fix(server): agents can continue the same reviewer conversation#23253

@@ -27,9 +23,29 @@ function matchesWebhookFilter(filter: ScheduledTaskWebhookFilter, value: unknown
       return filter.value.includes(text);
     case "startsWith":
       return text.startsWith(filter.value);
+    case "exists":
+      return true;
   }
 }
 
+/**
+ * Placeholders render null as missing, so filters treat it the same way. A
+ * path with a `[]` wildcard resolves to a list: `equals`, `in` and
+ * `startsWith` match when any element does, `notEquals` only when none equals
+ * the value, and `exists` when the list has an element.
+ */
+function matchesWebhookFilter(filter: ScheduledTaskWebhookFilter, value: unknown): boolean {
+  if (Array.isArray(value) && /\[\]/.test(filter.path)) {
+    const texts = value.map(scalarText).filter((text): text is string => text !== undefined);
+    if (filter.op === "notEquals") return texts.every((text) => text !== filter.value);
+    return texts.some((text) => matchesScalar(filter, text));

@@ -27,9 +23,29 @@ function matchesWebhookFilter(filter: ScheduledTaskWebhookFilter, value: unknown
       return filter.value.includes(text);
     case "startsWith":
       return text.startsWith(filter.value);
+    case "exists":
+      return true;
   }
 }
 
+/**
+ * Placeholders render null as missing, so filters treat it the same way. A
+ * path with a `[]` wildcard resolves to a list: `equals`, `in` and
+ * `startsWith` match when any element does, `notEquals` only when none equals
+ * the value, and `exists` when the list has an element.
+ */
+function matchesWebhookFilter(filter: ScheduledTaskWebhookFilter, value: unknown): boolean {
+  if (Array.isArray(value) && /\[\]/.test(filter.path)) {
+    const texts = value.map(scalarText).filter((text): text is string => text !== undefined);
+    if (filter.op === "notEquals") return texts.every((text) => text !== filter.value);
+    return texts.some((text) => matchesScalar(filter, text));

@@ -252,13 +252,13 @@ omits it for a provider that offers all of them. When the target lists
 `runtimeModes`, an explicit `runtimeMode` outside that list is refused, and an
 inherited mode steps down to the broadest mode the target offers.
 
-Each delegated review round uses a new `delegate_task` call with the original brief,
+Each independent review round uses a new `delegate_task` call with the original brief,
 prior findings, responses, and unresolved objections. Track each round by its own `taskId` and use
 a distinct `clientRequestId` per round, stable across retries of that round.
-`childThreadId` is backing storage, not a target for another review round through
-`t3_thread_send`. Ordinary thread messaging remains available for user-requested
-conversations; it does not reopen a completed task. There is no task-level follow-up
-API for preserving the same reviewer session.
+`childThreadId` is backing storage, not a target for another independent review round through
+`t3_thread_send`. A follow-up that needs the same child's conversation goes to
+`childThreadId` through `t3_thread_send`; it starts a fresh task in that thread and
+does not reopen the completed one.