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

REFACTOR: Explanatory Core Architecture & Terminology Alignment

Browse Source
This commit is contained in:
Amr Gharbeia
2026-04-13 09:03:42 -04:00
parent 10a500c480
commit 3e68cc11af
52 changed files with 446 additions and 1756 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
literate/context.org
View File

@@ -11,7 +11,7 @@ A common failure mode for Large Language Models (LLMs) is the "Lost in the Middl
The ~org-agent~ harness implements a deterministic, tree-aware solution: the **Foveal-Peripheral Hybrid Model**.
*** 1. The Foveal Focus (High Resolution)
When the harness prepares a prompt for the Associative Engine, it identifies a "Foveal Focus"—typically the specific Org headline or task the user is currently interacting with. This node, along with its immediate children and semantically relevant neighbors, is rendered at "High Resolution," meaning its full body text, properties, and metadata are included in the prompt.
When the harness prepares a prompt for the Probabilistic Engine, it identifies a "Foveal Focus"—typically the specific Org headline or task the user is currently interacting with. This node, along with its immediate children and semantically relevant neighbors, is rendered at "High Resolution," meaning its full body text, properties, and metadata are included in the prompt.
*** 2. The Peripheral Vision (Low Resolution)
To maintain global awareness without bloating the context window, the rest of the Memex is rendered at "Low Resolution." The harness recursively walks the Object Store and generates a skeletal outline consisting only of titles and IDs. This gives the LLM a "mental map" of the entire system, allowing it to reference other projects or skills without needing to see their full content until they are explicitly brought into focus.
@@ -28,7 +28,7 @@ flowchart TD
Identification --> Peripheral[Render Outline: Titles Only]
Foveal --> Assembly[Assemble Global Awareness String]
Peripheral --> Assembly
Assembly --> LLM[Associative Engine Proposal]
Assembly --> LLM[Probabilistic Engine Proposal]
#+end_src
* Context Assembly (context.lisp)
@@ -105,7 +105,7 @@ Reads the raw literate Org source of a specific skill. This is a foundational ca
#+end_src
** Harness Logs (context-get-system-logs)
Retrieves the most recent entries from the harness's internal circular log buffer. This allows the Associative Engine to see recent errors or successful dispatches, enabling it to course-correct or explain failures to the user.
Retrieves the most recent entries from the harness's internal circular log buffer. This allows the Probabilistic Engine to see recent errors or successful dispatches, enabling it to course-correct or explain failures to the user.
#+begin_src lisp :tangle ../src/context.lisp
(defun context-get-system-logs (&optional (limit 20))