feat: support bulk TaskCreate calls

README.md

@@ -57,20 +57,40 @@ The extension renders a persistent widget above the editor:
 
 ### `TaskCreate`
 
-Create a structured task. Used proactively for complex multi-step work.
+Create one structured task, or create multiple tasks in one call with `tasks`. Used proactively for complex multi-step work.
 
 | Parameter | Type | Required | Description |
 |-----------|------|----------|-------------|
-| `subject` | string | yes | Brief imperative title |
-| `description` | string | yes | Detailed context and acceptance criteria |
+| `subject` | string | yes* | Brief imperative title |
+| `description` | string | yes* | Detailed context and acceptance criteria |
 | `activeForm` | string | no | Present continuous form for spinner (e.g., "Running tests") |
 | `agentType` | string | no | Agent type for subagent execution (e.g., `"general-purpose"`, `"Explore"`) |
 | `metadata` | object | no | Arbitrary key-value pairs |
+| `tasks` | array | no* | Bulk task list. Each item accepts `subject`, `description`, `activeForm`, `agentType`, and `metadata`. |
+
+\* Provide either top-level `subject` + `description`, or a non-empty `tasks` array.
 
 ```
 → Task #1 created successfully: Fix authentication bug
 ```
 
+Bulk example:
+
+```json
+{
+  "tasks": [
+    { "subject": "Design API", "description": "Define endpoints and data contracts" },
+    { "subject": "Implement API", "description": "Build endpoints after design is approved" }
+  ]
+}
+```
+
+```
+→ Created 2 tasks successfully:
+  Task #1: Design API
+  Task #2: Implement API
+```
+
 ### `TaskList`
 
 List all tasks with status, owner, and blocked-by info.

src/index.ts

@@ -426,9 +426,12 @@ NOTE that you should not use this tool if there is only one trivial task to do.
 
 ## Task Fields
 
+TaskCreate supports either a single task using top-level fields, or multiple tasks using the \`tasks\` array.
+
 - **subject**: A brief, actionable title in imperative form (e.g., "Fix authentication bug in login flow")
 - **description**: Detailed description of what needs to be done, including context and acceptance criteria
 - **activeForm** (optional): Present continuous form shown in the spinner when the task is in_progress (e.g., "Fixing authentication bug"). If omitted, the spinner shows the subject instead.
+- **tasks** (optional): Array of task objects with the same fields for bulk creation. Use this when creating multiple related tasks at once.
 
 All tasks are created with status \`pending\`.
 
@@ -445,20 +448,52 @@ All tasks are created with status \`pending\`.
       "Use TaskList to check for available work after completing a task.",
     ],
     parameters: Type.Object({
-      subject: Type.String({ description: "A brief title for the task" }),
-      description: Type.String({ description: "A detailed description of what needs to be done" }),
+      subject: Type.Optional(Type.String({ description: "A brief title for the task" })),
+      description: Type.Optional(Type.String({ description: "A detailed description of what needs to be done" })),
       activeForm: Type.Optional(Type.String({ description: "Present continuous form shown in spinner when in_progress (e.g., 'Running tests')" })),
       agentType: Type.Optional(Type.String({ description: "Agent type for subagent execution (e.g., 'general-purpose', 'Explore'). Tasks with agentType can be started via TaskExecute." })),
       metadata: Type.Optional(Type.Record(Type.String(), Type.Any(), { description: "Arbitrary metadata to attach to the task" })),
+      tasks: Type.Optional(Type.Array(Type.Object({
+        subject: Type.String({ description: "A brief title for the task" }),
+        description: Type.String({ description: "A detailed description of what needs to be done" }),
+        activeForm: Type.Optional(Type.String({ description: "Present continuous form shown in spinner when in_progress (e.g., 'Running tests')" })),
+        agentType: Type.Optional(Type.String({ description: "Agent type for subagent execution (e.g., 'general-purpose', 'Explore'). Tasks with agentType can be started via TaskExecute." })),
+        metadata: Type.Optional(Type.Record(Type.String(), Type.Any(), { description: "Arbitrary metadata to attach to the task" })),
+      }), { description: "Create multiple tasks in one call. Each task accepts subject, description, activeForm, agentType, and metadata." })),
     }),
 
     execute(_toolCallId, params, _signal, _onUpdate, _ctx) {
       autoClear.resetBatchCountdown();
-      const meta = params.metadata ?? {};
-      if (params.agentType) meta.agentType = params.agentType;
-      const task = store.create(params.subject, params.description, params.activeForm, Object.keys(meta).length > 0 ? meta : undefined);
+      const inputTasks = params.tasks ?? (
+        params.subject && params.description
+          ? [{
+              subject: params.subject,
+              description: params.description,
+              activeForm: params.activeForm,
+              agentType: params.agentType,
+              metadata: params.metadata,
+            }]
+          : []
+      );
+
+      if (inputTasks.length === 0) {
+        throw new Error("TaskCreate requires either subject + description, or a non-empty tasks array");
+      }
+
+      const created = inputTasks.map((input) => {
+        const meta = { ...(input.metadata ?? {}) };
+        if (input.agentType) meta.agentType = input.agentType;
+        return store.create(input.subject, input.description, input.activeForm, Object.keys(meta).length > 0 ? meta : undefined);
+      });
+
       widget.update();
-      return Promise.resolve(textResult(`Task #${task.id} created successfully: ${task.subject}`));
+      if (created.length === 1) {
+        const task = created[0];
+        return Promise.resolve(textResult(`Task #${task.id} created successfully: ${task.subject}`));
+      }
+      return Promise.resolve(textResult(
+        `Created ${created.length} tasks successfully:\n${created.map(task => `Task #${task.id}: ${task.subject}`).join("\n")}`,
+      ));
     },
   });
 

test/subagent-integration.test.ts

@@ -481,6 +481,32 @@ describe("Standalone operation (no subagents extension)", () => {
     expect(result.content[0].text).toContain("Write tests");
   });
 
+  it("TaskCreate can create multiple tasks in one call", async () => {
+    const result = await mock.executeTool("TaskCreate", {
+      tasks: [
+        { subject: "Design API", description: "Define endpoints", agentType: "Explore" },
+        { subject: "Implement API", description: "Build endpoints", activeForm: "Building endpoints" },
+      ],
+    });
+
+    expect(result.content[0].text).toContain("Created 2 tasks successfully");
+    expect(result.content[0].text).toContain("Task #1: Design API");
+    expect(result.content[0].text).toContain("Task #2: Implement API");
+
+    const first = await mock.executeTool("TaskGet", { taskId: "1" });
+    expect(first.content[0].text).toContain("Metadata: {\"agentType\":\"Explore\"}");
+
+    const list = await mock.executeTool("TaskList", {});
+    expect(list.content[0].text).toContain("#1 [pending] Design API");
+    expect(list.content[0].text).toContain("#2 [pending] Implement API");
+  });
+
+  it("TaskCreate rejects calls without single-task fields or bulk tasks", async () => {
+    await expect(mock.executeTool("TaskCreate", {})).rejects.toThrow(
+      "TaskCreate requires either subject + description, or a non-empty tasks array",
+    );
+  });
+
   it("TaskList works without subagents", async () => {
     await mock.executeTool("TaskCreate", { subject: "A", description: "desc" });
     await mock.executeTool("TaskCreate", { subject: "B", description: "desc" });