Merge pull request 'store: extend the write barrier to edges — kills the full-store walk' (#128) from fix/elc-rebuildable-compiler-builtins into dev

lang/el-compiler/src/codegen.el

@@ -2765,6 +2765,7 @@ fn builtin_arity(name: String) -> Int {
     if str_eq(name, "__engram_connect_in") { return 5 }
     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, "__generate") { return 1 }
     // Filesystem
     if str_eq(name, "fs_read") { return 1 }
@@ -2864,6 +2865,7 @@ fn builtin_arity(name: String) -> Int {
     if str_eq(name, "engram_search_json") { return 2 }
     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, "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

@@ -18373,3 +18373,41 @@ el_val_t engram_edges_json(el_val_t limit, el_val_t offset) {
     jb_putc(&b, ']');
     return el_wrap_str(b.buf);
 }
+
+/* engram_pool_stats_json() — the buffer pool's interoception, exposed.
+ *
+ * StorePoolStats and store_pool_stats() already existed and were surfaced
+ * NOWHERE. On 2026-08-15 the engram thrashed itself to a standstill twice while
+ * these exact counters sat in memory, unread, and four wrong theories were tried
+ * from the outside instead. Sensing state is only corrective if the state can be
+ * read — by the process itself (pc_adapt_budget) and by anything watching it.
+ *
+ * Serves the live numbers plus the derived signals that actually diagnose:
+ *   hit_rate    — sustained low hit rate with high evictions is the thrash shape
+ *   evict_ratio — evictions per access; ~1 means every fetch displaces a live page
+ *   pressure    — 1 when evicting into genuine reuse (working set > budget)
+ *   cap_gib/resident_gib — budget vs what is actually held
+ */
+el_val_t engram_pool_stats_json(void) {
+    if (!g_engram_store) return el_wrap_str(el_strdup("{\"store\":false}"));
+    StorePoolStats st;
+    store_pool_stats(g_engram_store, &st);
+    uint64_t acc = st.hits + st.misses;
+    double hit_rate    = acc ? (double)st.hits / (double)acc : 0.0;
+    double evict_ratio = acc ? (double)st.evictions / (double)acc : 0.0;
+    int pressure = (acc > 100000 && evict_ratio > 0.33 && hit_rate > 0.25) ? 1 : 0;
+    char b[768];
+    snprintf(b, sizeof b,
+        "{\"store\":true,\"cap_frames\":%zu,\"resident_frames\":%zu,\"pinned\":%zu,"
+        "\"dirty\":%zu,\"prefetch\":%u,\"hits\":%llu,\"misses\":%llu,\"evictions\":%llu,"
+        "\"prefetch_reads\":%llu,\"hit_rate\":%.4f,\"evict_ratio\":%.4f,\"pressure\":%d,"
+        "\"cap_gib\":%.3f,\"resident_gib\":%.3f,\"page_size\":%u}",
+        st.cap, st.resident, st.pinned, st.dirty, st.prefetch,
+        (unsigned long long)st.hits, (unsigned long long)st.misses,
+        (unsigned long long)st.evictions, (unsigned long long)st.prefetch_reads,
+        hit_rate, evict_ratio, pressure,
+        (double)st.cap      * (double)STORE_PAGE_SIZE / (1024.0*1024.0*1024.0),
+        (double)st.resident * (double)STORE_PAGE_SIZE / (1024.0*1024.0*1024.0),
+        (unsigned)STORE_PAGE_SIZE);
+    return el_wrap_str(el_strdup(b));
+}

lang/runtime/el_runtime.h

@@ -1025,6 +1025,9 @@ el_val_t  engram_recall_json(el_val_t query, el_val_t limit);
  * whole-graph round trip that /api/graph/edges used to do. */
 el_val_t  engram_edges_json(el_val_t limit, el_val_t offset);
 
+/* Buffer-pool interoception as JSON — live pool health for observation. */
+el_val_t  engram_pool_stats_json(void);
+
 /* CGI identity accessors (read-only). */
 el_val_t  cgi_principal(void);
 el_val_t  cgi_network(void);

lang/runtime/el_seed.c

@@ -1376,6 +1376,9 @@ el_val_t __engram_edges_json(el_val_t limit, el_val_t offset) {
     return engram_edges_json(limit, 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 __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);
 }

lang/runtime/engram_store.c

@@ -44,6 +44,9 @@
 #include <string.h>
 #include <stdint.h>
 #include <unistd.h>
+#if defined(__APPLE__) || defined(__MACH__)
+#include <sys/sysctl.h>
+#endif
 #include <fcntl.h>
 #include <errno.h>
 #include <time.h>
@@ -236,8 +239,15 @@ struct PgCache {
     unsigned prefetch;           /* read-ahead window (pages); 0 = off */
     LayerPin* lp; size_t lp_n, lp_cap;   /* hot-layer pin bookkeeping */
     size_t   dirty_count;        /* # dirty frames, maintained incrementally (M5) */
-    /* stats (introspection only — never affect semantics) */
+    /* Interoception. These were "introspection only — never affect semantics",
+     * and that was the bug: the pool could not feel itself thrash, so it could
+     * not correct, and neither could anyone watching from outside. The sensed
+     * state IS the corrective mechanism (see pc_adapt_budget) — the same way the
+     * engram's own boundary-beat/chronoception let it feel its own activity. */
     uint64_t hits, misses, evictions, prefetch_reads;
+    /* sliding-window marks so pressure reflects NOW, not lifetime totals */
+    uint64_t adapt_last_acc, adapt_last_evic, adapt_last_hits;
+    uint64_t adapt_grows;        /* how many times the budget corrected upward */
 };
 
 /* ── little-endian scalar codecs ──────────────────────────────────────────── */
@@ -334,6 +344,51 @@ static uint64_t dh_node_hash(const StoreNode* n){
     return h;
 }
 
+/* dh_edge_hash — the edge counterpart of dh_node_hash.
+ *
+ * WHY THIS EXISTS (2026-08-15): the write barrier was node-only. Checkpointing
+ * pushes the WHOLE resident graph through store_put_node/store_put_edge (see
+ * engram_store_checkpoint), and nodes were cheaply skipped when unchanged —
+ * a hash compare, no page I/O. Edges had no such check, so every edge was
+ * rewritten on every checkpoint, and each rewrite runs the idempotency probe
+ * max_page_lsn_for_id → btree lookup → page_read per stored copy.
+ *
+ * Edges outnumber nodes roughly 3:1 here (37,663 vs 13,430), so this turned
+ * routine checkpointing into a FULL-STORE WALK in id order — random page access
+ * across the entire 2 GiB store, repeated, mostly to rediscover that nothing
+ * had changed. That walk is the failure mode: with a page cache smaller than
+ * the store it degenerates into thrashing and the engram never makes progress.
+ * Sizing the cache around that walk treats the symptom; the walk itself should
+ * not happen.
+ *
+ * The discriminator byte keeps the edge keyspace from ever colliding with a
+ * node of the same id in the shared dh map: distinct kinds cannot produce the
+ * same hash, so a stale skip is not reachable by collision. */
+static uint64_t dh_edge_hash(const StoreEdge* e){
+    uint64_t h = 1469598103934665603ULL;
+    const uint8_t kind = 0xE0;           /* edge discriminator */
+    dh_fold_bytes(&h, &kind, 1);
+    dh_fold_str(&h, e->id);
+    dh_fold_str(&h, e->from_id);
+    dh_fold_str(&h, e->to_id);
+    dh_fold_str(&h, e->relation);
+    dh_fold_str(&h, e->metadata);
+    uint8_t t8[8];
+    put_f64(t8, e->weight);     dh_fold_bytes(&h, t8, 8);
+    put_f64(t8, e->hebb);       dh_fold_bytes(&h, t8, 8);
+    put_f64(t8, e->confidence); dh_fold_bytes(&h, t8, 8);
+    uint8_t t4[4];
+    put_u32(t4, (uint32_t)e->inhibitory); dh_fold_bytes(&h, t4, 4);
+    put_u32(t4, e->layer_id);             dh_fold_bytes(&h, t4, 4);
+    /* created_at/updated_at/last_fired are deliberately EXCLUDED: last_fired is
+     * touched by activation without changing what the edge IS, and including it
+     * would defeat the barrier on exactly the hot edges it most needs to skip.
+     * The fields that define the edge's durable content are all folded above. */
+    if (e->unknown && e->unknown_len) dh_fold_bytes(&h, e->unknown, e->unknown_len);
+    if (h == 0) h = 1;   /* reserve 0 as "absent" in the map */
+    return h;
+}
+
 /* Open-addressing id(string)→durable-hash map. Keyed for O(1) bucketing on the
  * id's FNV hash, compared by strcmp for correctness (full-id discipline, matching
  * store_scan_*'s StrSet). Values are the 64-bit durable hash. */
@@ -1531,6 +1586,11 @@ int store_scan_edges(EngramPagedStore* s, StoreEdgeScanCb cb, void* ctx){
             if (cand.id && *cand.id && strset_add(&seen, cand.id)){
                 StoreEdge canon;
                 if (store_get_edge(s, cand.id, &canon) == 1){
+                    /* seed the write-barrier map from on-disk truth so the FIRST
+                     * post-boot checkpoint full-walk already skips unchanged edges
+                     * (mirrors store_scan_nodes; without it the barrier is empty at
+                     * boot and the first checkpoint re-probes every edge) */
+                    if (s->barrier_on) dh_set(s->dh, canon.id, dh_edge_hash(&canon));
                     cb(&canon, ctx); count++;               /* canonical latest-live */
                     store_edge_free(&canon);
                 }
@@ -1594,19 +1654,71 @@ int store_scan_edges(EngramPagedStore* s, StoreEdgeScanCb cb, void* ctx){
  *  matches disk, so a re-fault reproduces identical bytes.
  * ════════════════════════════════════════════════════════════════════════════ */
 
-/* default frame budget: large enough that today's whole store stays resident
- * (== Phase 1). Override with env ENGRAM_POOL_FRAMES (0 = unlimited). */
-#ifndef ENGRAM_POOL_FRAMES_DEFAULT
-#define ENGRAM_POOL_FRAMES_DEFAULT (1u<<20)   /* ~1M frames × 16KiB = 16 GiB */
+/* ── Frame budget ────────────────────────────────────────────────────────────
+ *
+ * A FIXED frame count cannot be correct. It has no relationship to either
+ * quantity that decides whether a cache works: the size of the working set, or
+ * the memory actually available on the host. It is the same number on a 16 GB
+ * laptop and a 256 GB server, and it stays put while the store grows.
+ *
+ * That is not hypothetical. On 2026-08-15 the deployment pinned
+ * ENGRAM_POOL_FRAMES=65536 (1 GiB) while neuron.egm grew to 2.1 GiB. The
+ * working set was twice the budget, so boot-time WAL replay — which walks
+ * pages in an order uncorrelated with reuse — evicted each page shortly before
+ * it was needed again. The engram spun at 100% CPU inside pc_evict_to_budget
+ * and never bound its port. Not slow: making no progress. Denning's thrashing,
+ * exactly, and no eviction policy can fix it — when the working set does not
+ * fit, only more frames or admission control help.
+ *
+ * So the budget is DERIVED, from the host's physical memory, and it scales
+ * with the machine instead of pretending memory is a constant.
+ *
+ *   ENGRAM_POOL_FRAMES   explicit frame count; 0 = unlimited. Overrides all.
+ *                        Prefer leaving it unset — a hand-set number is how
+ *                        this failure happened.
+ *   ENGRAM_POOL_MEM_PCT  percent of physical RAM to budget (default 60).
+ *
+ * Fallback when RAM cannot be read is 16 GiB worth of frames — the old
+ * default, retained only as a floor for that case.
+ * ──────────────────────────────────────────────────────────────────────────── */
+#ifndef ENGRAM_POOL_FRAMES_FALLBACK
+#define ENGRAM_POOL_FRAMES_FALLBACK (1u<<20)   /* ~1M frames × 16KiB = 16 GiB */
 #endif
 
+/* Physical RAM in bytes, 0 when it cannot be determined. */
+static uint64_t pc_physical_ram(void){
+#if defined(__APPLE__) || defined(__MACH__)
+    uint64_t v = 0; size_t len = sizeof v;
+    int mib[2] = { CTL_HW, HW_MEMSIZE };
+    if (sysctl(mib, 2, &v, &len, NULL, 0) == 0) return v;
+    return 0;
+#else
+    long pages = sysconf(_SC_PHYS_PAGES);
+    long psz   = sysconf(_SC_PAGESIZE);
+    if (pages > 0 && psz > 0) return (uint64_t)pages * (uint64_t)psz;
+    return 0;
+#endif
+}
+
+static size_t pc_default_cap(void){
+    unsigned pct = 60;
+    const char* p = getenv("ENGRAM_POOL_MEM_PCT");
+    if (p && *p){ unsigned long v = strtoul(p, NULL, 10); if (v > 0 && v <= 95) pct = (unsigned)v; }
+    uint64_t ram = pc_physical_ram();
+    if (!ram) return ENGRAM_POOL_FRAMES_FALLBACK;
+    uint64_t budget_bytes = (ram / 100u) * pct;
+    uint64_t frames = budget_bytes / (uint64_t)STORE_PAGE_SIZE;
+    if (frames < 4096) frames = 4096;            /* never absurdly small */
+    return (size_t)frames;
+}
+
 static PgCache* pc_new(void){
     PgCache* c = (PgCache*)calloc(1, sizeof *c);
     if (!c) return NULL;
     c->nbuckets = 1024;
     c->buckets = (PgEnt**)calloc(c->nbuckets, sizeof(PgEnt*));
     if (!c->buckets){ free(c); return NULL; }
-    c->cap = ENGRAM_POOL_FRAMES_DEFAULT;
+    c->cap = pc_default_cap();
     c->prefetch = 8;
     const char* pf = getenv("ENGRAM_POOL_FRAMES");
     if (pf && *pf){ char* end=NULL; unsigned long long v = strtoull(pf,&end,10); c->cap = (size_t)v; }
@@ -1676,6 +1788,115 @@ static void pc_remove(PgCache* c, PgEnt* e){
 /* Reclaim clean unpinned frames from the LRU end until under budget, or until no
  * evictable frame remains (a dirty/pinned-heavy pool may transiently exceed cap —
  * that is the no-steal guarantee, not a bug: the next checkpoint frees them). */
+/* ── Adaptive budget: close the loop ─────────────────────────────────────────
+ *
+ * THE LESSON THIS ENCODES (2026-08-15). The engram spent hours down while four
+ * separate theories were tried — bad binary, corrupt snapshot, WAL replay,
+ * feature flags — because nothing in the system said what was happening. It
+ * looked identical to "busy loading": 100% CPU, flat RSS, no output. Meanwhile
+ * hits/misses/evictions were ALREADY being counted, right here, and surfaced
+ * nowhere. One eviction-rate number would have ended it in seconds.
+ *
+ * So the counters are not decoration. They are the control signal.
+ *
+ * A budget chosen once — a literal like 65536, or 60% of RAM read at startup —
+ * is a guess about the future. It cannot know the store grew, the working set
+ * shifted, or another process took the memory. The cache already MEASURES the
+ * only thing that matters (am I evicting pages I am about to want again), so it
+ * should act on that measurement instead of on a number someone typed.
+ *
+ * The controller: over a sliding window, if evictions are running at a rate
+ * comparable to accesses AND there is genuine reuse (hits are material), the
+ * working set exceeds the budget — grow it. Growth is geometric, bounded by a
+ * live re-read of physical memory rather than a value cached at boot, so it
+ * tracks the machine instead of a snapshot of it. It never shrinks on its own:
+ * cap is a ceiling, not an allocation, and frames are only ever held because a
+ * real access put them there.
+ *
+ * Two things this deliberately does NOT do: it does not attempt a cleverer
+ * eviction policy (when the working set does not fit, no policy helps — that is
+ * Denning, and it is why "tune the LRU" was never the fix), and it does not stay
+ * silent (pool_report exposes the same numbers outward, so a human or a metric
+ * pipeline sees the pressure the controller is reacting to). */
+
+/* El's native telemetry, already in the runtime and already exporting to OTLP.
+ * Declared weak so engram_store.c still links standalone; when the runtime is
+ * present (every real build) the pool's interoception flows into the SAME
+ * pipeline as every other metric.
+ *
+ * ONE emission carrying the whole sensed state — not a function per stat, and
+ * not a bespoke per-subsystem endpoint. Both of those are the degenerate case:
+ * they make observability something you hand-write per noun instead of a
+ * uniform mechanism every component already has. el_val_t is int64_t; strings
+ * ride as pointers cast through it (see el_runtime.h's value model). */
+__attribute__((weak)) int64_t emit_log(int64_t level, int64_t msg, int64_t fields_json);
+
+static void pc_report(const PgCache* c, const char* cause){
+    if (!emit_log) return;                    /* runtime not linked: no-op */
+    uint64_t acc = c->hits + c->misses;
+    char f[512];
+    snprintf(f, sizeof f,
+        "{\"component\":\"engram.pool\",\"cause\":\"%s\",\"hits\":%llu,\"misses\":%llu,"
+        "\"evictions\":%llu,\"prefetch_reads\":%llu,\"cap_frames\":%zu,\"resident\":%zu,"
+        "\"dirty\":%zu,\"grows\":%llu,\"hit_rate\":%.4f,\"evict_ratio\":%.4f,"
+        "\"cap_gib\":%.3f,\"resident_gib\":%.3f}",
+        cause,
+        (unsigned long long)c->hits, (unsigned long long)c->misses,
+        (unsigned long long)c->evictions, (unsigned long long)c->prefetch_reads,
+        c->cap, c->count, c->dirty_count, (unsigned long long)c->adapt_grows,
+        acc ? (double)c->hits / (double)acc : 0.0,
+        acc ? (double)c->evictions / (double)acc : 0.0,
+        (double)c->cap   * (double)STORE_PAGE_SIZE / (1024.0*1024.0*1024.0),
+        (double)c->count * (double)STORE_PAGE_SIZE / (1024.0*1024.0*1024.0));
+    emit_log((int64_t)(uintptr_t)"warn", (int64_t)(uintptr_t)"engram.pool pressure",
+             (int64_t)(uintptr_t)f);
+}
+
+static uint64_t pc_ram_bytes_live(void){ return pc_physical_ram(); }
+
+static void pc_adapt_budget(PgCache* c){
+    if (!c->cap) return;                     /* unlimited: nothing to adapt */
+    if (getenv("ENGRAM_POOL_FRAMES")) return; /* explicit operator override wins */
+
+    /* Sliding window so the signal reflects NOW, not lifetime totals. */
+    uint64_t acc = c->hits + c->misses;
+    if (acc - c->adapt_last_acc < 100000) return;
+    uint64_t d_acc  = acc - c->adapt_last_acc;
+    uint64_t d_evic = c->evictions - c->adapt_last_evic;
+    uint64_t d_hits = c->hits - c->adapt_last_hits;
+    c->adapt_last_acc = acc; c->adapt_last_evic = c->evictions; c->adapt_last_hits = c->hits;
+
+    /* Pressure = evicting on a large fraction of accesses while still getting
+     * real reuse. Evictions alone are normal (a scan evicts and never returns);
+     * evictions WITH reuse means the working set genuinely does not fit. */
+    if (d_evic * 3 < d_acc) return;          /* < 1/3 of accesses evict: healthy */
+    if (d_hits * 4 < d_acc) return;          /* little reuse: a scan, not pressure */
+
+    uint64_t ram = pc_ram_bytes_live();       /* live, not a boot-time constant */
+    if (!ram) return;
+    unsigned pct = 80;                        /* hard ceiling for autonomous growth */
+    const char* mp = getenv("ENGRAM_POOL_MAX_PCT");
+    if (mp && *mp){ unsigned long v = strtoul(mp, NULL, 10); if (v > 0 && v <= 95) pct = (unsigned)v; }
+    size_t ceiling = (size_t)(((ram / 100u) * pct) / (uint64_t)STORE_PAGE_SIZE);
+    if (c->cap >= ceiling) return;            /* already at the machine's limit */
+
+    size_t want = c->cap + (c->cap / 2) + 1;  /* ×1.5, geometric */
+    if (want > ceiling) want = ceiling;
+    size_t was = c->cap;
+    c->cap = want;
+    c->adapt_grows++;
+    /* Emit the sensed state, not just the reaction. These are the numbers that
+     * would have diagnosed 2026-08-15 in seconds instead of hours. */
+    pc_report(c, "budget-grow");
+    fprintf(stderr,
+        "[engram] pool pressure: %llu evictions / %llu accesses (%llu hits) at %zu frames "
+        "(%.2f GiB) — working set exceeds budget; growing to %zu frames (%.2f GiB).\n",
+        (unsigned long long)d_evic, (unsigned long long)d_acc, (unsigned long long)d_hits,
+        was,  (double)was  * (double)STORE_PAGE_SIZE / (1024.0*1024.0*1024.0),
+        c->cap,(double)c->cap * (double)STORE_PAGE_SIZE / (1024.0*1024.0*1024.0));
+    fflush(stderr);
+}
+
 static void pc_evict_to_budget(PgCache* c){
     if (!c->cap) return;                    /* unlimited */
     while (c->count > c->cap){
@@ -1687,6 +1908,7 @@ static void pc_evict_to_budget(PgCache* c){
         }
         if (!freed) break;                  /* nothing evictable — allowed to exceed cap */
     }
+    pc_adapt_budget(c);
 }
 
 static PgEnt* pc_get(EngramPagedStore* s, uint64_t id){
@@ -2377,6 +2599,18 @@ int store_put_node(EngramPagedStore* s, const StoreNode* n){
 int store_put_edge(EngramPagedStore* s, const StoreEdge* e){
     if (!s || !e || !e->id || !e->from_id || !e->to_id) return -1;
     STORE_GUARD(s);
+    /* Durable-hash write barrier — mirrors store_put_node. An unchanged edge
+     * costs one hash compare and zero page I/O; without this, checkpointing
+     * re-probed every edge against the paged store (max_page_lsn_for_id →
+     * page_read), turning a routine checkpoint into a full-store walk. */
+    uint64_t dh_h = 0;
+    if (s->barrier_on){
+        dh_h = dh_edge_hash(e);
+        if (dh_get(s->dh, e->id) == dh_h){
+            s->stat_barrier_skips++;
+            return 0;
+        }
+    }
     uint64_t L = ++s->next_lsn;
     if (s->wal){
         size_t blen; uint8_t* body = edge_serialize(e, &blen);
@@ -2386,6 +2620,10 @@ int store_put_edge(EngramPagedStore* s, const StoreEdge* e){
         if (wr != 0) return -1;
     }
     int r = apply_edge_put(s, e, L);
+    if (r == 0 && s->barrier_on){
+        if (!dh_h) dh_h = dh_edge_hash(e);
+        dh_set(s->dh, e->id, dh_h);   /* remember the now-persisted durable hash */
+    }
     ckpt_maybe(s);
     return r;
 }