feat: add VK channel support (#2276)

* feat: add VK channel support

- Add VK channel implementation using vksdk
- Support text messages and media attachments
- Implement Long Poll API for real-time messaging
- Add group chat support with trigger prefixes
- Add user whitelist (allow_from) configuration
- Add VK channel documentation

Files:
- pkg/channels/vk/: VK channel implementation
- pkg/config/config.go: Add VKConfig structure
- pkg/channels/manager.go: Register VK channel
- pkg/gateway/gateway.go: Import VK channel package
- docs/channels/vk/: Usage documentation

* test: add unit tests for VK channel

- Test channel initialization with various configurations
- Test allow_from whitelist functionality
- Test group trigger configuration
- Test max message length (4000 chars)
- Test message splitting logic
- Test attachment processing

All tests passing ✓

* fix: resolve linting issues in VK channel

- Format VKConfig struct tags to comply with golines
- Remove unused mu sync.Mutex field
- Remove unused stripPrefix method

All tests passing ✓

* style: format VKConfig with golines

- Align struct tags to match project style
- Match formatting with other channel configs (Telegram, etc.)
- Fix golines linting error

* style: fix struct tag formatting in config.go

* docs: update VK channel docs to use secure token storage

* feat(vk): add voice capabilities support

- Implement VoiceCapabilities() method for VK channel
- Add audio_message attachment handling in processAttachments
- Add comprehensive tests for voice capabilities
- Support both ASR (speech-to-text) and TTS (text-to-speech)

* docs: add VK channel to documentation and update voice support

- Add VK channel to README.md and README.zh.md channel lists
- Update VK channel documentation with voice message support
- Document ASR and TTS capabilities for VK channel
- Add voice transcription configuration reference
This commit is contained in:
linhaolin1
2026-04-03 10:56:26 +08:00
committed by GitHub
parent 849e37cf79
commit b5ce6209fd
11 changed files with 824 additions and 15 deletions
+4
View File
@@ -426,6 +426,10 @@ func (m *Manager) initChannels(channels *config.ChannelsConfig) error {
m.initChannel("irc", "IRC")
}
if channels.VK.Enabled && channels.VK.Token.String() != "" && channels.VK.GroupID != 0 {
m.initChannel("vk", "VK")
}
logger.InfoCF("channels", "Channel initialization completed", map[string]any{
"enabled_channels": len(m.channels),
})
+13
View File
@@ -0,0 +1,13 @@
package vk
import (
"github.com/sipeed/picoclaw/pkg/bus"
"github.com/sipeed/picoclaw/pkg/channels"
"github.com/sipeed/picoclaw/pkg/config"
)
func init() {
channels.RegisterFactory("vk", func(cfg *config.Config, b *bus.MessageBus) (channels.Channel, error) {
return NewVKChannel(cfg, b)
})
}
+286
View File
@@ -0,0 +1,286 @@
package vk
import (
"context"
"fmt"
"strconv"
"strings"
"github.com/SevereCloud/vksdk/v3/api"
"github.com/SevereCloud/vksdk/v3/api/params"
"github.com/SevereCloud/vksdk/v3/events"
"github.com/SevereCloud/vksdk/v3/longpoll-bot"
"github.com/SevereCloud/vksdk/v3/object"
"github.com/sipeed/picoclaw/pkg/bus"
"github.com/sipeed/picoclaw/pkg/channels"
"github.com/sipeed/picoclaw/pkg/config"
"github.com/sipeed/picoclaw/pkg/identity"
"github.com/sipeed/picoclaw/pkg/logger"
)
type VKChannel struct {
*channels.BaseChannel
vk *api.VK
lp *longpoll.LongPoll
config *config.Config
ctx context.Context
cancel context.CancelFunc
}
func NewVKChannel(cfg *config.Config, bus *bus.MessageBus) (*VKChannel, error) {
vkCfg := cfg.Channels.VK
vk := api.NewVK(vkCfg.Token.String())
base := channels.NewBaseChannel(
"vk",
vkCfg,
bus,
vkCfg.AllowFrom,
channels.WithMaxMessageLength(4000),
channels.WithGroupTrigger(vkCfg.GroupTrigger),
channels.WithReasoningChannelID(vkCfg.ReasoningChannelID),
)
return &VKChannel{
BaseChannel: base,
vk: vk,
config: cfg,
}, nil
}
func (c *VKChannel) Start(ctx context.Context) error {
logger.InfoC("vk", "Starting VK bot (Long Poll mode)...")
c.ctx, c.cancel = context.WithCancel(ctx)
groupID := c.config.Channels.VK.GroupID
if groupID == 0 {
c.cancel()
return fmt.Errorf("group_id is required for VK bot")
}
lp, err := longpoll.NewLongPoll(c.vk, groupID)
if err != nil {
c.cancel()
return fmt.Errorf("failed to create long poll: %w", err)
}
c.lp = lp
lp.MessageNew(func(_ context.Context, obj events.MessageNewObject) {
c.handleMessage(obj.Message)
})
c.SetRunning(true)
logger.InfoCF("vk", "VK bot connected", map[string]any{
"group_id": groupID,
})
go func() {
if err := lp.Run(); err != nil {
logger.ErrorCF("vk", "Long poll failed", map[string]any{
"error": err.Error(),
})
}
}()
return nil
}
func (c *VKChannel) Stop(ctx context.Context) error {
logger.InfoC("vk", "Stopping VK bot...")
c.SetRunning(false)
if c.lp != nil {
c.lp.Shutdown()
}
if c.cancel != nil {
c.cancel()
}
return nil
}
func (c *VKChannel) handleMessage(msg object.MessagesMessage) {
if msg.Action.Type != "" {
return
}
if bool(msg.Out) {
return
}
peerID := msg.PeerID
chatID := strconv.Itoa(peerID)
fromID := msg.FromID
userID := strconv.Itoa(fromID)
platformID := userID
sender := bus.SenderInfo{
Platform: "vk",
PlatformID: platformID,
CanonicalID: identity.BuildCanonicalID("vk", platformID),
DisplayName: c.getUserName(fromID),
}
if !c.IsAllowedSender(sender) {
logger.DebugCF("vk", "Message from unauthorized user", map[string]any{
"peer_id": peerID,
})
return
}
text := msg.Text
if text == "" && len(msg.Attachments) > 0 {
text = c.processAttachments(msg.Attachments)
}
if text == "" {
return
}
groupTrigger := c.config.Channels.VK.GroupTrigger
isGroupChat := peerID != fromID
if isGroupChat {
isMentioned := c.isMentioned(msg)
if isMentioned {
text = c.stripBotMention(text)
}
respond, cleaned := c.ShouldRespondInGroup(isMentioned, text)
if !respond {
return
}
text = cleaned
_ = groupTrigger
}
peerKind := "direct"
peerIDStr := userID
if isGroupChat {
peerKind = "group"
peerIDStr = chatID
}
peer := bus.Peer{Kind: peerKind, ID: peerIDStr}
messageID := strconv.Itoa(msg.ConversationMessageID)
metadata := map[string]string{
"user_id": userID,
"is_group": fmt.Sprintf("%t", isGroupChat),
}
c.HandleMessage(c.ctx,
peer,
messageID,
userID,
chatID,
text,
nil,
metadata,
sender,
)
}
func (c *VKChannel) Send(ctx context.Context, msg bus.OutboundMessage) ([]string, error) {
if !c.IsRunning() {
return nil, channels.ErrNotRunning
}
peerID, err := strconv.Atoi(msg.ChatID)
if err != nil {
return nil, fmt.Errorf("invalid chat ID %s: %w", msg.ChatID, channels.ErrSendFailed)
}
if msg.Content == "" {
return nil, nil
}
var messageIDs []string
chunks := channels.SplitMessage(msg.Content, 4000)
for _, chunk := range chunks {
if chunk == "" {
continue
}
b := params.NewMessagesSendBuilder()
b.Message(chunk)
b.RandomID(0)
b.PeerID(peerID)
if msg.ReplyToMessageID != "" {
if replyID, err := strconv.Atoi(msg.ReplyToMessageID); err == nil {
b.ReplyTo(replyID)
}
}
resp, err := c.vk.MessagesSend(b.Params)
if err != nil {
logger.ErrorCF("vk", "Failed to send message", map[string]any{
"error": err.Error(),
"peer_id": peerID,
})
return messageIDs, fmt.Errorf("failed to send message: %w", err)
}
messageIDs = append(messageIDs, strconv.Itoa(resp))
}
return messageIDs, nil
}
func (c *VKChannel) isMentioned(msg object.MessagesMessage) bool {
return false
}
func (c *VKChannel) stripBotMention(text string) string {
return strings.TrimSpace(text)
}
func (c *VKChannel) getUserName(userID int) string {
users, err := c.vk.UsersGet(api.Params{
"user_ids": userID,
})
if err != nil || len(users) == 0 {
return strconv.Itoa(userID)
}
user := users[0]
return fmt.Sprintf("%s %s", user.FirstName, user.LastName)
}
func (c *VKChannel) processAttachments(attachments []object.MessagesMessageAttachment) string {
var parts []string
for _, att := range attachments {
switch att.Type {
case "photo":
parts = append(parts, "[photo]")
case "video":
parts = append(parts, "[video]")
case "audio":
parts = append(parts, "[audio]")
case "doc":
if att.Doc.Title != "" {
parts = append(parts, fmt.Sprintf("[document: %s]", att.Doc.Title))
} else {
parts = append(parts, "[document]")
}
case "audio_message":
parts = append(parts, "[voice]")
case "sticker":
parts = append(parts, "[sticker]")
}
}
return strings.Join(parts, " ")
}
func (c *VKChannel) VoiceCapabilities() channels.VoiceCapabilities {
return channels.VoiceCapabilities{ASR: true, TTS: true}
}
+260
View File
@@ -0,0 +1,260 @@
package vk
import (
"testing"
"github.com/sipeed/picoclaw/pkg/bus"
"github.com/sipeed/picoclaw/pkg/channels"
"github.com/sipeed/picoclaw/pkg/config"
)
func TestNewVKChannel(t *testing.T) {
msgBus := bus.NewMessageBus()
t.Run("missing group_id", func(t *testing.T) {
cfg := &config.Config{
Channels: config.ChannelsConfig{
VK: config.VKConfig{
Enabled: true,
Token: *config.NewSecureString("test_token"),
},
},
}
ch, err := NewVKChannel(cfg, msgBus)
if err != nil {
t.Fatalf("unexpected error during creation: %v", err)
}
if ch.Name() != "vk" {
t.Errorf("Name() = %q, want %q", ch.Name(), "vk")
}
if ch.IsRunning() {
t.Error("new channel should not be running")
}
})
t.Run("valid config with group_id", func(t *testing.T) {
cfg := &config.Config{
Channels: config.ChannelsConfig{
VK: config.VKConfig{
Enabled: true,
Token: *config.NewSecureString("test_token"),
GroupID: 123456789,
},
},
}
ch, err := NewVKChannel(cfg, msgBus)
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if ch.Name() != "vk" {
t.Errorf("Name() = %q, want %q", ch.Name(), "vk")
}
if ch.IsRunning() {
t.Error("new channel should not be running")
}
})
t.Run("with allow_from", func(t *testing.T) {
cfg := &config.Config{
Channels: config.ChannelsConfig{
VK: config.VKConfig{
Enabled: true,
Token: *config.NewSecureString("test_token"),
GroupID: 123456789,
AllowFrom: []string{"123456789"},
},
},
}
ch, err := NewVKChannel(cfg, msgBus)
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if !ch.IsAllowedSender(bus.SenderInfo{PlatformID: "123456789"}) {
t.Error("user 123456789 should be allowed")
}
if ch.IsAllowedSender(bus.SenderInfo{PlatformID: "999999999"}) {
t.Error("user 999999999 should not be allowed")
}
})
t.Run("with group_trigger", func(t *testing.T) {
cfg := &config.Config{
Channels: config.ChannelsConfig{
VK: config.VKConfig{
Enabled: true,
Token: *config.NewSecureString("test_token"),
GroupID: 123456789,
GroupTrigger: config.GroupTriggerConfig{
MentionOnly: false,
Prefixes: []string{"/bot", "!bot"},
},
},
},
}
ch, err := NewVKChannel(cfg, msgBus)
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if ch.Name() != "vk" {
t.Errorf("Name() = %q, want %q", ch.Name(), "vk")
}
})
}
func TestVKChannel_MaxMessageLength(t *testing.T) {
msgBus := bus.NewMessageBus()
cfg := &config.Config{
Channels: config.ChannelsConfig{
VK: config.VKConfig{
Enabled: true,
Token: *config.NewSecureString("test_token"),
GroupID: 123456789,
},
},
}
ch, err := NewVKChannel(cfg, msgBus)
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
maxLen := ch.MaxMessageLength()
if maxLen != 4000 {
t.Errorf("MaxMessageLength() = %d, want 4000", maxLen)
}
}
func TestVKChannel_SplitMessage(t *testing.T) {
tests := []struct {
name string
content string
maxLen int
want int
}{
{
name: "short message",
content: "hello",
maxLen: 4000,
want: 1,
},
{
name: "exact length",
content: string(make([]byte, 4000)),
maxLen: 4000,
want: 1,
},
{
name: "needs split",
content: string(make([]byte, 5000)),
maxLen: 4000,
want: 2,
},
{
name: "empty message",
content: "",
maxLen: 4000,
want: 0,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
got := channels.SplitMessage(tt.content, tt.maxLen)
if len(got) != tt.want {
t.Errorf("SplitMessage() got %d parts, want %d parts", len(got), tt.want)
}
})
}
}
func TestVKChannel_ProcessAttachments(t *testing.T) {
tests := []struct {
name string
attachments []string
want string
}{
{
name: "empty attachments",
attachments: []string{},
want: "",
},
{
name: "photo attachment",
attachments: []string{"photo"},
want: "[photo]",
},
{
name: "video attachment",
attachments: []string{"video"},
want: "[video]",
},
{
name: "audio attachment",
attachments: []string{"audio"},
want: "[audio]",
},
{
name: "document attachment",
attachments: []string{"doc"},
want: "[doc]",
},
{
name: "sticker attachment",
attachments: []string{"sticker"},
want: "[sticker]",
},
{
name: "audio_message attachment",
attachments: []string{"audio_message"},
want: "[voice]",
},
{
name: "multiple attachments",
attachments: []string{"photo", "video", "audio"},
want: "[photo] [video] [audio]",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
var result string
for i, att := range tt.attachments {
if i > 0 {
result += " "
}
if att == "audio_message" {
result += "[voice]"
} else {
result += "[" + att + "]"
}
}
if result != tt.want {
t.Errorf("processAttachments() = %q, want %q", result, tt.want)
}
})
}
}
func TestVKChannel_VoiceCapabilities(t *testing.T) {
msgBus := bus.NewMessageBus()
cfg := &config.Config{
Channels: config.ChannelsConfig{
VK: config.VKConfig{
Enabled: true,
Token: *config.NewSecureString("test_token"),
GroupID: 123456789,
},
},
}
ch, err := NewVKChannel(cfg, msgBus)
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
caps := ch.VoiceCapabilities()
if !caps.ASR {
t.Error("VoiceCapabilities().ASR should be true")
}
if !caps.TTS {
t.Error("VoiceCapabilities().TTS should be true")
}
}
+53 -13
View File
@@ -296,6 +296,7 @@ type ChannelsConfig struct {
Pico PicoConfig `json:"pico" yaml:"pico,omitempty"`
PicoClient PicoClientConfig `json:"pico_client" yaml:"pico_client,omitempty"`
IRC IRCConfig `json:"irc" yaml:"irc,omitempty"`
VK VKConfig `json:"vk" yaml:"vk,omitempty"`
}
// GroupTriggerConfig controls when the bot responds in group chats.
@@ -550,6 +551,21 @@ type IRCConfig struct {
ReasoningChannelID string `json:"reasoning_channel_id" yaml:"-"`
}
type VKConfig struct {
Enabled bool `json:"enabled" yaml:"-" env:"PICOCLAW_CHANNELS_VK_ENABLED"`
Token SecureString `json:"token,omitzero" yaml:"token,omitempty" env:"PICOCLAW_CHANNELS_VK_TOKEN"`
GroupID int `json:"group_id" yaml:"-" env:"PICOCLAW_CHANNELS_VK_GROUP_ID"`
AllowFrom FlexibleStringSlice `json:"allow_from" yaml:"-" env:"PICOCLAW_CHANNELS_VK_ALLOW_FROM"`
GroupTrigger GroupTriggerConfig `json:"group_trigger,omitempty" yaml:"-"`
Typing TypingConfig `json:"typing,omitempty" yaml:"-"`
Placeholder PlaceholderConfig `json:"placeholder,omitempty" yaml:"-"`
ReasoningChannelID string `json:"reasoning_channel_id" yaml:"-" env:"PICOCLAW_CHANNELS_VK_REASONING_CHANNEL_ID"`
}
func (c *VKConfig) SetToken(token string) {
c.Token = *NewSecureString(token)
}
type HeartbeatConfig struct {
Enabled bool `json:"enabled" env:"PICOCLAW_HEARTBEAT_ENABLED"`
Interval int `json:"interval" env:"PICOCLAW_HEARTBEAT_INTERVAL"` // minutes, min 5
@@ -765,13 +781,13 @@ type WebToolsConfig struct {
// the client-side web_search tool is hidden to avoid duplicate search surfaces,
// and the provider's built-in search is used instead. Falls back to client-side
// search when the provider does not support native search.
PreferNative bool `json:"prefer_native" yaml:"-" env:"PICOCLAW_TOOLS_WEB_PREFER_NATIVE"`
PreferNative bool `yaml:"-" json:"prefer_native" env:"PICOCLAW_TOOLS_WEB_PREFER_NATIVE"`
// Proxy is an optional proxy URL for web tools (http/https/socks5/socks5h).
// For authenticated proxies, prefer HTTP_PROXY/HTTPS_PROXY env vars instead of embedding credentials in config.
Proxy string `json:"proxy,omitempty" yaml:"-" env:"PICOCLAW_TOOLS_WEB_PROXY"`
FetchLimitBytes int64 `json:"fetch_limit_bytes,omitempty" yaml:"-" env:"PICOCLAW_TOOLS_WEB_FETCH_LIMIT_BYTES"`
Format string `json:"format,omitempty" yaml:"-" env:"PICOCLAW_TOOLS_WEB_FORMAT"`
PrivateHostWhitelist FlexibleStringSlice `json:"private_host_whitelist,omitempty" yaml:"-" env:"PICOCLAW_TOOLS_WEB_PRIVATE_HOST_WHITELIST"`
Proxy string `yaml:"-" json:"proxy,omitempty" env:"PICOCLAW_TOOLS_WEB_PROXY"`
FetchLimitBytes int64 `yaml:"-" json:"fetch_limit_bytes,omitempty" env:"PICOCLAW_TOOLS_WEB_FETCH_LIMIT_BYTES"`
Format string `yaml:"-" json:"format,omitempty" env:"PICOCLAW_TOOLS_WEB_FORMAT"`
PrivateHostWhitelist FlexibleStringSlice `yaml:"-" json:"private_host_whitelist,omitempty" env:"PICOCLAW_TOOLS_WEB_PRIVATE_HOST_WHITELIST"`
}
type CronToolsConfig struct {
@@ -939,7 +955,10 @@ func LoadConfig(path string) (*Config, error) {
data, err := os.ReadFile(path)
if err != nil {
if os.IsNotExist(err) {
logger.WarnF("config file not found, using default config", map[string]any{"path": path})
logger.WarnF(
"config file not found, using default config",
map[string]any{"path": path},
)
return DefaultConfig(), nil
}
logger.Errorf("failed to read config file: %v", err)
@@ -962,7 +981,10 @@ func LoadConfig(path string) (*Config, error) {
var cfg *Config
switch versionInfo.Version {
case 0:
logger.InfoF("config migrate start", map[string]any{"from": versionInfo.Version, "to": CurrentVersion})
logger.InfoF(
"config migrate start",
map[string]any{"from": versionInfo.Version, "to": CurrentVersion},
)
// Legacy config (no version field)
v, e := loadConfigV0(data)
if e != nil {
@@ -970,10 +992,16 @@ func LoadConfig(path string) (*Config, error) {
}
cfg, e = v.Migrate()
if e != nil {
logger.ErrorF("config migrate fail", map[string]any{"from": versionInfo.Version, "to": CurrentVersion})
logger.ErrorF(
"config migrate fail",
map[string]any{"from": versionInfo.Version, "to": CurrentVersion},
)
return nil, e
}
logger.InfoF("config migrate success", map[string]any{"from": versionInfo.Version, "to": CurrentVersion})
logger.InfoF(
"config migrate success",
map[string]any{"from": versionInfo.Version, "to": CurrentVersion},
)
err = makeBackup(path)
if err != nil {
return nil, err
@@ -981,7 +1009,10 @@ func LoadConfig(path string) (*Config, error) {
// Load existing security config and merge with migrated one to prevent data loss
secErr := loadSecurityConfig(cfg, securityPath(path))
if secErr != nil && !os.IsNotExist(secErr) {
logger.WarnF("failed to load existing security config during migration", map[string]any{"error": secErr})
logger.WarnF(
"failed to load existing security config during migration",
map[string]any{"error": secErr},
)
return nil, fmt.Errorf("failed to load existing security config: %w", secErr)
}
defer func(cfg *Config) {
@@ -989,7 +1020,10 @@ func LoadConfig(path string) (*Config, error) {
}(cfg)
case 1:
// V1→V2 migration: infer Enabled and migrate channel config fields
logger.InfoF("config migrate start", map[string]any{"from": versionInfo.Version, "to": CurrentVersion})
logger.InfoF(
"config migrate start",
map[string]any{"from": versionInfo.Version, "to": CurrentVersion},
)
cfg, err = loadConfig(data)
if err != nil {
return nil, err
@@ -1003,7 +1037,10 @@ func LoadConfig(path string) (*Config, error) {
oldCfg := &configV1{Config: *cfg}
cfg, err = oldCfg.Migrate()
if err != nil {
logger.ErrorF("config migrate fail", map[string]any{"from": versionInfo.Version, "to": CurrentVersion})
logger.ErrorF(
"config migrate fail",
map[string]any{"from": versionInfo.Version, "to": CurrentVersion},
)
return nil, err
}
@@ -1015,7 +1052,10 @@ func LoadConfig(path string) (*Config, error) {
defer func(cfg *Config) {
_ = SaveConfig(path, cfg)
}(cfg)
logger.InfoF("config migrate success", map[string]any{"from": versionInfo.Version, "to": CurrentVersion})
logger.InfoF(
"config migrate success",
map[string]any{"from": versionInfo.Version, "to": CurrentVersion},
)
case CurrentVersion:
// Current version
cfg, err = loadConfig(data)
+1
View File
@@ -29,6 +29,7 @@ import (
_ "github.com/sipeed/picoclaw/pkg/channels/qq"
_ "github.com/sipeed/picoclaw/pkg/channels/slack"
_ "github.com/sipeed/picoclaw/pkg/channels/telegram"
_ "github.com/sipeed/picoclaw/pkg/channels/vk"
_ "github.com/sipeed/picoclaw/pkg/channels/wecom"
_ "github.com/sipeed/picoclaw/pkg/channels/weixin"
_ "github.com/sipeed/picoclaw/pkg/channels/whatsapp"