Merge pull request 'runtime: allocation accounting — deterministic signal for complexity gating' (#131) from feat/alloc-accounting into dev

lang/el-compiler/src/codegen.el

@@ -2766,6 +2766,9 @@ fn builtin_arity(name: String) -> Int {
     if str_eq(name, "__engram_scan_nodes_json") { return 2 }
     if str_eq(name, "__engram_edges_json") { return 2 }
     if str_eq(name, "__engram_pool_stats_json") { return 0 }
+    if str_eq(name, "__el_alloc_count") { return 0 }
+    if str_eq(name, "__el_alloc_bytes") { return 0 }
+    if str_eq(name, "__el_peak_rss") { return 0 }
     if str_eq(name, "__generate") { return 1 }
     // Filesystem
     if str_eq(name, "fs_read") { return 1 }
@@ -2866,6 +2869,9 @@ fn builtin_arity(name: String) -> Int {
     if str_eq(name, "engram_scan_nodes_json") { return 2 }
     if str_eq(name, "engram_edges_json") { return 2 }
     if str_eq(name, "engram_pool_stats_json") { return 0 }
+    if str_eq(name, "el_alloc_count") { return 0 }
+    if str_eq(name, "el_alloc_bytes") { return 0 }
+    if str_eq(name, "el_peak_rss") { return 0 }
     if str_eq(name, "engram_neighbors_json") { return 3 }
     if str_eq(name, "engram_activate_json") { return 2 }
     if str_eq(name, "engram_stats_json") { return 0 }

lang/runtime/el_runtime.c

@@ -155,21 +155,55 @@ el_val_t el_arena_pop(el_val_t mark) {
     return 0;
 }
 
+/* ── Allocation accounting ───────────────────────────────────────────────────
+ *
+ * Every string allocation in the runtime funnels through the four functions
+ * below, so counting here counts everything the language does.
+ *
+ * WHY THIS EXISTS: a growth-curve gate needs a signal that is DETERMINISTIC.
+ * Wall-clock needs statistics, warmup, and a quiet machine; it is noisy on
+ * shared CI and unusable as a hard build gate. Allocation COUNT has none of
+ * those problems — the same input allocates the same number of times on every
+ * machine, every run. Fit allocations against input size and a complexity
+ * regression becomes a build failure with zero flake.
+ *
+ * This is not hypothetical. elc's known defect is quadratic ALLOCATION VOLUME.
+ * The old shipped binary paid it in RSS (27 GB, OOM); the rebuilt one pays the
+ * same quadratic in malloc/free churn (42s on a 1.4 MB input). The allocation
+ * count was the invariant across both — RSS and wall-clock were just the two
+ * ways it surfaced. An `expect allocs O(n)` assertion on the compile path
+ * would have failed the build the day it was introduced.
+ *
+ * Peak RSS is exported too but is explicitly NOT the gating signal: it is
+ * perturbed by allocator behaviour, page cache, and the OS. Gate on counts,
+ * report RSS as context.
+ *
+ * Counters are plain unsigned longs, incremented on the allocating thread with
+ * no synchronisation: this is measurement, and a lock here would change the
+ * thing being measured. Under threads the count is approximate; for the
+ * single-threaded compile path it is exact.
+ * ──────────────────────────────────────────────────────────────────────────── */
+static unsigned long _el_alloc_count = 0;
+static unsigned long _el_alloc_bytes = 0;
+
 /* Persistent allocation — bypasses the arena (state_set, engram internals). */
 static char* el_strdup_persist(const char* s) {
-    if (!s) return strdup("");
+    if (!s) { _el_alloc_count++; _el_alloc_bytes += 1; return strdup(""); }
+    _el_alloc_count++; _el_alloc_bytes += strlen(s) + 1;
     return strdup(s);
 }
 static char* el_strbuf_persist(size_t n) {
     char* p = malloc(n + 1);
     if (!p) { fputs("el_runtime: out of memory\n", stderr); exit(1); }
     p[0] = '\0';
+    _el_alloc_count++; _el_alloc_bytes += n + 1;
     return p;
 }
 
 static char* el_strdup(const char* s) {
-    if (!s) { char* p = strdup(""); el_arena_track(p); return p; }
+    if (!s) { char* p = strdup(""); _el_alloc_count++; _el_alloc_bytes += 1; el_arena_track(p); return p; }
     char* p = strdup(s);
+    _el_alloc_count++; _el_alloc_bytes += strlen(s) + 1;
     el_arena_track(p);
     return p;
 }
@@ -178,6 +212,7 @@ static char* el_strbuf(size_t n) {
     char* p = malloc(n + 1);
     if (!p) { fputs("el_runtime: out of memory\n", stderr); exit(1); }
     p[0] = '\0';
+    _el_alloc_count++; _el_alloc_bytes += n + 1;
     el_arena_track(p);
     return p;
 }
@@ -18411,3 +18446,34 @@ el_val_t engram_pool_stats_json(void) {
         (unsigned)STORE_PAGE_SIZE);
     return el_wrap_str(el_strdup(b));
 }
+
+/* ── Allocation/RSS introspection (test-framework complexity gate, §6.5) ─────
+ *
+ * el_alloc_count() — total runtime string allocations since process start.
+ *   THE gating signal. Deterministic: same input => same count, every machine,
+ *   every run. A benchmark harness samples it before and after an operation at
+ *   several input sizes and fits the deltas against n; a curve worse than the
+ *   declared one fails the build. No warmup, no statistics, no baseline file,
+ *   no flake — none of which is true of wall-clock.
+ *
+ * el_alloc_bytes() — total bytes requested. Same determinism; catches the case
+ *   where allocation COUNT stays linear but per-allocation SIZE grows, which is
+ *   the classic accidental-quadratic shape (rebuilding a whole buffer per
+ *   append). Count alone would miss it.
+ *
+ * el_peak_rss() — peak resident set in bytes. Context, NOT a gate: perturbed by
+ *   allocator internals, the page cache, and the OS. Reported so a human can
+ *   see the physical consequence; never fitted.
+ */
+el_val_t el_alloc_count(void) { return (el_val_t)(int64_t)_el_alloc_count; }
+el_val_t el_alloc_bytes(void) { return (el_val_t)(int64_t)_el_alloc_bytes; }
+
+el_val_t el_peak_rss(void) {
+    struct rusage ru;
+    if (getrusage(RUSAGE_SELF, &ru) != 0) return (el_val_t)0;
+#if defined(__APPLE__) || defined(__MACH__)
+    return (el_val_t)(int64_t)ru.ru_maxrss;            /* macOS: bytes */
+#else
+    return (el_val_t)(int64_t)(ru.ru_maxrss * 1024L);  /* Linux: KB -> bytes */
+#endif
+}

lang/runtime/el_runtime.h

@@ -1017,6 +1017,12 @@ el_val_t  stdout_to_file(el_val_t path);
 el_val_t  stdout_restore(void);
 el_val_t  el_mem_check(void);
 
+/* Allocation accounting — the deterministic signal behind complexity gating.
+ * Gate on counts/bytes; peak RSS is context only. */
+el_val_t  el_alloc_count(void);
+el_val_t  el_alloc_bytes(void);
+el_val_t  el_peak_rss(void);
+
 /* Semantic retrieval surface. NOT interchangeable with engram_search_json,
  * which is lexical by design — see the note at the definition. */
 el_val_t  engram_recall_json(el_val_t query, el_val_t limit);

lang/runtime/el_seed.c

@@ -1379,6 +1379,13 @@ el_val_t __engram_edges_json(el_val_t limit, el_val_t offset) {
 el_val_t engram_pool_stats_json(void);
 el_val_t __engram_pool_stats_json(void) { return engram_pool_stats_json(); }
 
+el_val_t el_alloc_count(void);
+el_val_t el_alloc_bytes(void);
+el_val_t el_peak_rss(void);
+el_val_t __el_alloc_count(void) { return el_alloc_count(); }
+el_val_t __el_alloc_bytes(void) { return el_alloc_bytes(); }
+el_val_t __el_peak_rss(void)    { return el_peak_rss(); }
+
 el_val_t __engram_scan_nodes_by_type_json(el_val_t node_type, el_val_t limit, el_val_t offset) {
     return engram_scan_nodes_by_type_json(node_type, limit, offset);
 }