fix: clean up infer MCP runtimes

CHANGELOG.md

@@ -17,6 +17,7 @@ Docs: https://docs.openclaw.ai
 - Telegram/webhook: acknowledge validated webhook updates before running bot middleware, keeping slow agent turns from tripping Telegram delivery retries while preserving per-chat processing lanes. Fixes #71392.
 - MCP: retire one-shot embedded bundled MCP runtimes at run end, skip bundle-MCP startup when a runtime tool allowlist cannot reach bundle-MCP tools, and add `mcp.sessionIdleTtlMs` idle eviction for leaked session runtimes. Fixes #71106, #71110, #70389, and #70808.
 - MCP/config reload: hot-apply `mcp.*` changes by disposing cached session MCP runtimes, and dispose bundled MCP runtimes during gateway shutdown so removed `mcp.servers` entries reap child processes promptly. Fixes #60656.
+- Infer/MCP: treat `openclaw infer model run` as a one-shot agent turn for bundled MCP lifecycle cleanup, so local and gateway infer runs do not keep MCP stdio children alive after the result is returned. Fixes #71457.
 - Gateway/restart continuation: durably hand restart continuations to a session-delivery queue before deleting the restart sentinel, recover queued continuation work after crashy restarts, and fall back to a session-only wake when no channel route survives reboot. (#70780) Thanks @fuller-stack-dev.
 - Agents/tool-result pruning: harden the tool-result character estimator and context-pruning loops against malformed `{ type: "text" }` blocks created by void or undefined tool handler results, serializing non-string text payloads for size accounting so they cannot bypass trimming as zero-sized. Fixes #34979. (#51267) Thanks @cgdusek.
 - Daemon/service-env: add Nix Home Manager profile bin directories to generated gateway service PATHs on macOS and Linux, honoring `NIX_PROFILES` right-to-left precedence and falling back to `~/.nix-profile/bin` when unset. Fixes #44402. (#59935) Thanks @jerome-benoit.

src/cli/capability-cli.test.ts

@@ -360,6 +360,37 @@ describe("capability cli", () => {
     );
   });
 
+  it("cleans up bundled MCP runtimes for local model runs", async () => {
+    await runRegisteredCli({
+      register: registerCapabilityCli as (program: Command) => void,
+      argv: ["capability", "model", "run", "--prompt", "hello", "--json"],
+    });
+
+    expect(mocks.agentCommand).toHaveBeenCalledWith(
+      expect.objectContaining({
+        cleanupBundleMcpOnRunEnd: true,
+      }),
+      expect.anything(),
+      expect.anything(),
+    );
+  });
+
+  it("requests bundled MCP runtime cleanup for gateway model runs", async () => {
+    await runRegisteredCli({
+      register: registerCapabilityCli as (program: Command) => void,
+      argv: ["capability", "model", "run", "--prompt", "hello", "--gateway", "--json"],
+    });
+
+    expect(mocks.callGateway).toHaveBeenCalledWith(
+      expect.objectContaining({
+        method: "agent",
+        params: expect.objectContaining({
+          cleanupBundleMcpOnRunEnd: true,
+        }),
+      }),
+    );
+  });
+
   it("defaults tts status to gateway transport", async () => {
     await runRegisteredCli({
       register: registerCapabilityCli as (program: Command) => void,

src/cli/capability-cli.ts

@@ -530,6 +530,7 @@ async function runModelRun(params: {
         agentId,
         model: params.model,
         json: false,
+        cleanupBundleMcpOnRunEnd: true,
       },
       {
         ...defaultRuntime,
@@ -565,6 +566,7 @@ async function runModelRun(params: {
       message: params.prompt,
       provider,
       model,
+      cleanupBundleMcpOnRunEnd: true,
       idempotencyKey: randomIdempotencyKey(),
     },
     expectFinal: true,