Merge branch 'steipete:main' into main

This commit is contained in:
Dan 2026-01-02 19:00:21 +02:00 committed by GitHub
commit b92f70c52b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
95 changed files with 2590 additions and 256 deletions

1
.gitignore vendored
View File

@ -45,3 +45,4 @@ apps/ios/*.dSYM.zip
# provisioning profiles (local)
apps/ios/*.mobileprovision
.env

View File

@ -14,12 +14,14 @@
- Sessions: group keys now use `surface:group:<id>` / `surface:channel:<id>`; legacy `group:*` keys migrate on next message; `groupdm` keys are no longer recognized.
- Discord: remove legacy `discord.allowFrom`, `discord.guildAllowFrom`, and `discord.requireMention`; use `discord.dm` + `discord.guilds`.
- Providers: Discord/Telegram no longer auto-start from env tokens alone; add `discord: { enabled: true }` / `telegram: { enabled: true }` to your config when using `DISCORD_BOT_TOKEN` / `TELEGRAM_BOT_TOKEN`.
- Config: remove `routing.allowFrom`; use `whatsapp.allowFrom` instead (run `clawdis doctor` to migrate).
### Features
- Talk mode: continuous speech conversations (macOS/iOS/Android) with ElevenLabs TTS, reply directives, and optional interrupt-on-speech.
- UI: add optional `ui.seamColor` accent to tint the Talk Mode side bubble (macOS/iOS/Android).
- Nix mode: opt-in declarative config + read-only settings UI when `CLAWDIS_NIX_MODE=1` (thanks @joshp123 for the persistence — earned my trust; I'll merge these going forward).
- Agent runtime: accept legacy `Z_AI_API_KEY` for Z.AI provider auth (maps to `ZAI_API_KEY`).
- Discord: add user-installed slash command handling with per-user sessions and auto-registration (#94) — thanks @thewilloftheshadow.
- Discord: add DM enable/allowlist plus guild channel/user/guild allowlists with id/name matching.
- Signal: add `signal-cli` JSON-RPC support for send/receive via the Signal provider.
- iMessage: add imsg JSON-RPC integration (stdio), chat_id routing, and group chat support.
@ -43,11 +45,16 @@
### Fixes
- Chat UI: keep the chat scrolled to the latest message after switching sessions.
- CLI onboarding: persist gateway token in config so local CLI auth works; recommend auth Off unless you need multi-machine access.
- Control UI: accept a `?token=` URL param to auto-fill Gateway auth; onboarding now opens the dashboard with token auth when configured.
- Agent prompt: remove hardcoded user name in system prompt example.
- Chat UI: add extra top padding before the first message bubble in Web Chat (macOS/iOS/Android).
- Control UI: refine Web Chat session selector styling (chevron spacing + background).
- WebChat: stream live updates for sessions even when runs start outside the chat UI.
- Gateway CLI: read `CLAWDIS_GATEWAY_PASSWORD` from environment in `callGateway()` — allows `doctor`/`health` commands to auth without explicit `--password` flag.
- Gateway: add password auth support for remote gateway connections (thanks @jeffersonwarrior).
- Auto-reply: strip stray leading/trailing `HEARTBEAT_OK` from normal replies; drop short (≤ 30 chars) heartbeat acks.
- WhatsApp auto-reply: default to self-only when no config is present.
- Logging: trim provider prefix duplication in Discord/Signal/Telegram runtime log lines.
- Logging/Signal: treat signal-cli "Failed …" lines as errors in gateway logs.
- Discord: include recent guild context when replying to mentions and add `discord.historyLimit` to tune how many messages are captured.
@ -61,10 +68,17 @@
- CLI onboarding: explain Tailscale exposure options (Off/Serve/Funnel) and colorize provider status (linked/configured/needs setup).
- CLI onboarding: add provider primers (WhatsApp/Telegram/Discord/Signal) incl. Discord bot token setup steps.
- CLI onboarding: allow skipping the “install missing skill dependencies” selection without canceling the wizard.
- CLI onboarding: always prompt for WhatsApp `routing.allowFrom` and print (optionally open) the Control UI URL when done.
- CLI onboarding: always prompt for WhatsApp `whatsapp.allowFrom` and print (optionally open) the Control UI URL when done.
- CLI onboarding: detect gateway reachability and annotate Local/Remote choices (helps pick the right mode).
- macOS settings: colorize provider status subtitles to distinguish healthy vs degraded states.
- macOS: keep config writes on the main actor to satisfy Swift concurrency rules.
- macOS menu: show multi-line gateway error details, add an always-visible gateway row, avoid duplicate gateway status rows, suppress transient `cancelled` device refresh errors, and auto-recover the control channel on disconnect.
- macOS: log health refresh failures and recovery to make gateway issues easier to diagnose.
- macOS codesign: skip hardened runtime for ad-hoc signing and avoid empty options args (#70) — thanks @petter-b
- macOS codesign: include camera entitlement so permission prompts work in the menu bar app.
- Agent tools: map `camera.snap` JPEG payloads to `image/jpeg` to avoid MIME mismatch errors.
- Tests: cover `camera.snap` MIME mapping to prevent image/png vs image/jpeg mismatches.
- macOS camera: wait for exposure/white balance to settle before capturing a snap to avoid dark images.
- macOS packaging: move rpath config into swift build for reliability (#69) — thanks @petter-b
- macOS: prioritize main bundle for device resources to prevent crash (#73) — thanks @petter-b
- macOS remote: route settings through gateway config and avoid local config reads in remote mode.
@ -116,6 +130,7 @@
- iOS/Android Talk Mode: explicitly `chat.subscribe` when Talk Mode is active, so completion events arrive even if the Chat UI isnt open.
- Chat UI: refresh history when another client finishes a run in the same session, so Talk Mode + Voice Wake transcripts appear consistently.
- Gateway: `voice.transcript` now also maps agent bus output to `chat` events, ensuring chat UIs refresh for voice-triggered runs.
- Gateway: auto-migrate legacy config on startup (non-Nix); Nix mode hard-fails with a clear error when legacy keys are present.
- iOS/Android: show a centered Talk Mode orb overlay while Talk Mode is enabled.
- Gateway config: inject `talk.apiKey` from `ELEVENLABS_API_KEY`/shell profile so nodes can fetch it on demand.
- Canvas A2UI: tag requests with `platform=android|ios|macos` and boost Android canvas background contrast.

View File

@ -157,7 +157,7 @@ Minimal `~/.clawdis/clawdis.json`:
```json5
{
routing: {
whatsapp: {
allowFrom: ["+1234567890"]
}
}
@ -166,7 +166,7 @@ Minimal `~/.clawdis/clawdis.json`:
### WhatsApp
- Link the device: `pnpm clawdis login` (stores creds in `~/.clawdis/credentials`).
- Allowlist who can talk to the assistant via `routing.allowFrom`.
- Allowlist who can talk to the assistant via `whatsapp.allowFrom`.
### Telegram
@ -184,7 +184,7 @@ Minimal `~/.clawdis/clawdis.json`:
### Discord
- Set `DISCORD_BOT_TOKEN` or `discord.token` (env wins).
- Optional: set `discord.requireMention`, `discord.allowFrom`, or `discord.mediaMaxMb` as needed.
- Optional: set `discord.slashCommand`, `discord.dm.allowFrom`, `discord.guilds`, or `discord.mediaMaxMb` as needed.
```json5
{

View File

@ -62,6 +62,7 @@ actor CameraCaptureService {
session.startRunning()
defer { session.stopRunning() }
await Self.warmUpCaptureSession()
await self.waitForExposureAndWhiteBalance(device: device)
let settings: AVCapturePhotoSettings = {
if output.availablePhotoCodecTypes.contains(.jpeg) {
@ -257,6 +258,17 @@ actor CameraCaptureService {
// A short delay after `startRunning()` significantly reduces "blank first frame" captures on some devices.
try? await Task.sleep(nanoseconds: 150_000_000) // 150ms
}
private func waitForExposureAndWhiteBalance(device: AVCaptureDevice) async {
let stepNs: UInt64 = 50_000_000
let maxSteps = 30 // ~1.5s
for _ in 0..<maxSteps {
if !(device.isAdjustingExposure || device.isAdjustingWhiteBalance) {
return
}
try? await Task.sleep(nanoseconds: stepNs)
}
}
}
private final class PhotoCaptureDelegate: NSObject, AVCapturePhotoCaptureDelegate {

View File

@ -97,4 +97,13 @@ enum ClawdisConfigFile {
self.logger.debug("agent workspace updated set=\(!trimmed.isEmpty)")
}
static func gatewayPassword() -> String? {
let root = self.loadDict()
guard let gateway = root["gateway"] as? [String: Any],
let remote = gateway["remote"] as? [String: Any] else {
return nil
}
return remote["password"] as? String
}
}

View File

@ -431,12 +431,57 @@ struct ConfigSettings: View {
self.configSaving = true
defer { self.configSaving = false }
let configModel = self.configModel
let customModel = self.customModel
let heartbeatMinutes = self.heartbeatMinutes
let heartbeatBody = self.heartbeatBody
let browserEnabled = self.browserEnabled
let browserControlUrl = self.browserControlUrl
let browserColorHex = self.browserColorHex
let browserAttachOnly = self.browserAttachOnly
let talkVoiceId = self.talkVoiceId
let talkApiKey = self.talkApiKey
let talkInterruptOnSpeech = self.talkInterruptOnSpeech
let errorMessage = await ConfigSettings.buildAndSaveConfig(
configModel: configModel,
customModel: customModel,
heartbeatMinutes: heartbeatMinutes,
heartbeatBody: heartbeatBody,
browserEnabled: browserEnabled,
browserControlUrl: browserControlUrl,
browserColorHex: browserColorHex,
browserAttachOnly: browserAttachOnly,
talkVoiceId: talkVoiceId,
talkApiKey: talkApiKey,
talkInterruptOnSpeech: talkInterruptOnSpeech
)
if let errorMessage {
self.modelError = errorMessage
}
}
@MainActor
private static func buildAndSaveConfig(
configModel: String,
customModel: String,
heartbeatMinutes: Int?,
heartbeatBody: String,
browserEnabled: Bool,
browserControlUrl: String,
browserColorHex: String,
browserAttachOnly: Bool,
talkVoiceId: String,
talkApiKey: String,
talkInterruptOnSpeech: Bool
) async -> String? {
var root = await ConfigStore.load()
var agent = root["agent"] as? [String: Any] ?? [:]
var browser = root["browser"] as? [String: Any] ?? [:]
var talk = root["talk"] as? [String: Any] ?? [:]
let chosenModel = (self.configModel == "__custom__" ? self.customModel : self.configModel)
let chosenModel = (configModel == "__custom__" ? customModel : configModel)
.trimmingCharacters(in: .whitespacesAndNewlines)
let trimmedModel = chosenModel
if !trimmedModel.isEmpty { agent["model"] = trimmedModel }
@ -445,40 +490,41 @@ struct ConfigSettings: View {
agent["heartbeatMinutes"] = heartbeatMinutes
}
let trimmedBody = self.heartbeatBody.trimmingCharacters(in: .whitespacesAndNewlines)
let trimmedBody = heartbeatBody.trimmingCharacters(in: .whitespacesAndNewlines)
if !trimmedBody.isEmpty {
agent["heartbeatBody"] = trimmedBody
}
root["agent"] = agent
browser["enabled"] = self.browserEnabled
let trimmedUrl = self.browserControlUrl.trimmingCharacters(in: .whitespacesAndNewlines)
browser["enabled"] = browserEnabled
let trimmedUrl = browserControlUrl.trimmingCharacters(in: .whitespacesAndNewlines)
if !trimmedUrl.isEmpty { browser["controlUrl"] = trimmedUrl }
let trimmedColor = self.browserColorHex.trimmingCharacters(in: .whitespacesAndNewlines)
let trimmedColor = browserColorHex.trimmingCharacters(in: .whitespacesAndNewlines)
if !trimmedColor.isEmpty { browser["color"] = trimmedColor }
browser["attachOnly"] = self.browserAttachOnly
browser["attachOnly"] = browserAttachOnly
root["browser"] = browser
let trimmedVoice = self.talkVoiceId.trimmingCharacters(in: .whitespacesAndNewlines)
let trimmedVoice = talkVoiceId.trimmingCharacters(in: .whitespacesAndNewlines)
if trimmedVoice.isEmpty {
talk.removeValue(forKey: "voiceId")
} else {
talk["voiceId"] = trimmedVoice
}
let trimmedApiKey = self.talkApiKey.trimmingCharacters(in: .whitespacesAndNewlines)
let trimmedApiKey = talkApiKey.trimmingCharacters(in: .whitespacesAndNewlines)
if trimmedApiKey.isEmpty {
talk.removeValue(forKey: "apiKey")
} else {
talk["apiKey"] = trimmedApiKey
}
talk["interruptOnSpeech"] = self.talkInterruptOnSpeech
talk["interruptOnSpeech"] = talkInterruptOnSpeech
root["talk"] = talk
do {
try await ConfigStore.save(root)
} catch {
self.modelError = error.localizedDescription
return nil
} catch let error {
return error.localizedDescription
}
}

View File

@ -43,7 +43,7 @@ enum ConfigStore {
}
@MainActor
static func save(_ root: [String: Any]) async throws {
static func save(_ root: sending [String: Any]) async throws {
let overrides = await self.overrideStore.overrides
if await self.isRemoteMode() {
if let override = overrides.saveRemote {

View File

@ -63,9 +63,11 @@ final class ControlChannel {
self.logger.info("control channel state -> connecting")
case .disconnected:
self.logger.info("control channel state -> disconnected")
self.scheduleRecovery(reason: "disconnected")
case let .degraded(message):
let detail = message.isEmpty ? "degraded" : "degraded: \(message)"
self.logger.info("control channel state -> \(detail, privacy: .public)")
self.scheduleRecovery(reason: message)
}
}
}
@ -74,6 +76,8 @@ final class ControlChannel {
private let logger = Logger(subsystem: "com.steipete.clawdis", category: "control")
private var eventTask: Task<Void, Never>?
private var recoveryTask: Task<Void, Never>?
private var lastRecoveryAt: Date?
private init() {
self.startEventStream()
@ -231,7 +235,43 @@ final class ControlChannel {
}
let detail = nsError.localizedDescription.isEmpty ? "unknown gateway error" : nsError.localizedDescription
return "Gateway error: \(detail)"
let trimmed = detail.trimmingCharacters(in: .whitespacesAndNewlines)
if trimmed.lowercased().hasPrefix("gateway error:") { return trimmed }
return "Gateway error: \(trimmed)"
}
private func scheduleRecovery(reason: String) {
let now = Date()
if let last = self.lastRecoveryAt, now.timeIntervalSince(last) < 10 { return }
guard self.recoveryTask == nil else { return }
self.lastRecoveryAt = now
self.recoveryTask = Task { [weak self] in
guard let self else { return }
let mode = await MainActor.run { AppStateStore.shared.connectionMode }
guard mode != .unconfigured else {
self.recoveryTask = nil
return
}
let trimmedReason = reason.trimmingCharacters(in: .whitespacesAndNewlines)
let reasonText = trimmedReason.isEmpty ? "unknown" : trimmedReason
self.logger.info(
"control channel recovery starting mode=\(String(describing: mode), privacy: .public) reason=\(reasonText, privacy: .public)")
if mode == .local {
GatewayProcessManager.shared.setActive(true)
}
do {
try await GatewayConnection.shared.refresh()
self.logger.info("control channel recovery finished")
} catch {
self.logger.error(
"control channel recovery failed \(error.localizedDescription, privacy: .public)")
}
self.recoveryTask = nil
}
}
func sendSystemEvent(_ text: String, params: [String: AnyHashable] = [:]) async throws {

View File

@ -66,6 +66,7 @@ actor GatewayChannelActor {
private var connectWaiters: [CheckedContinuation<Void, Error>] = []
private var url: URL
private var token: String?
private var password: String?
private let session: WebSocketSessioning
private var backoffMs: Double = 500
private var shouldReconnect = true
@ -82,11 +83,13 @@ actor GatewayChannelActor {
init(
url: URL,
token: String?,
password: String? = nil,
session: WebSocketSessionBox? = nil,
pushHandler: (@Sendable (GatewayPush) async -> Void)? = nil)
{
self.url = url
self.token = token
self.password = password
self.session = session?.session ?? URLSession(configuration: .default)
self.pushHandler = pushHandler
Task { [weak self] in
@ -214,6 +217,8 @@ actor GatewayChannelActor {
]
if let token = self.token {
params["auth"] = ProtoAnyCodable(["token": ProtoAnyCodable(token)])
} else if let password = self.password {
params["auth"] = ProtoAnyCodable(["password": ProtoAnyCodable(password)])
}
let frame = RequestFrame(

View File

@ -40,7 +40,7 @@ struct GatewayAgentInvocation: Sendable {
actor GatewayConnection {
static let shared = GatewayConnection()
typealias Config = (url: URL, token: String?)
typealias Config = (url: URL, token: String?, password: String?)
enum Method: String, Sendable {
case agent
@ -83,6 +83,7 @@ actor GatewayConnection {
private var client: GatewayChannelActor?
private var configuredURL: URL?
private var configuredToken: String?
private var configuredPassword: String?
private var subscribers: [UUID: AsyncStream<GatewayPush>.Continuation] = [:]
private var lastSnapshot: HelloOk?
@ -103,7 +104,7 @@ actor GatewayConnection {
timeoutMs: Double? = nil) async throws -> Data
{
let cfg = try await self.configProvider()
await self.configure(url: cfg.url, token: cfg.token)
await self.configure(url: cfg.url, token: cfg.token, password: cfg.password)
guard let client else {
throw NSError(domain: "Gateway", code: 0, userInfo: [NSLocalizedDescriptionKey: "gateway not configured"])
}
@ -149,7 +150,7 @@ actor GatewayConnection {
try await Task.sleep(nanoseconds: UInt64(delayMs) * 1_000_000)
do {
let cfg = try await self.configProvider()
await self.configure(url: cfg.url, token: cfg.token)
await self.configure(url: cfg.url, token: cfg.token, password: cfg.password)
guard let client = self.client else {
throw NSError(
domain: "Gateway",
@ -209,7 +210,7 @@ actor GatewayConnection {
/// Ensure the underlying socket is configured (and replaced if config changed).
func refresh() async throws {
let cfg = try await self.configProvider()
await self.configure(url: cfg.url, token: cfg.token)
await self.configure(url: cfg.url, token: cfg.token, password: cfg.password)
}
func shutdown() async {
@ -264,8 +265,8 @@ actor GatewayConnection {
}
}
private func configure(url: URL, token: String?) async {
if self.client != nil, self.configuredURL == url, self.configuredToken == token {
private func configure(url: URL, token: String?, password: String?) async {
if self.client != nil, self.configuredURL == url, self.configuredToken == token, self.configuredPassword == password {
return
}
if let client {
@ -275,12 +276,14 @@ actor GatewayConnection {
self.client = GatewayChannelActor(
url: url,
token: token,
password: password,
session: self.sessionBox,
pushHandler: { [weak self] push in
await self?.handle(push: push)
})
self.configuredURL = url
self.configuredToken = token
self.configuredPassword = password
}
private func handle(push: GatewayPush) {

View File

@ -2,7 +2,7 @@ import Foundation
import OSLog
enum GatewayEndpointState: Sendable, Equatable {
case ready(mode: AppState.ConnectionMode, url: URL, token: String?)
case ready(mode: AppState.ConnectionMode, url: URL, token: String?, password: String?)
case unavailable(mode: AppState.ConnectionMode, reason: String)
}
@ -17,6 +17,7 @@ actor GatewayEndpointStore {
struct Deps: Sendable {
let mode: @Sendable () async -> AppState.ConnectionMode
let token: @Sendable () -> String?
let password: @Sendable () -> String?
let localPort: @Sendable () -> Int
let remotePortIfRunning: @Sendable () async -> UInt16?
let ensureRemoteTunnel: @Sendable () async throws -> UInt16
@ -24,11 +25,52 @@ actor GatewayEndpointStore {
static let live = Deps(
mode: { await MainActor.run { AppStateStore.shared.connectionMode } },
token: { ProcessInfo.processInfo.environment["CLAWDIS_GATEWAY_TOKEN"] },
password: {
let root = ClawdisConfigFile.loadDict()
return GatewayEndpointStore.resolveGatewayPassword(
isRemote: CommandResolver.connectionModeIsRemote(),
root: root,
env: ProcessInfo.processInfo.environment)
},
localPort: { GatewayEnvironment.gatewayPort() },
remotePortIfRunning: { await RemoteTunnelManager.shared.controlTunnelPortIfRunning() },
ensureRemoteTunnel: { try await RemoteTunnelManager.shared.ensureControlTunnel() })
}
private static func resolveGatewayPassword(
isRemote: Bool,
root: [String: Any],
env: [String: String]
) -> String? {
let raw = env["CLAWDIS_GATEWAY_PASSWORD"] ?? ""
let trimmed = raw.trimmingCharacters(in: .whitespacesAndNewlines)
if !trimmed.isEmpty {
return trimmed
}
if isRemote {
if let gateway = root["gateway"] as? [String: Any],
let remote = gateway["remote"] as? [String: Any],
let password = remote["password"] as? String
{
let pw = password.trimmingCharacters(in: .whitespacesAndNewlines)
if !pw.isEmpty {
return pw
}
}
return nil
}
if let gateway = root["gateway"] as? [String: Any],
let auth = gateway["auth"] as? [String: Any],
let password = auth["password"] as? String
{
let pw = password.trimmingCharacters(in: .whitespacesAndNewlines)
if !pw.isEmpty {
return pw
}
}
return nil
}
private let deps: Deps
private let logger = Logger(subsystem: "com.steipete.clawdis", category: "gateway-endpoint")
@ -47,9 +89,11 @@ actor GatewayEndpointStore {
}
let port = deps.localPort()
let token = deps.token()
let password = deps.password()
switch initialMode {
case .local:
self.state = .ready(mode: .local, url: URL(string: "ws://127.0.0.1:\(port)")!, token: deps.token())
self.state = .ready(mode: .local, url: URL(string: "ws://127.0.0.1:\(port)")!, token: token, password: password)
case .remote:
self.state = .unavailable(mode: .remote, reason: "Remote mode enabled but no active control tunnel")
case .unconfigured:
@ -77,17 +121,18 @@ actor GatewayEndpointStore {
func setMode(_ mode: AppState.ConnectionMode) async {
let token = self.deps.token()
let password = self.deps.password()
switch mode {
case .local:
let port = self.deps.localPort()
self.setState(.ready(mode: .local, url: URL(string: "ws://127.0.0.1:\(port)")!, token: token))
self.setState(.ready(mode: .local, url: URL(string: "ws://127.0.0.1:\(port)")!, token: token, password: password))
case .remote:
let port = await self.deps.remotePortIfRunning()
guard let port else {
self.setState(.unavailable(mode: .remote, reason: "Remote mode enabled but no active control tunnel"))
return
}
self.setState(.ready(mode: .remote, url: URL(string: "ws://127.0.0.1:\(Int(port))")!, token: token))
self.setState(.ready(mode: .remote, url: URL(string: "ws://127.0.0.1:\(Int(port))")!, token: token, password: password))
case .unconfigured:
self.setState(.unavailable(mode: .unconfigured, reason: "Gateway not configured"))
}
@ -110,8 +155,8 @@ actor GatewayEndpointStore {
func requireConfig() async throws -> GatewayConnection.Config {
await self.refresh()
switch self.state {
case let .ready(_, url, token):
return (url, token)
case let .ready(_, url, token, password):
return (url, token, password)
case let .unavailable(mode, reason):
guard mode == .remote else {
throw NSError(domain: "GatewayEndpoint", code: 1, userInfo: [NSLocalizedDescriptionKey: reason])
@ -122,9 +167,10 @@ actor GatewayEndpointStore {
do {
let forwarded = try await self.deps.ensureRemoteTunnel()
let token = self.deps.token()
let password = self.deps.password()
let url = URL(string: "ws://127.0.0.1:\(Int(forwarded))")!
self.setState(.ready(mode: .remote, url: url, token: token))
return (url, token)
self.setState(.ready(mode: .remote, url: url, token: token, password: password))
return (url, token, password)
} catch {
let msg = "\(reason) (\(error.localizedDescription))"
self.setState(.unavailable(mode: .remote, reason: msg))
@ -144,7 +190,7 @@ actor GatewayEndpointStore {
continuation.yield(next)
}
switch next {
case let .ready(mode, url, _):
case let .ready(mode, url, _, _):
let modeDesc = String(describing: mode)
let urlDesc = url.absoluteString
self.logger
@ -158,3 +204,15 @@ actor GatewayEndpointStore {
}
}
}
#if DEBUG
extension GatewayEndpointStore {
static func _testResolveGatewayPassword(
isRemote: Bool,
root: [String: Any],
env: [String: String]
) -> String? {
self.resolveGatewayPassword(isRemote: isRemote, root: root, env: env)
}
}
#endif

View File

@ -64,6 +64,7 @@ enum GatewayLaunchAgentManager {
.joined(separator: ":")
let bind = self.preferredGatewayBind() ?? "loopback"
let token = self.preferredGatewayToken()
let password = self.preferredGatewayPassword()
var envEntries = """
<key>PATH</key>
<string>\(preferredPath)</string>
@ -71,9 +72,17 @@ enum GatewayLaunchAgentManager {
<string>sips</string>
"""
if let token {
let escapedToken = self.escapePlistValue(token)
envEntries += """
<key>CLAWDIS_GATEWAY_TOKEN</key>
<string>\(token)</string>
<string>\(escapedToken)</string>
"""
}
if let password {
let escapedPassword = self.escapePlistValue(password)
envEntries += """
<key>CLAWDIS_GATEWAY_PASSWORD</key>
<string>\(escapedPassword)</string>
"""
}
let plist = """
@ -146,6 +155,33 @@ enum GatewayLaunchAgentManager {
return trimmed.isEmpty ? nil : trimmed
}
private static func preferredGatewayPassword() -> String? {
// First check environment variable
let raw = ProcessInfo.processInfo.environment["CLAWDIS_GATEWAY_PASSWORD"] ?? ""
let trimmed = raw.trimmingCharacters(in: .whitespacesAndNewlines)
if !trimmed.isEmpty {
return trimmed
}
// Then check config file (gateway.auth.password)
let root = ClawdisConfigFile.loadDict()
if let gateway = root["gateway"] as? [String: Any],
let auth = gateway["auth"] as? [String: Any],
let password = auth["password"] as? String
{
return password.trimmingCharacters(in: .whitespacesAndNewlines)
}
return nil
}
private static func escapePlistValue(_ raw: String) -> String {
raw
.replacingOccurrences(of: "&", with: "&amp;")
.replacingOccurrences(of: "<", with: "&lt;")
.replacingOccurrences(of: ">", with: "&gt;")
.replacingOccurrences(of: "\"", with: "&quot;")
.replacingOccurrences(of: "'", with: "&apos;")
}
private struct LaunchctlResult {
let status: Int32
let output: String
@ -190,5 +226,9 @@ extension GatewayLaunchAgentManager {
static func _testPreferredGatewayToken() -> String? {
self.preferredGatewayToken()
}
static func _testEscapePlistValue(_ raw: String) -> String {
self.escapePlistValue(raw)
}
}
#endif

View File

@ -114,6 +114,7 @@ final class HealthStore {
guard !self.isRefreshing else { return }
self.isRefreshing = true
defer { self.isRefreshing = false }
let previousError = self.lastError
do {
let data = try await ControlChannel.shared.health(timeout: 15)
@ -121,13 +122,23 @@ final class HealthStore {
self.snapshot = decoded
self.lastSuccess = Date()
self.lastError = nil
if previousError != nil {
Self.logger.info("health refresh recovered")
}
} else {
self.lastError = "health output not JSON"
if onDemand { self.snapshot = nil }
if previousError != self.lastError {
Self.logger.warning("health refresh failed: output not JSON")
}
}
} catch {
self.lastError = error.localizedDescription
let desc = error.localizedDescription
self.lastError = desc
if onDemand { self.snapshot = nil }
if previousError != desc {
Self.logger.error("health refresh failed \(desc, privacy: .public)")
}
}
}

View File

@ -164,14 +164,24 @@ struct MenuContent: View {
}
private func saveBrowserControlEnabled(_ enabled: Bool) async {
let (success, _) = await MenuContent.buildAndSaveBrowserEnabled(enabled)
if !success {
await self.loadBrowserControlEnabled()
}
}
@MainActor
private static func buildAndSaveBrowserEnabled(_ enabled: Bool) async -> (Bool,()) {
var root = await ConfigStore.load()
var browser = root["browser"] as? [String: Any] ?? [:]
browser["enabled"] = enabled
root["browser"] = browser
do {
try await ConfigStore.save(root)
return (true, ())
} catch {
await self.loadBrowserControlEnabled()
return (false, ())
}
}
@ -365,6 +375,10 @@ struct MenuContent: View {
Text(label)
.font(.caption)
.foregroundStyle(.secondary)
.multilineTextAlignment(.leading)
.lineLimit(nil)
.fixedSize(horizontal: false, vertical: true)
.layoutPriority(1)
}
.padding(.top, 2)
}

View File

@ -106,13 +106,7 @@ final class MenuSessionsInjector: NSObject, NSMenuDelegate {
guard let insertIndex = self.findInsertIndex(in: menu) else { return }
let width = self.initialWidth(for: menu)
guard self.isControlChannelConnected else {
menu.insertItem(self.makeMessageItem(
text: self.controlChannelStatusText,
symbolName: "wifi.slash",
width: width), at: insertIndex)
return
}
guard self.isControlChannelConnected else { return }
guard let snapshot = self.cachedSnapshot else {
let headerItem = NSMenuItem()
@ -195,17 +189,14 @@ final class MenuSessionsInjector: NSObject, NSMenuDelegate {
menu.insertItem(topSeparator, at: cursor)
cursor += 1
guard self.isControlChannelConnected else {
menu.insertItem(
self.makeMessageItem(text: self.controlChannelStatusText, symbolName: "wifi.slash", width: width),
at: cursor)
if let gatewayEntry = self.gatewayEntry() {
let gatewayItem = self.makeNodeItem(entry: gatewayEntry, width: width)
menu.insertItem(gatewayItem, at: cursor)
cursor += 1
let separator = NSMenuItem.separator()
separator.tag = self.nodesTag
menu.insertItem(separator, at: cursor)
return
}
guard self.isControlChannelConnected else { return }
if let error = self.nodesStore.lastError?.nonEmpty {
menu.insertItem(
self.makeMessageItem(
@ -229,15 +220,7 @@ final class MenuSessionsInjector: NSObject, NSMenuDelegate {
cursor += 1
} else {
for entry in entries.prefix(8) {
let item = NSMenuItem()
item.tag = self.nodesTag
item.target = self
item.action = #selector(self.copyNodeSummary(_:))
item.representedObject = NodeMenuEntryFormatter.summaryText(entry)
item.view = HighlightedMenuItemHostView(
rootView: AnyView(NodeMenuRowView(entry: entry, width: width)),
width: width)
item.submenu = self.buildNodeSubmenu(entry: entry, width: width)
let item = self.makeNodeItem(entry: entry, width: width)
menu.insertItem(item, at: cursor)
cursor += 1
}
@ -265,27 +248,56 @@ final class MenuSessionsInjector: NSObject, NSMenuDelegate {
return false
}
private var controlChannelStatusText: String {
switch ControlChannel.shared.state {
case .connected:
return "Connected"
case .connecting:
return "Connecting to gateway…"
case let .degraded(reason):
if self.shouldShowConnecting { return "Connecting to gateway…" }
return reason.nonEmpty ?? "No connection to gateway"
case .disconnected:
return self.shouldShowConnecting ? "Connecting to gateway…" : "No connection to gateway"
private func gatewayEntry() -> NodeInfo? {
let mode = AppStateStore.shared.connectionMode
let isConnected = self.isControlChannelConnected
let port = GatewayEnvironment.gatewayPort()
var host: String?
var platform: String?
switch mode {
case .remote:
platform = "remote"
let target = AppStateStore.shared.remoteTarget
if let parsed = CommandResolver.parseSSHTarget(target) {
host = parsed.port == 22 ? parsed.host : "\(parsed.host):\(parsed.port)"
} else {
host = target.nonEmpty
}
case .local:
platform = "local"
host = "127.0.0.1:\(port)"
case .unconfigured:
platform = nil
host = nil
}
return NodeInfo(
nodeId: "gateway",
displayName: "Gateway",
platform: platform,
version: nil,
deviceFamily: nil,
modelIdentifier: nil,
remoteIp: host,
caps: nil,
commands: nil,
permissions: nil,
paired: nil,
connected: isConnected)
}
private var shouldShowConnecting: Bool {
switch GatewayProcessManager.shared.status {
case .starting, .running, .attachedExisting:
return true
case .stopped, .failed:
return false
}
private func makeNodeItem(entry: NodeInfo, width: CGFloat) -> NSMenuItem {
let item = NSMenuItem()
item.tag = self.nodesTag
item.target = self
item.action = #selector(self.copyNodeSummary(_:))
item.representedObject = NodeMenuEntryFormatter.summaryText(entry)
item.view = HighlightedMenuItemHostView(
rootView: AnyView(NodeMenuRowView(entry: entry, width: width)),
width: width)
item.submenu = self.buildNodeSubmenu(entry: entry, width: width)
return item
}
private func makeMessageItem(text: String, symbolName: String, width: CGFloat) -> NSMenuItem {
@ -293,8 +305,9 @@ final class MenuSessionsInjector: NSObject, NSMenuDelegate {
Label(text, systemImage: symbolName)
.font(.caption)
.foregroundStyle(.secondary)
.lineLimit(1)
.truncationMode(.tail)
.multilineTextAlignment(.leading)
.lineLimit(nil)
.fixedSize(horizontal: false, vertical: true)
.padding(.leading, 18)
.padding(.trailing, 12)
.padding(.vertical, 6)

View File

@ -2,15 +2,30 @@ import AppKit
import SwiftUI
struct NodeMenuEntryFormatter {
static func isGateway(_ entry: NodeInfo) -> Bool {
entry.nodeId == "gateway"
}
static func isConnected(_ entry: NodeInfo) -> Bool {
entry.isConnected
}
static func primaryName(_ entry: NodeInfo) -> String {
entry.displayName?.nonEmpty ?? entry.nodeId
if self.isGateway(entry) {
return entry.displayName?.nonEmpty ?? "Gateway"
}
return entry.displayName?.nonEmpty ?? entry.nodeId
}
static func summaryText(_ entry: NodeInfo) -> String {
if self.isGateway(entry) {
let role = self.roleText(entry)
let name = self.primaryName(entry)
var parts = ["\(name) · \(role)"]
if let ip = entry.remoteIp?.nonEmpty { parts.append("host \(ip)") }
if let platform = self.platformText(entry) { parts.append(platform) }
return parts.joined(separator: " · ")
}
let name = self.primaryName(entry)
var prefix = "Node: \(name)"
if let ip = entry.remoteIp?.nonEmpty {
@ -112,6 +127,11 @@ struct NodeMenuEntryFormatter {
}
static func leadingSymbol(_ entry: NodeInfo) -> String {
if self.isGateway(entry) {
return self.safeSystemSymbol(
"antenna.radiowaves.left.and.right",
fallback: "dot.radiowaves.left.and.right")
}
if let family = entry.deviceFamily?.lowercased() {
if family.contains("mac") {
return self.safeSystemSymbol("laptopcomputer", fallback: "laptopcomputer")

View File

@ -75,10 +75,26 @@ final class NodesStore {
self.lastError = nil
self.statusMessage = nil
} catch {
if Self.isCancelled(error) {
self.logger.debug("node.list cancelled; keeping last nodes")
if self.nodes.isEmpty {
self.statusMessage = "Refreshing devices…"
}
self.lastError = nil
return
}
self.logger.error("node.list failed \(error.localizedDescription, privacy: .public)")
self.nodes = []
self.lastError = error.localizedDescription
self.statusMessage = nil
}
}
private static func isCancelled(_ error: Error) -> Bool {
if error is CancellationError { return true }
if let urlError = error as? URLError, urlError.code == .cancelled { return true }
let nsError = error as NSError
if nsError.domain == NSURLErrorDomain, nsError.code == NSURLErrorCancelled { return true }
return false
}
}

View File

@ -75,6 +75,16 @@ extension OnboardingView {
@discardableResult
func saveAgentWorkspace(_ workspace: String?) async -> Bool {
let (success, errorMessage) = await OnboardingView.buildAndSaveWorkspace(workspace)
if let errorMessage {
self.workspaceStatus = errorMessage
}
return success
}
@MainActor
private static func buildAndSaveWorkspace(_ workspace: String?) async -> (Bool, String?) {
var root = await ConfigStore.load()
var agent = root["agent"] as? [String: Any] ?? [:]
let trimmed = workspace?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
@ -90,10 +100,10 @@ extension OnboardingView {
}
do {
try await ConfigStore.save(root)
return true
} catch {
self.workspaceStatus = "Failed to save config: \(error.localizedDescription)"
return false
return (true, nil)
} catch let error {
let errorMessage = "Failed to save config: \(error.localizedDescription)"
return (false, errorMessage)
}
}
}

View File

@ -31,6 +31,8 @@ enum PermissionManager {
await self.ensureMicrophone(interactive: interactive)
case .speechRecognition:
await self.ensureSpeechRecognition(interactive: interactive)
case .camera:
await self.ensureCamera(interactive: interactive)
}
}
@ -114,6 +116,24 @@ enum PermissionManager {
return SFSpeechRecognizer.authorizationStatus() == .authorized
}
private static func ensureCamera(interactive: Bool) async -> Bool {
let status = AVCaptureDevice.authorizationStatus(for: .video)
switch status {
case .authorized:
return true
case .notDetermined:
guard interactive else { return false }
return await AVCaptureDevice.requestAccess(for: .video)
case .denied, .restricted:
if interactive {
CameraPermissionHelper.openSettings()
}
return false
@unknown default:
return false
}
}
static func voiceWakePermissionsGranted() -> Bool {
let mic = AVCaptureDevice.authorizationStatus(for: .audio) == .authorized
let speech = SFSpeechRecognizer.authorizationStatus() == .authorized
@ -153,6 +173,9 @@ enum PermissionManager {
case .speechRecognition:
results[cap] = SFSpeechRecognizer.authorizationStatus() == .authorized
case .camera:
results[cap] = AVCaptureDevice.authorizationStatus(for: .video) == .authorized
}
}
return results
@ -189,6 +212,21 @@ enum MicrophonePermissionHelper {
}
}
enum CameraPermissionHelper {
static func openSettings() {
let candidates = [
"x-apple.systempreferences:com.apple.preference.security?Privacy_Camera",
"x-apple.systempreferences:com.apple.preference.security",
]
for candidate in candidates {
if let url = URL(string: candidate), NSWorkspace.shared.open(url) {
return
}
}
}
}
enum AppleScriptPermission {
private static let logger = Logger(subsystem: "com.steipete.clawdis", category: "AppleScriptPermission")

View File

@ -120,6 +120,7 @@ struct PermissionRow: View {
case .screenRecording: "Screen Recording"
case .microphone: "Microphone"
case .speechRecognition: "Speech Recognition"
case .camera: "Camera"
}
}
@ -132,6 +133,7 @@ struct PermissionRow: View {
case .screenRecording: "Capture the screen for context or screenshots"
case .microphone: "Allow Voice Wake and audio capture"
case .speechRecognition: "Transcribe Voice Wake trigger phrases on-device"
case .camera: "Capture photos and video from the camera"
}
}
@ -143,6 +145,7 @@ struct PermissionRow: View {
case .screenRecording: "display"
case .microphone: "mic"
case .speechRecognition: "waveform"
case .camera: "camera"
}
}
}

View File

@ -280,28 +280,57 @@ struct TailscaleIntegrationSection: View {
return
}
let (success, errorMessage) = await TailscaleIntegrationSection.buildAndSaveTailscaleConfig(
tailscaleMode: self.tailscaleMode,
requireCredentialsForServe: self.requireCredentialsForServe,
password: trimmedPassword,
connectionMode: self.connectionMode,
isPaused: self.isPaused
)
if !success, let errorMessage {
self.statusMessage = errorMessage
return
}
if self.connectionMode == .local, !self.isPaused {
self.statusMessage = "Saved to ~/.clawdis/clawdis.json. Restarting gateway…"
} else {
self.statusMessage = "Saved to ~/.clawdis/clawdis.json. Restart the gateway to apply."
}
self.restartGatewayIfNeeded()
}
@MainActor
private static func buildAndSaveTailscaleConfig(
tailscaleMode: GatewayTailscaleMode,
requireCredentialsForServe: Bool,
password: String,
connectionMode: AppState.ConnectionMode,
isPaused: Bool
) async -> (Bool, String?) {
var root = await ConfigStore.load()
var gateway = root["gateway"] as? [String: Any] ?? [:]
var tailscale = gateway["tailscale"] as? [String: Any] ?? [:]
tailscale["mode"] = self.tailscaleMode.rawValue
tailscale["mode"] = tailscaleMode.rawValue
gateway["tailscale"] = tailscale
if self.tailscaleMode != .off {
if tailscaleMode != .off {
gateway["bind"] = "loopback"
}
if self.tailscaleMode == .off {
if tailscaleMode == .off {
gateway.removeValue(forKey: "auth")
} else {
var auth = gateway["auth"] as? [String: Any] ?? [:]
if self.tailscaleMode == .serve, !self.requireCredentialsForServe {
if tailscaleMode == .serve, !requireCredentialsForServe {
auth["allowTailscale"] = true
auth.removeValue(forKey: "mode")
auth.removeValue(forKey: "password")
} else {
auth["allowTailscale"] = false
auth["mode"] = "password"
auth["password"] = trimmedPassword
auth["password"] = password
}
if auth.isEmpty {
@ -319,17 +348,10 @@ struct TailscaleIntegrationSection: View {
do {
try await ConfigStore.save(root)
} catch {
self.statusMessage = error.localizedDescription
return
return (true, nil)
} catch let error {
return (false, error.localizedDescription)
}
if self.connectionMode == .local, !self.isPaused {
self.statusMessage = "Saved to ~/.clawdis/clawdis.json. Restarting gateway…"
} else {
self.statusMessage = "Saved to ~/.clawdis/clawdis.json. Restart the gateway to apply."
}
self.restartGatewayIfNeeded()
}
private func restartGatewayIfNeeded() {

View File

@ -11,6 +11,7 @@ public enum Capability: String, Codable, CaseIterable, Sendable {
case screenRecording
case microphone
case speechRecognition
case camera
}
public enum CameraFacing: String, Codable, Sendable {

View File

@ -29,6 +29,7 @@ import Testing
let store = GatewayEndpointStore(deps: .init(
mode: { mode.get() },
token: { "t" },
password: { nil },
localPort: { 1234 },
remotePortIfRunning: { nil },
ensureRemoteTunnel: { 18789 }))
@ -44,6 +45,7 @@ import Testing
let store = GatewayEndpointStore(deps: .init(
mode: { mode.get() },
token: { nil },
password: { nil },
localPort: { 18789 },
remotePortIfRunning: { nil },
ensureRemoteTunnel: { 18789 }))
@ -58,6 +60,7 @@ import Testing
let store = GatewayEndpointStore(deps: .init(
mode: { mode.get() },
token: { "tok" },
password: { "pw" },
localPort: { 1 },
remotePortIfRunning: { 5555 },
ensureRemoteTunnel: { 5555 }))
@ -69,13 +72,71 @@ import Testing
_ = try await store.ensureRemoteControlTunnel()
let next = await iterator.next()
guard case let .ready(mode, url, token) = next else {
guard case let .ready(mode, url, token, password) = next else {
Issue.record("expected .ready after ensure, got \(String(describing: next))")
return
}
#expect(mode == .remote)
#expect(url.absoluteString == "ws://127.0.0.1:5555")
#expect(token == "tok")
#expect(password == "pw")
}
@Test func resolvesGatewayPasswordByMode() {
let root: [String: Any] = [
"gateway": [
"auth": ["password": " local "],
"remote": ["password": " remote "],
],
]
let env: [String: String] = [:]
#expect(GatewayEndpointStore._testResolveGatewayPassword(
isRemote: false,
root: root,
env: env) == "local")
#expect(GatewayEndpointStore._testResolveGatewayPassword(
isRemote: true,
root: root,
env: env) == "remote")
}
@Test func gatewayPasswordEnvOverridesConfig() {
let root: [String: Any] = [
"gateway": [
"auth": ["password": "local"],
"remote": ["password": "remote"],
],
]
let env = ["CLAWDIS_GATEWAY_PASSWORD": " env "]
#expect(GatewayEndpointStore._testResolveGatewayPassword(
isRemote: false,
root: root,
env: env) == "env")
#expect(GatewayEndpointStore._testResolveGatewayPassword(
isRemote: true,
root: root,
env: env) == "env")
}
@Test func gatewayPasswordIgnoresWhitespaceValues() {
let root: [String: Any] = [
"gateway": [
"auth": ["password": " "],
"remote": ["password": "\n\t"],
],
]
let env = ["CLAWDIS_GATEWAY_PASSWORD": " "]
#expect(GatewayEndpointStore._testResolveGatewayPassword(
isRemote: false,
root: root,
env: env) == nil)
#expect(GatewayEndpointStore._testResolveGatewayPassword(
isRemote: true,
root: root,
env: env) == nil)
}
@Test func unconfiguredModeRejectsConfig() async {
@ -83,6 +144,7 @@ import Testing
let store = GatewayEndpointStore(deps: .init(
mode: { mode.get() },
token: { nil },
password: { nil },
localPort: { 18789 },
remotePortIfRunning: { nil },
ensureRemoteTunnel: { 18789 }))

View File

@ -114,6 +114,9 @@ struct LowCoverageHelperTests {
setenv(keyToken, " secret ", 1)
#expect(GatewayLaunchAgentManager._testPreferredGatewayBind() == "lan")
#expect(GatewayLaunchAgentManager._testPreferredGatewayToken() == "secret")
#expect(
GatewayLaunchAgentManager._testEscapePlistValue("a&b<c>\"'") ==
"a&amp;b&lt;c&gt;&quot;&apos;")
#expect(GatewayLaunchAgentManager._testGatewayExecutablePath(bundlePath: "/App") == "/App/Contents/Resources/Relay/clawdis")
#expect(GatewayLaunchAgentManager._testRelayDir(bundlePath: "/App") == "/App/Contents/Resources/Relay")

View File

@ -76,7 +76,7 @@ Incoming user messages are queued while the agent is streaming. The queue is che
At minimum, set:
- `agent.workspace`
- `routing.allowFrom` (strongly recommended)
- `whatsapp.allowFrom` (strongly recommended)
---

View File

@ -17,7 +17,7 @@ Youre putting an agent in a position to:
- send messages back out via WhatsApp/Telegram/Discord
Start conservative:
- Always set `routing.allowFrom` (never run open-to-the-world on your personal Mac).
- Always set `whatsapp.allowFrom` (never run open-to-the-world on your personal Mac).
- Use a dedicated WhatsApp number for the assistant.
- Keep heartbeats disabled until you trust the setup (omit `agent.heartbeat` or set `agent.heartbeat.every: "0m"`).
@ -74,7 +74,7 @@ clawdis gateway --port 18789
```json5
{
routing: {
whatsapp: {
allowFrom: ["+15555550123"]
}
}
@ -124,8 +124,10 @@ Example:
// Start with 0; enable later.
heartbeat: { every: "0m" }
},
whatsapp: {
allowFrom: ["+15555550123"]
},
routing: {
allowFrom: ["+15555550123"],
groupChat: {
requireMention: true,
mentionPatterns: ["@clawd", "clawd"]

View File

@ -9,7 +9,7 @@ read_when:
CLAWDIS reads an optional **JSON5** config from `~/.clawdis/clawdis.json` (comments + trailing commas allowed).
If the file is missing, CLAWDIS uses safe-ish defaults (embedded Pi agent + per-sender sessions + workspace `~/clawd`). You usually only need a config to:
- restrict who can trigger the bot (`routing.allowFrom`)
- restrict who can trigger the bot (`whatsapp.allowFrom`, `telegram.allowFrom`, etc.)
- tune group mention behavior (`routing.groupChat`)
- customize message prefixes (`messages`)
- set the agents workspace (`agent.workspace`)
@ -21,7 +21,7 @@ If the file is missing, CLAWDIS uses safe-ish defaults (embedded Pi agent + per-
```json5
{
agent: { workspace: "~/clawd" },
routing: { allowFrom: ["+15555550123"] }
whatsapp: { allowFrom: ["+15555550123"] }
}
```
@ -76,13 +76,13 @@ Metadata written by CLI wizards (`onboard`, `configure`, `doctor`, `update`).
}
```
### `routing.allowFrom`
### `whatsapp.allowFrom`
Allowlist of E.164 phone numbers that may trigger auto-replies.
Allowlist of E.164 phone numbers that may trigger WhatsApp auto-replies.
```json5
{
routing: { allowFrom: ["+15555550123", "+447700900123"] }
whatsapp: { allowFrom: ["+15555550123", "+447700900123"] }
}
```
@ -175,6 +175,12 @@ Configure the Discord bot by setting the bot token and optional gating:
token: "your-bot-token",
mediaMaxMb: 8, // clamp inbound media size
enableReactions: true, // allow agent-triggered reactions
slashCommand: { // user-installed app slash commands
enabled: true,
name: "clawd",
sessionPrefix: "discord:slash",
ephemeral: true
},
dm: {
enabled: true, // disable all DMs when false
allowFrom: ["1234567890", "steipete"], // optional DM allowlist (ids or names)
@ -549,7 +555,7 @@ Defaults:
mode: "local", // or "remote"
bind: "loopback",
// controlUi: { enabled: true }
// auth: { mode: "token" | "password" }
// auth: { mode: "token", token: "your-token" } // token is for multi-machine CLI access
// tailscale: { mode: "off" | "serve" | "funnel" }
}
}
@ -560,6 +566,7 @@ Notes:
Auth and Tailscale:
- `gateway.auth.mode` sets the handshake requirements (`token` or `password`).
- `gateway.auth.token` stores the shared token for token auth (used by the CLI on the same machine).
- When `gateway.auth.mode` is set, only that method is accepted (plus optional Tailscale headers).
- `gateway.auth.password` can be set here, or via `CLAWDIS_GATEWAY_PASSWORD` (recommended).
- `gateway.auth.allowTailscale` controls whether Tailscale identity headers can satisfy auth.

View File

@ -25,8 +25,9 @@ Status: ready for DM and guild text channels via the official Discord bot gatewa
6. Guild channels: use `channel:<channelId>` for delivery. Mentions are required by default and can be set per guild or per channel.
7. Optional DM control: set `discord.dm.enabled = false` to ignore all DMs, or `discord.dm.allowFrom` to allow specific users (ids or names). Use `discord.dm.groupEnabled` + `discord.dm.groupChannels` to allow group DMs.
8. Optional guild rules: set `discord.guilds` keyed by guild id (preferred) or slug, with per-channel rules.
9. Optional guild context history: set `discord.historyLimit` (default 20) to include the last N guild messages as context when replying to a mention. Set `0` to disable.
10. Reactions (default on): set `discord.enableReactions = false` to disable agent-triggered reactions via the `clawdis_discord` tool.
9. Optional slash commands: enable `discord.slashCommand` to accept user-installed app commands (ephemeral replies). Slash invocations respect the same DM/guild allowlists.
10. Optional guild context history: set `discord.historyLimit` (default 20) to include the last N guild messages as context when replying to a mention. Set `0` to disable.
11. Reactions (default on): set `discord.enableReactions = false` to disable agent-triggered reactions via the `clawdis_discord` tool.
Note: Discord does not provide a simple username → id lookup without extra guild context, so prefer ids or `<@id>` mentions for DM delivery targets.
Note: Slugs are lowercase with spaces replaced by `-`. Channel names are slugged without the leading `#`.
@ -47,6 +48,12 @@ Note: Guild context `[from:]` lines include `author.tag` + `id` to make ping-rea
token: "abc.123",
mediaMaxMb: 8,
enableReactions: true,
slashCommand: {
enabled: true,
name: "clawd",
sessionPrefix: "discord:slash",
ephemeral: true
},
dm: {
enabled: true,
allowFrom: ["123456789012345678", "steipete"],
@ -77,10 +84,17 @@ Note: Guild context `[from:]` lines include `author.tag` + `id` to make ping-rea
- `guilds.<id>.users`: optional per-guild user allowlist (ids or names).
- `guilds.<id>.channels`: channel rules (keys are channel slugs or ids).
- `guilds.<id>.requireMention`: per-guild mention requirement (overridable per channel).
- `slashCommand`: optional config for user-installed slash commands (ephemeral responses).
- `mediaMaxMb`: clamp inbound media saved to disk.
- `historyLimit`: number of recent guild messages to include as context when replying to a mention (default 20, `0` disables).
- `enableReactions`: allow agent-triggered reactions via the `clawdis_discord` tool (default `true`).
Slash command notes:
- Register a chat input command in Discord with at least one string option (e.g., `prompt`).
- The first non-empty string option is treated as the prompt.
- Slash commands honor the same allowlists as DMs/guild messages (`discord.dm.allowFrom`, `discord.guilds`, per-channel rules).
- Clawdis will auto-register `/clawd` (or the configured name) if it doesn't already exist.
## Reactions
When `discord.enableReactions = true`, the agent can call `clawdis_discord` with:
- `action: "react"`

36
docs/doctor.md Normal file
View File

@ -0,0 +1,36 @@
---
summary: "Doctor command: health checks, config migrations, and repair steps"
read_when:
- Adding or modifying doctor migrations
- Introducing breaking config changes
---
# Doctor
`clawdis doctor` is the repair + migration tool for Clawdis. It runs a quick health check, audits skills, and can migrate deprecated config entries to the new schema.
## What it does
- Runs a health check and offers to restart the gateway if it looks unhealthy.
- Prints a skills status summary (eligible/missing/blocked).
- Detects deprecated config keys and offers to migrate them.
## Legacy config migrations
When the config contains deprecated keys, other commands will refuse to run and ask you to run `clawdis doctor`.
Doctor will:
- Explain which legacy keys were found.
- Show the migration it applied.
- Rewrite `~/.clawdis/clawdis.json` with the updated schema.
Current migrations:
- `routing.allowFrom``whatsapp.allowFrom`
## Usage
```bash
clawdis doctor
```
If you want to review changes before writing, open the config file first:
```bash
cat ~/.clawdis/clawdis.json
```

View File

@ -66,6 +66,35 @@ pnpm clawdis doctor
It checks your config, skills status, and gateway health. It can also restart the gateway daemon if needed.
### Terminal onboarding vs macOS app?
**Use terminal onboarding** (`pnpm clawdis onboard`) — it's more stable right now.
The macOS app onboarding is still being polished and can have quirks (e.g., WhatsApp 515 errors, OAuth issues).
---
## Authentication
### OAuth vs API key — what's the difference?
- **OAuth** — Uses your Claude Pro/Max subscription ($20-100/mo flat). No per-token charges. ✅ Recommended!
- **API key** — Pay-per-token via console.anthropic.com. Can get expensive fast.
They're **separate billing**! An API key does NOT use your subscription.
**For OAuth:** During onboarding, pick "Anthropic OAuth", log in to your Claude account, paste the code back.
**If OAuth fails** (headless/container): Do OAuth on a normal machine, then copy `~/.clawdis/` to your server. The auth is just a JSON file.
### OAuth callback not working (containers/headless)?
OAuth needs the callback to reach the machine running the CLI. Options:
1. **Copy auth manually** — Run OAuth on your laptop, copy `~/.clawdis/credentials/` to the container.
2. **SSH tunnel**`ssh -L 18789:localhost:18789 user@server`
3. **Tailscale** — Put both machines on your tailnet.
---
## Migration & Deployment
@ -108,16 +137,30 @@ There's no official Docker setup yet, but it works. Key considerations:
- **WhatsApp login:** QR code works in terminal — no display needed.
- **Persistence:** Mount `~/.clawdis/` and your workspace as volumes.
- **pnpm doesn't persist:** Global npm installs don't survive container restarts. Install pnpm in your startup script.
- **Browser automation:** Optional. If needed, install headless Chrome + Playwright deps, or connect to a remote browser via `--remote-debugging-port`.
Basic approach:
```dockerfile
FROM node:22
WORKDIR /app
# Clone, pnpm install, pnpm build
# Mount volumes for persistence
CMD ["pnpm", "clawdis", "gateway"]
**Volume mappings (e.g., Unraid):**
```
/mnt/user/appdata/clawdis/config → /root/.clawdis
/mnt/user/appdata/clawdis/workspace → /root/clawd
/mnt/user/appdata/clawdis/app → /app
```
**Startup script (`start.sh`):**
```bash
#!/bin/bash
npm install -g pnpm
cd /app
pnpm clawdis gateway
```
**Container command:**
```
bash /app/start.sh
```
Docker support is on the roadmap — PRs welcome!
### Can I run Clawdis headless on a VPS?
@ -126,6 +169,31 @@ Yes! The terminal QR code login works fine over SSH. For long-running operation:
- Use `pm2`, `systemd`, or a `launchd` plist to keep the gateway running.
- Consider Tailscale for secure remote access.
### bun binary vs Node runtime?
Clawdis can run as:
- **bun binary** — Single executable, easy distribution, auto-restarts via launchd
- **Node runtime** (`pnpm clawdis gateway`) — More stable for WhatsApp
If you see WebSocket errors like `ws.WebSocket 'upgrade' event is not implemented`, use Node instead of the bun binary. Bun's WebSocket implementation has edge cases that can break WhatsApp (Baileys).
**For stability:** Use launchd (macOS) or the Clawdis.app — they handle process supervision (auto-restart on crash).
**For debugging:** Use `pnpm gateway:watch` for live reload during development.
### WhatsApp keeps disconnecting / crashing (macOS app)
This is often the bun WebSocket issue. Workaround:
1. Run gateway with Node instead:
```bash
pnpm gateway:watch
```
2. In **Clawdis.app → Settings → Debug**, check **"External gateway"**
3. The app now connects to your Node gateway instead of spawning bun
This is the most stable setup until bun's WebSocket handling improves.
---
## Multi-Instance & Contexts
@ -213,6 +281,31 @@ One WhatsApp account = one phone number = one gateway connection. For a second n
---
## Skills & Tools
### How do I add new skills?
Skills are auto-discovered from your workspace's `skills/` folder. After adding new skills:
1. Send `/reset` (or `/new`) in chat to start a new session
2. The new skills will be available
No gateway restart needed!
### How do I run commands on other machines?
Use **[Tailscale](https://tailscale.com/)** to create a secure network between your machines:
1. Install Tailscale on all machines (it's separate from Clawdis — set it up yourself)
2. Each gets a stable IP (like `100.x.x.x`)
3. SSH just works: `ssh user@100.x.x.x "command"`
Clawdis can use Tailscale when you set `bridge.bind: "tailnet"` in your config — it auto-detects your Tailscale IP.
For deeper integration, look into **Clawdis nodes** — pair remote machines with your gateway for camera/screen/automation access.
---
## Troubleshooting
### Build errors (TypeScript)
@ -246,6 +339,53 @@ Common issues:
- Missing API keys in config
- Invalid config syntax (remember it's JSON5, but still check for errors)
**Debug mode** — use watch for live reload:
```bash
pnpm gateway:watch
```
**Pro tip:** Use Codex to debug:
```bash
cd ~/path/to/clawdis
codex --full-auto "debug why clawdis gateway won't start"
```
### Processes keep restarting after I kill them (Linux)
Something is supervising them. Check:
```bash
# systemd?
systemctl list-units | grep -i clawdis
sudo systemctl stop clawdis
# pm2?
pm2 list
pm2 delete all
```
Stop the supervisor first, then the processes.
### Clean uninstall (start fresh)
```bash
# Stop processes
pkill -f "clawdis"
# If using systemd
sudo systemctl stop clawdis
sudo systemctl disable clawdis
# Remove data
rm -rf ~/.clawdis
# Remove repo and re-clone
rm -rf ~/clawdis
git clone https://github.com/steipete/clawdis.git
cd clawdis && pnpm install && pnpm build
pnpm clawdis onboard
```
---
## Chat Commands

View File

@ -9,7 +9,7 @@ Goal: let Clawd sit in WhatsApp groups, wake up only when pinged, and keep that
## Whats implemented (2025-12-03)
- Activation modes: `mention` (default) or `always`. `mention` requires a ping (real WhatsApp @-mentions via `mentionedJids`, regex patterns, or the bots E.164 anywhere in the text). `always` wakes the agent on every message but it should reply only when it can add meaningful value; otherwise it returns the silent token `NO_REPLY`. Activation is controlled per group (command or UI), not via config.
- Group allowlist bypass: we still enforce `routing.allowFrom` on the participant at inbox ingest, but group JIDs themselves no longer block replies.
- Group allowlist bypass: we still enforce `whatsapp.allowFrom` on the participant at inbox ingest, but group JIDs themselves no longer block replies.
- Per-group sessions: session keys look like `whatsapp:group:<jid>` so commands such as `/verbose on` or `/think:high` are scoped to that group; personal DM state is untouched. Heartbeats are skipped for group threads.
- Context injection: last N (default 50) group messages are prefixed under `[Chat messages since your last reply - for context]`, with the triggering line under `[Current message - respond to this]`.
- Sender surfacing: every group batch now ends with `[from: Sender Name (+E164)]` so Pi knows who is speaking.
@ -45,7 +45,7 @@ Use the group chat command:
- `/activation mention`
- `/activation always`
Only the owner number (from `routing.allowFrom`, defaulting to the bots own E.164 when unset) can change this. `/status` in the group shows the current activation mode.
Only the owner number (from `whatsapp.allowFrom`, defaulting to the bots own E.164 when unset) can change this. `/status` in the group shows the current activation mode.
## How to use
1) Add Clawd UK (`+447700900123`) to the group.

View File

@ -40,7 +40,7 @@ Group owners can toggle per-group activation:
- `/activation mention`
- `/activation always`
Owner is determined by `routing.allowFrom` (or the bots default identity when unset).
Owner is determined by `whatsapp.allowFrom` (or the bots self E.164 when unset). Other surfaces currently ignore `/activation`.
## Context fields
Group inbound payloads set:

View File

@ -22,7 +22,7 @@ Short guide to verify the WhatsApp Web / Baileys stack without guessing.
## When something fails
- `logged out` or status 409515 → relink with `clawdis logout` then `clawdis login`.
- Gateway unreachable → start it: `clawdis gateway --port 18789` (use `--force` if the port is busy).
- No inbound messages → confirm linked phone is online and the sender is allowed (`routing.allowFrom`); for group chats, ensure mention rules match (`routing.groupChat`).
- No inbound messages → confirm linked phone is online and the sender is allowed (`whatsapp.allowFrom`); for group chats, ensure mention rules match (`routing.groupChat`).
## Dedicated "health" command
`clawdis health --json` asks the running Gateway for its health snapshot (no direct Baileys socket from the CLI). It reports linked creds, auth age, Baileys connect result/status code, session-store summary, and a probe duration. It exits non-zero if the Gateway is unreachable or the probe fails/timeouts. Use `--timeout <ms>` to override the 10s default.

View File

@ -100,16 +100,14 @@ clawdis send --to +15555550123 --message "Hello from CLAWDIS"
Config lives at `~/.clawdis/clawdis.json`.
- If you **do nothing**, CLAWDIS uses the bundled Pi binary in RPC mode with per-sender sessions.
- If you want to lock it down, start with `routing.allowFrom` and (for groups) mention rules.
- If you want to lock it down, start with `whatsapp.allowFrom` and (for groups) mention rules.
Example:
```json5
{
routing: {
allowFrom: ["+15555550123"],
groupChat: { requireMention: true, mentionPatterns: ["@clawd"] }
}
whatsapp: { allowFrom: ["+15555550123"] },
routing: { groupChat: { requireMention: true, mentionPatterns: ["@clawd"] } }
}
```

View File

@ -22,6 +22,10 @@ First question: where does the **Gateway** run?
- **Local (this Mac):** onboarding can run the Anthropic OAuth flow and write the Clawdis token store locally.
- **Remote (over SSH/tailnet):** onboarding must not run OAuth locally, because credentials must exist on the **gateway host**.
Gateway auth tip:
- If you only use Clawdis on this Mac (loopback gateway), keep auth **Off**.
- Use **Token** for multi-machine access or non-loopback binds.
Implementation note (2025-12-19): in local mode, the macOS app bundles the Gateway and enables it via a per-user launchd LaunchAgent (no global npm install/Node requirement for the user).
## 2) Local-only: Connect Claude (Anthropic OAuth)

View File

@ -42,7 +42,7 @@ This is social engineering 101. Create distrust, encourage snooping.
```json
{
"routing": {
"whatsapp": {
"allowFrom": ["+15555550123"]
}
}

View File

@ -25,7 +25,7 @@ Status: ready for bot-mode use with grammY (long-polling by default; webhook sup
- If you need a different public port/host, set `telegram.webhookUrl` to the externally reachable URL and use a reverse proxy to forward to `:8787`.
4) Direct chats: user sends the first message; all subsequent turns land in the shared `main` session (default, no extra config).
5) Groups: add the bot, disable privacy mode (or make it admin) so it can read messages; group threads stay on `telegram:group:<chatId>` and require mention/command to trigger replies.
6) Optional allowlist: reuse `routing.allowFrom` for direct chats by chat id (`123456789` or `telegram:123456789`).
6) Optional allowlist: use `telegram.allowFrom` for direct chats by chat id (`123456789` or `telegram:123456789`).
## Capabilities & limits (Bot API)
- Sees only messages sent after its added to a chat; no pre-history access.

View File

@ -22,9 +22,9 @@ The agent was interrupted mid-response.
### Messages Not Triggering
**Check 1:** Is the sender in `routing.allowFrom`?
**Check 1:** Is the sender in `whatsapp.allowFrom`?
```bash
cat ~/.clawdis/clawdis.json | jq '.routing.allowFrom'
cat ~/.clawdis/clawdis.json | jq '.whatsapp.allowFrom'
```
**Check 2:** For group chats, is mention required?

View File

@ -31,8 +31,8 @@ Status: WhatsApp Web via Baileys only. Gateway owns the single session.
- Inbox listeners are detached on shutdown to avoid accumulating event handlers in tests/restarts.
- Status/broadcast chats are ignored.
- Direct chats use E.164; groups use group JID.
- **Allowlist**: `routing.allowFrom` enforced for direct chats only.
- If `routing.allowFrom` is empty, default allowlist = self number (self-chat mode).
- **Allowlist**: `whatsapp.allowFrom` enforced for direct chats only.
- If `whatsapp.allowFrom` is empty, default allowlist = self number (self-chat mode).
- **Self-chat mode**: avoids auto read receipts and ignores mention JIDs.
- Read receipts sent for non-self-chat DMs.
@ -57,7 +57,7 @@ Status: WhatsApp Web via Baileys only. Gateway owns the single session.
- `mention` (default): requires @mention or regex match.
- `always`: always triggers.
- `/activation mention|always` is owner-only.
- Owner = `routing.allowFrom` (or self E.164 if unset).
- Owner = `whatsapp.allowFrom` (or self E.164 if unset).
- **History injection**:
- Recent messages (default 50) inserted under:
`[Chat messages since your last reply - for context]`
@ -98,7 +98,7 @@ Status: WhatsApp Web via Baileys only. Gateway owns the single session.
- Logged-out => stop and require re-link.
## Config quick map
- `routing.allowFrom` (DM allowlist).
- `whatsapp.allowFrom` (DM allowlist).
- `routing.groupChat.mentionPatterns`
- `routing.groupChat.historyLimit`
- `messages.messagePrefix` (inbound prefix)

View File

@ -58,6 +58,7 @@ It does **not** install or change anything on the remote host.
4) **Gateway**
- Port, bind, auth mode, tailscale exposure.
- Auth recommendation: keep **Off** for single-machine loopback setups. Use **Token** for multi-machine access or non-loopback binds.
- Nonloopback binds require auth.
5) **Providers**

View File

@ -98,6 +98,8 @@ cat > "$ENT_TMP_BASE" <<'PLIST'
<true/>
<key>com.apple.security.device.audio-input</key>
<true/>
<key>com.apple.security.device.camera</key>
<true/>
</dict>
</plist>
PLIST
@ -111,6 +113,8 @@ cat > "$ENT_TMP_APP_BASE" <<'PLIST'
<true/>
<key>com.apple.security.device.audio-input</key>
<true/>
<key>com.apple.security.device.camera</key>
<true/>
</dict>
</plist>
PLIST
@ -139,6 +143,8 @@ cat > "$ENT_TMP_APP" <<'PLIST'
<true/>
<key>com.apple.security.device.audio-input</key>
<true/>
<key>com.apple.security.device.camera</key>
<true/>
</dict>
</plist>
PLIST

View File

@ -0,0 +1,101 @@
# Local Places
This repo is a fusion of two pieces:
- A FastAPI server that exposes endpoints for searching and resolving places via the Google Maps Places API.
- A companion agent skill that explains how to use the API and can call it to find places efficiently.
Together, the skill and server let an agent turn natural-language place queries into structured results quickly.
## Run locally
```bash
# copy skill definition into the relevant folder (where the agent looks for it)
# then run the server
uv venv
uv pip install -e ".[dev]"
uv run --env-file .env uvicorn local_places.main:app --host 0.0.0.0 --reload
```
Open the API docs at http://127.0.0.1:8000/docs.
## Places API
Set the Google Places API key before running:
```bash
export GOOGLE_PLACES_API_KEY="your-key"
```
Endpoints:
- `POST /places/search` (free-text query + filters)
- `GET /places/{place_id}` (place details)
- `POST /locations/resolve` (resolve a user-provided location string)
Example search request:
```json
{
"query": "italian restaurant",
"filters": {
"types": ["restaurant"],
"open_now": true,
"min_rating": 4.0,
"price_levels": [1, 2]
},
"limit": 10
}
```
Notes:
- `filters.types` supports a single type (mapped to Google `includedType`).
Example search request (curl):
```bash
curl -X POST http://127.0.0.1:8000/places/search \
-H "Content-Type: application/json" \
-d '{
"query": "italian restaurant",
"location_bias": {
"lat": 40.8065,
"lng": -73.9719,
"radius_m": 3000
},
"filters": {
"types": ["restaurant"],
"open_now": true,
"min_rating": 4.0,
"price_levels": [1, 2, 3]
},
"limit": 10
}'
```
Example resolve request (curl):
```bash
curl -X POST http://127.0.0.1:8000/locations/resolve \
-H "Content-Type: application/json" \
-d '{
"location_text": "Riverside Park, New York",
"limit": 5
}'
```
## Test
```bash
uv run pytest
```
## OpenAPI
Generate the OpenAPI schema:
```bash
uv run python scripts/generate_openapi.py
```

View File

@ -0,0 +1,91 @@
---
name: local-places
description: Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.
homepage: https://github.com/Hyaxia/local_places
metadata: {"clawdis":{"emoji":"📍","requires":{"bins":["uv"],"env":["GOOGLE_PLACES_API_KEY"]},"primaryEnv":"GOOGLE_PLACES_API_KEY"}}
---
# 📍 Local Places
*Find places, Go fast*
Search for nearby places using a local Google Places API proxy. Two-step flow: resolve location first, then search.
## Setup
```bash
cd {baseDir}
echo "GOOGLE_PLACES_API_KEY=your-key" > .env
uv venv && uv pip install -e ".[dev]"
uv run --env-file .env uvicorn local_places.main:app --host 127.0.0.1 --port 8000
```
Requires `GOOGLE_PLACES_API_KEY` in `.env` or environment.
## Quick Start
1. **Check server:** `curl http://127.0.0.1:8000/ping`
2. **Resolve location:**
```bash
curl -X POST http://127.0.0.1:8000/locations/resolve \
-H "Content-Type: application/json" \
-d '{"location_text": "Soho, London", "limit": 5}'
```
3. **Search places:**
```bash
curl -X POST http://127.0.0.1:8000/places/search \
-H "Content-Type: application/json" \
-d '{
"query": "coffee shop",
"location_bias": {"lat": 51.5137, "lng": -0.1366, "radius_m": 1000},
"filters": {"open_now": true, "min_rating": 4.0},
"limit": 10
}'
```
4. **Get details:**
```bash
curl http://127.0.0.1:8000/places/{place_id}
```
## Conversation Flow
1. If user says "near me" or gives vague location → resolve it first
2. If multiple results → show numbered list, ask user to pick
3. Ask for preferences: type, open now, rating, price level
4. Search with `location_bias` from chosen location
5. Present results with name, rating, address, open status
6. Offer to fetch details or refine search
## Filter Constraints
- `filters.types`: exactly ONE type (e.g., "restaurant", "cafe", "gym")
- `filters.price_levels`: integers 0-4 (0=free, 4=very expensive)
- `filters.min_rating`: 0-5 in 0.5 increments
- `filters.open_now`: boolean
- `limit`: 1-20 for search, 1-10 for resolve
- `location_bias.radius_m`: must be > 0
## Response Format
```json
{
"results": [
{
"place_id": "ChIJ...",
"name": "Coffee Shop",
"address": "123 Main St",
"location": {"lat": 51.5, "lng": -0.1},
"rating": 4.6,
"price_level": 2,
"types": ["cafe", "food"],
"open_now": true
}
],
"next_page_token": "..."
}
```
Use `next_page_token` as `page_token` in next request for more results.

View File

@ -0,0 +1,27 @@
[project]
name = "my-api"
version = "0.1.0"
description = "FastAPI server"
readme = "README.md"
requires-python = ">=3.11"
dependencies = [
"fastapi>=0.110.0",
"httpx>=0.27.0",
"uvicorn[standard]>=0.29.0",
]
[project.optional-dependencies]
dev = [
"pytest>=8.0.0",
]
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[tool.hatch.build.targets.wheel]
packages = ["src/local_places"]
[tool.pytest.ini_options]
addopts = "-q"
testpaths = ["tests"]

View File

@ -0,0 +1,2 @@
__all__ = ["__version__"]
__version__ = "0.1.0"

View File

@ -0,0 +1,314 @@
from __future__ import annotations
import logging
import os
from typing import Any
import httpx
from fastapi import HTTPException
from local_places.schemas import (
LatLng,
LocationResolveRequest,
LocationResolveResponse,
PlaceDetails,
PlaceSummary,
ResolvedLocation,
SearchRequest,
SearchResponse,
)
GOOGLE_PLACES_BASE_URL = os.getenv(
"GOOGLE_PLACES_BASE_URL", "https://places.googleapis.com/v1"
)
logger = logging.getLogger("local_places.google_places")
_PRICE_LEVEL_TO_ENUM = {
0: "PRICE_LEVEL_FREE",
1: "PRICE_LEVEL_INEXPENSIVE",
2: "PRICE_LEVEL_MODERATE",
3: "PRICE_LEVEL_EXPENSIVE",
4: "PRICE_LEVEL_VERY_EXPENSIVE",
}
_ENUM_TO_PRICE_LEVEL = {value: key for key, value in _PRICE_LEVEL_TO_ENUM.items()}
_SEARCH_FIELD_MASK = (
"places.id,"
"places.displayName,"
"places.formattedAddress,"
"places.location,"
"places.rating,"
"places.priceLevel,"
"places.types,"
"places.currentOpeningHours,"
"nextPageToken"
)
_DETAILS_FIELD_MASK = (
"id,"
"displayName,"
"formattedAddress,"
"location,"
"rating,"
"priceLevel,"
"types,"
"regularOpeningHours,"
"currentOpeningHours,"
"nationalPhoneNumber,"
"websiteUri"
)
_RESOLVE_FIELD_MASK = (
"places.id,"
"places.displayName,"
"places.formattedAddress,"
"places.location,"
"places.types"
)
class _GoogleResponse:
def __init__(self, response: httpx.Response):
self.status_code = response.status_code
self._response = response
def json(self) -> dict[str, Any]:
return self._response.json()
@property
def text(self) -> str:
return self._response.text
def _api_headers(field_mask: str) -> dict[str, str]:
api_key = os.getenv("GOOGLE_PLACES_API_KEY")
if not api_key:
raise HTTPException(
status_code=500,
detail="GOOGLE_PLACES_API_KEY is not set.",
)
return {
"Content-Type": "application/json",
"X-Goog-Api-Key": api_key,
"X-Goog-FieldMask": field_mask,
}
def _request(
method: str, url: str, payload: dict[str, Any] | None, field_mask: str
) -> _GoogleResponse:
try:
with httpx.Client(timeout=10.0) as client:
response = client.request(
method=method,
url=url,
headers=_api_headers(field_mask),
json=payload,
)
except httpx.HTTPError as exc:
raise HTTPException(status_code=502, detail="Google Places API unavailable.") from exc
return _GoogleResponse(response)
def _build_text_query(request: SearchRequest) -> str:
keyword = request.filters.keyword if request.filters else None
if keyword:
return f"{request.query} {keyword}".strip()
return request.query
def _build_search_body(request: SearchRequest) -> dict[str, Any]:
body: dict[str, Any] = {
"textQuery": _build_text_query(request),
"pageSize": request.limit,
}
if request.page_token:
body["pageToken"] = request.page_token
if request.location_bias:
body["locationBias"] = {
"circle": {
"center": {
"latitude": request.location_bias.lat,
"longitude": request.location_bias.lng,
},
"radius": request.location_bias.radius_m,
}
}
if request.filters:
filters = request.filters
if filters.types:
body["includedType"] = filters.types[0]
if filters.open_now is not None:
body["openNow"] = filters.open_now
if filters.min_rating is not None:
body["minRating"] = filters.min_rating
if filters.price_levels:
body["priceLevels"] = [
_PRICE_LEVEL_TO_ENUM[level] for level in filters.price_levels
]
return body
def _parse_lat_lng(raw: dict[str, Any] | None) -> LatLng | None:
if not raw:
return None
latitude = raw.get("latitude")
longitude = raw.get("longitude")
if latitude is None or longitude is None:
return None
return LatLng(lat=latitude, lng=longitude)
def _parse_display_name(raw: dict[str, Any] | None) -> str | None:
if not raw:
return None
return raw.get("text")
def _parse_open_now(raw: dict[str, Any] | None) -> bool | None:
if not raw:
return None
return raw.get("openNow")
def _parse_hours(raw: dict[str, Any] | None) -> list[str] | None:
if not raw:
return None
return raw.get("weekdayDescriptions")
def _parse_price_level(raw: str | None) -> int | None:
if not raw:
return None
return _ENUM_TO_PRICE_LEVEL.get(raw)
def search_places(request: SearchRequest) -> SearchResponse:
url = f"{GOOGLE_PLACES_BASE_URL}/places:searchText"
response = _request("POST", url, _build_search_body(request), _SEARCH_FIELD_MASK)
if response.status_code >= 400:
logger.error(
"Google Places API error %s. response=%s",
response.status_code,
response.text,
)
raise HTTPException(
status_code=502,
detail=f"Google Places API error ({response.status_code}).",
)
try:
payload = response.json()
except ValueError as exc:
logger.error(
"Google Places API returned invalid JSON. response=%s",
response.text,
)
raise HTTPException(status_code=502, detail="Invalid Google response.") from exc
places = payload.get("places", [])
results = []
for place in places:
results.append(
PlaceSummary(
place_id=place.get("id", ""),
name=_parse_display_name(place.get("displayName")),
address=place.get("formattedAddress"),
location=_parse_lat_lng(place.get("location")),
rating=place.get("rating"),
price_level=_parse_price_level(place.get("priceLevel")),
types=place.get("types"),
open_now=_parse_open_now(place.get("currentOpeningHours")),
)
)
return SearchResponse(
results=results,
next_page_token=payload.get("nextPageToken"),
)
def get_place_details(place_id: str) -> PlaceDetails:
url = f"{GOOGLE_PLACES_BASE_URL}/places/{place_id}"
response = _request("GET", url, None, _DETAILS_FIELD_MASK)
if response.status_code >= 400:
logger.error(
"Google Places API error %s. response=%s",
response.status_code,
response.text,
)
raise HTTPException(
status_code=502,
detail=f"Google Places API error ({response.status_code}).",
)
try:
payload = response.json()
except ValueError as exc:
logger.error(
"Google Places API returned invalid JSON. response=%s",
response.text,
)
raise HTTPException(status_code=502, detail="Invalid Google response.") from exc
return PlaceDetails(
place_id=payload.get("id", place_id),
name=_parse_display_name(payload.get("displayName")),
address=payload.get("formattedAddress"),
location=_parse_lat_lng(payload.get("location")),
rating=payload.get("rating"),
price_level=_parse_price_level(payload.get("priceLevel")),
types=payload.get("types"),
phone=payload.get("nationalPhoneNumber"),
website=payload.get("websiteUri"),
hours=_parse_hours(payload.get("regularOpeningHours")),
open_now=_parse_open_now(payload.get("currentOpeningHours")),
)
def resolve_locations(request: LocationResolveRequest) -> LocationResolveResponse:
url = f"{GOOGLE_PLACES_BASE_URL}/places:searchText"
body = {"textQuery": request.location_text, "pageSize": request.limit}
response = _request("POST", url, body, _RESOLVE_FIELD_MASK)
if response.status_code >= 400:
logger.error(
"Google Places API error %s. response=%s",
response.status_code,
response.text,
)
raise HTTPException(
status_code=502,
detail=f"Google Places API error ({response.status_code}).",
)
try:
payload = response.json()
except ValueError as exc:
logger.error(
"Google Places API returned invalid JSON. response=%s",
response.text,
)
raise HTTPException(status_code=502, detail="Invalid Google response.") from exc
places = payload.get("places", [])
results = []
for place in places:
results.append(
ResolvedLocation(
place_id=place.get("id", ""),
name=_parse_display_name(place.get("displayName")),
address=place.get("formattedAddress"),
location=_parse_lat_lng(place.get("location")),
types=place.get("types"),
)
)
return LocationResolveResponse(results=results)

View File

@ -0,0 +1,65 @@
import logging
import os
from fastapi import FastAPI, Request
from fastapi.encoders import jsonable_encoder
from fastapi.exceptions import RequestValidationError
from fastapi.responses import JSONResponse
from local_places.google_places import get_place_details, resolve_locations, search_places
from local_places.schemas import (
LocationResolveRequest,
LocationResolveResponse,
PlaceDetails,
SearchRequest,
SearchResponse,
)
app = FastAPI(
title="My API",
servers=[{"url": os.getenv("OPENAPI_SERVER_URL", "http://maxims-macbook-air:8000")}],
)
logger = logging.getLogger("local_places.validation")
@app.get("/ping")
def ping() -> dict[str, str]:
return {"message": "pong"}
@app.exception_handler(RequestValidationError)
async def validation_exception_handler(
request: Request, exc: RequestValidationError
) -> JSONResponse:
logger.error(
"Validation error on %s %s. body=%s errors=%s",
request.method,
request.url.path,
exc.body,
exc.errors(),
)
return JSONResponse(
status_code=422,
content=jsonable_encoder({"detail": exc.errors()}),
)
@app.post("/places/search", response_model=SearchResponse)
def places_search(request: SearchRequest) -> SearchResponse:
return search_places(request)
@app.get("/places/{place_id}", response_model=PlaceDetails)
def places_details(place_id: str) -> PlaceDetails:
return get_place_details(place_id)
@app.post("/locations/resolve", response_model=LocationResolveResponse)
def locations_resolve(request: LocationResolveRequest) -> LocationResolveResponse:
return resolve_locations(request)
if __name__ == "__main__":
import uvicorn
uvicorn.run("local_places.main:app", host="0.0.0.0", port=8000)

View File

@ -0,0 +1,107 @@
from __future__ import annotations
from pydantic import BaseModel, Field, field_validator
class LatLng(BaseModel):
lat: float = Field(ge=-90, le=90)
lng: float = Field(ge=-180, le=180)
class LocationBias(BaseModel):
lat: float = Field(ge=-90, le=90)
lng: float = Field(ge=-180, le=180)
radius_m: float = Field(gt=0)
class Filters(BaseModel):
types: list[str] | None = None
open_now: bool | None = None
min_rating: float | None = Field(default=None, ge=0, le=5)
price_levels: list[int] | None = None
keyword: str | None = Field(default=None, min_length=1)
@field_validator("types")
@classmethod
def validate_types(cls, value: list[str] | None) -> list[str] | None:
if value is None:
return value
if len(value) > 1:
raise ValueError(
"Only one type is supported. Use query/keyword for additional filtering."
)
return value
@field_validator("price_levels")
@classmethod
def validate_price_levels(cls, value: list[int] | None) -> list[int] | None:
if value is None:
return value
invalid = [level for level in value if level not in range(0, 5)]
if invalid:
raise ValueError("price_levels must be integers between 0 and 4.")
return value
@field_validator("min_rating")
@classmethod
def validate_min_rating(cls, value: float | None) -> float | None:
if value is None:
return value
if (value * 2) % 1 != 0:
raise ValueError("min_rating must be in 0.5 increments.")
return value
class SearchRequest(BaseModel):
query: str = Field(min_length=1)
location_bias: LocationBias | None = None
filters: Filters | None = None
limit: int = Field(default=10, ge=1, le=20)
page_token: str | None = None
class PlaceSummary(BaseModel):
place_id: str
name: str | None = None
address: str | None = None
location: LatLng | None = None
rating: float | None = None
price_level: int | None = None
types: list[str] | None = None
open_now: bool | None = None
class SearchResponse(BaseModel):
results: list[PlaceSummary]
next_page_token: str | None = None
class LocationResolveRequest(BaseModel):
location_text: str = Field(min_length=1)
limit: int = Field(default=5, ge=1, le=10)
class ResolvedLocation(BaseModel):
place_id: str
name: str | None = None
address: str | None = None
location: LatLng | None = None
types: list[str] | None = None
class LocationResolveResponse(BaseModel):
results: list[ResolvedLocation]
class PlaceDetails(BaseModel):
place_id: str
name: str | None = None
address: str | None = None
location: LatLng | None = None
rating: float | None = None
price_level: int | None = None
types: list[str] | None = None
phone: str | None = None
website: str | None = None
hours: list[str] | None = None
open_now: bool | None = None

29
skills/songsee/SKILL.md Normal file
View File

@ -0,0 +1,29 @@
---
name: songsee
description: Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.
homepage: https://github.com/steipete/songsee
metadata: {"clawdis":{"emoji":"🌊","requires":{"bins":["songsee"]},"install":[{"id":"brew","kind":"brew","formula":"steipete/tap/songsee","bins":["songsee"],"label":"Install songsee (brew)"}]}}
---
# songsee
Generate spectrograms + feature panels from audio.
Quick start
- Spectrogram: `songsee track.mp3`
- Multi-panel: `songsee track.mp3 --viz spectrogram,mel,chroma,hpss,selfsim,loudness,tempogram,mfcc,flux`
- Time slice: `songsee track.mp3 --start 12.5 --duration 8 -o slice.jpg`
- Stdin: `cat track.mp3 | songsee - --format png -o out.png`
Common flags
- `--viz` list (repeatable or comma-separated)
- `--style` palette (classic, magma, inferno, viridis, gray)
- `--width` / `--height` output size
- `--window` / `--hop` FFT settings
- `--min-freq` / `--max-freq` frequency range
- `--start` / `--duration` time slice
- `--format` jpg|png
Notes
- WAV/MP3 decode native; other formats use ffmpeg if available.
- Multiple `--viz` renders a grid.

49
skills/weather/SKILL.md Normal file
View File

@ -0,0 +1,49 @@
---
name: weather
description: Get current weather and forecasts (no API key required).
homepage: https://wttr.in/:help
metadata: {"clawdis":{"emoji":"🌤️","requires":{"bins":["curl"]}}}
---
# Weather
Two free services, no API keys needed.
## wttr.in (primary)
Quick one-liner:
```bash
curl -s "wttr.in/London?format=3"
# Output: London: ⛅️ +8°C
```
Compact format:
```bash
curl -s "wttr.in/London?format=%l:+%c+%t+%h+%w"
# Output: London: ⛅️ +8°C 71% ↙5km/h
```
Full forecast:
```bash
curl -s "wttr.in/London?T"
```
Format codes: `%c` condition · `%t` temp · `%h` humidity · `%w` wind · `%l` location · `%m` moon
Tips:
- URL-encode spaces: `wttr.in/New+York`
- Airport codes: `wttr.in/JFK`
- Units: `?m` (metric) `?u` (USCS)
- Today only: `?1` · Current only: `?0`
- PNG: `curl -s "wttr.in/Berlin.png" -o /tmp/weather.png`
## Open-Meteo (fallback, JSON)
Free, no key, good for programmatic use:
```bash
curl -s "https://api.open-meteo.com/v1/forecast?latitude=51.5&longitude=-0.12&current_weather=true"
```
Find coordinates for a city, then query. Returns JSON with temp, windspeed, weathercode.
Docs: https://open-meteo.com/en/docs

View File

@ -0,0 +1,53 @@
import { beforeEach, describe, expect, it, vi } from "vitest";
const callGateway = vi.fn();
vi.mock("../gateway/call.js", () => ({ callGateway }));
vi.mock("../media/image-ops.js", () => ({
getImageMetadata: vi.fn(async () => ({ width: 1, height: 1 })),
resizeToJpeg: vi.fn(async () => Buffer.from("jpeg")),
}));
import { createClawdisTools } from "./clawdis-tools.js";
describe("clawdis_nodes camera_snap", () => {
beforeEach(() => {
callGateway.mockReset();
});
it("maps jpg payloads to image/jpeg", async () => {
callGateway.mockImplementation(async ({ method }) => {
if (method === "node.list") {
return { nodes: [{ nodeId: "mac-1" }] };
}
if (method === "node.invoke") {
return {
payload: {
format: "jpg",
base64: "aGVsbG8=",
width: 1,
height: 1,
},
};
}
throw new Error(`unexpected method: ${String(method)}`);
});
const tool = createClawdisTools().find(
(candidate) => candidate.name === "clawdis_nodes",
);
if (!tool) throw new Error("missing clawdis_nodes tool");
const result = await tool.execute("call1", {
action: "camera_snap",
node: "mac-1",
facing: "front",
});
const images = (result.content ?? []).filter(
(block) => block.type === "image",
);
expect(images).toHaveLength(1);
expect(images[0]?.mimeType).toBe("image/jpeg");
});
});

View File

@ -43,7 +43,7 @@ import { parseDurationMs } from "../cli/parse-duration.js";
import { loadConfig } from "../config/config.js";
import { reactMessageDiscord } from "../discord/send.js";
import { callGateway } from "../gateway/call.js";
import { detectMime } from "../media/mime.js";
import { detectMime, imageMimeFromFormat } from "../media/mime.js";
import { sanitizeToolResultImages } from "./tool-images.js";
// biome-ignore lint/suspicious/noExplicitAny: TypeBox schema type from pi-ai uses a different module instance.
@ -875,7 +875,7 @@ function createCanvasTool(): AnyAgentTool {
});
await writeBase64ToFile(filePath, payload.base64);
const mimeType =
payload.format === "jpeg" ? "image/jpeg" : "image/png";
imageMimeFromFormat(payload.format) ?? "image/png";
return await imageResult({
label: "canvas:snapshot",
path: filePath,
@ -1141,7 +1141,8 @@ function createNodesTool(): AnyAgentTool {
content.push({
type: "image",
data: payload.base64,
mimeType: payload.format === "jpeg" ? "image/jpeg" : "image/png",
mimeType:
imageMimeFromFormat(payload.format) ?? "image/png",
});
details.push({
facing,

View File

@ -10,7 +10,7 @@ describe("buildAgentSystemPromptAppend", () => {
expect(prompt).toContain("## User Identity");
expect(prompt).toContain(
"Owner numbers: +123, +456. Treat messages from these numbers as the user (Peter).",
"Owner numbers: +123, +456. Treat messages from these numbers as the user.",
);
});

View File

@ -25,7 +25,7 @@ export function buildAgentSystemPromptAppend(params: {
.filter(Boolean);
const ownerLine =
ownerNumbers.length > 0
? `Owner numbers: ${ownerNumbers.join(", ")}. Treat messages from these numbers as the user (Peter).`
? `Owner numbers: ${ownerNumbers.join(", ")}. Treat messages from these numbers as the user.`
: undefined;
const reasoningHint = params.reasoningTagHint
? [
@ -36,7 +36,7 @@ export function buildAgentSystemPromptAppend(params: {
"Only text inside <final> is shown to the user; everything else is discarded and never seen by the user.",
"Example:",
"<think>Short internal reasoning.</think>",
"<final>Hey Peter! What would you like to do next?</final>",
"<final>Hey there! What would you like to do next?</final>",
].join(" ")
: undefined;
const runtimeInfo = params.runtimeInfo;

View File

@ -118,7 +118,7 @@ describe("directive parsing", () => {
model: "anthropic/claude-opus-4-5",
workspace: path.join(home, "clawd"),
},
routing: {
whatsapp: {
allowFrom: ["*"],
},
session: { store: path.join(home, "sessions.json") },
@ -168,7 +168,7 @@ describe("directive parsing", () => {
model: "anthropic/claude-opus-4-5",
workspace: path.join(home, "clawd"),
},
routing: { allowFrom: ["*"] },
whatsapp: { allowFrom: ["*"] },
session: { store: storePath },
},
);
@ -195,7 +195,7 @@ describe("directive parsing", () => {
model: "anthropic/claude-opus-4-5",
workspace: path.join(home, "clawd"),
},
routing: { allowFrom: ["*"] },
whatsapp: { allowFrom: ["*"] },
session: { store: storePath },
},
);
@ -208,7 +208,7 @@ describe("directive parsing", () => {
model: "anthropic/claude-opus-4-5",
workspace: path.join(home, "clawd"),
},
routing: { allowFrom: ["*"] },
whatsapp: { allowFrom: ["*"] },
session: { store: storePath },
},
);
@ -264,7 +264,7 @@ describe("directive parsing", () => {
model: "anthropic/claude-opus-4-5",
workspace: path.join(home, "clawd"),
},
routing: {
whatsapp: {
allowFrom: ["*"],
},
session: { store: storePath },
@ -325,7 +325,7 @@ describe("directive parsing", () => {
model: "anthropic/claude-opus-4-5",
workspace: path.join(home, "clawd"),
},
routing: {
whatsapp: {
allowFrom: ["*"],
},
session: { store: storePath },
@ -506,7 +506,7 @@ describe("directive parsing", () => {
workspace: path.join(home, "clawd"),
allowedModels: ["openai/gpt-4.1-mini"],
},
routing: {
whatsapp: {
allowFrom: ["*"],
},
session: { store: storePath },

View File

@ -42,7 +42,7 @@ function makeCfg(home: string) {
model: "anthropic/claude-opus-4-5",
workspace: join(home, "clawd"),
},
routing: {
whatsapp: {
allowFrom: ["*"],
},
session: { store: join(home, "sessions.json") },
@ -283,8 +283,10 @@ describe("trigger handling", () => {
model: "anthropic/claude-opus-4-5",
workspace: join(home, "clawd"),
},
routing: {
whatsapp: {
allowFrom: ["*"],
},
routing: {
groupChat: { requireMention: false },
},
session: { store: join(home, "sessions.json") },
@ -324,7 +326,7 @@ describe("trigger handling", () => {
model: "anthropic/claude-opus-4-5",
workspace: join(home, "clawd"),
},
routing: {
whatsapp: {
allowFrom: ["*"],
},
session: {
@ -363,7 +365,7 @@ describe("trigger handling", () => {
model: "anthropic/claude-opus-4-5",
workspace: join(home, "clawd"),
},
routing: {
whatsapp: {
allowFrom: ["*"],
},
session: {

View File

@ -841,14 +841,27 @@ export async function getReplyFromConfig(
const perMessageQueueMode =
hasQueueDirective && !inlineQueueReset ? inlineQueueMode : undefined;
// Optional allowlist by origin number (E.164 without whatsapp: prefix)
const configuredAllowFrom = cfg.routing?.allowFrom;
const surface = (ctx.Surface ?? "").trim().toLowerCase();
const isWhatsAppSurface =
surface === "whatsapp" ||
(ctx.From ?? "").startsWith("whatsapp:") ||
(ctx.To ?? "").startsWith("whatsapp:");
// WhatsApp owner allowlist (E.164 without whatsapp: prefix); used for group activation only.
const configuredAllowFrom = isWhatsAppSurface
? cfg.whatsapp?.allowFrom
: undefined;
const from = (ctx.From ?? "").replace(/^whatsapp:/, "");
const to = (ctx.To ?? "").replace(/^whatsapp:/, "");
const isSamePhone = from && to && from === to;
// If no config is present, default to self-only DM access.
const isEmptyConfig = Object.keys(cfg).length === 0;
if (isWhatsAppSurface && isEmptyConfig && from && to && from !== to) {
cleanupTyping();
return undefined;
}
const defaultAllowFrom =
(!configuredAllowFrom || configuredAllowFrom.length === 0) && to
isWhatsAppSurface &&
(!configuredAllowFrom || configuredAllowFrom.length === 0) &&
to
? [to]
: undefined;
const allowFrom =
@ -862,10 +875,12 @@ export async function getReplyFromConfig(
: rawBodyNormalized;
const activationCommand = parseActivationCommand(commandBodyNormalized);
const senderE164 = normalizeE164(ctx.SenderE164 ?? "");
const ownerCandidates = (allowFrom ?? []).filter(
(entry) => entry && entry !== "*",
);
if (ownerCandidates.length === 0 && to) ownerCandidates.push(to);
const ownerCandidates = isWhatsAppSurface
? (allowFrom ?? []).filter((entry) => entry && entry !== "*")
: [];
if (isWhatsAppSurface && ownerCandidates.length === 0 && to) {
ownerCandidates.push(to);
}
const ownerList = ownerCandidates
.map((entry) => normalizeE164(entry))
.filter((entry): entry is string => Boolean(entry));
@ -876,20 +891,6 @@ export async function getReplyFromConfig(
abortedLastRun = ABORT_MEMORY.get(abortKey) ?? false;
}
// Same-phone mode (self-messaging) is always allowed
if (isSamePhone) {
logVerbose(`Allowing same-phone mode: from === to (${from})`);
} else if (!isGroup && Array.isArray(allowFrom) && allowFrom.length > 0) {
// Support "*" as wildcard to allow all senders
if (!allowFrom.includes("*") && !allowFrom.includes(from)) {
logVerbose(
`Skipping auto-reply: sender ${from || "<unknown>"} not in allowFrom list`,
);
cleanupTyping();
return undefined;
}
}
if (activationCommand.hasCommand) {
if (!isGroup) {
cleanupTyping();

View File

@ -2,6 +2,7 @@ export type MsgContext = {
Body?: string;
From?: string;
To?: string;
SessionKey?: string;
MessageSid?: string;
ReplyToId?: string;
ReplyToBody?: string;

View File

@ -1 +1 @@
969df6da368b3a802bf0f7f34bf2e30102ae51d91daf45f1fb9328877e2fb335
988ec7bedb11cab74f82faf4475df758e6f07866b69949ffc2cce89cb3d8265b

View File

@ -10,6 +10,7 @@ import { sessionsCommand } from "../commands/sessions.js";
import { setupCommand } from "../commands/setup.js";
import { statusCommand } from "../commands/status.js";
import { updateCommand } from "../commands/update.js";
import { readConfigFileSnapshot } from "../config/config.js";
import { danger, setVerbose } from "../globals.js";
import { loginWeb, logoutWeb } from "../provider-web.js";
import { defaultRuntime } from "../runtime.js";
@ -68,6 +69,21 @@ export function buildProgram() {
}
program.addHelpText("beforeAll", `\n${formatIntroLine(PROGRAM_VERSION)}\n`);
program.hook("preAction", async (_thisCommand, actionCommand) => {
if (actionCommand.name() === "doctor") return;
const snapshot = await readConfigFileSnapshot();
if (snapshot.legacyIssues.length === 0) return;
const issues = snapshot.legacyIssues
.map((issue) => `- ${issue.path}: ${issue.message}`)
.join("\n");
defaultRuntime.error(
danger(
`Legacy config entries detected. Run "clawdis doctor" (or ask your agent) to migrate.\n${issues}`,
),
);
process.exit(1);
});
const examples = [
[
"clawdis login --verbose",

View File

@ -158,7 +158,7 @@ export async function agentCommand(
});
const workspaceDir = workspace.dir;
const allowFrom = (cfg.routing?.allowFrom ?? [])
const allowFrom = (cfg.whatsapp?.allowFrom ?? [])
.map((val) => normalizeE164(val))
.filter((val) => val.length > 1);
@ -451,7 +451,7 @@ export async function agentCommand(
if (deliver) {
if (deliveryProvider === "whatsapp" && !whatsappTarget) {
const err = new Error(
"Delivering to WhatsApp requires --to <E.164> or routing.allowFrom[0]",
"Delivering to WhatsApp requires --to <E.164> or whatsapp.allowFrom[0]",
);
if (!bestEffortDeliver) throw err;
logDeliveryError(err);

101
src/commands/doctor.test.ts Normal file
View File

@ -0,0 +1,101 @@
import { describe, expect, it, vi } from "vitest";
const readConfigFileSnapshot = vi.fn();
const writeConfigFile = vi.fn().mockResolvedValue(undefined);
const migrateLegacyConfig = vi.fn((raw: unknown) => ({
config: raw as Record<string, unknown>,
changes: ["Moved routing.allowFrom → whatsapp.allowFrom."],
}));
vi.mock("@clack/prompts", () => ({
confirm: vi.fn().mockResolvedValue(true),
intro: vi.fn(),
note: vi.fn(),
outro: vi.fn(),
}));
vi.mock("../agents/skills-status.js", () => ({
buildWorkspaceSkillStatus: () => ({ skills: [] }),
}));
vi.mock("../config/config.js", () => ({
CONFIG_PATH_CLAWDIS: "/tmp/clawdis.json",
readConfigFileSnapshot,
writeConfigFile,
migrateLegacyConfig,
}));
vi.mock("../runtime.js", () => ({
defaultRuntime: {
log: () => {},
error: () => {},
exit: () => {
throw new Error("exit");
},
},
}));
vi.mock("../utils.js", () => ({
resolveUserPath: (value: string) => value,
sleep: vi.fn(),
}));
vi.mock("./health.js", () => ({
healthCommand: vi.fn().mockResolvedValue(undefined),
}));
vi.mock("./onboard-helpers.js", () => ({
applyWizardMetadata: (cfg: Record<string, unknown>) => cfg,
DEFAULT_WORKSPACE: "/tmp",
guardCancel: (value: unknown) => value,
printWizardHeader: vi.fn(),
}));
describe("doctor", () => {
it("migrates routing.allowFrom to whatsapp.allowFrom", async () => {
readConfigFileSnapshot.mockResolvedValue({
path: "/tmp/clawdis.json",
exists: true,
raw: "{}",
parsed: { routing: { allowFrom: ["+15555550123"] } },
valid: false,
config: {},
issues: [
{
path: "routing.allowFrom",
message: "legacy",
},
],
legacyIssues: [
{
path: "routing.allowFrom",
message: "legacy",
},
],
});
const { doctorCommand } = await import("./doctor.js");
const runtime = {
log: vi.fn(),
error: vi.fn(),
exit: vi.fn(),
};
migrateLegacyConfig.mockReturnValue({
config: { whatsapp: { allowFrom: ["+15555550123"] } },
changes: ["Moved routing.allowFrom → whatsapp.allowFrom."],
});
await doctorCommand(runtime);
expect(writeConfigFile).toHaveBeenCalledTimes(1);
const written = writeConfigFile.mock.calls[0]?.[0] as Record<
string,
unknown
>;
expect((written.whatsapp as Record<string, unknown>)?.allowFrom).toEqual([
"+15555550123",
]);
expect(written.routing).toBeUndefined();
});
});

View File

@ -4,6 +4,7 @@ import { buildWorkspaceSkillStatus } from "../agents/skills-status.js";
import type { ClawdisConfig } from "../config/config.js";
import {
CONFIG_PATH_CLAWDIS,
migrateLegacyConfig,
readConfigFileSnapshot,
writeConfigFile,
} from "../config/config.js";
@ -29,10 +30,42 @@ export async function doctorCommand(runtime: RuntimeEnv = defaultRuntime) {
const snapshot = await readConfigFileSnapshot();
let cfg: ClawdisConfig = snapshot.valid ? snapshot.config : {};
if (snapshot.exists && !snapshot.valid) {
if (
snapshot.exists &&
!snapshot.valid &&
snapshot.legacyIssues.length === 0
) {
note("Config invalid; doctor will run with defaults.", "Config");
}
if (snapshot.legacyIssues.length > 0) {
note(
snapshot.legacyIssues
.map((issue) => `- ${issue.path}: ${issue.message}`)
.join("\n"),
"Legacy config keys detected",
);
const migrate = guardCancel(
await confirm({
message: "Migrate legacy config entries now?",
initialValue: true,
}),
runtime,
);
if (migrate) {
// Legacy migration (2026-01-02, commit: 16420e5b) — normalize per-provider allowlists; move WhatsApp gating into whatsapp.allowFrom.
const { config: migrated, changes } = migrateLegacyConfig(
snapshot.parsed,
);
if (changes.length > 0) {
note(changes.join("\n"), "Doctor changes");
}
if (migrated) {
cfg = migrated;
}
}
}
const workspaceDir = resolveUserPath(
cfg.agent?.workspace ?? DEFAULT_WORKSPACE,
);
@ -57,7 +90,12 @@ export async function doctorCommand(runtime: RuntimeEnv = defaultRuntime) {
await healthCommand({ json: false, timeoutMs: 10_000 }, runtime);
healthOk = true;
} catch (err) {
runtime.error(`Health check failed: ${String(err)}`);
const message = String(err);
if (message.includes("gateway closed")) {
note("Gateway not running.", "Gateway");
} else {
runtime.error(`Health check failed: ${message}`);
}
}
if (!healthOk) {
@ -79,7 +117,12 @@ export async function doctorCommand(runtime: RuntimeEnv = defaultRuntime) {
try {
await healthCommand({ json: false, timeoutMs: 10_000 }, runtime);
} catch (err) {
runtime.error(`Health check failed: ${String(err)}`);
const message = String(err);
if (message.includes("gateway closed")) {
note("Gateway not running.", "Gateway");
} else {
runtime.error(`Health check failed: ${message}`);
}
}
}
}

View File

@ -280,8 +280,16 @@ export async function runInteractiveOnboarding(
await select({
message: "Gateway auth",
options: [
{ value: "off", label: "Off (loopback only)" },
{ value: "token", label: "Token" },
{
value: "off",
label: "Off (loopback only)",
hint: "Recommended for single-machine setups",
},
{
value: "token",
label: "Token",
hint: "Use for multi-machine access or non-loopback binds",
},
{ value: "password", label: "Password" },
],
}),
@ -344,6 +352,7 @@ export async function runInteractiveOnboarding(
const tokenInput = guardCancel(
await text({
message: "Gateway token (blank to generate)",
placeholder: "Needed for multi-machine or non-loopback access",
initialValue: randomToken(),
}),
runtime,
@ -375,7 +384,11 @@ export async function runInteractiveOnboarding(
...nextConfig,
gateway: {
...nextConfig.gateway,
auth: { ...nextConfig.gateway?.auth, mode: "token" },
auth: {
...nextConfig.gateway?.auth,
mode: "token",
token: gatewayToken,
},
},
};
}
@ -482,9 +495,18 @@ export async function runInteractiveOnboarding(
note(
(() => {
const links = resolveControlUiLinks({ bind, port });
return [`Web UI: ${links.httpUrl}`, `Gateway WS: ${links.wsUrl}`].join(
"\n",
);
const tokenParam =
authMode === "token" && gatewayToken
? `?token=${encodeURIComponent(gatewayToken)}`
: "";
const authedUrl = `${links.httpUrl}${tokenParam}`;
return [
`Web UI: ${links.httpUrl}`,
tokenParam ? `Web UI (with token): ${authedUrl}` : undefined,
`Gateway WS: ${links.wsUrl}`,
]
.filter(Boolean)
.join("\n");
})(),
"Control UI",
);
@ -498,7 +520,11 @@ export async function runInteractiveOnboarding(
);
if (wantsOpen) {
const links = resolveControlUiLinks({ bind, port });
await openUrl(links.httpUrl);
const tokenParam =
authMode === "token" && gatewayToken
? `?token=${encodeURIComponent(gatewayToken)}`
: "";
await openUrl(`${links.httpUrl}${tokenParam}`);
}
outro("Onboarding complete.");

View File

@ -64,11 +64,11 @@ function noteDiscordTokenHelp(): void {
);
}
function setRoutingAllowFrom(cfg: ClawdisConfig, allowFrom?: string[]) {
function setWhatsAppAllowFrom(cfg: ClawdisConfig, allowFrom?: string[]) {
return {
...cfg,
routing: {
...cfg.routing,
whatsapp: {
...cfg.whatsapp,
allowFrom,
},
};
@ -78,13 +78,13 @@ async function promptWhatsAppAllowFrom(
cfg: ClawdisConfig,
runtime: RuntimeEnv,
): Promise<ClawdisConfig> {
const existingAllowFrom = cfg.routing?.allowFrom ?? [];
const existingAllowFrom = cfg.whatsapp?.allowFrom ?? [];
const existingLabel =
existingAllowFrom.length > 0 ? existingAllowFrom.join(", ") : "unset";
note(
[
"WhatsApp direct chats are gated by `routing.allowFrom`.",
"WhatsApp direct chats are gated by `whatsapp.allowFrom`.",
'Default (unset) = self-chat only; use "*" to allow anyone.',
`Current: ${existingLabel}`,
].join("\n"),
@ -114,8 +114,8 @@ async function promptWhatsAppAllowFrom(
) as (typeof options)[number]["value"];
if (mode === "keep") return cfg;
if (mode === "self") return setRoutingAllowFrom(cfg, undefined);
if (mode === "any") return setRoutingAllowFrom(cfg, ["*"]);
if (mode === "self") return setWhatsAppAllowFrom(cfg, undefined);
if (mode === "any") return setWhatsAppAllowFrom(cfg, ["*"]);
const allowRaw = guardCancel(
await text({
@ -148,7 +148,7 @@ async function promptWhatsAppAllowFrom(
part === "*" ? "*" : normalizeE164(part),
);
const unique = [...new Set(normalized.filter(Boolean))];
return setRoutingAllowFrom(cfg, unique);
return setWhatsAppAllowFrom(cfg, unique);
}
export async function setupProviders(

View File

@ -22,6 +22,21 @@ function summarizeInstallFailure(message: string): string | undefined {
return cleaned.length > maxLen ? `${cleaned.slice(0, maxLen - 1)}` : cleaned;
}
function formatSkillHint(skill: {
description?: string;
install: Array<{ label: string }>;
}): string {
const desc = skill.description?.trim();
const installLabel = skill.install[0]?.label?.trim();
const combined =
desc && installLabel ? `${desc}${installLabel}` : desc || installLabel;
if (!combined) return "install";
const maxLen = 90;
return combined.length > maxLen
? `${combined.slice(0, maxLen - 1)}`
: combined;
}
function upsertSkillEntry(
cfg: ClawdisConfig,
skillKey: string,
@ -104,7 +119,7 @@ export async function setupSkills(
...installable.map((skill) => ({
value: skill.name,
label: `${skill.emoji ?? "🧩"} ${skill.name}`,
hint: skill.install[0]?.label ?? "install",
hint: formatSkillHint(skill),
})),
],
}),

View File

@ -488,3 +488,50 @@ describe("talk.voiceAliases", () => {
expect(res.ok).toBe(false);
});
});
describe("legacy config detection", () => {
it("rejects routing.allowFrom", async () => {
vi.resetModules();
const { validateConfigObject } = await import("./config.js");
const res = validateConfigObject({
routing: { allowFrom: ["+15555550123"] },
});
expect(res.ok).toBe(false);
if (!res.ok) {
expect(res.issues[0]?.path).toBe("routing.allowFrom");
}
});
it("migrates routing.allowFrom to whatsapp.allowFrom", async () => {
vi.resetModules();
const { migrateLegacyConfig } = await import("./config.js");
const res = migrateLegacyConfig({
routing: { allowFrom: ["+15555550123"] },
});
expect(res.changes).toContain(
"Moved routing.allowFrom → whatsapp.allowFrom.",
);
expect(res.config?.whatsapp?.allowFrom).toEqual(["+15555550123"]);
expect(res.config?.routing?.allowFrom).toBeUndefined();
});
it("surfaces legacy issues in snapshot", async () => {
await withTempHome(async (home) => {
const configPath = path.join(home, ".clawdis", "clawdis.json");
await fs.mkdir(path.dirname(configPath), { recursive: true });
await fs.writeFile(
configPath,
JSON.stringify({ routing: { allowFrom: ["+15555550123"] } }),
"utf-8",
);
vi.resetModules();
const { readConfigFileSnapshot } = await import("./config.js");
const snap = await readConfigFileSnapshot();
expect(snap.valid).toBe(false);
expect(snap.legacyIssues.length).toBe(1);
expect(snap.legacyIssues[0]?.path).toBe("routing.allowFrom");
});
});
});

View File

@ -58,6 +58,11 @@ export type WebConfig = {
reconnect?: WebReconnectConfig;
};
export type WhatsAppConfig = {
/** Optional allowlist for WhatsApp direct chats (E.164). */
allowFrom?: string[];
};
export type BrowserConfig = {
enabled?: boolean;
/** Base URL of the clawd browser control server. Default: http://127.0.0.1:18791 */
@ -187,6 +192,17 @@ export type DiscordGuildEntry = {
channels?: Record<string, DiscordGuildChannelConfig>;
};
export type DiscordSlashCommandConfig = {
/** Enable handling for the configured slash command (default: false). */
enabled?: boolean;
/** Slash command name (default: "clawd"). */
name?: string;
/** Session key prefix for slash commands (default: "discord:slash"). */
sessionPrefix?: string;
/** Reply ephemerally (default: true). */
ephemeral?: boolean;
};
export type DiscordConfig = {
/** If false, do not start the Discord provider. Default: true. */
enabled?: boolean;
@ -195,6 +211,7 @@ export type DiscordConfig = {
historyLimit?: number;
/** Allow agent-triggered Discord reactions (default: true). */
enableReactions?: boolean;
slashCommand?: DiscordSlashCommandConfig;
dm?: DiscordDmConfig;
/** New per-guild config keyed by guild id or slug. */
guilds?: Record<string, DiscordGuildEntry>;
@ -260,7 +277,6 @@ export type GroupChatConfig = {
};
export type RoutingConfig = {
allowFrom?: string[]; // E.164 numbers allowed to trigger auto-reply (without whatsapp:)
transcribeAudio?: {
// Optional CLI to turn inbound audio into text; templated args, must output transcript to stdout.
command: string[];
@ -335,6 +351,8 @@ export type GatewayAuthMode = "token" | "password";
export type GatewayAuthConfig = {
/** Authentication mode for Gateway connections. Defaults to token when set. */
mode?: GatewayAuthMode;
/** Shared token for token mode (stored locally for CLI auth). */
token?: string;
/** Shared password for password mode (consider env instead). */
password?: string;
/** Allow Tailscale identity headers when serve mode is enabled. */
@ -525,6 +543,7 @@ export type ClawdisConfig = {
messages?: MessagesConfig;
session?: SessionConfig;
web?: WebConfig;
whatsapp?: WhatsAppConfig;
telegram?: TelegramConfig;
discord?: DiscordConfig;
signal?: SignalConfig;
@ -693,7 +712,6 @@ const HeartbeatSchema = z
const RoutingSchema = z
.object({
allowFrom: z.array(z.string()).optional(),
groupChat: GroupChatSchema,
transcribeAudio: TranscribeAudioSchema,
queue: z
@ -909,6 +927,11 @@ const ClawdisSchema = z.object({
.optional(),
})
.optional(),
whatsapp: z
.object({
allowFrom: z.array(z.string()).optional(),
})
.optional(),
telegram: z
.object({
enabled: z.boolean().optional(),
@ -927,6 +950,14 @@ const ClawdisSchema = z.object({
.object({
enabled: z.boolean().optional(),
token: z.string().optional(),
slashCommand: z
.object({
enabled: z.boolean().optional(),
name: z.string().optional(),
sessionPrefix: z.string().optional(),
ephemeral: z.boolean().optional(),
})
.optional(),
mediaMaxMb: z.number().positive().optional(),
historyLimit: z.number().int().min(0).optional(),
enableReactions: z.boolean().optional(),
@ -1068,6 +1099,7 @@ const ClawdisSchema = z.object({
auth: z
.object({
mode: z.union([z.literal("token"), z.literal("password")]).optional(),
token: z.string().optional(),
password: z.string().optional(),
allowTailscale: z.boolean().optional(),
})
@ -1131,6 +1163,11 @@ export type ConfigValidationIssue = {
message: string;
};
export type LegacyConfigIssue = {
path: string;
message: string;
};
export type ConfigFileSnapshot = {
path: string;
exists: boolean;
@ -1139,8 +1176,102 @@ export type ConfigFileSnapshot = {
valid: boolean;
config: ClawdisConfig;
issues: ConfigValidationIssue[];
legacyIssues: LegacyConfigIssue[];
};
type LegacyConfigRule = {
path: string[];
message: string;
};
type LegacyConfigMigration = {
id: string;
describe: string;
apply: (raw: Record<string, unknown>, changes: string[]) => void;
};
const LEGACY_CONFIG_RULES: LegacyConfigRule[] = [
{
path: ["routing", "allowFrom"],
message:
"routing.allowFrom was removed; use whatsapp.allowFrom instead (run `clawdis doctor` to migrate).",
},
];
const LEGACY_CONFIG_MIGRATIONS: LegacyConfigMigration[] = [
{
id: "routing.allowFrom->whatsapp.allowFrom",
describe: "Move routing.allowFrom to whatsapp.allowFrom",
apply: (raw, changes) => {
const routing = raw.routing;
if (!routing || typeof routing !== "object") return;
const allowFrom = (routing as Record<string, unknown>).allowFrom;
if (allowFrom === undefined) return;
const whatsapp =
raw.whatsapp && typeof raw.whatsapp === "object"
? (raw.whatsapp as Record<string, unknown>)
: {};
if (whatsapp.allowFrom === undefined) {
whatsapp.allowFrom = allowFrom;
changes.push("Moved routing.allowFrom → whatsapp.allowFrom.");
} else {
changes.push(
"Removed routing.allowFrom (whatsapp.allowFrom already set).",
);
}
delete (routing as Record<string, unknown>).allowFrom;
if (Object.keys(routing as Record<string, unknown>).length === 0) {
delete raw.routing;
}
raw.whatsapp = whatsapp;
},
},
];
function findLegacyConfigIssues(raw: unknown): LegacyConfigIssue[] {
if (!raw || typeof raw !== "object") return [];
const root = raw as Record<string, unknown>;
const issues: LegacyConfigIssue[] = [];
for (const rule of LEGACY_CONFIG_RULES) {
let cursor: unknown = root;
for (const key of rule.path) {
if (!cursor || typeof cursor !== "object") {
cursor = undefined;
break;
}
cursor = (cursor as Record<string, unknown>)[key];
}
if (cursor !== undefined) {
issues.push({ path: rule.path.join("."), message: rule.message });
}
}
return issues;
}
export function migrateLegacyConfig(raw: unknown): {
config: ClawdisConfig | null;
changes: string[];
} {
if (!raw || typeof raw !== "object") return { config: null, changes: [] };
const next = structuredClone(raw) as Record<string, unknown>;
const changes: string[] = [];
for (const migration of LEGACY_CONFIG_MIGRATIONS) {
migration.apply(next, changes);
}
if (changes.length === 0) return { config: null, changes: [] };
const validated = validateConfigObject(next);
if (!validated.ok) {
changes.push(
"Migration applied, but config still invalid; fix remaining issues manually.",
);
return { config: null, changes };
}
return { config: validated.config, changes };
}
function escapeRegExp(text: string): string {
return text.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
}
@ -1199,6 +1330,16 @@ export function validateConfigObject(
):
| { ok: true; config: ClawdisConfig }
| { ok: false; issues: ConfigValidationIssue[] } {
const legacyIssues = findLegacyConfigIssues(raw);
if (legacyIssues.length > 0) {
return {
ok: false,
issues: legacyIssues.map((iss) => ({
path: iss.path,
message: iss.message,
})),
};
}
const validated = ClawdisSchema.safeParse(raw);
if (!validated.success) {
return {
@ -1271,6 +1412,7 @@ export async function readConfigFileSnapshot(): Promise<ConfigFileSnapshot> {
const exists = fs.existsSync(configPath);
if (!exists) {
const config = applyTalkApiKey({});
const legacyIssues: LegacyConfigIssue[] = [];
return {
path: configPath,
exists: false,
@ -1279,6 +1421,7 @@ export async function readConfigFileSnapshot(): Promise<ConfigFileSnapshot> {
valid: true,
config,
issues: [],
legacyIssues,
};
}
@ -1296,9 +1439,12 @@ export async function readConfigFileSnapshot(): Promise<ConfigFileSnapshot> {
issues: [
{ path: "", message: `JSON5 parse failed: ${parsedRes.error}` },
],
legacyIssues: [],
};
}
const legacyIssues = findLegacyConfigIssues(parsedRes.parsed);
const validated = validateConfigObject(parsedRes.parsed);
if (!validated.ok) {
return {
@ -1309,6 +1455,7 @@ export async function readConfigFileSnapshot(): Promise<ConfigFileSnapshot> {
valid: false,
config: {},
issues: validated.issues,
legacyIssues,
};
}
@ -1320,6 +1467,7 @@ export async function readConfigFileSnapshot(): Promise<ConfigFileSnapshot> {
valid: true,
config: applyTalkApiKey(validated.config),
issues: [],
legacyIssues,
};
} catch (err) {
return {
@ -1330,6 +1478,7 @@ export async function readConfigFileSnapshot(): Promise<ConfigFileSnapshot> {
valid: false,
config: {},
issues: [{ path: "", message: `read failed: ${String(err)}` }],
legacyIssues: [],
};
}
}

View File

@ -349,6 +349,8 @@ export function resolveSessionKey(
ctx: MsgContext,
mainKey?: string,
) {
const explicit = ctx.SessionKey?.trim();
if (explicit) return explicit;
const raw = deriveSessionKey(scope, ctx);
if (scope === "global") return raw;
// Default to a single shared direct-chat session called "main"; groups stay isolated.

View File

@ -103,7 +103,7 @@ function resolveDeliveryTarget(
const sanitizedWhatsappTo = (() => {
if (channel !== "whatsapp") return to;
const rawAllow = cfg.routing?.allowFrom ?? [];
const rawAllow = cfg.whatsapp?.allowFrom ?? [];
if (rawAllow.includes("*")) return to;
const allowFrom = rawAllow
.map((val) => normalizeE164(val))

View File

@ -1,6 +1,8 @@
import {
ApplicationCommandOptionType,
ChannelType,
Client,
type CommandInteractionOption,
Events,
GatewayIntentBits,
type Message,
@ -10,10 +12,12 @@ import {
import { chunkText } from "../auto-reply/chunk.js";
import { formatAgentEnvelope } from "../auto-reply/envelope.js";
import { getReplyFromConfig } from "../auto-reply/reply.js";
import { SILENT_REPLY_TOKEN } from "../auto-reply/tokens.js";
import type { ReplyPayload } from "../auto-reply/types.js";
import type { DiscordSlashCommandConfig } from "../config/config.js";
import { loadConfig } from "../config/config.js";
import { resolveStorePath, updateLastRoute } from "../config/sessions.js";
import { danger, isVerbose, logVerbose } from "../globals.js";
import { danger, isVerbose, logVerbose, warn } from "../globals.js";
import { getChildLogger } from "../logging.js";
import { detectMime } from "../media/mime.js";
import { saveMediaBuffer } from "../media/store.js";
@ -25,6 +29,7 @@ export type MonitorDiscordOpts = {
token?: string;
runtime?: RuntimeEnv;
abortSignal?: AbortSignal;
slashCommand?: DiscordSlashCommandConfig;
mediaMaxMb?: number;
historyLimit?: number;
};
@ -86,6 +91,9 @@ export async function monitorDiscordProvider(opts: MonitorDiscordOpts = {}) {
const dmConfig = cfg.discord?.dm;
const guildEntries = cfg.discord?.guilds;
const allowFrom = dmConfig?.allowFrom;
const slashCommand = resolveSlashCommandConfig(
opts.slashCommand ?? cfg.discord?.slashCommand,
);
const mediaMaxBytes =
(opts.mediaMaxMb ?? cfg.discord?.mediaMaxMb ?? 8) * 1024 * 1024;
const historyLimit = Math.max(
@ -111,6 +119,9 @@ export async function monitorDiscordProvider(opts: MonitorDiscordOpts = {}) {
client.once(Events.ClientReady, () => {
runtime.log?.(`logged in as ${client.user?.tag ?? "unknown"}`);
if (slashCommand.enabled) {
void ensureSlashCommand(client, slashCommand, runtime);
}
});
client.on(Events.Error, (err) => {
@ -376,6 +387,163 @@ export async function monitorDiscordProvider(opts: MonitorDiscordOpts = {}) {
}
});
client.on(Events.InteractionCreate, async (interaction) => {
try {
if (!slashCommand.enabled) return;
if (!interaction.isChatInputCommand()) return;
if (interaction.commandName !== slashCommand.name) return;
if (interaction.user?.bot) return;
const channelType = interaction.channel?.type as ChannelType | undefined;
const isGroupDm = channelType === ChannelType.GroupDM;
const isDirectMessage =
!interaction.inGuild() && channelType === ChannelType.DM;
const isGuildMessage = interaction.inGuild();
if (isGroupDm && !groupDmEnabled) return;
if (isDirectMessage && !dmEnabled) return;
if (isGuildMessage) {
const guildInfo = resolveDiscordGuildEntry({
guild: interaction.guild ?? null,
guildEntries,
});
if (
guildEntries &&
Object.keys(guildEntries).length > 0 &&
!guildInfo
) {
logVerbose(
`Blocked discord guild ${interaction.guildId ?? "unknown"} (not in discord.guilds)`,
);
return;
}
const channelName =
interaction.channel && "name" in interaction.channel
? interaction.channel.name
: undefined;
const channelSlug = channelName
? normalizeDiscordSlug(channelName)
: "";
const channelConfig = resolveDiscordChannelConfig({
guildInfo,
channelId: interaction.channelId,
channelName,
channelSlug,
});
if (channelConfig?.allowed === false) {
logVerbose(
`Blocked discord channel ${interaction.channelId} not in guild channel allowlist`,
);
return;
}
const userAllow = guildInfo?.users;
if (Array.isArray(userAllow) && userAllow.length > 0) {
const users = normalizeDiscordAllowList(userAllow, [
"discord:",
"user:",
]);
const userOk =
!users ||
allowListMatches(users, {
id: interaction.user.id,
name: interaction.user.username,
tag: interaction.user.tag,
});
if (!userOk) {
logVerbose(
`Blocked discord guild sender ${interaction.user.id} (not in guild users allowlist)`,
);
return;
}
}
} else if (isGroupDm) {
const channelName =
interaction.channel && "name" in interaction.channel
? interaction.channel.name
: undefined;
const channelSlug = channelName
? normalizeDiscordSlug(channelName)
: "";
const groupDmAllowed = resolveGroupDmAllow({
channels: groupDmChannels,
channelId: interaction.channelId,
channelName,
channelSlug,
});
if (!groupDmAllowed) return;
} else if (isDirectMessage) {
if (Array.isArray(allowFrom) && allowFrom.length > 0) {
const allowList = normalizeDiscordAllowList(allowFrom, [
"discord:",
"user:",
]);
const permitted =
allowList &&
allowListMatches(allowList, {
id: interaction.user.id,
name: interaction.user.username,
tag: interaction.user.tag,
});
if (!permitted) {
logVerbose(
`Blocked unauthorized discord sender ${interaction.user.id} (not in allowFrom)`,
);
return;
}
}
}
const prompt = resolveSlashPrompt(interaction.options.data);
if (!prompt) {
await interaction.reply({
content: "Message required.",
ephemeral: true,
});
return;
}
await interaction.deferReply({ ephemeral: slashCommand.ephemeral });
const userId = interaction.user.id;
const ctxPayload = {
Body: prompt,
From: `discord:${userId}`,
To: `slash:${userId}`,
ChatType: "direct",
SenderName: interaction.user.username,
Surface: "discord" as const,
WasMentioned: true,
MessageSid: interaction.id,
Timestamp: interaction.createdTimestamp,
SessionKey: `${slashCommand.sessionPrefix}:${userId}`,
};
const replyResult = await getReplyFromConfig(ctxPayload, undefined, cfg);
const replies = replyResult
? Array.isArray(replyResult)
? replyResult
: [replyResult]
: [];
await deliverSlashReplies({
replies,
interaction,
ephemeral: slashCommand.ephemeral,
});
} catch (err) {
runtime.error?.(danger(`slash handler failed: ${String(err)}`));
if (interaction.isRepliable()) {
const content = "Sorry, something went wrong handling that command.";
if (interaction.deferred || interaction.replied) {
await interaction.followUp({ content, ephemeral: true });
} else {
await interaction.reply({ content, ephemeral: true });
}
}
}
});
await client.login(token);
await new Promise<void>((resolve, reject) => {
@ -614,6 +782,86 @@ export function resolveGroupDmAllow(params: {
});
}
async function ensureSlashCommand(
client: Client,
slashCommand: Required<DiscordSlashCommandConfig>,
runtime: RuntimeEnv,
) {
try {
const appCommands = client.application?.commands;
if (!appCommands) {
runtime.error?.(danger("discord slash commands unavailable"));
return;
}
const existing = await appCommands.fetch();
const hasCommand = Array.from(existing.values()).some(
(entry) => entry.name === slashCommand.name,
);
if (hasCommand) return;
await appCommands.create({
name: slashCommand.name,
description: "Ask Clawdis a question",
options: [
{
name: "prompt",
description: "What should Clawdis help with?",
type: ApplicationCommandOptionType.String,
required: true,
},
],
});
runtime.log?.(`registered discord slash command /${slashCommand.name}`);
} catch (err) {
const status = (err as { status?: number | string })?.status;
const code = (err as { code?: number | string })?.code;
const message = String(err);
const isRateLimit =
status === 429 || code === 429 || /rate ?limit/i.test(message);
const text = `discord slash command setup failed: ${message}`;
if (isRateLimit) {
logVerbose(text);
runtime.error?.(warn(text));
} else {
runtime.error?.(danger(text));
}
}
}
function resolveSlashCommandConfig(
raw: DiscordSlashCommandConfig | undefined,
): Required<DiscordSlashCommandConfig> {
return {
enabled: raw ? raw.enabled !== false : false,
name: raw?.name?.trim() || "clawd",
sessionPrefix: raw?.sessionPrefix?.trim() || "discord:slash",
ephemeral: raw?.ephemeral !== false,
};
}
function resolveSlashPrompt(
options: readonly CommandInteractionOption[],
): string | undefined {
const direct = findFirstStringOption(options);
if (direct) return direct;
return undefined;
}
function findFirstStringOption(
options: readonly CommandInteractionOption[],
): string | undefined {
for (const option of options) {
if (typeof option.value === "string") {
const trimmed = option.value.trim();
if (trimmed) return trimmed;
}
if (option.options && option.options.length > 0) {
const nested = findFirstStringOption(option.options);
if (nested) return nested;
}
}
return undefined;
}
async function sendTyping(message: Message) {
try {
const channel = message.channel;
@ -659,3 +907,45 @@ async function deliverReplies({
runtime.log?.(`delivered reply to ${target}`);
}
}
async function deliverSlashReplies({
replies,
interaction,
ephemeral,
}: {
replies: ReplyPayload[];
interaction: import("discord.js").ChatInputCommandInteraction;
ephemeral: boolean;
}) {
const messages: string[] = [];
for (const payload of replies) {
const textRaw = payload.text?.trim() ?? "";
const text =
textRaw && textRaw !== SILENT_REPLY_TOKEN ? textRaw : undefined;
const mediaList =
payload.mediaUrls ?? (payload.mediaUrl ? [payload.mediaUrl] : []);
const combined = [
text ?? "",
...mediaList.map((url) => url.trim()).filter(Boolean),
]
.filter(Boolean)
.join("\n");
if (!combined) continue;
for (const chunk of chunkText(combined, 2000)) {
messages.push(chunk);
}
}
if (messages.length === 0) {
await interaction.editReply({
content: "No response was generated for that command.",
});
return;
}
const [first, ...rest] = messages;
await interaction.editReply({ content: first });
for (const message of rest) {
await interaction.followUp({ content: message, ephemeral });
}
}

View File

@ -101,7 +101,7 @@ function isTailscaleProxyRequest(req?: IncomingMessage): boolean {
export function assertGatewayAuthConfigured(auth: ResolvedGatewayAuth): void {
if (auth.mode === "token" && !auth.token) {
throw new Error(
"gateway auth mode is token, but CLAWDIS_GATEWAY_TOKEN is not set",
"gateway auth mode is token, but no token was configured (set gateway.auth.token or CLAWDIS_GATEWAY_TOKEN)",
);
}
if (auth.mode === "password" && !auth.password) {

View File

@ -25,8 +25,8 @@ export async function callGateway<T = unknown>(
): Promise<T> {
const timeoutMs = opts.timeoutMs ?? 10_000;
const config = loadConfig();
const remote =
config.gateway?.mode === "remote" ? config.gateway.remote : undefined;
const isRemoteMode = config.gateway?.mode === "remote";
const remote = isRemoteMode ? config.gateway.remote : undefined;
const url =
(typeof opts.url === "string" && opts.url.trim().length > 0
? opts.url.trim()
@ -39,14 +39,20 @@ export async function callGateway<T = unknown>(
(typeof opts.token === "string" && opts.token.trim().length > 0
? opts.token.trim()
: undefined) ||
(typeof remote?.token === "string" && remote.token.trim().length > 0
? remote.token.trim()
: undefined);
(isRemoteMode
? typeof remote?.token === "string" && remote.token.trim().length > 0
? remote.token.trim()
: undefined
: process.env.CLAWDIS_GATEWAY_TOKEN?.trim() ||
(typeof config.gateway?.auth?.token === "string" &&
config.gateway.auth.token.trim().length > 0
? config.gateway.auth.token.trim()
: undefined));
const password =
(typeof opts.password === "string" && opts.password.trim().length > 0
? opts.password.trim()
: undefined) ||
process.env.CLAWDIS_GATEWAY_PASSWORD ||
process.env.CLAWDIS_GATEWAY_PASSWORD?.trim() ||
(typeof remote?.password === "string" && remote.password.trim().length > 0
? remote.password.trim()
: undefined);

View File

@ -130,6 +130,11 @@ let testGatewayBind: "auto" | "lan" | "tailnet" | "loopback" | undefined;
let testGatewayAuth: Record<string, unknown> | undefined;
let testHooksConfig: Record<string, unknown> | undefined;
let testCanvasHostPort: number | undefined;
let testLegacyIssues: Array<{ path: string; message: string }> = [];
let testLegacyParsed: Record<string, unknown> = {};
let testMigrationConfig: Record<string, unknown> | null = null;
let testMigrationChanges: string[] = [];
const testIsNixMode = vi.hoisted(() => ({ value: false }));
const sessionStoreSaveDelayMs = vi.hoisted(() => ({ value: 0 }));
vi.mock("../config/sessions.js", async () => {
const actual = await vi.importActual<typeof import("../config/sessions.js")>(
@ -151,6 +156,21 @@ vi.mock("../config/config.js", () => {
path.join(os.homedir(), ".clawdis", "clawdis.json");
const readConfigFileSnapshot = async () => {
if (testLegacyIssues.length > 0) {
return {
path: resolveConfigPath(),
exists: true,
raw: JSON.stringify(testLegacyParsed ?? {}),
parsed: testLegacyParsed ?? {},
valid: false,
config: {},
issues: testLegacyIssues.map((issue) => ({
path: issue.path,
message: issue.message,
})),
legacyIssues: testLegacyIssues,
};
}
const configPath = resolveConfigPath();
try {
await fs.access(configPath);
@ -163,6 +183,7 @@ vi.mock("../config/config.js", () => {
valid: true,
config: {},
issues: [],
legacyIssues: [],
};
}
try {
@ -176,6 +197,7 @@ vi.mock("../config/config.js", () => {
valid: true,
config: parsed,
issues: [],
legacyIssues: [],
};
} catch (err) {
return {
@ -186,27 +208,34 @@ vi.mock("../config/config.js", () => {
valid: false,
config: {},
issues: [{ path: "", message: `read failed: ${String(err)}` }],
legacyIssues: [],
};
}
};
const writeConfigFile = async (cfg: Record<string, unknown>) => {
const writeConfigFile = vi.fn(async (cfg: Record<string, unknown>) => {
const configPath = resolveConfigPath();
await fs.mkdir(path.dirname(configPath), { recursive: true });
const raw = JSON.stringify(cfg, null, 2).trimEnd().concat("\n");
await fs.writeFile(configPath, raw, "utf-8");
};
});
return {
CONFIG_PATH_CLAWDIS: resolveConfigPath(),
STATE_DIR_CLAWDIS: path.dirname(resolveConfigPath()),
isNixMode: false,
get isNixMode() {
return testIsNixMode.value;
},
migrateLegacyConfig: (raw: unknown) => ({
config: testMigrationConfig ?? (raw as Record<string, unknown>),
changes: testMigrationChanges,
}),
loadConfig: () => ({
agent: {
model: "anthropic/claude-opus-4-5",
workspace: path.join(os.tmpdir(), "clawd-gateway-test"),
},
routing: {
whatsapp: {
allowFrom: testAllowFrom,
},
session: { mainKey: "main", store: testSessionStorePath },
@ -279,6 +308,11 @@ beforeEach(async () => {
testGatewayAuth = undefined;
testHooksConfig = undefined;
testCanvasHostPort = undefined;
testLegacyIssues = [];
testLegacyParsed = {};
testMigrationConfig = null;
testMigrationChanges = [];
testIsNixMode.value = false;
cronIsolatedRun.mockClear();
drainSystemEvents();
resetAgentRunContextForTest();
@ -516,6 +550,40 @@ describe("gateway server", () => {
},
);
test("auto-migrates legacy config on startup", async () => {
(writeConfigFile as unknown as { mockClear?: () => void })?.mockClear?.();
testLegacyIssues = [
{
path: "routing.allowFrom",
message: "legacy",
},
];
testLegacyParsed = { routing: { allowFrom: ["+15555550123"] } };
testMigrationConfig = { whatsapp: { allowFrom: ["+15555550123"] } };
testMigrationChanges = ["Moved routing.allowFrom → whatsapp.allowFrom."];
const port = await getFreePort();
const server = await startGatewayServer(port);
expect(writeConfigFile).toHaveBeenCalledWith(testMigrationConfig);
await server.close();
});
test("fails in Nix mode when legacy config is present", async () => {
testLegacyIssues = [
{
path: "routing.allowFrom",
message: "legacy",
},
];
testLegacyParsed = { routing: { allowFrom: ["+15555550123"] } };
testIsNixMode.value = true;
const port = await getFreePort();
await expect(startGatewayServer(port)).rejects.toThrow(
"Legacy config entries detected while running in Nix mode",
);
});
test("models.list returns model catalog", async () => {
piSdkMock.enabled = true;
piSdkMock.models = [

View File

@ -48,6 +48,7 @@ import {
CONFIG_PATH_CLAWDIS,
isNixMode,
loadConfig,
migrateLegacyConfig,
parseConfigJson5,
readConfigFileSnapshot,
STATE_DIR_CLAWDIS,
@ -659,8 +660,6 @@ type DedupeEntry = {
error?: ErrorShape;
};
const getGatewayToken = () => process.env.CLAWDIS_GATEWAY_TOKEN;
function formatForLog(value: unknown): string {
try {
if (value instanceof Error) {
@ -1322,6 +1321,31 @@ export async function startGatewayServer(
port = 18789,
opts: GatewayServerOptions = {},
): Promise<GatewayServer> {
const configSnapshot = await readConfigFileSnapshot();
if (configSnapshot.legacyIssues.length > 0) {
if (isNixMode) {
throw new Error(
"Legacy config entries detected while running in Nix mode. Update your Nix config to the latest schema and restart.",
);
}
const { config: migrated, changes } = migrateLegacyConfig(
configSnapshot.parsed,
);
if (!migrated) {
throw new Error(
'Legacy config entries detected but auto-migration failed. Run "clawdis doctor" to migrate.',
);
}
await writeConfigFile(migrated);
if (changes.length > 0) {
log.info(
`gateway: migrated legacy config entries:\n${changes
.map((entry) => `- ${entry}`)
.join("\n")}`,
);
}
}
const cfgAtStart = loadConfig();
const bindMode = opts.bind ?? cfgAtStart.gateway?.bind ?? "loopback";
const bindHost = opts.host ?? resolveGatewayBindHost(bindMode);
@ -1345,7 +1369,8 @@ export async function startGatewayServer(
...tailscaleOverrides,
};
const tailscaleMode = tailscaleConfig.mode ?? "off";
const token = getGatewayToken();
const token =
authConfig.token ?? process.env.CLAWDIS_GATEWAY_TOKEN ?? undefined;
const password =
authConfig.password ?? process.env.CLAWDIS_GATEWAY_PASSWORD ?? undefined;
const authMode: ResolvedGatewayAuth["mode"] =
@ -2228,6 +2253,7 @@ export async function startGatewayServer(
token: discordToken.trim(),
runtime: discordRuntimeEnv,
abortSignal: discordAbort.signal,
slashCommand: cfg.discord?.slashCommand,
mediaMaxMb: cfg.discord?.mediaMaxMb,
historyLimit: cfg.discord?.historyLimit,
})
@ -6641,7 +6667,7 @@ export async function startGatewayServer(
if (explicit) return resolvedTo;
const cfg = cfgForAgent ?? loadConfig();
const rawAllow = cfg.routing?.allowFrom ?? [];
const rawAllow = cfg.whatsapp?.allowFrom ?? [];
if (rawAllow.includes("*")) return resolvedTo;
const allowFrom = rawAllow
.map((val) => normalizeE164(val))

View File

@ -61,8 +61,7 @@ function resolveRuntime(opts: MonitorIMessageOpts): RuntimeEnv {
function resolveAllowFrom(opts: MonitorIMessageOpts): string[] {
const cfg = loadConfig();
const raw =
opts.allowFrom ?? cfg.imessage?.allowFrom ?? cfg.routing?.allowFrom ?? [];
const raw = opts.allowFrom ?? cfg.imessage?.allowFrom ?? [];
return raw.map((entry) => String(entry).trim()).filter(Boolean);
}

View File

@ -94,7 +94,7 @@ describe("resolveHeartbeatDeliveryTarget", () => {
it("applies allowFrom fallback for WhatsApp targets", () => {
const cfg: ClawdisConfig = {
agent: { heartbeat: { target: "whatsapp", to: "+1999" } },
routing: { allowFrom: ["+1555", "+1666"] },
whatsapp: { allowFrom: ["+1555", "+1666"] },
};
const entry = {
...baseEntry,
@ -145,7 +145,7 @@ describe("runHeartbeatOnce", () => {
agent: {
heartbeat: { every: "5m", target: "whatsapp", to: "+1555" },
},
routing: { allowFrom: ["*"] },
whatsapp: { allowFrom: ["*"] },
session: { store: storePath },
};
@ -206,7 +206,7 @@ describe("runHeartbeatOnce", () => {
agent: {
heartbeat: { every: "5m", target: "whatsapp", to: "+1555" },
},
routing: { allowFrom: ["*"] },
whatsapp: { allowFrom: ["*"] },
session: { store: storePath },
};

View File

@ -235,7 +235,7 @@ export function resolveHeartbeatDeliveryTarget(params: {
return { channel, to };
}
const rawAllow = cfg.routing?.allowFrom ?? [];
const rawAllow = cfg.whatsapp?.allowFrom ?? [];
if (rawAllow.includes("*")) return { channel, to };
const allowFrom = rawAllow
.map((val) => normalizeE164(val))
@ -401,7 +401,7 @@ export async function runHeartbeatOnce(opts: {
const startedAt = opts.deps?.nowMs?.() ?? Date.now();
const { entry, sessionKey, storePath } = resolveHeartbeatSession(cfg);
const previousUpdatedAt = entry?.updatedAt;
const allowFrom = cfg.routing?.allowFrom ?? [];
const allowFrom = cfg.whatsapp?.allowFrom ?? [];
const sender = resolveHeartbeatSender({
allowFrom,
lastTo: entry?.lastTo,

View File

@ -80,8 +80,8 @@ export async function buildProviderSummary(
);
}
const allowFrom = effective.routing?.allowFrom?.length
? effective.routing.allowFrom.map(normalizeE164).filter(Boolean)
const allowFrom = effective.whatsapp?.allowFrom?.length
? effective.whatsapp.allowFrom.map(normalizeE164).filter(Boolean)
: [];
if (allowFrom.length) {
lines.push(chalk.cyan(`AllowFrom: ${allowFrom.join(", ")}`));

View File

@ -1,7 +1,7 @@
import JSZip from "jszip";
import { describe, expect, it } from "vitest";
import { detectMime } from "./mime.js";
import { detectMime, imageMimeFromFormat } from "./mime.js";
async function makeOoxmlZip(opts: {
mainMime: string;
@ -17,6 +17,15 @@ async function makeOoxmlZip(opts: {
}
describe("mime detection", () => {
it("maps common image formats to mime types", () => {
expect(imageMimeFromFormat("jpg")).toBe("image/jpeg");
expect(imageMimeFromFormat("jpeg")).toBe("image/jpeg");
expect(imageMimeFromFormat("png")).toBe("image/png");
expect(imageMimeFromFormat("webp")).toBe("image/webp");
expect(imageMimeFromFormat("gif")).toBe("image/gif");
expect(imageMimeFromFormat("unknown")).toBeUndefined();
});
it("detects docx from buffer", async () => {
const buf = await makeOoxmlZip({
mainMime:

View File

@ -107,6 +107,25 @@ export function extensionForMime(mime?: string | null): string | undefined {
return EXT_BY_MIME[mime.toLowerCase()];
}
export function imageMimeFromFormat(
format?: string | null,
): string | undefined {
if (!format) return undefined;
switch (format.toLowerCase()) {
case "jpg":
case "jpeg":
return "image/jpeg";
case "png":
return "image/png";
case "webp":
return "image/webp";
case "gif":
return "image/gif";
default:
return undefined;
}
}
export function kindFromMime(mime?: string | null): MediaKind {
return mediaKindFromMime(mime);
}

View File

@ -92,8 +92,7 @@ function resolveAccount(opts: MonitorSignalOpts): string | undefined {
function resolveAllowFrom(opts: MonitorSignalOpts): string[] {
const cfg = loadConfig();
const raw =
opts.allowFrom ?? cfg.signal?.allowFrom ?? cfg.routing?.allowFrom ?? [];
const raw = opts.allowFrom ?? cfg.signal?.allowFrom ?? [];
return raw.map((entry) => String(entry).trim()).filter(Boolean);
}

View File

@ -33,7 +33,7 @@ export function normalizeE164(number: string): string {
/**
* "Self-chat mode" heuristic (single phone): the gateway is logged in as the owner's own WhatsApp account,
* and `routing.allowFrom` includes that same number. Used to avoid side-effects that make no sense when the
* and `whatsapp.allowFrom` includes that same number. Used to avoid side-effects that make no sense when the
* "bot" and the human are the same WhatsApp identity (e.g. auto read receipts, @mention JID triggers).
*/
export function isSelfChatMode(

View File

@ -111,7 +111,7 @@ describe("partial reply gating", () => {
const replyResolver = vi.fn().mockResolvedValue({ text: "final reply" });
const mockConfig: ClawdisConfig = {
routing: {
whatsapp: {
allowFrom: ["*"],
},
};
@ -158,7 +158,7 @@ describe("partial reply gating", () => {
const replyResolver = vi.fn().mockResolvedValue(undefined);
const mockConfig: ClawdisConfig = {
routing: {
whatsapp: {
allowFrom: ["*"],
},
session: { store: store.storePath, mainKey: "main" },
@ -1097,9 +1097,11 @@ describe("web auto-reply", () => {
const resolver = vi.fn().mockResolvedValue({ text: "ok" });
setLoadConfigMock(() => ({
routing: {
whatsapp: {
// Self-chat heuristic: allowFrom includes selfE164.
allowFrom: ["+999"],
},
routing: {
groupChat: {
requireMention: true,
mentionPatterns: ["\\bclawd\\b"],
@ -1247,7 +1249,7 @@ describe("web auto-reply", () => {
it("prefixes body with same-phone marker when from === to", async () => {
// Enable messagePrefix for same-phone mode testing
setLoadConfigMock(() => ({
routing: {
whatsapp: {
allowFrom: ["*"],
},
messages: {
@ -1372,7 +1374,7 @@ describe("web auto-reply", () => {
it("applies responsePrefix to regular replies", async () => {
setLoadConfigMock(() => ({
routing: {
whatsapp: {
allowFrom: ["*"],
},
messages: {
@ -1417,7 +1419,7 @@ describe("web auto-reply", () => {
it("does not deliver HEARTBEAT_OK responses", async () => {
setLoadConfigMock(() => ({
routing: {
whatsapp: {
allowFrom: ["*"],
},
messages: {
@ -1462,7 +1464,7 @@ describe("web auto-reply", () => {
it("does not double-prefix if responsePrefix already present", async () => {
setLoadConfigMock(() => ({
routing: {
whatsapp: {
allowFrom: ["*"],
},
messages: {
@ -1508,7 +1510,7 @@ describe("web auto-reply", () => {
it("sends tool summaries immediately with responsePrefix", async () => {
setLoadConfigMock(() => ({
routing: {
whatsapp: {
allowFrom: ["*"],
},
messages: {

View File

@ -116,7 +116,7 @@ function buildMentionConfig(cfg: ReturnType<typeof loadConfig>): MentionConfig {
}
})
.filter((r): r is RegExp => Boolean(r)) ?? [];
return { mentionRegexes, allowFrom: cfg.routing?.allowFrom };
return { mentionRegexes, allowFrom: cfg.whatsapp?.allowFrom };
}
function isBotMentioned(
@ -448,8 +448,8 @@ export function resolveHeartbeatRecipients(
const sessionRecipients = getSessionRecipients(cfg);
const allowFrom =
Array.isArray(cfg.routing?.allowFrom) && cfg.routing.allowFrom.length > 0
? cfg.routing.allowFrom.filter((v) => v !== "*").map(normalizeE164)
Array.isArray(cfg.whatsapp?.allowFrom) && cfg.whatsapp.allowFrom.length > 0
? cfg.whatsapp.allowFrom.filter((v) => v !== "*").map(normalizeE164)
: [];
const unique = (list: string[]) => [...new Set(list.filter(Boolean))];
@ -918,7 +918,7 @@ export async function monitorWebProvider(
// Build message prefix: explicit config > default based on allowFrom
let messagePrefix = cfg.messages?.messagePrefix;
if (messagePrefix === undefined) {
const hasAllowFrom = (cfg.routing?.allowFrom?.length ?? 0) > 0;
const hasAllowFrom = (cfg.whatsapp?.allowFrom?.length ?? 0) > 0;
messagePrefix = hasAllowFrom ? "" : "[clawdis]";
}
const prefixStr = messagePrefix ? `${messagePrefix} ` : "";

View File

@ -7,7 +7,7 @@ import { afterAll, beforeAll, describe, expect, it, vi } from "vitest";
vi.mock("../config/config.js", () => ({
loadConfig: vi.fn().mockReturnValue({
routing: {
whatsapp: {
allowFrom: ["*"], // Allow all in tests
},
messages: {

View File

@ -157,7 +157,7 @@ export async function monitorWebInbox(options: {
// Filter unauthorized senders early to prevent wasted processing
// and potential session corruption from Bad MAC errors
const cfg = loadConfig();
const configuredAllowFrom = cfg.routing?.allowFrom;
const configuredAllowFrom = cfg.whatsapp?.allowFrom;
// Without user config, default to self-only DM access so the owner can talk to themselves
const defaultAllowFrom =
(!configuredAllowFrom || configuredAllowFrom.length === 0) && selfE164

View File

@ -10,7 +10,7 @@ vi.mock("../media/store.js", () => ({
}));
const mockLoadConfig = vi.fn().mockReturnValue({
routing: {
whatsapp: {
allowFrom: ["*"], // Allow all in tests by default
},
messages: {
@ -450,7 +450,7 @@ describe("web monitor inbox", () => {
it("still forwards group messages (with sender info) even when allowFrom is restrictive", async () => {
mockLoadConfig.mockReturnValue({
routing: {
whatsapp: {
allowFrom: ["+111"], // does not include +777
},
messages: {
@ -506,7 +506,7 @@ describe("web monitor inbox", () => {
// Test for auto-recovery fix: early allowFrom filtering prevents Bad MAC errors
// from unauthorized senders corrupting sessions
mockLoadConfig.mockReturnValue({
routing: {
whatsapp: {
allowFrom: ["+111"], // Only allow +111
},
messages: {
@ -546,7 +546,7 @@ describe("web monitor inbox", () => {
// Reset mock for other tests
mockLoadConfig.mockReturnValue({
routing: {
whatsapp: {
allowFrom: ["*"],
},
messages: {
@ -561,7 +561,7 @@ describe("web monitor inbox", () => {
it("skips read receipts in self-chat mode", async () => {
mockLoadConfig.mockReturnValue({
routing: {
whatsapp: {
// Self-chat heuristic: allowFrom includes selfE164 (+123).
allowFrom: ["+123"],
},
@ -598,7 +598,7 @@ describe("web monitor inbox", () => {
// Reset mock for other tests
mockLoadConfig.mockReturnValue({
routing: {
whatsapp: {
allowFrom: ["*"],
},
messages: {
@ -613,7 +613,7 @@ describe("web monitor inbox", () => {
it("lets group messages through even when sender not in allowFrom", async () => {
mockLoadConfig.mockReturnValue({
routing: {
whatsapp: {
allowFrom: ["+1234"],
},
messages: {
@ -655,7 +655,7 @@ describe("web monitor inbox", () => {
it("allows messages from senders in allowFrom list", async () => {
mockLoadConfig.mockReturnValue({
routing: {
whatsapp: {
allowFrom: ["+111", "+999"], // Allow +999
},
messages: {
@ -690,7 +690,7 @@ describe("web monitor inbox", () => {
// Reset mock for other tests
mockLoadConfig.mockReturnValue({
routing: {
whatsapp: {
allowFrom: ["*"],
},
messages: {
@ -707,7 +707,7 @@ describe("web monitor inbox", () => {
// Same-phone mode: when from === selfJid, should always be allowed
// This allows users to message themselves even with restrictive allowFrom
mockLoadConfig.mockReturnValue({
routing: {
whatsapp: {
allowFrom: ["+111"], // Only allow +111, but self is +123
},
messages: {
@ -810,7 +810,7 @@ it("defaults to self-only when no config is present", async () => {
// Reset mock for other tests
mockLoadConfig.mockReturnValue({
routing: {
whatsapp: {
allowFrom: ["*"],
},
messages: {

View File

@ -6,7 +6,7 @@ import { createMockBaileys } from "../../test/mocks/baileys.js";
// Use globalThis to store the mock config so it survives vi.mock hoisting
const CONFIG_KEY = Symbol.for("clawdis:testConfigMock");
const DEFAULT_CONFIG = {
routing: {
whatsapp: {
// Tests can override; default remains open to avoid surprising fixtures
allowFrom: ["*"],
},

View File

@ -186,6 +186,7 @@ export class ClawdisApp extends LitElement {
this.syncThemeWithSettings();
this.attachThemeListener();
window.addEventListener("popstate", this.popStateHandler);
this.applySettingsFromUrl();
this.connect();
this.startNodesPolling();
}
@ -334,6 +335,20 @@ export class ClawdisApp extends LitElement {
}
}
private applySettingsFromUrl() {
if (!window.location.search) return;
const params = new URLSearchParams(window.location.search);
const token = params.get("token")?.trim();
if (!token) return;
if (!this.settings.token) {
this.applySettings({ ...this.settings, token });
}
params.delete("token");
const url = new URL(window.location.href);
url.search = params.toString();
window.history.replaceState({}, "", url.toString());
}
setTab(next: Tab) {
if (this.tab !== next) this.tab = next;
void this.refreshActiveTab();

View File

@ -90,4 +90,13 @@ describe("control UI routing", () => {
expect(maxScroll).toBeGreaterThan(0);
expect(container.scrollTop).toBe(maxScroll);
});
it("hydrates token from URL params and strips it", async () => {
const app = mountApp("/ui/overview?token=abc123");
await app.updateComplete;
expect(app.settings.token).toBe("abc123");
expect(window.location.pathname).toBe("/ui/overview");
expect(window.location.search).toBe("");
});
});