feat(org-agent): sync Lisp Sandboxing implementation and tests
This commit is contained in:
6
gtd.org
6
gtd.org
@@ -100,7 +100,11 @@ Slim down the org-agent microkernel by moving non-essential cognitive functions
|
||||
:LOGBOOK:
|
||||
- State "DONE" from "TODO" [2026-04-09 Thu 15:35]
|
||||
:END:
|
||||
*** TODO Implement True Lisp Sandboxing (eval-safe mechanism in core and policy in skills)
|
||||
*** DONE Implement True Lisp Sandboxing (eval-safe mechanism in core and policy in skills)
|
||||
CLOSED: [2026-04-09 Thu 16:28]
|
||||
:LOGBOOK:
|
||||
- State "DONE" from "TODO" [2026-04-09 Thu 16:28]
|
||||
:END:
|
||||
*** DONE Decouple Vendor Logic from System 1 (Move Google/Anthropic/OpenAI to Skills)
|
||||
*** TODO Implement `org-skill-lisp-repair` (Self-correcting syntax gate for System 2)
|
||||
*** TODO Implement `org-skill-formal-verification` (Prove safety of high-impact actions)
|
||||
|
||||
Reference in New Issue
Block a user