amr/passepartout
1
0
Fork 0
Code Issues 15 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

PSF: Complete 'Thin Harness' refactor and move kernel logic to skills

Browse Source
This commit is contained in:
Amr Gharbeia
2026-04-12 16:43:43 -04:00
parent f047230e67
commit 294c1a976e
28 changed files with 454 additions and 466 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
literate/context.org
View File

@@ -181,67 +181,11 @@ The primary context generator. It identifies active projects and the current fov
output))
#+end_src
* Semantic Search (embedding.lisp)
The `embedding.lisp` module handles vector representations and cosine similarity for semantic discovery.
** Package Context
#+begin_src lisp :tangle ../src/embedding.lisp
(in-package :org-agent)
#+end_src
** Embedding Retrieval (get-embedding)
Fetches a numerical vector representation of text from the configured provider (defaults to Gemini `text-embedding-004`).
#+begin_src lisp :tangle ../src/embedding.lisp
(defun get-embedding (text)
"Retrieves a vector representation of text via the configured neural provider."
(let* ((auth (get-provider-auth :gemini)) (api-key (getf auth :api-key))
(endpoint "https://generativelanguage.googleapis.com/v1beta/models/text-embedding-004:embedContent"))
(unless api-key (return-from get-embedding nil))
(let* ((url (format nil "~a?key=~a" endpoint api-key)) (headers `(("Content-Type" . "application/json")))
(body (cl-json:encode-json-to-string `((model . "models/text-embedding-004") (content . ((parts . ((text . ,text)))))))))
(handler-case (let* ((response (dex:post url :headers headers :content body))
(json (cl-json:decode-json-from-string response)))
(cdr (assoc :values (cdr (assoc :embedding json)))))
(error (c) (kernel-log "EMBEDDING FAILURE: ~a" c) nil)))))
#+end_src
** Vector Math
Simple implementations of dot product and magnitude for similarity calculations.
#+begin_src lisp :tangle ../src/embedding.lisp
(defun dot-product (v1 v2)
"Calculates the dot product of two numerical vectors."
(reduce #'+ (mapcar #'* v1 v2)))
(defun magnitude (v)
"Calculates the Euclidean magnitude of a numerical vector."
(sqrt (reduce #'+ (mapcar (lambda (x) (* x x)) v))))
#+end_src
** Cosine Similarity (cosine-similarity)
Calculates the semantic distance (normalized dot product) between two vectors.
#+begin_src lisp :tangle ../src/embedding.lisp
(defun cosine-similarity (v1 v2)
"Calculates the semantic distance between two vectors."
(let ((m1 (magnitude v1)) (m2 (magnitude v2))) (if (or (zerop m1) (zerop m2)) 0 (/ (dot-product v1 v2) (* m1 m2)))))
#+end_src
** Semantic Discovery (find-most-similar)
Identifies the top-k most semantically related objects in the entire store by comparing their cached vectors against a query vector.
#+begin_src lisp :tangle ../src/embedding.lisp
(defun find-most-similar (query-vector top-k)
"Identifies the top-k most semantically related objects in the store."
(let ((similarities nil))
(maphash (lambda (id obj) (let ((vec (org-object-vector obj))) (when vec (push (cons (cosine-similarity query-vector vec) obj) similarities)))) *object-store*)
(let ((sorted (sort similarities #'> :key #'car))) (subseq sorted 0 (min top-k (length sorted))))))
#+end_src
* Phase E: Chaos (Verification)
Verification of the peripheral vision extraction and rendering logic.
Verification of the peripheral vision extraction and rendering logic.
#+begin_src lisp :tangle ../tests/peripheral-vision-tests.lisp
(defpackage :org-agent-peripheral-vision-tests
(:use :cl :fiveam :org-agent)