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]>

src/bots-queue/run-bot-reply.ts

@@ -1,6 +1,7 @@
 import type { BUN_SQLITE_COBBLE_BOTS } from "@/db/types/db";
 import { AppData } from "@/src/data/app-data";
 import {
+    ActionCheckNote,
     ChatReplyNote,
     CoordinatorReplyNote,
     CoordinatorSoloNote,
@@ -110,6 +111,7 @@ export default async function runBotReply({
                 prompt,
                 carry_over,
                 ChatReplyNote,
+                ActionCheckNote,
                 workspace_id ? WorkspaceLearningNote : "",
                 composeComputersNote({
                     computers,