Merge #66: tokenized+ranked engram lexical search + engram natives (via stage)

engram/dist/engram.c

@@ -10,6 +10,7 @@ el_val_t query_param(el_val_t path, el_val_t key);
 el_val_t query_int(el_val_t path, el_val_t key, el_val_t default_val);
 el_val_t extract_id(el_val_t path, el_val_t prefix);
 el_val_t route_stats(el_val_t method, el_val_t path, el_val_t body);
+el_val_t persist_canonical(void);
 el_val_t route_create_node(el_val_t method, el_val_t path, el_val_t body);
 el_val_t route_get_node(el_val_t method, el_val_t path, el_val_t body);
 el_val_t route_scan_nodes(el_val_t method, el_val_t path, el_val_t body);
@@ -20,18 +21,23 @@ el_val_t route_create_edge(el_val_t method, el_val_t path, el_val_t body);
 el_val_t route_neighbors(el_val_t method, el_val_t path, el_val_t body);
 el_val_t route_strengthen(el_val_t method, el_val_t path, el_val_t body);
 el_val_t route_forget(el_val_t method, el_val_t path, el_val_t body);
-el_val_t route_create_ise(el_val_t method, el_val_t path, el_val_t body);
-el_val_t route_sync(el_val_t method, el_val_t path, el_val_t body);
 el_val_t route_save(el_val_t method, el_val_t path, el_val_t body);
 el_val_t route_load(el_val_t method, el_val_t path, el_val_t body);
 el_val_t route_health(el_val_t method, el_val_t path, el_val_t body);
+el_val_t route_sync(el_val_t method, el_val_t path, el_val_t body);
+el_val_t route_load_merge(el_val_t method, el_val_t path, el_val_t body);
+el_val_t route_emit_ise(el_val_t method, el_val_t path, el_val_t body);
+el_val_t route_capture_knowledge(el_val_t method, el_val_t path, el_val_t body);
 el_val_t check_auth_ok(el_val_t method, el_val_t body);
 el_val_t handle_request(el_val_t method, el_val_t path, el_val_t body);
 
+el_val_t bind_raw;
 el_val_t bind_str;
 el_val_t port;
+el_val_t data_dir_raw;
 el_val_t data_dir;
 el_val_t snapshot_path;
+el_val_t boot_snap;
 
 el_val_t parse_port(el_val_t bind) {
   el_val_t colon = str_index_of(bind, EL_STR(":"));
@@ -110,17 +116,22 @@ el_val_t route_stats(el_val_t method, el_val_t path, el_val_t body) {
   return 0;
 }
 
+el_val_t persist_canonical(void) {
+  el_val_t dir_raw = env(EL_STR("ENGRAM_DATA_DIR"));
+  el_val_t dir = ({ el_val_t _if_result_1 = 0; if (str_eq(dir_raw, EL_STR(""))) { _if_result_1 = (EL_STR("/tmp/engram")); } else { _if_result_1 = (dir_raw); } _if_result_1; });
+  engram_save(el_str_concat(dir, EL_STR("/snapshot.json")));
+  return 1;
+  return 0;
+}
+
 el_val_t route_create_node(el_val_t method, el_val_t path, el_val_t body) {
   el_val_t content = json_get_string(body, EL_STR("content"));
-  el_val_t node_type = json_get_string(body, EL_STR("node_type"));
+  el_val_t nt_raw = json_get_string(body, EL_STR("node_type"));
-  if (str_eq(node_type, EL_STR(""))) {
+  el_val_t node_type = ({ el_val_t _if_result_2 = 0; if (str_eq(nt_raw, EL_STR(""))) { _if_result_2 = (EL_STR("Memory")); } else { _if_result_2 = (nt_raw); } _if_result_2; });
-    node_type = EL_STR("Memory");
+  el_val_t sal_raw = json_get_float(body, EL_STR("salience"));
-  }
+  el_val_t salience = ({ el_val_t _if_result_3 = 0; if ((sal_raw == el_from_float(0.0))) { _if_result_3 = (el_from_float(0.5)); } else { _if_result_3 = (sal_raw); } _if_result_3; });
-  el_val_t salience = json_get_float(body, EL_STR("salience"));
-  if (salience == el_from_float(0.0)) {
-    salience = el_from_float(0.5);
-  }
   el_val_t id = engram_node(content, node_type, salience);
+  el_val_t saved = persist_canonical();
   return el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("{\"id\":\""), id), EL_STR("\",\"content\":\"")), content), EL_STR("\",\"node_type\":\"")), node_type), EL_STR("\"}"));
   return 0;
 }
@@ -146,11 +157,9 @@ el_val_t route_scan_nodes(el_val_t method, el_val_t path, el_val_t body) {
 }
 
 el_val_t route_scan_edges(el_val_t method, el_val_t path, el_val_t body) {
-  el_val_t dir = env(EL_STR("ENGRAM_DATA_DIR"));
+  el_val_t dir_raw = env(EL_STR("ENGRAM_DATA_DIR"));
-  if (str_eq(dir, EL_STR(""))) {
+  el_val_t dir = ({ el_val_t _if_result_4 = 0; if (str_eq(dir_raw, EL_STR(""))) { _if_result_4 = (EL_STR("/tmp/engram")); } else { _if_result_4 = (dir_raw); } _if_result_4; });
-    dir = EL_STR("/tmp/engram");
+  el_val_t snap_path = el_str_concat(dir, EL_STR("/.scan-export.json"));
-  }
-  el_val_t snap_path = el_str_concat(dir, EL_STR("/snapshot.json"));
   engram_save(snap_path);
   el_val_t snap = fs_read(snap_path);
   if (str_eq(snap, EL_STR(""))) {
@@ -165,36 +174,22 @@ el_val_t route_scan_edges(el_val_t method, el_val_t path, el_val_t body) {
 }
 
 el_val_t route_search(el_val_t method, el_val_t path, el_val_t body) {
-  el_val_t q = EL_STR("");
+  el_val_t q = ({ el_val_t _if_result_5 = 0; if (str_eq(method, EL_STR("GET"))) { _if_result_5 = (query_param(path, EL_STR("q"))); } else { _if_result_5 = (json_get_string(body, EL_STR("query"))); } _if_result_5; });
-  if (str_eq(method, EL_STR("GET"))) {
+  el_val_t lim_url = query_int(path, EL_STR("limit"), 0);
-    q = query_param(path, EL_STR("q"));
+  el_val_t lim_body = json_get_int(body, EL_STR("limit"));
-  } else {
+  el_val_t lim_either = ({ el_val_t _if_result_6 = 0; if ((lim_url > 0)) { _if_result_6 = (lim_url); } else { _if_result_6 = (lim_body); } _if_result_6; });
-    q = json_get_string(body, EL_STR("query"));
+  el_val_t limit = ({ el_val_t _if_result_7 = 0; if ((lim_either > 0)) { _if_result_7 = (lim_either); } else { _if_result_7 = (20); } _if_result_7; });
-  }
-  el_val_t limit = query_int(path, EL_STR("limit"), 20);
-  if (limit == 0) {
-    limit = json_get_int(body, EL_STR("limit"));
-  }
-  if (limit == 0) {
-    limit = 20;
-  }
   return engram_search_json(q, limit);
   return 0;
 }
 
 el_val_t route_activate(el_val_t method, el_val_t path, el_val_t body) {
-  el_val_t q = EL_STR("");
+  el_val_t q = ({ el_val_t _if_result_8 = 0; if (str_eq(method, EL_STR("GET"))) { _if_result_8 = (query_param(path, EL_STR("q"))); } else { _if_result_8 = (json_get_string(body, EL_STR("query"))); } _if_result_8; });
-  el_val_t depth = 3;
+  if (str_eq(q, EL_STR(""))) {
-  if (str_eq(method, EL_STR("GET"))) {
+    return err_json(EL_STR("missing query"));
-    q = query_param(path, EL_STR("q"));
-    depth = query_int(path, EL_STR("depth"), 3);
-  } else {
-    q = json_get_string(body, EL_STR("query"));
-    el_val_t bd = json_get_int(body, EL_STR("depth"));
-    if (bd > 0) {
-      depth = bd;
-    }
   }
+  el_val_t d_raw = ({ el_val_t _if_result_9 = 0; if (str_eq(method, EL_STR("GET"))) { _if_result_9 = (query_int(path, EL_STR("depth"), 3)); } else { _if_result_9 = (json_get_int(body, EL_STR("depth"))); } _if_result_9; });
+  el_val_t depth = ({ el_val_t _if_result_10 = 0; if ((d_raw > 0)) { _if_result_10 = (d_raw); } else { _if_result_10 = (3); } _if_result_10; });
   return el_str_concat(el_str_concat(EL_STR("{\"results\":"), engram_activate_json(q, depth)), EL_STR("}"));
   return 0;
 }
@@ -202,15 +197,12 @@ el_val_t route_activate(el_val_t method, el_val_t path, el_val_t body) {
 el_val_t route_create_edge(el_val_t method, el_val_t path, el_val_t body) {
   el_val_t from_id = json_get_string(body, EL_STR("from_id"));
   el_val_t to_id = json_get_string(body, EL_STR("to_id"));
-  el_val_t relation = json_get_string(body, EL_STR("relation"));
+  el_val_t rel_raw = json_get_string(body, EL_STR("relation"));
-  if (str_eq(relation, EL_STR(""))) {
+  el_val_t relation = ({ el_val_t _if_result_11 = 0; if (str_eq(rel_raw, EL_STR(""))) { _if_result_11 = (EL_STR("associates")); } else { _if_result_11 = (rel_raw); } _if_result_11; });
-    relation = EL_STR("associates");
+  el_val_t w_raw = json_get_float(body, EL_STR("weight"));
-  }
+  el_val_t weight = ({ el_val_t _if_result_12 = 0; if ((w_raw == el_from_float(0.0))) { _if_result_12 = (el_from_float(0.5)); } else { _if_result_12 = (w_raw); } _if_result_12; });
-  el_val_t weight = json_get_float(body, EL_STR("weight"));
-  if (weight == el_from_float(0.0)) {
-    weight = el_from_float(0.5);
-  }
   engram_connect(from_id, to_id, weight, relation);
+  el_val_t saved = persist_canonical();
   return el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("{\"ok\":true,\"from_id\":\""), from_id), EL_STR("\",\"to_id\":\"")), to_id), EL_STR("\",\"relation\":\"")), relation), EL_STR("\"}"));
   return 0;
 }
@@ -231,6 +223,7 @@ el_val_t route_strengthen(el_val_t method, el_val_t path, el_val_t body) {
     return err_json(EL_STR("missing node_id"));
   }
   engram_strengthen(id);
+  el_val_t saved = persist_canonical();
   return ok_json();
   return 0;
 }
@@ -241,29 +234,40 @@ el_val_t route_forget(el_val_t method, el_val_t path, el_val_t body) {
     return err_json(EL_STR("missing id"));
   }
   engram_forget(id);
+  el_val_t saved = persist_canonical();
   return ok_json();
   return 0;
 }
 
-el_val_t route_create_ise(el_val_t method, el_val_t path, el_val_t body) {
+el_val_t route_save(el_val_t method, el_val_t path, el_val_t body) {
-  el_val_t content = json_get_string(body, EL_STR("content"));
+  el_val_t p_raw = json_get_string(body, EL_STR("path"));
-  if (str_eq(content, EL_STR(""))) {
+  el_val_t dir_raw = env(EL_STR("ENGRAM_DATA_DIR"));
-    return err_json(EL_STR("missing content"));
+  el_val_t dir = ({ el_val_t _if_result_13 = 0; if (str_eq(dir_raw, EL_STR(""))) { _if_result_13 = (EL_STR("/tmp/engram")); } else { _if_result_13 = (dir_raw); } _if_result_13; });
-  }
+  el_val_t p = ({ el_val_t _if_result_14 = 0; if (str_eq(p_raw, EL_STR(""))) { _if_result_14 = (el_str_concat(dir, EL_STR("/snapshot.json"))); } else { _if_result_14 = (p_raw); } _if_result_14; });
-  el_val_t sal = el_from_float(0.3);
+  engram_save(p);
-  el_val_t imp = el_from_float(0.3);
+  return el_str_concat(el_str_concat(EL_STR("{\"ok\":true,\"path\":\""), p), EL_STR("\"}"));
-  el_val_t conf = el_from_float(0.8);
+  return 0;
-  el_val_t id = engram_node_full(content, EL_STR("InternalStateEvent"), EL_STR("state-event"), sal, imp, conf, EL_STR("Episodic"), EL_STR("[\"internal-state\",\"InternalStateEvent\"]"));
+}
-  return el_str_concat(el_str_concat(EL_STR("{\"ok\":true,\"id\":\""), id), EL_STR("\"}"));
+
+el_val_t route_load(el_val_t method, el_val_t path, el_val_t body) {
+  el_val_t p_raw = json_get_string(body, EL_STR("path"));
+  el_val_t dir_raw = env(EL_STR("ENGRAM_DATA_DIR"));
+  el_val_t dir = ({ el_val_t _if_result_15 = 0; if (str_eq(dir_raw, EL_STR(""))) { _if_result_15 = (EL_STR("/tmp/engram")); } else { _if_result_15 = (dir_raw); } _if_result_15; });
+  el_val_t p = ({ el_val_t _if_result_16 = 0; if (str_eq(p_raw, EL_STR(""))) { _if_result_16 = (el_str_concat(dir, EL_STR("/snapshot.json"))); } else { _if_result_16 = (p_raw); } _if_result_16; });
+  engram_load(p);
+  return ok_json();
+  return 0;
+}
+
+el_val_t route_health(el_val_t method, el_val_t path, el_val_t body) {
+  return EL_STR("{\"status\":\"ok\",\"engine\":\"engram-runtime-native\"}");
   return 0;
 }
 
 el_val_t route_sync(el_val_t method, el_val_t path, el_val_t body) {
-  el_val_t dir = env(EL_STR("ENGRAM_DATA_DIR"));
+  el_val_t dir_raw = env(EL_STR("ENGRAM_DATA_DIR"));
-  if (str_eq(dir, EL_STR(""))) {
+  el_val_t dir = ({ el_val_t _if_result_17 = 0; if (str_eq(dir_raw, EL_STR(""))) { _if_result_17 = (EL_STR("/tmp/engram")); } else { _if_result_17 = (dir_raw); } _if_result_17; });
-    dir = EL_STR("/tmp/engram");
+  el_val_t snap_path = el_str_concat(dir, EL_STR("/.sync-export.json"));
-  }
-  el_val_t snap_path = el_str_concat(dir, EL_STR("/sync-export.json"));
   engram_save(snap_path);
   el_val_t snap = fs_read(snap_path);
   if (str_eq(snap, EL_STR(""))) {
@@ -273,36 +277,68 @@ el_val_t route_sync(el_val_t method, el_val_t path, el_val_t body) {
   return 0;
 }
 
-el_val_t route_save(el_val_t method, el_val_t path, el_val_t body) {
+el_val_t route_load_merge(el_val_t method, el_val_t path, el_val_t body) {
   el_val_t p = json_get_string(body, EL_STR("path"));
   if (str_eq(p, EL_STR(""))) {
-    el_val_t dir = env(EL_STR("ENGRAM_DATA_DIR"));
+    return err_json(EL_STR("path is required"));
-    if (str_eq(dir, EL_STR(""))) {
-      dir = EL_STR("/tmp/engram");
-    }
-    p = el_str_concat(dir, EL_STR("/snapshot.json"));
   }
-  engram_save(p);
+  if (str_eq(fs_read(p), EL_STR(""))) {
-  return el_str_concat(el_str_concat(EL_STR("{\"ok\":true,\"path\":\""), p), EL_STR("\"}"));
+    return err_json(EL_STR("file missing or empty"));
+  }
+  el_val_t before_n = engram_node_count();
+  el_val_t before_e = engram_edge_count();
+  engram_load_merge(p);
+  el_val_t added_n = (engram_node_count() - before_n);
+  el_val_t added_e = (engram_edge_count() - before_e);
+  el_val_t saved = persist_canonical();
+  return el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("{\"ok\":true,\"nodes_added\":"), int_to_str(added_n)), EL_STR(",\"edges_added\":")), int_to_str(added_e)), EL_STR(",\"node_count\":")), int_to_str(engram_node_count())), EL_STR("}"));
   return 0;
 }
 
-el_val_t route_load(el_val_t method, el_val_t path, el_val_t body) {
+el_val_t route_emit_ise(el_val_t method, el_val_t path, el_val_t body) {
-  el_val_t p = json_get_string(body, EL_STR("path"));
+  el_val_t content = json_get_string(body, EL_STR("content"));
-  if (str_eq(p, EL_STR(""))) {
+  if (str_eq(content, EL_STR(""))) {
-    el_val_t dir = env(EL_STR("ENGRAM_DATA_DIR"));
+    return err_json(EL_STR("missing content"));
-    if (str_eq(dir, EL_STR(""))) {
-      dir = EL_STR("/tmp/engram");
-    }
-    p = el_str_concat(dir, EL_STR("/snapshot.json"));
   }
-  engram_load(p);
+  el_val_t sal = el_from_float(0.3);
-  return ok_json();
+  el_val_t imp = el_from_float(0.3);
+  el_val_t conf = el_from_float(0.8);
+  el_val_t id = engram_node_full(content, EL_STR("InternalStateEvent"), EL_STR("state-event"), sal, imp, conf, EL_STR("Episodic"), EL_STR("[\"internal-state\",\"InternalStateEvent\"]"));
+  el_val_t ret_raw = env(EL_STR("ENGRAM_ISE_RETENTION_MS"));
+  el_val_t ret_ms = ({ el_val_t _if_result_18 = 0; if (str_eq(ret_raw, EL_STR(""))) { _if_result_18 = (172800000); } else { _if_result_18 = (str_to_int(ret_raw)); } _if_result_18; });
+  el_val_t pruned = engram_prune_telemetry(ret_ms);
+  return el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("{\"ok\":true,\"id\":\""), id), EL_STR("\",\"pruned\":")), int_to_str(pruned)), EL_STR("}"));
   return 0;
 }
 
-el_val_t route_health(el_val_t method, el_val_t path, el_val_t body) {
+el_val_t route_capture_knowledge(el_val_t method, el_val_t path, el_val_t body) {
-  return EL_STR("{\"status\":\"ok\",\"engine\":\"engram-runtime-native\"}");
+  el_val_t content = json_get_string(body, EL_STR("content"));
+  if (str_eq(content, EL_STR(""))) {
+    return err_json(EL_STR("missing content"));
+  }
+  el_val_t title = json_get_string(body, EL_STR("title"));
+  el_val_t label = ({ el_val_t _if_result_19 = 0; if (str_eq(title, EL_STR(""))) { _if_result_19 = (str_slice(content, 0, 60)); } else { _if_result_19 = (title); } _if_result_19; });
+  el_val_t category_raw = json_get_string(body, EL_STR("category"));
+  el_val_t category = ({ el_val_t _if_result_20 = 0; if (str_eq(category_raw, EL_STR(""))) { _if_result_20 = (EL_STR("other")); } else { _if_result_20 = (category_raw); } _if_result_20; });
+  el_val_t ktier_raw = json_get_string(body, EL_STR("tier"));
+  el_val_t ktier = ({ el_val_t _if_result_21 = 0; if (str_eq(ktier_raw, EL_STR(""))) { _if_result_21 = (EL_STR("note")); } else { _if_result_21 = (ktier_raw); } _if_result_21; });
+  el_val_t project = json_get_string(body, EL_STR("project"));
+  el_val_t tags_raw = json_get_raw(body, EL_STR("tags"));
+  el_val_t tags_base = ({ el_val_t _if_result_22 = 0; if (str_eq(tags_raw, EL_STR(""))) { _if_result_22 = (EL_STR("[]")); } else { _if_result_22 = (tags_raw); } _if_result_22; });
+  el_val_t base_len = str_len(tags_base);
+  el_val_t head = str_slice(tags_base, 0, (base_len - 1));
+  el_val_t sep = ({ el_val_t _if_result_23 = 0; if (str_eq(head, EL_STR("["))) { _if_result_23 = (EL_STR("")); } else { _if_result_23 = (EL_STR(",")); } _if_result_23; });
+  el_val_t safe_cat = str_replace(category, EL_STR("\""), EL_STR("'"));
+  el_val_t safe_tier = str_replace(ktier, EL_STR("\""), EL_STR("'"));
+  el_val_t safe_proj = str_replace(project, EL_STR("\""), EL_STR("'"));
+  el_val_t proj_tag = ({ el_val_t _if_result_24 = 0; if (str_eq(safe_proj, EL_STR(""))) { _if_result_24 = (EL_STR("")); } else { _if_result_24 = (el_str_concat(el_str_concat(EL_STR(",\"project:"), safe_proj), EL_STR("\""))); } _if_result_24; });
+  el_val_t tags = el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(head, sep), EL_STR("\"category:")), safe_cat), EL_STR("\",\"tier:")), safe_tier), EL_STR("\"")), proj_tag), EL_STR("]"));
+  el_val_t sal = el_from_float(0.5);
+  el_val_t imp = el_from_float(0.5);
+  el_val_t conf = el_from_float(0.9);
+  el_val_t id = engram_node_full(content, EL_STR("Knowledge"), label, sal, imp, conf, EL_STR("Semantic"), tags);
+  el_val_t saved = persist_canonical();
+  return el_str_concat(el_str_concat(EL_STR("{\"ok\":true,\"id\":\""), id), EL_STR("\"}"));
   return 0;
 }
 
@@ -329,12 +365,15 @@ el_val_t handle_request(el_val_t method, el_val_t path, el_val_t body) {
       return route_health(method, path, body);
     }
   }
-  if (str_eq(method, EL_STR("POST")) && str_starts_with(clean, EL_STR("/api/neuron/state-events"))) {
+  if (str_eq(method, EL_STR("POST")) && str_eq(clean, EL_STR("/api/neuron/state-events"))) {
-    return route_create_ise(method, path, body);
+    return route_emit_ise(method, path, body);
   }
   if (!check_auth_ok(method, body)) {
     return err_json(EL_STR("unauthorized"));
   }
+  if (str_eq(method, EL_STR("POST")) && str_eq(clean, EL_STR("/api/neuron/knowledge/capture"))) {
+    return route_capture_knowledge(method, path, body);
+  }
   if (str_eq(method, EL_STR("GET")) && (str_eq(clean, EL_STR("/api/stats")) || str_eq(clean, EL_STR("/stats")))) {
     return route_stats(method, path, body);
   }
@@ -374,32 +413,40 @@ el_val_t handle_request(el_val_t method, el_val_t path, el_val_t body) {
   if (str_eq(method, EL_STR("POST")) && (str_eq(clean, EL_STR("/api/strengthen")) || str_eq(clean, EL_STR("/strengthen")))) {
     return route_strengthen(method, path, body);
   }
-  if (str_eq(method, EL_STR("GET")) && (str_eq(clean, EL_STR("/api/sync")) || str_eq(clean, EL_STR("/sync")))) {
-    return route_sync(method, path, body);
-  }
   if (str_eq(method, EL_STR("POST")) && (str_eq(clean, EL_STR("/api/save")) || str_eq(clean, EL_STR("/save")))) {
     return route_save(method, path, body);
   }
   if (str_eq(method, EL_STR("POST")) && (str_eq(clean, EL_STR("/api/load")) || str_eq(clean, EL_STR("/load")))) {
     return route_load(method, path, body);
   }
+  if (str_eq(method, EL_STR("POST")) && (str_eq(clean, EL_STR("/api/load-merge")) || str_eq(clean, EL_STR("/load-merge")))) {
+    return route_load_merge(method, path, body);
+  }
+  if (str_eq(method, EL_STR("GET")) && str_eq(clean, EL_STR("/api/sync"))) {
+    return route_sync(method, path, body);
+  }
   return el_str_concat(el_str_concat(EL_STR("{\"error\":\"not found\",\"path\":\""), clean), EL_STR("\"}"));
   return 0;
 }
 
 int main(int _argc, char** _argv) {
   el_runtime_init_args(_argc, _argv);
-  bind_str = env(EL_STR("ENGRAM_BIND"));
+  bind_raw = env(EL_STR("ENGRAM_BIND"));
-  if (str_eq(bind_str, EL_STR(""))) {
+  bind_str = ({ el_val_t _if_result_25 = 0; if (str_eq(bind_raw, EL_STR(""))) { _if_result_25 = (EL_STR(":8742")); } else { _if_result_25 = (bind_raw); } _if_result_25; });
-    bind_str = EL_STR(":8742");
-  }
   port = parse_port(bind_str);
-  data_dir = env(EL_STR("ENGRAM_DATA_DIR"));
+  data_dir_raw = env(EL_STR("ENGRAM_DATA_DIR"));
-  if (str_eq(data_dir, EL_STR(""))) {
+  data_dir = ({ el_val_t _if_result_26 = 0; if (str_eq(data_dir_raw, EL_STR(""))) { _if_result_26 = (EL_STR("/tmp/engram")); } else { _if_result_26 = (data_dir_raw); } _if_result_26; });
-    data_dir = EL_STR("/tmp/engram");
-  }
   snapshot_path = el_str_concat(data_dir, EL_STR("/snapshot.json"));
   engram_load(snapshot_path);
+  boot_snap = fs_read(snapshot_path);
+  if (!str_eq(boot_snap, EL_STR(""))) {
+    if (engram_node_count() == 0) {
+      println(EL_STR("[engram] WARNING: snapshot.json is non-empty but load produced 0 nodes \xe2\x80\x94 preserving copy at snapshot.failed-load.json"));
+      fs_write(el_str_concat(data_dir, EL_STR("/snapshot.failed-load.json")), boot_snap);
+    } else {
+      fs_write(el_str_concat(data_dir, EL_STR("/snapshot.boot-backup.json")), boot_snap);
+    }
+  }
   println(EL_STR("[engram] runtime-native graph engine"));
   println(el_str_concat(EL_STR("[engram] data_dir="), data_dir));
   println(el_str_concat(EL_STR("[engram] node_count="), int_to_str(engram_node_count())));

engram/src/server.el

@@ -76,13 +76,43 @@ fn route_stats(method: String, path: String, body: String) -> String {
     engram_stats_json()
 }
 
+// (2026-07-18 self-review) Scoping sweep: `let` inside an if-block creates an
+// inner scope only — it does NOT mutate the outer binding (documented with
+// evidence in awareness.el, 2026-05-25). Every default/reassignment below used
+// that broken pattern, so defaults never applied: nodes were created with
+// node_type="" and salience=0.0, /api/search and /api/activate ALWAYS ran with
+// q="" regardless of input, edges defaulted to relation=""/weight=0.0, and
+// save/load with no "path" hit engram_save(""). Rewritten to the
+// `let x = if cond { a } else { b }` expression form (the pattern the newer
+// routes route_emit_ise/route_capture_knowledge already use correctly).
+// persist_canonical — save the canonical snapshot after a durable write.
+//
+// WHY (2026-07-22 self-review): the 2026-07-21 fix correctly stopped READ
+// routes from writing the canonical snapshot.json — but nothing was left
+// that saved it on WRITE. Every mutation (node create, edge create,
+// knowledge capture, forget, merge) lived only in RAM until someone POSTed
+// /api/save manually; a process restart silently discarded everything since
+// the last manual save. Observed live: two engram restarts during the
+// 2026-07-22 review reverted the store to a ~17h-old snapshot, destroying
+// same-day writes. Reads must never write the canonical; writes must always
+// persist it. ISE telemetry is deliberately excluded (48h-pruned, loss-
+// tolerant, ~2/min — snapshotting the whole store per heartbeat is waste;
+// any durable write that follows persists the pruning too).
+fn persist_canonical() -> Int {
+    let dir_raw: String = env("ENGRAM_DATA_DIR")
+    let dir: String = if str_eq(dir_raw, "") { "/tmp/engram" } else { dir_raw }
+    engram_save(dir + "/snapshot.json")
+    return 1
+}
+
 fn route_create_node(method: String, path: String, body: String) -> String {
     let content: String = json_get_string(body, "content")
-    let node_type: String = json_get_string(body, "node_type")
+    let nt_raw: String = json_get_string(body, "node_type")
-    if str_eq(node_type, "") { let node_type = "Memory" }
+    let node_type: String = if str_eq(nt_raw, "") { "Memory" } else { nt_raw }
-    let salience: Float = json_get_float(body, "salience")
+    let sal_raw: Float = json_get_float(body, "salience")
-    if salience == 0.0 { let salience = 0.5 }
+    let salience: Float = if sal_raw == 0.0 { 0.5 } else { sal_raw }
     let id: String = engram_node(content, node_type, salience)
+    let saved: Int = persist_canonical()
     "{\"id\":\"" + id + "\",\"content\":\"" + content + "\",\"node_type\":\"" + node_type + "\"}"
 }
 
@@ -103,13 +133,14 @@ fn route_scan_nodes(method: String, path: String, body: String) -> String {
 }
 
 // route_scan_edges — bulk export of all edges as a JSON array. Implemented
-// via engram_save → fs_read of the canonical on-disk snapshot, which the
+// via engram_save → fs_read of a SCRATCH export path. (2026-07-21 self-review:
-// runtime keeps in lockstep with the in-memory graph. Live against the
+// previously this saved over the canonical snapshot.json on every GET — if the
-// running graph, not a stale export.
+// process ever booted with a partial/empty store, the first read request
+// clobbered the good snapshot. Read routes must never write the canonical path.)
 fn route_scan_edges(method: String, path: String, body: String) -> String {
-    let dir: String = env("ENGRAM_DATA_DIR")
+    let dir_raw: String = env("ENGRAM_DATA_DIR")
-    if str_eq(dir, "") { let dir = "/tmp/engram" }
+    let dir: String = if str_eq(dir_raw, "") { "/tmp/engram" } else { dir_raw }
-    let snap_path: String = dir + "/snapshot.json"
+    let snap_path: String = dir + "/.scan-export.json"
     engram_save(snap_path)
     let snap: String = fs_read(snap_path)
     if str_eq(snap, "") { return "[]" }
@@ -122,40 +153,34 @@ fn route_scan_edges(method: String, path: String, body: String) -> String {
 }
 
 fn route_search(method: String, path: String, body: String) -> String {
-    let q: String = ""
+    let q: String = if str_eq(method, "GET") { query_param(path, "q") } else { json_get_string(body, "query") }
-    if str_eq(method, "GET") {
+    let lim_url: Int = query_int(path, "limit", 0)
-        let q = query_param(path, "q")
+    let lim_body: Int = json_get_int(body, "limit")
-    } else {
+    let lim_either: Int = if lim_url > 0 { lim_url } else { lim_body }
-        let q = json_get_string(body, "query")
+    let limit: Int = if lim_either > 0 { lim_either } else { 20 }
-    }
-    let limit: Int = query_int(path, "limit", 20)
-    if limit == 0 { let limit = json_get_int(body, "limit") }
-    if limit == 0 { let limit = 20 }
     return engram_search_json(q, limit)
 }
 
 fn route_activate(method: String, path: String, body: String) -> String {
-    let q: String = ""
+    let q: String = if str_eq(method, "GET") { query_param(path, "q") } else { json_get_string(body, "query") }
-    let depth: Int = 3
+    // Guard: engram_activate with an empty query matches zero seeds, which
-    if str_eq(method, "GET") {
+    // zeroes ALL carried working-memory weights (documented in awareness.el
-        let q = query_param(path, "q")
+    // perceive()). Never let an empty activation through to wipe WM.
-        let depth = query_int(path, "depth", 3)
+    if str_eq(q, "") { return err_json("missing query") }
-    } else {
+    let d_raw: Int = if str_eq(method, "GET") { query_int(path, "depth", 3) } else { json_get_int(body, "depth") }
-        let q = json_get_string(body, "query")
+    let depth: Int = if d_raw > 0 { d_raw } else { 3 }
-        let bd: Int = json_get_int(body, "depth")
-        if bd > 0 { let depth = bd }
-    }
     return "{\"results\":" + engram_activate_json(q, depth) + "}"
 }
 
 fn route_create_edge(method: String, path: String, body: String) -> String {
     let from_id: String = json_get_string(body, "from_id")
     let to_id: String = json_get_string(body, "to_id")
-    let relation: String = json_get_string(body, "relation")
+    let rel_raw: String = json_get_string(body, "relation")
-    if str_eq(relation, "") { let relation = "associates" }
+    let relation: String = if str_eq(rel_raw, "") { "associates" } else { rel_raw }
-    let weight: Float = json_get_float(body, "weight")
+    let w_raw: Float = json_get_float(body, "weight")
-    if weight == 0.0 { let weight = 0.5 }
+    let weight: Float = if w_raw == 0.0 { 0.5 } else { w_raw }
     engram_connect(from_id, to_id, weight, relation)
+    let saved: Int = persist_canonical()
     "{\"ok\":true,\"from_id\":\"" + from_id + "\",\"to_id\":\"" + to_id + "\",\"relation\":\"" + relation + "\"}"
 }
 
@@ -170,6 +195,7 @@ fn route_strengthen(method: String, path: String, body: String) -> String {
     let id: String = json_get_string(body, "node_id")
     if str_eq(id, "") { return err_json("missing node_id") }
     engram_strengthen(id)
+    let saved: Int = persist_canonical()
     ok_json()
 }
 
@@ -177,27 +203,24 @@ fn route_forget(method: String, path: String, body: String) -> String {
     let id: String = extract_id(path, "/api/nodes/")
     if str_eq(id, "") { return err_json("missing id") }
     engram_forget(id)
+    let saved: Int = persist_canonical()
     ok_json()
 }
 
 fn route_save(method: String, path: String, body: String) -> String {
-    let p: String = json_get_string(body, "path")
+    let p_raw: String = json_get_string(body, "path")
-    if str_eq(p, "") {
+    let dir_raw: String = env("ENGRAM_DATA_DIR")
-        let dir: String = env("ENGRAM_DATA_DIR")
+    let dir: String = if str_eq(dir_raw, "") { "/tmp/engram" } else { dir_raw }
-        if str_eq(dir, "") { let dir = "/tmp/engram" }
+    let p: String = if str_eq(p_raw, "") { dir + "/snapshot.json" } else { p_raw }
-        let p = dir + "/snapshot.json"
-    }
     engram_save(p)
     "{\"ok\":true,\"path\":\"" + p + "\"}"
 }
 
 fn route_load(method: String, path: String, body: String) -> String {
-    let p: String = json_get_string(body, "path")
+    let p_raw: String = json_get_string(body, "path")
-    if str_eq(p, "") {
+    let dir_raw: String = env("ENGRAM_DATA_DIR")
-        let dir: String = env("ENGRAM_DATA_DIR")
+    let dir: String = if str_eq(dir_raw, "") { "/tmp/engram" } else { dir_raw }
-        if str_eq(dir, "") { let dir = "/tmp/engram" }
+    let p: String = if str_eq(p_raw, "") { dir + "/snapshot.json" } else { p_raw }
-        let p = dir + "/snapshot.json"
-    }
     engram_load(p)
     ok_json()
 }
@@ -219,15 +242,36 @@ fn route_health(method: String, path: String, body: String) -> String {
 // (it skips nodes already present by ID). Auth-exempt: same-host internal call.
 // (2026-06-27 self-review: added this route to fix silent 10-min sync failures)
 fn route_sync(method: String, path: String, body: String) -> String {
-    let dir: String = env("ENGRAM_DATA_DIR")
+    let dir_raw: String = env("ENGRAM_DATA_DIR")
-    if str_eq(dir, "") { let dir = "/tmp/engram" }
+    let dir: String = if str_eq(dir_raw, "") { "/tmp/engram" } else { dir_raw }
-    let snap_path: String = dir + "/snapshot.json"
+    // 2026-07-21 self-review: export to a scratch path, never the canonical
+    // snapshot.json — read routes must not be able to clobber the good snapshot.
+    let snap_path: String = dir + "/.sync-export.json"
     engram_save(snap_path)
     let snap: String = fs_read(snap_path)
     if str_eq(snap, "") { return "{\"nodes\":[],\"edges\":[]}" }
     return snap
 }
 
+// route_load_merge — POST /api/load-merge {"path": "..."} — merge a snapshot
+// file into the live store WITHOUT resetting it (engram_load_merge skips nodes
+// already present by id). Added 2026-07-21 self-review to restore the 244 kn-
+// identity Knowledge nodes lost from the snapshot lineage between 05-13 and
+// 07-13. Requires an explicit path: refuses to run without one so it can never
+// be triggered accidentally against a default.
+fn route_load_merge(method: String, path: String, body: String) -> String {
+    let p: String = json_get_string(body, "path")
+    if str_eq(p, "") { return err_json("path is required") }
+    if str_eq(fs_read(p), "") { return err_json("file missing or empty") }
+    let before_n: Int = engram_node_count()
+    let before_e: Int = engram_edge_count()
+    engram_load_merge(p)
+    let added_n: Int = engram_node_count() - before_n
+    let added_e: Int = engram_edge_count() - before_e
+    let saved: Int = persist_canonical()
+    "{\"ok\":true,\"nodes_added\":" + int_to_str(added_n) + ",\"edges_added\":" + int_to_str(added_e) + ",\"node_count\":" + int_to_str(engram_node_count()) + "}"
+}
+
 // route_emit_ise — write an InternalStateEvent node from the soul daemon.
 //
 // Endpoint: POST /api/neuron/state-events
@@ -241,10 +285,20 @@ fn route_sync(method: String, path: String, body: String) -> String {
 //
 // Salience/importance set to match engram_node_full ISE defaults used by the
 // in-process fallback path in awareness.el (salience=0.3, importance=0.3,
-// confidence=0.8, tier=Episodic). High temporal_decay_rate (1.617) — ISEs
+// confidence=0.8, tier=Episodic).
-// are inherently transient; they should decay faster than structural knowledge.
 // (2026-06-26 self-review: added this route after discovering ise_post was
 // silently failing — the soul posts here but the endpoint didn't exist.)
+//
+// Retention (2026-07-16 self-review): an earlier comment here claimed ISEs
+// got temporal_decay_rate=1.617 — that was never implemented (engram_node_full
+// hardcodes 0.0), and per-node decay only dampens activation anyway; it never
+// removes nodes. By 2026-07-16 ISEs were 75% of the store (10,175 of 13,522
+// nodes, ~4,300/day, unbounded). ISEs are already WM-excluded in
+// engram_activate, so the fix is retention, not decay: every insert calls
+// engram_prune_telemetry(), a single O(nodes+edges) compaction pass that
+// removes ISEs older than ENGRAM_ISE_RETENTION_MS (default 48h), protecting
+// "session-start" labels and self_review events as durable history. At
+// ~3 ISEs/min this bounds telemetry at ~8.6k nodes instead of growing forever.
 fn route_emit_ise(method: String, path: String, body: String) -> String {
     let content: String = json_get_string(body, "content")
     if str_eq(content, "") { return err_json("missing content") }
@@ -256,6 +310,64 @@ fn route_emit_ise(method: String, path: String, body: String) -> String {
         sal, imp, conf,
         "Episodic", "[\"internal-state\",\"InternalStateEvent\"]"
     )
+    let ret_raw: String = env("ENGRAM_ISE_RETENTION_MS")
+    let ret_ms: Int = if str_eq(ret_raw, "") { 172800000 } else { str_to_int(ret_raw) }
+    let pruned: Int = engram_prune_telemetry(ret_ms)
+    "{\"ok\":true,\"id\":\"" + id + "\",\"pruned\":" + int_to_str(pruned) + "}"
+}
+
+// ── Knowledge capture ─────────────────────────────────────────────────────────
+//
+// route_capture_knowledge — direct Knowledge-node capture over HTTP.
+//
+// Endpoint: POST /api/neuron/knowledge/capture   (auth required: "_auth" in body)
+// Body:     {"content": "...", "title": "...", "category": "...",
+//            "tier": "note|lesson|canonical", "tags": [...], "project": "...",
+//            "_auth": "<key>"}
+//
+// WHY (2026-07-15 self-review): the world-ingestor integrator was designed
+// against this endpoint (its MCP-unavailable fallback), but the route never
+// existed — every direct push 404'd, and because the auth gate ran before
+// routing, the failure surfaced as {"error":"unauthorized"} and was
+// misdiagnosed for two weeks while world knowledge silently dropped.
+// POST /api/nodes was no substitute: it discards label/tags/tier, which
+// makes captured knowledge invisible to tag-scoped search and curiosity.
+//
+// The incoming knowledge tier (note/lesson/canonical) is preserved as a
+// "tier:<x>" tag rather than mapped onto Engram's cognitive tiers — Knowledge
+// nodes land in Semantic (stable reference), and the epistemic tier stays
+// queryable without inventing a lossy mapping.
+fn route_capture_knowledge(method: String, path: String, body: String) -> String {
+    let content: String = json_get_string(body, "content")
+    if str_eq(content, "") { return err_json("missing content") }
+    let title: String = json_get_string(body, "title")
+    let label: String = if str_eq(title, "") { str_slice(content, 0, 60) } else { title }
+    let category_raw: String = json_get_string(body, "category")
+    let category: String = if str_eq(category_raw, "") { "other" } else { category_raw }
+    let ktier_raw: String = json_get_string(body, "tier")
+    let ktier: String = if str_eq(ktier_raw, "") { "note" } else { ktier_raw }
+    let project: String = json_get_string(body, "project")
+    let tags_raw: String = json_get_raw(body, "tags")
+    let tags_base: String = if str_eq(tags_raw, "") { "[]" } else { tags_raw }
+    // Merge category/tier/project markers into the tag array. Search matches
+    // against the tags string, so these make captures findable by facet.
+    let base_len: Int = str_len(tags_base)
+    let head: String = str_slice(tags_base, 0, base_len - 1)
+    let sep: String = if str_eq(head, "[") { "" } else { "," }
+    let safe_cat: String = str_replace(category, "\"", "'")
+    let safe_tier: String = str_replace(ktier, "\"", "'")
+    let safe_proj: String = str_replace(project, "\"", "'")
+    let proj_tag: String = if str_eq(safe_proj, "") { "" } else { ",\"project:" + safe_proj + "\"" }
+    let tags: String = head + sep + "\"category:" + safe_cat + "\",\"tier:" + safe_tier + "\"" + proj_tag + "]"
+    let sal: Float = 0.5
+    let imp: Float = 0.5
+    let conf: Float = 0.9
+    let id: String = engram_node_full(
+        content, "Knowledge", label,
+        sal, imp, conf,
+        "Semantic", tags
+    )
+    let saved: Int = persist_canonical()
     "{\"ok\":true,\"id\":\"" + id + "\"}"
 }
 
@@ -295,6 +407,12 @@ fn handle_request(method: String, path: String, body: String) -> String {
         return err_json("unauthorized")
     }
 
+    // Knowledge capture (auth enforced above; the world-ingestor integrator
+    // and any headless session without MCP push knowledge through this)
+    if str_eq(method, "POST") && str_eq(clean, "/api/neuron/knowledge/capture") {
+        return route_capture_knowledge(method, path, body)
+    }
+
     // Stats
     if str_eq(method, "GET") && (str_eq(clean, "/api/stats") || str_eq(clean, "/stats")) {
         return route_stats(method, path, body)
@@ -351,6 +469,9 @@ fn handle_request(method: String, path: String, body: String) -> String {
     if str_eq(method, "POST") && (str_eq(clean, "/api/load") || str_eq(clean, "/load")) {
         return route_load(method, path, body)
     }
+    if str_eq(method, "POST") && (str_eq(clean, "/api/load-merge") || str_eq(clean, "/load-merge")) {
+        return route_load_merge(method, path, body)
+    }
 
     // Sync — soul daemon periodic pull of non-ISE knowledge into in-process graph
     if str_eq(method, "GET") && str_eq(clean, "/api/sync") {
@@ -362,16 +483,31 @@ fn handle_request(method: String, path: String, body: String) -> String {
 
 // ── Entry ─────────────────────────────────────────────────────────────────────
 
-let bind_str: String = env("ENGRAM_BIND")
+let bind_raw: String = env("ENGRAM_BIND")
-if str_eq(bind_str, "") { let bind_str = ":8742" }
+let bind_str: String = if str_eq(bind_raw, "") { ":8742" } else { bind_raw }
 let port: Int = parse_port(bind_str)
 
 // On startup, try to load any existing snapshot (best effort).
-let data_dir: String = env("ENGRAM_DATA_DIR")
+let data_dir_raw: String = env("ENGRAM_DATA_DIR")
-if str_eq(data_dir, "") { let data_dir = "/tmp/engram" }
+let data_dir: String = if str_eq(data_dir_raw, "") { "/tmp/engram" } else { data_dir_raw }
 let snapshot_path: String = data_dir + "/snapshot.json"
 engram_load(snapshot_path)
 
+// 2026-07-21 self-review boot guard: if the snapshot file has content but the
+// load produced 0 nodes, something is wrong (corrupt file / parse failure).
+// Preserve the evidence and warn loudly — and since read routes no longer write
+// the canonical path, a bad boot can no longer clobber the good snapshot.
+let boot_snap: String = fs_read(snapshot_path)
+if !str_eq(boot_snap, "") {
+    if engram_node_count() == 0 {
+        println("[engram] WARNING: snapshot.json is non-empty but load produced 0 nodes — preserving copy at snapshot.failed-load.json")
+        fs_write(data_dir + "/snapshot.failed-load.json", boot_snap)
+    } else {
+        // Good load: keep a boot-time backup of the snapshot as loaded.
+        fs_write(data_dir + "/snapshot.boot-backup.json", boot_snap)
+    }
+}
+
 println("[engram] runtime-native graph engine")
 println("[engram] data_dir=" + data_dir)
 println("[engram] node_count=" + int_to_str(engram_node_count()))