@tangle-network/agent-runtime 0.72.0 → 0.74.0

package/dist/chunk-O2UPHN7X.js

@@ -0,0 +1,114 @@
+// src/mcp/local-harness.ts
+import { spawn } from "child_process";
+var HARNESS_INVOCATIONS = {
+  claude: {
+    command: "claude",
+    buildArgs: (taskPrompt) => ["--headless", "-p", taskPrompt],
+    modelArgs: (model) => ["-m", model]
+  },
+  codex: {
+    command: "codex",
+    buildArgs: (taskPrompt) => ["run", taskPrompt],
+    modelArgs: (model) => ["-m", model]
+  },
+  opencode: {
+    command: "opencode",
+    buildArgs: (taskPrompt) => ["run", taskPrompt],
+    modelArgs: (model) => ["-m", model]
+  }
+};
+function harnessInvocation(harness, profile, taskPrompt) {
+  const invocation = HARNESS_INVOCATIONS[harness];
+  if (!invocation) {
+    throw new Error(`harnessInvocation: unknown harness ${String(harness)}`);
+  }
+  const systemPrompt = profile.prompt?.systemPrompt;
+  const composedPrompt = typeof systemPrompt === "string" && systemPrompt.trim().length > 0 ? `${systemPrompt}
+
+${taskPrompt}` : taskPrompt;
+  const args = invocation.buildArgs(composedPrompt);
+  const model = profile.model?.default;
+  if (typeof model === "string" && model.length > 0) {
+    args.push(...invocation.modelArgs(model));
+  }
+  return { command: invocation.command, args };
+}
+var DEFAULT_TIMEOUT_MS = 5 * 60 * 1e3;
+function runLocalHarness(options) {
+  const { harness, cwd, taskPrompt } = options;
+  const timeoutMs = options.timeoutMs ?? DEFAULT_TIMEOUT_MS;
+  const env = options.env ?? process.env;
+  const spawnImpl = options.spawn ?? spawn;
+  const invocation = HARNESS_INVOCATIONS[harness];
+  if (!invocation) {
+    return Promise.reject(new Error(`runLocalHarness: unknown harness ${String(harness)}`));
+  }
+  const startedAt = Date.now();
+  const command = options.invocation?.command ?? invocation.command;
+  const args = options.invocation ? [...options.invocation.args] : invocation.buildArgs(taskPrompt);
+  return new Promise((resolve, reject) => {
+    let child;
+    try {
+      child = spawnImpl(command, args, { cwd, env, stdio: "pipe" });
+    } catch (err) {
+      reject(err instanceof Error ? err : new Error(String(err)));
+      return;
+    }
+    child.stdin?.end();
+    let stdout = "";
+    let stderr = "";
+    let timedOut = false;
+    let settled = false;
+    const timer = timeoutMs > 0 ? setTimeout(() => {
+      timedOut = true;
+      if (!child.killed) child.kill("SIGTERM");
+    }, timeoutMs) : null;
+    if (timer && typeof timer.unref === "function") {
+      ;
+      timer.unref();
+    }
+    const onAbort = () => {
+      if (!child.killed) child.kill("SIGTERM");
+    };
+    if (options.signal) {
+      if (options.signal.aborted) onAbort();
+      else options.signal.addEventListener("abort", onAbort, { once: true });
+    }
+    child.stdout?.on("data", (chunk) => {
+      stdout += String(chunk);
+    });
+    child.stderr?.on("data", (chunk) => {
+      stderr += String(chunk);
+    });
+    const finalize = (result) => {
+      if (settled) return;
+      settled = true;
+      if (timer) clearTimeout(timer);
+      options.signal?.removeEventListener("abort", onAbort);
+      resolve(result);
+    };
+    child.on("error", (err) => {
+      if (settled) return;
+      settled = true;
+      if (timer) clearTimeout(timer);
+      options.signal?.removeEventListener("abort", onAbort);
+      reject(err);
+    });
+    child.on("close", (code, signal) => {
+      finalize({
+        exitCode: code,
+        stdout,
+        stderr,
+        killedBySignal: signal,
+        durationMs: Date.now() - startedAt,
+        timedOut
+      });
+    });
+  });
+}
+
+export {
+  harnessInvocation,
+  runLocalHarness
+};
+//# sourceMappingURL=chunk-O2UPHN7X.js.map

package/dist/chunk-O2UPHN7X.js.map

@@ -0,0 +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'\nimport type { AgentProfile } from '@tangle-network/agent-interface'\n\n/** Local coding harness available inside the sandbox. */\nexport type LocalHarness = 'claude' | 'codex' | 'opencode'\n\n/**\n * Default per-harness command + arg shape. `buildArgs` takes ONLY the task prompt and\n * emits the prompt-only invocation (no model, no system prompt) — the historical shape\n * the in-process executor's `streamPrompt` drives. `modelArgs` maps a resolved model to\n * the harness's selector flag (every supported harness takes `-m <model>`). The §1.5\n * profile-aware mapper `harnessInvocation` composes these to thread the full\n * supervisor-authored profile (systemPrompt + model) into argv.\n */\nconst HARNESS_INVOCATIONS: Record<\n  LocalHarness,\n  {\n    command: string\n    buildArgs: (taskPrompt: string) => string[]\n    /** Map a resolved model to the harness's model-selector flag. */\n    modelArgs: (model: string) => string[]\n  }\n> = {\n  claude: {\n    command: 'claude',\n    buildArgs: (taskPrompt) => ['--headless', '-p', taskPrompt],\n    modelArgs: (model) => ['-m', model],\n  },\n  codex: {\n    command: 'codex',\n    buildArgs: (taskPrompt) => ['run', taskPrompt],\n    modelArgs: (model) => ['-m', model],\n  },\n  opencode: {\n    command: 'opencode',\n    buildArgs: (taskPrompt) => ['run', taskPrompt],\n    modelArgs: (model) => ['-m', model],\n  },\n}\n\n/** Result of mapping an `AgentProfile` + task prompt onto a harness invocation. */\nexport interface HarnessInvocation {\n  command: string\n  args: string[]\n}\n\n/**\n * Map a supervisor-authored `AgentProfile` + the per-task prompt onto a concrete harness\n * `command` + `args` (the §1.5 fix). UNLIKE the prompt-only `HARNESS_INVOCATIONS.buildArgs`\n * — which drops both the authored model and the system prompt — this threads the FULL\n * profile payload into argv:\n *\n *  - `profile.prompt.systemPrompt` → the PROMPT channel: a portable, harness-agnostic\n *    default that prepends the system prompt above the task prompt (`<system>\\n\\n<task>`),\n *    so the authored standing instructions reach EVERY harness (none of the three CLIs\n *    expose a portable replace-system-prompt flag for a one-shot non-interactive run).\n *  - `profile.model.default` → the harness's `-m <model>` selector.\n *\n * The task prompt alone is the floor; an empty/absent profile yields exactly the legacy\n * `buildArgs(taskPrompt)` shape so existing callers are byte-identical.\n */\nexport function harnessInvocation(\n  harness: LocalHarness,\n  profile: AgentProfile,\n  taskPrompt: string,\n): HarnessInvocation {\n  const invocation = HARNESS_INVOCATIONS[harness]\n  if (!invocation) {\n    throw new Error(`harnessInvocation: unknown harness ${String(harness)}`)\n  }\n\n  const systemPrompt = profile.prompt?.systemPrompt\n  const composedPrompt =\n    typeof systemPrompt === 'string' && systemPrompt.trim().length > 0\n      ? `${systemPrompt}\\n\\n${taskPrompt}`\n      : taskPrompt\n\n  const args = invocation.buildArgs(composedPrompt)\n\n  const model = profile.model?.default\n  if (typeof model === 'string' && model.length > 0) {\n    args.push(...invocation.modelArgs(model))\n  }\n\n  return { command: invocation.command, args }\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  /**\n   * Pre-built command + args (e.g. from `harnessInvocation` so the full authored\n   * `AgentProfile` — systemPrompt + model — reaches the harness). When set it OVERRIDES the\n   * default prompt-only `buildArgs(taskPrompt)` path; `command` defaults to the harness's\n   * default binary when only `args` is supplied. When absent the legacy prompt-only shape\n   * is used unchanged.\n   */\n  invocation?: { command?: string; args: ReadonlyArray<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 command = options.invocation?.command ?? invocation.command\n  const args = options.invocation ? [...options.invocation.args] : invocation.buildArgs(taskPrompt)\n\n  return new Promise<LocalHarnessResult>((resolve, reject) => {\n    let child: ChildProcess\n    try {\n      child = spawnImpl(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;AAczC,IAAM,sBAQF;AAAA,EACF,QAAQ;AAAA,IACN,SAAS;AAAA,IACT,WAAW,CAAC,eAAe,CAAC,cAAc,MAAM,UAAU;AAAA,IAC1D,WAAW,CAAC,UAAU,CAAC,MAAM,KAAK;AAAA,EACpC;AAAA,EACA,OAAO;AAAA,IACL,SAAS;AAAA,IACT,WAAW,CAAC,eAAe,CAAC,OAAO,UAAU;AAAA,IAC7C,WAAW,CAAC,UAAU,CAAC,MAAM,KAAK;AAAA,EACpC;AAAA,EACA,UAAU;AAAA,IACR,SAAS;AAAA,IACT,WAAW,CAAC,eAAe,CAAC,OAAO,UAAU;AAAA,IAC7C,WAAW,CAAC,UAAU,CAAC,MAAM,KAAK;AAAA,EACpC;AACF;AAuBO,SAAS,kBACd,SACA,SACA,YACmB;AACnB,QAAM,aAAa,oBAAoB,OAAO;AAC9C,MAAI,CAAC,YAAY;AACf,UAAM,IAAI,MAAM,sCAAsC,OAAO,OAAO,CAAC,EAAE;AAAA,EACzE;AAEA,QAAM,eAAe,QAAQ,QAAQ;AACrC,QAAM,iBACJ,OAAO,iBAAiB,YAAY,aAAa,KAAK,EAAE,SAAS,IAC7D,GAAG,YAAY;AAAA;AAAA,EAAO,UAAU,KAChC;AAEN,QAAM,OAAO,WAAW,UAAU,cAAc;AAEhD,QAAM,QAAQ,QAAQ,OAAO;AAC7B,MAAI,OAAO,UAAU,YAAY,MAAM,SAAS,GAAG;AACjD,SAAK,KAAK,GAAG,WAAW,UAAU,KAAK,CAAC;AAAA,EAC1C;AAEA,SAAO,EAAE,SAAS,WAAW,SAAS,KAAK;AAC7C;AAsDA,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,UAAU,QAAQ,YAAY,WAAW,WAAW;AAC1D,QAAM,OAAO,QAAQ,aAAa,CAAC,GAAG,QAAQ,WAAW,IAAI,IAAI,WAAW,UAAU,UAAU;AAEhG,SAAO,IAAI,QAA4B,CAAC,SAAS,WAAW;AAC1D,QAAI;AACJ,QAAI;AACF,cAAQ,UAAU,SAAS,MAAM,EAAE,KAAK,KAAK,OAAO,OAAO,CAAC;AAAA,IAC9D,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":[]}

package/dist/{chunk-HXVMLRYU.js → chunk-QKNBYHMK.js}

@@ -1,6 +1,3 @@
-import {
-  runAnalystLoop
-} from "./chunk-P5OKDSLB.js";
 import {
   createKbGate
 } from "./chunk-FNMGYYSS.js";
@@ -8,13 +5,16 @@ import {
   definePersona,
   runPersonified,
   worktreeFanout
-} from "./chunk-PHKNOAOU.js";
+} from "./chunk-SA5GCF2X.js";
 import {
   createExecutorRegistry
-} from "./chunk-55WKGOGU.js";
+} from "./chunk-ZKMOIEOB.js";
+import {
+  runAnalystLoop
+} from "./chunk-IODKUOBA.js";
 import {
   ConfigError
-} from "./chunk-VLF5RHEQ.js";
+} from "./chunk-NBV35BR6.js";
 
 // src/loop-runner.ts
 import {
@@ -196,4 +196,4 @@ export {
   runLoopRunnerCli,
   parseLoopRunnerArgv
 };
-//# sourceMappingURL=chunk-HXVMLRYU.js.map
+//# sourceMappingURL=chunk-QKNBYHMK.js.map

package/dist/{chunk-PHKNOAOU.js → chunk-SA5GCF2X.js}

@@ -8,6 +8,7 @@ import {
   createWorktreeCliExecutor,
   defaultSelectWinner,
   gateOnDeliverable,
+  isAbortError,
   notifyRuntimeHookEvent,
   probeSandboxCapabilities,
   randomSuffix,
@@ -16,15 +17,14 @@ import {
   settledToIteration,
   sleep,
   stringifySafe,
-  throwIfAborted,
   withDriverExecutor,
   zeroTokenUsage
-} from "./chunk-55WKGOGU.js";
+} from "./chunk-ZKMOIEOB.js";
 import {
   AnalystError,
   PlannerError,
   ValidationError
-} from "./chunk-VLF5RHEQ.js";
+} from "./chunk-NBV35BR6.js";
 
 // src/runtime/index.ts
 import { computeFindingId, makeFinding as makeFinding2 } from "@tangle-network/agent-eval";
@@ -2515,6 +2515,18 @@ function printBenchmarkReport(report) {
 }
 
 // src/runtime/sandbox-run.ts
+var SandboxRunAbortError = class extends Error {
+  name = "AbortError";
+  /** Events drained from the stream before the abort interrupted the turn. */
+  events;
+  /** The last artifact read error, if the abort fired during the retry loop. */
+  readError;
+  constructor(events, readError) {
+    super("aborted");
+    this.events = events;
+    if (readError !== void 0) this.readError = readError;
+  }
+};
 async function openSandboxRun(client, options, deliverable) {
   const runId = options.runId ?? `sandbox-run-${randomSuffix()}`;
   const now = options.now ?? Date.now;
@@ -2567,17 +2579,22 @@ async function openSandboxRun(client, options, deliverable) {
   });
   async function settle2(box, events) {
     const collected = [];
-    for await (const ev of events) collected.push(ev);
+    try {
+      for await (const ev of events) collected.push(ev);
+    } catch (err) {
+      if (isAbortError(err)) throw new SandboxRunAbortError(collected);
+      throw err;
+    }
     if (deliverable.kind === "events") {
       return { out: deliverable.fromEvents(collected), events: collected };
     }
-    throwIfAborted(options.signal);
+    if (options.signal.aborted) throw new SandboxRunAbortError(collected);
     let raw = "";
     let readError;
     const readAttempts = 4;
     const readDelayMs = options.readRetryDelayMs ?? 1e3;
     for (let attempt = 0; attempt < readAttempts; attempt += 1) {
-      throwIfAborted(options.signal);
+      if (options.signal.aborted) throw new SandboxRunAbortError(collected, readError);
       try {
         raw = await box.fs.read(deliverable.path);
         readError = void 0;
@@ -3992,6 +4009,7 @@ export {
   runAgentic,
   runBenchmark,
   printBenchmarkReport,
+  SandboxRunAbortError,
   openSandboxRun,
   strategyAuthorContract,
   assertStrategyContract,
@@ -4018,4 +4036,4 @@ export {
   computeFindingId,
   makeFinding2 as makeFinding
 };
-//# sourceMappingURL=chunk-PHKNOAOU.js.map
+//# sourceMappingURL=chunk-SA5GCF2X.js.map