fix(agents): stabilize sessions_spawn e2e suite

src/agents/openclaw-tools.subagents.sessions-spawn.allowlist.e2e.test.ts

@@ -1,6 +1,6 @@
 import { beforeEach, describe, expect, it } from "vitest";
-import { createOpenClawTools } from "./openclaw-tools.js";
 import "./test-helpers/fast-core-tools.js";
+import { createOpenClawTools } from "./openclaw-tools.js";
 import {
   getCallGatewayMock,
   resetSessionsSpawnConfigOverride,
@@ -9,6 +9,7 @@ import {
 import { resetSubagentRegistryForTests } from "./subagent-registry.js";
 
 const callGatewayMock = getCallGatewayMock();
+const setConfigOverride = setSessionsSpawnConfigOverride;
 
 describe("openclaw-tools: subagents (sessions_spawn allowlist)", () => {
   beforeEach(() => {

src/agents/openclaw-tools.subagents.sessions-spawn.lifecycle.e2e.test.ts

@@ -1,16 +1,117 @@
-import { beforeEach, describe, expect, it } from "vitest";
+import { beforeEach, describe, expect, it, vi } from "vitest";
 import { emitAgentEvent } from "../infra/agent-events.js";
-import { sleep } from "../utils.js";
-import { createOpenClawTools } from "./openclaw-tools.js";
 import "./test-helpers/fast-core-tools.js";
+import { createOpenClawTools } from "./openclaw-tools.js";
 import {
   getCallGatewayMock,
   resetSessionsSpawnConfigOverride,
 } from "./openclaw-tools.subagents.sessions-spawn.test-harness.js";
 import { resetSubagentRegistryForTests } from "./subagent-registry.js";
 
+vi.mock("./pi-embedded.js", () => ({
+  isEmbeddedPiRunActive: () => false,
+  isEmbeddedPiRunStreaming: () => false,
+  queueEmbeddedPiMessage: () => false,
+  waitForEmbeddedPiRunEnd: async () => true,
+}));
+
 const callGatewayMock = getCallGatewayMock();
 
+type GatewayRequest = { method?: string; params?: unknown };
+type AgentWaitCall = { runId?: string; timeoutMs?: number };
+
+function setupSessionsSpawnGatewayMock(opts: {
+  includeSessionsList?: boolean;
+  includeChatHistory?: boolean;
+  onAgentSubagentSpawn?: (params: unknown) => void;
+  onSessionsPatch?: (params: unknown) => void;
+  onSessionsDelete?: (params: unknown) => void;
+  agentWaitResult?: { status: "ok" | "timeout"; startedAt: number; endedAt: number };
+}): {
+  calls: Array<GatewayRequest>;
+  waitCalls: Array<AgentWaitCall>;
+  getChild: () => { runId?: string; sessionKey?: string };
+} {
+  const calls: Array<GatewayRequest> = [];
+  const waitCalls: Array<AgentWaitCall> = [];
+  let agentCallCount = 0;
+  let childRunId: string | undefined;
+  let childSessionKey: string | undefined;
+
+  callGatewayMock.mockImplementation(async (optsUnknown: unknown) => {
+    const request = optsUnknown as GatewayRequest;
+    calls.push(request);
+
+    if (request.method === "sessions.list" && opts.includeSessionsList) {
+      return {
+        sessions: [
+          {
+            key: "main",
+            lastChannel: "whatsapp",
+            lastTo: "+123",
+          },
+        ],
+      };
+    }
+
+    if (request.method === "agent") {
+      agentCallCount += 1;
+      const runId = `run-${agentCallCount}`;
+      const params = request.params as { lane?: string; sessionKey?: string } | undefined;
+      // Only capture the first agent call (subagent spawn, not main agent trigger)
+      if (params?.lane === "subagent") {
+        childRunId = runId;
+        childSessionKey = params?.sessionKey ?? "";
+        opts.onAgentSubagentSpawn?.(params);
+      }
+      return {
+        runId,
+        status: "accepted",
+        acceptedAt: 1000 + agentCallCount,
+      };
+    }
+
+    if (request.method === "agent.wait") {
+      const params = request.params as AgentWaitCall | undefined;
+      waitCalls.push(params ?? {});
+      const res = opts.agentWaitResult ?? { status: "ok", startedAt: 1000, endedAt: 2000 };
+      return {
+        runId: params?.runId ?? "run-1",
+        ...res,
+      };
+    }
+
+    if (request.method === "sessions.patch") {
+      opts.onSessionsPatch?.(request.params);
+      return { ok: true };
+    }
+
+    if (request.method === "sessions.delete") {
+      opts.onSessionsDelete?.(request.params);
+      return { ok: true };
+    }
+
+    if (request.method === "chat.history" && opts.includeChatHistory) {
+      return {
+        messages: [
+          {
+            role: "assistant",
+            content: [{ type: "text", text: "done" }],
+          },
+        ],
+      };
+    }
+
+    return {};
+  });
+
+  return {
+    calls,
+    waitCalls,
+    getChild: () => ({ runId: childRunId, sessionKey: childSessionKey }),
+  };
+}
+
 describe("openclaw-tools: subagents (sessions_spawn lifecycle)", () => {
   beforeEach(() => {
     resetSessionsSpawnConfigOverride();
@@ -19,75 +120,17 @@ describe("openclaw-tools: subagents (sessions_spawn lifecycle)", () => {
   it("sessions_spawn runs cleanup flow after subagent completion", async () => {
     resetSubagentRegistryForTests();
     callGatewayMock.mockReset();
-    const calls: Array<{ method?: string; params?: unknown }> = [];
-    let agentCallCount = 0;
-    let childRunId: string | undefined;
-    let childSessionKey: string | undefined;
-    const waitCalls: Array<{ runId?: string; timeoutMs?: number }> = [];
     let patchParams: { key?: string; label?: string } = {};
 
-    callGatewayMock.mockImplementation(async (opts: unknown) => {
-      const request = opts as { method?: string; params?: unknown };
-      calls.push(request);
-      if (request.method === "sessions.list") {
-        return {
-          sessions: [
-            {
-              key: "main",
-              lastChannel: "whatsapp",
-              lastTo: "+123",
-            },
-          ],
-        };
-      }
-      if (request.method === "agent") {
-        agentCallCount += 1;
-        const runId = `run-${agentCallCount}`;
-        const params = request.params as {
-          message?: string;
-          sessionKey?: string;
-          lane?: string;
-        };
-        // Only capture the first agent call (subagent spawn, not main agent trigger)
-        if (params?.lane === "subagent") {
-          childRunId = runId;
-          childSessionKey = params?.sessionKey ?? "";
+    const ctx = setupSessionsSpawnGatewayMock({
+      includeSessionsList: true,
+      includeChatHistory: true,
+      onSessionsPatch: (params) => {
+        const rec = params as { key?: string; label?: string } | undefined;
+        if (typeof rec?.label === "string" && rec.label.trim()) {
+          patchParams = { key: rec.key, label: rec.label };
         }
-        return {
-          runId,
-          status: "accepted",
-          acceptedAt: 2000 + agentCallCount,
-        };
-      }
-      if (request.method === "agent.wait") {
-        const params = request.params as { runId?: string; timeoutMs?: number } | undefined;
-        waitCalls.push(params ?? {});
-        return {
-          runId: params?.runId ?? "run-1",
-          status: "ok",
-          startedAt: 1000,
-          endedAt: 2000,
-        };
-      }
-      if (request.method === "sessions.patch") {
-        const params = request.params as { key?: string; label?: string } | undefined;
-        patchParams = { key: params?.key, label: params?.label };
-        return { ok: true };
-      }
-      if (request.method === "chat.history") {
-        return {
-          messages: [
-            {
-              role: "assistant",
-              content: [{ type: "text", text: "done" }],
-            },
-          ],
-        };
-      }
-      if (request.method === "sessions.delete") {
-        return { ok: true };
-      }
-      return {};
+      },
     });
 
     const tool = createOpenClawTools({
@@ -108,11 +151,12 @@ describe("openclaw-tools: subagents (sessions_spawn lifecycle)", () => {
       runId: "run-1",
     });
 
-    if (!childRunId) {
+    const child = ctx.getChild();
+    if (!child.runId) {
       throw new Error("missing child runId");
     }
     emitAgentEvent({
-      runId: childRunId,
+      runId: child.runId,
       stream: "lifecycle",
       data: {
         phase: "end",
@@ -121,18 +165,21 @@ describe("openclaw-tools: subagents (sessions_spawn lifecycle)", () => {
       },
     });
 
-    await sleep(0);
-    await sleep(0);
-    await sleep(0);
+    vi.useFakeTimers();
+    try {
+      await vi.advanceTimersByTimeAsync(500);
+    } finally {
+      vi.useRealTimers();
+    }
 
-    const childWait = waitCalls.find((call) => call.runId === childRunId);
+    const childWait = ctx.waitCalls.find((call) => call.runId === child.runId);
     expect(childWait?.timeoutMs).toBe(1000);
     // Cleanup should patch the label
-    expect(patchParams.key).toBe(childSessionKey);
+    expect(patchParams.key).toBe(child.sessionKey);
     expect(patchParams.label).toBe("my-task");
 
     // Two agent calls: subagent spawn + main agent trigger
-    const agentCalls = calls.filter((c) => c.method === "agent");
+    const agentCalls = ctx.calls.filter((c) => c.method === "agent");
     expect(agentCalls).toHaveLength(2);
 
     // First call: subagent spawn
@@ -145,62 +192,25 @@ describe("openclaw-tools: subagents (sessions_spawn lifecycle)", () => {
     expect(second?.message).toContain("subagent task");
 
     // No direct send to external channel (main agent handles delivery)
-    const sendCalls = calls.filter((c) => c.method === "send");
+    const sendCalls = ctx.calls.filter((c) => c.method === "send");
     expect(sendCalls.length).toBe(0);
-    expect(childSessionKey?.startsWith("agent:main:subagent:")).toBe(true);
+    expect(child.sessionKey?.startsWith("agent:main:subagent:")).toBe(true);
   });
 
   it("sessions_spawn runs cleanup via lifecycle events", async () => {
     resetSubagentRegistryForTests();
     callGatewayMock.mockReset();
-    const calls: Array<{ method?: string; params?: unknown }> = [];
-    let agentCallCount = 0;
     let deletedKey: string | undefined;
-    let childRunId: string | undefined;
-    let childSessionKey: string | undefined;
-    const waitCalls: Array<{ runId?: string; timeoutMs?: number }> = [];
-
-    callGatewayMock.mockImplementation(async (opts: unknown) => {
-      const request = opts as { method?: string; params?: unknown };
-      calls.push(request);
-      if (request.method === "agent") {
-        agentCallCount += 1;
-        const runId = `run-${agentCallCount}`;
-        const params = request.params as {
-          message?: string;
-          sessionKey?: string;
-          channel?: string;
-          timeout?: number;
-          lane?: string;
-        };
-        if (params?.lane === "subagent") {
-          childRunId = runId;
-          childSessionKey = params?.sessionKey ?? "";
-          expect(params?.channel).toBe("discord");
-          expect(params?.timeout).toBe(1);
-        }
-        return {
-          runId,
-          status: "accepted",
-          acceptedAt: 1000 + agentCallCount,
-        };
-      }
-      if (request.method === "agent.wait") {
-        const params = request.params as { runId?: string; timeoutMs?: number } | undefined;
-        waitCalls.push(params ?? {});
-        return {
-          runId: params?.runId ?? "run-1",
-          status: "ok",
-          startedAt: 1000,
-          endedAt: 2000,
-        };
-      }
-      if (request.method === "sessions.delete") {
-        const params = request.params as { key?: string } | undefined;
-        deletedKey = params?.key;
-        return { ok: true };
-      }
-      return {};
+    const ctx = setupSessionsSpawnGatewayMock({
+      onAgentSubagentSpawn: (params) => {
+        const rec = params as { channel?: string; timeout?: number } | undefined;
+        expect(rec?.channel).toBe("discord");
+        expect(rec?.timeout).toBe(1);
+      },
+      onSessionsDelete: (params) => {
+        const rec = params as { key?: string } | undefined;
+        deletedKey = rec?.key;
+      },
     });
 
     const tool = createOpenClawTools({
@@ -221,13 +231,14 @@ describe("openclaw-tools: subagents (sessions_spawn lifecycle)", () => {
       runId: "run-1",
     });
 
-    if (!childRunId) {
+    const child = ctx.getChild();
+    if (!child.runId) {
       throw new Error("missing child runId");
     }
     vi.useFakeTimers();
     try {
       emitAgentEvent({
-        runId: childRunId,
+        runId: child.runId,
         stream: "lifecycle",
         data: {
           phase: "end",
@@ -241,10 +252,10 @@ describe("openclaw-tools: subagents (sessions_spawn lifecycle)", () => {
       vi.useRealTimers();
     }
 
-    const childWait = waitCalls.find((call) => call.runId === childRunId);
+    const childWait = ctx.waitCalls.find((call) => call.runId === child.runId);
     expect(childWait?.timeoutMs).toBe(1000);
 
-    const agentCalls = calls.filter((call) => call.method === "agent");
+    const agentCalls = ctx.calls.filter((call) => call.method === "agent");
     expect(agentCalls).toHaveLength(2);
 
     const first = agentCalls[0]?.params as
@@ -259,7 +270,7 @@ describe("openclaw-tools: subagents (sessions_spawn lifecycle)", () => {
     expect(first?.deliver).toBe(false);
     expect(first?.channel).toBe("discord");
     expect(first?.sessionKey?.startsWith("agent:main:subagent:")).toBe(true);
-    expect(childSessionKey?.startsWith("agent:main:subagent:")).toBe(true);
+    expect(child.sessionKey?.startsWith("agent:main:subagent:")).toBe(true);
 
     const second = agentCalls[1]?.params as
       | {
@@ -272,7 +283,7 @@ describe("openclaw-tools: subagents (sessions_spawn lifecycle)", () => {
     expect(second?.deliver).toBe(true);
     expect(second?.message).toContain("subagent task");
 
-    const sendCalls = calls.filter((c) => c.method === "send");
+    const sendCalls = ctx.calls.filter((c) => c.method === "send");
     expect(sendCalls.length).toBe(0);
 
     expect(deletedKey?.startsWith("agent:main:subagent:")).toBe(true);
@@ -281,65 +292,19 @@ describe("openclaw-tools: subagents (sessions_spawn lifecycle)", () => {
   it("sessions_spawn deletes session when cleanup=delete via agent.wait", async () => {
     resetSubagentRegistryForTests();
     callGatewayMock.mockReset();
-    const calls: Array<{ method?: string; params?: unknown }> = [];
-    let agentCallCount = 0;
     let deletedKey: string | undefined;
-    let childRunId: string | undefined;
-    let childSessionKey: string | undefined;
-    const waitCalls: Array<{ runId?: string; timeoutMs?: number }> = [];
-
-    callGatewayMock.mockImplementation(async (opts: unknown) => {
-      const request = opts as { method?: string; params?: unknown };
-      calls.push(request);
-      if (request.method === "agent") {
-        agentCallCount += 1;
-        const runId = `run-${agentCallCount}`;
-        const params = request.params as {
-          message?: string;
-          sessionKey?: string;
-          channel?: string;
-          timeout?: number;
-          lane?: string;
-        };
-        // Only capture the first agent call (subagent spawn, not main agent trigger)
-        if (params?.lane === "subagent") {
-          childRunId = runId;
-          childSessionKey = params?.sessionKey ?? "";
-          expect(params?.channel).toBe("discord");
-          expect(params?.timeout).toBe(1);
-        }
-        return {
-          runId,
-          status: "accepted",
-          acceptedAt: 2000 + agentCallCount,
-        };
-      }
-      if (request.method === "agent.wait") {
-        const params = request.params as { runId?: string; timeoutMs?: number } | undefined;
-        waitCalls.push(params ?? {});
-        return {
-          runId: params?.runId ?? "run-1",
-          status: "ok",
-          startedAt: 3000,
-          endedAt: 4000,
-        };
-      }
-      if (request.method === "chat.history") {
-        return {
-          messages: [
-            {
-              role: "assistant",
-              content: [{ type: "text", text: "done" }],
-            },
-          ],
-        };
-      }
-      if (request.method === "sessions.delete") {
-        const params = request.params as { key?: string } | undefined;
-        deletedKey = params?.key;
-        return { ok: true };
-      }
-      return {};
+    const ctx = setupSessionsSpawnGatewayMock({
+      includeChatHistory: true,
+      onAgentSubagentSpawn: (params) => {
+        const rec = params as { channel?: string; timeout?: number } | undefined;
+        expect(rec?.channel).toBe("discord");
+        expect(rec?.timeout).toBe(1);
+      },
+      onSessionsDelete: (params) => {
+        const rec = params as { key?: string } | undefined;
+        deletedKey = rec?.key;
+      },
+      agentWaitResult: { status: "ok", startedAt: 3000, endedAt: 4000 },
     });
 
     const tool = createOpenClawTools({
@@ -360,16 +325,20 @@ describe("openclaw-tools: subagents (sessions_spawn lifecycle)", () => {
       runId: "run-1",
     });
 
-    await sleep(0);
-    await sleep(0);
-    await sleep(0);
+    vi.useFakeTimers();
+    try {
+      await vi.advanceTimersByTimeAsync(500);
+    } finally {
+      vi.useRealTimers();
+    }
 
-    const childWait = waitCalls.find((call) => call.runId === childRunId);
+    const child = ctx.getChild();
+    const childWait = ctx.waitCalls.find((call) => call.runId === child.runId);
     expect(childWait?.timeoutMs).toBe(1000);
-    expect(childSessionKey?.startsWith("agent:main:subagent:")).toBe(true);
+    expect(child.sessionKey?.startsWith("agent:main:subagent:")).toBe(true);
 
     // Two agent calls: subagent spawn + main agent trigger
-    const agentCalls = calls.filter((call) => call.method === "agent");
+    const agentCalls = ctx.calls.filter((call) => call.method === "agent");
     expect(agentCalls).toHaveLength(2);
 
     // First call: subagent spawn
@@ -382,7 +351,7 @@ describe("openclaw-tools: subagents (sessions_spawn lifecycle)", () => {
     expect(second?.deliver).toBe(true);
 
     // No direct send to external channel (main agent handles delivery)
-    const sendCalls = calls.filter((c) => c.method === "send");
+    const sendCalls = ctx.calls.filter((c) => c.method === "send");
     expect(sendCalls.length).toBe(0);
 
     // Session should be deleted
@@ -446,9 +415,12 @@ describe("openclaw-tools: subagents (sessions_spawn lifecycle)", () => {
       runId: "run-1",
     });
 
-    await sleep(0);
-    await sleep(0);
-    await sleep(0);
+    vi.useFakeTimers();
+    try {
+      await vi.advanceTimersByTimeAsync(500);
+    } finally {
+      vi.useRealTimers();
+    }
 
     const mainAgentCall = calls
       .filter((call) => call.method === "agent")

src/agents/openclaw-tools.subagents.sessions-spawn.model.e2e.test.ts

@@ -271,7 +271,9 @@ describe("openclaw-tools: subagents (sessions_spawn model + thinking)", () => {
       modelApplied: true,
     });
 
-    const patchCall = calls.find((call) => call.method === "sessions.patch");
+    const patchCall = calls.find(
+      (call) => call.method === "sessions.patch" && (call.params as { model?: string })?.model,
+    );
     expect(patchCall?.params).toMatchObject({
       model: "opencode/claude",
     });
@@ -287,7 +289,11 @@ describe("openclaw-tools: subagents (sessions_spawn model + thinking)", () => {
       const request = opts as { method?: string; params?: unknown };
       calls.push(request);
       if (request.method === "sessions.patch") {
-        throw new Error("invalid model: bad-model");
+        const params = request.params as { model?: unknown } | undefined;
+        if (typeof params?.model === "string" && params.model.trim()) {
+          throw new Error("invalid model: bad-model");
+        }
+        return { ok: true };
       }
       if (request.method === "agent") {
         agentCallCount += 1;

src/agents/tools/sessions-spawn-tool.ts

@@ -28,6 +28,7 @@ const SessionsSpawnToolSchema = Type.Object({
   model: Type.Optional(Type.String()),
   thinking: Type.Optional(Type.String()),
   runTimeoutSeconds: Type.Optional(Type.Number({ minimum: 0 })),
+  timeoutSeconds: Type.Optional(Type.Number({ minimum: 0 })),
   cleanup: optionalStringEnum(["delete", "keep"] as const),
 });
 
@@ -97,10 +98,14 @@ export function createSessionsSpawnTool(opts?: {
       });
       // Default to 0 (no timeout) when omitted. Sub-agent runs are long-lived
       // by default and should not inherit the main agent 600s timeout.
+      const legacyTimeoutSeconds =
+        typeof params.timeoutSeconds === "number" && Number.isFinite(params.timeoutSeconds)
+          ? Math.max(0, Math.floor(params.timeoutSeconds))
+          : undefined;
       const runTimeoutSeconds =
         typeof params.runTimeoutSeconds === "number" && Number.isFinite(params.runTimeoutSeconds)
           ? Math.max(0, Math.floor(params.runTimeoutSeconds))
-          : 0;
+          : (legacyTimeoutSeconds ?? 0);
       let modelWarning: string | undefined;
       let modelApplied = false;