fix(background-cancel): skip notification when user explicitly cancels tasks

- Add skipNotification option to cancelTask method
- Apply skipNotification to background_cancel tool
- Prevents unwanted notifications when user cancels via tool

src/tools/background-task/tools.test.ts

@@ -328,6 +328,58 @@ describe("background_cancel", () => {
     expect(output).toContain("| `task-a` | running task | running | `ses-a` |")
     expect(output).toContain("| `task-b` | pending task | pending | (not started) |")
   })
+
+  test("passes skipNotification: true to cancelTask to prevent deadlock", async () => {
+    // #given
+    const task = createTask({ id: "task-1", status: "running" })
+    const cancelOptions: Array<{ taskId: string; options: unknown }> = []
+    const manager = {
+      getTask: (id: string) => (id === task.id ? task : undefined),
+      getAllDescendantTasks: () => [task],
+      cancelTask: async (taskId: string, options?: unknown) => {
+        cancelOptions.push({ taskId, options })
+        task.status = "cancelled"
+        return true
+      },
+    } as unknown as BackgroundManager
+    const client = { session: { abort: async () => ({}) } } as BackgroundCancelClient
+    const tool = createBackgroundCancel(manager, client)
+
+    // #when - cancel all tasks
+    await tool.execute({ all: true }, mockContext)
+
+    // #then - skipNotification should be true to prevent self-deadlock
+    expect(cancelOptions).toHaveLength(1)
+    expect(cancelOptions[0].options).toEqual(
+      expect.objectContaining({ skipNotification: true })
+    )
+  })
+
+  test("passes skipNotification: true when cancelling single task", async () => {
+    // #given
+    const task = createTask({ id: "task-1", status: "running" })
+    const cancelOptions: Array<{ taskId: string; options: unknown }> = []
+    const manager = {
+      getTask: (id: string) => (id === task.id ? task : undefined),
+      getAllDescendantTasks: () => [task],
+      cancelTask: async (taskId: string, options?: unknown) => {
+        cancelOptions.push({ taskId, options })
+        task.status = "cancelled"
+        return true
+      },
+    } as unknown as BackgroundManager
+    const client = { session: { abort: async () => ({}) } } as BackgroundCancelClient
+    const tool = createBackgroundCancel(manager, client)
+
+    // #when - cancel single task
+    await tool.execute({ taskId: task.id }, mockContext)
+
+    // #then - skipNotification should be true
+    expect(cancelOptions).toHaveLength(1)
+    expect(cancelOptions[0].options).toEqual(
+      expect.objectContaining({ skipNotification: true })
+    )
+  })
 })
 type BackgroundOutputMessage = {
   id?: string

src/tools/background-task/tools.ts

@@ -642,6 +642,7 @@ export function createBackgroundCancel(manager: BackgroundManager, client: Backg
             const cancelled = await manager.cancelTask(task.id, {
               source: "background_cancel",
               abortSession: originalStatus === "running",
+              skipNotification: true,
             })
             if (!cancelled) continue
             cancelledInfo.push({
@@ -690,6 +691,7 @@ Only running or pending tasks can be cancelled.`
         const cancelled = await manager.cancelTask(task.id, {
           source: "background_cancel",
           abortSession: task.status === "running",
+          skipNotification: true,
         })
         if (!cancelled) {
           return `[ERROR] Failed to cancel task: ${task.id}`

src/tools/look-at/tools.test.ts

@@ -4,9 +4,9 @@ import { normalizeArgs, validateArgs, createLookAt } from "./tools"
 
 describe("look-at tool", () => {
   describe("normalizeArgs", () => {
-    // given LLM이 file_path 대신 path를 사용할 수 있음
-    // when path 파라미터로 호출
-    // then file_path로 정규화되어야 함
+    // given LLM might use `path` instead of `file_path`
+    // when called with path parameter
+    // then should normalize to file_path
     test("normalizes path to file_path for LLM compatibility", () => {
       const args = { path: "/some/file.png", goal: "analyze" }
       const normalized = normalizeArgs(args as any)
@@ -14,18 +14,18 @@ describe("look-at tool", () => {
       expect(normalized.goal).toBe("analyze")
     })
 
-    // given 정상적인 file_path 사용
-    // when file_path 파라미터로 호출
-    // then 그대로 유지
+    // given proper file_path usage
+    // when called with file_path parameter
+    // then keep as-is
     test("keeps file_path when properly provided", () => {
       const args = { file_path: "/correct/path.pdf", goal: "extract" }
       const normalized = normalizeArgs(args)
       expect(normalized.file_path).toBe("/correct/path.pdf")
     })
 
-    // given 둘 다 제공된 경우
-    // when file_path와 path 모두 있음
-    // then file_path 우선
+    // given both parameters provided
+    // when file_path and path are both present
+    // then prefer file_path
     test("prefers file_path over path when both provided", () => {
       const args = { file_path: "/preferred.png", path: "/fallback.png", goal: "test" }
       const normalized = normalizeArgs(args as any)
@@ -34,17 +34,17 @@ describe("look-at tool", () => {
   })
 
   describe("validateArgs", () => {
-    // given 유효한 인자
-    // when 검증
-    // then null 반환 (에러 없음)
+    // given valid arguments
+    // when validated
+    // then return null (no error)
     test("returns null for valid args", () => {
       const args = { file_path: "/valid/path.png", goal: "analyze" }
       expect(validateArgs(args)).toBeNull()
     })
 
-    // given file_path 누락
-    // when 검증
-    // then 명확한 에러 메시지
+    // given file_path missing
+    // when validated
+    // then clear error message
     test("returns error when file_path is missing", () => {
       const args = { goal: "analyze" } as any
       const error = validateArgs(args)
@@ -52,9 +52,9 @@ describe("look-at tool", () => {
       expect(error).toContain("required")
     })
 
-    // given goal 누락
-    // when 검증
-    // then 명확한 에러 메시지
+    // given goal missing
+    // when validated
+    // then clear error message
     test("returns error when goal is missing", () => {
       const args = { file_path: "/some/path.png" } as any
       const error = validateArgs(args)
@@ -62,9 +62,9 @@ describe("look-at tool", () => {
       expect(error).toContain("required")
     })
 
-    // given file_path가 빈 문자열
-    // when 검증
-    // then 에러 반환
+    // given file_path is empty string
+    // when validated
+    // then return error
     test("returns error when file_path is empty string", () => {
       const args = { file_path: "", goal: "analyze" }
       const error = validateArgs(args)
@@ -73,9 +73,9 @@ describe("look-at tool", () => {
   })
 
   describe("createLookAt error handling", () => {
-    // given session.prompt에서 JSON parse 에러 발생
-    // when LookAt 도구 실행
-    // then 사용자 친화적 에러 메시지 반환
+    // given JSON parse error occurs in session.prompt
+    // when LookAt tool executed
+    // then return user-friendly error message
     test("handles JSON parse error from session.prompt gracefully", async () => {
       const mockClient = {
         session: {
@@ -115,9 +115,9 @@ describe("look-at tool", () => {
       expect(result).toContain("image/png")
     })
 
-    // given session.prompt에서 일반 에러 발생
-    // when LookAt 도구 실행
-    // then 원본 에러 메시지 포함한 에러 반환
+    // given generic error occurs in session.prompt
+    // when LookAt tool executed
+    // then return error including original error message
     test("handles generic prompt error gracefully", async () => {
       const mockClient = {
         session: {
@@ -158,8 +158,8 @@ describe("look-at tool", () => {
 
   describe("createLookAt model passthrough", () => {
     // given multimodal-looker agent has resolved model info
-    // when LookAt 도구 실행
-    // then session.prompt에 model 정보가 전달되어야 함
+    // when LookAt tool executed
+    // then model info should be passed to session.prompt
     test("passes multimodal-looker model to session.prompt when available", async () => {
       let promptBody: any