Atomic engram_save + anti-clobber floor (validated, darwin build recipe) #57

Closed
tim.lingo wants to merge 1 commits from fix/engram-save-atomic-darwin into chore/live-darwin-runtime
2 changed files with 60 additions and 4 deletions
+39 -4
View File
@@ -7300,13 +7300,48 @@ el_val_t engram_save(el_val_t path) {
jb_putc(&b, '}');
}
jb_puts(&b, "]}");
FILE* f = fopen(p, "wb");
if (!f) { free(b.buf); return 0; }
/* --- Anti-clobber sparse-write floor (NTN engram clobber fix) ---------
* Refuse to overwrite an existing populated snapshot with a drastically
* smaller one. A bad boot that loaded only ~63 identity nodes must never
* be able to clobber a healthy 5000+ node snapshot, regardless of the
* upstream cause (genesis fallback, partial load, etc.). */
{
struct stat _st;
if (stat(p, &_st) == 0 && _st.st_size > 200000 &&
(uint64_t)b.len < (uint64_t)_st.st_size / 16) {
fprintf(stderr,
"[engram_save] REFUSED sparse write: new %zu bytes vs existing "
"%lld bytes (< 1/16) — protecting snapshot %s\n",
b.len, (long long)_st.st_size, p);
free(b.buf);
return 0;
}
}
/* --- Atomic write: tmp + fsync + rename ------------------------------
* Write to a sibling temp file, fsync it durable, then rename() over the
* target. rename() is atomic on POSIX, so a concurrent reader (a booting
* soul's engram_load) never observes a truncated or 0-byte snapshot
* which was the root of the genesis/clobber loop. */
size_t _plen = strlen(p);
char* _tmp = (char*)malloc(_plen + 5);
if (!_tmp) { free(b.buf); return 0; }
memcpy(_tmp, p, _plen);
memcpy(_tmp + _plen, ".tmp", 5); /* includes NUL */
FILE* f = fopen(_tmp, "wb");
if (!f) { free(_tmp); free(b.buf); return 0; }
size_t w = fwrite(b.buf, 1, b.len, f);
int wok = (w == b.len);
if (wok) { fflush(f); fsync(fileno(f)); }
fclose(f);
int ok = (w == b.len);
free(b.buf);
return ok ? 1 : 0;
if (!wok) { unlink(_tmp); free(_tmp); return 0; }
if (rename(_tmp, p) != 0) { unlink(_tmp); free(_tmp); return 0; }
free(_tmp);
return 1;
}
/* Helper: extract a string field from a JSON object substring. */
+21
View File
@@ -0,0 +1,21 @@
#!/bin/sh
# build-soul-darwin.sh — replicate `elb` on macOS/arm64 with clang.
# Proven 2026-06-16: produces a Mach-O arm64 soul that boots and serves :7770.
# The official builder `elb` ships Linux-only (CI); this lets us build + test the
# darwin soul locally (e.g. to validate the atomic engram_save fix in isolation).
#
# Usage: scripts/build-soul-darwin.sh <path-to-neuron/dist> [output-binary]
set -e
DIST="${1:?usage: build-soul-darwin.sh <neuron/dist dir> [out]}"
OUT="${2:-./neuron}"
RT="$(cd "$(dirname "$0")/.." && pwd)/lang/el-compiler/runtime"
B="$(mktemp -d)"
# elc-generated dist modules use C89-style implicit cross-module declarations that
# Apple clang rejects as errors by default; resolve at link, so downgrade them.
CFLAGS="-Wno-implicit-function-declaration -Wno-implicit-int -Wno-int-conversion -I$B -I$DIST -I$RT"
cp "$RT/el_runtime.h" "$B/"
clang -c $CFLAGS "$RT/el_runtime.c" -o "$B/el_runtime.o"
for c in "$DIST"/*.c; do clang -c $CFLAGS "$c" -o "$B/$(basename "$c" .c).o"; done
# NOTE: link *.o once — do not also list el_runtime.o separately (duplicate symbols).
clang "$B"/*.o -o "$OUT" -lcurl -lm
echo "built $OUT"