Merge pull request 'Fix engram_node_full field corruption + add validation' (#52) from fix/engram-node-full-field-corruption into dev

Fix engram_node_full field corruption + add validation (+ SessionSummary allowlist)

lang/runtime/engram.el

@@ -6,15 +6,55 @@
 //
 // Dependencies: runtime/string.el, runtime/json.el
 
+// --- Validation (defense in depth) ---
+// el_val_t is an untyped machine word, so a wrong TYPE can't be caught here — but a
+// wrong VALUE can (a tier in the node_type slot, an empty/garbage string, an int, a
+// path, a model name, a cgi id). Reject loudly instead of silently writing junk.
+
+fn engram_valid_node_type(t: String) -> Bool {
+    return str_eq(t, "Memory") || str_eq(t, "Knowledge") || str_eq(t, "Belief")
+        || str_eq(t, "Project") || str_eq(t, "Tag") || str_eq(t, "BacklogItem")
+        || str_eq(t, "Artifact") || str_eq(t, "Conversation") || str_eq(t, "ExecutionContext")
+        || str_eq(t, "InternalStateEvent") || str_eq(t, "Self") || str_eq(t, "Entity")
+        || str_eq(t, "Process") || str_eq(t, "ConfigEntry") || str_eq(t, "Concept") || str_eq(t, "Imprint")
+        || str_eq(t, "SessionSummary")
+}
+
+fn engram_valid_tier(t: String) -> Bool {
+    return str_eq(t, "Semantic") || str_eq(t, "Episodic") || str_eq(t, "Working")
+        || str_eq(t, "Procedural") || str_eq(t, "Canonical") || str_eq(t, "Note") || str_eq(t, "Lesson")
+}
+
 // --- Node creation ---
 
 fn engram_node(content: String, node_type: String, salience: Float) -> String {
+    if !engram_valid_node_type(node_type) {
+        __println("[engram] REJECTED node write — invalid node_type '" + node_type + "'")
+        return ""
+    }
     return __engram_node(content, node_type, salience)
 }
 
-fn engram_node_full(content: String, nt: String, sal: Float, imp: Float,
-                    source: String, lang: String, ts: Int, tags: String) -> String {
-    return __engram_node_full(content, nt, sal, imp, source, lang, ts, tags)
+// Signature MUST match the C primitive __engram_node_full exactly (el_seed.h):
+//   (content, node_type, label, salience, importance, confidence, tier, tags)
+// The previous wrapper declared a stale 8-arg schema with wrong names AND types
+// (sal:Float at the label slot, ts:Int at the tier slot). Because el_val_t is an
+// untyped machine word, the EL compiler coerced caller args to those wrong param
+// types and then forwarded them BY POSITION into the C function — so tier received
+// an int, importance/confidence received strings, label received a float, etc.
+// That is the field-corruption bug. Match the contract 1:1 — no coercion, no reorder.
+fn engram_node_full(content: String, node_type: String, label: String,
+                    salience: Float, importance: Float, confidence: Float,
+                    tier: String, tags: String) -> String {
+    if !engram_valid_node_type(node_type) {
+        __println("[engram] REJECTED node write — invalid node_type '" + node_type + "' (label=" + label + ")")
+        return ""
+    }
+    if !engram_valid_tier(tier) {
+        __println("[engram] REJECTED node write — invalid tier '" + tier + "' (node_type=" + node_type + ", label=" + label + ")")
+        return ""
+    }
+    return __engram_node_full(content, node_type, label, salience, importance, confidence, tier, tags)
 }
 
 // --- Node retrieval ---