Merge pull request #135 from souloss/fix/ci-flakes-brotli-rmsync

fix(test): stop viewer resources before temp-dir cleanup

Author: weiesky

history.md

@@ -2,6 +2,8 @@
 
 ## Unreleased
 
+- fix(test): **stop viewer resources before removing CLI-test temp directories** — `server-ports-busy` and `branch-server` now tear down `server.js` timers/watchers before deleting their isolated `CCV_LOG_DIR`; shared best-effort cleanup uses `fs.promises.rm` with native retries for transient `EBUSY`/`ENOTEMPTY`/`EPERM` failures.
+
 - fix(migrate): **迁移完成后仍反复提示迁移** — `pendingOf()` 仅按文件大小比对判断是否需要迁移，忽略了 `wire-v2-convert-state.json` 中的 `status: 'done'` 标记。迁移完成后活跃的 v1 日志继续增长（双写），大小不匹配导致误判为待迁移。修复：`pendingOf()` 检测到 `status === 'done'` 时直接返回无需迁移。
 
 - fix(ccswitch-import): **running cc-switch → `database is locked`** — importing from cc-switch *while it is open* failed with `导入失败（未检测到 cc-switch 或读取出错）: query failed: database is locked` because the read-only connection's first query contends with cc-switch's `BEGIN EXCLUSIVE` write lock (its real contention mode: a valid hot journal under an EXCLUSIVE transaction blocks even read-only readers, unlike `BEGIN IMMEDIATE`). The prior malformed-journal fix only caught `SQLITE_BUSY` on its own escalation path; on the main read path `BUSY` escaped to the catch-all and surfaced as the opaque `query failed: database is locked`. Fix in `server/lib/ccswitch-import.js`: detect `SQLITE_BUSY` on **every** path (the read-only open and the providers query), retry once after a 200ms backoff (cc-switch's write transactions are short — transient locks usually clear), and if still held surface the friendly `cc-switch db is locked (cc-switch may be running); retry shortly` instead of the raw wrapper. New `test/ccswitch-import.test.js` cases use a child process holding `BEGIN EXCLUSIVE` to deterministically reproduce both the held-lock (→ friendly message) and transient-lock (→ retry recovers providers) paths.

test/_helpers/rm-sync.mjs

@@ -0,0 +1,13 @@
+// Best-effort recursive removal with native retries for transient filesystem errors.
+//
+// Each caller first stops the server resources that can write into the directory.
+// fs.rm then handles transient EBUSY/ENOTEMPTY/EPERM failures with its built-in
+// retry policy. A final cleanup failure is harmless because every test uses a
+// unique directory under os.tmpdir().
+import { rm } from 'node:fs/promises';
+
+export async function rmBestEffort(dir) {
+  try {
+    await rm(dir, { recursive: true, force: true, maxRetries: 5, retryDelay: 50 });
+  } catch { /* isolated test cleanup; the OS will reap any leftover temp directory */ }
+}

test/branch-server.test.js

@@ -29,6 +29,7 @@ import { join } from 'node:path';
 import { tmpdir, networkInterfaces } from 'node:os';
 import { createRequire } from 'node:module';
 import { pathToFileURL } from 'node:url';
+import { rmBestEffort } from './_helpers/rm-sync.mjs';
 
 // ── 必须在任何拉起 findcc.js 的 import 之前设置 ──
 const tmpDir = mkdtempSync(join(tmpdir(), 'ccv-branch-srv-'));
@@ -882,7 +883,10 @@ export default {
 describeCli('server.js turn-end 状态机 / SDK export 分支', { concurrency: false }, () => {
   let mod;
   before(async () => { mod = await import('../server/server.js'); });
-  after(() => { rmSync(tmpDir, { recursive: true, force: true }); });
+  after(async () => {
+    mod.__testing.reset();
+    try { await mod.stopViewer(); } finally { await rmBestEffort(tmpDir); }
+  });
 
   it('__testing namespace 在 NODE_ENV=test 下为真实实现（非 frozen no-op）', () => {
     assert.ok(mod.__testing);

test/server-ports-busy.test.js

@@ -12,9 +12,10 @@ import { describe, it, before, after } from 'node:test';
 import { describeCli } from './_helpers/cli-tier.mjs';
 import assert from 'node:assert/strict';
 import { createServer } from 'node:net';
-import { mkdtempSync, rmSync, mkdirSync } from 'node:fs';
+import { mkdtempSync, mkdirSync } from 'node:fs';
 import { join } from 'node:path';
 import { tmpdir } from 'node:os';
+import { rmBestEffort } from './_helpers/rm-sync.mjs';
 
 const tmpDir = mkdtempSync(join(tmpdir(), 'ccv-ports-busy-'));
 mkdirSync(join(tmpDir, 'logs'), { recursive: true });
@@ -36,7 +37,7 @@ delete process.env.CCV_USE_PASSWORD;
 delete process.env.CCV_PASSWORD;
 
 describeCli('server.js startViewer exhausts the port range (portsBusy)', { concurrency: false }, () => {
-  let squatter;
+  let squatter, mod;
 
   before(async () => {
     // 占住唯一端口：监听 127.0.0.1:BUSY_PORT，让 startViewer 的 probe connect 命中。
@@ -49,12 +50,12 @@ describeCli('server.js startViewer exhausts the port range (portsBusy)', { concu
 
   after(async () => {
     await new Promise((resolve) => { try { squatter.close(() => resolve()); } catch { resolve(); } });
-    rmSync(tmpDir, { recursive: true, force: true });
+    try { await mod?.stopViewer(); } finally { await rmBestEffort(tmpDir); }
   });
 
   // ── 835-839：唯一端口被占 → probe connect 成功 → tryListen(port+1) → >MAX → resolve(null) ──
   it('startViewer resolves null when every port in the range is occupied', async () => {
-    const mod = await import('../server/server.js');
+    mod = await import('../server/server.js');
     const srv = await mod.startViewer();
     assert.equal(srv, null, 'startViewer must resolve null when the port range is exhausted');
   });