@tangle-network/agent-runtime 0.71.1 → 0.73.0

package/dist/chunk-PBE35ULD.js

@@ -0,0 +1,52 @@
+import {
+  buildLoopOtelSpans,
+  createOtelExporter
+} from "./chunk-VMNEQHJR.js";
+
+// src/mcp/trace-propagation.ts
+function readTraceContextFromEnv() {
+  const traceId = process.env.TRACE_ID || generateTraceId();
+  const parentSpanId = process.env.PARENT_SPAN_ID || void 0;
+  return { traceId, parentSpanId };
+}
+function createPropagatingTraceEmitter(ctx) {
+  const exporter = createOtelExporter();
+  const buffers = /* @__PURE__ */ new Map();
+  const emitter = {
+    emit(event) {
+      if (!exporter) return;
+      const buf = buffers.get(event.runId);
+      if (buf) buf.push(event);
+      else buffers.set(event.runId, [event]);
+      if (event.kind === "loop.ended") {
+        const events = buffers.get(event.runId) ?? [event];
+        buffers.delete(event.runId);
+        for (const span of buildLoopOtelSpans(events, ctx.traceId, ctx.parentSpanId)) {
+          exporter.exportSpan(span);
+        }
+      }
+    }
+  };
+  return { emitter, exporter, context: ctx };
+}
+function traceContextToEnv(ctx) {
+  const env = { TRACE_ID: ctx.traceId };
+  if (ctx.parentSpanId) env.PARENT_SPAN_ID = ctx.parentSpanId;
+  return env;
+}
+function generateTraceId() {
+  const bytes = new Uint8Array(16);
+  if (typeof globalThis.crypto?.getRandomValues === "function") {
+    globalThis.crypto.getRandomValues(bytes);
+  } else {
+    for (let i = 0; i < 16; i++) bytes[i] = Math.floor(Math.random() * 256);
+  }
+  return Array.from(bytes).map((b) => b.toString(16).padStart(2, "0")).join("");
+}
+
+export {
+  readTraceContextFromEnv,
+  createPropagatingTraceEmitter,
+  traceContextToEnv
+};
+//# sourceMappingURL=chunk-PBE35ULD.js.map

package/dist/chunk-PBE35ULD.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/mcp/trace-propagation.ts"],"sourcesContent":["/**\n * @experimental\n *\n * Trace context propagation for MCP subprocess.\n *\n * When the MCP server is launched as a child process by a sandbox harness,\n * the parent passes trace context via environment variables:\n *\n *   TRACE_ID=<current-run-trace-id>\n *   PARENT_SPAN_ID=<span-that-dispatched-the-delegation>\n *\n * The MCP server reads these at startup and uses them as the root of its\n * internal trace tree. All spans emitted by `runLoop` invocations inside\n * the MCP are children of the parent's delegation span.\n *\n * When these env vars are absent, the MCP generates a fresh trace root —\n * the server operates standalone without trace joining.\n */\n\nimport type { OtelExporter } from '../otel-export'\nimport { buildLoopOtelSpans, createOtelExporter } from '../otel-export'\nimport type { LoopTraceEmitter, LoopTraceEvent } from '../runtime/types'\n\nexport interface TraceContext {\n  /** Trace id inherited from the parent process, or a fresh one. */\n  traceId: string\n  /** Parent span id from the delegation that launched this MCP server. */\n  parentSpanId?: string\n}\n\n/**\n * Read trace context from the process environment.\n * Returns a context with inherited ids or a freshly generated root.\n */\nexport function readTraceContextFromEnv(): TraceContext {\n  const traceId = process.env.TRACE_ID || generateTraceId()\n  const parentSpanId = process.env.PARENT_SPAN_ID || undefined\n  return { traceId, parentSpanId }\n}\n\n/**\n * Create a LoopTraceEmitter that:\n *   1. Parents all spans under the inherited PARENT_SPAN_ID.\n *   2. Exports spans to OTEL when OTEL_EXPORTER_OTLP_ENDPOINT is set.\n *\n * Returns both the emitter and the optional exporter handle for shutdown.\n */\nexport function createPropagatingTraceEmitter(ctx: TraceContext): {\n  emitter: LoopTraceEmitter\n  exporter: OtelExporter | undefined\n  context: TraceContext\n} {\n  const exporter = createOtelExporter()\n\n  // Buffer events per loop run, then emit the full nested span tree on\n  // `loop.ended` so the topology hierarchy (loop → round → branch) reaches the\n  // OTLP collector — not a flat list of zero-duration point spans. A run that\n  // never reaches `loop.ended` (hard abort) drops its buffer; acceptable for\n  // the short-lived MCP subprocess.\n  const buffers = new Map<string, LoopTraceEvent[]>()\n\n  const emitter: LoopTraceEmitter = {\n    emit(event: LoopTraceEvent) {\n      if (!exporter) return\n      const buf = buffers.get(event.runId)\n      if (buf) buf.push(event)\n      else buffers.set(event.runId, [event])\n      if (event.kind === 'loop.ended') {\n        const events = buffers.get(event.runId) ?? [event]\n        buffers.delete(event.runId)\n        for (const span of buildLoopOtelSpans(events, ctx.traceId, ctx.parentSpanId)) {\n          exporter.exportSpan(span)\n        }\n      }\n    },\n  }\n\n  return { emitter, exporter, context: ctx }\n}\n\n/**\n * Build env vars to pass to a child MCP subprocess so it inherits the\n * current trace context.\n */\nexport function traceContextToEnv(ctx: TraceContext): Record<string, string> {\n  const env: Record<string, string> = { TRACE_ID: ctx.traceId }\n  if (ctx.parentSpanId) env.PARENT_SPAN_ID = ctx.parentSpanId\n  return env\n}\n\nfunction generateTraceId(): string {\n  const bytes = new Uint8Array(16)\n  if (typeof globalThis.crypto?.getRandomValues === 'function') {\n    globalThis.crypto.getRandomValues(bytes)\n  } else {\n    for (let i = 0; i < 16; 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"],"mappings":";;;;;;AAkCO,SAAS,0BAAwC;AACtD,QAAM,UAAU,QAAQ,IAAI,YAAY,gBAAgB;AACxD,QAAM,eAAe,QAAQ,IAAI,kBAAkB;AACnD,SAAO,EAAE,SAAS,aAAa;AACjC;AASO,SAAS,8BAA8B,KAI5C;AACA,QAAM,WAAW,mBAAmB;AAOpC,QAAM,UAAU,oBAAI,IAA8B;AAElD,QAAM,UAA4B;AAAA,IAChC,KAAK,OAAuB;AAC1B,UAAI,CAAC,SAAU;AACf,YAAM,MAAM,QAAQ,IAAI,MAAM,KAAK;AACnC,UAAI,IAAK,KAAI,KAAK,KAAK;AAAA,UAClB,SAAQ,IAAI,MAAM,OAAO,CAAC,KAAK,CAAC;AACrC,UAAI,MAAM,SAAS,cAAc;AAC/B,cAAM,SAAS,QAAQ,IAAI,MAAM,KAAK,KAAK,CAAC,KAAK;AACjD,gBAAQ,OAAO,MAAM,KAAK;AAC1B,mBAAW,QAAQ,mBAAmB,QAAQ,IAAI,SAAS,IAAI,YAAY,GAAG;AAC5E,mBAAS,WAAW,IAAI;AAAA,QAC1B;AAAA,MACF;AAAA,IACF;AAAA,EACF;AAEA,SAAO,EAAE,SAAS,UAAU,SAAS,IAAI;AAC3C;AAMO,SAAS,kBAAkB,KAA2C;AAC3E,QAAM,MAA8B,EAAE,UAAU,IAAI,QAAQ;AAC5D,MAAI,IAAI,aAAc,KAAI,iBAAiB,IAAI;AAC/C,SAAO;AACT;AAEA,SAAS,kBAA0B;AACjC,QAAM,QAAQ,IAAI,WAAW,EAAE;AAC/B,MAAI,OAAO,WAAW,QAAQ,oBAAoB,YAAY;AAC5D,eAAW,OAAO,gBAAgB,KAAK;AAAA,EACzC,OAAO;AACL,aAAS,IAAI,GAAG,IAAI,IAAI,IAAK,OAAM,CAAC,IAAI,KAAK,MAAM,KAAK,OAAO,IAAI,GAAG;AAAA,EACxE;AACA,SAAO,MAAM,KAAK,KAAK,EACpB,IAAI,CAAC,MAAM,EAAE,SAAS,EAAE,EAAE,SAAS,GAAG,GAAG,CAAC,EAC1C,KAAK,EAAE;AACZ;","names":[]}

package/dist/{chunk-VLF5RHEQ.js → chunk-T2HVQVB4.js}

@@ -1,58 +1,3 @@
-// src/errors.ts
-import { AgentEvalError } from "@tangle-network/agent-eval";
-import {
-  AgentEvalError as AgentEvalError2,
-  ConfigError,
-  JudgeError,
-  NotFoundError,
-  ValidationError
-} from "@tangle-network/agent-eval";
-var SessionMismatchError = class extends AgentEvalError {
-  sessionBackend;
-  requestedBackend;
-  constructor(sessionBackend, requestedBackend, options) {
-    super(
-      "validation",
-      `Cannot resume ${sessionBackend} session with ${requestedBackend} backend`,
-      options
-    );
-    this.sessionBackend = sessionBackend;
-    this.requestedBackend = requestedBackend;
-  }
-};
-var BackendTransportError = class extends AgentEvalError {
-  backend;
-  status;
-  /**
-   * Truncated upstream response body (≤2 KiB) when available. Diagnostic
-   * only — surfaces in `backend_error.error.body` and `final.error.body`
-   * so operators can see "free_tier_limit", "invalid_api_key", etc. without
-   * cracking the log line open.
-   */
-  body;
-  constructor(backend, message, options) {
-    super("config", message, options);
-    this.backend = backend;
-    this.status = options?.status;
-    this.body = options?.body;
-  }
-};
-var RuntimeRunStateError = class extends AgentEvalError {
-  constructor(message, options) {
-    super("validation", message, options);
-  }
-};
-var PlannerError = class extends AgentEvalError {
-  constructor(message, options) {
-    super("validation", message, options);
-  }
-};
-var AnalystError = class extends AgentEvalError {
-  constructor(message, options) {
-    super("validation", message, options);
-  }
-};
-
 // src/runtime/sandbox-events.ts
 function extractLlmCallEvent(event, agentRunName) {
   if (!event || typeof event !== "object") return void 0;
@@ -127,17 +72,7 @@ function mapSandboxEvent(event, opts = {}) {
 }
 
 export {
-  SessionMismatchError,
-  BackendTransportError,
-  RuntimeRunStateError,
-  PlannerError,
-  AnalystError,
-  AgentEvalError2 as AgentEvalError,
-  ConfigError,
-  JudgeError,
-  NotFoundError,
-  ValidationError,
   extractLlmCallEvent,
   mapSandboxEvent
 };
-//# sourceMappingURL=chunk-VLF5RHEQ.js.map
+//# sourceMappingURL=chunk-T2HVQVB4.js.map

package/dist/chunk-T2HVQVB4.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/runtime/sandbox-events.ts"],"sourcesContent":["/**\n * Sandbox-event → runtime-event mapping.\n *\n * The sandbox SDK emits a polymorphic `SandboxEvent = { type, data, id? }`\n * whose `type` vocabulary is backend-determined (opencode, etc.) rather than\n * enumerated by the SDK. Two consumers project it:\n *   - the loop kernel's cost ledger (`extractLlmCallEvent`) — sums usage off\n *     every cost-bearing event, regardless of stream shape;\n *   - the `AgentRuntime.act` streaming contract (`mapSandboxEvent`) — projects\n *     incremental events to the `RuntimeStreamEvent` chat-UX vocabulary.\n *\n * Both live here so the empirically-observed `type` vocabulary has one home.\n */\n\nimport type { SandboxEvent } from '@tangle-network/sandbox'\nimport type { RuntimeStreamEvent } from '../types'\n\n/**\n * Extract a `RuntimeStreamEvent`-shaped `llm_call` from a sandbox event when\n * the event carries usage/cost data. Returns `undefined` for non-cost events\n * so the kernel can iterate the full stream without branching.\n *\n * Canonical cost-carrying types observed in the wild:\n *   - `llm_call` — `data: { model, tokensIn, tokensOut, costUsd, ... }`\n *   - `message.completed` / `result` — `data: { usage: { inputTokens,\n *      outputTokens, totalCostUsd? } }`\n *   - `cost.usage` / `usage` — same shape under a dedicated type\n *\n * Numeric coercion is strict: `Number.isFinite` gates every accumulator write\n * so a sentinel `NaN` from a misbehaving backend cannot poison the ledger.\n */\nexport function extractLlmCallEvent(\n  event: SandboxEvent,\n  agentRunName: string,\n): (RuntimeStreamEvent & { type: 'llm_call' }) | undefined {\n  if (!event || typeof event !== 'object') return undefined\n  const type = String(event.type ?? '')\n  const data =\n    event.data && typeof event.data === 'object'\n      ? (event.data as Record<string, unknown>)\n      : ({} as Record<string, unknown>)\n\n  if (type === 'llm_call' || type === 'cost.usage' || type === 'usage') {\n    return buildLlmCall(data, agentRunName)\n  }\n  if (type === 'message.completed' || type === 'result' || type === 'final') {\n    const usage = data.usage as Record<string, unknown> | undefined\n    if (!usage || typeof usage !== 'object') return undefined\n    return buildLlmCall({ ...usage, model: data.model ?? usage.model }, agentRunName)\n  }\n  // sandbox 0.4.0 terminal event: `data = { tokenUsage: { inputTokens, outputTokens,\n  // reasoningTokens, cacheReadInputTokens }, totalCostUsd }`. Usage lives under\n  // `tokenUsage` (not `usage`) and the cost is top-level — neither matched the\n  // branches above, so an in-process loopDispatch run reported {0,0} and the\n  // backend-integrity guard misread a real run as a stub. Reasoning tokens are\n  // billed output (reasoning models), so they fold into the output count.\n  if (type === 'done') {\n    const usage = data.tokenUsage as Record<string, unknown> | undefined\n    if (!usage || typeof usage !== 'object') return undefined\n    const out = pickFiniteNumber(usage, ['outputTokens', 'completion_tokens', 'tokensOut'])\n    const reasoning = pickFiniteNumber(usage, ['reasoningTokens'])\n    const mergedOut =\n      out !== undefined || reasoning !== undefined ? (out ?? 0) + (reasoning ?? 0) : undefined\n    return buildLlmCall(\n      {\n        inputTokens: usage.inputTokens,\n        outputTokens: mergedOut,\n        totalCostUsd: data.totalCostUsd,\n        model: data.model ?? usage.model,\n      },\n      agentRunName,\n    )\n  }\n  return undefined\n}\n\nfunction buildLlmCall(\n  data: Record<string, unknown>,\n  agentRunName: string,\n): (RuntimeStreamEvent & { type: 'llm_call' }) | undefined {\n  const tokensIn = pickFiniteNumber(data, ['tokensIn', 'inputTokens', 'prompt_tokens'])\n  const tokensOut = pickFiniteNumber(data, ['tokensOut', 'outputTokens', 'completion_tokens'])\n  const costUsd = pickFiniteNumber(data, ['costUsd', 'totalCostUsd', 'cost_usd', 'cost'])\n  if (tokensIn === undefined && tokensOut === undefined && costUsd === undefined) {\n    return undefined\n  }\n  const model = typeof data.model === 'string' && data.model.length > 0 ? data.model : agentRunName\n  const event: RuntimeStreamEvent & { type: 'llm_call' } = {\n    type: 'llm_call',\n    model,\n  }\n  if (tokensIn !== undefined) event.tokensIn = tokensIn\n  if (tokensOut !== undefined) event.tokensOut = tokensOut\n  if (costUsd !== undefined) event.costUsd = costUsd\n  return event\n}\n\nfunction pickFiniteNumber(data: Record<string, unknown>, keys: string[]): number | undefined {\n  for (const key of keys) {\n    const value = data[key]\n    if (typeof value === 'number' && Number.isFinite(value)) return value\n  }\n  return undefined\n}\n\n/**\n * Project one `SandboxEvent` onto the `RuntimeStreamEvent` chat-UX vocabulary,\n * for runtimes that bridge a sandbox `streamPrompt` into the\n * `AgentRuntime.act` streaming contract. Returns `undefined` for events that\n * have no faithful projection — the raw stream is preserved separately for the\n * `OutputAdapter`, so an unmapped event never loses data.\n *\n * Mapped (the task-optional incremental variants — no synthesized task\n * lifecycle, no guessed tool-part shapes):\n *   - `message.part.updated` text part → `text_delta`\n *   - `message.part.updated` reasoning/thinking part → `reasoning_delta`\n *   - cost-bearing events → `llm_call` (shared with the ledger extractor)\n *\n * The opencode backend emits incremental text as\n * `{ type: 'message.part.updated', data: { part: { type, text }, delta } }`;\n * `delta` is the increment, `part.text` the running accumulation.\n */\nexport function mapSandboxEvent(\n  event: SandboxEvent,\n  opts: { agentRunName?: string } = {},\n): RuntimeStreamEvent | undefined {\n  if (!event || typeof event !== 'object') return undefined\n  const type = String(event.type ?? '')\n  const data =\n    event.data && typeof event.data === 'object'\n      ? (event.data as Record<string, unknown>)\n      : ({} as Record<string, unknown>)\n\n  if (type === 'message.part.updated') {\n    const part =\n      data.part && typeof data.part === 'object' ? (data.part as Record<string, unknown>) : {}\n    const partType = String(part.type ?? '')\n    const delta = typeof data.delta === 'string' ? data.delta : undefined\n    const text = delta ?? (typeof part.text === 'string' ? part.text : undefined)\n    if (text === undefined) return undefined\n    if (partType === 'text') return { type: 'text_delta', text }\n    if (partType === 'reasoning' || partType === 'thinking')\n      return { type: 'reasoning_delta', text }\n    return undefined\n  }\n\n  return extractLlmCallEvent(event, opts.agentRunName ?? 'agent')\n}\n"],"mappings":";AA+BO,SAAS,oBACd,OACA,cACyD;AACzD,MAAI,CAAC,SAAS,OAAO,UAAU,SAAU,QAAO;AAChD,QAAM,OAAO,OAAO,MAAM,QAAQ,EAAE;AACpC,QAAM,OACJ,MAAM,QAAQ,OAAO,MAAM,SAAS,WAC/B,MAAM,OACN,CAAC;AAER,MAAI,SAAS,cAAc,SAAS,gBAAgB,SAAS,SAAS;AACpE,WAAO,aAAa,MAAM,YAAY;AAAA,EACxC;AACA,MAAI,SAAS,uBAAuB,SAAS,YAAY,SAAS,SAAS;AACzE,UAAM,QAAQ,KAAK;AACnB,QAAI,CAAC,SAAS,OAAO,UAAU,SAAU,QAAO;AAChD,WAAO,aAAa,EAAE,GAAG,OAAO,OAAO,KAAK,SAAS,MAAM,MAAM,GAAG,YAAY;AAAA,EAClF;AAOA,MAAI,SAAS,QAAQ;AACnB,UAAM,QAAQ,KAAK;AACnB,QAAI,CAAC,SAAS,OAAO,UAAU,SAAU,QAAO;AAChD,UAAM,MAAM,iBAAiB,OAAO,CAAC,gBAAgB,qBAAqB,WAAW,CAAC;AACtF,UAAM,YAAY,iBAAiB,OAAO,CAAC,iBAAiB,CAAC;AAC7D,UAAM,YACJ,QAAQ,UAAa,cAAc,UAAa,OAAO,MAAM,aAAa,KAAK;AACjF,WAAO;AAAA,MACL;AAAA,QACE,aAAa,MAAM;AAAA,QACnB,cAAc;AAAA,QACd,cAAc,KAAK;AAAA,QACnB,OAAO,KAAK,SAAS,MAAM;AAAA,MAC7B;AAAA,MACA;AAAA,IACF;AAAA,EACF;AACA,SAAO;AACT;AAEA,SAAS,aACP,MACA,cACyD;AACzD,QAAM,WAAW,iBAAiB,MAAM,CAAC,YAAY,eAAe,eAAe,CAAC;AACpF,QAAM,YAAY,iBAAiB,MAAM,CAAC,aAAa,gBAAgB,mBAAmB,CAAC;AAC3F,QAAM,UAAU,iBAAiB,MAAM,CAAC,WAAW,gBAAgB,YAAY,MAAM,CAAC;AACtF,MAAI,aAAa,UAAa,cAAc,UAAa,YAAY,QAAW;AAC9E,WAAO;AAAA,EACT;AACA,QAAM,QAAQ,OAAO,KAAK,UAAU,YAAY,KAAK,MAAM,SAAS,IAAI,KAAK,QAAQ;AACrF,QAAM,QAAmD;AAAA,IACvD,MAAM;AAAA,IACN;AAAA,EACF;AACA,MAAI,aAAa,OAAW,OAAM,WAAW;AAC7C,MAAI,cAAc,OAAW,OAAM,YAAY;AAC/C,MAAI,YAAY,OAAW,OAAM,UAAU;AAC3C,SAAO;AACT;AAEA,SAAS,iBAAiB,MAA+B,MAAoC;AAC3F,aAAW,OAAO,MAAM;AACtB,UAAM,QAAQ,KAAK,GAAG;AACtB,QAAI,OAAO,UAAU,YAAY,OAAO,SAAS,KAAK,EAAG,QAAO;AAAA,EAClE;AACA,SAAO;AACT;AAmBO,SAAS,gBACd,OACA,OAAkC,CAAC,GACH;AAChC,MAAI,CAAC,SAAS,OAAO,UAAU,SAAU,QAAO;AAChD,QAAM,OAAO,OAAO,MAAM,QAAQ,EAAE;AACpC,QAAM,OACJ,MAAM,QAAQ,OAAO,MAAM,SAAS,WAC/B,MAAM,OACN,CAAC;AAER,MAAI,SAAS,wBAAwB;AACnC,UAAM,OACJ,KAAK,QAAQ,OAAO,KAAK,SAAS,WAAY,KAAK,OAAmC,CAAC;AACzF,UAAM,WAAW,OAAO,KAAK,QAAQ,EAAE;AACvC,UAAM,QAAQ,OAAO,KAAK,UAAU,WAAW,KAAK,QAAQ;AAC5D,UAAM,OAAO,UAAU,OAAO,KAAK,SAAS,WAAW,KAAK,OAAO;AACnE,QAAI,SAAS,OAAW,QAAO;AAC/B,QAAI,aAAa,OAAQ,QAAO,EAAE,MAAM,cAAc,KAAK;AAC3D,QAAI,aAAa,eAAe,aAAa;AAC3C,aAAO,EAAE,MAAM,mBAAmB,KAAK;AACzC,WAAO;AAAA,EACT;AAEA,SAAO,oBAAoB,OAAO,KAAK,gBAAgB,OAAO;AAChE;","names":[]}

package/dist/{chunk-K3RM4MPM.js → chunk-U56XGKVY.js}

@@ -1,21 +1,20 @@
-import {
-  runAnalystLoop
-} from "./chunk-P5OKDSLB.js";
 import {
   createKbGate
 } from "./chunk-FNMGYYSS.js";
 import {
-  detachedSessionDelegate
-} from "./chunk-INXDNX2W.js";
-import {
-  createExecutorRegistry,
   definePersona,
   runPersonified,
   worktreeFanout
-} from "./chunk-5ISW5JUF.js";
+} from "./chunk-HPYWEFVY.js";
+import {
+  createExecutorRegistry
+} from "./chunk-NCH4XUZ7.js";
+import {
+  runAnalystLoop
+} from "./chunk-IODKUOBA.js";
 import {
   ConfigError
-} from "./chunk-VLF5RHEQ.js";
+} from "./chunk-NBV35BR6.js";
 
 // src/loop-runner.ts
 import {
@@ -47,19 +46,6 @@ async function runDelegatedLoop(mode, registry, options = {}) {
     };
   }
 }
-function coderLoopRunner(options) {
-  const delegate = detachedSessionDelegate({
-    sandboxClient: options.sandboxClient,
-    ...options.reviewer ? { reviewer: options.reviewer } : {},
-    ...options.winnerSelection ? { winnerSelection: options.winnerSelection } : {},
-    ...options.fanoutHarnesses ? { fanoutHarnesses: options.fanoutHarnesses } : {}
-  });
-  return async (signal) => {
-    const ctx = { signal, report: () => {
-    } };
-    return delegate(options.args, ctx);
-  };
-}
 function worktreeLoopRunner(options) {
   const shape = worktreeFanout({
     repoRoot: options.repoRoot,
@@ -203,7 +189,6 @@ export {
   DELEGATED_LOOP_MODES,
   isDelegatedLoopMode,
   runDelegatedLoop,
-  coderLoopRunner,
   worktreeLoopRunner,
   researchLoopRunner,
   selfImproveLoopRunner,
@@ -211,4 +196,4 @@ export {
   runLoopRunnerCli,
   parseLoopRunnerArgv
 };
-//# sourceMappingURL=chunk-K3RM4MPM.js.map
+//# sourceMappingURL=chunk-U56XGKVY.js.map

package/dist/chunk-U56XGKVY.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/loop-runner.ts","../src/loop-runner-bin.ts"],"sourcesContent":["/**\n * @experimental\n *\n * `runDelegatedLoop` — the configured delegated loop-runner.\n *\n * One typed entrypoint a worker agent (or a scheduled routine) calls to run a\n * disciplined loop in a chosen MODE, over agent-runtime's hardened engines:\n *\n *   code         → build-in-a-loop on the GENERIC recursive path (worktreeLoopRunner: author one\n *                  `AgentProfile` per harness → worktree-CLI leaves → `patchDelivered` gate)\n *   review       → caller-registered runner — a `code` runner with an approval gate over candidates\n *   research     → research-in-a-loop with valid-only KB growth (createKbGate)\n *   audit        → analyze trace/run data → findings (runAnalystLoop, caller-wired)\n *   self-improve → closed-loop text/config optimization (selfImprove, held-out gated)\n *\n * It is intentionally a thin façade: the value is that EVERY product reuses the\n * one hardened engine instead of forking delegation logic. The dispatcher owns\n * mode routing, timing, fail-loud on an unregistered mode, and a uniform result\n * shape; each mode's engine is a pre-configured runner in the registry (build it\n * with the factories below, or inject your own / a stub).\n */\n\nimport type { Scenario } from '@tangle-network/agent-eval/campaign'\nimport {\n  type SelfImproveOptions,\n  type SelfImproveResult,\n  selfImprove,\n} from '@tangle-network/agent-eval/contract'\nimport { runAnalystLoop } from './analyst-loop'\nimport type { RunAnalystLoopOpts, RunAnalystLoopResult } from './analyst-loop/types'\nimport { ConfigError } from './errors'\nimport { type CreateKbGateOptions, createKbGate, type FactCandidate } from './mcp/kb-gate'\nimport {\n  type AuthoredHarness,\n  type Budget,\n  createExecutorRegistry,\n  definePersona,\n  runPersonified,\n  type WinnerStrategy,\n  type WorktreeFanoutOptions,\n  type WorktreePatchArtifact,\n  worktreeFanout,\n} from './runtime'\n\n/** @experimental Every delegated-loop mode, for validation + CLI surfaces. */\nexport const DELEGATED_LOOP_MODES = ['code', 'review', 'research', 'audit', 'self-improve'] as const\n\n/** @experimental */\nexport type DelegatedLoopMode = (typeof DELEGATED_LOOP_MODES)[number]\n\n/** @experimental Type guard for an untrusted mode string (CLI / config input). */\nexport function isDelegatedLoopMode(value: unknown): value is DelegatedLoopMode {\n  return typeof value === 'string' && (DELEGATED_LOOP_MODES as readonly string[]).includes(value)\n}\n\n/** @experimental A pre-configured loop for one mode. Returns the mode's raw\n *  output; the dispatcher wraps it in a {@link DelegatedLoopResult}. */\nexport type DelegatedLoopRunner<T = unknown> = (signal: AbortSignal) => Promise<T>\n\n/** @experimental Mode → configured runner. Partial: only register the modes a\n *  given product/routine actually uses. */\nexport type DelegatedLoopRegistry = Partial<Record<DelegatedLoopMode, DelegatedLoopRunner>>\n\n/** @experimental Uniform result — never throws from a registered runner; a\n *  thrown engine becomes `{ ok: false, error }` so a routine can record + move on. */\nexport interface DelegatedLoopResult<T = unknown> {\n  mode: DelegatedLoopMode\n  ok: boolean\n  output?: T\n  error?: string\n  durationMs: number\n}\n\n/** @experimental */\nexport interface RunDelegatedLoopOptions {\n  signal?: AbortSignal\n  /** Clock override for deterministic tests. */\n  now?: () => number\n}\n\n/**\n * @experimental\n *\n * Dispatch a configured loop by mode. Fails loud (throws `ConfigError`) when no\n * runner is registered for the mode — a routine pointed at an unwired mode is a\n * config bug, not a silent no-op. A runner that throws is captured as\n * `{ ok: false }` so unattended runs record the failure rather than crash.\n */\nexport async function runDelegatedLoop<T = unknown>(\n  mode: DelegatedLoopMode,\n  registry: DelegatedLoopRegistry,\n  options: RunDelegatedLoopOptions = {},\n): Promise<DelegatedLoopResult<T>> {\n  const runner = registry[mode] as DelegatedLoopRunner<T> | undefined\n  if (!runner) {\n    throw new ConfigError(\n      `runDelegatedLoop: no runner registered for mode '${mode}' (registered: ${\n        Object.keys(registry).join(', ') || 'none'\n      })`,\n    )\n  }\n  const now = options.now ?? Date.now\n  const signal = options.signal ?? new AbortController().signal\n  const start = now()\n  try {\n    const output = await runner(signal)\n    return { mode, ok: true, output, durationMs: now() - start }\n  } catch (err) {\n    return {\n      mode,\n      ok: false,\n      error: err instanceof Error ? err.message : String(err),\n      durationMs: now() - start,\n    }\n  }\n}\n\n/** @experimental Options for the local-repo `code` runner over the GENERIC recursive path. */\nexport interface WorktreeLoopRunnerOptions {\n  /** Absolute path to the local git checkout each worktree is cut from. */\n  repoRoot: string\n  /** The instruction handed to every authored harness (composed under each profile's systemPrompt). */\n  taskPrompt: string\n  /** The supervisor-authored harness profiles — one fanout item (one worktree-CLI leaf) each. */\n  harnesses: ReadonlyArray<AuthoredHarness>\n  /** Conserved budget pool bounding the fanout (equal-k holds by construction). */\n  budget: Budget\n  /** Shell command run in each worktree to derive the tests-PASS signal. */\n  testCmd?: string\n  /** Shell command run in each worktree to derive the typecheck-PASS signal. */\n  typecheckCmd?: string\n  /** Which verification signals the deliverable REQUIRES present-and-passing (default none). */\n  require?: ReadonlyArray<'tests' | 'typecheck'>\n  /** Diff-size cap (lines). */\n  maxDiffLines?: number\n  /** Literal path prefixes the patch must not touch (the secret-floor is always on regardless). */\n  forbiddenPaths?: string[]\n  /** Winner-selection strategy among gated candidates. Default `highest-score`. */\n  winnerStrategy?: WinnerStrategy\n  /** Test seams forwarded to the worktree-CLI leaves so the runner drives offline. */\n  runGit?: WorktreeFanoutOptions['runGit']\n  runHarness?: WorktreeFanoutOptions['runHarness']\n  runCommand?: WorktreeFanoutOptions['runCommand']\n}\n\n/**\n * @experimental\n *\n * `code` mode on the GENERIC recursive path: author one `AgentProfile` per harness, run them as a\n * `worktreeFanout` (N `createWorktreeCliExecutor` leaves, each `gateOnDeliverable`) through\n * `runPersonified` on the keystone Supervisor. The sandbox-session counterpart that drives the in-box\n * harness over a `SandboxClient` is `detachedSessionDelegate` (`./mcp/delegates`); here there is no\n * `runLoop` driver, no role-coupled delegate — the harness list is the fanout, the gate is\n * `patchDelivered`,\n * the winner is the shared valid-only selector (NOT `defaultSelectWinner`, whose non-valid fallback\n * would surface an ungated patch). Equal-k holds by the conserved budget pool. Returns the winning\n * patch artifact, or throws when no candidate is delivered (fail loud, never a vacuous done).\n */\nexport function worktreeLoopRunner(\n  options: WorktreeLoopRunnerOptions,\n): DelegatedLoopRunner<WorktreePatchArtifact> {\n  const shape = worktreeFanout<string>({\n    repoRoot: options.repoRoot,\n    taskPrompt: options.taskPrompt,\n    harnesses: options.harnesses,\n    ...(options.testCmd !== undefined ? { testCmd: options.testCmd } : {}),\n    ...(options.typecheckCmd !== undefined ? { typecheckCmd: options.typecheckCmd } : {}),\n    ...(options.require !== undefined ? { require: options.require } : {}),\n    ...(options.maxDiffLines !== undefined ? { maxDiffLines: options.maxDiffLines } : {}),\n    ...(options.forbiddenPaths !== undefined ? { forbiddenPaths: options.forbiddenPaths } : {}),\n    ...(options.winnerStrategy !== undefined ? { winnerStrategy: options.winnerStrategy } : {}),\n    ...(options.runGit ? { runGit: options.runGit } : {}),\n    ...(options.runHarness ? { runHarness: options.runHarness } : {}),\n    ...(options.runCommand ? { runCommand: options.runCommand } : {}),\n  })\n  // The persona's only role here is to carry the fanout shape onto the Supervisor; each item's\n  // executor is BYO (the gated worktree-CLI leaf), so the registry only needs to pass BYO through.\n  const persona = definePersona<WorktreePatchArtifact>({\n    name: 'worktree-coder',\n    root: { profile: { name: 'worktree-coder' }, harness: null },\n    directive: 'deliver a minimal validated patch on a fresh worktree',\n    context: { role: 'coder' },\n    executors: { registry: createExecutorRegistry() },\n  })\n  return async (signal) => {\n    const result = await runPersonified<string, WorktreePatchArtifact>({\n      persona,\n      shape,\n      task: options.taskPrompt,\n      budget: options.budget,\n      signal,\n    })\n    if (result.kind !== 'winner' || result.out.kind !== 'done') {\n      const blockers =\n        result.kind === 'winner' && result.out.kind === 'blocked'\n          ? result.out.blockers.join('; ')\n          : `supervisor settled ${result.kind}`\n      throw new Error(`worktreeLoopRunner: no delivered patch (${blockers})`)\n    }\n    return result.out.deliverable\n  }\n}\n\n/** @experimental A fact rejected at the KB gate — surfaced, never dropped. */\nexport interface VetoedFact {\n  candidate: FactCandidate\n  vetoedBy?: string\n  reason?: string\n}\n\n/** @experimental */\nexport interface ResearchLoopResult {\n  /** Facts that passed the fail-closed gate — safe to write to the KB. */\n  accepted: FactCandidate[]\n  /** Facts the gate vetoed in the final round — escalate, do not silently drop. */\n  vetoed: VetoedFact[]\n  /** Research rounds actually run. */\n  rounds: number\n}\n\n/** @experimental Options for the default `research` runner. */\nexport interface ResearchLoopRunnerOptions {\n  /**\n   * The research engine (the consumer's web/doc searcher + extractor). Called\n   * each round with the prior round's vetoes so it can re-research the gaps.\n   * Returns fact candidates carrying their grounding (`verbatimPassage` +\n   * `sourceText`).\n   */\n  research: (round: number, vetoed: VetoedFact[]) => Promise<FactCandidate[]>\n  /** Gate config (extra judges, self-artifact kinds, …). The floor is always on. */\n  gate?: CreateKbGateOptions\n  /** Max research rounds (correct-on-veto remediation). Default 1. */\n  maxRounds?: number\n}\n\n/**\n * @experimental `research` mode — research-in-a-loop with valid-only KB growth.\n *\n * Each round: research → gate every candidate (fail-closed; passage MUST be in\n * the source) → accept the clean ones → re-research the vetoed ones next round,\n * up to `maxRounds`. Vetoed facts in the final round are RETURNED (escalate,\n * never silently dropped) so the caller audits vs retries.\n */\nexport function researchLoopRunner(\n  o: ResearchLoopRunnerOptions,\n): DelegatedLoopRunner<ResearchLoopResult> {\n  const gate = createKbGate(o.gate)\n  const maxRounds = Math.max(1, Math.trunc(o.maxRounds ?? 1))\n  return async (signal) => {\n    const accepted: FactCandidate[] = []\n    let vetoed: VetoedFact[] = []\n    let rounds = 0\n    for (let round = 0; round < maxRounds; round += 1) {\n      if (signal.aborted) break\n      rounds += 1\n      const candidates = await o.research(round, vetoed)\n      if (candidates.length === 0) break\n      vetoed = []\n      for (const c of candidates) {\n        const v = await gate(c)\n        if (v.accepted) accepted.push(c)\n        else vetoed.push({ candidate: c, vetoedBy: v.vetoedBy, reason: v.reason })\n      }\n      if (vetoed.length === 0) break\n    }\n    return { accepted, vetoed, rounds }\n  }\n}\n\n/** @experimental `self-improve` mode — agent-eval's one-call closed loop (held-out gated). */\nexport function selfImproveLoopRunner<TScenario extends Scenario, TArtifact>(\n  options: SelfImproveOptions<TScenario, TArtifact>,\n): DelegatedLoopRunner<SelfImproveResult<TScenario, TArtifact>> {\n  return async () => selfImprove<TScenario, TArtifact>(options)\n}\n\n/** @experimental `audit` mode — analyst loop over captured trace/run data. */\nexport function auditLoopRunner<TProposal = unknown, TEdit = unknown>(\n  options: RunAnalystLoopOpts,\n): DelegatedLoopRunner<RunAnalystLoopResult<TProposal, TEdit>> {\n  return async () => runAnalystLoop<TProposal, TEdit>(options)\n}\n","#!/usr/bin/env node\n/**\n * @experimental\n *\n * `agent-runtime-loop` — the schedulable entrypoint for the configured\n * delegated loop-runner. A cron job / routine / Makefile target invokes:\n *\n *   agent-runtime-loop --mode research --config ./loops.config.js\n *\n * The config module wires the registry (with full access to env / creds —\n * which is why the deps live there, not in this generic bin). It must default-\n * export a `DelegatedLoopRegistry`, or a `() => DelegatedLoopRegistry | Promise<…>`.\n * The bin runs the selected mode, prints the `DelegatedLoopResult` as JSON, and\n * exits 0 on `ok`, 1 on a recorded failure, 2 on a usage/config error.\n */\n\nimport {\n  DELEGATED_LOOP_MODES,\n  type DelegatedLoopMode,\n  type DelegatedLoopRegistry,\n  type DelegatedLoopResult,\n  isDelegatedLoopMode,\n  runDelegatedLoop,\n} from './loop-runner'\n\n/** @experimental Parsed CLI invocation. */\nexport interface LoopRunnerCliArgs {\n  mode: string\n  /** Loads the registry — the bin wires this from `--config`; tests inject a stub. */\n  loadRegistry: () => Promise<DelegatedLoopRegistry> | DelegatedLoopRegistry\n  now?: () => number\n}\n\n/** @experimental */\nexport interface LoopRunnerCliResult {\n  exitCode: number\n  result?: DelegatedLoopResult\n  error?: string\n}\n\n/**\n * @experimental\n *\n * Pure CLI core (no process / argv / IO) so it's unit-testable: validate the\n * mode, load the registry, dispatch, map to an exit code (0 ok / 1 failed /\n * 2 usage). Exported for embedding in custom runners + tests.\n */\nexport async function runLoopRunnerCli(args: LoopRunnerCliArgs): Promise<LoopRunnerCliResult> {\n  if (!isDelegatedLoopMode(args.mode)) {\n    return {\n      exitCode: 2,\n      error: `unknown mode '${args.mode}' (expected one of: ${DELEGATED_LOOP_MODES.join(', ')})`,\n    }\n  }\n  let registry: DelegatedLoopRegistry\n  try {\n    registry = await args.loadRegistry()\n  } catch (err) {\n    return { exitCode: 2, error: `failed to load registry: ${errMsg(err)}` }\n  }\n  if (!registry[args.mode]) {\n    return {\n      exitCode: 2,\n      error: `config registers no runner for mode '${args.mode}' (registered: ${\n        Object.keys(registry).join(', ') || 'none'\n      })`,\n    }\n  }\n  // runDelegatedLoop throws only on a missing runner (guarded above); a failing\n  // engine is captured as { ok: false } → exit 1, not a crash.\n  const result = await runDelegatedLoop(args.mode as DelegatedLoopMode, registry, {\n    ...(args.now ? { now: args.now } : {}),\n  })\n  return { exitCode: result.ok ? 0 : 1, result }\n}\n\n/** Parse `--mode X --config Y` from an argv tail (`process.argv.slice(2)`). */\nexport function parseLoopRunnerArgv(argv: string[]): { mode?: string; config?: string } {\n  const out: { mode?: string; config?: string } = {}\n  for (let i = 0; i < argv.length; i += 1) {\n    const a = argv[i]\n    if (a === '--mode') out.mode = argv[++i]\n    else if (a === '--config') out.config = argv[++i]\n    else if (a?.startsWith('--mode=')) out.mode = a.slice('--mode='.length)\n    else if (a?.startsWith('--config=')) out.config = a.slice('--config='.length)\n  }\n  return out\n}\n\n/** Normalize a config module's default export → a registry. */\nfunction resolveRegistry(mod: unknown): DelegatedLoopRegistry {\n  const def = (mod as { default?: unknown })?.default ?? mod\n  const value = typeof def === 'function' ? (def as () => unknown)() : def\n  return value as DelegatedLoopRegistry\n}\n\nfunction errMsg(err: unknown): string {\n  return err instanceof Error ? err.message : String(err)\n}\n\n/** The argv → IO → exit shell. Kept thin; logic lives in `runLoopRunnerCli`. */\nasync function main(): Promise<void> {\n  const { mode, config } = parseLoopRunnerArgv(process.argv.slice(2))\n  if (!mode || !config) {\n    process.stderr.write(\n      'usage: agent-runtime-loop --mode <mode> --config <module>\\n' +\n        `  modes: ${DELEGATED_LOOP_MODES.join(' | ')}\\n` +\n        '  config: a JS/TS module default-exporting a DelegatedLoopRegistry (or a factory)\\n',\n    )\n    process.exit(2)\n  }\n  const { pathToFileURL } = await import('node:url')\n  const { resolve } = await import('node:path')\n  const cli = await runLoopRunnerCli({\n    mode,\n    loadRegistry: async () => resolveRegistry(await import(pathToFileURL(resolve(config)).href)),\n  })\n  process.stdout.write(`${JSON.stringify(cli.result ?? { error: cli.error }, null, 2)}\\n`)\n  if (cli.error) process.stderr.write(`${cli.error}\\n`)\n  process.exit(cli.exitCode)\n}\n\n// Run only when executed as the bin — never when imported for the testable\n// core, and never when bundled into a runtime that has no `process.argv`\n// (e.g. Cloudflare Workers, where `process` is a shim without `argv`). Reading\n// `process.argv[1]` directly would throw at module load there; `process.argv?.`\n// keeps the guard a no-op instead of crashing the Worker on startup.\nconst invokedScript = typeof process !== 'undefined' ? process.argv?.[1] : undefined\nif (invokedScript && /loop-runner-bin\\.(js|ts|mjs)$/.test(invokedScript)) {\n  void main()\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;AAuBA;AAAA,EAGE;AAAA,OACK;AAkBA,IAAM,uBAAuB,CAAC,QAAQ,UAAU,YAAY,SAAS,cAAc;AAMnF,SAAS,oBAAoB,OAA4C;AAC9E,SAAO,OAAO,UAAU,YAAa,qBAA2C,SAAS,KAAK;AAChG;AAmCA,eAAsB,iBACpB,MACA,UACA,UAAmC,CAAC,GACH;AACjC,QAAM,SAAS,SAAS,IAAI;AAC5B,MAAI,CAAC,QAAQ;AACX,UAAM,IAAI;AAAA,MACR,oDAAoD,IAAI,kBACtD,OAAO,KAAK,QAAQ,EAAE,KAAK,IAAI,KAAK,MACtC;AAAA,IACF;AAAA,EACF;AACA,QAAM,MAAM,QAAQ,OAAO,KAAK;AAChC,QAAM,SAAS,QAAQ,UAAU,IAAI,gBAAgB,EAAE;AACvD,QAAM,QAAQ,IAAI;AAClB,MAAI;AACF,UAAM,SAAS,MAAM,OAAO,MAAM;AAClC,WAAO,EAAE,MAAM,IAAI,MAAM,QAAQ,YAAY,IAAI,IAAI,MAAM;AAAA,EAC7D,SAAS,KAAK;AACZ,WAAO;AAAA,MACL;AAAA,MACA,IAAI;AAAA,MACJ,OAAO,eAAe,QAAQ,IAAI,UAAU,OAAO,GAAG;AAAA,MACtD,YAAY,IAAI,IAAI;AAAA,IACtB;AAAA,EACF;AACF;AA2CO,SAAS,mBACd,SAC4C;AAC5C,QAAM,QAAQ,eAAuB;AAAA,IACnC,UAAU,QAAQ;AAAA,IAClB,YAAY,QAAQ;AAAA,IACpB,WAAW,QAAQ;AAAA,IACnB,GAAI,QAAQ,YAAY,SAAY,EAAE,SAAS,QAAQ,QAAQ,IAAI,CAAC;AAAA,IACpE,GAAI,QAAQ,iBAAiB,SAAY,EAAE,cAAc,QAAQ,aAAa,IAAI,CAAC;AAAA,IACnF,GAAI,QAAQ,YAAY,SAAY,EAAE,SAAS,QAAQ,QAAQ,IAAI,CAAC;AAAA,IACpE,GAAI,QAAQ,iBAAiB,SAAY,EAAE,cAAc,QAAQ,aAAa,IAAI,CAAC;AAAA,IACnF,GAAI,QAAQ,mBAAmB,SAAY,EAAE,gBAAgB,QAAQ,eAAe,IAAI,CAAC;AAAA,IACzF,GAAI,QAAQ,mBAAmB,SAAY,EAAE,gBAAgB,QAAQ,eAAe,IAAI,CAAC;AAAA,IACzF,GAAI,QAAQ,SAAS,EAAE,QAAQ,QAAQ,OAAO,IAAI,CAAC;AAAA,IACnD,GAAI,QAAQ,aAAa,EAAE,YAAY,QAAQ,WAAW,IAAI,CAAC;AAAA,IAC/D,GAAI,QAAQ,aAAa,EAAE,YAAY,QAAQ,WAAW,IAAI,CAAC;AAAA,EACjE,CAAC;AAGD,QAAM,UAAU,cAAqC;AAAA,IACnD,MAAM;AAAA,IACN,MAAM,EAAE,SAAS,EAAE,MAAM,iBAAiB,GAAG,SAAS,KAAK;AAAA,IAC3D,WAAW;AAAA,IACX,SAAS,EAAE,MAAM,QAAQ;AAAA,IACzB,WAAW,EAAE,UAAU,uBAAuB,EAAE;AAAA,EAClD,CAAC;AACD,SAAO,OAAO,WAAW;AACvB,UAAM,SAAS,MAAM,eAA8C;AAAA,MACjE;AAAA,MACA;AAAA,MACA,MAAM,QAAQ;AAAA,MACd,QAAQ,QAAQ;AAAA,MAChB;AAAA,IACF,CAAC;AACD,QAAI,OAAO,SAAS,YAAY,OAAO,IAAI,SAAS,QAAQ;AAC1D,YAAM,WACJ,OAAO,SAAS,YAAY,OAAO,IAAI,SAAS,YAC5C,OAAO,IAAI,SAAS,KAAK,IAAI,IAC7B,sBAAsB,OAAO,IAAI;AACvC,YAAM,IAAI,MAAM,2CAA2C,QAAQ,GAAG;AAAA,IACxE;AACA,WAAO,OAAO,IAAI;AAAA,EACpB;AACF;AA0CO,SAAS,mBACd,GACyC;AACzC,QAAM,OAAO,aAAa,EAAE,IAAI;AAChC,QAAM,YAAY,KAAK,IAAI,GAAG,KAAK,MAAM,EAAE,aAAa,CAAC,CAAC;AAC1D,SAAO,OAAO,WAAW;AACvB,UAAM,WAA4B,CAAC;AACnC,QAAI,SAAuB,CAAC;AAC5B,QAAI,SAAS;AACb,aAAS,QAAQ,GAAG,QAAQ,WAAW,SAAS,GAAG;AACjD,UAAI,OAAO,QAAS;AACpB,gBAAU;AACV,YAAM,aAAa,MAAM,EAAE,SAAS,OAAO,MAAM;AACjD,UAAI,WAAW,WAAW,EAAG;AAC7B,eAAS,CAAC;AACV,iBAAW,KAAK,YAAY;AAC1B,cAAM,IAAI,MAAM,KAAK,CAAC;AACtB,YAAI,EAAE,SAAU,UAAS,KAAK,CAAC;AAAA,YAC1B,QAAO,KAAK,EAAE,WAAW,GAAG,UAAU,EAAE,UAAU,QAAQ,EAAE,OAAO,CAAC;AAAA,MAC3E;AACA,UAAI,OAAO,WAAW,EAAG;AAAA,IAC3B;AACA,WAAO,EAAE,UAAU,QAAQ,OAAO;AAAA,EACpC;AACF;AAGO,SAAS,sBACd,SAC8D;AAC9D,SAAO,YAAY,YAAkC,OAAO;AAC9D;AAGO,SAAS,gBACd,SAC6D;AAC7D,SAAO,YAAY,eAAiC,OAAO;AAC7D;;;AC1OA,eAAsB,iBAAiB,MAAuD;AAC5F,MAAI,CAAC,oBAAoB,KAAK,IAAI,GAAG;AACnC,WAAO;AAAA,MACL,UAAU;AAAA,MACV,OAAO,iBAAiB,KAAK,IAAI,uBAAuB,qBAAqB,KAAK,IAAI,CAAC;AAAA,IACzF;AAAA,EACF;AACA,MAAI;AACJ,MAAI;AACF,eAAW,MAAM,KAAK,aAAa;AAAA,EACrC,SAAS,KAAK;AACZ,WAAO,EAAE,UAAU,GAAG,OAAO,4BAA4B,OAAO,GAAG,CAAC,GAAG;AAAA,EACzE;AACA,MAAI,CAAC,SAAS,KAAK,IAAI,GAAG;AACxB,WAAO;AAAA,MACL,UAAU;AAAA,MACV,OAAO,wCAAwC,KAAK,IAAI,kBACtD,OAAO,KAAK,QAAQ,EAAE,KAAK,IAAI,KAAK,MACtC;AAAA,IACF;AAAA,EACF;AAGA,QAAM,SAAS,MAAM,iBAAiB,KAAK,MAA2B,UAAU;AAAA,IAC9E,GAAI,KAAK,MAAM,EAAE,KAAK,KAAK,IAAI,IAAI,CAAC;AAAA,EACtC,CAAC;AACD,SAAO,EAAE,UAAU,OAAO,KAAK,IAAI,GAAG,OAAO;AAC/C;AAGO,SAAS,oBAAoB,MAAoD;AACtF,QAAM,MAA0C,CAAC;AACjD,WAAS,IAAI,GAAG,IAAI,KAAK,QAAQ,KAAK,GAAG;AACvC,UAAM,IAAI,KAAK,CAAC;AAChB,QAAI,MAAM,SAAU,KAAI,OAAO,KAAK,EAAE,CAAC;AAAA,aAC9B,MAAM,WAAY,KAAI,SAAS,KAAK,EAAE,CAAC;AAAA,aACvC,GAAG,WAAW,SAAS,EAAG,KAAI,OAAO,EAAE,MAAM,UAAU,MAAM;AAAA,aAC7D,GAAG,WAAW,WAAW,EAAG,KAAI,SAAS,EAAE,MAAM,YAAY,MAAM;AAAA,EAC9E;AACA,SAAO;AACT;AAGA,SAAS,gBAAgB,KAAqC;AAC5D,QAAM,MAAO,KAA+B,WAAW;AACvD,QAAM,QAAQ,OAAO,QAAQ,aAAc,IAAsB,IAAI;AACrE,SAAO;AACT;AAEA,SAAS,OAAO,KAAsB;AACpC,SAAO,eAAe,QAAQ,IAAI,UAAU,OAAO,GAAG;AACxD;AAGA,eAAe,OAAsB;AACnC,QAAM,EAAE,MAAM,OAAO,IAAI,oBAAoB,QAAQ,KAAK,MAAM,CAAC,CAAC;AAClE,MAAI,CAAC,QAAQ,CAAC,QAAQ;AACpB,YAAQ,OAAO;AAAA,MACb;AAAA,WACc,qBAAqB,KAAK,KAAK,CAAC;AAAA;AAAA;AAAA,IAEhD;AACA,YAAQ,KAAK,CAAC;AAAA,EAChB;AACA,QAAM,EAAE,cAAc,IAAI,MAAM,OAAO,KAAU;AACjD,QAAM,EAAE,QAAQ,IAAI,MAAM,OAAO,MAAW;AAC5C,QAAM,MAAM,MAAM,iBAAiB;AAAA,IACjC;AAAA,IACA,cAAc,YAAY,gBAAgB,MAAM,OAAO,cAAc,QAAQ,MAAM,CAAC,EAAE,KAAK;AAAA,EAC7F,CAAC;AACD,UAAQ,OAAO,MAAM,GAAG,KAAK,UAAU,IAAI,UAAU,EAAE,OAAO,IAAI,MAAM,GAAG,MAAM,CAAC,CAAC;AAAA,CAAI;AACvF,MAAI,IAAI,MAAO,SAAQ,OAAO,MAAM,GAAG,IAAI,KAAK;AAAA,CAAI;AACpD,UAAQ,KAAK,IAAI,QAAQ;AAC3B;AAOA,IAAM,gBAAgB,OAAO,YAAY,cAAc,QAAQ,OAAO,CAAC,IAAI;AAC3E,IAAI,iBAAiB,gCAAgC,KAAK,aAAa,GAAG;AACxE,OAAK,KAAK;AACZ;","names":[]}

package/dist/chunk-UZ5SODU7.js

@@ -0,0 +1,29 @@
+// src/profiles/coder.ts
+var DEFAULT_MAX_DIFF_LINES = 400;
+function coderTaskToPrompt(task) {
+  const base = task.baseBranch ?? "main";
+  const testCmd = task.testCmd ?? "pnpm test --run";
+  const typecheckCmd = task.typecheckCmd ?? "pnpm typecheck";
+  const maxDiff = task.maxDiffLines ?? DEFAULT_MAX_DIFF_LINES;
+  const forbidden = task.forbiddenPaths?.length ? task.forbiddenPaths.join(", ") : "(none)";
+  const context = task.contextFiles?.length ? task.contextFiles.map((f) => `  - ${f}`).join("\n") : "  (none)";
+  return [
+    `Goal: ${task.goal}`,
+    `Repo: ${task.repoRoot}`,
+    `Base branch: ${base}`,
+    `Run tests with: ${testCmd}`,
+    `Run typecheck with: ${typecheckCmd}`,
+    `Forbidden paths: ${forbidden}`,
+    `Max diff lines: ${maxDiff}`,
+    "Context files:",
+    context,
+    "",
+    "Produce a minimal patch on a fresh branch. Run tests and typecheck before",
+    "returning. Emit the final JSON result block exactly as instructed."
+  ].join("\n");
+}
+
+export {
+  coderTaskToPrompt
+};
+//# sourceMappingURL=chunk-UZ5SODU7.js.map

package/dist/chunk-UZ5SODU7.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/profiles/coder.ts"],"sourcesContent":["/**\n * @experimental\n *\n * `CoderTask` + `coderTaskToPrompt` — the per-task DATA + pure formatter for code-modification tasks\n * (§1.5: the system authors profiles; there is no hardcoded coder profile constant). A domain\n * customizes the worker by authoring its own `AgentProfile` and handing it to a leaf executor\n * (`createWorktreeCliExecutor`) or a fanout (`worktreeFanout`); \"is it delivered\" is a\n * `DeliverableSpec` (`patchDelivered`), not a bundled validator. This formatter renders a `CoderTask`\n * into the per-task instruction that profile receives.\n */\n\nconst DEFAULT_MAX_DIFF_LINES = 400\n\n/** @experimental The per-task inputs `coderTaskToPrompt` renders + the worktree gate enforces. */\nexport interface CoderTask {\n  /** What the agent must accomplish. Free-form prose. */\n  goal: string\n  /** Absolute path inside the sandbox where the repo lives. */\n  repoRoot: string\n  /** Default `main`. The branch the agent diffs against. */\n  baseBranch?: string\n  /** Default `pnpm test --run`. */\n  testCmd?: string\n  /** Default `pnpm typecheck`. */\n  typecheckCmd?: string\n  /** Files the agent may inspect for context. Surfaced verbatim in the prompt. */\n  contextFiles?: string[]\n  /**\n   * Paths the agent must not touch. The mechanical gate hard-fails on any match.\n   * Use glob-free literal path prefixes for unambiguous enforcement.\n   */\n  forbiddenPaths?: string[]\n  /** Default 400. Hard cap; the gate hard-fails when exceeded. */\n  maxDiffLines?: number\n}\n\n/** @experimental Render a `CoderTask` into the per-task instruction handed to the coder profile. */\nexport function coderTaskToPrompt(task: CoderTask): string {\n  const base = task.baseBranch ?? 'main'\n  const testCmd = task.testCmd ?? 'pnpm test --run'\n  const typecheckCmd = task.typecheckCmd ?? 'pnpm typecheck'\n  const maxDiff = task.maxDiffLines ?? DEFAULT_MAX_DIFF_LINES\n  const forbidden = task.forbiddenPaths?.length ? task.forbiddenPaths.join(', ') : '(none)'\n  const context = task.contextFiles?.length\n    ? task.contextFiles.map((f) => `  - ${f}`).join('\\n')\n    : '  (none)'\n  return [\n    `Goal: ${task.goal}`,\n    `Repo: ${task.repoRoot}`,\n    `Base branch: ${base}`,\n    `Run tests with: ${testCmd}`,\n    `Run typecheck with: ${typecheckCmd}`,\n    `Forbidden paths: ${forbidden}`,\n    `Max diff lines: ${maxDiff}`,\n    'Context files:',\n    context,\n    '',\n    'Produce a minimal patch on a fresh branch. Run tests and typecheck before',\n    'returning. Emit the final JSON result block exactly as instructed.',\n  ].join('\\n')\n}\n"],"mappings":";AAWA,IAAM,yBAAyB;AA0BxB,SAAS,kBAAkB,MAAyB;AACzD,QAAM,OAAO,KAAK,cAAc;AAChC,QAAM,UAAU,KAAK,WAAW;AAChC,QAAM,eAAe,KAAK,gBAAgB;AAC1C,QAAM,UAAU,KAAK,gBAAgB;AACrC,QAAM,YAAY,KAAK,gBAAgB,SAAS,KAAK,eAAe,KAAK,IAAI,IAAI;AACjF,QAAM,UAAU,KAAK,cAAc,SAC/B,KAAK,aAAa,IAAI,CAAC,MAAM,OAAO,CAAC,EAAE,EAAE,KAAK,IAAI,IAClD;AACJ,SAAO;AAAA,IACL,SAAS,KAAK,IAAI;AAAA,IAClB,SAAS,KAAK,QAAQ;AAAA,IACtB,gBAAgB,IAAI;AAAA,IACpB,mBAAmB,OAAO;AAAA,IAC1B,uBAAuB,YAAY;AAAA,IACnC,oBAAoB,SAAS;AAAA,IAC7B,mBAAmB,OAAO;AAAA,IAC1B;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,EACF,EAAE,KAAK,IAAI;AACb;","names":[]}