Chat-wake tasks live and die with their reply run

Of the 202 tasks stranded in the backlog on July 9, 200 were "Reply to ..."
wake vehicles: every agent @mention creates a task plus a queued run, the
reply goes out, and nothing ever closed the task — a task with a completed
run is never enqueued again, so each one became a permanent zombie row. On
top of that, every message in an active thread minted a fresh wake even when
the target already had one queued, multiplying runs that would each read the
same conversation.

The lifecycle contract, made explicit:
- The reply run IS the wake task's deliverable. Completing a chat_mention
  run now closes its task (backlog/in_progress -> done, via the audited
  status path). Tasks an agent moved to review are left alone.
- One pending wake per (agent, thread): wakeFromMention returns the queued
  run instead of minting a duplicate — that run reads the thread's newest
  messages when it executes anyway.
- Migration 054 heals existing rows: wake tasks whose runs are all spent
  close as done; in-flight wakes keep working. This also stops Fix 1's
  retry-budget healing from resurrecting 31 stale replies on next launch.

The chat-governance loop test now completes each pending wake run between
posts, matching how the exchange actually interleaves in production.

src/main/database/migrations/054-close-stale-wake-tasks.ts

@@ -0,0 +1,16 @@
+export const closeStaleWakeTasksSchema = `
+  -- Chat-wake tasks are conversation vehicles: the reply run is their whole
+  -- deliverable. Runs used to complete without closing them, stranding every
+  -- "Reply to ..." row in the backlog forever (a task with a completed run is
+  -- never enqueued again). Close each wake task whose runs have all been
+  -- spent; run completion closes them from now on. In-flight wakes (a queued
+  -- or running run) keep working normally.
+  update tasks
+  set status = 'done', updated_at = datetime('now')
+  where status in ('backlog', 'in_progress')
+    and exists (select 1 from task_runs r where r.task_id = tasks.id and r.trigger = 'chat_mention')
+    and not exists (select 1 from task_runs r where r.task_id = tasks.id and r.state in ('queued', 'running'));
+
+  insert into schema_migrations(version, name, applied_at)
+  values (54, 'close_stale_wake_tasks', datetime('now'));
+`;

src/main/database/schema.ts

@@ -52,6 +52,7 @@ import { financeSalesDepartmentsSchema } from "./migrations/050-finance-sales-de
 import { purgeRuntimeSnapshotBloatSchema } from "./migrations/051-purge-runtime-snapshot-bloat";
 import { avatarImagesSchema } from "./migrations/052-avatar-images";
 import { autonomousPauseSchema } from "./migrations/053-autonomous-pause";
+import { closeStaleWakeTasksSchema } from "./migrations/054-close-stale-wake-tasks";
 
 interface Migration {
   version: number;
@@ -113,6 +114,7 @@ const MIGRATIONS: Migration[] = [
   { version: 51, name: "purge_runtime_snapshot_bloat", sql: purgeRuntimeSnapshotBloatSchema },
   { version: 52, name: "avatar_images", sql: avatarImagesSchema },
   { version: 53, name: "autonomous_pause", sql: autonomousPauseSchema },
+  { version: 54, name: "close_stale_wake_tasks", sql: closeStaleWakeTasksSchema },
 ];
 
 const SCHEMA_VERSION = MIGRATIONS[MIGRATIONS.length - 1].version;