Let bots manage their hooks, with the user confirming what widens them

Bots get list_hooks, pause_hook and delete_hook, which act directly since
they only take away. A new hook, or a new name, brief or filter, or
switching a paused one back on, goes through propose_hook: it stores a
hook_proposals row and puts a [hook-proposal:ID] card in the reply, which
the user it was proposed to confirms or rejects. The card is read from
what Confirm saves, with the bot's reason labelled as its own; confirming
checks everything again and saves through the Hooks modal's helpers. A
new hook's URL is shown on the card once, to the user only, never in the
outcome the bot is told. What calls a hook, its computers and its signing
are never proposed. Only chat replies propose, and a hook call's own run
gets no hook tools, so a caller's payload can't reach them.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

src/harness/tools/bot/grab-bot-chat-tools.ts

@@ -62,8 +62,8 @@ type Params = {
      */
     onTakeOver?: (params: { ref: string }) => void;
     /**
-     * Called when the coordinator proposes an MCP server or tool for the
-     * user to confirm.
+     * Called when the bot proposes a hook, or the coordinator an MCP
+     * server, tool or skill, for the user to confirm.
      */
     onPropose?: (params: { ref: string }) => void;
     /**
@@ -120,6 +120,7 @@ export default async function grabBotChatTools({
             is_coordinator: powers.is_coordinator,
             admin_workspace_ids: powers.admin_workspace_ids,
             scopes,
+            onPropose,
         })),
         startTaskTool({
             user_id,