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

@@ -140,8 +140,8 @@ export default async function runBotReply({
 
     const take_overs: string[] = [];
     /**
-     * The MCP servers and tools the coordinator proposed: their cards need
-     * the user just like a take-over.
+     * The hooks the bot proposed, and the MCP servers, tools and skills the
+     * coordinator did: their cards need the user just like a take-over.
      */
     const proposals: string[] = [];
     /**

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

@@ -155,6 +155,7 @@ export default async function runBotTask({
                 is_coordinator: powers.is_coordinator,
                 admin_workspace_ids: powers.admin_workspace_ids,
                 scopes,
+                hooked,
             })),
             ...admin_tools,
             ...(powers.is_coordinator