Merge branch 'dev' into fix/1671-tmux-layout

This commit is contained in:
YeonGyu-Kim
2026-02-17 01:54:08 +09:00
committed by GitHub
55 changed files with 2689 additions and 144 deletions
@@ -1003,6 +1003,52 @@ describe("BackgroundManager.notifyParentSession - aborted parent", () => {
})
})
describe("BackgroundManager.notifyParentSession - notifications toggle", () => {
test("should skip parent prompt injection when notifications are disabled", async () => {
//#given
let promptCalled = false
const promptMock = async () => {
promptCalled = true
return {}
}
const client = {
session: {
prompt: promptMock,
promptAsync: promptMock,
abort: async () => ({}),
messages: async () => ({ data: [] }),
},
}
const manager = new BackgroundManager(
{ client, directory: tmpdir() } as unknown as PluginInput,
undefined,
{ enableParentSessionNotifications: false },
)
const task: BackgroundTask = {
id: "task-no-parent-notification",
sessionID: "session-child",
parentSessionID: "session-parent",
parentMessageID: "msg-parent",
description: "task notifications disabled",
prompt: "test",
agent: "explore",
status: "completed",
startedAt: new Date(),
completedAt: new Date(),
}
getPendingByParent(manager).set("session-parent", new Set([task.id]))
//#when
await (manager as unknown as { notifyParentSession: (task: BackgroundTask) => Promise<void> })
.notifyParentSession(task)
//#then
expect(promptCalled).toBe(false)
manager.shutdown()
})
})
function buildNotificationPromptBody(
task: BackgroundTask,
currentMessage: CurrentMessage | null
+84 -72
View File
@@ -92,6 +92,7 @@ export class BackgroundManager {
private completionTimers: Map<string, ReturnType<typeof setTimeout>> = new Map()
private idleDeferralTimers: Map<string, ReturnType<typeof setTimeout>> = new Map()
private notificationQueueByParent: Map<string, Promise<void>> = new Map()
private enableParentSessionNotifications: boolean
readonly taskHistory = new TaskHistory()
constructor(
@@ -101,6 +102,7 @@ export class BackgroundManager {
tmuxConfig?: TmuxConfig
onSubagentSessionCreated?: OnSubagentSessionCreated
onShutdown?: () => void
enableParentSessionNotifications?: boolean
}
) {
this.tasks = new Map()
@@ -113,6 +115,7 @@ export class BackgroundManager {
this.tmuxEnabled = options?.tmuxConfig?.enabled ?? false
this.onSubagentSessionCreated = options?.onSubagentSessionCreated
this.onShutdown = options?.onShutdown
this.enableParentSessionNotifications = options?.enableParentSessionNotifications ?? true
this.registerProcessCleanup()
}
@@ -1203,19 +1206,22 @@ export class BackgroundManager {
allComplete = true
}
const statusText = task.status === "completed" ? "COMPLETED" : task.status === "interrupt" ? "INTERRUPTED" : "CANCELLED"
const errorInfo = task.error ? `\n**Error:** ${task.error}` : ""
let notification: string
let completedTasks: BackgroundTask[] = []
if (allComplete) {
completedTasks = Array.from(this.tasks.values())
const completedTasks = allComplete
? Array.from(this.tasks.values())
.filter(t => t.parentSessionID === task.parentSessionID && t.status !== "running" && t.status !== "pending")
const completedTasksText = completedTasks
.map(t => `- \`${t.id}\`: ${t.description}`)
.join("\n")
: []
notification = `<system-reminder>
if (this.enableParentSessionNotifications) {
const statusText = task.status === "completed" ? "COMPLETED" : task.status === "interrupt" ? "INTERRUPTED" : "CANCELLED"
const errorInfo = task.error ? `\n**Error:** ${task.error}` : ""
let notification: string
if (allComplete) {
const completedTasksText = completedTasks
.map(t => `- \`${t.id}\`: ${t.description}`)
.join("\n")
notification = `<system-reminder>
[ALL BACKGROUND TASKS COMPLETE]
**Completed:**
@@ -1223,9 +1229,9 @@ ${completedTasksText || `- \`${task.id}\`: ${task.description}`}
Use \`background_output(task_id="<id>")\` to retrieve each result.
</system-reminder>`
} else {
// Individual completion - silent notification
notification = `<system-reminder>
} else {
// Individual completion - silent notification
notification = `<system-reminder>
[BACKGROUND TASK ${statusText}]
**ID:** \`${task.id}\`
**Description:** ${task.description}
@@ -1236,70 +1242,76 @@ Do NOT poll - continue productive work.
Use \`background_output(task_id="${task.id}")\` to retrieve this result when ready.
</system-reminder>`
}
}
let agent: string | undefined = task.parentAgent
let model: { providerID: string; modelID: string } | undefined
let agent: string | undefined = task.parentAgent
let model: { providerID: string; modelID: string } | undefined
try {
const messagesResp = await this.client.session.messages({ path: { id: task.parentSessionID } })
const messages = normalizeSDKResponse(messagesResp, [] as Array<{
info?: { agent?: string; model?: { providerID: string; modelID: string }; modelID?: string; providerID?: string }
}>)
for (let i = messages.length - 1; i >= 0; i--) {
const info = messages[i].info
if (info?.agent || info?.model || (info?.modelID && info?.providerID)) {
agent = info.agent ?? task.parentAgent
model = info.model ?? (info.providerID && info.modelID ? { providerID: info.providerID, modelID: info.modelID } : undefined)
break
try {
const messagesResp = await this.client.session.messages({ path: { id: task.parentSessionID } })
const messages = normalizeSDKResponse(messagesResp, [] as Array<{
info?: { agent?: string; model?: { providerID: string; modelID: string }; modelID?: string; providerID?: string }
}>)
for (let i = messages.length - 1; i >= 0; i--) {
const info = messages[i].info
if (info?.agent || info?.model || (info?.modelID && info?.providerID)) {
agent = info.agent ?? task.parentAgent
model = info.model ?? (info.providerID && info.modelID ? { providerID: info.providerID, modelID: info.modelID } : undefined)
break
}
}
} catch (error) {
if (this.isAbortedSessionError(error)) {
log("[background-agent] Parent session aborted while loading messages; using messageDir fallback:", {
taskId: task.id,
parentSessionID: task.parentSessionID,
})
}
const messageDir = getMessageDir(task.parentSessionID)
const currentMessage = messageDir ? findNearestMessageWithFields(messageDir) : null
agent = currentMessage?.agent ?? task.parentAgent
model = currentMessage?.model?.providerID && currentMessage?.model?.modelID
? { providerID: currentMessage.model.providerID, modelID: currentMessage.model.modelID }
: undefined
}
log("[background-agent] notifyParentSession context:", {
taskId: task.id,
resolvedAgent: agent,
resolvedModel: model,
})
try {
await this.client.session.promptAsync({
path: { id: task.parentSessionID },
body: {
noReply: !allComplete,
...(agent !== undefined ? { agent } : {}),
...(model !== undefined ? { model } : {}),
...(task.parentTools ? { tools: task.parentTools } : {}),
parts: [{ type: "text", text: notification }],
},
})
log("[background-agent] Sent notification to parent session:", {
taskId: task.id,
allComplete,
noReply: !allComplete,
})
} catch (error) {
if (this.isAbortedSessionError(error)) {
log("[background-agent] Parent session aborted while sending notification; continuing cleanup:", {
taskId: task.id,
parentSessionID: task.parentSessionID,
})
} else {
log("[background-agent] Failed to send notification:", error)
}
}
} catch (error) {
if (this.isAbortedSessionError(error)) {
log("[background-agent] Parent session aborted while loading messages; using messageDir fallback:", {
taskId: task.id,
parentSessionID: task.parentSessionID,
})
}
const messageDir = getMessageDir(task.parentSessionID)
const currentMessage = messageDir ? findNearestMessageWithFields(messageDir) : null
agent = currentMessage?.agent ?? task.parentAgent
model = currentMessage?.model?.providerID && currentMessage?.model?.modelID
? { providerID: currentMessage.model.providerID, modelID: currentMessage.model.modelID }
: undefined
}
log("[background-agent] notifyParentSession context:", {
taskId: task.id,
resolvedAgent: agent,
resolvedModel: model,
})
try {
await this.client.session.promptAsync({
path: { id: task.parentSessionID },
body: {
noReply: !allComplete,
...(agent !== undefined ? { agent } : {}),
...(model !== undefined ? { model } : {}),
...(task.parentTools ? { tools: task.parentTools } : {}),
parts: [{ type: "text", text: notification }],
},
})
log("[background-agent] Sent notification to parent session:", {
} else {
log("[background-agent] Parent session notifications disabled, skipping prompt injection:", {
taskId: task.id,
allComplete,
noReply: !allComplete,
parentSessionID: task.parentSessionID,
})
} catch (error) {
if (this.isAbortedSessionError(error)) {
log("[background-agent] Parent session aborted while sending notification; continuing cleanup:", {
taskId: task.id,
parentSessionID: task.parentSessionID,
})
} else {
log("[background-agent] Failed to send notification:", error)
}
}
if (allComplete) {
@@ -0,0 +1,33 @@
import { describe, expect, test } from "bun:test"
import { resolveParentDirectory } from "./parent-directory-resolver"
describe("background-agent parent-directory-resolver", () => {
const originalPlatform = process.platform
test("uses current working directory on Windows when parent session directory is AppData", async () => {
//#given
Object.defineProperty(process, "platform", { value: "win32" })
try {
const client = {
session: {
get: async () => ({
data: { directory: "C:\\Users\\test\\AppData\\Local\\ai.opencode.desktop" },
}),
},
}
//#when
const result = await resolveParentDirectory({
client: client as Parameters<typeof resolveParentDirectory>[0]["client"],
parentSessionID: "ses_parent",
defaultDirectory: "C:\\Users\\test\\AppData\\Roaming\\opencode",
})
//#then
expect(result).toBe(process.cwd())
} finally {
Object.defineProperty(process, "platform", { value: originalPlatform })
}
})
})
@@ -1,5 +1,5 @@
import type { OpencodeClient } from "../constants"
import { log } from "../../../shared"
import { log, resolveSessionDirectory } from "../../../shared"
export async function resolveParentDirectory(options: {
client: OpencodeClient
@@ -15,7 +15,10 @@ export async function resolveParentDirectory(options: {
return null
})
const parentDirectory = parentSession?.data?.directory ?? defaultDirectory
const parentDirectory = resolveSessionDirectory({
parentDirectory: parentSession?.data?.directory,
fallbackDirectory: defaultDirectory,
})
log(`[background-agent] Parent dir: ${parentSession?.data?.directory}, using: ${parentDirectory}`)
return parentDirectory
}
@@ -140,4 +140,35 @@ describe("createBuiltinSkills", () => {
// #then
expect(skills.length).toBe(4)
})
test("returns playwright-cli skill when browserProvider is 'playwright-cli'", () => {
// given
const options = { browserProvider: "playwright-cli" as const }
// when
const skills = createBuiltinSkills(options)
// then
const playwrightSkill = skills.find((s) => s.name === "playwright")
const agentBrowserSkill = skills.find((s) => s.name === "agent-browser")
expect(playwrightSkill).toBeDefined()
expect(playwrightSkill!.description).toContain("browser")
expect(playwrightSkill!.allowedTools).toContain("Bash(playwright-cli:*)")
expect(playwrightSkill!.mcpConfig).toBeUndefined()
expect(agentBrowserSkill).toBeUndefined()
})
test("playwright-cli skill template contains CLI commands", () => {
// given
const options = { browserProvider: "playwright-cli" as const }
// when
const skills = createBuiltinSkills(options)
const skill = skills.find((s) => s.name === "playwright")
// then
expect(skill!.template).toContain("playwright-cli open")
expect(skill!.template).toContain("playwright-cli snapshot")
expect(skill!.template).toContain("playwright-cli click")
})
})
+9 -1
View File
@@ -4,6 +4,7 @@ import type { BrowserAutomationProvider } from "../../config/schema"
import {
playwrightSkill,
agentBrowserSkill,
playwrightCliSkill,
frontendUiUxSkill,
gitMasterSkill,
devBrowserSkill,
@@ -17,7 +18,14 @@ export interface CreateBuiltinSkillsOptions {
export function createBuiltinSkills(options: CreateBuiltinSkillsOptions = {}): BuiltinSkill[] {
const { browserProvider = "playwright", disabledSkills } = options
const browserSkill = browserProvider === "agent-browser" ? agentBrowserSkill : playwrightSkill
let browserSkill: BuiltinSkill
if (browserProvider === "agent-browser") {
browserSkill = agentBrowserSkill
} else if (browserProvider === "playwright-cli") {
browserSkill = playwrightCliSkill
} else {
browserSkill = playwrightSkill
}
const skills = [browserSkill, frontendUiUxSkill, gitMasterSkill, devBrowserSkill]
@@ -1,4 +1,5 @@
export { playwrightSkill, agentBrowserSkill } from "./playwright"
export { playwrightCliSkill } from "./playwright-cli"
export { frontendUiUxSkill } from "./frontend-ui-ux"
export { gitMasterSkill } from "./git-master"
export { devBrowserSkill } from "./dev-browser"
@@ -0,0 +1,268 @@
import type { BuiltinSkill } from "../types"
/**
* Playwright CLI skill — token-efficient CLI alternative to the MCP-based playwright skill.
*
* Uses name "playwright" (not "playwright-cli") because agents hardcode "playwright" as the
* canonical browser skill name. The browserProvider config swaps the implementation behind
* the same name: "playwright" gives MCP, "playwright-cli" gives this CLI variant.
* The binary is still called `playwright-cli` (see allowedTools).
*/
export const playwrightCliSkill: BuiltinSkill = {
name: "playwright",
description: "MUST USE for any browser-related tasks. Browser automation via playwright-cli - verification, browsing, information gathering, web scraping, testing, screenshots, and all browser interactions.",
template: `# Browser Automation with playwright-cli
## Quick start
\`\`\`bash
# open new browser
playwright-cli open
# navigate to a page
playwright-cli goto https://playwright.dev
# interact with the page using refs from the snapshot
playwright-cli click e15
playwright-cli type "page.click"
playwright-cli press Enter
# take a screenshot
playwright-cli screenshot
# close the browser
playwright-cli close
\`\`\`
## Commands
### Core
\`\`\`bash
playwright-cli open
# open and navigate right away
playwright-cli open https://example.com/
playwright-cli goto https://playwright.dev
playwright-cli type "search query"
playwright-cli click e3
playwright-cli dblclick e7
playwright-cli fill e5 "user@example.com"
playwright-cli drag e2 e8
playwright-cli hover e4
playwright-cli select e9 "option-value"
playwright-cli upload ./document.pdf
playwright-cli check e12
playwright-cli uncheck e12
playwright-cli snapshot
playwright-cli snapshot --filename=after-click.yaml
playwright-cli eval "document.title"
playwright-cli eval "el => el.textContent" e5
playwright-cli dialog-accept
playwright-cli dialog-accept "confirmation text"
playwright-cli dialog-dismiss
playwright-cli resize 1920 1080
playwright-cli close
\`\`\`
### Navigation
\`\`\`bash
playwright-cli go-back
playwright-cli go-forward
playwright-cli reload
\`\`\`
### Keyboard
\`\`\`bash
playwright-cli press Enter
playwright-cli press ArrowDown
playwright-cli keydown Shift
playwright-cli keyup Shift
\`\`\`
### Mouse
\`\`\`bash
playwright-cli mousemove 150 300
playwright-cli mousedown
playwright-cli mousedown right
playwright-cli mouseup
playwright-cli mouseup right
playwright-cli mousewheel 0 100
\`\`\`
### Save as
\`\`\`bash
playwright-cli screenshot
playwright-cli screenshot e5
playwright-cli screenshot --filename=page.png
playwright-cli pdf --filename=page.pdf
\`\`\`
### Tabs
\`\`\`bash
playwright-cli tab-list
playwright-cli tab-new
playwright-cli tab-new https://example.com/page
playwright-cli tab-close
playwright-cli tab-close 2
playwright-cli tab-select 0
\`\`\`
### Storage
\`\`\`bash
playwright-cli state-save
playwright-cli state-save auth.json
playwright-cli state-load auth.json
# Cookies
playwright-cli cookie-list
playwright-cli cookie-list --domain=example.com
playwright-cli cookie-get session_id
playwright-cli cookie-set session_id abc123
playwright-cli cookie-set session_id abc123 --domain=example.com --httpOnly --secure
playwright-cli cookie-delete session_id
playwright-cli cookie-clear
# LocalStorage
playwright-cli localstorage-list
playwright-cli localstorage-get theme
playwright-cli localstorage-set theme dark
playwright-cli localstorage-delete theme
playwright-cli localstorage-clear
# SessionStorage
playwright-cli sessionstorage-list
playwright-cli sessionstorage-get step
playwright-cli sessionstorage-set step 3
playwright-cli sessionstorage-delete step
playwright-cli sessionstorage-clear
\`\`\`
### Network
\`\`\`bash
playwright-cli route "**/*.jpg" --status=404
playwright-cli route "https://api.example.com/**" --body='{"mock": true}'
playwright-cli route-list
playwright-cli unroute "**/*.jpg"
playwright-cli unroute
\`\`\`
### DevTools
\`\`\`bash
playwright-cli console
playwright-cli console warning
playwright-cli network
playwright-cli run-code "async page => await page.context().grantPermissions(['geolocation'])"
playwright-cli tracing-start
playwright-cli tracing-stop
playwright-cli video-start
playwright-cli video-stop video.webm
\`\`\`
### Install
\`\`\`bash
playwright-cli install --skills
playwright-cli install-browser
\`\`\`
### Configuration
\`\`\`bash
# Use specific browser when creating session
playwright-cli open --browser=chrome
playwright-cli open --browser=firefox
playwright-cli open --browser=webkit
playwright-cli open --browser=msedge
# Connect to browser via extension
playwright-cli open --extension
# Use persistent profile (by default profile is in-memory)
playwright-cli open --persistent
# Use persistent profile with custom directory
playwright-cli open --profile=/path/to/profile
# Start with config file
playwright-cli open --config=my-config.json
# Close the browser
playwright-cli close
# Delete user data for the default session
playwright-cli delete-data
\`\`\`
### Browser Sessions
\`\`\`bash
# create new browser session named "mysession" with persistent profile
playwright-cli -s=mysession open example.com --persistent
# same with manually specified profile directory (use when requested explicitly)
playwright-cli -s=mysession open example.com --profile=/path/to/profile
playwright-cli -s=mysession click e6
playwright-cli -s=mysession close # stop a named browser
playwright-cli -s=mysession delete-data # delete user data for persistent session
playwright-cli list
# Close all browsers
playwright-cli close-all
# Forcefully kill all browser processes
playwright-cli kill-all
\`\`\`
## Example: Form submission
\`\`\`bash
playwright-cli open https://example.com/form
playwright-cli snapshot
playwright-cli fill e1 "user@example.com"
playwright-cli fill e2 "password123"
playwright-cli click e3
playwright-cli snapshot
playwright-cli close
\`\`\`
## Example: Multi-tab workflow
\`\`\`bash
playwright-cli open https://example.com
playwright-cli tab-new https://example.com/other
playwright-cli tab-list
playwright-cli tab-select 0
playwright-cli snapshot
playwright-cli close
\`\`\`
## Example: Debugging with DevTools
\`\`\`bash
playwright-cli open https://example.com
playwright-cli click e4
playwright-cli fill e7 "test"
playwright-cli console
playwright-cli network
playwright-cli close
\`\`\`
\`\`\`bash
playwright-cli open https://example.com
playwright-cli tracing-start
playwright-cli click e4
playwright-cli fill e7 "test"
playwright-cli tracing-stop
playwright-cli close
\`\`\`
## Specific tasks
* **Request mocking** [references/request-mocking.md](references/request-mocking.md)
* **Running Playwright code** [references/running-code.md](references/running-code.md)
* **Browser session management** [references/session-management.md](references/session-management.md)
* **Storage state (cookies, localStorage)** [references/storage-state.md](references/storage-state.md)
* **Test generation** [references/test-generation.md](references/test-generation.md)
* **Tracing** [references/tracing.md](references/tracing.md)
* **Video recording** [references/video-recording.md](references/video-recording.md)`,
allowedTools: ["Bash(playwright-cli:*)"],
}