fix(runtime): pass model through to the LLM API (+ UTF-8 JSON escaping) #53

Merged
will.anderson merged 3 commits from fix/llm-model-and-utf8 into stage 2026-06-10 22:01:52 +00:00
+43 -14
View File
@@ -3135,23 +3135,49 @@ static void jb_puts(JsonBuf* b, const char* s) {
static void jb_emit_escaped(JsonBuf* b, const char* s) {
jb_putc(b, '"');
for (; *s; s++) {
unsigned char c = (unsigned char)*s;
const unsigned char* p = (const unsigned char*)s;
while (*p) {
unsigned char c = *p;
switch (c) {
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;
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;
default:
if (c < 0x20) {
char tmp[8];
snprintf(tmp, sizeof(tmp), "\\u%04x", c);
jb_puts(b, tmp);
} else {
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++;
}
break;
}
@@ -8447,7 +8473,7 @@ static el_val_t llm_provider_request(const char* url, const char* key,
}
}
static el_val_t llm_chain_call(const char* system_str, const char* user_str) {
static el_val_t llm_chain_call(const char* model_pref, 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);
@@ -8460,6 +8486,7 @@ static el_val_t llm_chain_call(const char* system_str, const char* user_str) {
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);
@@ -8470,7 +8497,7 @@ static el_val_t llm_chain_call(const char* system_str, const char* user_str) {
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, NULL, system_str, user_str);
return llm_provider_request(LLM_API_URL, api_key, 1, model_pref, system_str, user_str);
}
/* Legacy llm_request — kept for backward compat with agentic loop internals */
@@ -8534,14 +8561,16 @@ 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(NULL, u);
return llm_chain_call(m, 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(s, u);
return llm_chain_call(m, s, u);
}
/* ── Tool registry for llm_call_agentic ─────────────────────────────────── */