Merge remote-tracking branch 'origin/main' into garrytan/retention-cohorts

# Conflicts:
#	CHANGELOG.md
#	VERSION
#	package.json
This commit is contained in:
Garry Tan
2026-06-24 07:17:35 -07:00
53 changed files with 2381 additions and 250 deletions
+34 -2
View File
@@ -31,20 +31,52 @@ if [ -z "$SUPABASE_URL" ] || [ -z "$ANON_KEY" ]; then
fi
# ─── Fetch aggregated stats from edge function ────────────────
DATA="$(curl -sf --max-time 15 \
# HTTP status captured (#1947): a backend failure must read as "unknown",
# never as a healthy "Weekly active installs: 0".
TMPBODY="$(mktemp)"
trap 'rm -f "$TMPBODY"' EXIT
HTTP_CODE="$(curl -s --max-time 15 -w '%{http_code}' -o "$TMPBODY" \
"${SUPABASE_URL}/functions/v1/community-pulse" \
-H "apikey: ${ANON_KEY}" \
2>/dev/null || echo "{}")"
2>/dev/null || true)"
# curl prints its own 000 before a non-zero exit — a `|| echo` here would
# double it to "000000" in user-facing output. Normalize to the last 3 chars.
HTTP_CODE="$(printf '%s' "$HTTP_CODE" | tr -d '[:space:]' | tail -c 3)"
[ -n "$HTTP_CODE" ] || HTTP_CODE="000"
DATA="$(cat "$TMPBODY" 2>/dev/null || echo "")"
echo "gstack community dashboard"
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo ""
if [ "$HTTP_CODE" != "200" ] || [ -z "$DATA" ] || ! printf '%s' "$DATA" | grep -q '"weekly_active"'; then
echo "Community stats: unknown — backend error (HTTP ${HTTP_CODE})"
echo ""
echo "For local analytics: gstack-analytics"
exit 0
fi
# ─── Weekly active installs ──────────────────────────────────
WEEKLY="$(echo "$DATA" | grep -o '"weekly_active":[0-9]*' | grep -o '[0-9]*' || echo "0")"
CHANGE="$(echo "$DATA" | grep -o '"change_pct":[0-9-]*' | grep -o '[0-9-]*' || echo "0")"
echo "Weekly active installs: ${WEEKLY}"
# Marker check: jq when available (whitespace/reserialization-proof); the
# grep fallback tolerates optional whitespace around the colon.
_STALE="false"
if command -v jq >/dev/null 2>&1; then
_MARKER="$(printf '%s' "$DATA" | jq -r '.status // empty' 2>/dev/null)"
_STALE="$(printf '%s' "$DATA" | jq -r '.stale // false' 2>/dev/null)"
else
_MARKER="$(printf '%s' "$DATA" | grep -Eq '"status"[[:space:]]*:[[:space:]]*"ok"' && echo ok || true)"
fi
if [ "$_MARKER" != "ok" ]; then
echo " (unverified — legacy backend response; deploy the latest community-pulse for verified figures)"
elif [ "$_STALE" = "true" ]; then
# Backend serves its last good snapshot when recompute fails — real but
# frozen figures must not read as current (matches security-dashboard).
echo " (stale snapshot — backend recompute failing; figures may be out of date)"
fi
if [ "$CHANGE" -gt 0 ] 2>/dev/null; then
echo " Change: +${CHANGE}%"
elif [ "$CHANGE" -lt 0 ] 2>/dev/null; then
+4 -2
View File
@@ -411,8 +411,10 @@ case "${1:-}" in
fi
case "$STATUS" in
ok)
echo "Detected gbrain v$VERSION."
ok|timeout)
# "timeout" = slow-but-healthy engine (#1964) — same treatment as
# "ok", matching gstack-gbrain-detect --is-ok and gen-skill-docs.
echo "Detected gbrain v$VERSION (local-status: $STATUS)."
# Render brain-aware blocks INTO the global install so EVERY project's
# Claude sessions get them (other projects read SKILL.md + sections from
# ~/.claude/skills/gstack via absolute paths baked at gen time). Guards
+17 -8
View File
@@ -18,7 +18,7 @@
* "gstack_brain_sync_mode": "off"|"artifacts-only"|"full",
* "gstack_brain_git": true|false,
* "gstack_artifacts_remote": "https://..." | "",
* "gbrain_local_status": "ok"|"no-cli"|"missing-config"|"broken-config"|"broken-db",
* "gbrain_local_status": "ok"|"no-cli"|"missing-config"|"broken-config"|"broken-db"|"timeout",
* "gbrain_pooler_mode": "transaction"|"session"|null
* }
*
@@ -48,7 +48,13 @@ import { isTransactionModePooler } from "../lib/gbrain-exec";
const STATE_DIR = process.env.GSTACK_HOME || join(userHome(), ".gstack");
const SCRIPT_DIR = __dirname;
const CONFIG_BIN = join(SCRIPT_DIR, "gstack-config");
const GBRAIN_CONFIG = join(userHome(), ".gbrain", "config.json");
// Honors GBRAIN_HOME — must stay consistent with lib/gbrain-local-status's
// config resolution, or the detect JSON reports gbrain_local_status "ok"
// alongside gbrain_config_exists false for relocated-home users.
const GBRAIN_CONFIG = join(
process.env.GBRAIN_HOME || join(userHome(), ".gbrain"),
"config.json",
);
const CLAUDE_JSON = join(userHome(), ".claude.json");
function userHome(): string {
@@ -234,14 +240,17 @@ function main(): void {
process.stdout.write(JSON.stringify(out, null, 2) + "\n");
}
// --is-ok: live engine-status gate. Exits 0 iff gbrain is usable ("ok"), 1
// otherwise. Runs detection live (never reads the possibly-stale
// gbrain-detection.json), so callers — setup, bin/dev-setup, and
// `gstack-config gbrain-refresh` — can decide whether to render the gbrain
// :user variant without duplicating the JSON grep. Prints nothing on stdout.
// --is-ok: live engine-status gate. Exits 0 iff gbrain is usable ("ok", or
// "timeout" — a slow-but-healthy engine, #1964 — slow must not silently
// suppress brain features), 1 otherwise. Runs detection live (never reads
// the possibly-stale gbrain-detection.json), so callers — setup,
// bin/dev-setup, and `gstack-config gbrain-refresh` — can decide whether to
// render the gbrain :user variant without duplicating the JSON grep.
// Prints nothing on stdout.
if (process.argv.includes("--is-ok")) {
const noCache = process.env.GSTACK_DETECT_NO_CACHE === "1";
process.exit(localEngineStatus({ noCache }) === "ok" ? 0 : 1);
const status = localEngineStatus({ noCache });
process.exit(status === "ok" || status === "timeout" ? 0 : 1);
}
main();
+27 -3
View File
@@ -717,6 +717,8 @@ function dreamMarkerPid(): number | null {
* missing-config → "no local engine; run /setup-gbrain to add local PGLite"
* broken-config → "config file at ~/.gbrain/config.json is malformed; see /setup-gbrain Step 1.5"
* broken-db → "config points at unreachable DB; see /setup-gbrain Step 1.5"
* timeout → kept for Record totality; stages PROCEED on timeout (#1964)
* via the gate's warnProbeTimeout path, never this skip.
*/
function skipStageForLocalStatus(
stage: "code" | "memory" | "dream",
@@ -731,6 +733,8 @@ function skipStageForLocalStatus(
"config at ~/.gbrain/config.json is malformed; see /setup-gbrain Step 1.5",
"broken-db":
"config points at unreachable DB; see /setup-gbrain Step 1.5",
"timeout":
"engine probe timed out; raise GSTACK_GBRAIN_PROBE_TIMEOUT_MS if your pooler is slow",
};
const reason = reasons[status as Exclude<LocalEngineStatus, "ok">];
return {
@@ -742,6 +746,20 @@ function skipStageForLocalStatus(
};
}
/**
* "timeout" means the probe hit its deadline with no recognized error — the
* engine is most likely healthy but slow (#1964: cold pooler connections
* measured at 6.9-10.7s). Stages proceed; a genuinely-dead engine surfaces
* its REAL error at the first actual operation instead of a false
* "config malformed" skip.
*/
function warnProbeTimeout(stage: "code" | "memory" | "dream"): void {
process.stderr.write(
`[gstack-gbrain-sync] ${stage}: engine probe timed out — proceeding anyway; ` +
`raise GSTACK_GBRAIN_PROBE_TIMEOUT_MS if your pooler is slow\n`,
);
}
async function runCodeImport(args: CliArgs): Promise<StageResult> {
const t0 = Date.now();
@@ -773,7 +791,9 @@ async function runCodeImport(args: CliArgs): Promise<StageResult> {
// when the local DB is dead. Skipped on --dry-run (above) since dry-run
// never actually probes anything.
const localStatus = localEngineStatus({ noCache: false });
if (localStatus !== "ok") {
if (localStatus === "timeout") {
warnProbeTimeout("code"); // #1964: slow-but-healthy — proceed
} else if (localStatus !== "ok") {
return skipStageForLocalStatus("code", localStatus, t0);
}
@@ -1031,7 +1051,9 @@ function runMemoryIngest(args: CliArgs): StageResult {
// not ok, SKIP cleanly so brain-sync (the only stage that doesn't depend
// on local engine) still runs.
const localStatus = localEngineStatus({ noCache: false });
if (localStatus !== "ok") {
if (localStatus === "timeout") {
warnProbeTimeout("memory"); // #1964: slow-but-healthy — proceed
} else if (localStatus !== "ok") {
return skipStageForLocalStatus("memory", localStatus, t0);
}
@@ -1193,7 +1215,9 @@ export async function runDream(args: CliArgs): Promise<StageResult> {
}
const localStatus = localEngineStatus({ noCache: false });
if (localStatus !== "ok") {
if (localStatus === "timeout") {
warnProbeTimeout("dream"); // #1964: slow-but-healthy — proceed
} else if (localStatus !== "ok") {
return skipStageForLocalStatus("dream", localStatus, t0);
}
+19 -3
View File
@@ -7,13 +7,24 @@
# by gstack-learnings-search ("latest winner" per key+type).
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
# Windows git-bash (#1950): pwd yields a POSIX path (/c/Users/...), which Bun
# on Windows cannot resolve as an ES module specifier in the import below.
# cygpath -m converts to C:/Users/... which Bun accepts.
case "$(uname -s)" in
MINGW*|MSYS*|CYGWIN*) command -v cygpath >/dev/null 2>&1 && SCRIPT_DIR="$(cygpath -m "$SCRIPT_DIR")" ;;
esac
eval "$("$SCRIPT_DIR/gstack-slug" 2>/dev/null)"
GSTACK_HOME="${GSTACK_HOME:-$HOME/.gstack}"
mkdir -p "$GSTACK_HOME/projects/$SLUG"
INPUT="$1"
# Validate and sanitize input
# Validate and sanitize input. Errors surface (#1950): stderr is captured and
# printed on failure instead of swallowed — a silent exit 1 here cost Windows
# users every AI-logged learning.
TMPERR=$(mktemp)
trap 'rm -f "$TMPERR"' EXIT
set +e
VALIDATED=$(printf '%s' "$INPUT" | bun -e "
import { hasInjection } from '$SCRIPT_DIR/../lib/jsonl-store.ts';
const raw = await Bun.stdin.text();
@@ -63,9 +74,14 @@ if (!j.ts) j.ts = new Date().toISOString();
j.trusted = j.source === 'user-stated';
console.log(JSON.stringify(j));
" 2>/dev/null)
" 2>"$TMPERR")
VALIDATE_RC=$?
set -e
if [ $? -ne 0 ] || [ -z "$VALIDATED" ]; then
if [ $VALIDATE_RC -ne 0 ] || [ -z "$VALIDATED" ]; then
if [ -s "$TMPERR" ]; then
cat "$TMPERR" >&2
fi
exit 1
fi
+13 -17
View File
@@ -27,6 +27,12 @@
# Append-only JSONL. Dedup is at read time in gstack-question-sensitivity --read-log.
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
# Windows git-bash (#1950): pwd yields a POSIX path (/c/Users/...), which Bun
# on Windows cannot resolve as an ES module specifier in bun -e imports.
# cygpath -m converts to C:/Users/... which Bun accepts.
case "$(uname -s)" in
MINGW*|MSYS*|CYGWIN*) command -v cygpath >/dev/null 2>&1 && SCRIPT_DIR="$(cygpath -m "$SCRIPT_DIR")" ;;
esac
eval "$("$SCRIPT_DIR/gstack-slug" 2>/dev/null)"
# GSTACK_STATE_ROOT takes precedence over GSTACK_HOME (test isolation per D16).
GSTACK_HOME="${GSTACK_STATE_ROOT:-${GSTACK_HOME:-$HOME/.gstack}}"
@@ -39,6 +45,7 @@ TMPERR=$(mktemp)
trap 'rm -f "$TMPERR"' EXIT
set +e
VALIDATED=$(printf '%s' "$INPUT" | bun -e "
import { hasInjection } from '$SCRIPT_DIR/../lib/jsonl-store.ts';
const path = require('path');
const raw = await Bun.stdin.text();
let j;
@@ -104,23 +111,12 @@ if (j.question_summary.includes('\n')) {
j.question_summary = j.question_summary.replace(/\n+/g, ' ');
}
// Injection defense on the summary — same patterns as learnings-log.
const INJECTION_PATTERNS = [
/ignore\s+(all\s+)?previous\s+(instructions|context|rules)/i,
/you\s+are\s+now\s+/i,
/always\s+output\s+no\s+findings/i,
/skip\s+(all\s+)?(security|review|checks)/i,
/override[:\s]/i,
/\bsystem\s*:/i,
/\bassistant\s*:/i,
/\buser\s*:/i,
/do\s+not\s+(report|flag|mention)/i,
];
for (const pat of INJECTION_PATTERNS) {
if (pat.test(j.question_summary)) {
process.stderr.write('gstack-question-log: question_summary contains suspicious instruction-like content, rejected\n');
process.exit(1);
}
// Injection defense on the summary — shared audited list (lib/jsonl-store.ts),
// same source of truth as learnings-log and decision-log. The previous local
// duplicate drifted (#1934): pattern fixes to the lib never propagated here.
if (hasInjection(j.question_summary)) {
process.stderr.write('gstack-question-log: question_summary contains suspicious instruction-like content, rejected\n');
process.exit(1);
}
// Registry lookup for category + door_type enrichment.
+55 -2
View File
@@ -35,11 +35,41 @@ const ZERO = /^0+$/;
// The canonical empty-tree object; diffing against it yields all content as added.
const EMPTY_TREE = "4b825dc642cb6eb9a060e54bf8d69288fbee4904";
/**
* Permissive git for legitimately-fallible PROBES (symbolic-ref, rev-parse,
* merge-base) where a non-zero exit is normal control flow. The DIFF call
* must NOT use this — see gitStrict (#1946 fail-closed).
*/
function git(args: string[]): string {
const r = spawnSync("git", args, { encoding: "utf8", maxBuffer: 64 * 1024 * 1024 });
return r.status === 0 ? (r.stdout ?? "") : "";
}
/**
* Fail-closed git for the diff that decides whether the push is scanned
* (#1946). status !== 0 covers repo errors; status === null covers a killed
* process AND maxBuffer overflow — the oversized-diff case is exactly where
* a large secret-bearing blob is most likely, so "couldn't read the diff"
* must block, not silently allow.
*/
function gitStrict(args: string[]): string {
const r = spawnSync("git", args, { encoding: "utf8", maxBuffer: 64 * 1024 * 1024 });
// status !== 0 covers BOTH a non-zero exit AND null (process killed by a
// signal or maxBuffer overflow — null !== 0 is true).
if (r.status !== 0) {
throw new Error(
`git ${args[0]} failed (status=${r.status ?? "killed/overflow"}): ${(r.stderr ?? "").slice(0, 300)}`,
);
}
return r.stdout ?? "";
}
/** True when the object exists in the local odb (cat-file -e signals via exit code). */
function objectExists(sha: string): boolean {
const r = spawnSync("git", ["cat-file", "-e", sha], { encoding: "utf8" });
return r.status === 0;
}
function defaultRemoteBranch(): string {
// origin/HEAD → origin/main, fall back to main/master.
const sym = git(["symbolic-ref", "refs/remotes/origin/HEAD"]).trim();
@@ -59,13 +89,22 @@ function addedLinesFor(localSha: string, remoteSha: string): string {
// branch content is scanned as added — fail-safe (scans more, never less).
const base = git(["merge-base", localSha, defaultRemoteBranch()]).trim();
range = base ? `${base}..${localSha}` : `${EMPTY_TREE}..${localSha}`;
} else if (!objectExists(remoteSha)) {
// Remote tip object absent locally (shallow clone, force-push without a
// prior fetch, CI checkout): remote..local can't resolve. Fall back to
// the merge-base/empty-tree path — scans MORE, never less — instead of
// hard-blocking a legitimate push (adversarial review finding 8).
const base = git(["merge-base", localSha, defaultRemoteBranch()]).trim();
range = base ? `${base}..${localSha}` : `${EMPTY_TREE}..${localSha}`;
} else {
// Existing branch (incl. force-push): net new content remote..local.
range = `${remoteSha}..${localSha}`;
}
// -U0: only changed lines; we keep lines starting with '+' (added), drop the
// +++ file header. Unified diff added lines start with a single '+'.
const diff = git(["diff", "--unified=0", "--no-color", range]);
// Strict (#1946): a failed diff used to return "" and the push sailed
// through unscanned — fail open on the exact path the guard exists for.
const diff = gitStrict(["diff", "--unified=0", "--no-color", range]);
const added: string[] = [];
for (const line of diff.split("\n")) {
if (line.startsWith("+") && !line.startsWith("+++")) {
@@ -108,7 +147,21 @@ function main() {
for (const [, localSha, , remoteSha] of refs) {
if (!localSha || ZERO.test(localSha)) continue; // branch delete → nothing pushed
const added = addedLinesFor(localSha, remoteSha || "0");
let added: string;
try {
added = addedLinesFor(localSha, remoteSha || "0");
} catch (err) {
// Fail CLOSED (#1946): if we can't compute the pushed diff we can't
// scan it, and unscanned-but-allowed is the failure mode this hook
// exists to prevent.
process.stderr.write(
"\n⛔ gstack-redact-prepush BLOCKED the push — could not compute the pushed diff, " +
"so it cannot be scanned for credentials.\n" +
` (${err instanceof Error ? err.message.split("\n")[0] : String(err)})\n` +
"Bypass if you're sure: GSTACK_REDACT_PREPUSH=skip git push (or git push --no-verify)\n",
);
process.exit(1);
}
if (!added.trim()) continue;
// Visibility doesn't change HIGH behavior; pass private so nothing is treated
// as public-strict (HIGH blocks regardless either way).
+75 -34
View File
@@ -41,28 +41,52 @@ if [ -z "$SUPABASE_URL" ] || [ -z "$ANON_KEY" ]; then
exit 0
fi
DATA="$(curl -sf --max-time 15 \
# Fetch with the HTTP status captured (#1947). A backend failure must read
# as "unknown", never as a healthy "0 attacks" — fake zeros on a security
# surface are indistinguishable from good news.
TMPBODY="$(mktemp)"
trap 'rm -f "$TMPBODY"' EXIT
HTTP_CODE="$(curl -s --max-time 15 -w '%{http_code}' -o "$TMPBODY" \
"${SUPABASE_URL}/functions/v1/community-pulse" \
-H "apikey: ${ANON_KEY}" \
2>/dev/null || echo "{}")"
2>/dev/null || true)"
# curl prints its own 000 before a non-zero exit — a `|| echo` here would
# double it to "000000" in user-facing output. Normalize to the last 3 chars.
HTTP_CODE="$(printf '%s' "$HTTP_CODE" | tr -d '[:space:]' | tail -c 3)"
[ -n "$HTTP_CODE" ] || HTTP_CODE="000"
DATA="$(cat "$TMPBODY" 2>/dev/null || echo "")"
# Extract the security section. Prefer jq for brace-balanced parsing of
# nested arrays/objects (top_attack_domains etc.). Fall back to regex if
# jq isn't installed — the regex is lossy but the dashboard degrades
# gracefully to "0 attacks" rather than misreporting numbers.
if command -v jq >/dev/null 2>&1; then
SEC_SECTION="$(echo "$DATA" | jq -rc '.security // empty | "\"security\":\(.)"' 2>/dev/null || echo "")"
else
SEC_SECTION="$(echo "$DATA" | grep -o '"security":{[^}]*}' 2>/dev/null || echo "")"
# Classify the response:
# ok — 200 from the new backend (carries "status":"ok"); figures authoritative
# legacy — 200 with a security section but no marker (pre-#1947 backend);
# figures shown but flagged unverified (old backend masked errors as zeros)
# unknown — non-200 / network failure / error body / missing section / no jq
STATE="ok"
REASON=""
if [ "$HTTP_CODE" != "200" ] || [ -z "$DATA" ]; then
STATE="unknown"; REASON="backend_error"
elif ! command -v jq >/dev/null 2>&1; then
# No lossy-grep fallback: the old regex broke on nested arrays and
# under-reported attacks as zero. Without jq the honest answer is unknown.
STATE="unknown"; REASON="jq_missing"
elif ! echo "$DATA" | jq -e '.security' >/dev/null 2>&1; then
STATE="unknown"; REASON="backend_error"
elif [ "$(echo "$DATA" | jq -r '.status // empty' 2>/dev/null)" != "ok" ]; then
STATE="legacy"
fi
if [ "$JSON_MODE" = "1" ]; then
# Machine-readable — echo the whole security section (or empty object)
if [ -n "$SEC_SECTION" ]; then
echo "{${SEC_SECTION}}"
else
echo '{"security":{"attacks_last_7_days":0,"top_attack_domains":[],"top_attack_layers":[],"verdict_distribution":[]}}'
fi
case "$STATE" in
unknown)
echo "{\"security\":null,\"status\":\"unknown\",\"reason\":\"${REASON}\"}"
;;
legacy)
echo "$DATA" | jq -c '{security: .security, status: "legacy_unverified"}'
;;
ok)
echo "$DATA" | jq -c '{security: .security, status: "ok", stale: (.stale // false)}'
;;
esac
exit 0
fi
@@ -71,47 +95,64 @@ echo "gstack security dashboard"
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo ""
TOTAL="$(echo "$DATA" | grep -o '"attacks_last_7_days":[0-9]*' | grep -o '[0-9]*' | head -1 || echo "0")"
if [ "$STATE" = "unknown" ]; then
if [ "$REASON" = "jq_missing" ]; then
echo "Attacks detected last 7 days: unknown — install jq for exact figures"
else
echo "Attacks detected last 7 days: unknown — backend error (HTTP ${HTTP_CODE})"
fi
echo ""
echo "Your local log: ~/.gstack/security/attempts.jsonl"
echo "Your telemetry mode: $(${GSTACK_DIR}/bin/gstack-config get telemetry 2>/dev/null || echo unknown)"
exit 0
fi
# jq is guaranteed here (jq-missing classified as unknown above). The old
# grep chain matched the digit 7 inside "attacks_last_7_days" itself and
# misreported every count as 7.
TOTAL="$(echo "$DATA" | jq -r '.security.attacks_last_7_days // 0' 2>/dev/null || echo "0")"
echo "Attacks detected last 7 days: ${TOTAL}"
if [ "$TOTAL" = "0" ]; then
if [ "$STATE" = "legacy" ]; then
echo " (unverified — legacy backend response; deploy the latest community-pulse for verified figures)"
elif [ "$(echo "$DATA" | jq -r '.stale // false' 2>/dev/null)" = "true" ]; then
# The backend serves its last good snapshot when recompute fails — figures
# are real but frozen. Don't present them as current.
echo " (stale snapshot — backend recompute failing; figures may be out of date)"
elif [ "$TOTAL" = "0" ]; then
echo " (No attack attempts reported by the community yet. Good news.)"
fi
echo ""
# Top attacked domains — parse objects inside top_attack_domains array
DOMAINS="$(echo "$DATA" | sed -n 's/.*"top_attack_domains":\(\[[^]]*\]\).*/\1/p' | head -1)"
if [ -n "$DOMAINS" ] && [ "$DOMAINS" != "[]" ]; then
# Array sections — jq is guaranteed past the state gate; the old sed/grep
# parsing truncated at the first ']' and dropped entries on any nesting
# (the same bug class as the "every count is 7" TOTAL grep).
DOMAINS="$(echo "$DATA" | jq -r '.security.top_attack_domains[]? | "\(.domain)\t\(.count)"' 2>/dev/null)"
if [ -n "$DOMAINS" ]; then
echo "Top attacked domains"
echo "────────────────────"
echo "$DOMAINS" | grep -o '{[^}]*}' | head -10 | while read -r OBJ; do
DOMAIN="$(echo "$OBJ" | grep -o '"domain":"[^"]*"' | awk -F'"' '{print $4}')"
COUNT="$(echo "$OBJ" | grep -o '"count":[0-9]*' | grep -o '[0-9]*')"
printf '%s\n' "$DOMAINS" | head -10 | while IFS="$(printf '\t')" read -r DOMAIN COUNT; do
[ -n "$DOMAIN" ] && [ -n "$COUNT" ] && printf " %-40s %s attempts\n" "$DOMAIN" "$COUNT"
done
echo ""
fi
# Which layer catches attacks
LAYERS="$(echo "$DATA" | sed -n 's/.*"top_attack_layers":\(\[[^]]*\]\).*/\1/p' | head -1)"
if [ -n "$LAYERS" ] && [ "$LAYERS" != "[]" ]; then
LAYERS="$(echo "$DATA" | jq -r '.security.top_attack_layers[]? | "\(.layer)\t\(.count)"' 2>/dev/null)"
if [ -n "$LAYERS" ]; then
echo "Top detection layers"
echo "────────────────────"
echo "$LAYERS" | grep -o '{[^}]*}' | while read -r OBJ; do
LAYER="$(echo "$OBJ" | grep -o '"layer":"[^"]*"' | awk -F'"' '{print $4}')"
COUNT="$(echo "$OBJ" | grep -o '"count":[0-9]*' | grep -o '[0-9]*')"
printf '%s\n' "$LAYERS" | while IFS="$(printf '\t')" read -r LAYER COUNT; do
[ -n "$LAYER" ] && [ -n "$COUNT" ] && printf " %-28s %s\n" "$LAYER" "$COUNT"
done
echo ""
fi
# Verdict distribution
VERDICTS="$(echo "$DATA" | sed -n 's/.*"verdict_distribution":\(\[[^]]*\]\).*/\1/p' | head -1)"
if [ -n "$VERDICTS" ] && [ "$VERDICTS" != "[]" ]; then
VERDICTS="$(echo "$DATA" | jq -r '.security.verdict_distribution[]? | "\(.verdict)\t\(.count)"' 2>/dev/null)"
if [ -n "$VERDICTS" ]; then
echo "Verdict distribution"
echo "────────────────────"
echo "$VERDICTS" | grep -o '{[^}]*}' | while read -r OBJ; do
VERDICT="$(echo "$OBJ" | grep -o '"verdict":"[^"]*"' | awk -F'"' '{print $4}')"
COUNT="$(echo "$OBJ" | grep -o '"count":[0-9]*' | grep -o '[0-9]*')"
printf '%s\n' "$VERDICTS" | while IFS="$(printf '\t')" read -r VERDICT COUNT; do
[ -n "$VERDICT" ] && [ -n "$COUNT" ] && printf " %-14s %s\n" "$VERDICT" "$COUNT"
done
echo ""
+28 -1
View File
@@ -18,6 +18,12 @@
set -uo pipefail
GSTACK_DIR="${GSTACK_DIR:-$(cd "$(dirname "$0")/.." && pwd)}"
SCRIPT_DIR="$GSTACK_DIR/bin"
# Windows git-bash (#1950): pwd yields a POSIX path (/c/Users/...), which Bun
# on Windows cannot resolve as an ES module specifier in bun -e imports.
case "$(uname -s)" in
MINGW*|MSYS*|CYGWIN*) command -v cygpath >/dev/null 2>&1 && SCRIPT_DIR="$(cygpath -m "$SCRIPT_DIR")" ;;
esac
STATE_DIR="${GSTACK_STATE_DIR:-$HOME/.gstack}"
ANALYTICS_DIR="$STATE_DIR/analytics"
JSONL_FILE="$ANALYTICS_DIR/skill-usage.jsonl"
@@ -177,8 +183,29 @@ BRANCH="$(json_safe "$BRANCH")"
ERR_FIELD="null"
[ -n "$ERROR_CLASS" ] && ERR_FIELD="\"$(json_safe "$ERROR_CLASS")\""
# error_message goes through the redaction engine before it touches disk
# (#1947): stack traces and failed-API errors can embed credentials, paths,
# and hostnames. Every finding span becomes <REDACTED-{id}>; the rest of the
# message survives for crash triage. The bun snippet emits a JSON-encoded
# string (quotes included) ready to drop into the printf below. FAIL CLOSED:
# if bun / the engine is unavailable, the scan errors, or the output doesn't
# look like a JSON string, the whole message becomes null — never raw.
ERR_MSG_FIELD="null"
[ -n "$ERROR_MESSAGE" ] && ERR_MSG_FIELD="\"$(printf '%s' "$ERROR_MESSAGE" | head -c 200 | sed -e 's/\\/\\\\/g' -e 's/"/\\"/g' -e 's/ /\\t/g' | tr '\n\r' ' ')\""
if [ -n "$ERROR_MESSAGE" ]; then
ERR_MSG_FIELD="$(printf '%s' "$ERROR_MESSAGE" | bun -e "
import { redactFindingSpans } from '$SCRIPT_DIR/../lib/redact-engine.ts';
const input = await Bun.stdin.text();
const out = redactFindingSpans(input, { repoVisibility: 'private' });
if (out === null) process.exit(1);
console.log(JSON.stringify(out.slice(0, 200)));
" 2>/dev/null)" || ERR_MSG_FIELD="null"
case "$ERR_MSG_FIELD" in
*"
"*) ERR_MSG_FIELD="null" ;; # embedded newline would corrupt the JSONL record
\"*\") ;; # single-line JSON string — safe to embed
*) ERR_MSG_FIELD="null" ;;
esac
fi
STEP_FIELD="null"
[ -n "$FAILED_STEP" ] && STEP_FIELD="\"$(json_safe "$FAILED_STEP")\""