opencode/packages/core/test/tool-webfetch.test.ts

import { describe, expect, test } from "bun:test"
import { Duration, Effect, Fiber, Layer, Schema } from "effect"
import * as TestClock from "effect/testing/TestClock"
import { HttpClient, HttpClientRequest, HttpClientResponse } from "effect/unstable/http"
import { AppNodeBuilder } from "@opencode-ai/core/effect/app-node-builder"
import { LayerNode } from "@opencode-ai/util/effect/layer-node"
import { LayerNodePlatform } from "@opencode-ai/util/effect/app-node-platform"
import { PermissionV2 } from "@opencode-ai/core/permission"
import { SessionV2 } from "@opencode-ai/core/session"
import { ToolRegistry } from "@opencode-ai/core/tool/registry"
import { WebFetchTool } from "@opencode-ai/core/tool/webfetch"
import { ToolOutputStore } from "@opencode-ai/core/tool-output-store"
import { makeLocationNode } from "@opencode-ai/util/effect/app-node"
import { Image } from "@opencode-ai/core/image"
import { testEffect } from "./lib/effect"
import { imagePassthrough } from "./lib/image"
import { toolIdentity, executeTool, registerToolPlugin, toolDefinitions } from "./lib/tool"

const webFetchToolNode = makeLocationNode({
  name: "test/webfetch-tool-plugin",
  layer: Layer.effectDiscard(registerToolPlugin(WebFetchTool.Plugin)),
  deps: [ToolRegistry.toolsNode, PermissionV2.node, LayerNodePlatform.httpClient],
})

const sessionID = SessionV2.ID.make("ses_webfetch_test")
const requests: Array<{ readonly url: string; readonly headers: Record<string, string> }> = []
const assertions: PermissionV2.AssertInput[] = []
let respond = (_request: HttpClientRequest.HttpClientRequest) =>
  Effect.succeed(new Response("hello", { headers: { "content-type": "text/plain" } }))

const http = Layer.succeed(
  HttpClient.HttpClient,
  HttpClient.make((request) =>
    Effect.sync(() => requests.push({ url: request.url, headers: request.headers })).pipe(
      Effect.andThen(respond(request)),
      Effect.map((response) => HttpClientResponse.fromWeb(request, response)),
    ),
  ),
)
const permission = Layer.succeed(
  PermissionV2.Service,
  PermissionV2.Service.of({
    assert: (input) => Effect.sync(() => assertions.push(input)),
    ask: () => Effect.die("unused"),
    reply: () => Effect.die("unused"),
    get: () => Effect.die("unused"),
    forSession: () => Effect.die("unused"),
    list: () => Effect.die("unused"),
  }),
)
const toolLayer = (replacements: LayerNode.Replacements = []) =>
  AppNodeBuilder.build(LayerNode.group([ToolRegistry.node, ToolRegistry.toolsNode, webFetchToolNode]), [
    [PermissionV2.node, permission],
    [ToolOutputStore.node, ToolOutputStore.nodeWithoutConfig],
    [Image.node, imagePassthrough],
    ...replacements,
  ])
const it = testEffect(toolLayer([[LayerNodePlatform.httpClient, http]]))
const live = testEffect(toolLayer())

const reset = () => {
  requests.length = 0
  assertions.length = 0
  respond = () => Effect.succeed(new Response("hello", { headers: { "content-type": "text/plain" } }))
}

const call = (input: typeof WebFetchTool.Input.Type, id = "call-webfetch") => ({
  sessionID,
  ...toolIdentity,
  call: { type: "tool-call" as const, id, name: "webfetch", input },
})

describe("WebFetchTool helpers", () => {
  test("defaults format and rejects invalid timeout controls", () => {
    const decode = Schema.decodeUnknownSync(WebFetchTool.Input)
    expect(decode({ url: "https://example.com" })).toEqual({ url: "https://example.com", format: "markdown" })
    expect(() => decode({ url: "https://example.com", timeout: 0 })).toThrow()
    expect(() => decode({ url: "https://example.com", timeout: WebFetchTool.MAX_TIMEOUT_SECONDS + 1 })).toThrow()
  })

  test("ports HTML text and markdown conversions without active content", () => {
    const html = "<h1>Hello</h1><script>bad()</script><p>world <strong>wide</strong></p><style>.bad {}</style>"
    expect(WebFetchTool.extractTextFromHTML(html)).toBe("Helloworld wide")
    expect(WebFetchTool.convertHTMLToMarkdown(html)).toBe("# Hello\n\nworld **wide**")
  })
})

describe("WebFetchTool registration", () => {
  it.effect("registers and fetches an ordinary hostname HTTP URL without rewriting it", () =>
    Effect.gen(function* () {
      reset()
      const registry = yield* ToolRegistry.Service
      const url = "http://example.com/public"

      expect((yield* toolDefinitions(registry)).map((tool) => tool.name)).toEqual(["webfetch", "execute"])
      expect(yield* executeTool(registry, call({ url, format: "text", timeout: 4 }))).toEqual({
        status: "completed",
        output: { url, contentType: "text/plain", format: "text", output: "hello" },
        content: [{ type: "text", text: "hello" }],
        metadata: { contentType: "text/plain" },
      })
      expect(assertions).toMatchObject([
        { sessionID, action: "webfetch", resources: [url], save: ["*"], metadata: { url, format: "text", timeout: 4 } },
      ])
      expect(requests).toMatchObject([{ url, headers: { accept: expect.stringContaining("text/plain;q=1.0") } }])
    }),
  )

  it.effect("accepts localhost URLs with the same requested-URL permission check", () =>
    Effect.gen(function* () {
      reset()
      const registry = yield* ToolRegistry.Service
      const url = "http://localhost/private"

      expect(yield* executeTool(registry, call({ url, format: "text" }))).toMatchObject({
        status: "completed",
        content: [{ type: "text", text: "hello" }],
      })
      expect(assertions).toMatchObject([
        { sessionID, action: "webfetch", resources: [url], save: ["*"], metadata: { url, format: "text" } },
      ])
      expect(requests.map((request) => request.url)).toEqual([url])
    }),
  )

  live.effect("follows redirects while approving only the requested URL", () =>
    Effect.acquireUseRelease(
      Effect.sync(() =>
        Bun.serve({
          port: 0,
          fetch: (request) =>
            new URL(request.url).pathname === "/redirect"
              ? new Response("", { status: 302, headers: { location: "/target" } })
              : new Response("redirected", { headers: { "content-type": "text/plain" } }),
        }),
      ),
      (server) =>
        Effect.gen(function* () {
          reset()
          const registry = yield* ToolRegistry.Service
          const url = new URL("/redirect", server.url).toString()

          expect(yield* executeTool(registry, call({ url, format: "text" }))).toMatchObject({
            status: "completed",
            content: [{ type: "text", text: "redirected" }],
          })
          expect(assertions).toMatchObject([
            { sessionID, action: "webfetch", resources: [url], save: ["*"], metadata: { url, format: "text" } },
          ])
        }),
      (server) => Effect.promise(() => server.stop(true)),
    ),
  )

  it.effect("rejects non-HTTP schemes before permission or transport", () =>
    Effect.gen(function* () {
      reset()
      const registry = yield* ToolRegistry.Service

      // toSessionError unwraps the "Unable to fetch <url>" ToolFailure to its cause message.
      expect(yield* executeTool(registry, call({ url: "file:///etc/passwd", format: "text" }))).toEqual({
        status: "error",
        error: { type: "unknown", message: "URL must use http:// or https://" },
      })
      expect(assertions).toEqual([])
      expect(requests).toEqual([])
    }),
  )

  it.effect("converts HTML to requested markdown and text", () =>
    Effect.gen(function* () {
      reset()
      respond = () =>
        Effect.succeed(
          new Response("<h1>Hello</h1><p>world</p><script>bad()</script>", {
            headers: { "content-type": "text/html; charset=utf-8" },
          }),
        )
      const registry = yield* ToolRegistry.Service

      expect(yield* executeTool(registry, call({ url: "https://1.1.1.1", format: "markdown" }))).toMatchObject({
        status: "completed",
        content: [{ type: "text", text: "# Hello\n\nworld" }],
      })
      expect(yield* executeTool(registry, call({ url: "https://1.1.1.1", format: "text" }))).toMatchObject({
        status: "completed",
        content: [{ type: "text", text: "Helloworld" }],
      })
    }),
  )

  it.effect("returns an error result when HTML-to-Markdown conversion throws", () =>
    Effect.gen(function* () {
      reset()
      respond = () =>
        Effect.succeed(
          new Response("<div>".repeat(10_000) + "content" + "</div>".repeat(10_000), {
            headers: { "content-type": "text/html" },
          }),
        )
      const registry = yield* ToolRegistry.Service
      const url = "https://1.1.1.1/deep-html"

      expect(yield* executeTool(registry, call({ url, format: "markdown" }))).toMatchObject({
        status: "error",
        error: { type: "unknown" },
      })
    }),
  )

  it.effect("rejects declared and streamed oversized bodies", () =>
    Effect.gen(function* () {
      reset()
      const registry = yield* ToolRegistry.Service
      respond = () =>
        Effect.succeed(
          new Response("small", {
            headers: { "content-type": "text/plain", "content-length": String(WebFetchTool.MAX_RESPONSE_BYTES + 1) },
          }),
        )
      expect(yield* executeTool(registry, call({ url: "https://1.1.1.1/declared", format: "text" }))).toEqual({
        status: "error",
        error: {
          type: "unknown",
          message: `Response too large (exceeds ${WebFetchTool.MAX_RESPONSE_BYTES} byte limit)`,
        },
      })

      respond = () =>
        Effect.succeed(
          new Response("x".repeat(WebFetchTool.MAX_RESPONSE_BYTES + 1), { headers: { "content-type": "text/plain" } }),
        )
      expect(yield* executeTool(registry, call({ url: "https://1.1.1.1/streamed", format: "text" }))).toEqual({
        status: "error",
        error: {
          type: "unknown",
          message: `Response too large (exceeds ${WebFetchTool.MAX_RESPONSE_BYTES} byte limit)`,
        },
      })
    }),
  )

  it.effect("keeps images and files unsupported until typed outcomes can carry attachments", () =>
    Effect.gen(function* () {
      reset()
      const registry = yield* ToolRegistry.Service
      respond = () => Effect.succeed(new Response("png", { headers: { "content-type": "image/png" } }))
      expect(yield* executeTool(registry, call({ url: "https://1.1.1.1/image", format: "html" }))).toEqual({
        status: "error",
        error: { type: "unknown", message: "Unsupported fetched image content type: image/png" },
      })

      respond = () => Effect.succeed(new Response("pdf", { headers: { "content-type": "application/pdf" } }))
      expect(yield* executeTool(registry, call({ url: "https://1.1.1.1/file", format: "html" }))).toEqual({
        status: "error",
        error: { type: "unknown", message: "Unsupported fetched file content type: application/pdf" },
      })
    }),
  )

  it.effect("retries Cloudflare challenges with an honest user agent", () =>
    Effect.gen(function* () {
      reset()
      let count = 0
      respond = () =>
        Effect.succeed(
          ++count === 1
            ? new Response("challenge", { status: 403, headers: { "cf-mitigated": "challenge" } })
            : new Response("ok", { headers: { "content-type": "text/plain" } }),
        )
      const registry = yield* ToolRegistry.Service

      expect(yield* executeTool(registry, call({ url: "https://1.1.1.1", format: "text" }))).toMatchObject({
        status: "completed",
        content: [{ type: "text", text: "ok" }],
      })
      expect(requests).toHaveLength(2)
      expect(requests[0]?.headers["user-agent"]).toContain("Mozilla/5.0")
      expect(requests[1]?.headers["user-agent"]).toBe("opencode")
    }),
  )

  it.effect("times out stalled requests", () =>
    Effect.gen(function* () {
      reset()
      respond = () => Effect.never
      const registry = yield* ToolRegistry.Service
      const fiber = yield* executeTool(
        registry,
        call({ url: "https://1.1.1.1/slow", format: "text", timeout: 1 }),
      ).pipe(Effect.forkChild)
      yield* TestClock.adjust(Duration.seconds(1))

      expect(yield* Fiber.join(fiber)).toEqual({
        status: "error",
        error: { type: "unknown", message: "Request timed out" },
      })
    }),
  )
})