From f9101a1f8e84ae59e45a7c16b0de10823743f1bb Mon Sep 17 00:00:00 2001
From: Benjamin Borbe <benjamin.borbe@gmail.com>
Date: Mon, 10 Aug 2026 14:07:48 +0200
Subject: [PATCH] fix: ast-grep-runner: use --slurpfile to avoid ARG_MAX on
 large payloads

---
 CHANGELOG.md               |  4 ++++
 scripts/ast-grep-runner.sh | 17 ++++++++---------
 2 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 301b762..56e6cdc 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -8,6 +8,10 @@ Please choose versions by [Semantic Versioning](http://semver.org/).
 * MINOR version when you add functionality in a backwards-compatible manner, and
 * PATCH version when you make backwards-compatible bug fixes.
 
+## Unreleased
+
+- fix: ast-grep-runner: pass finding payloads to `jq` via `--slurpfile` instead of `--argjson`, fixing `Argument list too long` on large result sets. Both sites moved: the per-owner merge and the final assembly. Payloads were being read out of files into shell variables and pushed back through `argv`; `jq` now reads the files directly, so payload size is irrelevant. Scales with finding count and matched-text size, not file count — reproduced with 1,956 findings from 429 files, which previously produced an **empty output file and exit 0**.
+
 ## v0.42.0
 
 - feat: golden set covers `curated-1` — 155 entries over 20 PRs, up from 42 over 5. All 115 unmatched findings from the curated-1 Opus pass were adjudicated individually: 113 new entries, plus 2 findings that turned out to be an issue the set already held, re-reported in different words, where the existing key was relaxed rather than duplicated. One issue, one entry — a duplicate is what inflated recall to a spurious `1.000` in `v0.37.0`
diff --git a/scripts/ast-grep-runner.sh b/scripts/ast-grep-runner.sh
index 84e7be2..e329e9c 100755
--- a/scripts/ast-grep-runner.sh
+++ b/scripts/ast-grep-runner.sh
@@ -297,20 +297,19 @@ for owner_file in "$FINDINGS_DIR"/*.jsonl; do
   # but owner names use '-' not '/', so the original name is preserved)
   basename_no_ext="$(basename "$owner_file" .jsonl)"
   owner_name="$basename_no_ext"
-  # Collect all findings for this owner into a JSON array
-  findings_array=$(jq -s '.' "$owner_file")
+  # Merge this owner's findings via --slurpfile, NOT --argjson.
+  # --argjson passes the whole payload through argv and dies with
+  # "Argument list too long" past ARG_MAX; --slurpfile makes jq read the
+  # file itself, so payload size is irrelevant.
   FINDINGS_JSON_TMP="$TMPDIR_WORK/fbo_tmp.json"
-  jq --arg o "$owner_name" --argjson arr "$findings_array" \
+  jq --arg o "$owner_name" --slurpfile arr "$owner_file" \
     '. + {($o): $arr}' "$FINDINGS_JSON" > "$FINDINGS_JSON_TMP" && mv "$FINDINGS_JSON_TMP" "$FINDINGS_JSON"
 done
 
-ERRORS_JSON="$(cat "$ERRORS_FILE")"
-FINDINGS_OBJ="$(cat "$FINDINGS_JSON")"
-
 jq -n \
   --argjson yamls_run "$YAMLS_RUN" \
   --argjson findings_count "$FINDINGS_COUNT" \
   --argjson elapsed_ms "$ELAPSED" \
-  --argjson findings_by_owner "$FINDINGS_OBJ" \
-  --argjson errors "$ERRORS_JSON" \
-  '{stats:{yamls_run:$yamls_run, findings_count:$findings_count, elapsed_ms:$elapsed_ms}, findings_by_owner:$findings_by_owner, errors:$errors}'
+  --slurpfile findings_by_owner_arr "$FINDINGS_JSON" \
+  --slurpfile errors_arr "$ERRORS_FILE" \
+  '{stats:{yamls_run:$yamls_run, findings_count:$findings_count, elapsed_ms:$elapsed_ms}, findings_by_owner:$findings_by_owner_arr[0], errors:$errors_arr[0]}'