feat(agents): add centralized GPT apply_patch permission guard

Extract hardcoded GPT apply_patch permission logic into a reusable module
to ensure consistent behavior across all agents. This prevents GPT models
from using the unreliable apply_patch tool while allowing other models.

- Add gpt-apply-patch-guard.ts with GPT_APPLY_PATCH_GUIDANCE and getGptApplyPatchPermission
- Update Hephaestus agent to use centralized permission logic
- Update Sisyphus-Junior agent to use centralized permission logic
- Update all GPT prompt builders to reference shared guidance constant

🤖 Generated with assistance of OhMyOpenCode

This commit is contained in:

YeonGyu-Kim

2026-04-10 10:47:27 +09:00

parent 498d021dc2

commit 2083cb0710

18 changed files with 87 additions and 41 deletions

									
										src/plugin-interface.test.ts
									
		+1
		
												View File
												
				@@ -15,6 +15,7 @@ import {

				  updateSessionAgent,

				} from "./features/claude-code-session-state"

				describe("createPluginInterface - command.execute.before", () => {

				  let testDir = ""