Merge pull request 'runtime: extract engram_text.c, and repair 10 harnesses that could not link' (#162) from fix/runtime-extract-text into fix/runtime-growth-guard

engram/test/run_interoception_p0.sh

@@ -3,10 +3,14 @@
 # Throwaway HOME + /tmp only. Never touches ~/.neuron or :8742.
 set -u
 HERE="$(cd "$(dirname "$0")" && pwd)"
-RT="$HERE/../../lang/runtime/el_runtime.c"
+RTSRC="$("$HERE/../../scripts/el-runtime-sources.sh" "$HERE/../../lang/runtime")"
-ST="$HERE/../../lang/runtime/engram_store.c"
+# The runtime is MULTI-FILE (lang/runtime/SOURCES). This harness used to link
-GEO="$HERE/../../lang/runtime/engram_geometry.c"
+# el_runtime.c + engram_store.c only, which stopped linking once el_runtime.c
-VIDX="$HERE/../../lang/runtime/engram_vindex.c"
+# began calling into the other engram siblings. Unquoted on purpose: a list.
+SSLFLAGS=""
+if command -v brew >/dev/null 2>&1 && O="$(brew --prefix openssl@3 2>/dev/null)"; then
+  SSLFLAGS="-I$O/include -L$O/lib"
+fi
 INC="$HERE/../../lang/runtime"
 WORK="$(mktemp -d /tmp/engram-p0-XXXXXX)"
 export HOME="$WORK/home"; mkdir -p "$HOME"
@@ -14,8 +18,8 @@ unset ENGRAM_STORE
 fail=0
 
 echo "== compile (plain) =="
-gcc -O1 -std=c11 -I "$INC" "$HERE/test_interoception_p0_emb.c" "$RT" "$ST" "$GEO" "$VIDX" \
+gcc -O1 -std=c11 -I "$INC" "$HERE/test_interoception_p0_emb.c" $RTSRC $SSLFLAGS \
-    -lcurl -lm -o "$WORK/p0" 2>"$WORK/cc.log" || { echo "COMPILE FAILED"; cat "$WORK/cc.log"; rm -rf "$WORK"; exit 1; }
+    -lcurl -lssl -lcrypto -lpthread -lm -lm -o "$WORK/p0" 2>"$WORK/cc.log" || { echo "COMPILE FAILED"; cat "$WORK/cc.log"; rm -rf "$WORK"; exit 1; }
 
 D="$WORK/d"; mkdir -p "$D"
 "$WORK/p0" "$D" || { echo "FAIL: run"; fail=1; }
@@ -69,8 +73,8 @@ PY
 echo
 echo "== ASan+UBSan =="
 gcc -O1 -g -std=c11 -fsanitize=address,undefined -fno-sanitize-recover=undefined \
-    -I "$INC" "$HERE/test_interoception_p0_emb.c" "$RT" "$ST" "$GEO" "$VIDX" \
+    -I "$INC" "$HERE/test_interoception_p0_emb.c" $RTSRC $SSLFLAGS \
-    -lcurl -lm -o "$WORK/p0.san" 2>"$WORK/san_cc.log" || { echo "SAN COMPILE FAILED"; tail -20 "$WORK/san_cc.log"; fail=1; }
+    -lcurl -lssl -lcrypto -lpthread -lm -lm -o "$WORK/p0.san" 2>"$WORK/san_cc.log" || { echo "SAN COMPILE FAILED"; tail -20 "$WORK/san_cc.log"; fail=1; }
 if [ -x "$WORK/p0.san" ]; then
   export ASAN_OPTIONS=detect_leaks=0
   DS="$WORK/ds"; mkdir -p "$DS"

engram/test/run_interoception_p1.sh

@@ -3,10 +3,14 @@
 # Throwaway HOME + /tmp only. Never touches ~/.neuron or :8742.
 set -u
 HERE="$(cd "$(dirname "$0")" && pwd)"
-RT="$HERE/../../lang/runtime/el_runtime.c"
+RTSRC="$("$HERE/../../scripts/el-runtime-sources.sh" "$HERE/../../lang/runtime")"
-ST="$HERE/../../lang/runtime/engram_store.c"
+# The runtime is MULTI-FILE (lang/runtime/SOURCES). This harness used to link
-GEO="$HERE/../../lang/runtime/engram_geometry.c"
+# el_runtime.c + engram_store.c only, which stopped linking once el_runtime.c
-VIDX="$HERE/../../lang/runtime/engram_vindex.c"
+# began calling into the other engram siblings. Unquoted on purpose: a list.
+SSLFLAGS=""
+if command -v brew >/dev/null 2>&1 && O="$(brew --prefix openssl@3 2>/dev/null)"; then
+  SSLFLAGS="-I$O/include -L$O/lib"
+fi
 INC="$HERE/../../lang/runtime"
 WORK="$(mktemp -d /tmp/engram-p1-XXXXXX)"
 export HOME="$WORK/home"; mkdir -p "$HOME"
@@ -14,8 +18,8 @@ unset ENGRAM_STORE ENGRAM_CONSOLIDATION ENGRAM_CONSOL_CONN_MIN ENGRAM_CONSOL_PER
 fail=0
 
 echo "== compile =="
-gcc -O1 -std=c11 -I "$INC" "$HERE/test_interoception_p1_consol.c" "$RT" "$ST" "$GEO" "$VIDX" \
+gcc -O1 -std=c11 -I "$INC" "$HERE/test_interoception_p1_consol.c" $RTSRC $SSLFLAGS \
-    -lcurl -lm -o "$WORK/p1" 2>"$WORK/cc.log" || { echo "COMPILE FAILED"; cat "$WORK/cc.log"; rm -rf "$WORK"; exit 1; }
+    -lcurl -lssl -lcrypto -lpthread -lm -lm -o "$WORK/p1" 2>"$WORK/cc.log" || { echo "COMPILE FAILED"; cat "$WORK/cc.log"; rm -rf "$WORK"; exit 1; }
 
 echo
 echo "== (a) HEADLINE: hebb accrual curve over N co-activations (flag OFF, pure trunk) =="
@@ -129,8 +133,8 @@ cat "$WORK/off.txt" | sed 's/^/    /'
 echo
 echo "== ASan+UBSan (connect + perm + accrual-short) =="
 gcc -O1 -g -std=c11 -fsanitize=address,undefined -fno-sanitize-recover=undefined \
-    -I "$INC" "$HERE/test_interoception_p1_consol.c" "$RT" "$ST" "$GEO" "$VIDX" \
+    -I "$INC" "$HERE/test_interoception_p1_consol.c" $RTSRC $SSLFLAGS \
-    -lcurl -lm -o "$WORK/p1.san" 2>"$WORK/san_cc.log" || { echo "SAN COMPILE FAILED"; tail -25 "$WORK/san_cc.log"; fail=1; }
+    -lcurl -lssl -lcrypto -lpthread -lm -lm -o "$WORK/p1.san" 2>"$WORK/san_cc.log" || { echo "SAN COMPILE FAILED"; tail -25 "$WORK/san_cc.log"; fail=1; }
 if [ -x "$WORK/p1.san" ]; then
   export ASAN_OPTIONS=detect_leaks=0
   DS="$WORK/san"; mkdir -p "$DS"

engram/test/run_interoception_p2.sh

@@ -3,10 +3,14 @@
 # Throwaway HOME + /tmp only. TC defaults to 3600s; we pin it for the math.
 set -u
 HERE="$(cd "$(dirname "$0")" && pwd)"
-RT="$HERE/../../lang/runtime/el_runtime.c"
+RTSRC="$("$HERE/../../scripts/el-runtime-sources.sh" "$HERE/../../lang/runtime")"
-ST="$HERE/../../lang/runtime/engram_store.c"
+# The runtime is MULTI-FILE (lang/runtime/SOURCES). This harness used to link
-GEO="$HERE/../../lang/runtime/engram_geometry.c"
+# el_runtime.c + engram_store.c only, which stopped linking once el_runtime.c
-VIDX="$HERE/../../lang/runtime/engram_vindex.c"
+# began calling into the other engram siblings. Unquoted on purpose: a list.
+SSLFLAGS=""
+if command -v brew >/dev/null 2>&1 && O="$(brew --prefix openssl@3 2>/dev/null)"; then
+  SSLFLAGS="-I$O/include -L$O/lib"
+fi
 INC="$HERE/../../lang/runtime"
 WORK="$(mktemp -d /tmp/engram-p2-XXXXXX)"
 export HOME="$WORK/home"; mkdir -p "$HOME"
@@ -15,8 +19,8 @@ unset ENGRAM_STORE
 fail=0
 
 echo "== compile =="
-gcc -O1 -std=c11 -I "$INC" "$HERE/test_interoception_p2_chrono.c" "$RT" "$ST" "$GEO" "$VIDX" \
+gcc -O1 -std=c11 -I "$INC" "$HERE/test_interoception_p2_chrono.c" $RTSRC $SSLFLAGS \
-    -lcurl -lm -o "$WORK/p2" 2>"$WORK/cc.log" || { echo "COMPILE FAILED"; cat "$WORK/cc.log"; rm -rf "$WORK"; exit 1; }
+    -lcurl -lssl -lcrypto -lpthread -lm -lm -o "$WORK/p2" 2>"$WORK/cc.log" || { echo "COMPILE FAILED"; cat "$WORK/cc.log"; rm -rf "$WORK"; exit 1; }
 
 sum_wm(){ python3 -c "import json,sys; g=json.load(open('$1')); print(sum(n.get('working_memory_weight',0) for n in g['nodes']))"; }
 
@@ -78,8 +82,8 @@ python3 -c "import sys; sys.exit(0 if abs($OFFWM-1.2)<1e-9 else 1)" \
 echo
 echo "== ASan+UBSan =="
 gcc -O1 -g -std=c11 -fsanitize=address,undefined -fno-sanitize-recover=undefined \
-    -I "$INC" "$HERE/test_interoception_p2_chrono.c" "$RT" "$ST" "$GEO" "$VIDX" \
+    -I "$INC" "$HERE/test_interoception_p2_chrono.c" $RTSRC $SSLFLAGS \
-    -lcurl -lm -o "$WORK/p2.san" 2>"$WORK/san_cc.log" || { echo "SAN COMPILE FAILED"; tail -25 "$WORK/san_cc.log"; fail=1; }
+    -lcurl -lssl -lcrypto -lpthread -lm -lm -o "$WORK/p2.san" 2>"$WORK/san_cc.log" || { echo "SAN COMPILE FAILED"; tail -25 "$WORK/san_cc.log"; fail=1; }
 if [ -x "$WORK/p2.san" ]; then
   export ASAN_OPTIONS=detect_leaks=0
   DS="$WORK/san"; mkdir -p "$DS"

engram/test/run_interoception_p3.sh

@@ -3,18 +3,22 @@
 # Read-only pure primitive; no store, no flag. Throwaway /tmp only.
 set -u
 HERE="$(cd "$(dirname "$0")" && pwd)"
-RT="$HERE/../../lang/runtime/el_runtime.c"
+RTSRC="$("$HERE/../../scripts/el-runtime-sources.sh" "$HERE/../../lang/runtime")"
-ST="$HERE/../../lang/runtime/engram_store.c"
+# The runtime is MULTI-FILE (lang/runtime/SOURCES). This harness used to link
-GEO="$HERE/../../lang/runtime/engram_geometry.c"
+# el_runtime.c + engram_store.c only, which stopped linking once el_runtime.c
-VIDX="$HERE/../../lang/runtime/engram_vindex.c"
+# began calling into the other engram siblings. Unquoted on purpose: a list.
+SSLFLAGS=""
+if command -v brew >/dev/null 2>&1 && O="$(brew --prefix openssl@3 2>/dev/null)"; then
+  SSLFLAGS="-I$O/include -L$O/lib"
+fi
 INC="$HERE/../../lang/runtime"
 WORK="$(mktemp -d /tmp/engram-p3-XXXXXX)"
 export HOME="$WORK/home"; mkdir -p "$HOME"
 fail=0
 
 echo "== compile =="
-gcc -O1 -std=c11 -I "$INC" "$HERE/test_interoception_p3_drift.c" "$RT" "$ST" "$GEO" "$VIDX" \
+gcc -O1 -std=c11 -I "$INC" "$HERE/test_interoception_p3_drift.c" $RTSRC $SSLFLAGS \
-    -lcurl -lm -o "$WORK/p3" 2>"$WORK/cc.log" || { echo "COMPILE FAILED"; cat "$WORK/cc.log"; rm -rf "$WORK"; exit 1; }
+    -lcurl -lssl -lcrypto -lpthread -lm -lm -o "$WORK/p3" 2>"$WORK/cc.log" || { echo "COMPILE FAILED"; cat "$WORK/cc.log"; rm -rf "$WORK"; exit 1; }
 
 "$WORK/p3" > "$WORK/out.txt" 2>&1 || { echo "FAIL run"; cat "$WORK/out.txt"; fail=1; }
 cat "$WORK/out.txt" | sed 's/^/    /'
@@ -52,8 +56,8 @@ PY
 echo
 echo "== ASan+UBSan =="
 gcc -O1 -g -std=c11 -fsanitize=address,undefined -fno-sanitize-recover=undefined \
-    -I "$INC" "$HERE/test_interoception_p3_drift.c" "$RT" "$ST" "$GEO" "$VIDX" \
+    -I "$INC" "$HERE/test_interoception_p3_drift.c" $RTSRC $SSLFLAGS \
-    -lcurl -lm -o "$WORK/p3.san" 2>"$WORK/san_cc.log" || { echo "SAN COMPILE FAILED"; tail -25 "$WORK/san_cc.log"; fail=1; }
+    -lcurl -lssl -lcrypto -lpthread -lm -lm -o "$WORK/p3.san" 2>"$WORK/san_cc.log" || { echo "SAN COMPILE FAILED"; tail -25 "$WORK/san_cc.log"; fail=1; }
 if [ -x "$WORK/p3.san" ]; then
   export ASAN_OPTIONS=detect_leaks=0
   "$WORK/p3.san" >/dev/null 2>"$WORK/san.log"

engram/test/run_interoception_p4.sh

@@ -2,10 +2,14 @@
 # M-INTEROCEPTION P4 gate: afferent input counters in act-stats (additive).
 set -u
 HERE="$(cd "$(dirname "$0")" && pwd)"
-RT="$HERE/../../lang/runtime/el_runtime.c"
+RTSRC="$("$HERE/../../scripts/el-runtime-sources.sh" "$HERE/../../lang/runtime")"
-ST="$HERE/../../lang/runtime/engram_store.c"
+# The runtime is MULTI-FILE (lang/runtime/SOURCES). This harness used to link
-GEO="$HERE/../../lang/runtime/engram_geometry.c"
+# el_runtime.c + engram_store.c only, which stopped linking once el_runtime.c
-VIDX="$HERE/../../lang/runtime/engram_vindex.c"
+# began calling into the other engram siblings. Unquoted on purpose: a list.
+SSLFLAGS=""
+if command -v brew >/dev/null 2>&1 && O="$(brew --prefix openssl@3 2>/dev/null)"; then
+  SSLFLAGS="-I$O/include -L$O/lib"
+fi
 INC="$HERE/../../lang/runtime"
 WORK="$(mktemp -d /tmp/engram-p4-XXXXXX)"
 export HOME="$WORK/home"; mkdir -p "$HOME"
@@ -13,8 +17,8 @@ unset ENGRAM_STORE
 fail=0
 
 echo "== compile =="
-gcc -O1 -std=c11 -I "$INC" "$HERE/test_interoception_p4_afferent.c" "$RT" "$ST" "$GEO" "$VIDX" \
+gcc -O1 -std=c11 -I "$INC" "$HERE/test_interoception_p4_afferent.c" $RTSRC $SSLFLAGS \
-    -lcurl -lm -o "$WORK/p4" 2>"$WORK/cc.log" || { echo "COMPILE FAILED"; cat "$WORK/cc.log"; rm -rf "$WORK"; exit 1; }
+    -lcurl -lssl -lcrypto -lpthread -lm -lm -o "$WORK/p4" 2>"$WORK/cc.log" || { echo "COMPILE FAILED"; cat "$WORK/cc.log"; rm -rf "$WORK"; exit 1; }
 
 "$WORK/p4" > "$WORK/out.txt" 2>&1 || { echo "FAIL run"; cat "$WORK/out.txt"; fail=1; }
 grep -oE 'aff_[a-z_]+":[0-9]+' "$WORK/out.txt" | sed 's/^/    /' | head -30
@@ -53,8 +57,8 @@ PY
 echo
 echo "== ASan+UBSan =="
 gcc -O1 -g -std=c11 -fsanitize=address,undefined -fno-sanitize-recover=undefined \
-    -I "$INC" "$HERE/test_interoception_p4_afferent.c" "$RT" "$ST" "$GEO" "$VIDX" \
+    -I "$INC" "$HERE/test_interoception_p4_afferent.c" $RTSRC $SSLFLAGS \
-    -lcurl -lm -o "$WORK/p4.san" 2>"$WORK/san_cc.log" || { echo "SAN COMPILE FAILED"; tail -25 "$WORK/san_cc.log"; fail=1; }
+    -lcurl -lssl -lcrypto -lpthread -lm -lm -o "$WORK/p4.san" 2>"$WORK/san_cc.log" || { echo "SAN COMPILE FAILED"; tail -25 "$WORK/san_cc.log"; fail=1; }
 if [ -x "$WORK/p4.san" ]; then
   export ASAN_OPTIONS=detect_leaks=0
   "$WORK/p4.san" >/dev/null 2>"$WORK/san.log"

engram/test/run_interoception_p5.sh

@@ -2,10 +2,14 @@
 # M-INTEROCEPTION P5 gate: dream-recall builtin engram_dreams_json (honesty rail).
 set -u
 HERE="$(cd "$(dirname "$0")" && pwd)"
-RT="$HERE/../../lang/runtime/el_runtime.c"
+RTSRC="$("$HERE/../../scripts/el-runtime-sources.sh" "$HERE/../../lang/runtime")"
-ST="$HERE/../../lang/runtime/engram_store.c"
+# The runtime is MULTI-FILE (lang/runtime/SOURCES). This harness used to link
-GEO="$HERE/../../lang/runtime/engram_geometry.c"
+# el_runtime.c + engram_store.c only, which stopped linking once el_runtime.c
-VIDX="$HERE/../../lang/runtime/engram_vindex.c"
+# began calling into the other engram siblings. Unquoted on purpose: a list.
+SSLFLAGS=""
+if command -v brew >/dev/null 2>&1 && O="$(brew --prefix openssl@3 2>/dev/null)"; then
+  SSLFLAGS="-I$O/include -L$O/lib"
+fi
 INC="$HERE/../../lang/runtime"
 WORK="$(mktemp -d /tmp/engram-p5-XXXXXX)"
 export HOME="$WORK/home"; mkdir -p "$HOME"
@@ -13,8 +17,8 @@ unset ENGRAM_STORE
 fail=0
 
 echo "== compile =="
-gcc -O1 -std=c11 -I "$INC" "$HERE/test_interoception_p5_dreams.c" "$RT" "$ST" "$GEO" "$VIDX" \
+gcc -O1 -std=c11 -I "$INC" "$HERE/test_interoception_p5_dreams.c" $RTSRC $SSLFLAGS \
-    -lcurl -lm -o "$WORK/p5" 2>"$WORK/cc.log" || { echo "COMPILE FAILED"; cat "$WORK/cc.log"; rm -rf "$WORK"; exit 1; }
+    -lcurl -lssl -lcrypto -lpthread -lm -lm -o "$WORK/p5" 2>"$WORK/cc.log" || { echo "COMPILE FAILED"; cat "$WORK/cc.log"; rm -rf "$WORK"; exit 1; }
 
 D="$WORK/d"; mkdir -p "$D"
 "$WORK/p5" "$D" > "$WORK/out.txt" 2>&1 || { echo "FAIL run"; cat "$WORK/out.txt"; fail=1; }
@@ -57,8 +61,8 @@ PY
 echo
 echo "== ASan+UBSan =="
 gcc -O1 -g -std=c11 -fsanitize=address,undefined -fno-sanitize-recover=undefined \
-    -I "$INC" "$HERE/test_interoception_p5_dreams.c" "$RT" "$ST" "$GEO" "$VIDX" \
+    -I "$INC" "$HERE/test_interoception_p5_dreams.c" $RTSRC $SSLFLAGS \
-    -lcurl -lm -o "$WORK/p5.san" 2>"$WORK/san_cc.log" || { echo "SAN COMPILE FAILED"; tail -25 "$WORK/san_cc.log"; fail=1; }
+    -lcurl -lssl -lcrypto -lpthread -lm -lm -o "$WORK/p5.san" 2>"$WORK/san_cc.log" || { echo "SAN COMPILE FAILED"; tail -25 "$WORK/san_cc.log"; fail=1; }
 if [ -x "$WORK/p5.san" ]; then
   export ASAN_OPTIONS=detect_leaks=0
   DS="$WORK/ds"; mkdir -p "$DS"

engram/test/run_m35_hebb_persist.sh

@@ -6,8 +6,14 @@
 # Writes ONLY under a throwaway /tmp dir with a throwaway HOME.
 set -u
 HERE="$(cd "$(dirname "$0")" && pwd)"
-RT="$HERE/../../lang/runtime/el_runtime.c"
+RTSRC="$("$HERE/../../scripts/el-runtime-sources.sh" "$HERE/../../lang/runtime")"
-ST="$HERE/../../lang/runtime/engram_store.c"
+# The runtime is MULTI-FILE (lang/runtime/SOURCES). This harness used to link
+# el_runtime.c + engram_store.c only, which stopped linking once el_runtime.c
+# began calling into the other engram siblings. Unquoted on purpose: a list.
+SSLFLAGS=""
+if command -v brew >/dev/null 2>&1 && O="$(brew --prefix openssl@3 2>/dev/null)"; then
+  SSLFLAGS="-I$O/include -L$O/lib"
+fi
 INC="$HERE/../../lang/runtime"
 WORK="$(mktemp -d /tmp/engram-m35-XXXXXX)"
 BIN="$WORK/m35"
@@ -17,7 +23,7 @@ unset ENGRAM_STORE
 fail=0
 
 echo "== compiling harness (gcc: el_runtime.c + engram_store.c + test_m35_hebb_persist.c) =="
-gcc -O1 -std=c11 -I "$INC" "$HERE/test_m35_hebb_persist.c" "$RT" "$ST" -lcurl -o "$BIN" 2>"$WORK/cc.log"
+gcc -O1 -std=c11 -I "$INC" "$HERE/test_m35_hebb_persist.c" $RTSRC $SSLFLAGS -lcurl -lssl -lcrypto -lpthread -lm -o "$BIN" 2>"$WORK/cc.log"
 if [ $? -ne 0 ]; then echo "COMPILE FAILED:"; cat "$WORK/cc.log"; rm -rf "$WORK"; exit 1; fi
 
 echo
@@ -139,7 +145,7 @@ echo
 echo "== 5) ASan+UBSan build, exercise the full persist+reboot flow (leaks off — harness intentionally leaks el_strdup) =="
 SANBIN="$WORK/m35.san"
 gcc -O1 -g -std=c11 -fsanitize=address,undefined -fno-sanitize-recover=undefined \
-    -I "$INC" "$HERE/test_m35_hebb_persist.c" "$RT" "$ST" -lcurl -o "$SANBIN" 2>"$WORK/san_cc.log"
+    -I "$INC" "$HERE/test_m35_hebb_persist.c" $RTSRC $SSLFLAGS -lcurl -lssl -lcrypto -lpthread -lm -o "$SANBIN" 2>"$WORK/san_cc.log"
 if [ $? -ne 0 ]; then echo "  SAN COMPILE FAILED:"; tail -20 "$WORK/san_cc.log"; fail=1; else
   export ASAN_OPTIONS=detect_leaks=0
   DSAN="$WORK/san"; mkdir -p "$DSAN"

engram/test/run_m3_parity.sh

@@ -4,8 +4,14 @@
 # Writes ONLY under a throwaway /tmp dir with a throwaway HOME + ENGRAM_DATA_DIR.
 set -u
 HERE="$(cd "$(dirname "$0")" && pwd)"
-RT="$HERE/../../lang/runtime/el_runtime.c"
+RTSRC="$("$HERE/../../scripts/el-runtime-sources.sh" "$HERE/../../lang/runtime")"
-ST="$HERE/../../lang/runtime/engram_store.c"
+# The runtime is MULTI-FILE (lang/runtime/SOURCES). This harness used to link
+# el_runtime.c + engram_store.c only, which stopped linking once el_runtime.c
+# began calling into the other engram siblings. Unquoted on purpose: a list.
+SSLFLAGS=""
+if command -v brew >/dev/null 2>&1 && O="$(brew --prefix openssl@3 2>/dev/null)"; then
+  SSLFLAGS="-I$O/include -L$O/lib"
+fi
 INC="$HERE/../../lang/runtime"
 WORK="$(mktemp -d /tmp/engram-m3-XXXXXX)"
 DATA="$WORK/data"; mkdir -p "$DATA"
@@ -17,7 +23,7 @@ unset ENGRAM_STORE
 fail=0
 
 echo "== compiling harness (gcc: el_runtime.c + engram_store.c + test_m3_parity.c) =="
-gcc -O1 -std=c11 -I "$INC" "$HERE/test_m3_parity.c" "$RT" "$ST" -lcurl -o "$BIN" 2>"$WORK/cc.log"
+gcc -O1 -std=c11 -I "$INC" "$HERE/test_m3_parity.c" $RTSRC $SSLFLAGS -lcurl -lssl -lcrypto -lpthread -lm -o "$BIN" 2>"$WORK/cc.log"
 if [ $? -ne 0 ]; then echo "COMPILE FAILED:"; cat "$WORK/cc.log"; rm -rf "$WORK"; exit 1; fi
 grep -i warning "$WORK/cc.log" | grep -iE 'engram_store|eg_store|eg_load|scan_nodes|scan_edges' && echo "(warnings in M3 code above)" || true
 
@@ -106,7 +112,7 @@ echo
 echo "== 5) ASan+UBSan build, exercise M3 scan/boot/hooks (leaks off — harness intentionally leaks el_strdup) =="
 SANBIN="$WORK/m3.san"
 gcc -O1 -g -std=c11 -fsanitize=address,undefined -fno-sanitize-recover=undefined \
-    -I "$INC" "$HERE/test_m3_parity.c" "$RT" "$ST" -lcurl -o "$SANBIN" 2>"$WORK/san_cc.log"
+    -I "$INC" "$HERE/test_m3_parity.c" $RTSRC $SSLFLAGS -lcurl -lssl -lcrypto -lpthread -lm -o "$SANBIN" 2>"$WORK/san_cc.log"
 if [ $? -ne 0 ]; then echo "  SAN COMPILE FAILED:"; tail -20 "$WORK/san_cc.log"; fail=1; else
   export ASAN_OPTIONS=detect_leaks=0
   DATA2="$WORK/data2"; mkdir -p "$DATA2"

engram/test/run_m7_traversal.sh

@@ -6,8 +6,14 @@
 # Writes ONLY under a throwaway /tmp dir with a throwaway HOME.
 set -u
 HERE="$(cd "$(dirname "$0")" && pwd)"
-RT="$HERE/../../lang/runtime/el_runtime.c"
+RTSRC="$("$HERE/../../scripts/el-runtime-sources.sh" "$HERE/../../lang/runtime")"
-ST="$HERE/../../lang/runtime/engram_store.c"
+# The runtime is MULTI-FILE (lang/runtime/SOURCES). This harness used to link
+# el_runtime.c + engram_store.c only, which stopped linking once el_runtime.c
+# began calling into the other engram siblings. Unquoted on purpose: a list.
+SSLFLAGS=""
+if command -v brew >/dev/null 2>&1 && O="$(brew --prefix openssl@3 2>/dev/null)"; then
+  SSLFLAGS="-I$O/include -L$O/lib"
+fi
 INC="$HERE/../../lang/runtime"
 WORK="$(mktemp -d /tmp/engram-m7-XXXXXX)"
 DATA="$WORK/data"; mkdir -p "$DATA"
@@ -22,7 +28,7 @@ unset ENGRAM_STORE
 fail=0
 
 echo "== compiling harness (gcc: el_runtime.c + engram_store.c + test_m7_traversal.c) =="
-gcc -O2 -std=c11 -I "$INC" "$HERE/test_m7_traversal.c" "$RT" "$ST" -lcurl -lm -o "$BIN" 2>"$WORK/cc.log"
+gcc -O2 -std=c11 -I "$INC" "$HERE/test_m7_traversal.c" $RTSRC $SSLFLAGS -lcurl -lssl -lcrypto -lpthread -lm -o "$BIN" 2>"$WORK/cc.log"
 if [ $? -ne 0 ]; then echo "COMPILE FAILED:"; cat "$WORK/cc.log"; rm -rf "$WORK"; exit 1; fi
 echo "  ok: compiled"
 
@@ -115,7 +121,7 @@ echo
 echo "== 3) ASan+UBSan clean across parity + a small perf loop (leaks off — harness intentionally leaks el_strdup) =="
 SANBIN="$WORK/m7.san"
 gcc -O1 -g -std=c11 -fsanitize=address,undefined -fno-sanitize-recover=undefined \
-    -I "$INC" "$HERE/test_m7_traversal.c" "$RT" "$ST" -lcurl -lm -o "$SANBIN" 2>"$WORK/san_cc.log"
+    -I "$INC" "$HERE/test_m7_traversal.c" $RTSRC $SSLFLAGS -lcurl -lssl -lcrypto -lpthread -lm -lm -o "$SANBIN" 2>"$WORK/san_cc.log"
 if [ $? -ne 0 ]; then echo "  SAN COMPILE FAILED:"; tail -20 "$WORK/san_cc.log"; fail=1; else
   export ASAN_OPTIONS=detect_leaks=0
   D2="$WORK/data2"; mkdir -p "$D2"

engram/test/run_wal_tests.sh

@@ -3,8 +3,17 @@
 set -e
 HERE="$(cd "$(dirname "$0")" && pwd)"
 REL="$HERE/../../lang/runtime"
+# test_wal.c and test_failloud.c #include "el_runtime.c" directly, so el_runtime.c
+# is already IN the translation unit — link the SIBLINGS only, or every symbol in
+# it is defined twice. The siblings are still required: el_runtime.c calls into
+# all six engram TUs. (lang/runtime/SOURCES is the source of truth.)
+RTSIB="$("$HERE/../../scripts/el-runtime-sources.sh" "$REL" | grep -v '/el_runtime\.c$')"
+SSLFLAGS=""
+if command -v brew >/dev/null 2>&1 && O="$(brew --prefix openssl@3 2>/dev/null)"; then
+  SSLFLAGS="-I$O/include -L$O/lib"
+fi
 cc -O2 -fbracket-depth=1024 -Wno-parentheses-equality -I"$REL" \
-   "$HERE/test_wal.c" -lcurl -lpthread -o /tmp/test_wal
+   "$HERE/test_wal.c" $RTSIB $SSLFLAGS -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/test_wal
 HOME=/tmp/engram-throwaway-home /tmp/test_wal
 # Fail-loud data-dir check (must exit 1 with a FATAL line):
 cat > /tmp/test_failloud.c <<'C'
@@ -12,5 +21,5 @@ cat > /tmp/test_failloud.c <<'C'
 int main(void){ unsetenv("ENGRAM_DATA_DIR"); unsetenv("HOME");
   engram_resolve_data_dir(); printf("REACHED\n"); return 0; }
 C
-cc -O2 -fbracket-depth=1024 -Wno-parentheses-equality -I"$REL" /tmp/test_failloud.c -lcurl -lpthread -o /tmp/test_failloud
+cc -O2 -fbracket-depth=1024 -Wno-parentheses-equality -I"$REL" /tmp/test_failloud.c $RTSIB $SSLFLAGS -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/test_failloud
 if env -u HOME -u ENGRAM_DATA_DIR /tmp/test_failloud; then echo "FAIL: should have exited"; exit 1; else echo "[PASS] fail-loud exit on unresolvable HOME"; fi

lang/install.sh

@@ -60,12 +60,14 @@ RUNTIME_SOURCES=(
     el_runtime.c el_seed.c
     engram_store.c engram_vindex.c engram_geometry.c
     engram_reason.c engram_verify.c engram_cognition.c
+    engram_text.c
     eg_cosine_batch.c eg_cosine_batch_strategy_cpu.c
 )
 RUNTIME_HEADERS=(
     el_runtime.h el_seed.h
     engram_store.h engram_vindex.h engram_geometry.h
     engram_reason.h engram_verify.h engram_cognition.h
+    engram_text.h
     eg_cosine_batch.h eg_cosine_batch_strategy.h
 )
 

lang/runtime/BUDGET

@@ -28,12 +28,14 @@
 # FORMAT: <key> <value>   — `#` comments and blank lines ignored.
 
 # Maximum lines in lang/runtime/el_runtime.c.
-# 2026-08-16: 20,527 — the high-water mark, ratcheted from here.
+# 2026-08-16: 20,527 — the high-water mark.
-max_lines 20527
+# 2026-08-16: 20,427 — engram_text.c extracted (tokenize, token hygiene,
+#             word-boundary match, damage signature). Ratcheted down.
+max_lines 20427
 
 # Maximum top-level engram/eg_/cog_ function definitions in el_runtime.c.
 # ~47.5% of the file is engram code, and engram already owns six dedicated
 # sibling files (engram_{store,vindex,geometry,reason,verify,cognition}.c).
 # Every one of these belongs in one of them. This is the Stage 3 scoreboard.
-# 2026-08-16: 279.
+# 2026-08-16: 279 -> 275 (4 moved to engram_text.c).
-max_engram_fns 279
+max_engram_fns 275

lang/runtime/SOURCES

@@ -44,6 +44,11 @@ engram_reason.c
 engram_verify.c
 engram_cognition.c
 
+# --- Text: tokenization, token hygiene, damage signature ---------------------
+# Extracted from el_runtime.c 2026-08-16. Plain C over <ctype.h>/<string.h> —
+# touches no EL value type and no engram store type. New text helpers go HERE.
+engram_text.c
+
 # --- Vector math: batch cosine + its CPU strategy ----------------------------
 # The ggml strategy (eg_cosine_batch_strategy_ggml.c) is an OPTIONAL swap-in and
 # is deliberately NOT in the default set — it needs ggml headers. Link it in

lang/runtime/el_runtime.c

@@ -8638,6 +8638,7 @@ static char* engram_first_n_chars(const char* s, size_t n) {
  *      mutation (node/edge create, forget) is mirrored through the store's
  *      WAL-logged API so neuron.egm/neuron.wal stay authoritative.
  * ══════════════════════════════════════════════════════════════════════════ */
+#include "engram_text.h"   /* text: tokenize, token hygiene, loss signature */
 #include "engram_store.h"
 #include "engram_vindex.h"   /* M8: ANN (HNSW) index for activation seed selection */
 #include "engram_geometry.h" /* M9: centered relational-neighborhood geometry (priming) */
@@ -9061,31 +9062,9 @@ el_val_t engram_node(el_val_t content, el_val_t node_type, el_val_t salience) {
  *           RIGHT NOW" — which is the regression question, and the one that
  *           would have caught this in a day instead of two months.
  *
- * SIGNATURE. Conservative on purpose — a false alarm that cries corruption
+ * The SIGNATURE itself (eg_text_loss_signature) moved to engram_text.c on
- * over ordinary punctuation is worse than useless. Two patterns, both of
+ * 2026-08-16 — it is plain C over <ctype.h> and touches nothing in here. The
- * which are essentially absent from well-formed English prose:
+ * stock/flow gauges below stay, because they touch store and EL value types. */
- *   (a) alnum '?' alnum   — "na?ve", "caf?s", "don?t". A real question mark
- *                           never sits between two word characters.
- *   (b) ' ? ' followed by a lowercase letter — a lost em/en dash. A real
- *                           question mark is not preceded by a space, and
- *                           what follows one starts a new sentence.
- * Deliberately NOT flagged: a trailing '?' after a word, '? ' before a
- * capital, or '?' at end of string — all legitimate. This under-counts (it
- * cannot see a mangled 'café ' where the '?' landed before a space), so the
- * census is a floor on the damage, never an exaggeration of it. */
-static int eg_text_loss_signature(const char* s) {
-    if (!s) return 0;
-    for (const char* p = s; *p; p++) {
-        if (*p != '?') continue;
-        unsigned char prev = (p == s) ? 0 : (unsigned char)p[-1];
-        unsigned char next = (unsigned char)p[1];
-        /* (a) sandwiched between word characters. */
-        if (isalnum(prev) && isalnum(next)) return 1;
-        /* (b) spaced, with lowercase continuation — a lost dash. */
-        if (prev == ' ' && next == ' ' && islower((unsigned char)p[2])) return 1;
-    }
-    return 0;
-}
 
 /* Damaged-node creations since process start. See the block comment above. */
 static int64_t _eg_txt_write_damaged = 0;
@@ -9697,37 +9676,7 @@ static int istr_contains(const char* hay, const char* needle) {
  * fix landed but never reached this release runtime — the copy the engram
  * binary actually builds against.) */
 #define ENGRAM_MAX_QTOKENS 32
-#define ENGRAM_QTOK_LEN    256
+/* ENGRAM_QTOK_LEN and engram_tokenize_query moved to engram_text.h/.c. */
-
-/* Split q on whitespace into up to ENGRAM_MAX_QTOKENS distinct
- * (case-insensitive) tokens. Returns the token count. Over-long tokens are
- * truncated to ENGRAM_QTOK_LEN-1; over-count tokens are ignored. */
-static int engram_tokenize_query(const char* q,
-                                 char toks[][ENGRAM_QTOK_LEN], int maxtok) {
-    int n = 0;
-    if (!q) return 0;
-    const char* p = q;
-    while (*p && n < maxtok) {
-        while (*p && isspace((unsigned char)*p)) p++;
-        if (!*p) break;
-        char buf[ENGRAM_QTOK_LEN];
-        size_t tl = 0;
-        while (*p && !isspace((unsigned char)*p)) {
-            if (tl < sizeof(buf) - 1) buf[tl++] = *p;
-            p++;
-        }
-        buf[tl] = '\0';
-        if (tl == 0) continue;
-        int dup = 0;
-        for (int s = 0; s < n; s++) {
-            if (strcasecmp(toks[s], buf) == 0) { dup = 1; break; }
-        }
-        if (dup) continue;
-        memcpy(toks[n], buf, tl + 1);
-        n++;
-    }
-    return n;
-}
 
 /* Count how many of the ntok distinct query tokens appear (case-insensitive)
  * in the node's content, label, or tags. 0 == no match. */
@@ -16389,29 +16338,6 @@ el_val_t engram_label_df(el_val_t term) {
 #define ENGRAM_ST_TOKLEN    64
 #define ENGRAM_ST_SCANCHARS 400
 
-/* Trim leading/trailing non-alphanumerics, then accept only tokens whose core
- * is alphanumeric plus '-' and '_' with at least 3 letters. This subsumes the
- * quoted-title guard (2026-07-25) and the "<!--" flood (2026-08-03)
- * structurally: markup and punctuation-bearing tokens never become
- * candidates, rather than being blocklisted after the fact. */
-static int eg_st_clean_token(const char* raw, size_t rawlen,
-                             char* out, size_t outcap) {
-    size_t s = 0, e = rawlen;
-    while (s < e && !isalnum((unsigned char)raw[s])) s++;
-    while (e > s && !isalnum((unsigned char)raw[e - 1])) e--;
-    size_t len = e - s;
-    if (len < 4 || len >= outcap) return 0;
-    int alpha = 0;
-    for (size_t i = 0; i < len; i++) {
-        unsigned char c = (unsigned char)raw[s + i];
-        if (isalpha(c)) alpha++;
-        else if (!isdigit(c) && c != '-' && c != '_') return 0;
-    }
-    if (alpha < 3) return 0;
-    memcpy(out, raw + s, len);
-    out[len] = '\0';
-    return 1;
-}
 
 /* ENGRAM_ST_DEBUG=1 dumps the full scored candidate set to stderr. One
  * cached branch in production. This exists because the first live run of this
@@ -16424,32 +16350,6 @@ static int _eg_st_debug(void) {
     return v;
 }
 
-/* Word-boundary document frequency. engram_label_df uses istr_contains, i.e.
- * SUBSTRING matching, and that is the wrong estimator for term specificity on
- * short tokens: "them" hits inside "theme" and "anthem", "about" and "whole"
- * come back with df 2 and 1 rather than 0. That matters here specifically
- * because the min_df floor is what rejects English function words, and it can
- * only do that job if their df is honestly zero. Substring df quietly handed
- * them a survival ticket. Measured on the live store before this fix, "whole"
- * (df=1, idf=8.76) and "about" (df=2, idf=8.36) were outscoring real topical
- * terms and losing only on position — one node whose text happened to open
- * with a function word would have seeded on it.
- *
- * engram_label_df keeps substring semantics: it is a separate published
- * measure with existing callers, and changing it underneath them is not this
- * change's business. */
-static int eg_st_label_has_word(const char* hay, const char* word) {
-    size_t wl = strlen(word);
-    for (const char* p = hay; *p; p++) {
-        if (strncasecmp(p, word, wl) != 0) continue;
-        char before = (p == hay) ? '\0' : p[-1];
-        char after  = p[wl];
-        if (before && (isalnum((unsigned char)before) || before == '_')) continue;
-        if (after  && (isalnum((unsigned char)after)  || after  == '_')) continue;
-        return 1;
-    }
-    return 0;
-}
 
 /* YAKE T_Case, adapted to this corpus. YAKE up-weights all-caps tokens
  * because in ordinary prose an acronym is rare and carries topic. That

lang/runtime/engram_text.c

@@ -0,0 +1,122 @@
+/* engram_text.c — see engram_text.h.
+ *
+ * Moved verbatim out of el_runtime.c (2026-08-16). Bodies are unchanged; only
+ * `static` was dropped so they link from this translation unit, and each
+ * function's doc comment travelled with it.
+ */
+#include "engram_text.h"
+
+#include <ctype.h>
+#include <string.h>
+
+/* Split q on whitespace into up to ENGRAM_MAX_QTOKENS distinct
+ * (case-insensitive) tokens. Returns the token count. Over-long tokens are
+ * truncated to ENGRAM_QTOK_LEN-1; over-count tokens are ignored. */
+int engram_tokenize_query(const char* q,
+                                 char toks[][ENGRAM_QTOK_LEN], int maxtok) {
+    int n = 0;
+    if (!q) return 0;
+    const char* p = q;
+    while (*p && n < maxtok) {
+        while (*p && isspace((unsigned char)*p)) p++;
+        if (!*p) break;
+        char buf[ENGRAM_QTOK_LEN];
+        size_t tl = 0;
+        while (*p && !isspace((unsigned char)*p)) {
+            if (tl < sizeof(buf) - 1) buf[tl++] = *p;
+            p++;
+        }
+        buf[tl] = '\0';
+        if (tl == 0) continue;
+        int dup = 0;
+        for (int s = 0; s < n; s++) {
+            if (strcasecmp(toks[s], buf) == 0) { dup = 1; break; }
+        }
+        if (dup) continue;
+        memcpy(toks[n], buf, tl + 1);
+        n++;
+    }
+    return n;
+}
+
+/* Trim leading/trailing non-alphanumerics, then accept only tokens whose core
+ * is alphanumeric plus '-' and '_' with at least 3 letters. This subsumes the
+ * quoted-title guard (2026-07-25) and the "<!--" flood (2026-08-03)
+ * structurally: markup and punctuation-bearing tokens never become
+ * candidates, rather than being blocklisted after the fact. */
+int eg_st_clean_token(const char* raw, size_t rawlen,
+                             char* out, size_t outcap) {
+    size_t s = 0, e = rawlen;
+    while (s < e && !isalnum((unsigned char)raw[s])) s++;
+    while (e > s && !isalnum((unsigned char)raw[e - 1])) e--;
+    size_t len = e - s;
+    if (len < 4 || len >= outcap) return 0;
+    int alpha = 0;
+    for (size_t i = 0; i < len; i++) {
+        unsigned char c = (unsigned char)raw[s + i];
+        if (isalpha(c)) alpha++;
+        else if (!isdigit(c) && c != '-' && c != '_') return 0;
+    }
+    if (alpha < 3) return 0;
+    memcpy(out, raw + s, len);
+    out[len] = '\0';
+    return 1;
+}
+
+/* Word-boundary document frequency. engram_label_df uses istr_contains, i.e.
+ * SUBSTRING matching, and that is the wrong estimator for term specificity on
+ * short tokens: "them" hits inside "theme" and "anthem", "about" and "whole"
+ * come back with df 2 and 1 rather than 0. That matters here specifically
+ * because the min_df floor is what rejects English function words, and it can
+ * only do that job if their df is honestly zero. Substring df quietly handed
+ * them a survival ticket. Measured on the live store before this fix, "whole"
+ * (df=1, idf=8.76) and "about" (df=2, idf=8.36) were outscoring real topical
+ * terms and losing only on position — one node whose text happened to open
+ * with a function word would have seeded on it.
+ *
+ * engram_label_df keeps substring semantics: it is a separate published
+ * measure with existing callers, and changing it underneath them is not this
+ * change's business. */
+int eg_st_label_has_word(const char* hay, const char* word) {
+    size_t wl = strlen(word);
+    for (const char* p = hay; *p; p++) {
+        if (strncasecmp(p, word, wl) != 0) continue;
+        char before = (p == hay) ? '\0' : p[-1];
+        char after  = p[wl];
+        if (before && (isalnum((unsigned char)before) || before == '_')) continue;
+        if (after  && (isalnum((unsigned char)after)  || after  == '_')) continue;
+        return 1;
+    }
+    return 0;
+}
+
+/* Text-damage signature. Extracted with the function from el_runtime.c's
+ * "Text-integrity instrumentation" block; the stock/flow gauges that use it
+ * (engram_text_health_json, _eg_txt_write_damaged) stay there because they
+ * touch store and EL value types.
+ *
+ * SIGNATURE. Conservative on purpose — a false alarm that cries corruption
+ * over ordinary punctuation is worse than useless. Two patterns, both of
+ * which are essentially absent from well-formed English prose:
+ *   (a) alnum '?' alnum   — "na?ve", "caf?s", "don?t". A real question mark
+ *                           never sits between two word characters.
+ *   (b) ' ? ' followed by a lowercase letter — a lost em/en dash. A real
+ *                           question mark is not preceded by a space, and
+ *                           what follows one starts a new sentence.
+ * Deliberately NOT flagged: a trailing '?' after a word, '? ' before a
+ * capital, or '?' at end of string — all legitimate. This under-counts (it
+ * cannot see a mangled 'café ' where the '?' landed before a space), so the
+ * census is a floor on the damage, never an exaggeration of it. */
+int eg_text_loss_signature(const char* s) {
+    if (!s) return 0;
+    for (const char* p = s; *p; p++) {
+        if (*p != '?') continue;
+        unsigned char prev = (p == s) ? 0 : (unsigned char)p[-1];
+        unsigned char next = (unsigned char)p[1];
+        /* (a) sandwiched between word characters. */
+        if (isalnum(prev) && isalnum(next)) return 1;
+        /* (b) spaced, with lowercase continuation — a lost dash. */
+        if (prev == ' ' && next == ' ' && islower((unsigned char)p[2])) return 1;
+    }
+    return 0;
+}

lang/runtime/engram_text.h

@@ -0,0 +1,66 @@
+/* engram_text.h — text handling for the engram: query tokenization, candidate
+ * token hygiene, word-boundary matching, and the text-damage signature.
+ *
+ * WHY THIS FILE EXISTS
+ * --------------------
+ * These functions lived in el_runtime.c, which is a 2026-05-03 build shim that
+ * was scheduled for deletion, never retired, and grew to 20,527 lines. They do
+ * not belong there: they touch no EL value type and no engram store type. They
+ * are plain C over <ctype.h>/<string.h> operating on char buffers, and they are
+ * a concern of their own — so they get a translation unit of their own.
+ *
+ * Adding a new text helper?  Add it HERE, not to el_runtime.c. A new .c costs
+ * exactly one line in lang/runtime/SOURCES, and every build path picks it up.
+ * Placement is a LINK-TIME concern: the compiler cannot tell which .c a symbol
+ * came from (builtin_arity is an arity guard, not a dispatch table), so a
+ * function defined here is exactly as linkable as one defined in el_runtime.c.
+ */
+#ifndef ENGRAM_TEXT_H
+#define ENGRAM_TEXT_H
+
+#include <stddef.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Max bytes per query token, including the NUL. */
+#define ENGRAM_QTOK_LEN 256
+
+/* Split q on whitespace into up to ENGRAM_MAX_QTOKENS distinct
+ * (case-insensitive) tokens. Returns the token count. Over-long tokens are
+ * truncated to ENGRAM_QTOK_LEN-1; over-count tokens are ignored. */
+int engram_tokenize_query(const char* q, char toks[][ENGRAM_QTOK_LEN], int maxtok);
+
+/* Trim leading/trailing non-alphanumerics, then accept only tokens whose core
+ * is alphanumeric plus '-' and '_' with at least 3 letters. This subsumes the
+ * quoted-title guard (2026-07-25) and the "<!--" flood (2026-08-03)
+ * structurally: markup and punctuation-bearing tokens never become
+ * candidates, rather than being blocklisted after the fact. */
+int eg_st_clean_token(const char* raw, size_t rawlen, char* out, size_t outcap);
+
+/* Word-boundary document frequency. engram_label_df uses istr_contains, i.e.
+ * SUBSTRING matching, and that is the wrong estimator for term specificity on
+ * short tokens: "them" hits inside "theme" and "anthem", "about" and "whole"
+ * come back with df 2 and 1 rather than 0. That matters here specifically
+ * because the min_df floor is what rejects English function words, and it can
+ * only do that job if their df is honestly zero. Substring df quietly handed
+ * them a survival ticket. Measured on the live store before this fix, "whole"
+ * (df=1, idf=8.76) and "about" (df=2, idf=8.36) were outscoring real topical
+ * terms and losing only on position — one node whose text happened to open
+ * with a function word would have seeded on it.
+ *
+ * engram_label_df keeps substring semantics: it is a separate published
+ * measure with existing callers, and changing it underneath them is not this
+ * change's business. */
+int eg_st_label_has_word(const char* hay, const char* word);
+
+/* Whether s carries the text-loss signature left by the \uXXXX -> '?' parser
+ * defect. Conservative by design; see engram_text.c for the full rationale. */
+int eg_text_loss_signature(const char* s);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* ENGRAM_TEXT_H */