feat: Switch to playwright-go for better DOM automation

Major refactor using Playwright (pure Go):
- Add playwright-go dependency (v0.5700.1)
- Create PlaywrightProvider with auto-wait for elements
- Use LaunchPersistentContext for session persistence
- Implement Locator-based element finding (auto-wait)
- Fill input using Playwright's built-in methods
- Add fallback selectors for input fields
- Better error messages with page URL and title

Key improvements over Rod:
- Auto-wait for elements (solves 'input field not found')
- More mature browser automation library
- Better documentation and examples
- Based on project-golem's proven strategies

Installation:
- Playwright driver and Chromium downloaded to ~/Library/Caches/ms-playwright/
- ~160MB download (one-time setup)
This commit is contained in:
王性驊 2026-04-03 01:20:42 +08:00
parent 17b001d8c2
commit 3d5f2d91c0
4 changed files with 451 additions and 1 deletions

4
go.mod
View File

@ -8,10 +8,14 @@ require (
)
require (
github.com/deckarep/golang-set/v2 v2.8.0 // indirect
github.com/dustin/go-humanize v1.0.1 // indirect
github.com/go-jose/go-jose/v3 v3.0.5 // indirect
github.com/go-rod/rod v0.116.2 // indirect
github.com/go-stack/stack v1.8.1 // indirect
github.com/mattn/go-isatty v0.0.20 // indirect
github.com/ncruces/go-strftime v1.0.0 // indirect
github.com/playwright-community/playwright-go v0.5700.1 // indirect
github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
github.com/ysmood/fetchup v0.2.3 // indirect
github.com/ysmood/goob v0.4.0 // indirect

53
go.sum
View File

@ -1,7 +1,15 @@
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/deckarep/golang-set/v2 v2.8.0 h1:swm0rlPCmdWn9mESxKOjWk8hXSqoxOp+ZlfuyaAdFlQ=
github.com/deckarep/golang-set/v2 v2.8.0/go.mod h1:VAky9rY/yGXJOLEDv3OMci+7wtDpOF4IN+y82NBOac4=
github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=
github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=
github.com/go-jose/go-jose/v3 v3.0.5 h1:BLLJWbC4nMZOfuPVxoZIxeYsn6Nl2r1fITaJ78UQlVQ=
github.com/go-jose/go-jose/v3 v3.0.5/go.mod h1:5b+7YgP7ZICgJDBdfjZaIt+H/9L9T/YQrVfLAMboGkQ=
github.com/go-rod/rod v0.116.2 h1:A5t2Ky2A+5eD/ZJQr1EfsQSe5rms5Xof/qj296e+ZqA=
github.com/go-rod/rod v0.116.2/go.mod h1:H+CMO9SCNc2TJ2WfrG+pKhITz57uGNYU43qYHh438Mg=
github.com/go-stack/stack v1.8.1 h1:ntEHSVwIt7PNXNpgPmVfMrNhLtgjlmnZha2kOpuRiDw=
github.com/go-stack/stack v1.8.1/go.mod h1:dcoOX6HbPZSZptuspn9bctJ+N/CnF5gGygcUP3XYfe4=
github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e h1:ijClszYn+mADRFY17kjQEVQ1XRhq2/JR1M3sGqeJoxs=
github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e/go.mod h1:boTsfXsheKC2y+lKOCMpSfarhxDeIzfZG1jqGcPl3cA=
github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
@ -12,8 +20,13 @@ github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWE
github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
github.com/ncruces/go-strftime v1.0.0 h1:HMFp8mLCTPp341M/ZnA4qaf7ZlsbTc+miZjCLOFAw7w=
github.com/ncruces/go-strftime v1.0.0/go.mod h1:Fwc5htZGVVkseilnfgOVb9mKy6w1naJmn9CehxcKcls=
github.com/playwright-community/playwright-go v0.5700.1 h1:PNFb1byWqrTT720rEO0JL88C6Ju0EmUnR5deFLvtP/U=
github.com/playwright-community/playwright-go v0.5700.1/go.mod h1:MlSn1dZrx8rszbCxY6x3qK89ZesJUYVx21B2JnkoNF0=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE=
github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/ysmood/fetchup v0.2.3 h1:ulX+SonA0Vma5zUFXtv52Kzip/xe7aj4vqT5AJwQ+ZQ=
github.com/ysmood/fetchup v0.2.3/go.mod h1:xhibcRKziSvol0H1/pj33dnKrYyI2ebIvz5cOOkYGns=
github.com/ysmood/goob v0.4.0 h1:HsxXhyLBeGzWXnqVKtmT9qM7EuVs/XOgkX7T6r1o1AQ=
@ -25,15 +38,55 @@ github.com/ysmood/gson v0.7.3 h1:QFkWbTH8MxyUTKPkVWAENJhxqdBa4lYTQWqZCiLG6kE=
github.com/ysmood/gson v0.7.3/go.mod h1:3Kzs5zDl21g5F/BlLTNcuAGAYLKt2lV5G8D1zF3RNmg=
github.com/ysmood/leakless v0.9.0 h1:qxCG5VirSBvmi3uynXFkcnLMzkphdh3xx5FtrORwDCU=
github.com/ysmood/leakless v0.9.0/go.mod h1:R8iAXPRaG97QJwqxs74RdwzcRHT1SWCGTNqY8q0JvMQ=
github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
golang.org/x/crypto v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDfU=
golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
golang.org/x/mod v0.33.0 h1:tHFzIWbBifEmbwtGz65eaWyGiGZatSrT9prnU8DbVL8=
golang.org/x/mod v0.33.0/go.mod h1:swjeQEj+6r7fODbD2cqrnje9PnziFuw4bmLbBZFrQ5w=
golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.19.0 h1:vV+1eWNmZ5geRlYjzm2adRgW2/mcpevXNg50YZtPCE4=
golang.org/x/sync v0.19.0/go.mod h1:9KTHXmSnoGruLpwFjVSX0lNNA75CykiMECbovNTZqGI=
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.17.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.42.0 h1:omrd2nAlyT5ESRdCLYdm3+fMfNFE/+Rf4bDIQImRJeo=
golang.org/x/sys v0.42.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
golang.org/x/term v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo=
golang.org/x/term v0.17.0/go.mod h1:lLRBjIVuehSbZlaOtGMbcMncT+aqLLLmKrsjNrUguwk=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
golang.org/x/tools v0.42.0 h1:uNgphsn75Tdz5Ji2q36v/nsFSfR/9BRFvqhGBaJGd5k=
golang.org/x/tools v0.42.0/go.mod h1:Ma6lCIwGZvHK6XtgbswSoWroEkhugApmsXyrUmBhfr0=
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
modernc.org/cc/v4 v4.27.1 h1:9W30zRlYrefrDV2JE2O8VDtJ1yPGownxciz5rrbQZis=
modernc.org/cc/v4 v4.27.1/go.mod h1:uVtb5OGqUKpoLWhqwNQo/8LwvoiEBLvZXIQ/SmO6mL0=
modernc.org/ccgo/v4 v4.32.0 h1:hjG66bI/kqIPX1b2yT6fr/jt+QedtP2fqojG2VrFuVw=

View File

@ -25,7 +25,8 @@ func NewProvider(cfg config.BridgeConfig) (Provider, error) {
case "cursor":
return cursor.NewProvider(cfg), nil
case "gemini-web":
return geminiweb.NewProvider(cfg), nil
// 使用新的 Playwright provider
return geminiweb.NewPlaywrightProvider(cfg)
default:
return nil, fmt.Errorf("unknown provider: %s", providerType)
}

View File

@ -0,0 +1,392 @@
package geminiweb
import (
"context"
"cursor-api-proxy/internal/apitypes"
"cursor-api-proxy/internal/config"
"fmt"
"os"
"path/filepath"
"strings"
"sync"
"time"
"github.com/playwright-community/playwright-go"
)
// PlaywrightProvider 使用 Playwright 的 Gemini Provider
type PlaywrightProvider struct {
cfg config.BridgeConfig
pw *playwright.Playwright
browser playwright.Browser
context playwright.BrowserContext
page playwright.Page
mu sync.Mutex
userDataDir string
}
var (
playwrightInstance *playwright.Playwright
playwrightOnce sync.Once
playwrightErr error
)
// NewPlaywrightProvider 建立新的 Playwright Provider
func NewPlaywrightProvider(cfg config.BridgeConfig) (*PlaywrightProvider, error) {
// 確保 Playwright 已初始化(單例)
playwrightOnce.Do(func() {
playwrightInstance, playwrightErr = playwright.Run()
if playwrightErr != nil {
playwrightErr = fmt.Errorf("failed to run playwright: %w", playwrightErr)
}
})
if playwrightErr != nil {
return nil, playwrightErr
}
// 清理 Chrome 鎖檔案
userDataDir := filepath.Join(cfg.GeminiAccountDir, "default-session")
cleanLockFiles(userDataDir)
// 確保目錄存在
if err := os.MkdirAll(userDataDir, 0755); err != nil {
return nil, fmt.Errorf("failed to create user data dir: %w", err)
}
return &PlaywrightProvider{
cfg: cfg,
pw: playwrightInstance,
userDataDir: userDataDir,
}, nil
}
// getName 返回 Provider 名稱
func (p *PlaywrightProvider) Name() string {
return "gemini-web"
}
// launchIfNeeded 如果需要則啟動瀏覽器
func (p *PlaywrightProvider) launchIfNeeded() error {
p.mu.Lock()
defer p.mu.Unlock()
if p.context != nil && p.page != nil {
return nil
}
fmt.Println("[GeminiWeb] Launching Chromium...")
// 使用 LaunchPersistentContext自動保存 session
context, err := p.pw.Chromium.LaunchPersistentContext(p.userDataDir,
playwright.BrowserTypeLaunchPersistentContextOptions{
Headless: playwright.Bool(!p.cfg.GeminiBrowserVisible),
Args: []string{
"--no-first-run",
"--no-default-browser-check",
"--disable-background-networking",
"--disable-extensions",
"--disable-plugins",
"--disable-sync",
},
})
if err != nil {
return fmt.Errorf("failed to launch persistent context: %w", err)
}
p.context = context
// 取得或建立頁面
pages := context.Pages()
if len(pages) > 0 {
p.page = pages[0]
} else {
page, err := context.NewPage()
if err != nil {
_ = context.Close()
return fmt.Errorf("failed to create page: %w", err)
}
p.page = page
}
fmt.Println("[GeminiWeb] Browser launched")
return nil
}
// Generate 生成回應
func (p *PlaywrightProvider) Generate(ctx context.Context, model string, messages []apitypes.Message, tools []apitypes.Tool, cb func(apitypes.StreamChunk)) error {
fmt.Printf("[GeminiWeb] Starting generation with model: %s\n", model)
// 1. 確保瀏覽器已啟動
if err := p.launchIfNeeded(); err != nil {
return fmt.Errorf("failed to launch browser: %w", err)
}
// 2. 導航到 Gemini如果需要
currentURL := p.page.URL()
if !strings.Contains(currentURL, "gemini.google.com") {
fmt.Println("[GeminiWeb] Navigating to Gemini...")
if _, err := p.page.Goto("https://gemini.google.com/app", playwright.PageGotoOptions{
WaitUntil: playwright.WaitUntilStateNetworkidle,
Timeout: playwright.Float(30000),
}); err != nil {
return fmt.Errorf("failed to navigate: %w", err)
}
time.Sleep(2 * time.Second)
}
// 3. 檢查登入狀態
fmt.Println("[GeminiWeb] Checking login status...")
loggedIn := p.isLoggedIn()
if !loggedIn {
fmt.Println("[GeminiWeb] Not logged in, continuing anyway")
if p.cfg.GeminiBrowserVisible {
fmt.Println("\n========================================")
fmt.Println("Browser is open. You can:")
fmt.Println("1. Log in to Gemini now")
fmt.Println("2. Continue without login")
fmt.Println("========================================\n")
}
} else {
fmt.Println("[GeminiWeb] Logged in")
}
// 4. 等待頁面就緒
if err := p.waitForReady(); err != nil {
fmt.Printf("[GeminiWeb] Warning: %v\n", err)
}
// 5. 建構提示詞
prompt := buildPromptFromMessagesPlaywright(messages)
fmt.Printf("[GeminiWeb] Typing prompt (%d chars)...\n", len(prompt))
// 6. 輸入文字(使用 Playwright 的 Auto-wait
if err := p.typeInput(prompt); err != nil {
return fmt.Errorf("failed to type: %w", err)
}
// 7. 發送訊息
fmt.Println("[GeminiWeb] Sending message...")
if err := p.sendMessage(); err != nil {
return fmt.Errorf("failed to send: %w", err)
}
// 8. 提取回應
fmt.Println("[GeminiWeb] Waiting for response...")
response, err := p.extractResponse()
if err != nil {
return fmt.Errorf("failed to extract response: %w", err)
}
// 9. 回調
cb(apitypes.StreamChunk{Type: apitypes.ChunkText, Text: response})
cb(apitypes.StreamChunk{Type: apitypes.ChunkDone, Done: true})
fmt.Printf("[GeminiWeb] Response complete (%d chars)\n", len(response))
return nil
}
// Close 關閉 Provider
func (p *PlaywrightProvider) Close() error {
p.mu.Lock()
defer p.mu.Unlock()
if p.context != nil {
if err := p.context.Close(); err != nil {
return err
}
p.context = nil
p.page = nil
}
return nil
}
// isLoggedIn 檢查是否已登入
func (p *PlaywrightProvider) isLoggedIn() bool {
// 嘗試找輸入框(登入狀態的主要特徵)
selectors := []string{
".ProseMirror",
"rich-textarea",
"div[role='textbox']",
"div[contenteditable='true']",
"textarea",
}
for _, sel := range selectors {
if _, err := p.page.WaitForSelector(sel, playwright.PageWaitForSelectorOptions{
Timeout: playwright.Float(3000),
}); err == nil {
return true
}
}
return false
}
// waitForReady 等待頁面就緒
func (p *PlaywrightProvider) waitForReady() error {
fmt.Println("[GeminiWeb] Checking if page is ready...")
// 等待停止按鈕消失(如果存在)
_, _ = p.page.WaitForSelector("button[aria-label*='Stop']", playwright.PageWaitForSelectorOptions{
State: playwright.WaitForSelectorStateDetached,
Timeout: playwright.Float(5000),
})
fmt.Println("[GeminiWeb] Page is ready")
return nil
}
// typeInput 輸入文字(使用 Playwright 的 Auto-wait
func (p *PlaywrightProvider) typeInput(text string) error {
fmt.Println("[GeminiWeb] Looking for input field...")
selectors := []string{
".ProseMirror",
"rich-textarea",
"div[role='textbox'][contenteditable='true']",
"div[contenteditable='true']",
"textarea",
}
var inputLocator playwright.Locator
var found bool
for _, sel := range selectors {
fmt.Printf(" Trying: %s\n", sel)
locator := p.page.Locator(sel)
if err := locator.WaitFor(playwright.LocatorWaitForOptions{
Timeout: playwright.Float(3000),
}); err == nil {
inputLocator = locator
found = true
fmt.Printf(" ✓ Found with: %s\n", sel)
break
}
}
if !found {
// 顯示 debug 信息
url := p.page.URL()
title, _ := p.page.Title()
return fmt.Errorf("input field not found (URL=%s, Title=%s)", url, title)
}
// Focus 並填充Playwright 自動等待)
fmt.Printf("[GeminiWeb] Typing %d chars...\n", len(text))
if err := inputLocator.Fill(text); err != nil {
return fmt.Errorf("failed to fill: %w", err)
}
fmt.Println("[GeminiWeb] Input complete")
return nil
}
// sendMessage 發送訊息
func (p *PlaywrightProvider) sendMessage() error {
// 方法 1: 按 Enter最可靠
if err := p.page.Keyboard().Press("Enter"); err != nil {
return fmt.Errorf("failed to press Enter: %w", err)
}
time.Sleep(200 * time.Millisecond)
// 方法 2: 嘗試點擊發送按鈕(補強)
_, _ = p.page.Evaluate(`
() => {
const keywords = ['發送', 'Send', '傳送'];
const buttons = Array.from(document.querySelectorAll('button, [role="button"]'));
for (const btn of buttons) {
const text = (btn.innerText || btn.textContent || '').trim();
const label = (btn.getAttribute('aria-label') || '').trim();
// 跳過停止按鈕
if (['停止', 'Stop', '中斷'].includes(text) || label.toLowerCase().includes('stop')) {
continue;
}
if (keywords.some(kw => text.includes(kw) || label.includes(kw))) {
btn.click();
return true;
}
}
return false;
}
`)
return nil
}
// extractResponse 提取回應
func (p *PlaywrightProvider) extractResponse() (string, error) {
selectors := []string{
".model-response-text",
".message-content",
".markdown",
".prose",
"model-response",
}
var lastText string
lastUpdate := time.Now()
timeout := 120 * time.Second
startTime := time.Now()
for time.Since(startTime) < timeout {
time.Sleep(500 * time.Millisecond)
// 嘗試所有選擇器
for _, sel := range selectors {
locator := p.page.Locator(sel)
count, _ := locator.Count()
if count > 0 {
// 取最後一個元素
lastEl := locator.Last()
text, err := lastEl.TextContent()
if err != nil {
continue
}
text = strings.TrimSpace(text)
if text != "" && len(text) > len(lastText) {
lastText = text
lastUpdate = time.Now()
fmt.Printf("[GeminiWeb] Response length: %d\n", len(text))
}
}
}
// 檢查是否完成2秒內無新內容
if time.Since(lastUpdate) > 2*time.Second && lastText != "" {
// 最終檢查:停止按鈕是否還存在
stopBtn := p.page.Locator("button[aria-label*='Stop'], button[aria-label*='停止']")
count, _ := stopBtn.Count()
if count == 0 {
return lastText, nil
}
}
}
if lastText != "" {
return lastText, nil
}
return "", fmt.Errorf("response timeout")
}
// buildPromptFromMessages 從訊息列表建構提示詞
func buildPromptFromMessagesPlaywright(messages []apitypes.Message) string {
var prompt string
for _, m := range messages {
switch m.Role {
case "system":
prompt += "System: " + m.Content + "\n\n"
case "user":
prompt += m.Content + "\n\n"
case "assistant":
prompt += "Assistant: " + m.Content + "\n\n"
}
}
return prompt
}