neuron-technologies/neuron
2
0
Fork 0
Code Issues 23 Pull Requests 5 Actions Packages Projects Releases Wiki Activity

ELP: two-layer activation pipeline (activate → suppress → reason → generate)

Browse Source 
elp-input.el: replace broken engram_search_json with engram_activate_json
as Layer 1. Layer 2 suppress/filter keeps nodes with non-zero salience/
importance. Reason step extracts patient from top activated node content.
ELP grammar realizes the response via generate().

routes.el: add 'elp' event_type to handle_dharma_recv so the studio can
route ELP requests through dharma.
This commit is contained in:
Will Anderson
2026-05-03 11:31:04 -05:00
parent e299c92662
commit 2622bb04bd
94 changed files with 52848 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
dist/morphology-ja.elh
Vendored
+9
View File
@@ -0,0 +1,9 @@
// auto-generated by elc --emit-header - do not edit
extern fn ja_verb_group(dict_form: String) -> String
extern fn ja_ichidan_stem(dict_form: String) -> String
extern fn ja_godan_stem_change(dict_form: String, row: String) -> String
extern fn ja_conjugate(dict_form: String, form: String) -> String
extern fn ja_particle(gram_case: String) -> String
extern fn ja_noun_phrase(noun: String, gram_case: String) -> String
extern fn ja_question_particle() -> String
extern fn ja_make_question(sentence: String) -> String