will.anderson
c20cb3b97c
Read routes (GET /api/embeddings, /api/graph/dump) need node embedding vectors, but every consumer emit path deliberately drops the ~5.7KB emb vector (include_emb=0) to stay under MCP token limits. Rather than perturb that shared path, add a dedicated additive builtin that pages nodes WITH their dense vector, emitting id/node_type/label/created_at/emb_dim plus emb as a JSON array whose length equals emb_dim (so a consumer can verify the vector round-trips). Un-embedded nodes emit emb_dim:0 / emb:[]. Same salience-sorted, transparent-layer-skipped, bounded pagination as engram_scan_nodes_json; default page 256. Purely additive: engram_emit_node_json and the default include_emb=0 are untouched, so every existing endpoint is byte-identical to trunk (verified: scan_nodes_json still carries no emb). The HTTP route wiring in server.el is DEFERRED to cutover per the elc-drift blocker (regenerating engram/dist diverges ~285 lines with no source change); the builtin is exercised directly by the pure-C gate instead. Measured on a copy: len(emb)==emb_dim for all nodes, pagination disjoint, existing path unchanged; full 256-node x 768-dim page = 16.7 ms / 1.18 MB. ASan+UBSan clean.
80 lines
3.5 KiB
C
80 lines
3.5 KiB
C
/* test_interoception_p0_emb.c — M-INTEROCEPTION Priority 0.
|
|
*
|
|
* Verifies the new READ-ONLY builtin engram_scan_nodes_emb_json(limit,offset):
|
|
* - every emitted node carries emb_dim and an emb JSON array of that length,
|
|
* - nodes without an embedding emit emb_dim:0 / emb:[],
|
|
* - pagination (limit/offset) is honoured,
|
|
* - the count matches engram_node_count,
|
|
* - the EXISTING engram_scan_nodes_json path is byte-unchanged (no emb field),
|
|
* i.e. the addition is purely additive / behavior-neutral.
|
|
*
|
|
* Pure-C harness (no elc). We craft a snapshot with real emb vectors, load it
|
|
* (engram_load parses "emb" comma-lists into node->emb via eg_parse_emb), then
|
|
* dump via both scan paths. Assertions live in run_interoception_p0.sh.
|
|
*/
|
|
#include "el_runtime.h"
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
|
|
static el_val_t S(const char* s){ return EL_STR(s); }
|
|
|
|
/* 16-d embedding as a comma list (>=8 required by eg_parse_emb). */
|
|
static void emb_list(char* out, size_t cap, int dim, double base){
|
|
size_t o = 0;
|
|
for (int i = 0; i < dim; i++){
|
|
o += snprintf(out+o, cap-o, "%s%.4f", i?",":"", base + 0.01*i);
|
|
}
|
|
}
|
|
|
|
int main(int argc, char** argv){
|
|
if (argc < 2){ fprintf(stderr, "usage: %s <dir>\n", argv[0]); return 2; }
|
|
const char* dir = argv[1];
|
|
char snap[1024]; snprintf(snap, sizeof snap, "%s/seed.json", dir);
|
|
|
|
char e1[512], e2[512];
|
|
emb_list(e1, sizeof e1, 16, 0.10);
|
|
emb_list(e2, sizeof e2, 16, 0.50);
|
|
|
|
/* Two embedded nodes (distinct salience → deterministic sort order) and one
|
|
* un-embedded node. */
|
|
FILE* f = fopen(snap, "w");
|
|
if (!f){ perror("fopen"); return 2; }
|
|
fprintf(f,
|
|
"{\"nodes\":["
|
|
"{\"id\":\"n-high\",\"content\":\"high salience embedded\",\"node_type\":\"Concept\","
|
|
"\"label\":\"emb-high\",\"tier\":\"Semantic\",\"salience\":0.9,\"importance\":0.8,"
|
|
"\"confidence\":1.0,\"created_at\":1000,\"emb\":\"%s\"},"
|
|
"{\"id\":\"n-mid\",\"content\":\"mid salience embedded\",\"node_type\":\"Concept\","
|
|
"\"label\":\"emb-mid\",\"tier\":\"Semantic\",\"salience\":0.5,\"importance\":0.5,"
|
|
"\"confidence\":1.0,\"created_at\":2000,\"emb\":\"%s\"},"
|
|
"{\"id\":\"n-low\",\"content\":\"low salience no embedding\",\"node_type\":\"Fact\","
|
|
"\"label\":\"noemb-low\",\"tier\":\"Semantic\",\"salience\":0.1,\"importance\":0.2,"
|
|
"\"confidence\":1.0,\"created_at\":3000}"
|
|
"],\"edges\":[]}", e1, e2);
|
|
fclose(f);
|
|
|
|
if (!engram_load(S(snap))){ fprintf(stderr, "load failed\n"); return 2; }
|
|
long long nc = (long long)(int64_t)engram_node_count();
|
|
printf("node_count=%lld\n", nc);
|
|
|
|
/* full page */
|
|
el_val_t all = engram_scan_nodes_emb_json((el_val_t)256, (el_val_t)0);
|
|
char p[1024];
|
|
snprintf(p, sizeof p, "%s/emb_all.json", dir);
|
|
f = fopen(p, "w"); fputs(EL_CSTR(all), f); fclose(f);
|
|
|
|
/* pagination: one node at offset 0 and one at offset 1 */
|
|
el_val_t pg0 = engram_scan_nodes_emb_json((el_val_t)1, (el_val_t)0);
|
|
el_val_t pg1 = engram_scan_nodes_emb_json((el_val_t)1, (el_val_t)1);
|
|
snprintf(p, sizeof p, "%s/emb_pg0.json", dir); f = fopen(p, "w"); fputs(EL_CSTR(pg0), f); fclose(f);
|
|
snprintf(p, sizeof p, "%s/emb_pg1.json", dir); f = fopen(p, "w"); fputs(EL_CSTR(pg1), f); fclose(f);
|
|
|
|
/* existing path — must be unchanged / carry NO emb */
|
|
el_val_t plain = engram_scan_nodes_json((el_val_t)256, (el_val_t)0);
|
|
snprintf(p, sizeof p, "%s/plain.json", dir); f = fopen(p, "w"); fputs(EL_CSTR(plain), f); fclose(f);
|
|
|
|
printf("wrote dumps to %s\n", dir);
|
|
return 0;
|
|
}
|