docs: mark v0.2.0 Autonomous Self-Editing Foundation tasks as DONE
- Exposed Structural AST Editing Tools. - Implemented Reflection Loops. - Hardened Actuators (path-traversal and Merkle snapshots). - Implemented tool permission tiers (ask/allow/deny). - Validated skill hot-reload capability.
This commit is contained in:
12
gtd.org
12
gtd.org
@@ -110,7 +110,7 @@ Elevating the user interface from raw shell piping to a high-fidelity, native Li
|
|||||||
|
|
||||||
Roadmap basis: Evolutionary roadmap from README.org. Working backwards from SOTA parity.
|
Roadmap basis: Evolutionary roadmap from README.org. Working backwards from SOTA parity.
|
||||||
|
|
||||||
**** TODO 0. Autonomous Self-Editing Foundation
|
**** DONE 0. Autonomous Self-Editing Foundation
|
||||||
***** DONE org-skill-lisp-repair (Lisp syntax repair)
|
***** DONE org-skill-lisp-repair (Lisp syntax repair)
|
||||||
- Deterministic: auto-balance parens via paren-counting
|
- Deterministic: auto-balance parens via paren-counting
|
||||||
- Probabilistic: LLM generates surgical fix on =:syntax-error= events
|
- Probabilistic: LLM generates surgical fix on =:syntax-error= events
|
||||||
@@ -121,19 +121,19 @@ Roadmap basis: Evolutionary roadmap from README.org. Working backwards from SOTA
|
|||||||
- Create/update/delete headlines, set properties, manage TODO states
|
- Create/update/delete headlines, set properties, manage TODO states
|
||||||
- Handle =id:= links and internal links
|
- Handle =id:= links and internal links
|
||||||
- Pure Lisp implementation (no Emacs subprocess)
|
- Pure Lisp implementation (no Emacs subprocess)
|
||||||
***** TODO Expose Structural AST Editing Tools
|
***** DONE Expose Structural AST Editing Tools
|
||||||
- Wrap org-skill-emacs-edit into def-cognitive-tool definitions
|
- Wrap org-skill-emacs-edit into def-cognitive-tool definitions
|
||||||
- Force LLM to use semantic node updates instead of regex file I/O
|
- Force LLM to use semantic node updates instead of regex file I/O
|
||||||
***** TODO Implement Reflection Loops
|
***** DONE Implement Reflection Loops
|
||||||
- Feed rejection traces (syntax errors, policy blocks) back to LLM to trigger self-correction
|
- Feed rejection traces (syntax errors, policy blocks) back to LLM to trigger self-correction
|
||||||
***** TODO Harden Actuators
|
***** DONE Harden Actuators
|
||||||
- Fix path-traversal vulnerabilities in file I/O tools (e.g. :write-file)
|
- Fix path-traversal vulnerabilities in file I/O tools (e.g. :write-file)
|
||||||
- Enforce Merkle-snapshots on all state-modifying actions
|
- Enforce Merkle-snapshots on all state-modifying actions
|
||||||
***** TODO Implement tool permission tiers (ask/allow/deny)
|
***** DONE Implement tool permission tiers (ask/allow/deny)
|
||||||
- Per-tool permission plist stored in org-object
|
- Per-tool permission plist stored in org-object
|
||||||
- =generate-tool-belt-prompt= filters denied tools before LLM sees them
|
- =generate-tool-belt-prompt= filters denied tools before LLM sees them
|
||||||
- Ask-tier prompts user before execution
|
- Ask-tier prompts user before execution
|
||||||
***** TODO Implement skill hot-reload (=:reload-skill= tool)
|
***** DONE Implement skill hot-reload (=:reload-skill= tool)
|
||||||
- Swap compiled skill files without breaking active sockets
|
- Swap compiled skill files without breaking active sockets
|
||||||
- Reload skill into jailed package namespace
|
- Reload skill into jailed package namespace
|
||||||
- DONE: Added :reload-skill, :read-file, :write-file, :replace-string tools
|
- DONE: Added :reload-skill, :read-file, :write-file, :replace-string tools
|
||||||
|
|||||||
Reference in New Issue
Block a user