181 lines
7.4 KiB
Org Mode
181 lines
7.4 KiB
Org Mode
#+PROPERTY: header-args:lisp :tangle (concat (getenv "INSTALL_DIR") "/skills/org-skill-scribe.lisp" (expand-file-name ""))
|
|
:PROPERTIES:
|
|
:ID: scribe-skill
|
|
:CREATED: [2026-04-13 Mon 18:40]
|
|
:END:
|
|
#+TITLE: SKILL: Autonomous Scribe (Knowledge Distillation)
|
|
#+STARTUP: content
|
|
#+FILETAGS: :scribe:distillation:memex:autonomy:
|
|
|
|
* Overview
|
|
The *Autonomous Scribe* is the background architect of the Memex. It is responsible for the "Nightly Distillation": a process that scans chronological daily logs, extracts evergreen concepts, and formalizes them into atomic Zettelkasten notes.
|
|
|
|
* Phase A: Demand (PRD)
|
|
:PROPERTIES:
|
|
:STATUS: SIGNED
|
|
:END:
|
|
|
|
** 1. Purpose
|
|
Automate the conversion of ephemeral, time-stamped thoughts into a permanent, structured knowledge graph.
|
|
|
|
** 2. Success Criteria
|
|
- [ ] *Capture:* Identify new headlines in the `daily/` directory that haven't been distilled yet.
|
|
- [ ] *Privacy:* Strictly ignore any node tagged with `@personal`.
|
|
- [ ] *Extraction:* Use neural reasoning to extract atomic concepts from raw logs.
|
|
- [ ] *Formalization:* Create new `.org` files in the `notes/` directory with proper Org-ID and back-links to the source.
|
|
|
|
* Phase B: Blueprint (PROTOCOL)
|
|
:PROPERTIES:
|
|
:STATUS: SIGNED
|
|
:END:
|
|
|
|
** 1. Architectural Intent
|
|
The Scribe reacts to the `:heartbeat` sensor. It maintains a state file (`scribe-state.lisp`) to track the last processed timestamp. It performs a "Read-Reason-Write" loop:
|
|
1. **Read:** Scan `daily/*.org` for nodes updated after the last checkpoint.
|
|
2. **Reason:** Ask the LLM to "Extract atomic notes from this text".
|
|
3. **Write:** Commit the resulting nodes to the `notes/` directory.
|
|
|
|
** 2. Semantic Interfaces
|
|
- Trigger: `(:sensor :heartbeat)`
|
|
- Action: `(:type :REQUEST :target :system :action :create-note :title "..." :content "..." :source-id "...")`
|
|
|
|
* Phase D: Build (Implementation)
|
|
|
|
** Package Context
|
|
#+begin_src lisp
|
|
(in-package :opencortex)
|
|
#+end_src
|
|
|
|
** State: Checkpoint Management
|
|
We track the last processed universal time to avoid redundant distillation.
|
|
|
|
#+begin_src lisp
|
|
(defvar *scribe-last-checkpoint* 0
|
|
"The universal-time of the last successful distillation run.")
|
|
|
|
(defun scribe-load-state ()
|
|
"Loads the scribe checkpoint from the state directory."
|
|
(let ((state-file (uiop:merge-pathnames* "state/scribe-checkpoint.lisp" (asdf:system-source-directory :opencortex))))
|
|
(if (uiop:file-exists-p state-file)
|
|
(setf *scribe-last-checkpoint* (read-from-string (uiop:read-file-string state-file)))
|
|
(setf *scribe-last-checkpoint* 0))))
|
|
|
|
(defun scribe-save-state ()
|
|
"Saves the current universal-time as the new checkpoint."
|
|
(let ((state-file (uiop:merge-pathnames* "state/scribe-checkpoint.lisp" (asdf:system-source-directory :opencortex))))
|
|
(ensure-directories-exist state-file)
|
|
(with-open-file (out state-file :direction :output :if-exists :supersede)
|
|
(format out "~a" (get-universal-time)))))
|
|
#+end_src
|
|
|
|
** Filtering: Privacy & Relevance
|
|
The Scribe only cares about non-personal, non-distilled headlines.
|
|
|
|
#+begin_src lisp
|
|
(defun scribe-get-distillable-nodes ()
|
|
"Returns a list of org-objects from the daily/ folder that require distillation."
|
|
(let ((results nil))
|
|
(maphash (lambda (id obj)
|
|
(declare (ignore id))
|
|
(let* ((attrs (org-object-attributes obj))
|
|
(tags (getf attrs :TAGS))
|
|
(type (org-object-type obj))
|
|
(version (org-object-version obj)))
|
|
(when (and (eq type :HEADLINE)
|
|
(> version *scribe-last-checkpoint*)
|
|
(not (member "@personal" tags :test #'string-equal)))
|
|
(push obj results))))
|
|
*memory*)
|
|
results))
|
|
#+end_src
|
|
|
|
** Probabilistic: Extraction Prompt
|
|
The LLM is tasked with identifying atomic concepts within the raw text.
|
|
|
|
#+begin_src lisp
|
|
(defun probabilistic-skill-scribe (context)
|
|
"Generates the extraction prompt for the Scribe."
|
|
(let* ((payload (getf context :payload))
|
|
(nodes (scribe-get-distillable-nodes)))
|
|
(if nodes
|
|
(let ((text-to-process ""))
|
|
(dolist (node nodes)
|
|
(setf text-to-process (concatenate 'string text-to-process
|
|
(format nil "ID: ~a~%TITLE: ~a~%CONTENT: ~a~%---~%"
|
|
(org-object-id node)
|
|
(getf (org-object-attributes node) :TITLE)
|
|
(org-object-content node)))))
|
|
(format nil "DISTILLATION TASK:
|
|
Below are raw chronological logs from my daily journal.
|
|
Extract ATOMIC EVERGREEN NOTES from this text.
|
|
|
|
RULES:
|
|
1. One note per distinct concept.
|
|
2. Output a list of Lisp plists: ((:title \"...\" :content \"...\" :source-id \"...\") ...)
|
|
3. The content should be in Org-mode format.
|
|
4. Keep titles descriptive and snake_case.
|
|
|
|
TEXT:
|
|
~a" text-to-process))
|
|
nil)))
|
|
#+end_src
|
|
|
|
** Deterministic: Note Committal
|
|
The deterministic gate receives the list of proposed notes and writes them to the filesystem.
|
|
|
|
#+begin_src lisp
|
|
(defun scribe-commit-notes (proposals)
|
|
"Writes proposed atomic notes to the notes/ directory. Appends if the note exists."
|
|
(let ((notes-dir (uiop:merge-pathnames* "notes/" (asdf:system-source-directory :opencortex))))
|
|
(ensure-directories-exist notes-dir)
|
|
(dolist (note proposals)
|
|
(let* ((title (getf note :title))
|
|
(content (getf note :content))
|
|
(source-id (getf note :source-id))
|
|
(filename (format nil "~a.org" (string-downcase (cl-ppcre:regex-replace-all " " title "_"))))
|
|
(path (merge-pathnames filename notes-dir)))
|
|
(if (uiop:file-exists-p path)
|
|
(with-open-file (out path :direction :output :if-exists :append)
|
|
(format out "~%~%* Appended insight from ~a~%~a" source-id content))
|
|
(with-open-file (out path :direction :output :if-exists :supersede)
|
|
(format out ":PROPERTIES:~%:ID: ~a~%:SOURCE_ID: ~a~%:END:~%#+TITLE: ~a~%~%~a"
|
|
(org-id-new) source-id title content)))
|
|
(harness-log "SCRIBE: Processed evergreen note ~a" filename)))))
|
|
|
|
(defun verify-skill-scribe (action context)
|
|
"Executes the note creation and marks source nodes as distilled."
|
|
(declare (ignore context))
|
|
(let ((data (cond ((and (listp action) (eq (getf action :type) :REQUEST))
|
|
(getf (getf action :payload) :payload))
|
|
((and (listp action) (not (member (getf action :type) '(:LOG :EVENT))))
|
|
action)
|
|
(t nil))))
|
|
(when data
|
|
(harness-log "SCRIBE: Committing ~a atomic notes..." (length data))
|
|
(scribe-commit-notes data)
|
|
(scribe-save-state)
|
|
(harness-log "SCRIBE: Distillation complete.")
|
|
;; Return a log event to stop the loop
|
|
(list :type :LOG :payload (list :text "Distillation successful.")))))
|
|
#+end_src
|
|
|
|
** Skill Registration
|
|
#+begin_src lisp
|
|
(defskill :skill-scribe
|
|
:priority 50
|
|
:trigger (lambda (ctx)
|
|
(let* ((payload (getf ctx :payload))
|
|
(sensor (getf payload :sensor)))
|
|
(and (eq sensor :heartbeat)
|
|
;; Only run once per hour to check if we need to distill
|
|
(> (- (get-universal-time) *scribe-last-checkpoint*) 3600)
|
|
(scribe-get-distillable-nodes))))
|
|
:probabilistic #'probabilistic-skill-scribe
|
|
:deterministic #'verify-skill-scribe)
|
|
#+end_src
|
|
|
|
** Initialization
|
|
#+begin_src lisp
|
|
(scribe-load-state)
|
|
#+end_src
|