fix(mvp): 100% Green Boot, Llama.cpp backend, and setup refinement
Some checks failed
Deploy-Agent-V15-Stdin / JOB-V15-STDIN (push) Failing after 2s
Some checks failed
Deploy-Agent-V15-Stdin / JOB-V15-STDIN (push) Failing after 2s
This commit is contained in:
64
skills/org-skill-llama-backend.org
Normal file
64
skills/org-skill-llama-backend.org
Normal file
@@ -0,0 +1,64 @@
|
||||
:PROPERTIES:
|
||||
:ID: llama-backend-skill
|
||||
:CREATED: [2026-04-17 Fri 20:00]
|
||||
:END:
|
||||
#+TITLE: SKILL: Llama.cpp Neuro-Backend (Sovereign Inference)
|
||||
#+STARTUP: content
|
||||
#+FILETAGS: :llm:backend:llama:sovereignty:
|
||||
|
||||
* Overview
|
||||
The *Llama.cpp Backend* allows the OpenCortex to use local, air-gapped inference. It connects to a \`llama.cpp\` server (typically running on the local network) and registers itself as a provider in the kernel's probabilistic cascade.
|
||||
|
||||
* Phase B: Blueprint (PROTOCOL)
|
||||
** 1. Architectural Intent
|
||||
This skill acts as a proxy between the OpenCortex kernel and the Lisp-agnostic \`llama.cpp\` REST API. It implements the standard backend signature required by \`register-probabilistic-backend\`.
|
||||
|
||||
** 2. Semantic Interfaces
|
||||
- Endpoint: \`(uiop:getenv "LLAMACPP_ENDPOINT")\` (e.g., "http://10.10.10.x:8080")
|
||||
- Method: \`POST /completion\`
|
||||
- Response: JSON (parsed into Lisp)
|
||||
|
||||
* Phase D: Build (Implementation)
|
||||
|
||||
** Package Context
|
||||
#+begin_src lisp
|
||||
(in-package :opencortex)
|
||||
#+end_src
|
||||
|
||||
** The Inference Engine (llama-inference)
|
||||
#+begin_src lisp
|
||||
(defun llama-inference (prompt system-prompt &key (model "local-model"))
|
||||
"Sends a completion request to the local llama.cpp server."
|
||||
(let ((endpoint (uiop:getenv "LLAMACPP_ENDPOINT")))
|
||||
(unless endpoint
|
||||
(harness-log "LLAMA ERROR: LLAMACPP_ENDPOINT not set in environment.")
|
||||
(return-from llama-inference (list :error "LLAMACPP_ENDPOINT_MISSING")))
|
||||
|
||||
(handler-case
|
||||
(let* ((full-prompt (format nil "System: ~a~%User: ~a~%Assistant:" system-prompt prompt))
|
||||
(payload (cl-json:encode-json-to-string
|
||||
\`((:prompt . ,full-prompt)
|
||||
(:n_predict . 1024)
|
||||
(:stop . ("User:" "System:")))))
|
||||
(response (dex:post (format nil "~a/completion" endpoint)
|
||||
:content payload
|
||||
:headers '(("Content-Type" . "application/json"))))
|
||||
(data (cl-json:decode-json-from-string response)))
|
||||
(cdr (assoc :content data)))
|
||||
(error (c)
|
||||
(harness-log "LLAMA ERROR: Connection failed -> ~a" c)
|
||||
(list :error (format nil "~a" c))))))
|
||||
#+end_src
|
||||
|
||||
** Registration
|
||||
#+begin_src lisp
|
||||
(progn
|
||||
(register-probabilistic-backend :llama #'llama-inference)
|
||||
(harness-log "LLAMA: Local backend registered and active."))
|
||||
|
||||
(defskill :skill-llama-backend
|
||||
:priority 50
|
||||
:trigger (lambda (ctx) (declare (ignore ctx)) nil) ; Pure infrastructure skill
|
||||
:probabilistic nil
|
||||
:deterministic (lambda (action ctx) (declare (ignore ctx)) action))
|
||||
#+end_src
|
||||
Reference in New Issue
Block a user