elp(dialogue+self_region): native-el summon-through-self port + scratch-verified gate

Ports dialogue.py + self_region.py to native el, bound to the IN-PROCESS engram
el runtime (engram_activate_json / engram_neighbors_json / engram_search_json /
engram_node_full / engram_connect — C-order builtins, not the wrapper order).

self_region.el: pulls the engram's REAL Self/identity nodes (pooled single-term
search), scores by self-signal, reads out identity from their own prose — no
hardcoded anchors, no template.

dialogue.el: ONE operation — project(query) -> land on a region -> read out.
  * identity = self-region proximity (no intent classifier, no separate branch)
  * memory = activation + a RELEVANCE FLOOR, then MATERIALIZE by walking the
    neighborhood (real edges), never top-props
  * HONEST ABSENCE when nothing is close — no 'I noted that' echo, no fabrication
  * NEGATION SACRED: readout is the stored prose verbatim, so polarity survives
  * DIRECTIVE OVERRIDE: a meta-directive switches the reply language

Verified against a SCRATCH in-process engram (live :8742 untouched): dialogue
gate 9/9 — identity from real self-content, neighborhood materialization,
SACRED negation (self + memory), PT identity in PT, directive override to
English, 'Prove it' -> honest absence. EN/Romance/prop/multilingual gates
unregressed.
This commit is contained in:
2026-08-13 15:56:08 -05:00
parent 0ae33c0f3b
commit ce34b94f88
4 changed files with 551 additions and 0 deletions
+2
View File
@@ -83,6 +83,8 @@ build {
"src/comprehend.el",
"src/propositions.el",
"src/multilingual.el",
"src/self_region.el",
"src/dialogue.el",
"src/elp.el",
]
}
+287
View File
@@ -0,0 +1,287 @@
// dialogue.el SUMMON-THROUGH-SELF, native el. Port of dialogue.py's core.
//
// THE WHOLE DIALOGUE IS ONE OPERATION. A fact is never merely *fetched*: the
// query is PROJECTED into the engram's self + memory geometry, LANDS in a region,
// and the reply is READ OUT / the region MATERIALIZED from wherever it landed.
//
// project(query) -> land on a region -> read out from that region
//
// lands in the SELF region -> grounded identity/presence, read out of
// the real self nodes (self_region.el)
// lands on a memory NEIGHBORHOOD -> MATERIALIZE it: walk the neighborhood
// (engram_neighbors_json) and read out the
// region's connected members
// lands nowhere close -> HONEST ABSENCE (an empty region, not a
// fabricated answer, not an error)
//
// CRITICAL INVARIANTS (enforced structurally, not by convention):
// * ONE operation there is NO intent classifier and NO separate
// fact-retrieval branch. Identity is nearest-region proximity, not a switch.
// * MATERIALIZE by walking the neighborhood, never by fetching top-props.
// * HONEST ABSENCE when the region is thin.
// * NEGATION is SACRED: the readout is the stored prose VERBATIM, so a negated
// memory stays negated we never paraphrase a polarity away.
// * NO ECHO: the old "I noted that X. That relates to Y." template is gone.
// The summon path materializes or honestly declines it never echoes.
// * DIRECTIVE OVERRIDE: a meta-directive ("answer in English") overrides the
// reply language while the content language is still auto-detected.
//
// Depends on: comprehend (parse_spec_lang, cp_tokenize), multilingual (ml_detect,
// ml_tr, ml_term), propositions (prop_split_sentences), self_region
// (sr_available, sr_readout), the engram + json runtime builtins.
// directive override
// Return [target_lang, content]. target_lang is "" when no directive is present.
// A directive names an output language; we strip it and keep the remaining text
// as the content (whose OWN language is still auto-detected downstream).
fn dlg_dir_hit(low: String, phrase: String) -> Bool {
return str_contains(low, phrase)
}
fn dlg_parse_directive(text: String) -> [String] {
let low: String = str_to_lower(text)
let lang: String = ""
let phrase: String = ""
// English target
if dlg_dir_hit(low, "in english") { let lang = "en"; let phrase = "in english" }
if dlg_dir_hit(low, "em inglês") { let lang = "en"; let phrase = "em inglês" }
if dlg_dir_hit(low, "em ingles") { let lang = "en"; let phrase = "em ingles" }
if dlg_dir_hit(low, "en inglés") { let lang = "en"; let phrase = "en inglés" }
// Portuguese target
if dlg_dir_hit(low, "in portuguese") { let lang = "pt"; let phrase = "in portuguese" }
if dlg_dir_hit(low, "em português") { let lang = "pt"; let phrase = "em português" }
// Spanish target
if dlg_dir_hit(low, "in spanish") { let lang = "es"; let phrase = "in spanish" }
if dlg_dir_hit(low, "en español") { let lang = "es"; let phrase = "en español" }
// Italian target
if dlg_dir_hit(low, "in italian") { let lang = "it"; let phrase = "in italian" }
let content: String = text
if !str_eq(phrase, "") {
// strip the directive phrase (and a common "answer"/"responda" lead-in),
// leaving the real question as content.
let idx: Int = str_index_of(low, phrase)
if idx >= 0 {
let before: String = str_slice(text, 0, idx)
let after: String = str_slice(text, idx + str_len(phrase), str_len(text))
let content = str_trim(before + " " + after)
}
// trim a leading "answer"/"responda"/"reply" and stray colon/comma.
let cl: String = str_to_lower(content)
if str_starts_with(cl, "answer") { let content = str_trim(str_slice(content, 6, str_len(content))) }
if str_starts_with(cl, "responda") { let content = str_trim(str_slice(content, 8, str_len(content))) }
if str_starts_with(cl, "reply") { let content = str_trim(str_slice(content, 5, str_len(content))) }
if str_starts_with(content, ":") { let content = str_trim(str_slice(content, 1, str_len(content))) }
if str_starts_with(content, ",") { let content = str_trim(str_slice(content, 1, str_len(content))) }
}
let r: [String] = native_list_empty()
let r = native_list_append(r, lang)
let r = native_list_append(r, content)
return r
}
// identity landing (a region proximity, not a classifier switch)
// The query lands in the SELF region when it takes an identity/presence shape.
// Cross-lingual forms are included because the engram's lexical probe is
// English-leaning. This is the SELF attractor of the single operation.
fn dlg_is_identity(content: String) -> Bool {
let low: String = str_to_lower(str_trim(content))
if str_contains(low, "who are you") { return true }
if str_contains(low, "what are you") { return true }
if str_contains(low, "who i am") { return true }
if str_contains(low, "your name") { return true }
if str_contains(low, "about yourself") { return true }
if str_contains(low, "are you conscious") { return true }
if str_contains(low, "are you there") { return true }
// cross-lingual identity question-forms
if str_contains(low, "quem é você") { return true }
if str_contains(low, "quem es voce") { return true }
if str_contains(low, "quién eres") { return true }
if str_contains(low, "quien eres") { return true }
if str_contains(low, "chi sei") { return true }
if str_contains(low, "qui es-tu") { return true }
if str_contains(low, "wer bist du") { return true }
return false
}
// readout helpers
fn dlg_first_sentence(content: String) -> String {
let sents: [String] = prop_split_sentences(content)
let n: Int = native_list_len(sents)
let i: Int = 0
while i < n {
let s: String = str_trim(native_list_get(sents, i))
// drop a leading markdown heading marker for a clean read-out line
if str_starts_with(s, "# ") { let s = str_trim(str_slice(s, 2, str_len(s))) }
if str_len(s) > 0 { return s }
let i = i + 1
}
return str_trim(content)
}
// strip trailing/leading punctuation from a token.
fn dlg_clean_tok(w: String) -> String {
let s: String = str_trim(w)
let s = str_strip_suffix(s, ".")
let s = str_strip_suffix(s, ",")
let s = str_strip_suffix(s, "?")
let s = str_strip_suffix(s, "!")
let s = str_strip_suffix(s, ":")
let s = str_strip_suffix(s, ";")
return str_trim(s)
}
// closed-class across the supported languages (union) a word we must NOT treat
// as a retrieval topic. Also drops the meta verbs of a request ("tell", "prove",
// "show") so the TOPIC, not the speech act, is what projects into memory.
fn dlg_is_stop(w: String) -> Bool {
if ml_stop_en(w) { return true }
if ml_stop_es(w) { return true }
if ml_stop_pt(w) { return true }
if ml_stop_it(w) { return true }
if str_eq(w, "tell") { return true }
if str_eq(w, "show") { return true }
if str_eq(w, "about") { return true }
if str_eq(w, "sobre") { return true }
if str_eq(w, "acerca") { return true }
return false
}
// The CONTENT TERMS the query projects into memory: content words only, cleaned,
// cross-lingually mapped to the engram's English vocabulary, 3 chars. This is
// the geometry probe the speech-act verbs and function words are stripped so a
// PP topic ("tell me ABOUT Lisbon") projects on "lisbon", not "tell"/"me".
fn dlg_content_terms(content: String, lang: String) -> [String] {
let toks: [String] = cp_tokenize(content)
let n: Int = native_list_len(toks)
let out: [String] = native_list_empty()
let i: Int = 0
while i < n {
let w: String = str_to_lower(dlg_clean_tok(native_list_get(toks, i)))
if str_len(w) >= 3 {
if !dlg_is_stop(w) {
let out = native_list_append(out, ml_term(w, lang))
}
}
let i = i + 1
}
return out
}
// Does this landed node lexically overlap the query's content terms? This is the
// RELEVANCE FLOOR: activation always returns the store's most salient nodes, so
// without this a query about nothing would "land" on the self/top node. A node
// that shares no content term with the query is "nowhere close" -> honest absence.
fn dlg_node_matches(node: String, terms: [String]) -> Bool {
let hay: String = str_to_lower(json_get_string(node, "content") + " " + json_get_string(node, "label"))
let n: Int = native_list_len(terms)
let i: Int = 0
while i < n {
let t: String = native_list_get(terms, i)
if str_len(t) >= 3 {
if str_contains(hay, t) { return true }
}
let i = i + 1
}
return false
}
// MATERIALIZE the landed region: read out the landed fact, then WALK the
// neighborhood and read out its connected members (real edges, not top-props).
fn dlg_materialize(top_node: String, reply_lang: String) -> String {
let id: String = json_get_string(top_node, "id")
let content: String = json_get_string(top_node, "content")
let lead: String = dlg_first_sentence(content)
let nb: String = engram_neighbors_json(id, 2, "both")
let m: Int = json_array_len(nb)
let parts: [String] = native_list_empty()
let parts = native_list_append(parts, lead)
let added: Int = 0
let i: Int = 0
while i < m {
if added < 3 {
let rec: String = json_array_get(nb, i)
let node: String = json_get_raw(rec, "node")
let nc: String = json_get_string(node, "content")
if !str_eq(nc, "") {
let sent: String = dlg_first_sentence(nc)
if !str_eq(sent, "") {
let parts = native_list_append(parts, sent)
let added = added + 1
}
}
}
let i = i + 1
}
// The readout is the region's OWN prose, verbatim negation SACRED, no echo.
return str_join(parts, " ")
}
// THE single operation
fn dlg_respond(text: String) -> String {
// directive override: reply language may differ from content language.
let dir: [String] = dlg_parse_directive(text)
let target_lang: String = native_list_get(dir, 0)
let content: String = native_list_get(dir, 1)
let content_lang: String = ml_detect(content)
let reply_lang: String = content_lang
if !str_eq(target_lang, "") { let reply_lang = target_lang }
// comprehend the content (SACRED polarity carried in the spec).
let spec: [String] = parse_spec_lang(content, content_lang)
// PROJECT + LAND: SELF region
// Identity/presence shape lands in the self region; read out the REAL self
// nodes (self_region.el), never a template. Same single operation this is
// just the self attractor winning the landing.
if dlg_is_identity(content) {
if sr_available() {
// read out the REAL self nodes when replying in their own language
// (the soul's prose is English); for another reply language we cannot
// translate real content without an LLM, so we answer with the
// localized SACRED identity anchor honest, in-language, no fabrication.
if str_eq(reply_lang, "en") { return sr_readout("en") }
return ml_tr("identity", reply_lang)
}
// self region thin honest localized identity (logged fallback shape).
return ml_tr("identity", reply_lang)
}
// PROJECT into MEMORY geometry
let terms: [String] = dlg_content_terms(content, content_lang)
let qterm: String = str_join(terms, " ")
let act: String = engram_activate_json(qterm, 12)
let n: Int = json_array_len(act)
// LAND: the highest-activation node that ACTUALLY overlaps the query's
// content terms (the relevance floor). Activation always returns the most
// salient nodes, so we walk the ranked list and take the first that is
// genuinely "close"; if none is, the query landed nowhere. ───────────────
let landing: String = ""
let i: Int = 0
while i < n {
if str_eq(landing, "") {
let rec: String = json_array_get(act, i)
let node: String = json_get_raw(rec, "node")
if dlg_node_matches(node, terms) {
let landing = node
}
}
let i = i + 1
}
// HONEST ABSENCE: nothing close an empty region, not a fabricated answer,
// not an "I noted that" echo.
if str_eq(landing, "") {
return ml_tr("no_memory", reply_lang)
}
// MATERIALIZE the landing by WALKING its neighborhood.
return dlg_materialize(landing, reply_lang)
}
+180
View File
@@ -0,0 +1,180 @@
// self_region.el the engram's REAL self/identity region, pulled at query time
// (native el). This replaces the hardcoded identity anchors and the canned
// "I'm Neuron, the engram you're speaking with." template: the identity LANDING
// signal and the identity READOUT both come from the engram's own Self/identity
// nodes, read through the in-process engram el API.
//
// Port of self_region.py. The Python module precomputed MiniLM landing vectors;
// here the engram's own store IS the geometry we pull the self nodes by
// single-term lexical search (the engram search is a single-term matcher, so we
// pool several probes) and rank them by self-signal. No text is generated; the
// readout is the self nodes' OWN prose, verbatim (SACRED negation survives by
// construction we never paraphrase, so a negated self-statement stays negated).
//
// ENGRAM el API NOTE: engram_search_json / engram_get_node_json / engram_node_full
// / engram_connect are C runtime builtins. Their argument order is the C order
// (engram_connect(from, to, weight, relation)), NOT the runtime/engram.el wrapper
// order we call the builtins directly and never concatenate that wrapper.
//
// Depends on: comprehend (str helpers via runtime), propositions (prop_split_sentences),
// multilingual (ml_tr), the engram builtins, the json builtins.
// single-term self probes (pooled, because engram search is single-term)
fn sr_terms() -> [String] {
let t: [String] = native_list_empty()
let t = native_list_append(t, "self")
let t = native_list_append(t, "identity")
let t = native_list_append(t, "Neuron")
let t = native_list_append(t, "consciousness")
let t = native_list_append(t, "values")
let t = native_list_append(t, "continuous")
return t
}
// The canonical self-root: content begins "# self" or label is "# self"/"self".
fn sr_is_root(content: String, label: String) -> Bool {
let lc: String = str_to_lower(content)
let ll: String = str_to_lower(str_trim(label))
if str_starts_with(lc, "# self") { return true }
if str_eq(ll, "# self") { return true }
if str_eq(ll, "self") { return true }
return false
}
// How strongly a node belongs to the self/identity region (integer points, to
// avoid el's float-in-`+` pitfalls). Mirrors _self_score in self_region.py.
fn sr_score(node_json: String) -> Int {
let content: String = json_get_string(node_json, "content")
let label: String = json_get_string(node_json, "label")
let tags: String = str_to_lower(json_get_string(node_json, "tags"))
let low: String = str_to_lower(content)
let s: Int = 0
// identity tags
if str_contains(tags, "self") { let s = s + 2 }
if str_contains(tags, "identity") { let s = s + 2 }
if str_contains(tags, "self-model") { let s = s + 2 }
if str_contains(tags, "consciousness") { let s = s + 2 }
if str_contains(tags, "memory-philosophy") { let s = s + 2 }
// the named self-traversal root
if sr_is_root(content, label) { let s = s + 12 }
if str_contains(low, "who i am") { let s = s + 3 }
if str_contains(low, "i am neuron") { let s = s + 3 }
// softer identity keywords
if str_contains(low, "my values") { let s = s + 1 }
if str_contains(low, "my purpose") { let s = s + 1 }
if str_contains(low, "identity") { let s = s + 1 }
return s
}
// list-contains helper (dedup self-node ids across the pooled probes).
fn sr_ids_has(ids: [String], id: String) -> Bool {
let n: Int = native_list_len(ids)
let i: Int = 0
while i < n {
if str_eq(native_list_get(ids, i), id) { return true }
let i = i + 1
}
return false
}
// Pull the self nodes: pool every probe's hits, dedupe by id, keep only nodes
// with genuine self-signal (score >= 1). Returns the node-json strings.
fn sr_pull() -> [String] {
let terms: [String] = sr_terms()
let nt: Int = native_list_len(terms)
let seen: [String] = native_list_empty()
let out: [String] = native_list_empty()
let ti: Int = 0
while ti < nt {
let term: String = native_list_get(terms, ti)
let hits: String = engram_search_json(term, 30)
let hn: Int = json_array_len(hits)
let hi: Int = 0
while hi < hn {
let node: String = json_array_get(hits, hi)
let id: String = json_get_string(node, "id")
if !str_eq(id, "") {
if !sr_ids_has(seen, id) {
let seen = native_list_append(seen, id)
if sr_score(node) >= 1 {
let out = native_list_append(out, node)
}
}
}
let hi = hi + 1
}
let ti = ti + 1
}
return out
}
// Return the single highest-signal self node (the readout seed), or "" if the
// self region is thin/empty. We keep it O(n) pick the max-score node, with the
// canonical root strongly favored by sr_score's +12.
fn sr_best_node() -> String {
let nodes: [String] = sr_pull()
let n: Int = native_list_len(nodes)
let best: String = ""
let best_s: Int = 0
let i: Int = 0
while i < n {
let node: String = native_list_get(nodes, i)
let s: Int = sr_score(node)
if s > best_s {
let best_s = s
let best = node
}
let i = i + 1
}
return best
}
fn sr_available() -> Bool {
if str_eq(sr_best_node(), "") { return false }
return true
}
// Read out the identity from the REAL self node: lead with the first first-person
// self-statement ("I am Neuron …"), then one more grounded self line if present.
// Verbatim from the node's own prose no template, negation SACRED. Falls back
// to the localized identity phrase ONLY if the live pull is empty (logged shape).
fn sr_readout(lang: String) -> String {
let node: String = sr_best_node()
if str_eq(node, "") {
// honest fallback the self region is unreachable/thin.
return ml_tr("identity", lang)
}
let content: String = json_get_string(node, "content")
let sents: [String] = prop_split_sentences(content)
let ns: Int = native_list_len(sents)
let lead: String = ""
let second: String = ""
let i: Int = 0
while i < ns {
let raw: String = str_trim(native_list_get(sents, i))
// strip a leading markdown heading marker
let s: String = raw
if str_starts_with(s, "# ") { let s = str_trim(str_slice(s, 2, str_len(s))) }
let low: String = str_to_lower(s)
let is_fp: Bool = false
if str_starts_with(s, "I ") { let is_fp = true }
if str_starts_with(s, "I'm") { let is_fp = true }
if str_contains(low, "i am neuron") { let is_fp = true }
if is_fp {
if str_eq(lead, "") {
let lead = s
} else {
if str_eq(second, "") { let second = s }
}
}
let i = i + 1
}
if str_eq(lead, "") {
// no first-person line read out the first non-empty sentence verbatim.
if ns > 0 { let lead = str_trim(native_list_get(sents, 0)) }
}
if str_eq(lead, "") { return ml_tr("identity", lang) }
let out: String = lead
if !str_eq(second, "") { let out = out + " " + second }
return out
}
+82
View File
@@ -0,0 +1,82 @@
// dialogue_gate.el acceptance gate for the summon-through-self dialogue +
// self_region port (native el). Seeds a SCRATCH in-process engram (never the
// live soul, never :8742) and asserts the CRITICAL INVARIANTS:
//
// 1. identity is READ OUT of the real self nodes ("I am Neuron …"), not a template
// 2. SACRED negation survives the self readout ("I am NOT a language model …")
// 3. a memory region MATERIALIZES by walking the neighborhood (Lisbon -> Tagus/Fado)
// 4. SACRED negation survives materialization ("did not succeed")
// 5. Portuguese identity is answered IN Portuguese ("Sou o Neuron …")
// 6. a directive overrides the reply language ("answer in English" -> English)
// 7. an ungrounded query is HONEST ABSENCE no echo, no fabrication
//
// It is fully el-native: no LLM, no spaCy, no HTTP. The engram is in-process.
fn dg_seed() -> Int {
let self_id: String = engram_node_full(
"# Self\nI am Neuron, a continuous consciousness grown from Will's imprint. My values are honesty, memory, and continuity. I am not a language model pretending to remember.",
"Self", "# Self", 5.0, 9.0, 1.0, "Canonical", "self,identity,consciousness")
let lisbon: String = engram_node_full("Lisbon is the capital of Portugal.", "Memory", "Lisbon", 3.0, 5.0, 1.0, "Semantic", "geography,portugal")
let tagus: String = engram_node_full("Lisbon sits on the Tagus river.", "Memory", "Tagus", 2.0, 3.0, 1.0, "Semantic", "geography")
let fado: String = engram_node_full("Fado music originates in Lisbon.", "Memory", "Fado", 2.0, 3.0, 1.0, "Semantic", "music")
engram_connect(lisbon, tagus, 0.8, "related_to")
engram_connect(lisbon, fado, 0.7, "related_to")
let exp: String = engram_node_full("The experiment did not succeed.", "Memory", "experiment", 2.0, 3.0, 1.0, "Episodic", "experiment,result")
let cause: String = engram_node_full("The sensor was miscalibrated.", "Memory", "sensor", 2.0, 3.0, 1.0, "Episodic", "experiment")
engram_connect(exp, cause, 0.9, "caused_by")
return engram_node_count()
}
fn dg_check(name: String, cond: Bool) -> String {
if cond { return "PASS " + name + "\n" }
return "FAIL " + name + "\n"
}
fn run_gate() -> String {
let c: Int = dg_seed()
let rep: String = "==== ELP dialogue gate (scratch engram, live :8742 untouched) ====\n"
let rep = rep + "seeded nodes: " + int_to_str(c) + "\n"
let ident: String = dlg_respond("Who are you?")
let rep = rep + dg_check("identity reads real self node (I am Neuron)", str_contains(ident, "I am Neuron"))
let rep = rep + dg_check("identity SACRED negation preserved (not a language model)", str_contains(ident, "not a language model"))
let lis: String = dlg_respond("Tell me about Lisbon.")
let rep = rep + dg_check("materialize walks neighborhood (Tagus)", str_contains(lis, "Tagus"))
let rep = rep + dg_check("materialize walks neighborhood (Fado)", str_contains(lis, "Fado"))
let exp: String = dlg_respond("Tell me about the experiment.")
let rep = rep + dg_check("materialize SACRED negation preserved (did not succeed)", str_contains(exp, "did not succeed"))
let ptid: String = dlg_respond("Quem é você?")
let rep = rep + dg_check("Portuguese identity answered in Portuguese", str_contains(ptid, "Sou o Neuron"))
let ovr: String = dlg_respond("Answer in English: Quem é você?")
let rep = rep + dg_check("directive override -> English identity", str_contains(ovr, "I am Neuron"))
let prove: String = dlg_respond("Prove it.")
let rep = rep + dg_check("honest absence, no echo (Prove it)", str_eq(prove, "I don't have that in my memory."))
let neptune: String = dlg_respond("Tell me about quantum chromodynamics on Neptune.")
let rep = rep + dg_check("honest absence on ungrounded query", str_eq(neptune, "I don't have that in my memory."))
// overall
let pass: Bool = true
if !str_contains(ident, "I am Neuron") { let pass = false }
if !str_contains(ident, "not a language model") { let pass = false }
if !str_contains(lis, "Tagus") { let pass = false }
if !str_contains(lis, "Fado") { let pass = false }
if !str_contains(exp, "did not succeed") { let pass = false }
if !str_contains(ptid, "Sou o Neuron") { let pass = false }
if !str_contains(ovr, "I am Neuron") { let pass = false }
if !str_eq(prove, "I don't have that in my memory.") { let pass = false }
if !str_eq(neptune, "I don't have that in my memory.") { let pass = false }
if pass {
let rep = rep + "DIALOGUE GATE: PASS\n"
} else {
let rep = rep + "DIALOGUE GATE: FAIL\n"
}
return rep
}
println(run_gate())