Compare commits
2 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| c2afcbddf5 | |||
| dfe4e83ed1 |
@@ -3135,49 +3135,23 @@ static void jb_puts(JsonBuf* b, const char* s) {
|
||||
|
||||
static void jb_emit_escaped(JsonBuf* b, const char* s) {
|
||||
jb_putc(b, '"');
|
||||
const unsigned char* p = (const unsigned char*)s;
|
||||
while (*p) {
|
||||
unsigned char c = *p;
|
||||
for (; *s; s++) {
|
||||
unsigned char c = (unsigned char)*s;
|
||||
switch (c) {
|
||||
case '"': jb_puts(b, "\\\""); p++; break;
|
||||
case '\\': jb_puts(b, "\\\\"); p++; break;
|
||||
case '\b': jb_puts(b, "\\b"); p++; break;
|
||||
case '\f': jb_puts(b, "\\f"); p++; break;
|
||||
case '\n': jb_puts(b, "\\n"); p++; break;
|
||||
case '\r': jb_puts(b, "\\r"); p++; break;
|
||||
case '\t': jb_puts(b, "\\t"); p++; break;
|
||||
case '"': jb_puts(b, "\\\""); break;
|
||||
case '\\': jb_puts(b, "\\\\"); break;
|
||||
case '\b': jb_puts(b, "\\b"); break;
|
||||
case '\f': jb_puts(b, "\\f"); break;
|
||||
case '\n': jb_puts(b, "\\n"); break;
|
||||
case '\r': jb_puts(b, "\\r"); break;
|
||||
case '\t': jb_puts(b, "\\t"); break;
|
||||
default:
|
||||
if (c < 0x20) {
|
||||
char tmp[8];
|
||||
snprintf(tmp, sizeof(tmp), "\\u%04x", c);
|
||||
jb_puts(b, tmp);
|
||||
p++;
|
||||
} else if (c < 0x80) {
|
||||
jb_putc(b, (char)c);
|
||||
p++;
|
||||
} else {
|
||||
/* Multi-byte UTF-8: validate sequence, pass through if valid,
|
||||
* escape as \u00xx if the start byte is invalid/orphaned. */
|
||||
int seq_len = 0;
|
||||
if ((c & 0xE0) == 0xC0) seq_len = 2;
|
||||
else if ((c & 0xF0) == 0xE0) seq_len = 3;
|
||||
else if ((c & 0xF8) == 0xF0) seq_len = 4;
|
||||
if (seq_len >= 2) {
|
||||
int valid = 1;
|
||||
for (int i = 1; i < seq_len; i++) {
|
||||
if ((p[i] & 0xC0) != 0x80) { valid = 0; break; }
|
||||
}
|
||||
if (valid) {
|
||||
for (int i = 0; i < seq_len; i++) jb_putc(b, (char)p[i]);
|
||||
p += seq_len;
|
||||
break;
|
||||
}
|
||||
}
|
||||
/* Invalid start byte or truncated sequence — escape it */
|
||||
char tmp[8];
|
||||
snprintf(tmp, sizeof(tmp), "\\u%04x", c);
|
||||
jb_puts(b, tmp);
|
||||
p++;
|
||||
jb_putc(b, (char)c);
|
||||
}
|
||||
break;
|
||||
}
|
||||
@@ -8473,7 +8447,7 @@ static el_val_t llm_provider_request(const char* url, const char* key,
|
||||
}
|
||||
}
|
||||
|
||||
static el_val_t llm_chain_call(const char* model_pref, const char* system_str, const char* user_str) {
|
||||
static el_val_t llm_chain_call(const char* system_str, const char* user_str) {
|
||||
char url_key[64], key_key[64], fmt_key[64], model_key[64];
|
||||
for (int i = 0; i < LLM_MAX_PROVIDERS; i++) {
|
||||
snprintf(url_key, sizeof(url_key), "NEURON_LLM_%d_URL", i);
|
||||
@@ -8486,7 +8460,6 @@ static el_val_t llm_chain_call(const char* model_pref, const char* system_str, c
|
||||
const char* fmt_s = getenv(fmt_key);
|
||||
int fmt = (fmt_s && strcmp(fmt_s, "anthropic") == 0) ? 1 : 0;
|
||||
const char* model = getenv(model_key);
|
||||
if (!model || !*model) model = model_pref; /* fall back to the caller-requested model */
|
||||
fprintf(stderr, "[llm] trying provider %d (%s)\n", i, url);
|
||||
el_val_t result = llm_provider_request(url, key, fmt, model, system_str, user_str);
|
||||
const char* t = EL_CSTR(result);
|
||||
@@ -8497,7 +8470,7 @@ static el_val_t llm_chain_call(const char* model_pref, const char* system_str, c
|
||||
const char* api_key = getenv("ANTHROPIC_API_KEY");
|
||||
if (!api_key || !*api_key) return http_error_json("no LLM providers configured");
|
||||
fprintf(stderr, "[llm] using legacy ANTHROPIC_API_KEY fallback\n");
|
||||
return llm_provider_request(LLM_API_URL, api_key, 1, model_pref, system_str, user_str);
|
||||
return llm_provider_request(LLM_API_URL, api_key, 1, NULL, system_str, user_str);
|
||||
}
|
||||
|
||||
/* Legacy llm_request — kept for backward compat with agentic loop internals */
|
||||
@@ -8561,16 +8534,14 @@ static el_val_t llm_extract_text(el_val_t resp_val) {
|
||||
}
|
||||
|
||||
el_val_t llm_call(el_val_t model, el_val_t prompt) {
|
||||
const char* m = EL_CSTR(model);
|
||||
const char* u = EL_CSTR(prompt); if (!u) u = "";
|
||||
return llm_chain_call(m, NULL, u);
|
||||
return llm_chain_call(NULL, u);
|
||||
}
|
||||
|
||||
el_val_t llm_call_system(el_val_t model, el_val_t system_prompt, el_val_t user_prompt) {
|
||||
const char* m = EL_CSTR(model);
|
||||
const char* s = EL_CSTR(system_prompt); if (!s) s = "";
|
||||
const char* u = EL_CSTR(user_prompt); if (!u) u = "";
|
||||
return llm_chain_call(m, s, u);
|
||||
return llm_chain_call(s, u);
|
||||
}
|
||||
|
||||
/* ── Tool registry for llm_call_agentic ─────────────────────────────────── */
|
||||
|
||||
+43
-3
@@ -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 ---
|
||||
|
||||
Reference in New Issue
Block a user