fix(13-08): declined actions never re-prompt + timeout chain covers the human wait

Two more on-device UAT findings:

1. Deny-retry loop: the model, told 'the user declined', simply called the
   tool again — each retry minted a fresh pending and re-opened the dialog
   (T-13-50 habituation, mechanized). ToolExecCtx now remembers declined
   actions for the turn, keyed by confirm::action_key — the same canonical
   (tool_name, validated_args) identity the nonce binds — and execute_tool
   refuses a re-ask before the gate, minting nothing. Regression test
   declined_action_never_reprompts_same_turn.

2. Timeout chain: rpcClient's 15s default aborted every confirmable turn
   client-side while the node kept the pending alive — the next turn then
   re-announced it (modal over and over) and every wait read as 'timed
   out'. assistant.chat now rides a 420s timeout; AIUI's bridge goes
   180s→430s so the host's error path (which also expires the dialog)
   always fires first. Declined ToolResult text now also tells the model
   to stop.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

aiui/packages/app/src/services/archyBridge.ts

@@ -278,14 +278,17 @@ export const archyBridge = {
         text,
       })
 
-      // Matches the node's ASSISTANT_HTTP_TIMEOUT (180s) — the assistant
-      // loop's tool-calling round trip can legitimately take that long.
+      // Must cover the node's WHOLE turn: multiple model round trips
+      // (ASSISTANT_HTTP_TIMEOUT 180s each) plus the confirm gate's
+      // human-speed wait (CONFIRM_TIMEOUT 300s). Kept just ABOVE the host
+      // page's own assistant.chat RPC timeout (420s) so the host's error
+      // path — which also expires the confirm dialog — fires first.
       setTimeout(() => {
         if (pendingRequests.has(id)) {
           pendingRequests.delete(id)
           reject(new Error('Chat request timed out'))
         }
-      }, 180000)
+      }, 430000)
     })
   },