fix: codex and similar processes keep dying on pty, solved by refactoring process spawning (#14257)

* exec: clean up PTY resources on timeout and exit

* cli: harden resume cleanup and watchdog stalled runs

* cli: productionize PTY and resume reliability paths

* docs: add PTY process supervision architecture plan

* docs: rewrite PTY supervision plan as pre-rewrite baseline

* docs: switch PTY supervision plan to one-go execution

* docs: add one-line root cause to PTY supervision plan

* docs: add OS contracts and test matrix to PTY supervision plan

* docs: define process-supervisor package placement and scope

* docs: tie supervisor plan to existing CI lanes

* docs: place PTY supervisor plan under src/process

* refactor(process): route exec and cli runs through supervisor

* docs(process): refresh PTY supervision plan

* wip

* fix(process): harden supervisor timeout and PTY termination

* fix(process): harden supervisor adapters env and wait handling

* ci: avoid failing formal conformance on comment permissions

* test(ui): fix cron request mock argument typing

* fix(ui): remove leftover conflict marker

* fix: supervise PTY processes (#14257) (openclaw#14257) (thanks @onutc)

src/agents/cli-runner/reliability.ts

@@ -0,0 +1,88 @@
+import path from "node:path";
+import type { CliBackendConfig } from "../../config/types.js";
+import {
+  CLI_FRESH_WATCHDOG_DEFAULTS,
+  CLI_RESUME_WATCHDOG_DEFAULTS,
+  CLI_WATCHDOG_MIN_TIMEOUT_MS,
+} from "../cli-watchdog-defaults.js";
+
+function pickWatchdogProfile(
+  backend: CliBackendConfig,
+  useResume: boolean,
+): {
+  noOutputTimeoutMs?: number;
+  noOutputTimeoutRatio: number;
+  minMs: number;
+  maxMs: number;
+} {
+  const defaults = useResume ? CLI_RESUME_WATCHDOG_DEFAULTS : CLI_FRESH_WATCHDOG_DEFAULTS;
+  const configured = useResume
+    ? backend.reliability?.watchdog?.resume
+    : backend.reliability?.watchdog?.fresh;
+
+  const ratio = (() => {
+    const value = configured?.noOutputTimeoutRatio;
+    if (typeof value !== "number" || !Number.isFinite(value)) {
+      return defaults.noOutputTimeoutRatio;
+    }
+    return Math.max(0.05, Math.min(0.95, value));
+  })();
+  const minMs = (() => {
+    const value = configured?.minMs;
+    if (typeof value !== "number" || !Number.isFinite(value)) {
+      return defaults.minMs;
+    }
+    return Math.max(CLI_WATCHDOG_MIN_TIMEOUT_MS, Math.floor(value));
+  })();
+  const maxMs = (() => {
+    const value = configured?.maxMs;
+    if (typeof value !== "number" || !Number.isFinite(value)) {
+      return defaults.maxMs;
+    }
+    return Math.max(CLI_WATCHDOG_MIN_TIMEOUT_MS, Math.floor(value));
+  })();
+
+  return {
+    noOutputTimeoutMs:
+      typeof configured?.noOutputTimeoutMs === "number" &&
+      Number.isFinite(configured.noOutputTimeoutMs)
+        ? Math.max(CLI_WATCHDOG_MIN_TIMEOUT_MS, Math.floor(configured.noOutputTimeoutMs))
+        : undefined,
+    noOutputTimeoutRatio: ratio,
+    minMs: Math.min(minMs, maxMs),
+    maxMs: Math.max(minMs, maxMs),
+  };
+}
+
+export function resolveCliNoOutputTimeoutMs(params: {
+  backend: CliBackendConfig;
+  timeoutMs: number;
+  useResume: boolean;
+}): number {
+  const profile = pickWatchdogProfile(params.backend, params.useResume);
+  // Keep watchdog below global timeout in normal cases.
+  const cap = Math.max(CLI_WATCHDOG_MIN_TIMEOUT_MS, params.timeoutMs - 1_000);
+  if (profile.noOutputTimeoutMs !== undefined) {
+    return Math.min(profile.noOutputTimeoutMs, cap);
+  }
+  const computed = Math.floor(params.timeoutMs * profile.noOutputTimeoutRatio);
+  const bounded = Math.min(profile.maxMs, Math.max(profile.minMs, computed));
+  return Math.min(bounded, cap);
+}
+
+export function buildCliSupervisorScopeKey(params: {
+  backend: CliBackendConfig;
+  backendId: string;
+  cliSessionId?: string;
+}): string | undefined {
+  const commandToken = path
+    .basename(params.backend.command ?? "")
+    .trim()
+    .toLowerCase();
+  const backendToken = params.backendId.trim().toLowerCase();
+  const sessionToken = params.cliSessionId?.trim();
+  if (!sessionToken) {
+    return undefined;
+  }
+  return `cli:${backendToken}:${commandToken}:${sessionToken}`;
+}