@tangle-network/agent-runtime 0.53.0 → 0.55.0

package/dist/chunk-A73RADPB.js

@@ -0,0 +1,281 @@
+import {
+  coderProfile,
+  multiHarnessCoderFanout
+} from "./chunk-KADIJAD4.js";
+import {
+  composeLoopTraceEmitters,
+  detachedTurnEvents,
+  formatDetachedSessionRef,
+  parseDetachedSessionRef,
+  runDetachedTurn,
+  runLoop
+} from "./chunk-JTH2FPCK.js";
+
+// src/mcp/executor.ts
+function createSiblingSandboxExecutor(options) {
+  const underlying = options.client;
+  const client = {
+    create(opts) {
+      return underlying.create(opts);
+    },
+    describePlacement(box) {
+      return { kind: "sibling", sandboxId: readId(box) };
+    }
+  };
+  return {
+    client,
+    placement: "sibling",
+    describe() {
+      return "sibling-sandbox (each delegation = fresh sandbox via client.create)";
+    }
+  };
+}
+function createFleetWorkspaceExecutor(options) {
+  const fleet = options.fleet;
+  const exclude = new Set(options.excludeMachineIds ?? []);
+  let callIndex = 0;
+  const placementBySandboxId = /* @__PURE__ */ new Map();
+  const client = {
+    async create() {
+      const ids = fleet.ids.filter((id) => !exclude.has(id));
+      if (ids.length === 0) {
+        throw new Error(
+          `agent-runtime: fleet ${fleet.fleetId} has no eligible worker machines (ids=[${fleet.ids.join(",")}], excluded=[${[...exclude].join(",")}])`
+        );
+      }
+      const selector = options.selectMachine;
+      const machineId = selector ? selector({ callIndex, ids }) : ids[callIndex % ids.length];
+      callIndex += 1;
+      if (typeof machineId !== "string" || machineId.length === 0) {
+        throw new Error("agent-runtime: fleet executor selectMachine returned an empty machine id");
+      }
+      const box = await fleet.sandbox(machineId);
+      const sandboxId = readId(box);
+      if (sandboxId) placementBySandboxId.set(sandboxId, { machineId });
+      return box;
+    },
+    describePlacement(box) {
+      const sandboxId = readId(box);
+      const recorded = sandboxId ? placementBySandboxId.get(sandboxId) : void 0;
+      return {
+        kind: "fleet",
+        sandboxId,
+        fleetId: fleet.fleetId,
+        machineId: recorded?.machineId
+      };
+    }
+  };
+  return {
+    client,
+    placement: "fleet",
+    describe() {
+      const excluded = exclude.size > 0 ? ` (excluded=[${[...exclude].join(",")}])` : "";
+      return `fleet-workspace (fleetId=${fleet.fleetId}, machines=[${fleet.ids.join(",")}]${excluded})`;
+    }
+  };
+}
+function readId(box) {
+  const raw = box.id;
+  return typeof raw === "string" && raw.length > 0 ? raw : void 0;
+}
+
+// src/mcp/delegates.ts
+function createDefaultCoderDelegate(options) {
+  const executor = resolveExecutor(options);
+  const sandboxClient = executor.client;
+  const fanoutHarnesses = options.fanoutHarnesses;
+  const maxConcurrency = options.maxConcurrency ?? 4;
+  const traceEmitter = options.traceEmitter;
+  return async (args, ctx) => {
+    const task = coderTaskFromArgs(args);
+    const variants = Math.max(1, Math.trunc(args.variants ?? 1));
+    const loopEmitter = composeLoopTraceEmitters(traceEmitter, ctx.traceEmitter);
+    ctx.report({ iteration: 0, phase: "starting" });
+    if (variants <= 1) {
+      const { agentRunSpec, output, validator } = coderProfile({
+        task,
+        ...options.harness ? { harness: options.harness } : {},
+        ...options.model ? { model: options.model } : {}
+      });
+      if (ctx.detachedSessionRef !== void 0 && ctx.updateDetachedSessionRef) {
+        const { sessionId } = parseDetachedSessionRef(ctx.detachedSessionRef);
+        const rebind = ctx.updateDetachedSessionRef;
+        const turn = await runDetachedTurn({
+          client: sandboxClient,
+          spec: agentRunSpec,
+          prompt: agentRunSpec.taskToPrompt(task),
+          sessionId,
+          bindSandbox: (sandboxId) => rebind(formatDetachedSessionRef({ sandboxId, sessionId })),
+          signal: ctx.signal,
+          report: ctx.report,
+          ...loopEmitter ? { traceEmitter: loopEmitter } : {},
+          ...executor.placement === "fleet" ? { placement: "fleet" } : {},
+          ...options.detachedTickIntervalMs !== void 0 ? { tickIntervalMs: options.detachedTickIntervalMs } : {},
+          ...options.detachedWallCapMs !== void 0 ? { wallCapMs: options.detachedWallCapMs } : {}
+        });
+        const chosen3 = await settleDetachedCoderTurn(turn, {
+          task,
+          sessionId,
+          signal: ctx.signal,
+          ...options.harness ? { harness: options.harness } : {},
+          ...options.model ? { model: options.model } : {},
+          ...options.reviewer ? { reviewer: options.reviewer } : {}
+        });
+        ctx.report({ iteration: 1, phase: "completed" });
+        return chosen3;
+      }
+      const result2 = await runLoop({
+        driver: singleShotDriver,
+        agentRun: agentRunSpec,
+        output,
+        validator,
+        task,
+        ctx: {
+          sandboxClient,
+          signal: ctx.signal,
+          ...loopEmitter ? { traceEmitter: loopEmitter } : {}
+        },
+        maxIterations: 1,
+        maxConcurrency
+      });
+      const chosen2 = await pickCoderWinner({
+        iterations: result2.iterations,
+        reviewer: options.reviewer,
+        selection: options.winnerSelection ?? "highest-score",
+        task,
+        signal: ctx.signal
+      });
+      if (!chosen2) throw new Error(noWinnerMessage(options.reviewer));
+      ctx.report({ iteration: 1, phase: "completed" });
+      return chosen2;
+    }
+    const fanout = multiHarnessCoderFanout({
+      ...fanoutHarnesses && fanoutHarnesses.length > 0 ? { harnesses: fanoutHarnesses.slice(0, variants) } : {},
+      ...options.fanoutModels ? { models: options.fanoutModels.slice(0, variants) } : {}
+    });
+    const agentRuns = fanout.agentRuns.slice(0, variants);
+    const result = await runLoop({
+      driver: fanout.driver,
+      agentRuns,
+      output: fanout.output,
+      validator: fanout.validator,
+      task,
+      ctx: {
+        sandboxClient,
+        signal: ctx.signal,
+        ...loopEmitter ? { traceEmitter: loopEmitter } : {}
+      },
+      maxIterations: variants,
+      maxConcurrency: Math.min(maxConcurrency, variants)
+    });
+    const chosen = await pickCoderWinner({
+      iterations: result.iterations,
+      reviewer: options.reviewer,
+      selection: options.winnerSelection ?? "highest-score",
+      task,
+      signal: ctx.signal
+    });
+    if (!chosen) throw new Error(noWinnerMessage(options.reviewer));
+    ctx.report({ iteration: agentRuns.length, phase: "completed" });
+    return chosen;
+  };
+}
+async function pickCoderWinner(args) {
+  const valid = [];
+  for (const iter of args.iterations) {
+    if (iter.output === void 0 || iter.error || iter.verdict?.valid !== true) continue;
+    valid.push({
+      index: iter.index,
+      output: iter.output,
+      score: iter.verdict.score ?? 0,
+      readiness: iter.verdict.score ?? 0
+    });
+  }
+  if (valid.length === 0) return void 0;
+  let eligible = valid;
+  if (args.reviewer) {
+    eligible = [];
+    for (const c of valid) {
+      const review = await args.reviewer(c.output, args.task, { signal: args.signal });
+      if (review.approved) eligible.push({ ...c, readiness: review.readiness });
+    }
+    if (eligible.length === 0) return void 0;
+  }
+  return selectCoderCandidate(eligible, args.selection).output;
+}
+function selectCoderCandidate(candidates, selection) {
+  const diffLines = (c) => c.output.diffStats.insertions + c.output.diffStats.deletions;
+  const sorted = [...candidates].sort((a, b) => {
+    switch (selection) {
+      case "smallest-diff":
+        return diffLines(a) - diffLines(b) || a.index - b.index;
+      case "highest-readiness":
+        return b.readiness - a.readiness || a.index - b.index;
+      case "first-approved":
+        return a.index - b.index;
+      default:
+        return b.score - a.score || a.index - b.index;
+    }
+  });
+  return sorted[0];
+}
+function noWinnerMessage(reviewer) {
+  return reviewer ? "coder delegate: no candidate passed validation + review" : "coder delegate: no candidate passed validation";
+}
+function coderTaskFromArgs(args) {
+  return {
+    goal: buildCoderGoal(args),
+    repoRoot: args.repoRoot,
+    testCmd: args.config?.testCmd,
+    typecheckCmd: args.config?.typecheckCmd,
+    forbiddenPaths: args.config?.forbiddenPaths,
+    maxDiffLines: args.config?.maxDiffLines
+  };
+}
+async function settleDetachedCoderTurn(turn, options) {
+  const { output, validator } = coderProfile({
+    task: options.task,
+    ...options.harness ? { harness: options.harness } : {},
+    ...options.model ? { model: options.model } : {}
+  });
+  const parsed = output.parse(detachedTurnEvents(options.sessionId, turn));
+  const verdict = await validator.validate(parsed, { iteration: 0, signal: options.signal });
+  if (verdict.valid !== true) throw new Error(noWinnerMessage(options.reviewer));
+  if (options.reviewer) {
+    const review = await options.reviewer(parsed, options.task, { signal: options.signal });
+    if (!review.approved) throw new Error(noWinnerMessage(options.reviewer));
+  }
+  return parsed;
+}
+function buildCoderGoal(args) {
+  if (!args.contextHint) return args.goal;
+  return [args.goal, "", "## Context", args.contextHint].join("\n");
+}
+function resolveExecutor(options) {
+  if (options.executor && options.sandboxClient) {
+    throw new Error("createDefaultCoderDelegate: pass exactly one of `executor` or `sandboxClient`");
+  }
+  if (options.executor) return options.executor;
+  if (options.sandboxClient) {
+    return createSiblingSandboxExecutor({ client: options.sandboxClient });
+  }
+  throw new Error("createDefaultCoderDelegate: `executor` or `sandboxClient` is required");
+}
+var singleShotDriver = {
+  name: "mcp-single-shot",
+  async plan(task, history) {
+    return history.length === 0 ? [task] : [];
+  },
+  decide(history) {
+    return history.length > 0 ? "pick-winner" : "fail";
+  }
+};
+
+export {
+  createSiblingSandboxExecutor,
+  createFleetWorkspaceExecutor,
+  createDefaultCoderDelegate,
+  coderTaskFromArgs,
+  settleDetachedCoderTurn
+};
+//# sourceMappingURL=chunk-A73RADPB.js.map

package/dist/chunk-A73RADPB.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/mcp/executor.ts","../src/mcp/delegates.ts"],"sourcesContent":["/**\n * @experimental\n *\n * Delegation executors — the layer between MCP delegates and the sandbox\n * substrate. Each executor exposes a {@link SandboxClient} the kernel\n * consumes plus a placement tag so the trace pipeline can correlate workers\n * with their physical placement.\n *\n * Two implementations ship in-box:\n *\n * - {@link createSiblingSandboxExecutor} — every delegation spawns a fresh\n *   sandbox sibling to the caller. Default when the MCP server runs as a\n *   standalone CLI mounted outside a fleet.\n *\n * - {@link createFleetWorkspaceExecutor} — delegations dispatch onto machines\n *   in the caller's existing fleet so worker diffs land directly on the\n *   caller's filesystem (the fleet's shared workspace). Selected when the\n *   parent sandbox passes `TANGLE_FLEET_ID` into the MCP server's env.\n */\n\nimport type { CreateSandboxOptions, SandboxInstance } from '@tangle-network/sandbox'\nimport type { LoopSandboxPlacement, SandboxClient } from '../runtime'\n\n/** @experimental */\nexport interface DelegationExecutor {\n  /** Sandbox client the kernel calls. Returned with `describePlacement` set. */\n  readonly client: SandboxClient\n  /** Best-effort one-liner used in stderr boot logs and diagnostics. */\n  describe(): string\n  /**\n   * Where delegated work physically runs. `sibling` and `fleet` placements are\n   * session-backed (boxes expose `driveTurn`, so detached dispatch + resume\n   * apply); `in-process` spawns local harness CLIs with no sandbox session to\n   * detach. Optional so consumer-implemented executors stay source-compatible;\n   * absent means \"unknown\" and detached dispatch is not enabled for it.\n   */\n  readonly placement?: 'sibling' | 'fleet' | 'in-process'\n}\n\n/** @experimental */\nexport interface SiblingSandboxExecutorOptions {\n  client: SandboxClient\n}\n\n/**\n * Wrap a raw sandbox SDK client so the kernel emits\n * `loop.iteration.dispatch` events with `{ placement: 'sibling', sandboxId }`.\n *\n * The returned client `.create()` delegates to the underlying client; the\n * only added behavior is a `describePlacement` tag the kernel reads.\n *\n * @experimental\n */\nexport function createSiblingSandboxExecutor(\n  options: SiblingSandboxExecutorOptions,\n): DelegationExecutor {\n  const underlying = options.client\n  const client: SandboxClient = {\n    create(opts?: CreateSandboxOptions): Promise<SandboxInstance> {\n      return underlying.create(opts)\n    },\n    describePlacement(box: SandboxInstance): LoopSandboxPlacement {\n      return { kind: 'sibling', sandboxId: readId(box) }\n    },\n  }\n  return {\n    client,\n    placement: 'sibling',\n    describe(): string {\n      return 'sibling-sandbox (each delegation = fresh sandbox via client.create)'\n    },\n  }\n}\n\n/**\n * Minimal `SandboxFleet` surface the fleet executor calls. Declared\n * structurally so tests can pass an in-memory stub without instantiating the\n * sandbox SDK.\n *\n * @experimental\n */\nexport interface FleetHandle {\n  readonly fleetId: string\n  /** Machine ids in dispatch-eligible order. The executor round-robins. */\n  readonly ids: ReadonlyArray<string>\n  /** Resolve a machine id to its `SandboxInstance` — that machine is mounted\n   * on the fleet's shared workspace, so any diff the worker writes lands on\n   * every other fleet machine's filesystem too. */\n  sandbox(machineId: string): Promise<SandboxInstance>\n}\n\n/** @experimental */\nexport interface FleetWorkspaceExecutorOptions {\n  fleet: FleetHandle\n  /**\n   * Override the machine-selection policy. Default = round-robin across\n   * `fleet.ids`, skipping the optional `excludeMachineIds` set (typically the\n   * coordinator machine the MCP server is running on).\n   */\n  selectMachine?: (call: { callIndex: number; ids: ReadonlyArray<string> }) => string\n  /**\n   * Machine ids to skip during default round-robin. Set to the caller's own\n   * machineId so workers don't compete with the orchestrator on the same VM.\n   */\n  excludeMachineIds?: ReadonlyArray<string>\n}\n\n/**\n * Build an executor that resolves each delegated iteration to an existing\n * machine in `fleet`. The fleet's shared-workspace policy means the worker\n * machine sees the caller's filesystem — diffs land in-place with no\n * cross-sandbox copy step.\n *\n * @experimental\n */\nexport function createFleetWorkspaceExecutor(\n  options: FleetWorkspaceExecutorOptions,\n): DelegationExecutor {\n  const fleet = options.fleet\n  const exclude = new Set(options.excludeMachineIds ?? [])\n  let callIndex = 0\n  // machineId-by-sandboxId, populated as we resolve machines so\n  // `describePlacement` can recover the assignment from the SandboxInstance\n  // the kernel hands back.\n  const placementBySandboxId = new Map<string, { machineId: string }>()\n\n  const client: SandboxClient = {\n    async create(): Promise<SandboxInstance> {\n      const ids = fleet.ids.filter((id) => !exclude.has(id))\n      if (ids.length === 0) {\n        throw new Error(\n          `agent-runtime: fleet ${fleet.fleetId} has no eligible worker machines (ids=[${fleet.ids.join(',')}], excluded=[${[...exclude].join(',')}])`,\n        )\n      }\n      const selector = options.selectMachine\n      const machineId = selector ? selector({ callIndex, ids }) : ids[callIndex % ids.length]\n      callIndex += 1\n      if (typeof machineId !== 'string' || machineId.length === 0) {\n        throw new Error('agent-runtime: fleet executor selectMachine returned an empty machine id')\n      }\n      const box = await fleet.sandbox(machineId)\n      const sandboxId = readId(box)\n      if (sandboxId) placementBySandboxId.set(sandboxId, { machineId })\n      return box\n    },\n    describePlacement(box: SandboxInstance): LoopSandboxPlacement {\n      const sandboxId = readId(box)\n      const recorded = sandboxId ? placementBySandboxId.get(sandboxId) : undefined\n      return {\n        kind: 'fleet',\n        sandboxId,\n        fleetId: fleet.fleetId,\n        machineId: recorded?.machineId,\n      }\n    },\n  }\n\n  return {\n    client,\n    placement: 'fleet',\n    describe(): string {\n      const excluded = exclude.size > 0 ? ` (excluded=[${[...exclude].join(',')}])` : ''\n      return `fleet-workspace (fleetId=${fleet.fleetId}, machines=[${fleet.ids.join(',')}]${excluded})`\n    },\n  }\n}\n\nfunction readId(box: SandboxInstance): string | undefined {\n  const raw = (box as unknown as { id?: unknown }).id\n  return typeof raw === 'string' && raw.length > 0 ? raw : undefined\n}\n","/**\n * @experimental\n *\n * Delegate factories — the layer between MCP tool handlers and the\n * underlying `runLoop` runners.\n *\n * The MCP server is profile-agnostic: it owns the task queue + feedback\n * store + transport. Each `*Delegate` is the closure that the queue\n * invokes when a task runs. Consumers can override either delegate to\n * inject custom drivers, mocks, fleet-aware dispatchers, etc.\n *\n * The default coder delegate is wired here because we own\n * `coderProfile` / `multiHarnessCoderFanout`. The default researcher\n * delegate is **not** wired in this file — `agent-knowledge` cannot be\n * imported from `agent-runtime` without inducing a cycle. Consumers\n * pass `researcherDelegate` explicitly when constructing the server.\n */\n\nimport { type CoderOutput, coderProfile, multiHarnessCoderFanout } from '../profiles/coder'\nimport type { AgentRunSpec, Iteration, LoopTraceEmitter, SandboxClient } from '../runtime'\nimport { runLoop } from '../runtime'\nimport { composeLoopTraceEmitters } from './delegation-trace'\nimport {\n  type DetachedTurn,\n  detachedTurnEvents,\n  formatDetachedSessionRef,\n  parseDetachedSessionRef,\n  runDetachedTurn,\n} from './detached-turn'\nimport { createSiblingSandboxExecutor, type DelegationExecutor } from './executor'\nimport type {\n  CoderTask,\n  DelegateCodeArgs,\n  DelegateResearchArgs,\n  DelegateUiAuditArgs,\n  DelegationProgress,\n  ResearchOutputShape,\n  UiAuditorDelegationOutput,\n} from './types'\n\n/** @experimental */\nexport interface DelegateRunCtx {\n  signal: AbortSignal\n  report(progress: DelegationProgress): void\n  /**\n   * Detached-run resume key recorded on the queue record at submit time\n   * (`formatDetachedSessionRef`). Present only when the submit path requested\n   * detached dispatch — its presence is what routes a session-backed delegate\n   * onto the `driveTurn` tick path instead of holding a stream.\n   */\n  detachedSessionRef?: string\n  /** Rebind the record's resume key (e.g. once the sandbox id is known). */\n  updateDetachedSessionRef?(ref: string): void\n  /**\n   * Per-delegation trace sink supplied by the queue — loop events emitted\n   * here land on the delegation record as a compact span tree. Delegates\n   * compose it with their configured OTEL emitter so both sinks observe\n   * the same stream.\n   */\n  traceEmitter?: LoopTraceEmitter\n}\n\n/** @experimental */\nexport type CoderDelegate = (\n  args: DelegateCodeArgs,\n  ctx: DelegateRunCtx,\n) => Promise<import('../profiles/coder').CoderOutput>\n\n/** @experimental */\nexport type ResearcherDelegate = (\n  args: DelegateResearchArgs,\n  ctx: DelegateRunCtx,\n) => Promise<ResearchOutputShape>\n\n/**\n * UI-auditor delegate — fully consumer-injected. agent-runtime ships no\n * default factory because the inputs are workspace path + judge function\n * + (optionally) a `SandboxClient`, and the judge is the consumer's\n * model seam. See `createInProcessUiAuditClient` + `uiAuditorProfile` in\n * `@tangle-network/agent-runtime/profiles` for the canonical wiring.\n *\n * @experimental\n */\nexport type UiAuditorDelegate = (\n  args: DelegateUiAuditArgs,\n  ctx: DelegateRunCtx,\n) => Promise<UiAuditorDelegationOutput>\n\n/** @experimental Structured review verdict over a coder candidate. */\nexport interface CoderReview {\n  /** Gate: only approved candidates are eligible to win. */\n  approved: boolean\n  /** Reviewer's recommendation — surfaced in traces. */\n  recommendation: 'ship' | 'approve-with-nits' | 'changes-requested' | 'reject'\n  /** Readiness 0..1, used by the `highest-readiness` winner-selection strategy. */\n  readiness: number\n  notes?: string\n}\n\n/**\n * @experimental\n *\n * Optional adversarial reviewer over a coder candidate that already passed\n * mechanical validation (tests/typecheck/forbidden/diff/no-op/secrets). Folded\n * from the ai-trading-blueprint delegation MCP: a candidate is only eligible to\n * win if the reviewer approves it. The reviewer is the consumer's seam — an LLM\n * judge, a `pnpm review` command, anything returning a `CoderReview`.\n */\nexport type CoderReviewer = (\n  output: import('../profiles/coder').CoderOutput,\n  task: CoderTask,\n  ctx: { signal: AbortSignal },\n) => Promise<CoderReview> | CoderReview\n\n/**\n * @experimental Winner-selection strategy among validated (+ reviewed)\n * candidates. `highest-readiness` requires a `reviewer`. Default `highest-score`\n * (the kernel's behavior — preserves backward compatibility).\n */\nexport type CoderWinnerSelection =\n  | 'highest-score'\n  | 'smallest-diff'\n  | 'highest-readiness'\n  | 'first-approved'\n\n/** @experimental */\nexport interface CreateDefaultCoderDelegateOptions {\n  /**\n   * Execution placement. Pass a {@link DelegationExecutor} (sibling or fleet)\n   * to control where worker iterations land. `sandboxClient` is a\n   * convenience shorthand that wraps the client in a sibling executor — pass\n   * one or the other, not both.\n   */\n  executor?: DelegationExecutor\n  /**\n   * Convenience shorthand for sibling placement. Equivalent to\n   * `executor: createSiblingSandboxExecutor({ client: sandboxClient })`.\n   */\n  sandboxClient?: SandboxClient\n  /** Backend harness for the single-coder path. Default comes from `coderProfile`. */\n  harness?: string\n  /** Model override for the single-coder path. */\n  model?: string\n  /** Default `['claude-code', 'codex', 'opencode/zai-coding-plan/glm-5.1']` when variants > 1. */\n  fanoutHarnesses?: string[]\n  /** Optional per-harness model override for `variants > 1`. */\n  fanoutModels?: (string | undefined)[]\n  /** Hard cap on the kernel's per-batch concurrency. Default 4. */\n  maxConcurrency?: number\n  /**\n   * Optional adversarial reviewer. When set, a candidate must pass mechanical\n   * validation AND `reviewer.approved` to be eligible to win — empty/secret/\n   * test-failing patches are already gone; this catches the \"compiles + passes\n   * but wrong/unsafe\" class the deterministic validator can't see.\n   */\n  reviewer?: CoderReviewer\n  /** Winner-selection strategy among eligible candidates. Default `highest-score`. */\n  winnerSelection?: CoderWinnerSelection\n  /**\n   * Loop trace emitter forwarded into every delegated `runLoop`. Wire\n   * `createPropagatingTraceEmitter(readTraceContextFromEnv())` here (the bin\n   * does) so delegated build-loops export their topology spans to the OTLP /\n   * Tangle Intelligence sink when `OTEL_EXPORTER_OTLP_ENDPOINT` is set — and\n   * are a cheap no-op when it isn't. Configurable by construction.\n   *\n   * Detached single-variant turns (taken when `ctx.detachedSessionRef` is set)\n   * bypass `runLoop`; `runDetachedTurn` synthesizes a single-iteration loop\n   * event stream for them so this emitter observes detached work too.\n   */\n  traceEmitter?: LoopTraceEmitter\n  /** Tick cadence (ms) for the detached single-variant path. Default 5000. */\n  detachedTickIntervalMs?: number\n  /** Wall-clock cap (ms) forwarded to `driveTurn` for detached turns. */\n  detachedWallCapMs?: number\n}\n\n/**\n * Build a coder delegate that drives `runLoop` against the project's\n * sandbox client + coder profile. When `args.variants > 1` it switches\n * to the multi-harness fanout topology.\n *\n * @experimental\n */\nexport function createDefaultCoderDelegate(\n  options: CreateDefaultCoderDelegateOptions,\n): CoderDelegate {\n  const executor = resolveExecutor(options)\n  const sandboxClient = executor.client\n  const fanoutHarnesses = options.fanoutHarnesses\n  const maxConcurrency = options.maxConcurrency ?? 4\n  const traceEmitter = options.traceEmitter\n  return async (args, ctx) => {\n    const task = coderTaskFromArgs(args)\n    const variants = Math.max(1, Math.trunc(args.variants ?? 1))\n    const loopEmitter = composeLoopTraceEmitters(traceEmitter, ctx.traceEmitter)\n    ctx.report({ iteration: 0, phase: 'starting' })\n    if (variants <= 1) {\n      const { agentRunSpec, output, validator } = coderProfile({\n        task,\n        ...(options.harness ? { harness: options.harness } : {}),\n        ...(options.model ? { model: options.model } : {}),\n      })\n      // Detached dispatch: one session on one box, driven by `driveTurn` ticks\n      // instead of a held stream, so the run survives an MCP-process restart\n      // (the resume driver re-attaches via the persisted ref). Only the\n      // single-variant path detaches — fanout needs N sessions + winner\n      // selection over every candidate, which one resume key cannot express.\n      if (ctx.detachedSessionRef !== undefined && ctx.updateDetachedSessionRef) {\n        const { sessionId } = parseDetachedSessionRef(ctx.detachedSessionRef)\n        const rebind = ctx.updateDetachedSessionRef\n        const turn = await runDetachedTurn({\n          client: sandboxClient,\n          spec: agentRunSpec as AgentRunSpec<unknown>,\n          prompt: agentRunSpec.taskToPrompt(task),\n          sessionId,\n          bindSandbox: (sandboxId) => rebind(formatDetachedSessionRef({ sandboxId, sessionId })),\n          signal: ctx.signal,\n          report: ctx.report,\n          ...(loopEmitter ? { traceEmitter: loopEmitter } : {}),\n          ...(executor.placement === 'fleet' ? { placement: 'fleet' as const } : {}),\n          ...(options.detachedTickIntervalMs !== undefined\n            ? { tickIntervalMs: options.detachedTickIntervalMs }\n            : {}),\n          ...(options.detachedWallCapMs !== undefined\n            ? { wallCapMs: options.detachedWallCapMs }\n            : {}),\n        })\n        const chosen = await settleDetachedCoderTurn(turn, {\n          task,\n          sessionId,\n          signal: ctx.signal,\n          ...(options.harness ? { harness: options.harness } : {}),\n          ...(options.model ? { model: options.model } : {}),\n          ...(options.reviewer ? { reviewer: options.reviewer } : {}),\n        })\n        ctx.report({ iteration: 1, phase: 'completed' })\n        return chosen\n      }\n      const result = await runLoop({\n        driver: singleShotDriver,\n        agentRun: agentRunSpec,\n        output,\n        validator,\n        task,\n        ctx: {\n          sandboxClient,\n          signal: ctx.signal,\n          ...(loopEmitter ? { traceEmitter: loopEmitter } : {}),\n        },\n        maxIterations: 1,\n        maxConcurrency,\n      })\n      const chosen = await pickCoderWinner({\n        iterations: result.iterations,\n        reviewer: options.reviewer,\n        selection: options.winnerSelection ?? 'highest-score',\n        task,\n        signal: ctx.signal,\n      })\n      if (!chosen) throw new Error(noWinnerMessage(options.reviewer))\n      ctx.report({ iteration: 1, phase: 'completed' })\n      return chosen\n    }\n    const fanout = multiHarnessCoderFanout({\n      ...(fanoutHarnesses && fanoutHarnesses.length > 0\n        ? { harnesses: fanoutHarnesses.slice(0, variants) }\n        : {}),\n      ...(options.fanoutModels ? { models: options.fanoutModels.slice(0, variants) } : {}),\n    })\n    const agentRuns = fanout.agentRuns.slice(0, variants)\n    const result = await runLoop({\n      driver: fanout.driver,\n      agentRuns,\n      output: fanout.output,\n      validator: fanout.validator,\n      task,\n      ctx: {\n        sandboxClient,\n        signal: ctx.signal,\n        ...(loopEmitter ? { traceEmitter: loopEmitter } : {}),\n      },\n      maxIterations: variants,\n      maxConcurrency: Math.min(maxConcurrency, variants),\n    })\n    const chosen = await pickCoderWinner({\n      iterations: result.iterations,\n      reviewer: options.reviewer,\n      selection: options.winnerSelection ?? 'highest-score',\n      task,\n      signal: ctx.signal,\n    })\n    if (!chosen) throw new Error(noWinnerMessage(options.reviewer))\n    ctx.report({ iteration: agentRuns.length, phase: 'completed' })\n    return chosen\n  }\n}\n\ninterface PickCoderWinnerArgs {\n  iterations: ReadonlyArray<Iteration<CoderTask, CoderOutput>>\n  reviewer: CoderReviewer | undefined\n  selection: CoderWinnerSelection\n  task: CoderTask\n  signal: AbortSignal\n}\n\ninterface CoderCandidate {\n  index: number\n  output: CoderOutput\n  score: number\n  readiness: number\n}\n\n/**\n * Pick the winning coder candidate from a finished loop's iterations:\n *   1. keep only mechanically-VALID candidates (the validator already gated\n *      tests/typecheck/forbidden/diff/no-op/secrets),\n *   2. if a `reviewer` is wired, keep only those it APPROVES,\n *   3. select among survivors by the chosen strategy.\n * Returns `undefined` when nothing survives — the delegate fails loud.\n */\nasync function pickCoderWinner(args: PickCoderWinnerArgs): Promise<CoderOutput | undefined> {\n  const valid: CoderCandidate[] = []\n  for (const iter of args.iterations) {\n    if (iter.output === undefined || iter.error || iter.verdict?.valid !== true) continue\n    valid.push({\n      index: iter.index,\n      output: iter.output,\n      score: iter.verdict.score ?? 0,\n      readiness: iter.verdict.score ?? 0,\n    })\n  }\n  if (valid.length === 0) return undefined\n\n  let eligible = valid\n  if (args.reviewer) {\n    eligible = []\n    for (const c of valid) {\n      const review = await args.reviewer(c.output, args.task, { signal: args.signal })\n      if (review.approved) eligible.push({ ...c, readiness: review.readiness })\n    }\n    if (eligible.length === 0) return undefined\n  }\n\n  return selectCoderCandidate(eligible, args.selection).output\n}\n\n/** Apply the winner-selection strategy; ties broken by earliest iteration. */\nfunction selectCoderCandidate(\n  candidates: CoderCandidate[],\n  selection: CoderWinnerSelection,\n): CoderCandidate {\n  const diffLines = (c: CoderCandidate) =>\n    c.output.diffStats.insertions + c.output.diffStats.deletions\n  const sorted = [...candidates].sort((a, b) => {\n    switch (selection) {\n      case 'smallest-diff':\n        return diffLines(a) - diffLines(b) || a.index - b.index\n      case 'highest-readiness':\n        return b.readiness - a.readiness || a.index - b.index\n      case 'first-approved':\n        return a.index - b.index\n      default:\n        return b.score - a.score || a.index - b.index\n    }\n  })\n  return sorted[0]!\n}\n\nfunction noWinnerMessage(reviewer: CoderReviewer | undefined): string {\n  return reviewer\n    ? 'coder delegate: no candidate passed validation + review'\n    : 'coder delegate: no candidate passed validation'\n}\n\n/**\n * Canonical `DelegateCodeArgs` → `CoderTask` mapping — the single source for\n * the delegate's live dispatch AND the resume driver's settle/message\n * rebuilding, so a resumed record reproduces exactly the task the original\n * process dispatched.\n *\n * @experimental\n */\nexport function coderTaskFromArgs(args: DelegateCodeArgs): CoderTask {\n  return {\n    goal: buildCoderGoal(args),\n    repoRoot: args.repoRoot,\n    testCmd: args.config?.testCmd,\n    typecheckCmd: args.config?.typecheckCmd,\n    forbiddenPaths: args.config?.forbiddenPaths,\n    maxDiffLines: args.config?.maxDiffLines,\n  }\n}\n\n/** @experimental */\nexport interface SettleDetachedCoderTurnOptions {\n  task: CoderTask\n  /** Session id of the detached turn — used as the synthesized event id. */\n  sessionId: string\n  signal: AbortSignal\n  harness?: string\n  model?: string\n  /** Same gate as the streaming path: an unapproved candidate cannot win. */\n  reviewer?: CoderReviewer\n}\n\n/**\n * Settle a completed detached coder turn through the same gate the streaming\n * path applies: parse the terminal payload with the coder output adapter,\n * run the mechanical validator (tests/typecheck/forbidden/diff/no-op/secrets),\n * then the optional reviewer. Throws when nothing survives — a resumed or\n * detached run must not return an unvalidated patch.\n *\n * @experimental\n */\nexport async function settleDetachedCoderTurn(\n  turn: DetachedTurn,\n  options: SettleDetachedCoderTurnOptions,\n): Promise<CoderOutput> {\n  const { output, validator } = coderProfile({\n    task: options.task,\n    ...(options.harness ? { harness: options.harness } : {}),\n    ...(options.model ? { model: options.model } : {}),\n  })\n  const parsed = output.parse(detachedTurnEvents(options.sessionId, turn))\n  const verdict = await validator.validate(parsed, { iteration: 0, signal: options.signal })\n  if (verdict.valid !== true) throw new Error(noWinnerMessage(options.reviewer))\n  if (options.reviewer) {\n    const review = await options.reviewer(parsed, options.task, { signal: options.signal })\n    if (!review.approved) throw new Error(noWinnerMessage(options.reviewer))\n  }\n  return parsed\n}\n\nfunction buildCoderGoal(args: DelegateCodeArgs): string {\n  if (!args.contextHint) return args.goal\n  return [args.goal, '', '## Context', args.contextHint].join('\\n')\n}\n\nfunction resolveExecutor(options: CreateDefaultCoderDelegateOptions): DelegationExecutor {\n  if (options.executor && options.sandboxClient) {\n    throw new Error('createDefaultCoderDelegate: pass exactly one of `executor` or `sandboxClient`')\n  }\n  if (options.executor) return options.executor\n  if (options.sandboxClient) {\n    return createSiblingSandboxExecutor({ client: options.sandboxClient })\n  }\n  throw new Error('createDefaultCoderDelegate: `executor` or `sandboxClient` is required')\n}\n\n/**\n * Single-shot driver — plan one task on iteration 0, stop after one\n * iteration. Used by the coder delegate when `variants <= 1`. Keeps the\n * runLoop kernel-level accounting (timing, cost, trace emission) while\n * skipping fanout/refine topology overhead.\n */\nconst singleShotDriver = {\n  name: 'mcp-single-shot',\n  async plan<Task>(task: Task, history: ReadonlyArray<unknown>): Promise<Task[]> {\n    return history.length === 0 ? [task] : []\n  },\n  decide(history: ReadonlyArray<unknown>): 'pick-winner' | 'fail' {\n    return history.length > 0 ? 'pick-winner' : 'fail'\n  },\n}\n"],"mappings":";;;;;;;;;;;;;;AAqDO,SAAS,6BACd,SACoB;AACpB,QAAM,aAAa,QAAQ;AAC3B,QAAM,SAAwB;AAAA,IAC5B,OAAO,MAAuD;AAC5D,aAAO,WAAW,OAAO,IAAI;AAAA,IAC/B;AAAA,IACA,kBAAkB,KAA4C;AAC5D,aAAO,EAAE,MAAM,WAAW,WAAW,OAAO,GAAG,EAAE;AAAA,IACnD;AAAA,EACF;AACA,SAAO;AAAA,IACL;AAAA,IACA,WAAW;AAAA,IACX,WAAmB;AACjB,aAAO;AAAA,IACT;AAAA,EACF;AACF;AA2CO,SAAS,6BACd,SACoB;AACpB,QAAM,QAAQ,QAAQ;AACtB,QAAM,UAAU,IAAI,IAAI,QAAQ,qBAAqB,CAAC,CAAC;AACvD,MAAI,YAAY;AAIhB,QAAM,uBAAuB,oBAAI,IAAmC;AAEpE,QAAM,SAAwB;AAAA,IAC5B,MAAM,SAAmC;AACvC,YAAM,MAAM,MAAM,IAAI,OAAO,CAAC,OAAO,CAAC,QAAQ,IAAI,EAAE,CAAC;AACrD,UAAI,IAAI,WAAW,GAAG;AACpB,cAAM,IAAI;AAAA,UACR,wBAAwB,MAAM,OAAO,0CAA0C,MAAM,IAAI,KAAK,GAAG,CAAC,gBAAgB,CAAC,GAAG,OAAO,EAAE,KAAK,GAAG,CAAC;AAAA,QAC1I;AAAA,MACF;AACA,YAAM,WAAW,QAAQ;AACzB,YAAM,YAAY,WAAW,SAAS,EAAE,WAAW,IAAI,CAAC,IAAI,IAAI,YAAY,IAAI,MAAM;AACtF,mBAAa;AACb,UAAI,OAAO,cAAc,YAAY,UAAU,WAAW,GAAG;AAC3D,cAAM,IAAI,MAAM,0EAA0E;AAAA,MAC5F;AACA,YAAM,MAAM,MAAM,MAAM,QAAQ,SAAS;AACzC,YAAM,YAAY,OAAO,GAAG;AAC5B,UAAI,UAAW,sBAAqB,IAAI,WAAW,EAAE,UAAU,CAAC;AAChE,aAAO;AAAA,IACT;AAAA,IACA,kBAAkB,KAA4C;AAC5D,YAAM,YAAY,OAAO,GAAG;AAC5B,YAAM,WAAW,YAAY,qBAAqB,IAAI,SAAS,IAAI;AACnE,aAAO;AAAA,QACL,MAAM;AAAA,QACN;AAAA,QACA,SAAS,MAAM;AAAA,QACf,WAAW,UAAU;AAAA,MACvB;AAAA,IACF;AAAA,EACF;AAEA,SAAO;AAAA,IACL;AAAA,IACA,WAAW;AAAA,IACX,WAAmB;AACjB,YAAM,WAAW,QAAQ,OAAO,IAAI,eAAe,CAAC,GAAG,OAAO,EAAE,KAAK,GAAG,CAAC,OAAO;AAChF,aAAO,4BAA4B,MAAM,OAAO,eAAe,MAAM,IAAI,KAAK,GAAG,CAAC,IAAI,QAAQ;AAAA,IAChG;AAAA,EACF;AACF;AAEA,SAAS,OAAO,KAA0C;AACxD,QAAM,MAAO,IAAoC;AACjD,SAAO,OAAO,QAAQ,YAAY,IAAI,SAAS,IAAI,MAAM;AAC3D;;;ACaO,SAAS,2BACd,SACe;AACf,QAAM,WAAW,gBAAgB,OAAO;AACxC,QAAM,gBAAgB,SAAS;AAC/B,QAAM,kBAAkB,QAAQ;AAChC,QAAM,iBAAiB,QAAQ,kBAAkB;AACjD,QAAM,eAAe,QAAQ;AAC7B,SAAO,OAAO,MAAM,QAAQ;AAC1B,UAAM,OAAO,kBAAkB,IAAI;AACnC,UAAM,WAAW,KAAK,IAAI,GAAG,KAAK,MAAM,KAAK,YAAY,CAAC,CAAC;AAC3D,UAAM,cAAc,yBAAyB,cAAc,IAAI,YAAY;AAC3E,QAAI,OAAO,EAAE,WAAW,GAAG,OAAO,WAAW,CAAC;AAC9C,QAAI,YAAY,GAAG;AACjB,YAAM,EAAE,cAAc,QAAQ,UAAU,IAAI,aAAa;AAAA,QACvD;AAAA,QACA,GAAI,QAAQ,UAAU,EAAE,SAAS,QAAQ,QAAQ,IAAI,CAAC;AAAA,QACtD,GAAI,QAAQ,QAAQ,EAAE,OAAO,QAAQ,MAAM,IAAI,CAAC;AAAA,MAClD,CAAC;AAMD,UAAI,IAAI,uBAAuB,UAAa,IAAI,0BAA0B;AACxE,cAAM,EAAE,UAAU,IAAI,wBAAwB,IAAI,kBAAkB;AACpE,cAAM,SAAS,IAAI;AACnB,cAAM,OAAO,MAAM,gBAAgB;AAAA,UACjC,QAAQ;AAAA,UACR,MAAM;AAAA,UACN,QAAQ,aAAa,aAAa,IAAI;AAAA,UACtC;AAAA,UACA,aAAa,CAAC,cAAc,OAAO,yBAAyB,EAAE,WAAW,UAAU,CAAC,CAAC;AAAA,UACrF,QAAQ,IAAI;AAAA,UACZ,QAAQ,IAAI;AAAA,UACZ,GAAI,cAAc,EAAE,cAAc,YAAY,IAAI,CAAC;AAAA,UACnD,GAAI,SAAS,cAAc,UAAU,EAAE,WAAW,QAAiB,IAAI,CAAC;AAAA,UACxE,GAAI,QAAQ,2BAA2B,SACnC,EAAE,gBAAgB,QAAQ,uBAAuB,IACjD,CAAC;AAAA,UACL,GAAI,QAAQ,sBAAsB,SAC9B,EAAE,WAAW,QAAQ,kBAAkB,IACvC,CAAC;AAAA,QACP,CAAC;AACD,cAAMA,UAAS,MAAM,wBAAwB,MAAM;AAAA,UACjD;AAAA,UACA;AAAA,UACA,QAAQ,IAAI;AAAA,UACZ,GAAI,QAAQ,UAAU,EAAE,SAAS,QAAQ,QAAQ,IAAI,CAAC;AAAA,UACtD,GAAI,QAAQ,QAAQ,EAAE,OAAO,QAAQ,MAAM,IAAI,CAAC;AAAA,UAChD,GAAI,QAAQ,WAAW,EAAE,UAAU,QAAQ,SAAS,IAAI,CAAC;AAAA,QAC3D,CAAC;AACD,YAAI,OAAO,EAAE,WAAW,GAAG,OAAO,YAAY,CAAC;AAC/C,eAAOA;AAAA,MACT;AACA,YAAMC,UAAS,MAAM,QAAQ;AAAA,QAC3B,QAAQ;AAAA,QACR,UAAU;AAAA,QACV;AAAA,QACA;AAAA,QACA;AAAA,QACA,KAAK;AAAA,UACH;AAAA,UACA,QAAQ,IAAI;AAAA,UACZ,GAAI,cAAc,EAAE,cAAc,YAAY,IAAI,CAAC;AAAA,QACrD;AAAA,QACA,eAAe;AAAA,QACf;AAAA,MACF,CAAC;AACD,YAAMD,UAAS,MAAM,gBAAgB;AAAA,QACnC,YAAYC,QAAO;AAAA,QACnB,UAAU,QAAQ;AAAA,QAClB,WAAW,QAAQ,mBAAmB;AAAA,QACtC;AAAA,QACA,QAAQ,IAAI;AAAA,MACd,CAAC;AACD,UAAI,CAACD,QAAQ,OAAM,IAAI,MAAM,gBAAgB,QAAQ,QAAQ,CAAC;AAC9D,UAAI,OAAO,EAAE,WAAW,GAAG,OAAO,YAAY,CAAC;AAC/C,aAAOA;AAAA,IACT;AACA,UAAM,SAAS,wBAAwB;AAAA,MACrC,GAAI,mBAAmB,gBAAgB,SAAS,IAC5C,EAAE,WAAW,gBAAgB,MAAM,GAAG,QAAQ,EAAE,IAChD,CAAC;AAAA,MACL,GAAI,QAAQ,eAAe,EAAE,QAAQ,QAAQ,aAAa,MAAM,GAAG,QAAQ,EAAE,IAAI,CAAC;AAAA,IACpF,CAAC;AACD,UAAM,YAAY,OAAO,UAAU,MAAM,GAAG,QAAQ;AACpD,UAAM,SAAS,MAAM,QAAQ;AAAA,MAC3B,QAAQ,OAAO;AAAA,MACf;AAAA,MACA,QAAQ,OAAO;AAAA,MACf,WAAW,OAAO;AAAA,MAClB;AAAA,MACA,KAAK;AAAA,QACH;AAAA,QACA,QAAQ,IAAI;AAAA,QACZ,GAAI,cAAc,EAAE,cAAc,YAAY,IAAI,CAAC;AAAA,MACrD;AAAA,MACA,eAAe;AAAA,MACf,gBAAgB,KAAK,IAAI,gBAAgB,QAAQ;AAAA,IACnD,CAAC;AACD,UAAM,SAAS,MAAM,gBAAgB;AAAA,MACnC,YAAY,OAAO;AAAA,MACnB,UAAU,QAAQ;AAAA,MAClB,WAAW,QAAQ,mBAAmB;AAAA,MACtC;AAAA,MACA,QAAQ,IAAI;AAAA,IACd,CAAC;AACD,QAAI,CAAC,OAAQ,OAAM,IAAI,MAAM,gBAAgB,QAAQ,QAAQ,CAAC;AAC9D,QAAI,OAAO,EAAE,WAAW,UAAU,QAAQ,OAAO,YAAY,CAAC;AAC9D,WAAO;AAAA,EACT;AACF;AAyBA,eAAe,gBAAgB,MAA6D;AAC1F,QAAM,QAA0B,CAAC;AACjC,aAAW,QAAQ,KAAK,YAAY;AAClC,QAAI,KAAK,WAAW,UAAa,KAAK,SAAS,KAAK,SAAS,UAAU,KAAM;AAC7E,UAAM,KAAK;AAAA,MACT,OAAO,KAAK;AAAA,MACZ,QAAQ,KAAK;AAAA,MACb,OAAO,KAAK,QAAQ,SAAS;AAAA,MAC7B,WAAW,KAAK,QAAQ,SAAS;AAAA,IACnC,CAAC;AAAA,EACH;AACA,MAAI,MAAM,WAAW,EAAG,QAAO;AAE/B,MAAI,WAAW;AACf,MAAI,KAAK,UAAU;AACjB,eAAW,CAAC;AACZ,eAAW,KAAK,OAAO;AACrB,YAAM,SAAS,MAAM,KAAK,SAAS,EAAE,QAAQ,KAAK,MAAM,EAAE,QAAQ,KAAK,OAAO,CAAC;AAC/E,UAAI,OAAO,SAAU,UAAS,KAAK,EAAE,GAAG,GAAG,WAAW,OAAO,UAAU,CAAC;AAAA,IAC1E;AACA,QAAI,SAAS,WAAW,EAAG,QAAO;AAAA,EACpC;AAEA,SAAO,qBAAqB,UAAU,KAAK,SAAS,EAAE;AACxD;AAGA,SAAS,qBACP,YACA,WACgB;AAChB,QAAM,YAAY,CAAC,MACjB,EAAE,OAAO,UAAU,aAAa,EAAE,OAAO,UAAU;AACrD,QAAM,SAAS,CAAC,GAAG,UAAU,EAAE,KAAK,CAAC,GAAG,MAAM;AAC5C,YAAQ,WAAW;AAAA,MACjB,KAAK;AACH,eAAO,UAAU,CAAC,IAAI,UAAU,CAAC,KAAK,EAAE,QAAQ,EAAE;AAAA,MACpD,KAAK;AACH,eAAO,EAAE,YAAY,EAAE,aAAa,EAAE,QAAQ,EAAE;AAAA,MAClD,KAAK;AACH,eAAO,EAAE,QAAQ,EAAE;AAAA,MACrB;AACE,eAAO,EAAE,QAAQ,EAAE,SAAS,EAAE,QAAQ,EAAE;AAAA,IAC5C;AAAA,EACF,CAAC;AACD,SAAO,OAAO,CAAC;AACjB;AAEA,SAAS,gBAAgB,UAA6C;AACpE,SAAO,WACH,4DACA;AACN;AAUO,SAAS,kBAAkB,MAAmC;AACnE,SAAO;AAAA,IACL,MAAM,eAAe,IAAI;AAAA,IACzB,UAAU,KAAK;AAAA,IACf,SAAS,KAAK,QAAQ;AAAA,IACtB,cAAc,KAAK,QAAQ;AAAA,IAC3B,gBAAgB,KAAK,QAAQ;AAAA,IAC7B,cAAc,KAAK,QAAQ;AAAA,EAC7B;AACF;AAuBA,eAAsB,wBACpB,MACA,SACsB;AACtB,QAAM,EAAE,QAAQ,UAAU,IAAI,aAAa;AAAA,IACzC,MAAM,QAAQ;AAAA,IACd,GAAI,QAAQ,UAAU,EAAE,SAAS,QAAQ,QAAQ,IAAI,CAAC;AAAA,IACtD,GAAI,QAAQ,QAAQ,EAAE,OAAO,QAAQ,MAAM,IAAI,CAAC;AAAA,EAClD,CAAC;AACD,QAAM,SAAS,OAAO,MAAM,mBAAmB,QAAQ,WAAW,IAAI,CAAC;AACvE,QAAM,UAAU,MAAM,UAAU,SAAS,QAAQ,EAAE,WAAW,GAAG,QAAQ,QAAQ,OAAO,CAAC;AACzF,MAAI,QAAQ,UAAU,KAAM,OAAM,IAAI,MAAM,gBAAgB,QAAQ,QAAQ,CAAC;AAC7E,MAAI,QAAQ,UAAU;AACpB,UAAM,SAAS,MAAM,QAAQ,SAAS,QAAQ,QAAQ,MAAM,EAAE,QAAQ,QAAQ,OAAO,CAAC;AACtF,QAAI,CAAC,OAAO,SAAU,OAAM,IAAI,MAAM,gBAAgB,QAAQ,QAAQ,CAAC;AAAA,EACzE;AACA,SAAO;AACT;AAEA,SAAS,eAAe,MAAgC;AACtD,MAAI,CAAC,KAAK,YAAa,QAAO,KAAK;AACnC,SAAO,CAAC,KAAK,MAAM,IAAI,cAAc,KAAK,WAAW,EAAE,KAAK,IAAI;AAClE;AAEA,SAAS,gBAAgB,SAAgE;AACvF,MAAI,QAAQ,YAAY,QAAQ,eAAe;AAC7C,UAAM,IAAI,MAAM,+EAA+E;AAAA,EACjG;AACA,MAAI,QAAQ,SAAU,QAAO,QAAQ;AACrC,MAAI,QAAQ,eAAe;AACzB,WAAO,6BAA6B,EAAE,QAAQ,QAAQ,cAAc,CAAC;AAAA,EACvE;AACA,QAAM,IAAI,MAAM,uEAAuE;AACzF;AAQA,IAAM,mBAAmB;AAAA,EACvB,MAAM;AAAA,EACN,MAAM,KAAW,MAAY,SAAkD;AAC7E,WAAO,QAAQ,WAAW,IAAI,CAAC,IAAI,IAAI,CAAC;AAAA,EAC1C;AAAA,EACA,OAAO,SAAyD;AAC9D,WAAO,QAAQ,SAAS,IAAI,gBAAgB;AAAA,EAC9C;AACF;","names":["chosen","result"]}

package/dist/chunk-GRAGM4MC.js

@@ -0,0 +1,72 @@
+// src/model-resolution.ts
+var DEFAULT_ROUTER_BASE_URL = "https://router.tangle.tools";
+function resolveRouterBaseUrl(env = {}) {
+  return (env.TANGLE_ROUTER_URL ?? env.TANGLE_ROUTER_BASE_URL ?? DEFAULT_ROUTER_BASE_URL).replace(/\/v1\/?$/, "").replace(/\/$/, "");
+}
+async function getModels(routerBaseUrl = DEFAULT_ROUTER_BASE_URL) {
+  const res = await fetch(`${routerBaseUrl}/v1/models`, {
+    headers: { Accept: "application/json" }
+  });
+  if (!res.ok) throw new Error(`router /v1/models ${res.status}`);
+  const body = await res.json();
+  return Array.isArray(body.data) ? body.data : [];
+}
+function cleanModelId(value) {
+  if (typeof value !== "string") return void 0;
+  const trimmed = value.trim();
+  return trimmed.length > 0 ? trimmed : void 0;
+}
+function resolveChatModel(candidates, fallback) {
+  for (const candidate of candidates) {
+    const model = cleanModelId(candidate.model);
+    if (model) return { source: candidate.source, model };
+  }
+  return fallback;
+}
+var WELL_FORMED_MODEL_ID = /^[A-Za-z0-9._/@:-]+$/;
+function isWellFormedModelId(modelId) {
+  return modelId.length <= 200 && WELL_FORMED_MODEL_ID.test(modelId);
+}
+function catalogIdsForModel(model) {
+  const ids = /* @__PURE__ */ new Set();
+  const id = cleanModelId(model.id);
+  if (id) ids.add(id);
+  const provider = cleanModelId(model._provider) ?? cleanModelId(model.provider);
+  if (provider && id && !id.includes("/")) ids.add(`${provider}/${id}`);
+  return [...ids];
+}
+async function validateChatModelId(modelId, options = {}) {
+  const {
+    allowlist = [],
+    routerBaseUrl = DEFAULT_ROUTER_BASE_URL,
+    loadModels = getModels
+  } = options;
+  const cleaned = cleanModelId(modelId);
+  if (!cleaned) return { succeeded: false, error: "Model id must be a non-empty string." };
+  if (!isWellFormedModelId(cleaned)) {
+    return { succeeded: false, error: `Model id is malformed: ${cleaned}` };
+  }
+  if (allowlist.some((id) => cleanModelId(id) === cleaned)) {
+    return { succeeded: true, value: cleaned };
+  }
+  let catalog;
+  try {
+    catalog = await loadModels(routerBaseUrl);
+  } catch (err) {
+    const message = err instanceof Error ? err.message : String(err);
+    return { succeeded: false, error: `Could not validate model catalog: ${message}` };
+  }
+  const ids = new Set(catalog.flatMap(catalogIdsForModel));
+  if (!ids.has(cleaned)) return { succeeded: false, error: `Model is not available: ${cleaned}` };
+  return { succeeded: true, value: cleaned };
+}
+
+export {
+  DEFAULT_ROUTER_BASE_URL,
+  resolveRouterBaseUrl,
+  getModels,
+  cleanModelId,
+  resolveChatModel,
+  validateChatModelId
+};
+//# sourceMappingURL=chunk-GRAGM4MC.js.map

package/dist/chunk-GRAGM4MC.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/model-resolution.ts"],"sourcesContent":["/**\n * @stable\n *\n * Chat-model resolution + catalog validation — the shared primitive every\n * product chat handler needs and was, until now, hand-rolling. Lifts the\n * router `/v1/models` fetch, the fail-closed id validation, and the\n * precedence resolver out of four near-identical per-repo copies.\n *\n * Policy-free by design: callers pass their own precedence order\n * (`resolveChatModel`) and their own known-good `allowlist`\n * (`validateChatModelId`), so each product keeps its resolution policy while\n * sharing the catalog fetch, the malformed-id guard, and the fail-closed\n * admission rule. No React, no `process.env` assumption — `env` is an\n * explicit narrow record so this runs unchanged in Node and in Workers.\n */\n\n/**\n * A model entry as returned by the Tangle Router `/v1/models` endpoint.\n * Intentionally minimal — only the fields resolution + validation read.\n */\nexport interface ModelInfo {\n  id: string\n  name?: string\n  description?: string\n  /** Provider slug, when the router exposes it (`provider` or `_provider`). */\n  provider?: string\n  _provider?: string\n  architecture?: {\n    modality?: string\n    input_modalities?: string[]\n    output_modalities?: string[]\n  }\n}\n\n/** Env keys the router base URL is resolved from. */\nexport interface RouterEnv {\n  TANGLE_ROUTER_URL?: string\n  TANGLE_ROUTER_BASE_URL?: string\n}\n\nexport const DEFAULT_ROUTER_BASE_URL = 'https://router.tangle.tools'\n\n/** Resolve the router base URL from env, normalised — no trailing `/v1` or `/`. */\nexport function resolveRouterBaseUrl(env: RouterEnv = {}): string {\n  return (env.TANGLE_ROUTER_URL ?? env.TANGLE_ROUTER_BASE_URL ?? DEFAULT_ROUTER_BASE_URL)\n    .replace(/\\/v1\\/?$/, '')\n    .replace(/\\/$/, '')\n}\n\n/**\n * Fetch the model catalog from the router's `/v1/models`. Throws on a non-2xx\n * response — callers decide whether to fail open (empty catalog) or closed.\n */\nexport async function getModels(\n  routerBaseUrl: string = DEFAULT_ROUTER_BASE_URL,\n): Promise<ModelInfo[]> {\n  const res = await fetch(`${routerBaseUrl}/v1/models`, {\n    headers: { Accept: 'application/json' },\n  })\n  if (!res.ok) throw new Error(`router /v1/models ${res.status}`)\n  const body = (await res.json()) as { data?: ModelInfo[] }\n  return Array.isArray(body.data) ? body.data : []\n}\n\n/** Trim a candidate model id; `undefined` for non-strings and blanks. */\nexport function cleanModelId(value: unknown): string | undefined {\n  if (typeof value !== 'string') return undefined\n  const trimmed = value.trim()\n  return trimmed.length > 0 ? trimmed : undefined\n}\n\nexport interface ChatModelCandidate {\n  /** Stable label for telemetry — e.g. `request`, `workspace`, `env`. */\n  source: string\n  model: string | undefined\n}\n\nexport interface ResolvedChatModel {\n  source: string\n  model: string\n}\n\n/**\n * Resolve a chat model by precedence: the first candidate carrying a\n * non-blank model wins, else `fallback`. The caller owns the precedence\n * order, so each product keeps its own policy (request → workspace → env,\n * etc.) while the first-non-blank logic and the telemetry shape stay shared.\n */\nexport function resolveChatModel(\n  candidates: ChatModelCandidate[],\n  fallback: ResolvedChatModel,\n): ResolvedChatModel {\n  for (const candidate of candidates) {\n    const model = cleanModelId(candidate.model)\n    if (model) return { source: candidate.source, model }\n  }\n  return fallback\n}\n\nexport type ChatModelValidation =\n  | { succeeded: true; value: string }\n  | { succeeded: false; error: string }\n\nconst WELL_FORMED_MODEL_ID = /^[A-Za-z0-9._/@:-]+$/\n\nfunction isWellFormedModelId(modelId: string): boolean {\n  return modelId.length <= 200 && WELL_FORMED_MODEL_ID.test(modelId)\n}\n\n/**\n * Every id a catalog entry can be addressed by — its bare id, plus a\n * `provider/id` form when the router exposes a separate provider slug.\n */\nfunction catalogIdsForModel(model: ModelInfo): string[] {\n  const ids = new Set<string>()\n  const id = cleanModelId(model.id)\n  if (id) ids.add(id)\n  const provider = cleanModelId(model._provider) ?? cleanModelId(model.provider)\n  if (provider && id && !id.includes('/')) ids.add(`${provider}/${id}`)\n  return [...ids]\n}\n\n/**\n * Validate a caller-supplied chat-model id. Rejects non-strings, malformed\n * ids, and ids absent from both the caller's `allowlist` and the live router\n * catalog. Fails closed: when the catalog cannot be fetched, an unverifiable\n * id is rejected rather than admitted — a bad model never reaches the agent.\n */\nexport async function validateChatModelId(\n  modelId: unknown,\n  options: {\n    /**\n     * Known-good ids that skip the catalog round trip — e.g. the product's\n     * default model plus any env-configured ids.\n     */\n    allowlist?: string[]\n    routerBaseUrl?: string\n    /** Injectable catalog loader — overridden in tests. */\n    loadModels?: (routerBaseUrl: string) => Promise<ModelInfo[]>\n  } = {},\n): Promise<ChatModelValidation> {\n  const {\n    allowlist = [],\n    routerBaseUrl = DEFAULT_ROUTER_BASE_URL,\n    loadModels = getModels,\n  } = options\n\n  const cleaned = cleanModelId(modelId)\n  if (!cleaned) return { succeeded: false, error: 'Model id must be a non-empty string.' }\n  if (!isWellFormedModelId(cleaned)) {\n    return { succeeded: false, error: `Model id is malformed: ${cleaned}` }\n  }\n  if (allowlist.some((id) => cleanModelId(id) === cleaned)) {\n    return { succeeded: true, value: cleaned }\n  }\n\n  let catalog: ModelInfo[]\n  try {\n    catalog = await loadModels(routerBaseUrl)\n  } catch (err) {\n    const message = err instanceof Error ? err.message : String(err)\n    return { succeeded: false, error: `Could not validate model catalog: ${message}` }\n  }\n\n  const ids = new Set(catalog.flatMap(catalogIdsForModel))\n  if (!ids.has(cleaned)) return { succeeded: false, error: `Model is not available: ${cleaned}` }\n  return { succeeded: true, value: cleaned }\n}\n"],"mappings":";AAwCO,IAAM,0BAA0B;AAGhC,SAAS,qBAAqB,MAAiB,CAAC,GAAW;AAChE,UAAQ,IAAI,qBAAqB,IAAI,0BAA0B,yBAC5D,QAAQ,YAAY,EAAE,EACtB,QAAQ,OAAO,EAAE;AACtB;AAMA,eAAsB,UACpB,gBAAwB,yBACF;AACtB,QAAM,MAAM,MAAM,MAAM,GAAG,aAAa,cAAc;AAAA,IACpD,SAAS,EAAE,QAAQ,mBAAmB;AAAA,EACxC,CAAC;AACD,MAAI,CAAC,IAAI,GAAI,OAAM,IAAI,MAAM,qBAAqB,IAAI,MAAM,EAAE;AAC9D,QAAM,OAAQ,MAAM,IAAI,KAAK;AAC7B,SAAO,MAAM,QAAQ,KAAK,IAAI,IAAI,KAAK,OAAO,CAAC;AACjD;AAGO,SAAS,aAAa,OAAoC;AAC/D,MAAI,OAAO,UAAU,SAAU,QAAO;AACtC,QAAM,UAAU,MAAM,KAAK;AAC3B,SAAO,QAAQ,SAAS,IAAI,UAAU;AACxC;AAmBO,SAAS,iBACd,YACA,UACmB;AACnB,aAAW,aAAa,YAAY;AAClC,UAAM,QAAQ,aAAa,UAAU,KAAK;AAC1C,QAAI,MAAO,QAAO,EAAE,QAAQ,UAAU,QAAQ,MAAM;AAAA,EACtD;AACA,SAAO;AACT;AAMA,IAAM,uBAAuB;AAE7B,SAAS,oBAAoB,SAA0B;AACrD,SAAO,QAAQ,UAAU,OAAO,qBAAqB,KAAK,OAAO;AACnE;AAMA,SAAS,mBAAmB,OAA4B;AACtD,QAAM,MAAM,oBAAI,IAAY;AAC5B,QAAM,KAAK,aAAa,MAAM,EAAE;AAChC,MAAI,GAAI,KAAI,IAAI,EAAE;AAClB,QAAM,WAAW,aAAa,MAAM,SAAS,KAAK,aAAa,MAAM,QAAQ;AAC7E,MAAI,YAAY,MAAM,CAAC,GAAG,SAAS,GAAG,EAAG,KAAI,IAAI,GAAG,QAAQ,IAAI,EAAE,EAAE;AACpE,SAAO,CAAC,GAAG,GAAG;AAChB;AAQA,eAAsB,oBACpB,SACA,UASI,CAAC,GACyB;AAC9B,QAAM;AAAA,IACJ,YAAY,CAAC;AAAA,IACb,gBAAgB;AAAA,IAChB,aAAa;AAAA,EACf,IAAI;AAEJ,QAAM,UAAU,aAAa,OAAO;AACpC,MAAI,CAAC,QAAS,QAAO,EAAE,WAAW,OAAO,OAAO,uCAAuC;AACvF,MAAI,CAAC,oBAAoB,OAAO,GAAG;AACjC,WAAO,EAAE,WAAW,OAAO,OAAO,0BAA0B,OAAO,GAAG;AAAA,EACxE;AACA,MAAI,UAAU,KAAK,CAAC,OAAO,aAAa,EAAE,MAAM,OAAO,GAAG;AACxD,WAAO,EAAE,WAAW,MAAM,OAAO,QAAQ;AAAA,EAC3C;AAEA,MAAI;AACJ,MAAI;AACF,cAAU,MAAM,WAAW,aAAa;AAAA,EAC1C,SAAS,KAAK;AACZ,UAAM,UAAU,eAAe,QAAQ,IAAI,UAAU,OAAO,GAAG;AAC/D,WAAO,EAAE,WAAW,OAAO,OAAO,qCAAqC,OAAO,GAAG;AAAA,EACnF;AAEA,QAAM,MAAM,IAAI,IAAI,QAAQ,QAAQ,kBAAkB,CAAC;AACvD,MAAI,CAAC,IAAI,IAAI,OAAO,EAAG,QAAO,EAAE,WAAW,OAAO,OAAO,2BAA2B,OAAO,GAAG;AAC9F,SAAO,EAAE,WAAW,MAAM,OAAO,QAAQ;AAC3C;","names":[]}

package/dist/{chunk-GLR25NG7.js → chunk-H2KWSZAN.js}

@@ -34,6 +34,7 @@ function runLocalHarness(options) {
       reject(err instanceof Error ? err : new Error(String(err)));
       return;
     }
+    child.stdin?.end();
     let stdout = "";
     let stderr = "";
     let timedOut = false;
@@ -89,4 +90,4 @@ function runLocalHarness(options) {
 export {
   runLocalHarness
 };
-//# sourceMappingURL=chunk-GLR25NG7.js.map
+//# sourceMappingURL=chunk-H2KWSZAN.js.map

package/dist/{chunk-GLR25NG7.js.map → chunk-H2KWSZAN.js.map}

@@ -1 +1 @@
-{"version":3,"sources":["../src/mcp/local-harness.ts"],"sourcesContent":["/**\n * @experimental\n *\n * Subprocess wrappers for the local coding-harness CLIs installed in the\n * sandbox image (claude-code, codex, opencode). Used by the in-process\n * delegation executor (`createInProcessExecutor`) so a `delegate_code` call\n * spawns a real harness on a real git worktree instead of provisioning a\n * sibling sandbox.\n *\n * All harness invocations:\n *   - run with `cwd` set to the worktree\n *   - inherit env from the parent (the MCP server inside the sandbox has\n *     the harness's auth already)\n *   - capture stdout/stderr\n *   - support cancellation via AbortSignal\n *   - enforce a wall-clock timeout\n */\n\nimport { type ChildProcess, spawn } from 'node:child_process'\n\n/** Local coding harness available inside the sandbox. */\nexport type LocalHarness = 'claude' | 'codex' | 'opencode'\n\n/** Default per-harness command + arg shape. */\nconst HARNESS_INVOCATIONS: Record<\n  LocalHarness,\n  { command: string; buildArgs: (taskPrompt: string) => string[] }\n> = {\n  claude: {\n    command: 'claude',\n    buildArgs: (taskPrompt) => ['--headless', '-p', taskPrompt],\n  },\n  codex: {\n    command: 'codex',\n    buildArgs: (taskPrompt) => ['run', taskPrompt],\n  },\n  opencode: {\n    command: 'opencode',\n    buildArgs: (taskPrompt) => ['run', taskPrompt],\n  },\n}\n\n/** @experimental */\nexport interface RunLocalHarnessOptions {\n  harness: LocalHarness\n  /** Working directory for the subprocess (typically a worktree path). */\n  cwd: string\n  /** Prompt forwarded as the harness CLI's task argument. */\n  taskPrompt: string\n  /** Wall-clock kill deadline (ms). Default 5 min. Subprocess SIGTERMed on expiry. */\n  timeoutMs?: number\n  /** Caller cancellation. SIGTERM is sent on abort. */\n  signal?: AbortSignal\n  /** Override env (defaults to inheriting from the parent). */\n  env?: NodeJS.ProcessEnv\n  /**\n   * Test seam — inject a custom spawner so unit tests can mock the\n   * subprocess without touching the OS. Defaults to node's `child_process.spawn`.\n   */\n  spawn?: (\n    command: string,\n    args: ReadonlyArray<string>,\n    opts: {\n      cwd: string\n      env: NodeJS.ProcessEnv\n      stdio: 'pipe'\n    },\n  ) => ChildProcess\n}\n\n/** @experimental */\nexport interface LocalHarnessResult {\n  /** OS exit code. `null` when killed before exit. */\n  exitCode: number | null\n  /** Concatenated stdout. */\n  stdout: string\n  /** Concatenated stderr. */\n  stderr: string\n  /** Set when the process exited via signal (timeout / abort). */\n  killedBySignal: NodeJS.Signals | null\n  /** Wall-clock duration ms (spawn → exit). */\n  durationMs: number\n  /** Set when timeoutMs elapsed before exit. */\n  timedOut: boolean\n}\n\nconst DEFAULT_TIMEOUT_MS = 5 * 60 * 1000\n\n/**\n * Spawn a local coding harness CLI as a subprocess + collect its output.\n *\n * NOT responsible for parsing the harness's output or extracting a diff —\n * the in-process executor's `streamPrompt` orchestrates `git diff` against\n * the worktree after this resolves. This function is intentionally narrow:\n * spawn, wait, capture, return.\n *\n * Fails loud — throws when:\n *   - `cwd` doesn't exist (subprocess emits ENOENT; surfaced as Error)\n *   - the harness binary is not on PATH (ENOENT)\n *\n * Does NOT throw when:\n *   - the subprocess exits non-zero (`result.exitCode` carries the code)\n *   - the subprocess is aborted / timed out (`result.killedBySignal` /\n *     `result.timedOut` carries the reason)\n *\n * @experimental\n */\nexport function runLocalHarness(options: RunLocalHarnessOptions): Promise<LocalHarnessResult> {\n  const { harness, cwd, taskPrompt } = options\n  const timeoutMs = options.timeoutMs ?? DEFAULT_TIMEOUT_MS\n  const env = options.env ?? process.env\n  const spawnImpl = options.spawn ?? spawn\n\n  const invocation = HARNESS_INVOCATIONS[harness]\n  if (!invocation) {\n    return Promise.reject(new Error(`runLocalHarness: unknown harness ${String(harness)}`))\n  }\n\n  const startedAt = Date.now()\n  const args = invocation.buildArgs(taskPrompt)\n\n  return new Promise<LocalHarnessResult>((resolve, reject) => {\n    let child: ChildProcess\n    try {\n      child = spawnImpl(invocation.command, args, { cwd, env, stdio: 'pipe' })\n    } catch (err) {\n      reject(err instanceof Error ? err : new Error(String(err)))\n      return\n    }\n\n    let stdout = ''\n    let stderr = ''\n    let timedOut = false\n    let settled = false\n\n    const timer =\n      timeoutMs > 0\n        ? setTimeout(() => {\n            timedOut = true\n            if (!child.killed) child.kill('SIGTERM')\n          }, timeoutMs)\n        : null\n    if (timer && typeof (timer as { unref?: () => void }).unref === 'function') {\n      ;(timer as { unref: () => void }).unref()\n    }\n\n    const onAbort = () => {\n      if (!child.killed) child.kill('SIGTERM')\n    }\n    if (options.signal) {\n      if (options.signal.aborted) onAbort()\n      else options.signal.addEventListener('abort', onAbort, { once: true })\n    }\n\n    child.stdout?.on('data', (chunk) => {\n      stdout += String(chunk)\n    })\n    child.stderr?.on('data', (chunk) => {\n      stderr += String(chunk)\n    })\n\n    const finalize = (result: LocalHarnessResult) => {\n      if (settled) return\n      settled = true\n      if (timer) clearTimeout(timer)\n      options.signal?.removeEventListener('abort', onAbort)\n      resolve(result)\n    }\n\n    child.on('error', (err) => {\n      if (settled) return\n      settled = true\n      if (timer) clearTimeout(timer)\n      options.signal?.removeEventListener('abort', onAbort)\n      reject(err)\n    })\n\n    child.on('close', (code, signal) => {\n      finalize({\n        exitCode: code,\n        stdout,\n        stderr,\n        killedBySignal: signal,\n        durationMs: Date.now() - startedAt,\n        timedOut,\n      })\n    })\n  })\n}\n"],"mappings":";AAkBA,SAA4B,aAAa;AAMzC,IAAM,sBAGF;AAAA,EACF,QAAQ;AAAA,IACN,SAAS;AAAA,IACT,WAAW,CAAC,eAAe,CAAC,cAAc,MAAM,UAAU;AAAA,EAC5D;AAAA,EACA,OAAO;AAAA,IACL,SAAS;AAAA,IACT,WAAW,CAAC,eAAe,CAAC,OAAO,UAAU;AAAA,EAC/C;AAAA,EACA,UAAU;AAAA,IACR,SAAS;AAAA,IACT,WAAW,CAAC,eAAe,CAAC,OAAO,UAAU;AAAA,EAC/C;AACF;AA8CA,IAAM,qBAAqB,IAAI,KAAK;AAqB7B,SAAS,gBAAgB,SAA8D;AAC5F,QAAM,EAAE,SAAS,KAAK,WAAW,IAAI;AACrC,QAAM,YAAY,QAAQ,aAAa;AACvC,QAAM,MAAM,QAAQ,OAAO,QAAQ;AACnC,QAAM,YAAY,QAAQ,SAAS;AAEnC,QAAM,aAAa,oBAAoB,OAAO;AAC9C,MAAI,CAAC,YAAY;AACf,WAAO,QAAQ,OAAO,IAAI,MAAM,oCAAoC,OAAO,OAAO,CAAC,EAAE,CAAC;AAAA,EACxF;AAEA,QAAM,YAAY,KAAK,IAAI;AAC3B,QAAM,OAAO,WAAW,UAAU,UAAU;AAE5C,SAAO,IAAI,QAA4B,CAAC,SAAS,WAAW;AAC1D,QAAI;AACJ,QAAI;AACF,cAAQ,UAAU,WAAW,SAAS,MAAM,EAAE,KAAK,KAAK,OAAO,OAAO,CAAC;AAAA,IACzE,SAAS,KAAK;AACZ,aAAO,eAAe,QAAQ,MAAM,IAAI,MAAM,OAAO,GAAG,CAAC,CAAC;AAC1D;AAAA,IACF;AAEA,QAAI,SAAS;AACb,QAAI,SAAS;AACb,QAAI,WAAW;AACf,QAAI,UAAU;AAEd,UAAM,QACJ,YAAY,IACR,WAAW,MAAM;AACf,iBAAW;AACX,UAAI,CAAC,MAAM,OAAQ,OAAM,KAAK,SAAS;AAAA,IACzC,GAAG,SAAS,IACZ;AACN,QAAI,SAAS,OAAQ,MAAiC,UAAU,YAAY;AAC1E;AAAC,MAAC,MAAgC,MAAM;AAAA,IAC1C;AAEA,UAAM,UAAU,MAAM;AACpB,UAAI,CAAC,MAAM,OAAQ,OAAM,KAAK,SAAS;AAAA,IACzC;AACA,QAAI,QAAQ,QAAQ;AAClB,UAAI,QAAQ,OAAO,QAAS,SAAQ;AAAA,UAC/B,SAAQ,OAAO,iBAAiB,SAAS,SAAS,EAAE,MAAM,KAAK,CAAC;AAAA,IACvE;AAEA,UAAM,QAAQ,GAAG,QAAQ,CAAC,UAAU;AAClC,gBAAU,OAAO,KAAK;AAAA,IACxB,CAAC;AACD,UAAM,QAAQ,GAAG,QAAQ,CAAC,UAAU;AAClC,gBAAU,OAAO,KAAK;AAAA,IACxB,CAAC;AAED,UAAM,WAAW,CAAC,WAA+B;AAC/C,UAAI,QAAS;AACb,gBAAU;AACV,UAAI,MAAO,cAAa,KAAK;AAC7B,cAAQ,QAAQ,oBAAoB,SAAS,OAAO;AACpD,cAAQ,MAAM;AAAA,IAChB;AAEA,UAAM,GAAG,SAAS,CAAC,QAAQ;AACzB,UAAI,QAAS;AACb,gBAAU;AACV,UAAI,MAAO,cAAa,KAAK;AAC7B,cAAQ,QAAQ,oBAAoB,SAAS,OAAO;AACpD,aAAO,GAAG;AAAA,IACZ,CAAC;AAED,UAAM,GAAG,SAAS,CAAC,MAAM,WAAW;AAClC,eAAS;AAAA,QACP,UAAU;AAAA,QACV;AAAA,QACA;AAAA,QACA,gBAAgB;AAAA,QAChB,YAAY,KAAK,IAAI,IAAI;AAAA,QACzB;AAAA,MACF,CAAC;AAAA,IACH,CAAC;AAAA,EACH,CAAC;AACH;","names":[]}
+{"version":3,"sources":["../src/mcp/local-harness.ts"],"sourcesContent":["/**\n * @experimental\n *\n * Subprocess wrappers for the local coding-harness CLIs installed in the\n * sandbox image (claude-code, codex, opencode). Used by the in-process\n * delegation executor (`createInProcessExecutor`) so a `delegate_code` call\n * spawns a real harness on a real git worktree instead of provisioning a\n * sibling sandbox.\n *\n * All harness invocations:\n *   - run with `cwd` set to the worktree\n *   - inherit env from the parent (the MCP server inside the sandbox has\n *     the harness's auth already)\n *   - capture stdout/stderr\n *   - support cancellation via AbortSignal\n *   - enforce a wall-clock timeout\n */\n\nimport { type ChildProcess, spawn } from 'node:child_process'\n\n/** Local coding harness available inside the sandbox. */\nexport type LocalHarness = 'claude' | 'codex' | 'opencode'\n\n/** Default per-harness command + arg shape. */\nconst HARNESS_INVOCATIONS: Record<\n  LocalHarness,\n  { command: string; buildArgs: (taskPrompt: string) => string[] }\n> = {\n  claude: {\n    command: 'claude',\n    buildArgs: (taskPrompt) => ['--headless', '-p', taskPrompt],\n  },\n  codex: {\n    command: 'codex',\n    buildArgs: (taskPrompt) => ['run', taskPrompt],\n  },\n  opencode: {\n    command: 'opencode',\n    buildArgs: (taskPrompt) => ['run', taskPrompt],\n  },\n}\n\n/** @experimental */\nexport interface RunLocalHarnessOptions {\n  harness: LocalHarness\n  /** Working directory for the subprocess (typically a worktree path). */\n  cwd: string\n  /** Prompt forwarded as the harness CLI's task argument. */\n  taskPrompt: string\n  /** Wall-clock kill deadline (ms). Default 5 min. Subprocess SIGTERMed on expiry. */\n  timeoutMs?: number\n  /** Caller cancellation. SIGTERM is sent on abort. */\n  signal?: AbortSignal\n  /** Override env (defaults to inheriting from the parent). */\n  env?: NodeJS.ProcessEnv\n  /**\n   * Test seam — inject a custom spawner so unit tests can mock the\n   * subprocess without touching the OS. Defaults to node's `child_process.spawn`.\n   */\n  spawn?: (\n    command: string,\n    args: ReadonlyArray<string>,\n    opts: {\n      cwd: string\n      env: NodeJS.ProcessEnv\n      stdio: 'pipe'\n    },\n  ) => ChildProcess\n}\n\n/** @experimental */\nexport interface LocalHarnessResult {\n  /** OS exit code. `null` when killed before exit. */\n  exitCode: number | null\n  /** Concatenated stdout. */\n  stdout: string\n  /** Concatenated stderr. */\n  stderr: string\n  /** Set when the process exited via signal (timeout / abort). */\n  killedBySignal: NodeJS.Signals | null\n  /** Wall-clock duration ms (spawn → exit). */\n  durationMs: number\n  /** Set when timeoutMs elapsed before exit. */\n  timedOut: boolean\n}\n\nconst DEFAULT_TIMEOUT_MS = 5 * 60 * 1000\n\n/**\n * Spawn a local coding harness CLI as a subprocess + collect its output.\n *\n * NOT responsible for parsing the harness's output or extracting a diff —\n * the in-process executor's `streamPrompt` orchestrates `git diff` against\n * the worktree after this resolves. This function is intentionally narrow:\n * spawn, wait, capture, return.\n *\n * Fails loud — throws when:\n *   - `cwd` doesn't exist (subprocess emits ENOENT; surfaced as Error)\n *   - the harness binary is not on PATH (ENOENT)\n *\n * Does NOT throw when:\n *   - the subprocess exits non-zero (`result.exitCode` carries the code)\n *   - the subprocess is aborted / timed out (`result.killedBySignal` /\n *     `result.timedOut` carries the reason)\n *\n * @experimental\n */\nexport function runLocalHarness(options: RunLocalHarnessOptions): Promise<LocalHarnessResult> {\n  const { harness, cwd, taskPrompt } = options\n  const timeoutMs = options.timeoutMs ?? DEFAULT_TIMEOUT_MS\n  const env = options.env ?? process.env\n  const spawnImpl = options.spawn ?? spawn\n\n  const invocation = HARNESS_INVOCATIONS[harness]\n  if (!invocation) {\n    return Promise.reject(new Error(`runLocalHarness: unknown harness ${String(harness)}`))\n  }\n\n  const startedAt = Date.now()\n  const args = invocation.buildArgs(taskPrompt)\n\n  return new Promise<LocalHarnessResult>((resolve, reject) => {\n    let child: ChildProcess\n    try {\n      child = spawnImpl(invocation.command, args, { cwd, env, stdio: 'pipe' })\n    } catch (err) {\n      reject(err instanceof Error ? err : new Error(String(err)))\n      return\n    }\n\n    // The harness takes its task as an argv arg, not on stdin. Leaving stdin\n    // OPEN makes a non-TTY `opencode run` (and likely the other harnesses)\n    // BLOCK forever waiting on input — zero output, SIGTERM at the wall cap,\n    // empty patch -> \"no candidate passed validation\". Close stdin so the\n    // subprocess sees EOF and proceeds (the `cliExecutor` leaf does the same).\n    child.stdin?.end()\n\n    let stdout = ''\n    let stderr = ''\n    let timedOut = false\n    let settled = false\n\n    const timer =\n      timeoutMs > 0\n        ? setTimeout(() => {\n            timedOut = true\n            if (!child.killed) child.kill('SIGTERM')\n          }, timeoutMs)\n        : null\n    if (timer && typeof (timer as { unref?: () => void }).unref === 'function') {\n      ;(timer as { unref: () => void }).unref()\n    }\n\n    const onAbort = () => {\n      if (!child.killed) child.kill('SIGTERM')\n    }\n    if (options.signal) {\n      if (options.signal.aborted) onAbort()\n      else options.signal.addEventListener('abort', onAbort, { once: true })\n    }\n\n    child.stdout?.on('data', (chunk) => {\n      stdout += String(chunk)\n    })\n    child.stderr?.on('data', (chunk) => {\n      stderr += String(chunk)\n    })\n\n    const finalize = (result: LocalHarnessResult) => {\n      if (settled) return\n      settled = true\n      if (timer) clearTimeout(timer)\n      options.signal?.removeEventListener('abort', onAbort)\n      resolve(result)\n    }\n\n    child.on('error', (err) => {\n      if (settled) return\n      settled = true\n      if (timer) clearTimeout(timer)\n      options.signal?.removeEventListener('abort', onAbort)\n      reject(err)\n    })\n\n    child.on('close', (code, signal) => {\n      finalize({\n        exitCode: code,\n        stdout,\n        stderr,\n        killedBySignal: signal,\n        durationMs: Date.now() - startedAt,\n        timedOut,\n      })\n    })\n  })\n}\n"],"mappings":";AAkBA,SAA4B,aAAa;AAMzC,IAAM,sBAGF;AAAA,EACF,QAAQ;AAAA,IACN,SAAS;AAAA,IACT,WAAW,CAAC,eAAe,CAAC,cAAc,MAAM,UAAU;AAAA,EAC5D;AAAA,EACA,OAAO;AAAA,IACL,SAAS;AAAA,IACT,WAAW,CAAC,eAAe,CAAC,OAAO,UAAU;AAAA,EAC/C;AAAA,EACA,UAAU;AAAA,IACR,SAAS;AAAA,IACT,WAAW,CAAC,eAAe,CAAC,OAAO,UAAU;AAAA,EAC/C;AACF;AA8CA,IAAM,qBAAqB,IAAI,KAAK;AAqB7B,SAAS,gBAAgB,SAA8D;AAC5F,QAAM,EAAE,SAAS,KAAK,WAAW,IAAI;AACrC,QAAM,YAAY,QAAQ,aAAa;AACvC,QAAM,MAAM,QAAQ,OAAO,QAAQ;AACnC,QAAM,YAAY,QAAQ,SAAS;AAEnC,QAAM,aAAa,oBAAoB,OAAO;AAC9C,MAAI,CAAC,YAAY;AACf,WAAO,QAAQ,OAAO,IAAI,MAAM,oCAAoC,OAAO,OAAO,CAAC,EAAE,CAAC;AAAA,EACxF;AAEA,QAAM,YAAY,KAAK,IAAI;AAC3B,QAAM,OAAO,WAAW,UAAU,UAAU;AAE5C,SAAO,IAAI,QAA4B,CAAC,SAAS,WAAW;AAC1D,QAAI;AACJ,QAAI;AACF,cAAQ,UAAU,WAAW,SAAS,MAAM,EAAE,KAAK,KAAK,OAAO,OAAO,CAAC;AAAA,IACzE,SAAS,KAAK;AACZ,aAAO,eAAe,QAAQ,MAAM,IAAI,MAAM,OAAO,GAAG,CAAC,CAAC;AAC1D;AAAA,IACF;AAOA,UAAM,OAAO,IAAI;AAEjB,QAAI,SAAS;AACb,QAAI,SAAS;AACb,QAAI,WAAW;AACf,QAAI,UAAU;AAEd,UAAM,QACJ,YAAY,IACR,WAAW,MAAM;AACf,iBAAW;AACX,UAAI,CAAC,MAAM,OAAQ,OAAM,KAAK,SAAS;AAAA,IACzC,GAAG,SAAS,IACZ;AACN,QAAI,SAAS,OAAQ,MAAiC,UAAU,YAAY;AAC1E;AAAC,MAAC,MAAgC,MAAM;AAAA,IAC1C;AAEA,UAAM,UAAU,MAAM;AACpB,UAAI,CAAC,MAAM,OAAQ,OAAM,KAAK,SAAS;AAAA,IACzC;AACA,QAAI,QAAQ,QAAQ;AAClB,UAAI,QAAQ,OAAO,QAAS,SAAQ;AAAA,UAC/B,SAAQ,OAAO,iBAAiB,SAAS,SAAS,EAAE,MAAM,KAAK,CAAC;AAAA,IACvE;AAEA,UAAM,QAAQ,GAAG,QAAQ,CAAC,UAAU;AAClC,gBAAU,OAAO,KAAK;AAAA,IACxB,CAAC;AACD,UAAM,QAAQ,GAAG,QAAQ,CAAC,UAAU;AAClC,gBAAU,OAAO,KAAK;AAAA,IACxB,CAAC;AAED,UAAM,WAAW,CAAC,WAA+B;AAC/C,UAAI,QAAS;AACb,gBAAU;AACV,UAAI,MAAO,cAAa,KAAK;AAC7B,cAAQ,QAAQ,oBAAoB,SAAS,OAAO;AACpD,cAAQ,MAAM;AAAA,IAChB;AAEA,UAAM,GAAG,SAAS,CAAC,QAAQ;AACzB,UAAI,QAAS;AACb,gBAAU;AACV,UAAI,MAAO,cAAa,KAAK;AAC7B,cAAQ,QAAQ,oBAAoB,SAAS,OAAO;AACpD,aAAO,GAAG;AAAA,IACZ,CAAC;AAED,UAAM,GAAG,SAAS,CAAC,MAAM,WAAW;AAClC,eAAS;AAAA,QACP,UAAU;AAAA,QACV;AAAA,QACA;AAAA,QACA,gBAAgB;AAAA,QAChB,YAAY,KAAK,IAAI,IAAI;AAAA,QACzB;AAAA,MACF,CAAC;AAAA,IACH,CAAC;AAAA,EACH,CAAC;AACH;","names":[]}