Merge pull request 'engram: reconcile #105's embed-cache/beam-BFS latency fixes onto current dev' (#115) from fix/engram-search-latency-reconciled into dev

lang/runtime/el_runtime.c

@@ -6847,10 +6847,16 @@ static float* eg_embed_fetch(const char* text, int32_t* out_dim) {
         else esc[w++] = (char)c;
     }
     esc[w] = '\0';
-    size_t blen = w + strlen(eg_embed_model()) + 64;
+    size_t blen = w + strlen(eg_embed_model()) + 96;
     char* body = malloc(blen);
     if (!body) { free(esc); return NULL; }
-    snprintf(body, blen, "{\"model\":\"%s\",\"prompt\":\"%s\"}",
+    /* keep_alive:-1 pins the embed model resident in Ollama indefinitely
+     * (2026-08-15, PR #105 port). Without it the tiny embed model is evicted
+     * whenever a larger generation model loads (unified-memory pressure), so
+     * the NEXT search pays a cold model reload — measured cold reload up to
+     * ~2.2s vs ~0.02-0.05s warm, well inside ENGRAM_EMBED_TIMEOUT_MS but a
+     * real tax on every activate() call that lands cold. Pinning removes it. */
+    snprintf(body, blen, "{\"model\":\"%s\",\"keep_alive\":-1,\"prompt\":\"%s\"}",
              eg_embed_model(), esc);
     free(esc);
     struct curl_slist* h = curl_slist_append(NULL, "Content-Type: application/json");
@@ -9508,6 +9514,36 @@ static inline double eg_cosq_at(EngramStore* g, double* cosq, unsigned char* cos
     return cosq[i];
 }
 
+/* ── Beam cap for engram_activate spreading activation (2026-08-15, PR #105
+ * port) ──────────────────────────────────────────────────────────────────
+ * #105 measured the OLD (pre-adjacency-index, pre-qgate, pre-fan-effect)
+ * BFS reaching multi-second/crash territory at depth 2-3 from unbounded
+ * hub-node fan-out. That specific failure mode is already substantially
+ * mitigated here by mechanisms #105's branch predates: the adjacency index
+ * (O(degree) not O(E) per hop), the query-aware qgate (prunes semantically
+ * irrelevant branches), the ACT-R fan-effect correction (dampens popular-
+ * hub over-connectivity), and the 0.02 firing threshold. A beam cap is still
+ * a genuine additional, orthogonal bound: it caps WORST-CASE per-hop
+ * expansion width regardless of how many targets happen to pass the soft
+ * gates above, so it is kept as defense in depth rather than dropped as
+ * redundant.
+ *
+ * Bounds the number of frontier nodes EXPANDED per hop-level (see the
+ * level-batching in the BFS below). Every reached node still gets its
+ * best_bg[]/reached[] recorded and appears in the returned/promoted set —
+ * the cap bounds only how far ASSOCIATIVE SPREAD continues past a level,
+ * never the direct seed matches or the reported result set. Tunable via
+ * ENGRAM_ACTIVATE_BEAM (default 128, matching #105); set very high (e.g.
+ * the node count) to recover the pre-cap unbounded-per-level behaviour. */
+static int64_t engram_activate_beam(void) {
+    static int64_t v = -1;
+    if (v >= 0) return v;
+    const char* s = getenv("ENGRAM_ACTIVATE_BEAM");
+    int64_t d = 128;
+    if (s && *s) { char* e = NULL; long t = strtol(s, &e, 10); if (e != s && t > 0) d = (int64_t)t; }
+    v = d; return v;
+}
+
 el_val_t engram_activate(el_val_t query, el_val_t depth) {
     EngramStore* g = engram_get();
     const char* q = EL_CSTR(query);
@@ -9552,25 +9588,43 @@ el_val_t engram_activate(el_val_t query, el_val_t depth) {
             backfilled++;
         }
     }
-    /* Query embedding, cached single-slot: the curiosity loop re-issues the
+    /* Query embedding cache (2026-08-15, PR #105 port: single-slot -> direct-
-     * same 4 rotating phrases, so consecutive identical queries skip the
+     * mapped multi-slot). The single-slot cache below this comment's history
-     * HTTP round-trip entirely. */
+     * only remembered the LAST query, so "the curiosity loop re-issues the
-    static char*   _eg_qcache_text = NULL;
+     * same 4 rotating phrases" only hit when two CONSECUTIVE calls used the
-    static float*  _eg_qcache_emb  = NULL;
+     * SAME phrase — any rotation among >1 phrase evicted the slot before it
-    static int32_t _eg_qcache_dim  = 0;
+     * could be reused. #105 measured this as a real cost (a repeated query
+     * costing a full Ollama round-trip whenever a different phrase intervened)
+     * and fixed it with a direct-mapped, FNV-1a-keyed cache sized for the
+     * rotation. Ported here on TOP of the existing cosq/e_eff semantic layer
+     * (this cache only ever supplies q_emb/q_dim into that unchanged
+     * pipeline) rather than replacing it — see the M8/#105 reconciliation
+     * note above eg_cosq_at. ENGRAM_QCACHE_SIZE must be a power of two (mask
+     * indexing below). Full strcmp on lookup rejects hash collisions; each
+     * slot owns its `text`/`vec` and is freed on eviction, matching the old
+     * single-slot free/replace contract — q_emb below still points at cache-
+     * owned memory the caller must NOT free, just as before. */
+#define ENGRAM_QCACHE_SIZE 1024
+    typedef struct { char* text; uint64_t hash; float* vec; int32_t dim; } EgQCacheEntry;
+    static EgQCacheEntry _eg_qcache[ENGRAM_QCACHE_SIZE];
     float*  q_emb = NULL;
     int32_t q_dim = 0;
-    if (_eg_qcache_text && strcmp(_eg_qcache_text, q) == 0) {
+    {
-        q_emb = _eg_qcache_emb; q_dim = _eg_qcache_dim;
+        uint64_t qh = engram_id_hash(q);
-    } else {
+        EgQCacheEntry* slot = &_eg_qcache[qh & (ENGRAM_QCACHE_SIZE - 1)];
-        int32_t d = 0;
+        if (slot->vec && slot->hash == qh && slot->text && strcmp(slot->text, q) == 0) {
-        float* v = eg_embed_fetch(q, &d);
+            q_emb = slot->vec; q_dim = slot->dim;
-        if (v) {
+        } else {
-            free(_eg_qcache_text); free(_eg_qcache_emb);
+            int32_t d = 0;
-            _eg_qcache_text = strdup(q);
+            float* v = eg_embed_fetch(q, &d);
-            _eg_qcache_emb  = v;
+            if (v) {
-            _eg_qcache_dim  = d;
+                free(slot->text); free(slot->vec);   /* evict prior occupant */
-            q_emb = v; q_dim = d;
+                slot->text = strdup(q);
+                slot->hash = qh;
+                slot->vec  = v;
+                slot->dim  = d;
+                q_emb = v; q_dim = d;
+            }
         }
     }
     /* ── Context centroid fold-in (2026-07-29) ──────────────────────────
@@ -9997,8 +10051,45 @@ el_val_t engram_activate(el_val_t query, el_val_t depth) {
     const double FAN_DREF = (g->adj_connected > 0)
         ? (2.0 * (double)g->edge_count / (double)g->adj_connected) : 0.0;
     _eg_act_fan_dref = FAN_DREF;
+    const int64_t activate_beam = engram_activate_beam();
     while (fhead < ftail) {
-        Frontier f = fr[fhead++];
+      /* Level-batch (2026-08-15, PR #105 port): entries sharing .hops are
+       * always contiguous — hop k+1 entries are appended only while
+       * processing hop k, strictly after the current ftail, so they form one
+       * block right after hop k's block (see engram_activate_beam's comment
+       * for why this holds even with the improve-and-re-enqueue behavior
+       * below). Find this level's extent, then beam-select which of it
+       * EXPANDS; every entry in the level still gets recorded via
+       * reached[]/best_bg[] regardless (that happened when it was enqueued,
+       * one level up) — the cap bounds propagation width only. */
+      int64_t level_hops  = fr[fhead].hops;
+      int64_t level_start = fhead;
+      int64_t level_end   = fhead;
+      while (level_end < ftail && fr[level_end].hops == level_hops) level_end++;
+      int64_t level_n = level_end - level_start;
+      unsigned char* expand = NULL;
+      if (level_n > activate_beam) {
+          expand = calloc((size_t)level_n, 1);
+          if (expand) {
+              /* Partial selection: mark the top-`activate_beam` entries by
+               * .act. O(beam*level_n) — beam is the small tunable. */
+              for (int64_t bsel = 0; bsel < activate_beam; bsel++) {
+                  int64_t best = -1;
+                  for (int64_t k = 0; k < level_n; k++) {
+                      if (expand[k]) continue;
+                      if (best < 0 || fr[level_start+k].act > fr[level_start+best].act)
+                          best = k;
+                  }
+                  if (best < 0) break;
+                  expand[best] = 1;
+              }
+          }
+          /* OOM on the selection map: expand stays NULL -> this level runs
+           * unbounded, same as if beam were disabled. Never silently wrong. */
+      }
+      for (int64_t lk = level_start; lk < level_end; lk++) {
+        if (expand && !expand[lk - level_start]) continue;
+        Frontier f = fr[lk];
         if (f.hops >= max_depth) continue;
         int64_t cur = f.idx;
         int64_t new_hops = f.hops + 1;
@@ -10130,6 +10221,9 @@ el_val_t engram_activate(el_val_t query, el_val_t depth) {
                 }
             }
         }
+      }
+      free(expand);
+      fhead = level_end;
     }
     /* Persist layer-1 background_activation to node store. */
     for (int64_t i = 0; i < g->node_count; i++) {