fix(agents): deny apply_patch for GPT models to prevent verification hangs (#2935)

GPT models (5.3-codex, 5.4, etc.) frequently hang when using apply_patch
due to verification loops. This adds:

1. Tool restriction: apply_patch is denied for GPT variants of
   Hephaestus, Sisyphus-Junior, and Sisyphus agents
2. Prompt guidance: GPT-specific prompts now explicitly instruct using
   edit/write tools instead of apply_patch
3. Removed the 'Always use apply_patch' instruction from
   sisyphus-junior/gpt-5-4.ts that contradicted the fix

The deny is model-conditional — Claude variants retain apply_patch
access since it works reliably there.

src/agents/sisyphus.ts

@@ -492,6 +492,7 @@ export function createSisyphusAgent(
       permission: {
         question: "allow",
         call_omo_agent: "deny",
+        apply_patch: "deny",
       } as AgentConfig["permission"],
       reasoningEffort: "medium",
     };
@@ -531,6 +532,7 @@ export function createSisyphusAgent(
   const permission = {
     question: "allow",
     call_omo_agent: "deny",
+    ...(isGptModel(model) ? { apply_patch: "deny" as const } : {}),
   } as AgentConfig["permission"];
   const base = {
     description: