From 716d9e09657eb4e156c4cb35560e8372253de243 Mon Sep 17 00:00:00 2001
From: teamchong <25894545+teamchong@users.noreply.github.com>
Date: Wed, 17 Jun 2026 10:44:46 -0400
Subject: [PATCH] test: cap corpus L0 test to an 8MB per-file prefix
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The real-corpus reflow check read whole transcript files; on a large ~/.claude/projects (multi-hundred-MB files) that blew the 30s timeout and aborted 'pnpm test' (hence prepublishOnly). Read only the first 8MB per file — enough for the per-file sample; a truncated trailing line just fails JSON.parse and is skipped. Corpus test now runs in ~5s.
---
 tests/reflow.test.ts | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/tests/reflow.test.ts b/tests/reflow.test.ts
index d9fc1e6..c98f1b1 100644
--- a/tests/reflow.test.ts
+++ b/tests/reflow.test.ts
@@ -14,7 +14,7 @@
  */
 
 import { describe, expect, it } from 'vitest';
-import { readdirSync, readFileSync, statSync, existsSync } from 'node:fs';
+import { readdirSync, readFileSync, statSync, existsSync, openSync, readSync, closeSync } from 'node:fs';
 import { join, resolve } from 'node:path';
 import { homedir } from 'node:os';
 import {
@@ -536,7 +536,21 @@ describe('reflow L0 contract – real corpus', () => {
       if (textsChecked >= MAX_TOTAL) break;
       let rawContent: string;
       try {
-        rawContent = readFileSync(filePath, 'utf-8');
+        // Read only a prefix, not the whole file: this corpus can contain
+        // multi-hundred-MB transcripts and we only need MAX_TEXTS_PER_FILE
+        // blocks per file. Whole-file reads here blew the 30s budget on large
+        // ~/.claude dirs. 8 MB is plenty for the per-file sample; a truncated
+        // trailing line just fails JSON.parse below and is skipped.
+        const CAP_BYTES = 8 * 1024 * 1024;
+        const toRead = Math.min(statSync(filePath).size, CAP_BYTES);
+        const fd = openSync(filePath, 'r');
+        try {
+          const buf = Buffer.allocUnsafe(toRead);
+          const n = readSync(fd, buf, 0, toRead, 0);
+          rawContent = buf.toString('utf-8', 0, n);
+        } finally {
+          closeSync(fd);
+        }
       } catch {
         continue; // unreadable — skip
       }