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

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
+5
View File
@@ -168,6 +168,11 @@ fn handle_dharma_recv(body: String) -> String {
return handle_chat_as_soul(eff_payload)
}
// ELP Engram Language Protocol: two-layer activation, no LLM
if str_eq(eff_event, "elp") {
return handle_elp_chat(eff_payload)
}
return "{\"error\":\"unknown event_type\",\"event_type\":\"" + eff_event + "\"}"
}