Compare commits

..

1 Commits

Author SHA1 Message Date
will.anderson f78da81aa4 runtime: fix the memory leak + write-corruption pair in el_runtime.c
El SDK Release / build-and-release (pull_request) Failing after 11m58s
Two independent investigations, one runtime, complementary halves:

1. Leak (Jul 2, this machine): JsonBuf buffers returned via el_wrap_str
   were raw malloc, never arena-tracked — every engram_*_json call leaked
   its output unconditionally. Added jb_finish() arena-tracking across all
   ~30 return sites. Plus el_arena_push/pop per-tick bracketing support
   for the soul's awareness loop (the loop ran outside any request arena,
   so even correctly-tracked allocations were permanent — 7.5GB RSS in
   under a minute at 1s tick).

2. Corruption (Tim's container soak, docs findings/container-migration):
   stored engram node/edge fields (content, node_type, label, tier, tags,
   metadata, from/to ids) were arena el_strdup — freed at request end,
   leaving dangling pointers that read back as recycled request-buffer
   bytes one request later. This is the June corruption root cause and
   the mechanism that grew snapshot.json to 18GB of empty-type junk
   (21.6M nodes, 3,335 real). 39 sites switched to el_strdup_persist,
   plus a latent double-free fix in engram_load metadata fixup.

Interaction note: fix 1's per-tick arena reclamation makes fix 2
mandatory — more aggressive arena recycling widens the use-after-free
window if stored fields still live in the arena. Apply as a pair, never
separately.

Verified live: soul + engram rebuilt from this runtime, booted against
the recovered real snapshot (3,335 nodes/40,146 edges), 5h stable at
<100MB RSS, write-then-next-request field-integrity test passes (the
June corruption fingerprint does not reproduce). engram/dist/engram
binary updated from this build.

Investigation credit: leak diagnosis this machine Jul 2-6; corruption
diagnosis + persist-fix patch by Tim's instance (docs PR #4).
2026-07-13 16:22:02 -05:00
2 changed files with 87 additions and 69 deletions
BIN
View File
Binary file not shown.
+87 -69
View File
@@ -710,6 +710,7 @@ static void jb_init(JsonBuf* b);
static void jb_putc(JsonBuf* b, char c);
static void jb_puts(JsonBuf* b, const char* s);
static void jb_emit_escaped(JsonBuf* b, const char* s);
static char* jb_finish(JsonBuf* b);
static int looks_like_string(el_val_t v);
static const char* json_find_key(const char* s, const char* key);
static const char* json_skip_value(const char* p);
@@ -2014,7 +2015,7 @@ el_val_t http_response(el_val_t status, el_val_t headers_json, el_val_t body) {
jb_puts(&out, ",\"body\":");
jb_emit_escaped(&out, b);
jb_putc(&out, '}');
return el_wrap_str(out.buf);
return el_wrap_str(jb_finish(&out));
}
/* ── Filesystem ──────────────────────────────────────────────────────────── */
@@ -2121,7 +2122,7 @@ el_val_t exec_capture(el_val_t cmdv) {
char buf[4096];
while (fgets(buf, sizeof(buf), f)) jb_puts(&b, buf);
pclose(f);
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
// exec — run a shell command via /bin/sh, capture stdout, return as String.
@@ -2145,7 +2146,7 @@ el_val_t exec(el_val_t cmdv) {
jb_puts(&b, buf);
}
pclose(f);
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
// exec_bg — run a shell command in background, return PID as String.
@@ -3292,6 +3293,23 @@ static void jb_puts(JsonBuf* b, const char* s) {
b->buf[b->len] = '\0';
}
/* jb_finish — call exactly once, at the point a JsonBuf's buffer is handed
* off as an el_val_t return value (via el_wrap_str). JsonBuf allocates through
* raw malloc/realloc (jb_init/jb_reserve), NOT el_strdup/el_strbuf, so unlike
* those helpers it was never registered with the per-request arena every
* JsonBuf-built JSON string leaked unconditionally, whether or not a request
* arena was active, because nothing ever freed it. el_arena_track() is a
* documented no-op when no arena is active, so this is safe to call from any
* context (HTTP request handler, CLI arena-scope, or no arena at all the
* last case still leaks, same as before, until the caller's context is itself
* arena-scoped). Do NOT call this on a JsonBuf whose ->buf is consumed by
* another builder (jb_puts(&other, x.buf)) and freed manually only on the
* one actually returned via el_wrap_str. */
static char* jb_finish(JsonBuf* b) {
el_arena_track(b->buf);
return b->buf;
}
static void jb_emit_escaped(JsonBuf* b, const char* s) {
jb_putc(b, '"');
const unsigned char* p = (const unsigned char*)s;
@@ -3400,7 +3418,7 @@ static void jb_emit_value(JsonBuf* b, el_val_t v) {
el_val_t json_stringify(el_val_t v) {
JsonBuf b; jb_init(&b);
jb_emit_value(&b, v);
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
/* ── JSON substring accessors ────────────────────────────────────────────── */
@@ -3587,7 +3605,7 @@ el_val_t json_set(el_val_t json_str, el_val_t key, el_val_t value) {
jb_putc(&b, ':');
jb_puts(&b, raw_val);
jb_putc(&b, '}');
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
const char* existing = json_find_key(json, k);
JsonBuf b; jb_init(&b);
@@ -3601,7 +3619,7 @@ el_val_t json_set(el_val_t json_str, el_val_t key, el_val_t value) {
b.buf[b.len] = '\0';
jb_puts(&b, raw_val);
jb_puts(&b, end);
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
/* Insert before closing '}'. Find last '}' */
size_t jl = strlen(json);
@@ -3633,7 +3651,7 @@ el_val_t json_set(el_val_t json_str, el_val_t key, el_val_t value) {
jb_puts(&b, raw_val);
/* Append from close_idx onward */
jb_puts(&b, json + close_idx);
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
el_val_t json_array_len(el_val_t json_str) {
@@ -3771,7 +3789,7 @@ el_val_t json_build_object(el_val_t kvs) {
jb_putc(&b, '"');
}
jb_putc(&b, '}');
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
/* json_build_array — build a JSON array from a list of raw JSON values.
@@ -3789,7 +3807,7 @@ el_val_t json_build_array(el_val_t items) {
jb_puts(&b, vs);
}
jb_putc(&b, ']');
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
/* ── Time ────────────────────────────────────────────────────────────────── */
@@ -5193,7 +5211,7 @@ el_val_t state_keys(void) {
}
jb_putc(&b, ']');
pthread_mutex_unlock(&_state_mu);
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
/* Returns 1 (true) if the key is present in the state store, else 0 (false). */
@@ -5399,7 +5417,7 @@ el_val_t str_format(el_val_t fmt, el_val_t data) {
jb_putc(&b, *p);
p++;
}
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
el_val_t str_lower(el_val_t s) { return str_to_lower(s); }
@@ -5815,7 +5833,7 @@ el_val_t list_join(el_val_t listv, el_val_t sep) {
jb_puts(&b, tmp);
}
}
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
el_val_t list_range(el_val_t start, el_val_t end) {
@@ -6465,12 +6483,12 @@ el_val_t engram_node(el_val_t content, el_val_t node_type, el_val_t salience) {
n->id = engram_new_id();
const char* c = EL_CSTR(content);
const char* nt = EL_CSTR(node_type);
n->content = el_strdup(c ? c : "");
n->node_type = el_strdup(nt && *nt ? nt : "Memory");
n->label = engram_first_n_chars(c, 60);
n->tier = el_strdup("Working");
n->tags = el_strdup("");
n->metadata = el_strdup("{}");
n->content = el_strdup_persist(c ? c : "");
n->node_type = el_strdup_persist(nt && *nt ? nt : "Memory");
{ char* _lb = engram_first_n_chars(c, 60); n->label = el_strdup_persist(_lb); } /* persist: stored field must outlive request arena */
n->tier = el_strdup_persist("Working");
n->tags = el_strdup_persist("");
n->metadata = el_strdup_persist("{}");
n->salience = engram_decode_score(salience);
if (n->salience <= 0.0 || n->salience > 1.0) n->salience = 0.5;
n->importance = 0.5;
@@ -6597,11 +6615,11 @@ el_val_t engram_node_layered(el_val_t content, el_val_t node_type, el_val_t labe
const char* lb = EL_CSTR(label);
const char* tg = EL_CSTR(tags);
const char* st = EL_CSTR(status);
n->content = el_strdup(c ? c : "");
n->node_type = el_strdup(nt && *nt ? nt : "Memory");
n->label = el_strdup(lb && *lb ? lb : (c ? engram_first_n_chars(c, 60) : ""));
n->tier = el_strdup("Working");
n->tags = el_strdup(tg ? tg : "");
n->content = el_strdup_persist(c ? c : "");
n->node_type = el_strdup_persist(nt && *nt ? nt : "Memory");
n->label = el_strdup_persist(lb && *lb ? lb : (c ? engram_first_n_chars(c, 60) : ""));
n->tier = el_strdup_persist("Working");
n->tags = el_strdup_persist(tg ? tg : "");
if (st && *st) {
/* Minimal metadata payload: {"status":"..."}. Keep it cheap so
* callers using `status` don't pay JSON parse cost on every read. */
@@ -6610,7 +6628,7 @@ el_val_t engram_node_layered(el_val_t content, el_val_t node_type, el_val_t labe
snprintf(meta, sl, "{\"status\":\"%s\"}", st);
n->metadata = meta;
} else {
n->metadata = el_strdup("{}");
n->metadata = el_strdup_persist("{}");
}
n->salience = engram_decode_score(salience);
n->importance = engram_decode_score(certainty);
@@ -6883,10 +6901,10 @@ void engram_connect(el_val_t from_id, el_val_t to_id, el_val_t weight, el_val_t
EngramEdge* e = &g->edges[g->edge_count];
memset(e, 0, sizeof(*e));
e->id = engram_new_id();
e->from_id = el_strdup(f);
e->to_id = el_strdup(t);
e->relation = el_strdup(r && *r ? r : "associate");
e->metadata = el_strdup("{}");
e->from_id = el_strdup_persist(f);
e->to_id = el_strdup_persist(t);
e->relation = el_strdup_persist(r && *r ? r : "associate");
e->metadata = el_strdup_persist("{}");
e->weight = engram_decode_score(weight);
if (e->weight <= 0.0 || e->weight > 1.0) e->weight = 0.5;
e->confidence = 1.0;
@@ -7519,11 +7537,11 @@ el_val_t engram_save(el_val_t path) {
/* Helper: extract a string field from a JSON object substring. */
static char* eg_get_str_field(const char* obj, const char* key) {
const char* p = json_find_key(obj, key);
if (!p) return el_strdup("");
if (*p != '"') return el_strdup("");
if (!p) return el_strdup_persist("");
if (*p != '"') return el_strdup_persist("");
JsonParser jp = { .p = p, .end = p + strlen(p), .err = 0 };
char* out = jp_parse_string_raw(&jp);
if (jp.err) { free(out); return el_strdup(""); }
if (jp.err) { free(out); return el_strdup_persist(""); }
return out;
}
@@ -7597,7 +7615,7 @@ el_val_t engram_load(el_val_t path) {
nn->tier = eg_get_str_field(obj, "tier");
nn->tags = eg_get_str_field(obj, "tags");
nn->metadata = eg_get_str_field(obj, "metadata");
if (!nn->metadata || !*nn->metadata) { free(nn->metadata); nn->metadata = el_strdup("{}"); }
if (!nn->metadata || !*nn->metadata) { free(nn->metadata); nn->metadata = el_strdup_persist("{}"); }
nn->salience = eg_get_num_field(obj, "salience");
nn->importance = eg_get_num_field(obj, "importance");
nn->confidence = eg_get_num_field(obj, "confidence");
@@ -7648,7 +7666,7 @@ el_val_t engram_load(el_val_t path) {
ee->to_id = eg_get_str_field(obj, "to_id");
ee->relation = eg_get_str_field(obj, "relation");
ee->metadata = eg_get_str_field(obj, "metadata");
if (!ee->metadata || !*ee->metadata) { free(ee->metadata); ee->metadata = el_strdup("{}"); }
if (!ee->metadata || !*ee->metadata) { free(ee->metadata); ee->metadata = el_strdup_persist("{}"); }
ee->weight = eg_get_num_field(obj, "weight");
ee->confidence = eg_get_num_field(obj, "confidence");
ee->created_at = eg_get_int_field(obj, "created_at");
@@ -7740,7 +7758,7 @@ el_val_t engram_get_node_json(el_val_t id) {
if (!n) return el_wrap_str(el_strdup("{}"));
JsonBuf b; jb_init(&b);
engram_emit_node_json(&b, n);
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
el_val_t engram_search_json(el_val_t query, el_val_t limit) {
@@ -7768,7 +7786,7 @@ el_val_t engram_search_json(el_val_t query, el_val_t limit) {
}
}
jb_putc(&b, ']');
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
el_val_t engram_scan_nodes_json(el_val_t limit, el_val_t offset) {
@@ -7777,9 +7795,9 @@ el_val_t engram_scan_nodes_json(el_val_t limit, el_val_t offset) {
int64_t off = (int64_t)offset; if (off < 0) off = 0;
JsonBuf b; jb_init(&b);
jb_putc(&b, '[');
if (g->node_count == 0) { jb_putc(&b, ']'); return el_wrap_str(b.buf); }
if (g->node_count == 0) { jb_putc(&b, ']'); return el_wrap_str(jb_finish(&b)); }
int64_t* idx = malloc((size_t)g->node_count * sizeof(int64_t));
if (!idx) { jb_putc(&b, ']'); return el_wrap_str(b.buf); }
if (!idx) { jb_putc(&b, ']'); return el_wrap_str(jb_finish(&b)); }
/* Skip transparent layers — introspection filter, same as engram_scan_nodes. */
int64_t live = 0;
for (int64_t i = 0; i < g->node_count; i++) {
@@ -7797,7 +7815,7 @@ el_val_t engram_scan_nodes_json(el_val_t limit, el_val_t offset) {
}
free(idx);
jb_putc(&b, ']');
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
/* engram_scan_nodes_by_type_json — filter by node_type before paginating.
@@ -7813,9 +7831,9 @@ el_val_t engram_scan_nodes_by_type_json(el_val_t type_v, el_val_t limit, el_val_
int64_t off = (int64_t)offset; if (off < 0) off = 0;
JsonBuf b; jb_init(&b);
jb_putc(&b, '[');
if (g->node_count == 0) { jb_putc(&b, ']'); return el_wrap_str(b.buf); }
if (g->node_count == 0) { jb_putc(&b, ']'); return el_wrap_str(jb_finish(&b)); }
int64_t* idx = malloc((size_t)g->node_count * sizeof(int64_t));
if (!idx) { jb_putc(&b, ']'); return el_wrap_str(b.buf); }
if (!idx) { jb_putc(&b, ']'); return el_wrap_str(jb_finish(&b)); }
int64_t live = 0;
for (int64_t i = 0; i < g->node_count; i++) {
if (engram_layer_is_transparent(g->nodes[i].layer_id)) continue;
@@ -7834,7 +7852,7 @@ el_val_t engram_scan_nodes_by_type_json(el_val_t type_v, el_val_t limit, el_val_
}
free(idx);
jb_putc(&b, ']');
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
el_val_t engram_neighbors_json(el_val_t node_id, el_val_t max_depth, el_val_t direction) {
@@ -7849,7 +7867,7 @@ el_val_t engram_neighbors_json(el_val_t node_id, el_val_t max_depth, el_val_t di
int allow_in = (strcmp(dir, "in") == 0) || (strcmp(dir, "both") == 0);
JsonBuf b; jb_init(&b);
jb_putc(&b, '[');
if (!sid || !*sid) { jb_putc(&b, ']'); return el_wrap_str(b.buf); }
if (!sid || !*sid) { jb_putc(&b, ']'); return el_wrap_str(jb_finish(&b)); }
/* Frontier of (node_id, hops). Cap to a sane size. */
char** frontier = calloc(1024, sizeof(char*));
@@ -7859,7 +7877,7 @@ el_val_t engram_neighbors_json(el_val_t node_id, el_val_t max_depth, el_val_t di
int64_t vc = 0;
if (!frontier || !frontier_h || !visited) {
free(frontier); free(frontier_h); free(visited);
jb_putc(&b, ']'); return el_wrap_str(b.buf);
jb_putc(&b, ']'); return el_wrap_str(jb_finish(&b));
}
/* Use plain strdup (not el_strdup) so arena doesn't track these pointers.
* The BFS loop manually frees them below arena would double-free them. */
@@ -7902,7 +7920,7 @@ el_val_t engram_neighbors_json(el_val_t node_id, el_val_t max_depth, el_val_t di
for (int64_t i = 0; i < vc; i++) free(visited[i]);
free(frontier); free(frontier_h); free(visited);
jb_putc(&b, ']');
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
el_val_t engram_activate_json(el_val_t query, el_val_t depth) {
@@ -7943,7 +7961,7 @@ el_val_t engram_activate_json(el_val_t query, el_val_t depth) {
}
}
jb_putc(&b, ']');
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
el_val_t engram_stats_json(void) {
@@ -7963,7 +7981,7 @@ el_val_t engram_list_layers_json(void) {
jb_putc(&b, '[');
/* Build a sorted index over live layers. */
size_t* idx = malloc((g->layer_count + 1) * sizeof(size_t));
if (!idx) { jb_putc(&b, ']'); return el_wrap_str(b.buf); }
if (!idx) { jb_putc(&b, ']'); return el_wrap_str(jb_finish(&b)); }
size_t live = 0;
for (size_t i = 0; i < g->layer_count; i++) {
if (g->layers[i].name) idx[live++] = i;
@@ -8000,7 +8018,7 @@ el_val_t engram_list_layers_json(void) {
}
free(idx);
jb_putc(&b, ']');
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
/* engram_compile_layered_json — produce a prompt-ready context block split
@@ -8086,7 +8104,7 @@ el_val_t engram_compile_layered_json(el_val_t intent, el_val_t depth) {
free(b.buf);
return el_wrap_str(el_strdup(""));
}
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
/* engram_query_range — temporal range query.
@@ -8131,7 +8149,7 @@ el_val_t engram_query_range(el_val_t start_ms_v, el_val_t end_ms_v) {
}
jb_putc(&b, ']');
free(idx);
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
/* engram_load_merge — like engram_load but WITHOUT resetting the store.
@@ -8382,7 +8400,7 @@ el_val_t engram_wm_top_json(el_val_t n_v) {
}
free(idx);
jb_putc(&b, ']');
return el_wrap_str(b.buf);
return el_wrap_str(jb_finish(&b));
}
#ifdef HAVE_CURL
@@ -8778,13 +8796,13 @@ static int64_t dharma_find_or_create_relation_edge(const char* peer_base, int cr
engram_grow_nodes();
EngramNode* n = &g->nodes[g->node_count];
memset(n, 0, sizeof(*n));
n->id = el_strdup(self_id);
n->content = el_strdup(_el_cgi_dharma_id ? _el_cgi_dharma_id : "(self)");
n->node_type = el_strdup("DharmaSelf");
n->label = el_strdup("dharma:self");
n->tier = el_strdup("Working");
n->tags = el_strdup("dharma");
n->metadata = el_strdup("{}");
n->id = el_strdup_persist(self_id);
n->content = el_strdup_persist(_el_cgi_dharma_id ? _el_cgi_dharma_id : "(self)");
n->node_type = el_strdup_persist("DharmaSelf");
n->label = el_strdup_persist("dharma:self");
n->tier = el_strdup_persist("Working");
n->tags = el_strdup_persist("dharma");
n->metadata = el_strdup_persist("{}");
n->salience = 1.0; n->importance = 1.0; n->confidence = 1.0;
int64_t now = engram_now_ms();
n->created_at = now; n->updated_at = now; n->last_activated = now;
@@ -8795,13 +8813,13 @@ static int64_t dharma_find_or_create_relation_edge(const char* peer_base, int cr
engram_grow_nodes();
EngramNode* n = &g->nodes[g->node_count];
memset(n, 0, sizeof(*n));
n->id = el_strdup(peer_node);
n->content = el_strdup(peer_base);
n->node_type = el_strdup("DharmaPeer");
n->label = el_strdup(peer_node);
n->tier = el_strdup("Working");
n->tags = el_strdup("dharma");
n->metadata = el_strdup("{}");
n->id = el_strdup_persist(peer_node);
n->content = el_strdup_persist(peer_base);
n->node_type = el_strdup_persist("DharmaPeer");
n->label = el_strdup_persist(peer_node);
n->tier = el_strdup_persist("Working");
n->tags = el_strdup_persist("dharma");
n->metadata = el_strdup_persist("{}");
n->salience = 0.5; n->importance = 0.5; n->confidence = 1.0;
int64_t now = engram_now_ms();
n->created_at = now; n->updated_at = now; n->last_activated = now;
@@ -8813,10 +8831,10 @@ static int64_t dharma_find_or_create_relation_edge(const char* peer_base, int cr
EngramEdge* e = &g->edges[g->edge_count];
memset(e, 0, sizeof(*e));
e->id = engram_new_id();
e->from_id = el_strdup(self_id);
e->to_id = el_strdup(peer_node);
e->relation = el_strdup("dharma-relation");
e->metadata = el_strdup("{}");
e->from_id = el_strdup_persist(self_id);
e->to_id = el_strdup_persist(peer_node);
e->relation = el_strdup_persist("dharma-relation");
e->metadata = el_strdup_persist("{}");
e->weight = 0.0;
e->confidence = 1.0;
int64_t now = engram_now_ms();
@@ -9109,7 +9127,7 @@ static el_val_t llm_extract_text(el_val_t resp_val) {
free(obj);
p = end;
}
return el_wrap_str(out.buf);
return el_wrap_str(jb_finish(&out));
}
el_val_t llm_call(el_val_t model, el_val_t prompt) {