fix(cron): route CLI-runtime cron models through compatible backend

Co-authored-by: vishutdhar <68405187+vishutdhar@users.noreply.github.com>

CHANGELOG.md

@@ -60,6 +60,7 @@ Docs: https://docs.openclaw.ai
 - Gateway: avoid repeated plugin tool descriptor config hashing so large runtime configs do not block reply startup and trigger reconnect/timeouts. (#75944) Thanks @joshavant.
 - Plugins/externalization: keep diagnostics ClawHub packages and persisted bundled-plugin relocation on npm-first install metadata for launch, and omit Discord from the core package now that its external package is published. Thanks @vincentkoc.
 - Setup/TUI: bound the Terminal hatch bootstrap run so a stalled provider request times out instead of leaving first-run hatching stuck behind the watchdog. (#76241) Thanks @joshavant.
+- Cron/CLI runtimes: route isolated cron jobs through configured CLI runtimes only when the resolved model provider is compatible, so OpenAI job overrides no longer inherit a mismatched Claude CLI backend. Thanks @vishutdhar.
 - Plugins/Codex: allow the official npm Codex plugin to install without the unsafe-install override, keep `/codex` command ownership, and cover the real npm Docker live path through managed `.openclaw/npm` dependencies plus uninstall failure proof.
 - Gateway/status: add concrete service, config, listener-owner, and log collection next steps when gateway probes fail and Bonjour finds no local gateway, so frozen or port-conflict reports include the data needed for root-cause triage. Refs #49012. Thanks @vincentkoc.
 - Codex harness: forward OpenClaw workspace bootstrap files such as `SOUL.md` through native Codex config instructions while leaving `AGENTS.md` to Codex project-doc discovery. Fixes #76273. Thanks @zknicker.

src/cron/isolated-agent.model-formatting.test.ts

@@ -401,6 +401,45 @@ describe("cron model formatting and precedence edge cases", () => {
     });
   });
 
+  describe("CLI runtime compatibility", () => {
+    it("uses a configured Claude CLI runtime for resolved Anthropic models", async () => {
+      await expectSelectedModel(
+        {
+          cfg: {
+            agents: {
+              defaults: {
+                model: "anthropic/claude-opus-4-6",
+                agentRuntime: { id: "claude-cli" },
+              },
+            },
+          },
+        },
+        { provider: "claude-cli", model: "claude-opus-4-6" },
+      );
+    });
+
+    it("keeps an OpenAI payload override on OpenAI when Claude CLI is configured", async () => {
+      await expectSelectedModel(
+        {
+          cfg: {
+            agents: {
+              defaults: {
+                model: "anthropic/claude-opus-4-6",
+                agentRuntime: { id: "claude-cli" },
+              },
+            },
+          },
+          payload: {
+            kind: "agentTurn",
+            message: DEFAULT_MESSAGE,
+            model: "openai/gpt-4.1-mini",
+          },
+        },
+        { provider: "openai", model: "gpt-4.1-mini" },
+      );
+    });
+  });
+
   describe("stored session overrides", () => {
     it("stored modelOverride/providerOverride are applied", async () => {
       await expectSelectedModel(

src/cron/isolated-agent/model-selection.ts

@@ -1,3 +1,4 @@
+import { resolveCliRuntimeExecutionProvider } from "../../agents/model-runtime-aliases.js";
 import type { OpenClawConfig } from "../../config/types.openclaw.js";
 import type { CronJob } from "../types.js";
 import {
@@ -147,5 +148,11 @@ export async function resolveCronModelSelection(
     }
   }
 
-  return { ok: true, provider, model };
+  const executionProvider =
+    resolveCliRuntimeExecutionProvider({
+      provider,
+      cfg: params.cfgWithAgentDefaults,
+    }) ?? provider;
+
+  return { ok: true, provider: executionProvider, model };
 }