test(sandbox): cover registry migration

steipete · steipete · commit 5881b01e481c · 2026-05-03T13:18:27.000+01:00
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -17,6 +17,7 @@ Docs: https://docs.openclaw.ai
 - Plugins/update: on the beta OpenClaw update channel, default-line npm and ClawHub plugin updates try `@beta` first and fall back to default/latest when no plugin beta release exists.
 - Channels/WhatsApp: support explicit WhatsApp Channel/Newsletter `@newsletter` outbound message targets with channel session metadata instead of DM routing. Fixes #13417; carries forward the narrow outbound target idea from #13424. Thanks @vincentkoc and @agentz-manfred.
 - Exec approvals: add a tree-sitter-backed shell command explainer for future approval and command-review surfaces. (#75004) Thanks @jesse-merhi.
+- Agents/sandbox: store sandbox container and browser registry entries as per-runtime shard files, reducing unrelated session lock contention while `openclaw doctor --fix` migrates legacy monolithic registry files. (#74831) Thanks @luckylhb90.
 
 ### Fixes
 
diff --git a/docs/cli/doctor.md b/docs/cli/doctor.md
@@ -57,6 +57,7 @@ Notes:
 - Doctor warns when Codex-mode agents are configured and personal Codex CLI assets exist in the operator's Codex home. Local Codex app-server launches use isolated per-agent homes, so use `openclaw migrate codex --dry-run` to inventory assets that should be promoted deliberately.
 - Doctor warns when skills allowed for the default agent are unavailable in the current runtime environment because bins, env vars, config, or OS requirements are missing. `doctor --fix` can disable those unavailable skills with `skills.entries.<skill>.enabled=false`; install/configure the missing requirement instead when you want to keep the skill active.
 - If sandbox mode is enabled but Docker is unavailable, doctor reports a high-signal warning with remediation (`install Docker` or `openclaw config set agents.defaults.sandbox.mode off`).
+- If legacy sandbox registry files (`~/.openclaw/sandbox/containers.json` or `~/.openclaw/sandbox/browsers.json`) are present, doctor reports them; `openclaw doctor --fix` migrates valid entries into sharded registry directories and quarantines invalid legacy files.
 - If `gateway.auth.token`/`gateway.auth.password` are SecretRef-managed and unavailable in the current command path, doctor reports a read-only warning and does not write plaintext fallback credentials.
 - If channel SecretRef inspection fails in a fix path, doctor continues and reports a warning instead of exiting early.
 - After state-directory migrations, doctor warns when enabled default Telegram or Discord accounts depend on env fallback and `TELEGRAM_BOT_TOKEN` or `DISCORD_BOT_TOKEN` is unavailable to the doctor process.
diff --git a/docs/cli/sandbox.md b/docs/cli/sandbox.md
@@ -164,6 +164,15 @@ Use `openclaw sandbox recreate` to force removal of old runtimes. They are recre
 Prefer `openclaw sandbox recreate` over manual backend-specific cleanup. It uses the Gateway's runtime registry and avoids mismatches when scope or session keys change.
 </Tip>
 
+## Registry migration
+
+OpenClaw stores sandbox runtime metadata as one JSON shard per container/browser entry under the sandbox state directory. Older installs may still have monolithic legacy files:
+
+- `~/.openclaw/sandbox/containers.json`
+- `~/.openclaw/sandbox/browsers.json`
+
+Regular sandbox runtime reads do not rewrite those files. Run `openclaw doctor --fix` to migrate valid legacy entries into the sharded registry directories. Invalid legacy files are quarantined so one bad old registry cannot hide current runtime entries.
+
 ## Configuration
 
 Sandbox settings live in `~/.openclaw/openclaw.json` under `agents.defaults.sandbox` (per-agent overrides go in `agents.list[].sandbox`):
diff --git a/src/agents/sandbox/registry.test.ts b/src/agents/sandbox/registry.test.ts
@@ -172,6 +172,22 @@ async function seedContainerRegistry(entries: SandboxRegistryEntry[]) {
   await fs.writeFile(SANDBOX_REGISTRY_PATH, `${JSON.stringify({ entries }, null, 2)}\n`, "utf-8");
 }
 
+async function seedBrowserRegistry(entries: SandboxBrowserRegistryEntry[]) {
+  await fs.writeFile(
+    SANDBOX_BROWSER_REGISTRY_PATH,
+    `${JSON.stringify({ entries }, null, 2)}\n`,
+    "utf-8",
+  );
+}
+
+async function seedStaleLock(lockPath: string) {
+  await fs.writeFile(
+    lockPath,
+    `${JSON.stringify({ pid: 999_999_999, createdAt: "2000-01-01T00:00:00.000Z" })}\n`,
+    "utf-8",
+  );
+}
+
 describe("registry race safety", () => {
   it("does not migrate legacy registry files from runtime reads", async () => {
     await seedContainerRegistry([containerEntry({ containerName: "legacy-container" })]);
@@ -204,6 +220,60 @@ describe("registry race safety", () => {
     ]);
   });
 
+  it("migrates legacy container and browser registry files after explicit repair", async () => {
+    await seedContainerRegistry([
+      containerEntry({
+        containerName: "legacy-container",
+        sessionKey: "agent:legacy",
+        lastUsedAtMs: 7,
+        configHash: "legacy-container-hash",
+      }),
+    ]);
+    await seedBrowserRegistry([
+      browserEntry({
+        containerName: "legacy-browser",
+        sessionKey: "agent:legacy",
+        cdpPort: 9333,
+        noVncPort: 6081,
+        configHash: "legacy-browser-hash",
+      }),
+    ]);
+    await seedStaleLock(`${SANDBOX_REGISTRY_PATH}.lock`);
+    await seedStaleLock(`${SANDBOX_BROWSER_REGISTRY_PATH}.lock`);
+
+    await expect(migrateLegacySandboxRegistryFiles()).resolves.toEqual([
+      expect.objectContaining({ kind: "containers", status: "migrated", entries: 1 }),
+      expect.objectContaining({ kind: "browsers", status: "migrated", entries: 1 }),
+    ]);
+
+    await expect(fs.access(SANDBOX_REGISTRY_PATH)).rejects.toThrow();
+    await expect(fs.access(SANDBOX_BROWSER_REGISTRY_PATH)).rejects.toThrow();
+    await expect(fs.access(`${SANDBOX_REGISTRY_PATH}.lock`)).rejects.toThrow();
+    await expect(fs.access(`${SANDBOX_BROWSER_REGISTRY_PATH}.lock`)).rejects.toThrow();
+    await expect(readRegistry()).resolves.toEqual({
+      entries: [
+        expect.objectContaining({
+          containerName: "legacy-container",
+          backendId: "docker",
+          runtimeLabel: "legacy-container",
+          sessionKey: "agent:legacy",
+          configHash: "legacy-container-hash",
+        }),
+      ],
+    });
+    await expect(readBrowserRegistry()).resolves.toEqual({
+      entries: [
+        expect.objectContaining({
+          containerName: "legacy-browser",
+          sessionKey: "agent:legacy",
+          cdpPort: 9333,
+          noVncPort: 6081,
+          configHash: "legacy-browser-hash",
+        }),
+      ],
+    });
+  });
+
   it("does not overwrite newer sharded entries during legacy migration", async () => {
     await updateRegistry(
       containerEntry({
