,MAAM;AAC5B,YAAI,WAAW,OAAW,OAAM,OAAO,YAAY,IAAI;AACvD,cAAM,OAAO,IAAI,EAAE,OAAO;AAC1B,YAAI,SAAS,OAAW,OAAM,iBAAiB,IAAI;AACnD,cAAM,UAAU,IAAI,EAAE,OAAO;AAC7B,YAAI,OAAO,QAAQ,UAAU,UAAW,OAAM,2BAA2B,IAAI,QAAQ;AACrF,cAAM,QAAQ,IAAI,QAAQ,KAAK;AAC/B,YAAI,UAAU,OAAW,OAAM,2BAA2B,IAAI;AAC9D,YAAI,IAAK,OAAM,mBAAmB,IAAI;AACtC,cAAM,MAAM,IAAI,EAAE,OAAO;AACzB,YAAI,QAAQ,OAAW,OAAM,gCAAgC,IAAI;AACjE,cAAM,MAAM,IAAI,EAAE,WAAW;AAC7B,YAAI,QAAQ,OAAW,OAAM,oCAAoC,IAAI;AACrE,cAAM,MAAM,IAAI,EAAE,UAAU;AAC5B,YAAI,QAAQ,OAAW,OAAM,mCAAmC,IAAI;AACpE,cAAM,UAAU,IAAI,EAAE,aAAa;AACnC,YAAI,QAAS,OAAM,sCAAsC,IAAI;AAC7D,eAAO,OAAO,OAAO,eAAe,IAAI,GAAG,KAAK,CAAC,CAAC;AAClD,YAAI;AAAA,UACF;AAAA,YACE,eAAe;AAAA,YACf,kBAAkB;AAAA,YAClB;AAAA,YACA;AAAA,YACA;AAAA,YACA,EAAE;AAAA,YACF;AAAA,YACA,QAAQ;AAAA,UACV;AAAA,QACF;AACA;AAAA,MACF;AAAA,MACA,KAAK,iBAAiB;AACpB,YAAI,cAAc;AAChB,gBAAM,MAAM,IAAI,EAAE,QAAQ;AAC1B,cAAI,IAAK,cAAa,MAAM,sBAAsB,IAAI;AACtD,qBAAW,EAAE,SAAS;AAAA,QACxB;AACA,yBAAiB;AACjB;AAAA,MACF;AAAA,IACF;AAAA,EACF;AACA,aAAW,OAAO;AAClB,SAAO;AACT;AAEA,SAAS,sBAA8C;AACrD,MAAI,OAAO,YAAY,YAAa,QAAO,CAAC;AAC5C,QAAM,MAAM,QAAQ,IAAI;AACxB,MAAI,CAAC,IAAK,QAAO,CAAC;AAClB,QAAM,MAA8B,CAAC;AACrC,aAAW,QAAQ,IAAI,MAAM,GAAG,GAAG;AACjC,UAAM,KAAK,KAAK,QAAQ,GAAG;AAC3B,QAAI,KAAK,EAAG;AACZ,UAAM,MAAM,KAAK,MAAM,GAAG,EAAE,EAAE,KAAK;AACnC,UAAM,QAAQ,KAAK,MAAM,KAAK,CAAC,EAAE,KAAK;AACtC,QAAI,IAAK,KAAI,GAAG,IAAI;AAAA,EACtB;AACA,SAAO;AACT;AAEA,SAAS,aAAa,QAAoE;AACxF,SAAO,OAAO,QAAQ,MAAM,EAAE,IAAI,CAAC,CAAC,KAAK,KAAK,OAAO;AAAA,IACnD;AAAA,IACA,OACE,OAAO,UAAU,WACb,OAAO,UAAU,KAAK,IACpB,EAAE,UAAU,MAAM,SAAS,EAAE,IAC7B,EAAE,aAAa,MAAM,IACvB,OAAO,UAAU,YACf,EAAE,WAAW,MAAM,IACnB,EAAE,aAAa,MAAM;AAAA,EAC/B,EAAE;AACJ;AAEA,SAAS,OAAO,IAAoB;AAClC,UAAQ,OAAO,KAAK,MAAM,EAAE,CAAC,IAAI,UAAY,SAAS;AACxD;AAEA,SAAS,UAAU,IAAoB;AACrC,QAAM,UAAU,GAAG,QAAQ,MAAM,EAAE;AACnC,SAAO,QAAQ,MAAM,GAAG,EAAE,EAAE,OAAO,IAAI,GAAG;AAC5C;AAEA,SAAS,WAAW,IAAoB;AACtC,QAAM,UAAU,GAAG,QAAQ,MAAM,EAAE;AACnC,SAAO,QAAQ,MAAM,GAAG,EAAE,EAAE,OAAO,IAAI,GAAG;AAC5C;AAEA,SAAS,iBAAyB;AAChC,QAAM,QAAQ,IAAI,WAAW,CAAC;AAC9B,MAAI,OAAO,WAAW,QAAQ,oBAAoB,YAAY;AAC5D,eAAW,OAAO,gBAAgB,KAAK;AAAA,EACzC,OAAO;AACL,aAAS,IAAI,GAAG,IAAI,GAAG,IAAK,OAAM,CAAC,IAAI,KAAK,MAAM,KAAK,OAAO,IAAI,GAAG;AAAA,EACvE;AACA,SAAO,MAAM,KAAK,KAAK,EACpB,IAAI,CAAC,MAAM,EAAE,SAAS,EAAE,EAAE,SAAS,GAAG,GAAG,CAAC,EAC1C,KAAK,EAAE;AACZ;AAaO,IAAM,4BAA4B;AAuDzC,IAAM,4BAA4B;AAQlC,eAAsB,eACpB,QACA,QAC+B;AAC/B,MAAI,OAAO,WAAW,EAAG,QAAO,EAAE,IAAI,MAAM,QAAQ,GAAG,UAAU,GAAG,UAAU,CAAC,EAAE;AACjF,QAAM,SACJ,QAAQ,WAAW,OAAO,YAAY,cAAc,QAAQ,IAAI,iBAAiB;AACnF,MAAI,CAAC;AACH,UAAM,IAAI,MAAM,4EAA4E;AAC9F,QAAM,OACJ,QAAQ,SACP,OAAO,YAAY,cAAc,QAAQ,IAAI,oBAAoB,WAClE;AACF,QAAM,MAAM,GAAG,KAAK,QAAQ,QAAQ,EAAE,CAAC;AACvC,QAAM,MAAM,MAAM,MAAM,KAAK;AAAA,IAC3B,QAAQ;AAAA,IACR,SAAS;AAAA,MACP,gBAAgB;AAAA,MAChB,eAAe,UAAU,MAAM;AAAA,MAC/B,yBAAyB;AAAA,MACzB,GAAI,QAAQ,iBAAiB,EAAE,mBAAmB,OAAO,eAAe,IAAI,CAAC;AAAA,IAC/E;AAAA,IACA,MAAM,KAAK,UAAU,EAAE,aAAa,2BAA2B,OAAO,CAAC;AAAA,EACzE,CAAC;AACD,MAAI,SAAqF,CAAC;AAC1F,MAAI;AACF,aAAU,MAAM,IAAI,KAAK;AAAA,EAC3B,QAAQ;AAAA,EAER;AACA,SAAO;AAAA,IACL,IAAI,IAAI;AAAA,IACR,QAAQ,IAAI;AAAA,IACZ,UAAU,OAAO,aAAa,IAAI,KAAK,OAAO,SAAS;AAAA,IACvD,UAAU,OAAO,YAAY,CAAC;AAAA,EAChC;AACF;","names":[]}

package/dist/{chunk-ML4IXGTV.js → chunk-V2K35HF2.js}

@@ -14,7 +14,7 @@ import {
   DELEGATION_STATUS_DESCRIPTION,
   DELEGATION_STATUS_INPUT_SCHEMA,
   DELEGATION_STATUS_TOOL_NAME
-} from "./chunk-RHW75JW5.js";
+} from "./chunk-BERLUBAP.js";
 
 // src/mcp/openai-tools.ts
 function buildTool(name, description, parameters) {
@@ -61,4 +61,4 @@ export {
   mcpToolsForRuntimeMcp,
   mcpToolsForRuntimeMcpSubset
 };
-//# sourceMappingURL=chunk-ML4IXGTV.js.map
+//# sourceMappingURL=chunk-V2K35HF2.js.map

package/dist/improvement.d.ts

@@ -18,8 +18,9 @@ import 'node:child_process';
  * the SAME driver at two settings of a dial.
  *   - cheap reflective path  → `reflectiveGenerator` (shots=1, no sandbox;
  *                              applies pre-drafted patches)
- *   - full agentic path      → `agenticGenerator` (shots=N, sandbox runLoop;
- *                              an agent reads code + report and edits)
+ *   - full agentic path      → `agenticGenerator` (shots=N, multi-shot
+ *                              verify-in-session loop; an agent reads code +
+ *                              report, edits, and re-tries on verifier failure)
  * Both emit changes into a worktree the driver finalizes into a
  * `CodeSurface{ worktreeRef }` the loop measures on the holdout. See
  * agent-eval's `docs/design/self-improvement-engine.md`.
@@ -75,11 +76,31 @@ declare function improvementDriver(opts: ImprovementDriverOptions): ImprovementD
  * candidate (which would reintroduce a host↔sandbox worktree-transport
  * problem that does not need solving here).
  *
- * `maxShots` is the DEPTH dial: the harness runs once; if it produced no change
- * (the worktree stays clean), the generator refines the prompt and retries, up
- * to `maxShots` times. A harness that already changed files returns on shot 1.
+ * `maxShots` is the DEPTH dial — a multi-shot verify-in-session loop, NOT the
+ * kernel `runLoop`. Each shot runs one full harness session in the (persistent)
+ * worktree; between shots the loop refines based on what the last shot produced:
+ *   - empty tree   → "you changed nothing, make the edits" → retry
+ *   - dirty + `verify` fails → feed the verifier's failure into the next shot
+ *       (the worktree persists, so the harness RESUMES atop its own failing
+ *       edits with the error in hand — no `--resume` session plumbing needed,
+ *       and harness-agnostic across claude/codex/opencode)
+ *   - dirty + `verify` ok (or no verifier configured) → return the candidate
+ * A candidate that never verifies within `maxShots` is discarded (`applied:
+ * false`), never shipped — if you configured a verifier, a non-passing tree is
+ * not a candidate. With no verifier the legacy behavior holds: first dirty shot
+ * is the candidate.
  */
 
+/** Outcome of verifying a candidate worktree. `feedback` (compiler errors,
+ *  failing test output) is fed into the next shot when `ok` is false. */
+interface VerifyResult {
+    ok: boolean;
+    feedback?: string;
+}
+/** Verifies the edited worktree. Sync or async; throws only on a setup fault
+ *  (a candidate that fails verification returns `{ok:false}`, it does not
+ *  throw). */
+type Verifier = (worktreePath: string) => Promise<VerifyResult> | VerifyResult;
 interface AgenticGeneratorOptions {
     /** Local coding harness to run in the worktree. Default `claude`. */
     harness?: LocalHarness;
@@ -91,12 +112,79 @@ interface AgenticGeneratorOptions {
         report: unknown;
         findings: AnalystFinding[];
     }) => string;
+    /** Verify the worktree after each dirtying shot. When set, a candidate that
+     *  fails verification is NOT returned — the failure feeds the next shot
+     *  (verify-in-session), up to `maxShots`; a candidate that never verifies is
+     *  discarded (`applied:false`), never shipped. Omitted ⇒ legacy behavior:
+     *  the first dirty shot is the candidate. See `commandVerifier`. */
+    verify?: Verifier;
     /** Test seam — inject the harness runner (defaults to `runLocalHarness`). */
     runHarness?: typeof runLocalHarness;
     /** Test seam — inject the worktree-dirty check (defaults to `git status`). */
     isDirty?: (worktreePath: string) => boolean;
 }
 declare function agenticGenerator(opts?: AgenticGeneratorOptions): CandidateGenerator;
+/** A `Verifier` that runs a command in the worktree: exit 0 ⇒ ok, any other
+ *  exit ⇒ failed with stdout+stderr as feedback. The common case — verify by
+ *  `tsc --noEmit`, `pnpm build`, or a test command. A timeout is treated as a
+ *  FAILED candidate (a change that hangs the build is a bad change); a missing
+ *  binary or spawn fault throws (a setup bug, not a failed candidate — no
+ *  silent fallback). */
+declare function commandVerifier(command: string, args?: string[], timeoutMs?: number): Verifier;
+
+/**
+ * Build-prompt starting points for the two buildable artifact types. There is
+ * NO `toolGenerator`/`mcpGenerator` wrapper — the factory is `agenticGenerator`
+ * + a verifier (docs/artifact-lifecycle-frontier.md), so a tool or an MCP
+ * server is built by composing the pieces directly:
+ *
+ *   // a tool:
+ *   agenticGenerator({ buildPrompt: toolBuildPrompt, verify: commandVerifier('pnpm', ['test']) })
+ *   // an MCP server:
+ *   agenticGenerator({ buildPrompt: mcpBuildPrompt, verify: mcpServeVerifier({ command: 'node', args: ['server.mjs'] }) })
+ *
+ * These are the only type-specific bit (the phrasing that points the agent at a
+ * tool vs. an MCP); the worktree, resume-on-failure loop, and improvement-loop
+ * wrapper are shared. MCP is the load-bearing target — it is how a harness
+ * acquires tools; raw tools matter where we control the loader.
+ */
+
+type FindingsArg = {
+    report: unknown;
+    findings: AnalystFinding[];
+};
+declare function toolBuildPrompt(args: FindingsArg): string;
+declare function mcpBuildPrompt(args: FindingsArg): string;
+
+/**
+ * `mcpServeVerifier` — the intrinsic verifier for a built MCP server: the
+ * boot-and-probe checker named in docs/artifact-lifecycle-frontier.md. A
+ * generated MCP server is only a candidate if it actually *serves* — so this
+ * boots it over stdio (the default local MCP transport) and runs the real
+ * handshake: `initialize` → `notifications/initialized` → `tools/list`, and
+ * asserts the server answers with at least `minTools` tools.
+ *
+ * Outcomes follow the `Verifier` contract: a server that fails to start, exits
+ * early, errors the handshake, times out, or exposes no tools is a FAILED
+ * candidate (`{ok:false}`, fed back into the next generation shot); a missing
+ * start binary or spawn fault THROWS (a setup bug, never a silent fallback).
+ *
+ * Protocol matches the runtime's own stdio MCP server (src/mcp/server.ts):
+ * newline-delimited JSON-RPC 2.0, protocol version 2024-11-05.
+ */
+
+interface McpServeSpec {
+    /** Command that starts the built MCP server in the worktree (stdio transport). */
+    command: string;
+    args?: string[];
+    /** Extra env for the server process (merged over `process.env`). */
+    env?: Record<string, string>;
+    /** Handshake timeout (ms). Default 30s. */
+    timeoutMs?: number;
+    /** Minimum tools the server must expose to pass. Default 1. */
+    minTools?: number;
+}
+declare function mcpServeVerifier(spec: McpServeSpec): Verifier;
 
 /**
  * @experimental
@@ -108,8 +196,8 @@ declare function agenticGenerator(opts?: AgenticGeneratorOptions): CandidateGene
  * construction (the patches are already drafted).
  *
  * This is the `shots=1, sandbox=off` setting of the one improvement driver.
- * The `agenticGenerator` (sandbox runLoop) is the `shots=N, sandbox=on`
- * setting — both plug into the same `improvementDriver`.
+ * The `agenticGenerator` (a multi-shot verify-in-session loop) is the
+ * `shots=N` setting — both plug into the same `improvementDriver`.
  */
 
 interface ReflectiveGeneratorOptions {
@@ -117,4 +205,4 @@ interface ReflectiveGeneratorOptions {
 }
 declare function reflectiveGenerator(opts: ReflectiveGeneratorOptions): CandidateGenerator;
 
-export { type AgenticGeneratorOptions, type CandidateGenerator, type ImprovementDriverOptions, type ReflectiveGeneratorOptions, agenticGenerator, improvementDriver, reflectiveGenerator };
+export { type AgenticGeneratorOptions, type CandidateGenerator, type ImprovementDriverOptions, type McpServeSpec, type ReflectiveGeneratorOptions, type Verifier, type VerifyResult, agenticGenerator, commandVerifier, improvementDriver, mcpBuildPrompt, mcpServeVerifier, reflectiveGenerator, toolBuildPrompt };