Make routines act on their own and check every bot action

Scheduled runs are pre-approved: they carry out their brief instead of drafting for confirmation. A run that can't do its brief calls report_run_failed and is retried 5 and 10 minutes later; only then does the user get one "failed after N tries" message, and the routine keeps why in last_error. Every reply and task now gets ActionCheckNote: look for an existing record before creating one, and verify an action took effect before saying it's done. Memory and instructions saves are read back, and create_bot, create_schedule, start_task and delegate_task refuse duplicates. Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-20 08:45:49 +01:00
parent 6c57fae444
commit 535adb6e16
25 changed files with 448 additions and 16 deletions
@@ -0,0 +1,21 @@
+import { describe, expect, test } from "bun:test";
+import reportRunFailedTool from "./report-run-failed-tool";
+
+const signal = new AbortController().signal;
+
+describe("reportRunFailedTool", () => {
+    test("passes the reason on", async () => {
+        const reasons: string[] = [];
+        const tool = reportRunFailedTool({ onFail: ({ reason }) => reasons.push(reason) });
+
+        await tool.run({ args: { reason: "  SMTP refused the login. " }, signal });
+
+        expect(reasons).toEqual(["SMTP refused the login."]);
+    });
+
+    test("rejects an empty reason", () => {
+        const tool = reportRunFailedTool({ onFail: () => {} });
+
+        expect(tool.schema?.safeParse({ reason: "  " }).success).toBe(false);
+    });
+});