feat(skills): add agent-browser option for browser automation (#1090)

Add configurable browser automation allowing users to choose between
Playwright MCP (default) and Vercel's agent-browser CLI.

Changes:
- Add browser_automation_engine.provider config option
- Dynamic skill loading based on provider selection
- Comprehensive agent-browser CLI reference (inline in skills.ts)
- Propagate browserProvider to delegate_task and buildAgent
- Update documentation with provider comparison

Co-authored-by: Suyeol Jeon <devxoul@gmail.com>
Co-authored-by: YeonGyu Kim <code.yeongyu@gmail.com>
This commit is contained in:
YeonGyu-Kim
2026-01-25 15:02:41 +09:00
committed by GitHub
parent 9f830e7f98
commit 893bd8b153
17 changed files with 1155 additions and 38 deletions
+108 -1
View File
@@ -3,14 +3,15 @@ import { DEFAULT_CATEGORIES, CATEGORY_PROMPT_APPENDS, CATEGORY_DESCRIPTIONS } fr
import { resolveCategoryConfig } from "./tools"
import type { CategoryConfig } from "../../config/schema"
import { __resetModelCache } from "../../shared/model-availability"
import { clearSkillCache } from "../../features/opencode-skill-loader/skill-content"
// Test constants - systemDefaultModel is required by resolveCategoryConfig
const SYSTEM_DEFAULT_MODEL = "anthropic/claude-sonnet-4-5"
describe("sisyphus-task", () => {
// Reset model cache before each test to prevent cross-test pollution
beforeEach(() => {
__resetModelCache()
clearSkillCache()
})
describe("DEFAULT_CATEGORIES", () => {
@@ -1324,6 +1325,112 @@ describe("sisyphus-task", () => {
}, { timeout: 20000 })
})
describe("browserProvider propagation", () => {
test("should resolve agent-browser skill when browserProvider is passed", async () => {
// #given - delegate_task configured with browserProvider: "agent-browser"
const { createDelegateTask } = require("./tools")
let promptBody: any
const mockManager = { launch: async () => ({}) }
const mockClient = {
app: { agents: async () => ({ data: [] }) },
config: { get: async () => ({ data: { model: SYSTEM_DEFAULT_MODEL } }) },
session: {
get: async () => ({ data: { directory: "/project" } }),
create: async () => ({ data: { id: "ses_browser_provider" } }),
prompt: async (input: any) => {
promptBody = input.body
return { data: {} }
},
messages: async () => ({
data: [{ info: { role: "assistant" }, parts: [{ type: "text", text: "Done" }] }]
}),
status: async () => ({ data: {} }),
},
}
// Pass browserProvider to createDelegateTask
const tool = createDelegateTask({
manager: mockManager,
client: mockClient,
browserProvider: "agent-browser",
})
const toolContext = {
sessionID: "parent-session",
messageID: "parent-message",
agent: "Sisyphus",
abort: new AbortController().signal,
}
// #when - request agent-browser skill
await tool.execute(
{
description: "Test browserProvider propagation",
prompt: "Do something",
category: "ultrabrain",
run_in_background: false,
load_skills: ["agent-browser"],
},
toolContext
)
// #then - agent-browser skill should be resolved (not in notFound)
expect(promptBody).toBeDefined()
expect(promptBody.system).toBeDefined()
expect(promptBody.system).toContain("agent-browser")
}, { timeout: 20000 })
test("should NOT resolve agent-browser skill when browserProvider is not set", async () => {
// #given - delegate_task without browserProvider (defaults to playwright)
const { createDelegateTask } = require("./tools")
const mockManager = { launch: async () => ({}) }
const mockClient = {
app: { agents: async () => ({ data: [] }) },
config: { get: async () => ({ data: { model: SYSTEM_DEFAULT_MODEL } }) },
session: {
get: async () => ({ data: { directory: "/project" } }),
create: async () => ({ data: { id: "ses_no_browser_provider" } }),
prompt: async () => ({ data: {} }),
messages: async () => ({
data: [{ info: { role: "assistant" }, parts: [{ type: "text", text: "Done" }] }]
}),
status: async () => ({ data: {} }),
},
}
// No browserProvider passed
const tool = createDelegateTask({
manager: mockManager,
client: mockClient,
})
const toolContext = {
sessionID: "parent-session",
messageID: "parent-message",
agent: "Sisyphus",
abort: new AbortController().signal,
}
// #when - request agent-browser skill without browserProvider
const result = await tool.execute(
{
description: "Test missing browserProvider",
prompt: "Do something",
category: "ultrabrain",
run_in_background: false,
load_skills: ["agent-browser"],
},
toolContext
)
// #then - should return skill not found error
expect(result).toContain("Skills not found")
expect(result).toContain("agent-browser")
})
})
describe("buildSystemContent", () => {
test("returns undefined when no skills and no category promptAppend", () => {
// #given
+4 -3
View File
@@ -3,7 +3,7 @@ import { existsSync, readdirSync } from "node:fs"
import { join } from "node:path"
import type { BackgroundManager } from "../../features/background-agent"
import type { DelegateTaskArgs } from "./types"
import type { CategoryConfig, CategoriesConfig, GitMasterConfig } from "../../config/schema"
import type { CategoryConfig, CategoriesConfig, GitMasterConfig, BrowserAutomationProvider } from "../../config/schema"
import { DEFAULT_CATEGORIES, CATEGORY_PROMPT_APPENDS, CATEGORY_DESCRIPTIONS } from "./constants"
import { findNearestMessageWithFields, findFirstMessageWithAgent, MESSAGE_STORAGE } from "../../features/hook-message-injector"
import { resolveMultipleSkillsAsync } from "../../features/opencode-skill-loader/skill-content"
@@ -157,6 +157,7 @@ export interface DelegateTaskToolOptions {
userCategories?: CategoriesConfig
gitMasterConfig?: GitMasterConfig
sisyphusJuniorModel?: string
browserProvider?: BrowserAutomationProvider
}
export interface BuildSystemContentInput {
@@ -179,7 +180,7 @@ export function buildSystemContent(input: BuildSystemContentInput): string | und
}
export function createDelegateTask(options: DelegateTaskToolOptions): ToolDefinition {
const { manager, client, directory, userCategories, gitMasterConfig, sisyphusJuniorModel } = options
const { manager, client, directory, userCategories, gitMasterConfig, sisyphusJuniorModel, browserProvider } = options
const allCategories = { ...DEFAULT_CATEGORIES, ...userCategories }
const categoryNames = Object.keys(allCategories)
@@ -239,7 +240,7 @@ Prompts MUST be in English.`
let skillContent: string | undefined
if (args.load_skills.length > 0) {
const { resolved, notFound } = await resolveMultipleSkillsAsync(args.load_skills, { gitMasterConfig })
const { resolved, notFound } = await resolveMultipleSkillsAsync(args.load_skills, { gitMasterConfig, browserProvider })
if (notFound.length > 0) {
const allSkills = await discoverSkills({ includeClaudeCodePaths: true })
const available = allSkills.map(s => s.name).join(", ")