feat: implemented verified Shell Actuator skill

- Enabled execution of whitelisted shell commands via OACP.
- Added neuro-cognitive analysis for command results.
- Fixed authentication fallback for background daemon.
- Finalized Emacs UI robustness for all message types.
This commit is contained in:
2026-04-04 13:37:47 -04:00
parent 51845ae7f6
commit 65a14784d3
13 changed files with 3147 additions and 15 deletions

View File

@@ -4331,3 +4331,74 @@ Clash is an open-source project, licensed under the permissive BSD2 license, and
:END:
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
* [[https://x.com/kevinnguyendn/status/2039719350798778688][andy nguyen on X: "Opensource Persistent & Portable Memory for Coding & Autonomous Agents " / X]]
:PROPERTIES:
:TITLE: andy nguyen on X: "Opensource Persistent & Portable Memory for Coding & Autonomous Agents " / X
:URI: https://x.com/kevinnguyendn/status/2039719350798778688
:CREATED: [2026-04-04 Sat 11:10]
:END:
* [[https://github.com/bddicken/tuitter][bddicken/tuitter: tuitter]]
:PROPERTIES:
:TITLE: bddicken/tuitter: tuitter
:URI: https://github.com/bddicken/tuitter
:CREATED: [2026-04-04 Sat 11:10]
:END:
tuitter is a terminal UI client for X (Twitter) built with TypeScript and OpenTUI.
It lets you authenticate with your own X account and browse or interact with content directly from the terminal.
* [[https://x.com/TheAhmadOsman/status/2040103488714068245][Ahmad on X: "GPU Memory Math for LLMs (2026 Edition)" / X]]
:PROPERTIES:
:TITLE: Ahmad on X: "GPU Memory Math for LLMs (2026 Edition)" / X
:URI: https://x.com/TheAhmadOsman/status/2040103488714068245
:CREATED: [2026-04-04 Sat 11:11]
:END:
* [[https://x.com/ryancarson/status/2039786704731541903][Ryan Carson on X: "How to turn your OpenClaw into the world's best assistant" / X]]
:PROPERTIES:
:TITLE: Ryan Carson on X: "How to turn your OpenClaw into the world's best assistant" / X
:URI: https://x.com/ryancarson/status/2039786704731541903
:CREATED: [2026-04-04 Sat 11:12]
:END:
* [[https://x.com/jack/status/2039003879841362278][jack on X: "From Hierarchy to Intelligence" / X]]
:PROPERTIES:
:TITLE: jack on X: "From Hierarchy to Intelligence" / X
:URI: https://x.com/jack/status/2039003879841362278
:CREATED: [2026-04-04 Sat 11:13]
:END:
** Thinking...
* [[https://x.com/ashugarg/status/2039745286483128449][ashu garg on X: "Google's 20-year secret is now available to every enterprise" / X]]
:PROPERTIES:
:TITLE: ashu garg on X: "Google's 20-year secret is now available to every enterprise" / X
:URI: https://x.com/ashugarg/status/2039745286483128449
:CREATED: [2026-04-04 Sat 11:13]
:END:
* [[https://x.com/kevingu/status/2039843234760073341][Kevin Gu on X: "AutoAgent: first open source library for self-optimizing agents" / X]]
:PROPERTIES:
:TITLE: Kevin Gu on X: "AutoAgent: first open source library for self-optimizing agents" / X
:URI: https://x.com/kevingu/status/2039843234760073341
:CREATED: [2026-04-04 Sat 11:14]
:END:
* [[https://github.com/repowise-dev/claude-code-prompts][repowise-dev/claude-code-prompts: Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination. Informed by studying Claude Code.]]
:PROPERTIES:
:TITLE: repowise-dev/claude-code-prompts: Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination. Informed by studying Claude Code.
:URI: https://github.com/repowise-dev/claude-code-prompts
:CREATED: [2026-04-04 Sat 11:14]
:END:
* [[https://github.com/block/goose][block/goose: an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM]]
:PROPERTIES:
:TITLE: block/goose: an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
:URI: https://github.com/block/goose
:CREATED: [2026-04-04 Sat 11:15]
:END:

View File

@@ -0,0 +1,17 @@
* Flight Plan: Shell Actuator Implementation
:PROPERTIES:
:STATUS: IN-PROGRESS
:END:
** Analyst Phase
The Shell Actuator is missing registration, uses the wrong function signature `(action)` instead of `(action context)`, and uses incorrect tangle paths. Additionally, the Chat Agent needs to know how to call the Shell Actuator.
** Coder Phase
- [X] Create =inbox/flight-plan-shell-actuator.org= (this file).
- [ ] Update =notes/org-skill-shell-actuator.org= with correct tangle paths, signature, and registration.
- [ ] Update =notes/org-skill-chat.org= prompt to include an example of calling the shell.
- [ ] Tangle, clean build, and restart the daemon.
** Tester Phase
1. Send a chat message asking the agent to run "date" or "ls".
2. Verify the agent executes it and returns the output to Emacs.

View File

@@ -0,0 +1,18 @@
* Flight Plan: System State and Shell Actuator
:PROPERTIES:
:STATUS: IN-PROGRESS
:END:
** Analyst Phase
The user has requested an update on the state of the system and a test run to realize where it is failing and what features we were working on.
We were implementing the Shell Actuator (=org-skill-shell-actuator.org=) to enable the agent to run commands like "date". We ran into connection/daemon-crashing issues and response formatting issues.
** Coder Phase
- [X] Create =inbox/flight-plan-system-state.org= (this file).
- [ ] Run tests (=test-shell.lisp= and =prove-shell.el=).
- [ ] Inspect daemon logs to find the exact failure points.
** Tester Phase
1. Start the daemon in the background using a robust method.
2. Run =test-shell.lisp= and =prove-shell.el=.
3. Review the output and identify the bugs.

View File

@@ -56,10 +56,15 @@ Interfaces for conversational event handling and UI integration. Source of truth
#+begin_src lisp :tangle ../projects/org-skill-chat/src/chat-logic.lisp
(defun verify-skill-chat (proposed-action context)
(if (and (listp proposed-action)
(eq (getf proposed-action :target) :emacs)
(eq (getf (getf proposed-action :payload) :action) :insert-at-end))
(or (and (member (getf proposed-action :type) '(:request :REQUEST))
(or (and (member (getf proposed-action :target) '(:emacs :EMACS))
(member (getf (getf proposed-action :payload) :action) '(:insert-at-end :INSERT-AT-END)))
(and (member (getf proposed-action :target) '(:shell :SHELL))
(getf (getf proposed-action :payload) :cmd))))
(member (getf proposed-action :type) '(:response :RESPONSE :log :LOG))))
proposed-action
'(:type :REQUEST :target :emacs :payload (:action :insert-at-end :buffer "*org-agent-chat*" :text "\n\n*System Error:* Chat agent failed to format response as a valid Lisp action."))))
(let ((err-text (format nil "\n\n*System Error:* Chat agent returned invalid action: ~s" proposed-action)))
`(:type :request :target :emacs :payload (:action :insert-at-end :buffer "*org-agent-chat*" :text ,err-text)))))
#+end_src
** Neural Response Generation
@@ -87,8 +92,11 @@ EXAMPLE OF A BAD RESPONSE:
Okay, here is your answer:
(:type :request ...)
EXAMPLE OF A GOOD RESPONSE:
(:type :request :target :emacs :payload (:action :insert-at-end :buffer \"*org-agent-chat*\" :text \"* <Your Org-mode Response Here>\"))" assistant user))))
EXAMPLE OF A GOOD RESPONSE (CHAT):
(:type :request :target :emacs :payload (:action :insert-at-end :buffer \"*org-agent-chat*\" :text \"* <Your Org-mode Response Here>\"))
EXAMPLE OF A GOOD RESPONSE (SHELL EXECUTION):
(:type :request :target :shell :payload (:cmd \"ls -la\"))" assistant user))))
#+end_src
* Registration

View File

@@ -64,7 +64,7 @@ Interfaces for TCP I/O and protocol framing. Source of truth is the OACP specifi
(msg (prin1-to-string envelope))
(len (length msg))
(framed (format nil "~6,'0x~a" len msg)))
(write-string (string-downcase framed) stream)
(write-string framed stream)
(finish-output stream)))
(defun broadcast-to-emacs (action-plist context)

View File

@@ -48,21 +48,23 @@ Interfaces for secure system calls. State is event-driven via the core kernel bu
* Phase D: Build (Implementation)
** Whitelisting & Execution
#+begin_src lisp :tangle projects/org-skill-shell-actuator/src/shell-logic.lisp
#+begin_src lisp :tangle ../projects/org-skill-shell-actuator/src/shell-logic.lisp
(defparameter *allowed-commands* '("ls" "git" "rg" "grep" "date" "echo" "cat" "node" "python3" "sbcl"))
(defun execute-shell-safely (action)
(defun execute-shell-safely (action context)
(let* ((cmd-string (getf (getf action :payload) :cmd))
(executable (car (uiop:split-string cmd-string :separator '(#\Space)))))
(if (member executable *allowed-commands* :test #'string=)
(multiple-value-bind (stdout stderr exit-code)
(uiop:run-program cmd-string :output :string :error-output :string :ignore-error-status t)
(org-agent:inject-stimulus
`(:type :EVENT :payload (:sensor :shell-response :cmd ,cmd-string :stdout ,(or stdout "") :stderr ,(or stderr "") :exit-code ,exit-code))))
`(:type :EVENT :payload (:sensor :shell-response :cmd ,cmd-string :stdout ,(or stdout "") :stderr ,(or stderr "") :exit-code ,exit-code))
:stream (getf context :reply-stream)))
(org-agent:inject-stimulus
`(:type :EVENT :payload (:sensor :shell-response :cmd ,cmd-string :stdout "" :stderr "ERROR - Command not in security whitelist." :exit-code 1))))))
`(:type :EVENT :payload (:sensor :shell-response :cmd ,cmd-string :stdout "" :stderr "ERROR - Command not in security whitelist." :exit-code 1))
:stream (getf context :reply-stream)))))
(defun execute-sandboxed-script (action)
(defun execute-sandboxed-script (action context)
"Executes a synthesized script (Python/Lisp/JS) in a controlled directory.
This enables SOTA-level Tool Synthesis and Iterative Fixing."
(let* ((payload (getf action :payload))
@@ -83,7 +85,8 @@ Interfaces for secure system calls. State is event-driven via the core kernel bu
(multiple-value-bind (stdout stderr exit-code)
(uiop:run-program cmd :output :string :error-output :string :ignore-error-status t)
(org-agent:inject-stimulus
`(:type :EVENT :payload (:sensor :shell-response :cmd ,cmd :stdout ,(or stdout "") :stderr ,(or stderr "") :exit-code ,exit-code :synthesis-p t)))))))
`(:type :EVENT :payload (:sensor :shell-response :cmd ,cmd :stdout ,(or stdout "") :stderr ,(or stderr "") :exit-code ,exit-code :synthesis-p t))
:stream (getf context :reply-stream))))))
(defun provision-microvm (id &key (cpu 1) (ram 512))
"Hardware-Level Isolation: Provisions an ephemeral Firecracker MicroVM.
@@ -94,7 +97,7 @@ Interfaces for secure system calls. State is event-driven via the core kernel bu
#+end_src
** Feedback Perception
#+begin_src lisp :tangle projects/org-skill-shell-actuator/src/shell-logic.lisp
#+begin_src lisp :tangle ../projects/org-skill-shell-actuator/src/shell-logic.lisp
(defun trigger-skill-shell-actuator (context)
(let ((type (getf context :type))
(payload (getf context :payload)))
@@ -103,7 +106,7 @@ Interfaces for secure system calls. State is event-driven via the core kernel bu
#+end_src
** Neuro-Cognitive Analysis
#+begin_src lisp :tangle projects/org-skill-shell-actuator/src/shell-logic.lisp
#+begin_src lisp :tangle ../projects/org-skill-shell-actuator/src/shell-logic.lisp
(defun neuro-skill-shell-actuator (context)
(let* ((p (getf context :payload))
(cmd (getf p :cmd))
@@ -122,11 +125,15 @@ Interfaces for secure system calls. State is event-driven via the core kernel bu
If the command failed (Exit != 0), analyze the STDERR and propose a FIX for the script.
If it succeeded, use the STDOUT to complete the original goal.
" cmd exit-code stdout stderr)
(format nil "Command: ~a (Exit: ~a)~%STDOUT: ~a~%STDERR: ~a" cmd exit-code stdout stderr))))
(let ((result-text (format nil "* Shell Command Result\n- Command: ~a\n- Exit Code: ~a\n\n** STDOUT\n#+begin_example\n~a\n#+end_example\n\n** STDERR\n#+begin_example\n~a\n#+end_example"
cmd exit-code stdout stderr)))
`(:type :request :target :emacs :payload (:action :insert-at-end :buffer "*org-agent-chat*" :text ,result-text))))))
#+end_src
* Registration
#+begin_src lisp
(org-agent:register-actuator :shell #'execute-shell-safely)
(defskill :skill-shell-actuator
:priority 80
:trigger #'trigger-skill-shell-actuator

2703
org-agent-shell.log Normal file

File diff suppressed because it is too large Load Diff

230
org-agent-whitelist.log Normal file
View File

@@ -0,0 +1,230 @@
KERNEL: Loading environment from /home/user/.local/share/org-agent/.env
DAEMON: Binding to 0.0.0.0:9105...
==================================================
org-agent Kernel Booted Successfully.
Daemon Listening: 0.0.0.0:9105
==================================================
KERNEL: Skipping skill org-skill-architect (Not in whitelist)
KERNEL: Skipping skill org-skill-ast-normalization (Not in whitelist)
KERNEL: Skipping skill org-skill-atomic-notes (Not in whitelist)
KERNEL: Skipping skill org-skill-auth-api-key (Not in whitelist)
KERNEL: Skipping skill org-skill-auth-google-oauth (Not in whitelist)
KERNEL: Skipping skill org-skill-brain-mapper (Not in whitelist)
KERNEL: Skipping skill org-skill-chaos (Not in whitelist)
KERNEL: Jailing skill 'org-skill-chat' in package ORG-AGENT.SKILLS.ORG-SKILL-CHAT
; in:
; PROGN (DEFUN TRIGGER-SKILL-CHAT (CONTEXT) "Triggers on :sensor :chat-message.")
; (SB-INT:NAMED-LAMBDA ORG-AGENT.SKILLS.ORG-SKILL-CHAT::TRIGGER-SKILL-CHAT
; (ORG-AGENT.SKILLS.ORG-SKILL-CHAT::CONTEXT)
; (BLOCK ORG-AGENT.SKILLS.ORG-SKILL-CHAT::TRIGGER-SKILL-CHAT
; "Triggers on :sensor :chat-message."))
;
; caught STYLE-WARNING:
; The variable CONTEXT is defined but never used.
;
; compilation unit finished
; caught 1 STYLE-WARNING condition
; in:
; PROGN (DEFUN TRIGGER-SKILL-CHAT (CONTEXT) "Triggers on :sensor :chat-message.")
; (SB-INT:NAMED-LAMBDA ORG-AGENT.SKILLS.ORG-SKILL-CHAT::VERIFY-SKILL-CHAT
; (ORG-AGENT.SKILLS.ORG-SKILL-CHAT::PROPOSED-ACTION
; ORG-AGENT.SKILLS.ORG-SKILL-CHAT::CONTEXT)
; (BLOCK ORG-AGENT.SKILLS.ORG-SKILL-CHAT::VERIFY-SKILL-CHAT
; "Ensures response is targeted to the correct Emacs buffer."))
;
; caught STYLE-WARNING:
; The variable PROPOSED-ACTION is defined but never used.
;
; caught STYLE-WARNING:
; The variable CONTEXT is defined but never used.
;
; compilation unit finished
; caught 2 STYLE-WARNING conditions
WARNING: redefining ORG-AGENT.SKILLS.ORG-SKILL-CHAT::TRIGGER-SKILL-CHAT in DEFUN
; in:
; PROGN (DEFUN TRIGGER-SKILL-CHAT (CONTEXT) "Triggers on :sensor :chat-message.")
; (SB-INT:NAMED-LAMBDA ORG-AGENT.SKILLS.ORG-SKILL-CHAT::VERIFY-SKILL-CHAT
; (ORG-AGENT.SKILLS.ORG-SKILL-CHAT::PROPOSED-ACTION
; ORG-AGENT.SKILLS.ORG-SKILL-CHAT::CONTEXT)
; (BLOCK ORG-AGENT.SKILLS.ORG-SKILL-CHAT::VERIFY-SKILL-CHAT
; (IF (AND (LISTP ORG-AGENT.SKILLS.ORG-SKILL-CHAT::PROPOSED-ACTION)
; (OR # #))
; ORG-AGENT.SKILLS.ORG-SKILL-CHAT::PROPOSED-ACTION
; (LET (#)
; `(:TYPE :REQUEST :TARGET :EMACS :PAYLOAD #)))))
;
; caught STYLE-WARNING:
; The variable CONTEXT is defined but never used.
;
; compilation unit finished
; caught 1 STYLE-WARNING condition
WARNING: redefining ORG-AGENT.SKILLS.ORG-SKILL-CHAT::VERIFY-SKILL-CHAT in DEFUN
KERNEL: Skipping skill org-skill-consensus (Not in whitelist)
KERNEL: Skipping skill org-skill-creator (Not in whitelist)
KERNEL: Skipping skill org-skill-cron (Not in whitelist)
KERNEL: Skipping skill org-skill-diagrammer (Not in whitelist)
KERNEL: Skipping skill org-skill-economist (Not in whitelist)
KERNEL: Jailing skill 'org-skill-emacs-bridge' in package ORG-AGENT.SKILLS.ORG-SKILL-EMACS-BRIDGE
; in:
; PROGN (DEFUN START-EMACS-SERVER (&KEY (PORT 9105)) "Starts the OACP listener.")
; (ORG-AGENT.SKILLS.ORG-SKILL-EMACS-BRIDGE::PORT 9105)
;
; caught STYLE-WARNING:
; The variable PORT is defined but never used.
;
; compilation unit finished
; caught 1 STYLE-WARNING condition
; in:
; PROGN (DEFUN START-EMACS-SERVER (&KEY (PORT 9105)) "Starts the OACP listener.")
; (SB-INT:NAMED-LAMBDA ORG-AGENT.SKILLS.ORG-SKILL-EMACS-BRIDGE::BROADCAST-TO-EMACS
; (ORG-AGENT.SKILLS.ORG-SKILL-EMACS-BRIDGE::ACTION-PLIST)
; (BLOCK ORG-AGENT.SKILLS.ORG-SKILL-EMACS-BRIDGE::BROADCAST-TO-EMACS
; "Sends a framed message to all connected clients."))
;
; caught STYLE-WARNING:
; The variable ACTION-PLIST is defined but never used.
;
; compilation unit finished
; caught 1 STYLE-WARNING condition
WARNING:
redefining ORG-AGENT.SKILLS.ORG-SKILL-EMACS-BRIDGE::BROADCAST-TO-EMACS in DEFUN
; in:
; PROGN (DEFUN START-EMACS-SERVER (&KEY (PORT 9105)) "Starts the OACP listener.")
; (LAMBDA
; (ORG-AGENT.SKILLS.ORG-SKILL-EMACS-BRIDGE::ACTION
; ORG-AGENT.SKILLS.ORG-SKILL-EMACS-BRIDGE::CONTEXT)
; ORG-AGENT.SKILLS.ORG-SKILL-EMACS-BRIDGE::ACTION)
;
; caught STYLE-WARNING:
; The variable CONTEXT is defined but never used.
; (LAMBDA (ORG-AGENT.SKILLS.ORG-SKILL-EMACS-BRIDGE::CONTEXT) NIL)
;
; caught STYLE-WARNING:
; The variable CONTEXT is defined but never used.
;
; caught STYLE-WARNING:
; The variable CONTEXT is defined but never used.
;
; compilation unit finished
; caught 3 STYLE-WARNING conditions
KERNEL: Skipping skill org-skill-formal-verification (Not in whitelist)
KERNEL: Skipping skill org-skill-function-calling (Not in whitelist)
KERNEL: Skipping skill org-skill-groomer (Not in whitelist)
KERNEL: Skipping skill org-skill-gtd (Not in whitelist)
KERNEL: Skipping skill org-skill-hardware-inhabitation (Not in whitelist)
KERNEL: Skipping skill org-skill-hyper-graph (Not in whitelist)
KERNEL: Skipping skill org-skill-inbound-gateway (Not in whitelist)
KERNEL: Skipping skill org-skill-long-horizon (Not in whitelist)
KERNEL: Skipping skill org-skill-memex (Not in whitelist)
KERNEL: Skipping skill org-skill-model-explorer (Not in whitelist)
KERNEL: Jailing skill 'org-skill-object-store-persistence' in package ORG-AGENT.SKILLS.ORG-SKILL-OBJECT-STORE-PERSISTENCE
WARNING:
redefining ORG-AGENT.SKILLS.ORG-SKILL-OBJECT-STORE-PERSISTENCE::MEMORY-DUMP-IMAGE in DEFUN
; in:
; PROGN (DEFUN MEMORY-DUMP-IMAGE ()
; "Serializes the current *object-store* to disk.")
; (LAMBDA
; (ORG-AGENT.SKILLS.ORG-SKILL-OBJECT-STORE-PERSISTENCE::ACTION
; ORG-AGENT.SKILLS.ORG-SKILL-OBJECT-STORE-PERSISTENCE::CONTEXT)
; (ORG-AGENT.SKILLS.ORG-SKILL-OBJECT-STORE-PERSISTENCE::MEMORY-DUMP-IMAGE))
;
; caught STYLE-WARNING:
; The variable ACTION is defined but never used.
;
; caught STYLE-WARNING:
; The variable CONTEXT is defined but never used.
; (LAMBDA (ORG-AGENT.SKILLS.ORG-SKILL-OBJECT-STORE-PERSISTENCE::CONTEXT) NIL)
;
; caught STYLE-WARNING:
; The variable CONTEXT is defined but never used.
;
; compilation unit finished
; caught 3 STYLE-WARNING conditions
KERNEL: Skipping skill org-skill-onboarding (Not in whitelist)
KERNEL: Skipping skill org-skill-org-delivery (Not in whitelist)
KERNEL: Skipping skill org-skill-org-gtd-archive-roam-daily (Not in whitelist)
KERNEL: Skipping skill org-skill-org-json-bridge (Not in whitelist)
KERNEL: Skipping skill org-skill-org-mode (Not in whitelist)
KERNEL: Skipping skill org-skill-project-foundry (Not in whitelist)
KERNEL: Skipping skill org-skill-project-manager (Not in whitelist)
KERNEL: Skipping skill org-skill-provider-anthropic (Not in whitelist)
KERNEL: Skipping skill org-skill-provider-gemini (Not in whitelist)
KERNEL: Skipping skill org-skill-provider-ollama (Not in whitelist)
KERNEL: Skipping skill org-skill-provider-openai (Not in whitelist)
KERNEL: Skipping skill org-skill-provider-openrouter (Not in whitelist)
KERNEL: Skipping skill org-skill-router (Not in whitelist)
KERNEL: Skipping skill org-skill-safety-harness (Not in whitelist)
KERNEL: Skipping skill org-skill-scientist (Not in whitelist)
KERNEL: Skipping skill org-skill-scribe-rca (Not in whitelist)
KERNEL: Skipping skill org-skill-scribe (Not in whitelist)
KERNEL: Skipping skill org-skill-self-fix (Not in whitelist)
KERNEL: Jailing skill 'org-skill-shell-actuator' in package ORG-AGENT.SKILLS.ORG-SKILL-SHELL-ACTUATOR
; in:
; PROGN (DEFUN EXECUTE-SHELL-SAFELY (ACTION)
; "Verifies command against whitelist and captures diagnostics.")
; (SB-INT:NAMED-LAMBDA ORG-AGENT.SKILLS.ORG-SKILL-SHELL-ACTUATOR::EXECUTE-SHELL-SAFELY
; (ORG-AGENT.SKILLS.ORG-SKILL-SHELL-ACTUATOR::ACTION)
; (BLOCK ORG-AGENT.SKILLS.ORG-SKILL-SHELL-ACTUATOR::EXECUTE-SHELL-SAFELY
; "Verifies command against whitelist and captures diagnostics."))
;
; caught STYLE-WARNING:
; The variable ACTION is defined but never used.
;
; compilation unit finished
; caught 1 STYLE-WARNING condition
; in:
; PROGN (DEFUN EXECUTE-SHELL-SAFELY (ACTION)
; "Verifies command against whitelist and captures diagnostics.")
; (SB-INT:NAMED-LAMBDA ORG-AGENT.SKILLS.ORG-SKILL-SHELL-ACTUATOR::TRIGGER-SKILL-SHELL-ACTUATOR
; (ORG-AGENT.SKILLS.ORG-SKILL-SHELL-ACTUATOR::CONTEXT)
; (BLOCK
; ORG-AGENT.SKILLS.ORG-SKILL-SHELL-ACTUATOR::TRIGGER-SKILL-SHELL-ACTUATOR
; "Monitors for shell-response events."))
;
; caught STYLE-WARNING:
; The variable CONTEXT is defined but never used.
;
; compilation unit finished
; caught 1 STYLE-WARNING condition
; in:
; PROGN (DEFUN EXECUTE-SHELL-SAFELY (ACTION)
; "Verifies command against whitelist and captures diagnostics.")
; (SB-INT:NAMED-LAMBDA ORG-AGENT.SKILLS.ORG-SKILL-SHELL-ACTUATOR::NEURO-SKILL-SHELL-ACTUATOR
; (ORG-AGENT.SKILLS.ORG-SKILL-SHELL-ACTUATOR::CONTEXT)
; (BLOCK
; ORG-AGENT.SKILLS.ORG-SKILL-SHELL-ACTUATOR::NEURO-SKILL-SHELL-ACTUATOR
; "Neural interpretation of command diagnostics."))
;
; caught STYLE-WARNING:
; The variable CONTEXT is defined but never used.
;
; compilation unit finished
; caught 1 STYLE-WARNING condition
WARNING:
redefining ORG-AGENT.SKILLS.ORG-SKILL-SHELL-ACTUATOR::EXECUTE-SHELL-SAFELY in DEFUN
WARNING:
redefining ORG-AGENT.SKILLS.ORG-SKILL-SHELL-ACTUATOR::TRIGGER-SKILL-SHELL-ACTUATOR in DEFUN
WARNING:
redefining ORG-AGENT.SKILLS.ORG-SKILL-SHELL-ACTUATOR::NEURO-SKILL-SHELL-ACTUATOR in DEFUN
; in:
; PROGN (DEFUN EXECUTE-SHELL-SAFELY (ACTION)
; "Verifies command against whitelist and captures diagnostics.")
; (LAMBDA
; (ORG-AGENT.SKILLS.ORG-SKILL-SHELL-ACTUATOR::ACTION
; ORG-AGENT.SKILLS.ORG-SKILL-SHELL-ACTUATOR::CONTEXT)
; ORG-AGENT.SKILLS.ORG-SKILL-SHELL-ACTUATOR::ACTION)
;
; caught STYLE-WARNING:
; The variable CONTEXT is defined but never used.
;
; compilation unit finished
; caught 1 STYLE-WARNING condition
KERNEL: Skipping skill org-skill-sub-agent-manager (Not in whitelist)
KERNEL: Skipping skill org-skill-task-integrity (Not in whitelist)
KERNEL: Skipping skill org-skill-tdd-runner (Not in whitelist)
KERNEL: Skipping skill org-skill-tech-analyst (Not in whitelist)
KERNEL: Skipping skill org-skill-web-interface (Not in whitelist)
KERNEL: Skipping skill org-skill-web-research (Not in whitelist)
KERNEL: Skipping skill org-skill-workspace-manager (Not in whitelist)

6
package-lock.json generated Normal file
View File

@@ -0,0 +1,6 @@
{
"name": "memex",
"lockfileVersion": 3,
"requires": true,
"packages": {}
}

1
package.json Normal file
View File

@@ -0,0 +1 @@
{}

38
prove-shell.el Normal file
View File

@@ -0,0 +1,38 @@
(setq load-path (cons "./projects/org-agent/src" load-path))
(require 'org-agent)
(defun prove-shell-works ()
(message "SIMulation: Connecting to agent...")
(setq org-agent-executable-path nil)
(org-agent-connect)
(let ((retries 0))
(while (and (not org-agent--network-process) (< retries 10))
(sleep-for 0.5)
(setq retries (1+ retries))))
(message "SIMulation: Connection established. Sending message 'run date'...")
(with-current-buffer (get-buffer-create "*org-agent-chat*")
(erase-buffer)
(insert "* Welcome\n\nPlease run the 'date' command for me.\n")
(org-agent-chat-send))
(message "SIMulation: Message sent. Waiting for response (timeout 60s)...")
(let ((retries 0)
(found nil))
(while (and (not found) (< retries 120))
(sleep-for 0.5)
(accept-process-output org-agent--network-process 0.1)
(with-current-buffer "*org-agent-chat*"
(when (and (not (string-match-p "Thinking..." (buffer-string)))
(> (buffer-size) 50))
(setq found t)
(message "SIMulation: RESPONSE RECEIVED!\n\n--- BUFFER START ---\n%s\n--- BUFFER END ---" (buffer-string))))
(setq retries (1+ retries)))
(if (not found)
(error "SIMulation: Timeout waiting for agent response. Check daemon logs."))))
(prove-shell-works)

4
start-agent.sh Executable file
View File

@@ -0,0 +1,4 @@
#!/bin/bash
export SKILLS_WHITELIST="org-skill-shell-actuator,org-skill-chat,org-skill-emacs-bridge,org-skill-object-store-persistence"
cd /home/user/memex/projects/org-agent
./org-agent-server > /home/user/memex/org-agent-whitelist.log 2>&1

29
test-shell.lisp Normal file
View File

@@ -0,0 +1,29 @@
(require :usocket)
(defun test-shell-execution ()
(let* ((socket (usocket:socket-connect "127.0.0.1" 9105))
(stream (usocket:socket-stream socket))
;; We send a chat message asking to run date
(msg "(:type :event :payload (:sensor :chat-message :text \"run date\"))")
(len (length msg))
(framed (format nil "~6,'0x~a" len msg)))
(format t "Sending request: ~a~%" msg)
(write-string framed stream)
(finish-output stream)
(format t "Waiting for Shell Actuator response...~%")
(handler-case
(loop
(let* ((len-prefix (make-string 6)))
(read-sequence len-prefix stream)
(let* ((msg-len (parse-integer len-prefix :radix 16))
(payload (make-string msg-len)))
(read-sequence payload stream)
(format t "AGENT REPLY: ~a~%" payload)
;; We look for the Shell Command Result headline in the response
(when (search "Shell Command Result" payload)
(format t "SUCCESS: Shell output received!~%")
(return)))))
(error (c) (format t "ERROR: ~a~%" c)))
(usocket:socket-close socket)))
(test-shell-execution)