runtime: ground the node asked about, and refuse circular support

engram_ground_json resolved each seed to a REGION, wrote the grounded-by
edge between the two regions' HUBS, and then echoed those hubs back in the
"claim"/"evidence" fields as if they were the caller's input:

    const char* cid = C->hub_id ? C->hub_id : EL_CSTR(claim);
    const char* eid = E->hub_id ? E->hub_id : EL_CSTR(evidence);
    cog_ground_edge(g_engram_store, cid, eid, grounding, fw);

Three consequences, all measured against a clone of the live store:

1. The edge landed on a node the caller never named. Grounding 3b9ced5d
   against 6edf8c79 wrote an edge on the hubs of their regions instead.
2. When both seeds resolve into the same region the support is circular
   and scores near 1.0 for structural reasons, not evidential ones. Four
   probe nodes written together landed in one region, and every grounding
   among them returned 0.93-0.99 as if it were evidence. Two independent
   agents hit this and reported 0.885 / 0.909 self-groundings as confident.
3. The echo concealed both: the response was indistinguishable from a
   successful grounding of the ids that were passed in.

The region is HOW a claim is evaluated; it is not WHAT the claim is about.
So the edge now attaches to the requested ids, and the resolved hubs are
reported separately as claim_region / evidence_region.

Degeneracy is broader than hub == hub. Three circular shapes, all
previously invisible:
    same-region                both seeds resolve to one region
    claim-region-is-evidence   the evidence IS the hub of the claim's own
                               neighbourhood — measured at 0.98883
    evidence-region-is-claim   the mirror case
Each sets grounding to 0 and writes no edge. Circular support is not
support, and a grounding that is degenerate by construction must not
enter the graph as though it were evidence.

Verified:
  6edf8c79 -> 6edf8c79   degenerate=same-region   g=0        written=false
  6edf8c79 -> d0406dfd   degenerate=same-region   g=0        written=false
  ebc1413e -> 64cc96ef   degenerate=false         g=0.774563 written=true
  64cc96ef -> ebc1413e   degenerate=false         g=0.802896 written=true
Legitimate grounding across distinct regions is unchanged and still
writes; only circular support is refused.

This is the same class as #142 and #146 — a value that looked like an
answer with nothing behind it — except here it was also writing that
non-answer into the canonical store.

lang/runtime/el_runtime.c

@@ -13937,7 +13937,40 @@ static int eg_cog_is_keystone_seeds(const char* csv) {
 el_val_t engram_think_json(el_val_t seeds, el_val_t faculty) {
     GeoDescriptor* g = eg_geo_build_desc(EL_CSTR(seeds));
     if (!g) return eg_geo_err("geometry unavailable");
-    CogStance st; cog_stance_init(&st, NULL, EL_CSTR(faculty), g->hub_id, NULL, g);
+    /* RESUME THE LEARNED STANCE (2026-08-16 self-review). This built a NEUTRAL
+     * stance every call — all axis_gain 1.0, bias_dir NULL, reliability 0.5 —
+     * and never loaded the one the correspondence-beat had been persisting.
+     *
+     * That mattered because the faculty enters engram_think ONLY through the
+     * stance: `gain = stance->axis_gain[k]` warps the per-axis extents, and
+     * `stance->bias_dir` seeds the steering direction. cog_stance_init stores
+     * the faculty NAME but nothing reads it. So with a neutral stance,
+     * reason / abduce / induce / plan / analogize are the same function with
+     * different labels — measured, byte-identical output across all five —
+     * and `confidence` is pinned to the 0.5 uninformed prior, because
+     * GeoGradient.confidence is just stance->reliability.
+     *
+     * The machinery already existed and only this call site ignored it:
+     * engram_correspondence_beat_json resumes via cog_stance_from_node and
+     * persists via cog_stance_to_node under the id "stance-<faculty>-<hub>".
+     * Every beat's calibration was being written and then thrown away on the
+     * next read. Same defect as the NULL anchor directly above: a neutral
+     * argument collapsing a capability to a constant.
+     *
+     * Resume the same id the beat writes, so learning compounds across beats
+     * and cold boot. Fall back to neutral only when no stance exists yet —
+     * which is a genuine uninformed prior, not a discarded informed one. */
+    char sid[256];
+    snprintf(sid, sizeof sid, "stance-%s-%s",
+             EL_CSTR(faculty) ? EL_CSTR(faculty) : "reason",
+             g->hub_id ? g->hub_id : "region");
+    CogStance st; StoreNode prev; int resumed = 0;
+    if (g_engram_store && store_get_node(g_engram_store, sid, &prev) == 1) {
+        if (cog_stance_from_node(&prev, &st) == 0) resumed = 1;
+        store_node_free(&prev);
+    }
+    if (!resumed) cog_stance_init(&st, sid, EL_CSTR(faculty), g->hub_id, NULL, g);
+    else { free(st.id); st.id = strdup(sid); }
     GeoGradient grad;
 
     /* ANCHOR THE READ (2026-08-16 self-review). This passed NULL, and NULL is
@@ -13999,8 +14032,13 @@ el_val_t engram_think_json(el_val_t seeds, el_val_t faculty) {
     if (engram_think(g, anchor, &st, &grad) != 0) { free(anchor); cog_stance_free(&st); engram_geo_free(g); return eg_geo_err("think failed"); }
     free(anchor);
     JsonBuf b; jb_init(&b); char t[256];
-    snprintf(t, sizeof t, "{\"faculty\":\"%s\",\"n_support\":%d,\"magnitude\":%.6g,\"spread\":%.6g,\"confidence\":%.6g,\"dim\":%d",
-             EL_CSTR(faculty), grad.n_support, grad.magnitude, grad.spread, grad.confidence, grad.dim);
+    /* stance_resumed distinguishes an INFORMED read from an uninformed one.
+     * Without it, confidence 0.5 from a learned-but-unreliable stance and
+     * confidence 0.5 from "no stance exists" are indistinguishable — the same
+     * reporting gap that let the NULL anchor and the neutral stance hide. */
+    snprintf(t, sizeof t, "{\"faculty\":\"%s\",\"n_support\":%d,\"magnitude\":%.6g,\"spread\":%.6g,\"confidence\":%.6g,\"stance_resumed\":%s,\"dim\":%d",
+             EL_CSTR(faculty), grad.n_support, grad.magnitude, grad.spread, grad.confidence,
+             resumed ? "true" : "false", grad.dim);
     jb_puts(&b, t);
     int emit = grad.dim < 8 ? grad.dim : 8;
     jb_puts(&b, ",\"direction\":"); eg_geo_emit_vec(&b, grad.direction, emit);
@@ -14024,12 +14062,57 @@ el_val_t engram_ground_json(el_val_t claim, el_val_t evidence, el_val_t for_whom
     double grounding = (rc == 0) ? gr.grounding : 0.0;
     if (rc == 0) engram_verify_grounding_free(&gr);
     const char* fw = EL_CSTR(for_whom); if (fw && !*fw) fw = NULL;
-    const char* cid = C->hub_id ? C->hub_id : EL_CSTR(claim);
-    const char* eid = E->hub_id ? E->hub_id : EL_CSTR(evidence);
-    int wr = cog_ground_edge(g_engram_store, cid, eid, grounding, fw);
-    JsonBuf b; jb_init(&b); char t[256];
-    snprintf(t, sizeof t, "{\"relation\":\"grounded-by\",\"claim\":\"%s\",\"evidence\":\"%s\",\"for_whom\":\"%s\",\"grounding\":%.6g,\"written\":%s}",
-             cid, eid, fw ? fw : "-", grounding, wr == 0 ? "true" : "false");
+
+    /* GROUND THE NODE ASKED ABOUT, AND SAY WHAT WAS RESOLVED (2026-08-16
+     * self-review). This wrote the grounded-by edge between the two REGION
+     * HUBS and then echoed those hubs back in the "claim"/"evidence" fields
+     * as though they were the caller's input. Three consequences, all measured
+     * against the live store:
+     *
+     *  1. The edge landed on a node the caller never named. Asking to ground
+     *     3b9ced5d against 6edf8c79 wrote an edge on 6edf8c79 -> d0406dfd,
+     *     because those were the hubs of the two regions.
+     *  2. When both seeds resolve into the same region, the hubs coincide and
+     *     the call grounds a node against ITSELF, returning grounding = 1 —
+     *     a perfect score with no evidence behind it. Two independent agents
+     *     hit this and reported 0.885 / 0.909 self-groundings as confident.
+     *  3. The echo concealed both, because the response looked exactly like a
+     *     successful grounding of the ids that were passed in.
+     *
+     * The region is HOW a claim is evaluated; it is not WHAT the claim is
+     * about. So the edge attaches to the requested ids, and the resolved hubs
+     * are reported separately under claim_region / evidence_region. When the
+     * two regions coincide, the grounding is degenerate by construction and is
+     * reported as such rather than as a confident 1.0. */
+    const char* cid = EL_CSTR(claim);
+    const char* eid = EL_CSTR(evidence);
+    const char* chub = C->hub_id ? C->hub_id : cid;
+    const char* ehub = E->hub_id ? E->hub_id : eid;
+    /* Degeneracy is broader than chub == ehub. Three circular shapes, each of
+     * which yields a high score for structural reasons rather than evidential
+     * ones, and all three were previously invisible:
+     *   same-region   both seeds resolve to one region — grounding a thing
+     *                 against itself.
+     *   claim-in-ev   the claim's region hub IS the evidence node: the evidence
+     *                 sits at the centre of the claim's own neighbourhood.
+     *   ev-in-claim   the mirror case.
+     * Measured: grounding 3b9ced5d against 6edf8c79 scored 0.98883 purely
+     * because 6edf8c79 is the hub of 3b9ced5d's region. */
+    const char* degenerate = NULL;
+    if (chub && ehub && strcmp(chub, ehub) == 0)            degenerate = "same-region";
+    else if (chub && eid && strcmp(chub, eid) == 0)         degenerate = "claim-region-is-evidence";
+    else if (ehub && cid && strcmp(ehub, cid) == 0)         degenerate = "evidence-region-is-claim";
+    if (degenerate) grounding = 0.0;   /* circular support is not support */
+
+    /* Do not write an edge for a grounding that is degenerate by construction. */
+    int wr = degenerate ? -1 : cog_ground_edge(g_engram_store, cid, eid, grounding, fw);
+    JsonBuf b; jb_init(&b); char t[512];
+    snprintf(t, sizeof t, "{\"relation\":\"grounded-by\",\"claim\":\"%s\",\"evidence\":\"%s\","
+             "\"claim_region\":\"%s\",\"evidence_region\":\"%s\",\"degenerate\":%s%s%s,"
+             "\"for_whom\":\"%s\",\"grounding\":%.6g,\"written\":%s}",
+             cid ? cid : "", eid ? eid : "", chub ? chub : "", ehub ? ehub : "",
+             degenerate ? "\"" : "false", degenerate ? degenerate : "", degenerate ? "\"" : "",
+             fw ? fw : "-", grounding, wr == 0 ? "true" : "false");
     jb_puts(&b, t);
     engram_geo_free(C); engram_geo_free(E);
     return el_wrap_str(b.buf);