Compare commits

..
177 changed files with 1349 additions and 4763 deletions

No files matched your search

-2
View File
@@ -55,5 +55,3 @@ apps/ios/*.mobileprovision
# Local untracked files
.local/
.vscode/
IDENTITY.md
USER.md
-8
View File
@@ -116,14 +116,6 @@
- launchd PATH is minimal; ensure the app’s launch agent PATH includes standard system paths plus your pnpm bin (typically `$HOME/Library/pnpm`) so `pnpm`/`clawdbot` binaries resolve when invoked via `clawdbot-mac`.
- For manual `clawdbot message send` messages that include `!`, use the heredoc pattern noted below to avoid the Bash tool’s escaping.
## NPM + 1Password (publish/verify)
- Use the 1password skill; all `op` commands must run inside a fresh tmux session.
- Sign in: `eval "$(op signin --account my.1password.com)"` (app unlocked + integration on).
- OTP: `op read 'op://Private/Npmjs/one-time password?attribute=otp'`.
- Publish: `npm publish --access public --otp="<otp>"` (run from the package dir).
- Verify without local npmrc side effects: `npm view <pkg> version --userconfig "$(mktemp)"`.
- Kill the tmux session after publish.
## Exclamation Mark Escaping Workaround
The Claude Code Bash tool escapes `!` to `\\!` in command arguments. When using `clawdbot message send` with messages containing exclamation marks, use heredoc syntax:
+12 -42
View File
@@ -2,71 +2,42 @@
## 2026.1.15 (unreleased)
### Highlights
- Plugins: add provider auth registry + `clawdbot models auth login` for plugin-driven OAuth/API key flows.
- Browser: improve remote CDP/Browserless support (auth passthrough, `wss` upgrade, timeouts, clearer errors).
- Heartbeat: per-agent configuration + 24h duplicate suppression. (#980) — thanks @voidserf.
- Security: audit warns on weak model tiers; app nodes store auth tokens encrypted (Keychain/SecurePrefs).
### Breaking
- **BREAKING:** iOS minimum version is now 18.0 to support Textual markdown rendering in native chat. (#702)
- **BREAKING:** Microsoft Teams is now a plugin; install `@clawdbot/msteams` via `clawdbot plugins install @clawdbot/msteams`.
### Changes
- CLI: set process titles to `clawdbot-<command>` for clearer process listings.
- CLI/macOS: sync remote SSH target/identity to config and let `gateway status` auto-infer SSH targets (ssh-config aware).
- Heartbeat: tighten prompt guidance + suppress duplicate alerts for 24h. (#980) — thanks @voidserf.
- Repo: ignore local identity files to avoid accidental commits. (#1001) — thanks @gerardward2007.
- Sessions/Security: add `session.dmScope` for multi-user DM isolation and audit warnings. (#948) — thanks @Alphonse-arianee.
- Plugins: add provider auth registry + `clawdbot models auth login` for plugin-driven OAuth/API key flows.
- Onboarding: switch channels setup to a single-select loop with per-channel actions and disabled hints in the picker.
- TUI: show provider/model labels for the active session and default model.
- Heartbeat: add per-agent heartbeat configuration and multi-agent docs example.
- UI: show gateway auth guidance + doc link on unauthorized Control UI connections.
- Security: warn on weak model tiers (Haiku, below GPT-5, below Claude 4.5) in `clawdbot security audit`.
- Apps: store node auth tokens encrypted (Keychain/SecurePrefs).
- Fix: list model picker entries as provider/model pairs for explicit selection. (#970) — thanks @mcinteerj.
- Fix: persist `gateway.mode=local` after selecting Local run mode in `clawdbot configure`, even if no other sections are chosen.
- Daemon: fix profile-aware service label resolution (env-driven) and add coverage for launchd/systemd/schtasks. (#969) — thanks @bjesuiter.
- Daemon: share profile/state-dir resolution across service helpers and honor `CLAWDBOT_STATE_DIR` for Windows task scripts.
- Docs: clarify multi-gateway rescue bot guidance. (#969) — thanks @bjesuiter.
- Agents: add Current Date & Time system prompt section with configurable time format (auto/12/24).
- Agents: avoid false positives when logging unsupported Google tool schema keywords.
- Agents: include recent context in reminder cron payloads. (#993) — thanks @cpojer.
- Status: restore usage summary line for current provider when no OAuth profiles exist.
- Tools: normalize Slack/Discord message timestamps with `timestampMs`/`timestampUtc` while keeping raw provider fields.
- macOS: add `system.which` for prompt-free remote skill discovery (with gateway fallback to `system.run`).
- Docs: add Date & Time guide and update prompt/timezone configuration docs.
- Messages: debounce rapid inbound messages across channels with per-connector overrides. (#971) — thanks @juanpablodlc.
- Messages: allow media-only sends (CLI/tool) and show Telegram voice recording status for voice notes. (#957) — thanks @rdev.
- Auth/Status: keep auth profiles sticky per session (rotate on compaction/new), surface provider usage headers in `/status` and `clawdbot models status`, and update docs.
- CLI: add `--json` output for `clawdbot daemon` lifecycle/install commands.
- Memory: make `node-llama-cpp` an optional dependency (avoid Node 25 install failures) and improve local-embeddings fallback/errors.
- Browser: add `snapshot refs=aria` (Playwright aria-ref ids) for self-resolving refs across `snapshot` → `act`.
- Browser: `profile="chrome"` now defaults to host control and returns clearer “attach a tab” errors.
- Browser: prefer stable Chrome for auto-detect, with Brave/Edge fallbacks and updated docs. (#983) — thanks @cpojer.
- Browser: increase remote CDP reachability timeouts + add `remoteCdpTimeoutMs`/`remoteCdpHandshakeTimeoutMs`.
- Browser: preserve auth/query tokens for remote CDP endpoints and pass Basic auth for CDP HTTP/WS. (#895) — thanks @mukhtharcm.
- Telegram: add bidirectional reaction support with configurable notifications and agent guidance. (#964) — thanks @bohdanpodvirnyi.
- Telegram: allow custom commands in the bot menu (merged with native; conflicts ignored). (#860) — thanks @nachoiacovino.
- Discord: allow allowlisted guilds without channel lists to receive messages when `groupPolicy="allowlist"`. — thanks @thewilloftheshadow.
- Discord: allow emoji/sticker uploads + channel actions in config defaults. (#870) — thanks @JDIVE.
### Fixes
- Fix: list model picker entries as provider/model pairs for explicit selection. (#970) — thanks @mcinteerj.
- Fix: align OpenAI image-gen defaults with DALL-E 3 standard quality and document output formats. (#880) — thanks @mkbehr.
- Fix: persist `gateway.mode=local` after selecting Local run mode in `clawdbot configure`, even if no other sections are chosen.
- Daemon: fix profile-aware service label resolution (env-driven) and add coverage for launchd/systemd/schtasks. (#969) — thanks @bjesuiter.
- Agents: avoid false positives when logging unsupported Google tool schema keywords.
- Agents: skip Gemini history downgrades for google-antigravity to preserve tool calls. (#894) — thanks @mukhtharcm.
- Status: restore usage summary line for current provider when no OAuth profiles exist.
- Fix: guard model fallback against undefined provider/model values. (#954) — thanks @roshanasingh4.
- Fix: refactor session store updates, add chat.inject, and harden subagent cleanup flow. (#944) — thanks @tyler6204.
- Fix: clean up suspended CLI processes across backends. (#978) — thanks @Nachx639.
- Fix: support MiniMax coding plan usage responses with `model_remains`/`current_interval_*` payloads.
- Fix: suppress WhatsApp pairing replies for historical catch-up DMs on initial link. (#904)
- Memory: make `node-llama-cpp` an optional dependency (avoid Node 25 install failures) and improve local-embeddings fallback/errors.
- Browser: add `snapshot refs=aria` (Playwright aria-ref ids) for self-resolving refs across `snapshot` → `act`.
- Browser: `profile="chrome"` now defaults to host control and returns clearer “attach a tab” errors.
- Browser: extension mode recovers when only one tab is attached (stale targetId fallback).
- Browser: prefer stable Chrome for auto-detect, with Brave/Edge fallbacks and updated docs. (#983) — thanks @cpojer.
- Browser: fix `tab not found` for extension relay snapshots/actions when Playwright blocks `newCDPSession` (use the single available Page).
- Browser: upgrade `ws` → `wss` when remote CDP uses `https` (fixes Browserless handshake).
- Telegram: add bidirectional reaction support with configurable notifications and agent guidance. (#964) — thanks @bohdanpodvirnyi.
- Telegram: skip `message_thread_id=1` for General topic sends while keeping typing indicators. (#848) — thanks @azade-c.
- Discord: allow allowlisted guilds without channel lists to receive messages when `groupPolicy="allowlist"`. — thanks @thewilloftheshadow.
- Fix: sanitize user-facing error text + strip `<final>` tags across reply pipelines. (#975) — thanks @ThomsenDrake.
- Fix: normalize pairing CLI aliases, allow extension channels, and harden Zalo webhook payload parsing. (#991) — thanks @longmaba.
- Fix: allow local Tailscale Serve hostnames without treating tailnet clients as direct. (#885) — thanks @oswalpalash.
- Fix: reset sessions after role-ordering conflicts to recover from consecutive user turns. (#998)
## 2026.1.14-1
@@ -168,7 +139,6 @@
### Fixes
- Packaging: include `dist/memory/**` in the npm tarball (fixes `ERR_MODULE_NOT_FOUND` for `dist/memory/index.js`).
- Agents: persist sub-agent registry across gateway restarts and resume announce flow safely. (#831) — thanks @roshanasingh4.
- Agents: strip invalid Gemini thought signatures from OpenRouter history to avoid 400s. (#841, #845) — thanks @MatthieuBizien.
## 2026.1.12-1
+1 -1
View File
@@ -119,7 +119,7 @@ dependencies {
testImplementation("io.kotest:kotest-runner-junit5-jvm:6.0.7")
testImplementation("io.kotest:kotest-assertions-core-jvm:6.0.7")
testImplementation("org.robolectric:robolectric:4.16")
testRuntimeOnly("org.junit.vintage:junit-vintage-engine:6.0.2")
testRuntimeOnly("org.junit.vintage:junit-vintage-engine:6.0.1")
}
tasks.withType<Test>().configureEach {
@@ -212,7 +212,7 @@ class BridgeSession(
connectWithSocket(endpoint, hello, null)
}
private suspend fun connectWithSocket(endpoint: BridgeEndpoint, hello: Hello, tls: BridgeTlsParams?) {
private fun connectWithSocket(endpoint: BridgeEndpoint, hello: Hello, tls: BridgeTlsParams?) {
val socket =
createBridgeSocket(tls) { fingerprint ->
onTlsFingerprint?.invoke(tls?.stableId ?: endpoint.stableId, fingerprint)
@@ -260,15 +260,15 @@ class BridgeSession(
else -> throw IllegalStateException("unexpected bridge response")
}
while (scope.isActive) {
val line = reader.readLine() ?: break
val frame = json.parseToJsonElement(line).asObjectOrNull() ?: continue
when (frame["type"].asStringOrNull()) {
"event" -> {
val event = frame["event"].asStringOrNull() ?: continue
val payload = frame["payloadJSON"].asStringOrNull()
onEvent(event, payload)
}
while (scope.isActive) {
val line = reader.readLine() ?: break
val frame = json.parseToJsonElement(line).asObjectOrNull() ?: continue
when (frame["type"].asStringOrNull()) {
"event" -> {
val event = frame["event"].asStringOrNull() ?: return@withContext
val payload = frame["payloadJSON"].asStringOrNull()
onEvent(event, payload)
}
"ping" -> {
val id = frame["id"].asStringOrNull() ?: ""
conn.sendJson(buildJsonObject { put("type", JsonPrimitive("pong")); put("id", JsonPrimitive(id)) })
@@ -314,20 +314,20 @@ class BridgeSession(
},
)
}
"invoke-res" -> {
// gateway->node only (ignore)
"invoke-res" -> {
// gateway->node only (ignore)
}
}
}
} finally {
currentConnection = null
for ((_, waiter) in pending) {
waiter.cancel()
}
pending.clear()
conn.closeQuietly()
}
} finally {
currentConnection = null
for ((_, waiter) in pending) {
waiter.cancel()
}
pending.clear()
conn.closeQuietly()
}
}
private fun buildHelloJson(hello: Hello): JsonObject =
buildJsonObject {
@@ -1,6 +1,5 @@
package com.clawdbot.android.bridge
import android.annotation.SuppressLint
import java.net.Socket
import java.security.MessageDigest
import java.security.SecureRandom
@@ -22,7 +21,6 @@ fun createBridgeSocket(params: BridgeTlsParams?, onStore: ((String) -> Unit)? =
if (params == null) return Socket()
val expected = params.expectedFingerprint?.let(::normalizeFingerprint)
val defaultTrust = defaultTrustManager()
@SuppressLint("CustomX509TrustManager")
val trustManager =
object : X509TrustManager {
override fun checkClientTrusted(chain: Array<X509Certificate>, authType: String) {
+6 -5
View File
@@ -32,10 +32,11 @@ func makeBridgeTLSOptions(_ params: BridgeTLSParams?) -> NWProtocolTLS.Options?
sec_protocol_options_set_verify_block(
options.securityProtocolOptions,
{ _, trust, complete in
let trustRef = sec_trust_copy_ref(trust).takeRetainedValue()
if let chain = SecTrustCopyCertificateChain(trustRef) as? [SecCertificate],
let cert = chain.first
{
guard let trust else {
complete(false)
return
}
if let cert = SecTrustGetCertificateAtIndex(trust, 0) {
let data = SecCertificateCopyData(cert) as Data
let fingerprint = sha256Hex(data)
if let expected {
@@ -48,7 +49,7 @@ func makeBridgeTLSOptions(_ params: BridgeTLSParams?) -> NWProtocolTLS.Options?
return
}
}
let ok = SecTrustEvaluateWithError(trustRef, nil)
let ok = SecTrustEvaluateWithError(trust, nil)
complete(ok)
},
DispatchQueue(label: "com.clawdbot.bridge.tls.verify"))
+9 -20
View File
@@ -190,7 +190,14 @@ actor CameraController {
}
func listDevices() -> [CameraDeviceInfo] {
return Self.discoverVideoDevices().map { device in
let types: [AVCaptureDevice.DeviceType] = [
.builtInWideAngleCamera,
]
let session = AVCaptureDevice.DiscoverySession(
deviceTypes: types,
mediaType: .video,
position: .unspecified)
return session.devices.map { device in
CameraDeviceInfo(
id: device.uniqueID,
name: device.localizedName,
@@ -225,7 +232,7 @@ actor CameraController {
deviceId: String?) -> AVCaptureDevice?
{
if let deviceId, !deviceId.isEmpty {
if let match = Self.discoverVideoDevices().first(where: { $0.uniqueID == deviceId }) {
if let match = AVCaptureDevice.devices(for: .video).first(where: { $0.uniqueID == deviceId }) {
return match
}
}
@@ -245,24 +252,6 @@ actor CameraController {
}
}
private nonisolated static func discoverVideoDevices() -> [AVCaptureDevice] {
let types: [AVCaptureDevice.DeviceType] = [
.builtInWideAngleCamera,
.builtInUltraWideCamera,
.builtInTelephotoCamera,
.builtInDualCamera,
.builtInDualWideCamera,
.builtInTripleCamera,
.builtInTrueDepthCamera,
.builtInLiDARDepthCamera,
]
let session = AVCaptureDevice.DiscoverySession(
deviceTypes: types,
mediaType: .video,
position: .unspecified)
return session.devices
}
nonisolated static func clampQuality(_ quality: Double?) -> Double {
let q = quality ?? 0.9
return min(1.0, max(0.05, q))
@@ -137,11 +137,9 @@ final class ScreenRecordService: @unchecked Sendable {
recordQueue: DispatchQueue) -> @Sendable (CMSampleBuffer, RPSampleBufferType, Error?) -> Void
{
{ sample, type, error in
let sampleBox = UncheckedSendableBox(value: sample)
// ReplayKit can call the capture handler on a background queue.
// Serialize writes to avoid queue asserts.
recordQueue.async {
let sample = sampleBox.value
if let error {
state.withLock { state in
if state.handlerError == nil { state.handlerError = error }
+1 -2
View File
@@ -26,8 +26,7 @@ Sources/Voice/VoiceTab.swift
Sources/Voice/VoiceWakeManager.swift
Sources/Voice/VoiceWakePreferences.swift
../shared/ClawdbotKit/Sources/ClawdbotChatUI/ChatComposer.swift
../shared/ClawdbotKit/Sources/ClawdbotChatUI/ChatMarkdownRenderer.swift
../shared/ClawdbotKit/Sources/ClawdbotChatUI/ChatMarkdownPreprocessor.swift
../shared/ClawdbotKit/Sources/ClawdbotChatUI/ChatMarkdownSplitter.swift
../shared/ClawdbotKit/Sources/ClawdbotChatUI/ChatMessageViews.swift
../shared/ClawdbotKit/Sources/ClawdbotChatUI/ChatModels.swift
../shared/ClawdbotKit/Sources/ClawdbotChatUI/ChatPayloadDecoding.swift
+1 -1
View File
@@ -2,7 +2,7 @@ name: Clawdbot
options:
bundleIdPrefix: com.clawdbot
deploymentTarget:
iOS: "18.0"
iOS: "17.0"
xcodeVersion: "16.0"
settings:
+1 -28
View File
@@ -1,5 +1,5 @@
{
"originHash" : "7eec77e2b399c480e76fdfc7dc3162652f5c775530e9fc282953de38ef2de79b",
"originHash" : "9de32b5fc115432dadd84c3ab4d67d2fed22ffaf5675a77033d69ea194ac3862",
"pins" : [
{
"identity" : "elevenlabskit",
@@ -73,15 +73,6 @@
"revision" : "8e5e4a8f3617283b556064574651fc0869943c9a"
}
},
{
"identity" : "swift-concurrency-extras",
"kind" : "remoteSourceControl",
"location" : "https://github.com/pointfreeco/swift-concurrency-extras",
"state" : {
"revision" : "5a3825302b1a0d744183200915a47b508c828e6f",
"version" : "1.3.2"
}
},
{
"identity" : "swift-configuration",
"kind" : "remoteSourceControl",
@@ -153,24 +144,6 @@
"revision" : "395a77f0aa927f0ff73941d7ac35f2b46d47c9db",
"version" : "1.6.3"
}
},
{
"identity" : "swiftui-math",
"kind" : "remoteSourceControl",
"location" : "https://github.com/gonzalezreal/swiftui-math",
"state" : {
"revision" : "0b5c2cfaaec8d6193db206f675048eeb5ce95f71",
"version" : "0.1.0"
}
},
{
"identity" : "textual",
"kind" : "remoteSourceControl",
"location" : "https://github.com/gonzalezreal/textual",
"state" : {
"revision" : "a03c1e103d88de4ea0dd8320ea1611ec0d4b29b3",
"version" : "0.2.0"
}
}
],
"version" : 3
+8 -49
View File
@@ -341,15 +341,6 @@ final class AppState {
return host
}
private static func sanitizeSSHTarget(_ value: String) -> String {
let trimmed = value.trimmingCharacters(in: .whitespacesAndNewlines)
if trimmed.hasPrefix("ssh ") {
return trimmed.replacingOccurrences(of: "ssh ", with: "")
.trimmingCharacters(in: .whitespacesAndNewlines)
}
return trimmed
}
private func startConfigWatcher() {
let configUrl = ClawdbotConfigFile.url()
self.configWatcher = ConfigFileWatcher(url: configUrl) { [weak self] in
@@ -415,7 +406,6 @@ final class AppState {
let connectionMode = self.connectionMode
let remoteTarget = self.remoteTarget
let remoteIdentity = self.remoteIdentity
let desiredMode: String? = switch connectionMode {
case .local:
"local"
@@ -445,46 +435,15 @@ final class AppState {
changed = true
}
if connectionMode == .remote {
if connectionMode == .remote, let host = remoteHost {
var remote = gateway["remote"] as? [String: Any] ?? [:]
var remoteChanged = false
if let host = remoteHost {
let existingUrl = (remote["url"] as? String)?
.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
let parsedExisting = existingUrl.isEmpty ? nil : URL(string: existingUrl)
let scheme = parsedExisting?.scheme?.isEmpty == false ? parsedExisting?.scheme : "ws"
let port = parsedExisting?.port ?? 18789
let desiredUrl = "\(scheme ?? "ws")://\(host):\(port)"
if existingUrl != desiredUrl {
remote["url"] = desiredUrl
remoteChanged = true
}
}
let sanitizedTarget = Self.sanitizeSSHTarget(remoteTarget)
if !sanitizedTarget.isEmpty {
if (remote["sshTarget"] as? String) != sanitizedTarget {
remote["sshTarget"] = sanitizedTarget
remoteChanged = true
}
} else if remote["sshTarget"] != nil {
remote.removeValue(forKey: "sshTarget")
remoteChanged = true
}
let trimmedIdentity = remoteIdentity.trimmingCharacters(in: .whitespacesAndNewlines)
if !trimmedIdentity.isEmpty {
if (remote["sshIdentity"] as? String) != trimmedIdentity {
remote["sshIdentity"] = trimmedIdentity
remoteChanged = true
}
} else if remote["sshIdentity"] != nil {
remote.removeValue(forKey: "sshIdentity")
remoteChanged = true
}
if remoteChanged {
let existingUrl = (remote["url"] as? String)?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
let parsedExisting = existingUrl.isEmpty ? nil : URL(string: existingUrl)
let scheme = parsedExisting?.scheme?.isEmpty == false ? parsedExisting?.scheme : "ws"
let port = parsedExisting?.port ?? 18789
let desiredUrl = "\(scheme ?? "ws")://\(host):\(port)"
if existingUrl != desiredUrl {
remote["url"] = desiredUrl
gateway["remote"] = remote
changed = true
}
@@ -188,15 +188,9 @@ extension CronJobEditor {
}
}
func applyDeleteAfterRun(
to root: inout [String: Any],
scheduleKind: ScheduleKind? = nil,
deleteAfterRun: Bool? = nil)
{
let resolvedSchedule = scheduleKind ?? self.scheduleKind
let resolvedDelete = deleteAfterRun ?? self.deleteAfterRun
if resolvedSchedule == .at {
root["deleteAfterRun"] = resolvedDelete
func applyDeleteAfterRun(to root: inout [String: Any]) {
if self.scheduleKind == .at {
root["deleteAfterRun"] = self.deleteAfterRun
} else if self.job?.deleteAfterRun != nil {
root["deleteAfterRun"] = false
}
@@ -2,16 +2,77 @@ import Foundation
enum GatewayLaunchAgentManager {
private static let logger = Logger(subsystem: "com.clawdbot", category: "gateway.launchd")
private static let supportedBindModes: Set<String> = ["loopback", "tailnet", "lan", "auto"]
private static let legacyGatewayLaunchdLabel = "com.steipete.clawdbot.gateway"
private static let disableLaunchAgentMarker = ".clawdbot/disable-launchagent"
private enum GatewayProgramArgumentsError: LocalizedError {
case message(String)
var errorDescription: String? {
switch self {
case let .message(message):
message
}
}
}
private static var plistURL: URL {
FileManager.default.homeDirectoryForCurrentUser
.appendingPathComponent("Library/LaunchAgents/\(gatewayLaunchdLabel).plist")
}
private static var legacyPlistURL: URL {
FileManager.default.homeDirectoryForCurrentUser
.appendingPathComponent("Library/LaunchAgents/\(legacyGatewayLaunchdLabel).plist")
}
private static func gatewayProgramArguments(
port: Int,
bind: String) -> Result<[String], GatewayProgramArgumentsError>
{
let projectRoot = CommandResolver.projectRoot()
#if DEBUG
if let localBin = CommandResolver.projectClawdbotExecutable(projectRoot: projectRoot) {
return .success([localBin, "gateway-daemon", "--port", "\(port)", "--bind", bind])
}
if let entry = CommandResolver.gatewayEntrypoint(in: projectRoot) {
switch CommandResolver.runtimeResolution() {
case let .success(runtime):
let cmd = CommandResolver.makeRuntimeCommand(
runtime: runtime,
entrypoint: entry,
subcommand: "gateway-daemon",
extraArgs: ["--port", "\(port)", "--bind", bind])
return .success(cmd)
case .failure:
break
}
}
#endif
let searchPaths = CommandResolver.preferredPaths()
if let gatewayBin = CommandResolver.clawdbotExecutable(searchPaths: searchPaths) {
return .success([gatewayBin, "gateway-daemon", "--port", "\(port)", "--bind", bind])
}
if let entry = CommandResolver.gatewayEntrypoint(in: projectRoot),
case let .success(runtime) = CommandResolver.runtimeResolution(searchPaths: searchPaths)
{
let cmd = CommandResolver.makeRuntimeCommand(
runtime: runtime,
entrypoint: entry,
subcommand: "gateway-daemon",
extraArgs: ["--port", "\(port)", "--bind", bind])
return .success(cmd)
}
return .failure(.message("clawdbot CLI not found in PATH; install the CLI."))
}
static func isLoaded() async -> Bool {
guard let loaded = await self.readDaemonLoaded() else { return false }
return loaded
guard FileManager.default.fileExists(atPath: self.plistURL.path) else { return false }
let result = await Launchctl.run(["print", "gui/\(getuid())/\(gatewayLaunchdLabel)"])
return result.status == 0
}
static func set(enabled: Bool, bundlePath: String, port: Int) async -> String? {
@@ -20,44 +81,255 @@ enum GatewayLaunchAgentManager {
self.logger.info("launchd enable skipped (disable marker set)")
return nil
}
if enabled {
self.logger.info("launchd enable requested via CLI port=\(port)")
return await self.runDaemonCommand([
"install",
"--force",
"--port",
"\(port)",
"--runtime",
"node",
])
_ = await Launchctl.run(["bootout", "gui/\(getuid())/\(self.legacyGatewayLaunchdLabel)"])
try? FileManager.default.removeItem(at: self.legacyPlistURL)
let desiredBind = self.preferredGatewayBind() ?? "loopback"
let desiredToken = self.preferredGatewayToken()
let desiredPassword = self.preferredGatewayPassword()
let desiredConfig = DesiredConfig(
port: port,
bind: desiredBind,
token: desiredToken,
password: desiredPassword)
let programArgumentsResult = self.gatewayProgramArguments(port: port, bind: desiredBind)
guard case let .success(programArguments) = programArgumentsResult else {
if case let .failure(error) = programArgumentsResult {
let message = error.localizedDescription
self.logger.error("launchd enable failed: \(message)")
return message
}
return "Failed to resolve gateway command."
}
// If launchd already loaded the job (common on login), avoid `bootout` unless we must
// change the config. `bootout` can kill a just-started gateway and cause attach loops.
let loaded = await self.isLoaded()
if loaded {
if let existing = self.readPlistConfig(), existing.matches(desiredConfig) {
self.logger.info("launchd job already loaded with desired config; skipping bootout")
await self.ensureEnabled()
_ = await Launchctl.run(["kickstart", "gui/\(getuid())/\(gatewayLaunchdLabel)"])
return nil
}
}
self.logger.info("launchd enable requested port=\(port) bind=\(desiredBind)")
self.writePlist(programArguments: programArguments)
await self.ensureEnabled()
if loaded {
_ = await Launchctl.run(["bootout", "gui/\(getuid())/\(gatewayLaunchdLabel)"])
}
let bootstrap = await Launchctl.run(["bootstrap", "gui/\(getuid())", self.plistURL.path])
if bootstrap.status != 0 {
let msg = bootstrap.output.trimmingCharacters(in: .whitespacesAndNewlines)
self.logger.error("launchd bootstrap failed: \(msg)")
return bootstrap.output.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty
? "Failed to bootstrap gateway launchd job"
: bootstrap.output.trimmingCharacters(in: .whitespacesAndNewlines)
}
await self.ensureEnabled()
return nil
}
self.logger.info("launchd disable requested via CLI")
return await self.runDaemonCommand(["uninstall"])
self.logger.info("launchd disable requested")
_ = await Launchctl.run(["bootout", "gui/\(getuid())/\(gatewayLaunchdLabel)"])
await self.ensureDisabled()
try? FileManager.default.removeItem(at: self.plistURL)
return nil
}
static func kickstart() async {
_ = await self.runDaemonCommand(["restart"], timeout: 20)
_ = await Launchctl.run(["kickstart", "-k", "gui/\(getuid())/\(gatewayLaunchdLabel)"])
}
private static func writePlist(programArguments: [String]) {
let preferredPath = CommandResolver.preferredPaths().joined(separator: ":")
let token = self.preferredGatewayToken()
let password = self.preferredGatewayPassword()
var envEntries = """
<key>PATH</key>
<string>\(preferredPath)</string>
"""
if let token {
let escapedToken = self.escapePlistValue(token)
envEntries += """
<key>CLAWDBOT_GATEWAY_TOKEN</key>
<string>\(escapedToken)</string>
"""
}
if let password {
let escapedPassword = self.escapePlistValue(password)
envEntries += """
<key>CLAWDBOT_GATEWAY_PASSWORD</key>
<string>\(escapedPassword)</string>
"""
}
let argsXml = programArguments
.map { "<string>\(self.escapePlistValue($0))</string>" }
.joined(separator: "\n ")
let plist = """
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>Label</key>
<string>\(gatewayLaunchdLabel)</string>
<key>ProgramArguments</key>
<array>
\(argsXml)
</array>
<key>WorkingDirectory</key>
<string>\(FileManager.default.homeDirectoryForCurrentUser.path)</string>
<key>RunAtLoad</key>
<true/>
<key>KeepAlive</key>
<true/>
<key>EnvironmentVariables</key>
<dict>
\(envEntries)
</dict>
<key>StandardOutPath</key>
<string>\(LogLocator.launchdGatewayLogPath)</string>
<key>StandardErrorPath</key>
<string>\(LogLocator.launchdGatewayLogPath)</string>
</dict>
</plist>
"""
do {
try plist.write(to: self.plistURL, atomically: true, encoding: .utf8)
} catch {
self.logger.error("launchd plist write failed: \(error.localizedDescription)")
}
}
private static func preferredGatewayBind() -> String? {
if CommandResolver.connectionModeIsRemote() {
return nil
}
if let env = ProcessInfo.processInfo.environment["CLAWDBOT_GATEWAY_BIND"] {
let trimmed = env.trimmingCharacters(in: .whitespacesAndNewlines).lowercased()
if self.supportedBindModes.contains(trimmed) {
return trimmed
}
}
let root = ClawdbotConfigFile.loadDict()
if let gateway = root["gateway"] as? [String: Any],
let bind = gateway["bind"] as? String
{
let trimmed = bind.trimmingCharacters(in: .whitespacesAndNewlines).lowercased()
if self.supportedBindModes.contains(trimmed) {
return trimmed
}
}
return nil
}
private static func preferredGatewayToken() -> String? {
let raw = ProcessInfo.processInfo.environment["CLAWDBOT_GATEWAY_TOKEN"] ?? ""
let trimmed = raw.trimmingCharacters(in: .whitespacesAndNewlines)
if !trimmed.isEmpty {
return trimmed
}
let root = ClawdbotConfigFile.loadDict()
if let gateway = root["gateway"] as? [String: Any],
let auth = gateway["auth"] as? [String: Any],
let token = auth["token"] as? String
{
let value = token.trimmingCharacters(in: .whitespacesAndNewlines)
if !value.isEmpty {
return value
}
}
return nil
}
private static func preferredGatewayPassword() -> String? {
// First check environment variable
let raw = ProcessInfo.processInfo.environment["CLAWDBOT_GATEWAY_PASSWORD"] ?? ""
let trimmed = raw.trimmingCharacters(in: .whitespacesAndNewlines)
if !trimmed.isEmpty {
return trimmed
}
// Then check config file (gateway.auth.password)
let root = ClawdbotConfigFile.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 DesiredConfig: Equatable {
let port: Int
let bind: String
let token: String?
let password: String?
}
private struct InstalledConfig: Equatable {
let port: Int?
let bind: String?
let token: String?
let password: String?
func matches(_ desired: DesiredConfig) -> Bool {
guard self.port == desired.port else { return false }
guard (self.bind ?? "loopback") == desired.bind else { return false }
guard self.token == desired.token else { return false }
guard self.password == desired.password else { return false }
return true
}
}
private static func readPlistConfig() -> InstalledConfig? {
guard let snapshot = LaunchAgentPlist.snapshot(url: self.plistURL) else { return nil }
return InstalledConfig(
port: snapshot.port,
bind: snapshot.bind,
token: snapshot.token,
password: snapshot.password)
}
static func launchdConfigSnapshot() -> LaunchAgentPlistSnapshot? {
LaunchAgentPlist.snapshot(url: self.plistURL)
}
static func launchdGatewayLogPath() -> String {
let snapshot = self.launchdConfigSnapshot()
if let stdout = snapshot?.stdoutPath?.trimmingCharacters(in: .whitespacesAndNewlines),
!stdout.isEmpty
{
return stdout
private static func ensureEnabled() async {
let result = await Launchctl.run(["enable", "gui/\(getuid())/\(gatewayLaunchdLabel)"])
guard result.status != 0 else { return }
let msg = result.output.trimmingCharacters(in: .whitespacesAndNewlines)
if msg.isEmpty {
self.logger.warning("launchd enable failed")
} else {
self.logger.warning("launchd enable failed: \(msg)")
}
if let stderr = snapshot?.stderrPath?.trimmingCharacters(in: .whitespacesAndNewlines),
!stderr.isEmpty
{
return stderr
}
private static func ensureDisabled() async {
let result = await Launchctl.run(["disable", "gui/\(getuid())/\(gatewayLaunchdLabel)"])
guard result.status != 0 else { return }
let msg = result.output.trimmingCharacters(in: .whitespacesAndNewlines)
if msg.isEmpty {
self.logger.warning("launchd disable failed")
} else {
self.logger.warning("launchd disable failed: \(msg)")
}
return LogLocator.launchdGatewayLogPath
}
}
@@ -67,102 +339,20 @@ extension GatewayLaunchAgentManager {
.appendingPathComponent(self.disableLaunchAgentMarker)
return FileManager.default.fileExists(atPath: marker.path)
}
}
private static func readDaemonLoaded() async -> Bool? {
let result = await self.runDaemonCommandResult(
["status", "--json", "--no-probe"],
timeout: 15,
quiet: true)
guard result.success, let payload = result.payload else { return nil }
guard
let json = try? JSONSerialization.jsonObject(with: payload) as? [String: Any],
let service = json["service"] as? [String: Any],
let loaded = service["loaded"] as? Bool
else {
return nil
}
return loaded
#if DEBUG
extension GatewayLaunchAgentManager {
static func _testPreferredGatewayBind() -> String? {
self.preferredGatewayBind()
}
private struct CommandResult {
let success: Bool
let payload: Data?
let message: String?
static func _testPreferredGatewayToken() -> String? {
self.preferredGatewayToken()
}
private struct ParsedDaemonJson {
let text: String
let object: [String: Any]
}
private static func runDaemonCommand(
_ args: [String],
timeout: Double = 15,
quiet: Bool = false) async -> String?
{
let result = await self.runDaemonCommandResult(args, timeout: timeout, quiet: quiet)
if result.success { return nil }
return result.message ?? "Gateway daemon command failed"
}
private static func runDaemonCommandResult(
_ args: [String],
timeout: Double,
quiet: Bool) async -> CommandResult
{
let command = CommandResolver.clawdbotCommand(
subcommand: "daemon",
extraArgs: self.withJsonFlag(args))
var env = ProcessInfo.processInfo.environment
env["PATH"] = CommandResolver.preferredPaths().joined(separator: ":")
let response = await ShellExecutor.runDetailed(command: command, cwd: nil, env: env, timeout: timeout)
let parsed = self.parseDaemonJson(from: response.stdout) ?? self.parseDaemonJson(from: response.stderr)
let ok = parsed?.object["ok"] as? Bool
let message = (parsed?.object["error"] as? String) ?? (parsed?.object["message"] as? String)
let payload = parsed?.text.data(using: .utf8)
?? (response.stdout.isEmpty ? response.stderr : response.stdout).data(using: .utf8)
let success = ok ?? response.success
if success {
return CommandResult(success: true, payload: payload, message: nil)
}
if quiet {
return CommandResult(success: false, payload: payload, message: message)
}
let detail = message ?? self.summarize(response.stderr) ?? self.summarize(response.stdout)
let exit = response.exitCode.map { "exit \($0)" } ?? (response.errorMessage ?? "failed")
let fullMessage = detail.map { "Gateway daemon command failed (\(exit)): \($0)" }
?? "Gateway daemon command failed (\(exit))"
self.logger.error("\(fullMessage, privacy: .public)")
return CommandResult(success: false, payload: payload, message: detail)
}
private static func withJsonFlag(_ args: [String]) -> [String] {
if args.contains("--json") { return args }
return args + ["--json"]
}
private static func parseDaemonJson(from raw: String) -> ParsedDaemonJson? {
let trimmed = raw.trimmingCharacters(in: .whitespacesAndNewlines)
guard let start = trimmed.firstIndex(of: "{"),
let end = trimmed.lastIndex(of: "}")
else {
return nil
}
let jsonText = String(trimmed[start...end])
guard let data = jsonText.data(using: .utf8) else { return nil }
guard let object = try? JSONSerialization.jsonObject(with: data) as? [String: Any] else { return nil }
return ParsedDaemonJson(text: jsonText, object: object)
}
private static func summarize(_ text: String) -> String? {
let lines = text
.split(whereSeparator: \.isNewline)
.map { $0.trimmingCharacters(in: .whitespacesAndNewlines) }
.filter { !$0.isEmpty }
guard let last = lines.last else { return nil }
let normalized = last.replacingOccurrences(of: "\\s+", with: " ", options: .regularExpression)
return normalized.count > 200 ? String(normalized.prefix(199)) + "…" : normalized
static func _testEscapePlistValue(_ raw: String) -> String {
self.escapePlistValue(raw)
}
}
#endif
@@ -87,14 +87,6 @@ final class GatewayProcessManager {
self.status = .stopped
return
}
// Many surfaces can call `setActive(true)` in quick succession (startup, Canvas, health checks).
// Avoid spawning multiple concurrent "start" tasks that can thrash launchd and flap the port.
switch self.status {
case .starting, .running, .attachedExisting:
return
case .stopped, .failed:
break
}
self.status = .starting
self.logger.debug("gateway start requested")
@@ -148,7 +140,7 @@ final class GatewayProcessManager {
func refreshLog() {
guard self.logRefreshTask == nil else { return }
let path = GatewayLaunchAgentManager.launchdGatewayLogPath()
let path = LogLocator.launchdGatewayLogPath
let limit = self.logLimit
self.logRefreshTask = Task { [weak self] in
let log = await Task.detached(priority: .utility) {
@@ -362,7 +354,7 @@ final class GatewayProcessManager {
func clearLog() {
self.log = ""
try? FileManager.default.removeItem(atPath: GatewayLaunchAgentManager.launchdGatewayLogPath())
try? FileManager.default.removeItem(atPath: LogLocator.launchdGatewayLogPath)
self.logger.debug("gateway log cleared")
}
@@ -92,13 +92,10 @@ struct GeneralSettings: View {
Text(policy.title).tag(policy)
}
}
.labelsHidden()
.pickerStyle(.menu)
.pickerStyle(.segmented)
Text("""
Controls remote command execution on this Mac when it is paired as a node. \
"Always Ask" prompts on each command; "Always Allow" runs without prompts; \
"Never" disables `system.run`.
Controls remote command execution on this Mac when it is paired as a node. "Always Ask" prompts on each command; "Always Allow" runs without prompts; "Never" disables `system.run`.
""")
.font(.footnote)
.foregroundStyle(.tertiary)
@@ -114,8 +111,7 @@ struct GeneralSettings: View {
Text("While Using").tag(ClawdbotLocationMode.whileUsing.rawValue)
Text("Always").tag(ClawdbotLocationMode.always.rawValue)
}
.labelsHidden()
.pickerStyle(.menu)
.pickerStyle(.segmented)
Toggle("Precise Location", isOn: self.$locationPreciseEnabled)
.disabled(self.locationMode == .off)
@@ -395,7 +395,7 @@ extension InstancesSettings {
host: "phone",
ip: "10.0.0.3",
version: "2.0.0",
platform: "iOS 18.0",
platform: "iOS 17.2",
deviceFamily: "iPhone",
modelIdentifier: nil,
lastInputSeconds: 35,
@@ -446,7 +446,7 @@ extension InstancesSettings {
_ = view.platformIcon("watchOS 10")
_ = view.platformIcon("unknown 1.0")
_ = view.prettyPlatform("macOS 14.2")
_ = view.prettyPlatform("iOS 18")
_ = view.prettyPlatform("iOS 17")
_ = view.prettyPlatform("ipados 17.1")
_ = view.prettyPlatform("linux")
_ = view.prettyPlatform(" ")
@@ -31,8 +31,6 @@ enum Launchctl {
struct LaunchAgentPlistSnapshot: Equatable, Sendable {
let programArguments: [String]
let environment: [String: String]
let stdoutPath: String?
let stderrPath: String?
let port: Int?
let bind: String?
@@ -55,10 +53,6 @@ enum LaunchAgentPlist {
guard let root = rootAny as? [String: Any] else { return nil }
let programArguments = root["ProgramArguments"] as? [String] ?? []
let env = root["EnvironmentVariables"] as? [String: String] ?? [:]
let stdoutPath = (root["StandardOutPath"] as? String)?
.trimmingCharacters(in: .whitespacesAndNewlines).nonEmpty
let stderrPath = (root["StandardErrorPath"] as? String)?
.trimmingCharacters(in: .whitespacesAndNewlines).nonEmpty
let port = Self.extractFlagInt(programArguments, flag: "--port")
let bind = Self.extractFlagString(programArguments, flag: "--bind")?.lowercased()
let token = env["CLAWDBOT_GATEWAY_TOKEN"]?.trimmingCharacters(in: .whitespacesAndNewlines).nonEmpty
@@ -66,8 +60,6 @@ enum LaunchAgentPlist {
return LaunchAgentPlistSnapshot(
programArguments: programArguments,
environment: env,
stdoutPath: stdoutPath,
stderrPath: stderrPath,
port: port,
bind: bind,
token: token,
@@ -460,7 +460,7 @@ actor MacNodeBridgeSession {
do {
try await self.send(response)
} catch {
self.logInvokeSendFailure(error)
await self.logInvokeSendFailure(error)
}
}
@@ -19,14 +19,14 @@ enum MacNodeBridgeTLSStore {
}
static func loadFingerprint(stableID: String) -> String? {
let key = self.keyPrefix + stableID
let raw = self.defaults.string(forKey: key)?.trimmingCharacters(in: .whitespacesAndNewlines)
let key = keyPrefix + stableID
let raw = defaults.string(forKey: key)?.trimmingCharacters(in: .whitespacesAndNewlines)
return raw?.isEmpty == false ? raw : nil
}
static func saveFingerprint(_ value: String, stableID: String) {
let key = self.keyPrefix + stableID
self.defaults.set(value, forKey: key)
let key = keyPrefix + stableID
defaults.set(value, forKey: key)
}
}
@@ -40,10 +40,11 @@ func makeMacNodeTLSOptions(_ params: MacNodeBridgeTLSParams?) -> NWProtocolTLS.O
sec_protocol_options_set_verify_block(
options.securityProtocolOptions,
{ _, trust, complete in
let trustRef = sec_trust_copy_ref(trust).takeRetainedValue()
if let chain = SecTrustCopyCertificateChain(trustRef) as? [SecCertificate],
let cert = chain.first
{
guard let trust else {
complete(false)
return
}
if let cert = SecTrustGetCertificateAtIndex(trust, 0) {
let data = SecCertificateCopyData(cert) as Data
let fingerprint = sha256Hex(data)
if let expected {
@@ -56,7 +57,7 @@ func makeMacNodeTLSOptions(_ params: MacNodeBridgeTLSParams?) -> NWProtocolTLS.O
return
}
}
let ok = SecTrustEvaluateWithError(trustRef, nil)
let ok = SecTrustEvaluateWithError(trust, nil)
complete(ok)
},
DispatchQueue(label: "com.clawdbot.macos.bridge.tls.verify"))
@@ -70,5 +71,5 @@ private func sha256Hex(_ data: Data) -> String {
}
private func normalizeMacNodeFingerprint(_ raw: String) -> String {
raw.lowercased().filter(\.isHexDigit)
raw.lowercased().filter { $0.isHexDigit }
}
@@ -164,7 +164,6 @@ final class MacNodeModeCoordinator {
]
if SystemRunPolicy.load() != .never {
commands.append(ClawdbotSystemCommand.which.rawValue)
commands.append(ClawdbotSystemCommand.run.rawValue)
}
@@ -464,7 +463,7 @@ final class MacNodeModeCoordinator {
}
}
private nonisolated static func targetFromResult(_ result: NWBrowser.Result) -> BridgeTarget? {
private static func targetFromResult(_ result: NWBrowser.Result) -> BridgeTarget? {
let endpoint = result.endpoint
guard case .service = endpoint else { return nil }
let stableID = BridgeEndpointID.stableID(endpoint)
@@ -478,7 +477,7 @@ final class MacNodeModeCoordinator {
return BridgeTarget(endpoint: endpoint, stableID: stableID, tls: tlsParams)
}
private nonisolated static func resolveDiscoveredTLSParams(
private static func resolveDiscoveredTLSParams(
stableID: String,
tlsEnabled: Bool,
tlsFingerprintSha256: String?) -> MacNodeBridgeTLSParams?
@@ -504,7 +503,7 @@ final class MacNodeModeCoordinator {
return nil
}
private nonisolated static func resolveManualTLSParams(stableID: String) -> MacNodeBridgeTLSParams? {
private static func resolveManualTLSParams(stableID: String) -> MacNodeBridgeTLSParams? {
if let stored = MacNodeBridgeTLSStore.loadFingerprint(stableID: stableID) {
return MacNodeBridgeTLSParams(
required: true,
@@ -520,12 +519,12 @@ final class MacNodeModeCoordinator {
storeKey: stableID)
}
private nonisolated static func txtValue(_ dict: [String: String], key: String) -> String? {
private static func txtValue(_ dict: [String: String], key: String) -> String? {
let raw = dict[key]?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
return raw.isEmpty ? nil : raw
}
private nonisolated static func txtBoolValue(_ dict: [String: String], key: String) -> Bool {
private static func txtBoolValue(_ dict: [String: String], key: String) -> Bool {
guard let raw = self.txtValue(dict, key: key)?.lowercased() else { return false }
return raw == "1" || raw == "true" || raw == "yes"
}
@@ -55,8 +55,6 @@ actor MacNodeRuntime {
return try await self.handleScreenRecordInvoke(req)
case ClawdbotSystemCommand.run.rawValue:
return try await self.handleSystemRun(req)
case ClawdbotSystemCommand.which.rawValue:
return try await self.handleSystemWhich(req)
case ClawdbotSystemCommand.notify.rawValue:
return try await self.handleSystemNotify(req)
default:
@@ -496,33 +494,6 @@ actor MacNodeRuntime {
return BridgeInvokeResponse(id: req.id, ok: true, payloadJSON: payload)
}
private func handleSystemWhich(_ req: BridgeInvokeRequest) async throws -> BridgeInvokeResponse {
let params = try Self.decodeParams(ClawdbotSystemWhichParams.self, from: req.paramsJSON)
let bins = params.bins
.map { $0.trimmingCharacters(in: .whitespacesAndNewlines) }
.filter { !$0.isEmpty }
guard !bins.isEmpty else {
return Self.errorResponse(req, code: .invalidRequest, message: "INVALID_REQUEST: bins required")
}
let searchPaths = CommandResolver.preferredPaths()
var matches: [String] = []
var paths: [String: String] = [:]
for bin in bins {
if let path = CommandResolver.findExecutable(named: bin, searchPaths: searchPaths) {
matches.append(bin)
paths[bin] = path
}
}
struct WhichPayload: Encodable {
let bins: [String]
let paths: [String: String]
}
let payload = try Self.encodePayload(WhichPayload(bins: matches, paths: paths))
return BridgeInvokeResponse(id: req.id, ok: true, payloadJSON: payload)
}
private func handleSystemNotify(_ req: BridgeInvokeRequest) async throws -> BridgeInvokeResponse {
let params = try Self.decodeParams(ClawdbotSystemNotifyParams.self, from: req.paramsJSON)
let title = params.title.trimmingCharacters(in: .whitespacesAndNewlines)
@@ -615,8 +586,8 @@ actor MacNodeRuntime {
let key = rawKey.trimmingCharacters(in: .whitespacesAndNewlines)
guard !key.isEmpty else { continue }
let upper = key.uppercased()
if self.blockedEnvKeys.contains(upper) { continue }
if self.blockedEnvPrefixes.contains(where: { upper.hasPrefix($0) }) { continue }
if blockedEnvKeys.contains(upper) { continue }
if blockedEnvPrefixes.contains(where: { upper.hasPrefix($0) }) { continue }
merged[key] = value
}
return merged
@@ -351,11 +351,10 @@ actor PortGuardian {
if port == GatewayEnvironment.gatewayPort() { return cmd.contains("ssh") }
return false
case .local:
// The gateway daemon may listen as `clawdbot` or as its runtime (`node`, `bun`, etc).
if !cmd.contains("clawdbot") { return false }
if full.contains("gateway-daemon") { return true }
// If args are unavailable, treat a clawdbot listener as expected.
if cmd.contains("clawdbot"), full == cmd { return true }
return false
return full == cmd
case .unconfigured:
return false
}
@@ -10,11 +10,11 @@ enum SystemRunPolicy: String, CaseIterable, Identifiable {
var title: String {
switch self {
case .never:
"Never"
return "Never"
case .ask:
"Always Ask"
return "Always Ask"
case .always:
"Always Allow"
return "Always Allow"
}
}
@@ -75,13 +75,13 @@ enum SystemRunAllowlist {
static func contains(_ argv: [String], defaults: UserDefaults = .standard) -> Bool {
let key = key(for: argv)
return self.load(from: defaults).contains(key)
return load(from: defaults).contains(key)
}
static func add(_ argv: [String], defaults: UserDefaults = .standard) {
let key = key(for: argv)
guard !key.isEmpty else { return }
var allowlist = self.load(from: defaults)
var allowlist = load(from: defaults)
if allowlist.insert(key).inserted {
MacNodeConfigFile.setSystemRunAllowlist(Array(allowlist).sorted())
}
@@ -1,4 +1,3 @@
import ClawdbotProtocol
import SwiftUI
import Testing
@testable import Clawdbot
@@ -38,7 +38,7 @@ struct CronJobEditorSmokeTests {
thinking: "low",
timeoutSeconds: 120,
deliver: true,
channel: "whatsapp",
provider: "whatsapp",
to: "+15551234567",
bestEffortDeliver: true),
isolation: CronIsolation(postToMainPrefix: "Cron"),
@@ -70,16 +70,22 @@ struct CronJobEditorSmokeTests {
}
@Test func cronJobEditorIncludesDeleteAfterRunForAtSchedule() throws {
let view = CronJobEditor(
var view = CronJobEditor(
job: nil,
isSaving: .constant(false),
error: .constant(nil),
onCancel: {},
onSave: { _ in })
view.name = "One-shot"
view.sessionTarget = .main
view.payloadKind = .systemEvent
view.systemEventText = "hello"
view.scheduleKind = .at
view.atDate = Date(timeIntervalSince1970: 1_700_000_000)
view.deleteAfterRun = true
var root: [String: Any] = [:]
view.applyDeleteAfterRun(to: &root, scheduleKind: .at, deleteAfterRun: true)
let raw = root["deleteAfterRun"] as? Bool
let payload = try view.buildPayload()
let raw = payload["deleteAfterRun"]?.value as? Bool
#expect(raw == true)
}
}
@@ -31,7 +31,7 @@ struct CronModelsTests {
thinking: "low",
timeoutSeconds: 15,
deliver: true,
channel: "whatsapp",
provider: "whatsapp",
to: "+15551234567",
bestEffortDeliver: false)
let data = try JSONEncoder().encode(payload)
@@ -7,8 +7,6 @@ import Testing
let snapshot = LaunchAgentPlistSnapshot(
programArguments: [],
environment: ["CLAWDBOT_GATEWAY_TOKEN": "launchd-token"],
stdoutPath: nil,
stderrPath: nil,
port: nil,
bind: nil,
token: "launchd-token",
@@ -33,8 +31,6 @@ import Testing
let snapshot = LaunchAgentPlistSnapshot(
programArguments: [],
environment: ["CLAWDBOT_GATEWAY_TOKEN": "launchd-token"],
stdoutPath: nil,
stderrPath: nil,
port: nil,
bind: nil,
token: "launchd-token",
@@ -52,8 +48,6 @@ import Testing
let snapshot = LaunchAgentPlistSnapshot(
programArguments: [],
environment: ["CLAWDBOT_GATEWAY_PASSWORD": "launchd-pass"],
stdoutPath: nil,
stderrPath: nil,
port: nil,
bind: nil,
token: nil,
@@ -39,7 +39,7 @@ struct InstancesSettingsSmokeTests {
host: "gateway",
ip: "10.0.0.4",
version: "3.0.0",
platform: "iOS 18",
platform: "iOS 17",
deviceFamily: nil,
modelIdentifier: nil,
lastInputSeconds: nil,
@@ -112,6 +112,20 @@ struct LowCoverageHelperTests {
_ = PresenceReporter._testPrimaryIPv4Address()
}
@Test func gatewayLaunchAgentHelpers() async throws {
await TestIsolation.withEnvValues(
[
"CLAWDBOT_GATEWAY_BIND": "Lan",
"CLAWDBOT_GATEWAY_TOKEN": " secret ",
]) {
#expect(GatewayLaunchAgentManager._testPreferredGatewayBind() == "lan")
#expect(GatewayLaunchAgentManager._testPreferredGatewayToken() == "secret")
#expect(
GatewayLaunchAgentManager._testEscapePlistValue("a&b<c>\"'") ==
"a&amp;b&lt;c&gt;&quot;&apos;")
}
}
@Test func portGuardianParsesListenersAndBuildsReports() {
let output = """
p123
@@ -11,8 +11,7 @@ import Testing
stateversion: StateVersion(presence: 1, health: 1),
uptimems: 123,
configpath: nil,
statedir: nil,
sessiondefaults: nil)
statedir: nil)
let hello = HelloOk(
type: "hello",
@@ -21,15 +21,6 @@ struct MacNodeRuntimeTests {
#expect(response.ok == false)
}
@Test func handleInvokeRejectsEmptySystemWhich() async throws {
let runtime = MacNodeRuntime()
let params = ClawdbotSystemWhichParams(bins: [])
let json = try String(data: JSONEncoder().encode(params), encoding: .utf8)
let response = await runtime.handleInvoke(
BridgeInvokeRequest(id: "req-2b", command: ClawdbotSystemCommand.which.rawValue, paramsJSON: json))
#expect(response.ok == false)
}
@Test func handleInvokeRejectsEmptyNotification() async throws {
let runtime = MacNodeRuntime()
let params = ClawdbotSystemNotifyParams(title: "", body: "")
@@ -74,10 +65,6 @@ struct MacNodeRuntimeTests {
{
CLLocation(latitude: 0, longitude: 0)
}
func confirmSystemRun(command: String, cwd: String?) async -> SystemRunDecision {
.allowOnce
}
}
let services = await MainActor.run { FakeMainActorServices() }
@@ -16,13 +16,13 @@ struct OnboardingViewSmokeTests {
}
@Test func pageOrderOmitsWorkspaceAndIdentitySteps() {
let order = OnboardingView.pageOrder(for: .local, showOnboardingChat: false)
let order = OnboardingView.pageOrder(for: .local, needsBootstrap: false)
#expect(!order.contains(7))
#expect(order.contains(3))
}
@Test func pageOrderOmitsOnboardingChatWhenIdentityKnown() {
let order = OnboardingView.pageOrder(for: .local, showOnboardingChat: false)
let order = OnboardingView.pageOrder(for: .local, needsBootstrap: false)
#expect(!order.contains(8))
}
}
@@ -49,7 +49,7 @@ struct SettingsViewSmokeTests {
thinking: "low",
timeoutSeconds: 30,
deliver: true,
channel: "sms",
provider: "sms",
to: "+15551234567",
bestEffortDeliver: true),
isolation: CronIsolation(postToMainPrefix: "[cron] "),
@@ -8,7 +8,7 @@ import Testing
let wav = makeWav16Mono(sampleRate: 8000, samples: 80)
defer { _ = TalkAudioPlayer.shared.stop() }
_ = try await withTimeout(seconds: 4.0) {
_ = try await withTimeout(seconds: 2.0) {
await TalkAudioPlayer.shared.play(data: wav)
}
@@ -27,7 +27,7 @@ import Testing
await Task.yield()
_ = await TalkAudioPlayer.shared.play(data: wav)
_ = try await withTimeout(seconds: 4.0) {
_ = try await withTimeout(seconds: 2.0) {
await first.value
}
#expect(true)
@@ -17,6 +17,6 @@ import Testing
#expect(opts.thinking == "low")
#expect(opts.deliver == true)
#expect(opts.to == nil)
#expect(opts.channel == .last)
#expect(opts.provider == .last)
}
}
+2 -9
View File
@@ -5,7 +5,7 @@ import PackageDescription
let package = Package(
name: "ClawdbotKit",
platforms: [
.iOS(.v18),
.iOS(.v17),
.macOS(.v15),
],
products: [
@@ -14,7 +14,6 @@ let package = Package(
],
dependencies: [
.package(url: "https://github.com/steipete/ElevenLabsKit", exact: "0.1.0"),
.package(url: "https://github.com/gonzalezreal/textual", exact: "0.2.0"),
],
targets: [
.target(
@@ -30,13 +29,7 @@ let package = Package(
]),
.target(
name: "ClawdbotChatUI",
dependencies: [
"ClawdbotKit",
.product(
name: "Textual",
package: "textual",
condition: .when(platforms: [.macOS, .iOS])),
],
dependencies: ["ClawdbotKit"],
swiftSettings: [
.enableUpcomingFeature("StrictConcurrency"),
]),
@@ -1,51 +0,0 @@
import Foundation
enum ChatMarkdownPreprocessor {
struct InlineImage: Identifiable {
let id = UUID()
let label: String
let image: ClawdbotPlatformImage?
}
struct Result {
let cleaned: String
let images: [InlineImage]
}
static func preprocess(markdown raw: String) -> Result {
let pattern = #"!\[([^\]]*)\]\((data:image\/[^;]+;base64,[^)]+)\)"#
guard let re = try? NSRegularExpression(pattern: pattern) else {
return Result(cleaned: raw, images: [])
}
let ns = raw as NSString
let matches = re.matches(in: raw, range: NSRange(location: 0, length: ns.length))
if matches.isEmpty { return Result(cleaned: raw, images: []) }
var images: [InlineImage] = []
var cleaned = raw
for match in matches.reversed() {
guard match.numberOfRanges >= 3 else { continue }
let label = ns.substring(with: match.range(at: 1))
let dataURL = ns.substring(with: match.range(at: 2))
let image: ClawdbotPlatformImage? = {
guard let comma = dataURL.firstIndex(of: ",") else { return nil }
let b64 = String(dataURL[dataURL.index(after: comma)...])
guard let data = Data(base64Encoded: b64) else { return nil }
return ClawdbotPlatformImage(data: data)
}()
images.append(InlineImage(label: label, image: image))
let start = cleaned.index(cleaned.startIndex, offsetBy: match.range.location)
let end = cleaned.index(start, offsetBy: match.range.length)
cleaned.replaceSubrange(start..<end, with: "")
}
let normalized = cleaned
.replacingOccurrences(of: "\n\n\n", with: "\n\n")
.trimmingCharacters(in: .whitespacesAndNewlines)
return Result(cleaned: normalized, images: images.reversed())
}
}
@@ -1,90 +0,0 @@
import SwiftUI
import Textual
public enum ChatMarkdownVariant: String, CaseIterable, Sendable {
case standard
case compact
}
@MainActor
struct ChatMarkdownRenderer: View {
enum Context {
case user
case assistant
}
let text: String
let context: Context
let variant: ChatMarkdownVariant
let font: Font
let textColor: Color
var body: some View {
let processed = ChatMarkdownPreprocessor.preprocess(markdown: self.text)
VStack(alignment: .leading, spacing: 10) {
StructuredText(markdown: processed.cleaned)
.modifier(ChatMarkdownStyle(
variant: self.variant,
context: self.context,
font: self.font,
textColor: self.textColor))
if !processed.images.isEmpty {
InlineImageList(images: processed.images)
}
}
}
}
private struct ChatMarkdownStyle: ViewModifier {
let variant: ChatMarkdownVariant
let context: ChatMarkdownRenderer.Context
let font: Font
let textColor: Color
func body(content: Content) -> some View {
Group {
if self.variant == .compact {
content.textual.structuredTextStyle(.default)
} else {
content.textual.structuredTextStyle(.gitHub)
}
}
.font(self.font)
.foregroundStyle(self.textColor)
.textual.inlineStyle(self.inlineStyle)
.textual.textSelection(.enabled)
}
private var inlineStyle: InlineStyle {
let linkColor: Color = self.context == .user ? self.textColor : .accentColor
let codeScale: CGFloat = self.variant == .compact ? 0.85 : 0.9
return InlineStyle()
.code(.monospaced, .fontScale(codeScale))
.link(.foregroundColor(linkColor))
}
}
@MainActor
private struct InlineImageList: View {
let images: [ChatMarkdownPreprocessor.InlineImage]
var body: some View {
ForEach(images, id: \.id) { item in
if let img = item.image {
ClawdbotPlatformImageFactory.image(img)
.resizable()
.scaledToFit()
.frame(maxHeight: 260)
.clipShape(RoundedRectangle(cornerRadius: 12, style: .continuous))
.overlay(
RoundedRectangle(cornerRadius: 12, style: .continuous)
.strokeBorder(Color.white.opacity(0.12), lineWidth: 1))
} else {
Text(item.label.isEmpty ? "Image" : item.label)
.font(.footnote)
.foregroundStyle(.secondary)
}
}
}
}
@@ -0,0 +1,114 @@
import Foundation
enum ChatMarkdownSplitter {
struct InlineImage: Identifiable {
let id = UUID()
let label: String
let image: ClawdbotPlatformImage?
}
struct Block: Identifiable {
enum Kind: Equatable {
case text
case code(language: String?)
}
let id = UUID()
let kind: Kind
let text: String
}
struct SplitResult {
let blocks: [Block]
let images: [InlineImage]
}
static func split(markdown raw: String) -> SplitResult {
let extracted = self.extractInlineImages(from: raw)
let blocks = self.splitCodeBlocks(from: extracted.cleaned)
return SplitResult(blocks: blocks, images: extracted.images)
}
private static func splitCodeBlocks(from raw: String) -> [Block] {
var blocks: [Block] = []
var buffer: [String] = []
var inCode = false
var codeLang: String?
var codeLines: [String] = []
for line in raw.split(separator: "\n", omittingEmptySubsequences: false).map(String.init) {
if line.hasPrefix("```") {
if inCode {
blocks.append(Block(kind: .code(language: codeLang), text: codeLines.joined(separator: "\n")))
codeLines.removeAll(keepingCapacity: true)
inCode = false
codeLang = nil
} else {
let text = buffer.joined(separator: "\n").trimmingCharacters(in: .whitespacesAndNewlines)
if !text.isEmpty {
blocks.append(Block(kind: .text, text: text))
}
buffer.removeAll(keepingCapacity: true)
inCode = true
codeLang = line.dropFirst(3).trimmingCharacters(in: .whitespacesAndNewlines)
if codeLang?.isEmpty == true { codeLang = nil }
}
continue
}
if inCode {
codeLines.append(line)
} else {
buffer.append(line)
}
}
if inCode {
blocks.append(Block(kind: .code(language: codeLang), text: codeLines.joined(separator: "\n")))
} else {
let text = buffer.joined(separator: "\n").trimmingCharacters(in: .whitespacesAndNewlines)
if !text.isEmpty {
blocks.append(Block(kind: .text, text: text))
}
}
return blocks.isEmpty ? [Block(kind: .text, text: raw)] : blocks
}
private static func extractInlineImages(from raw: String) -> (cleaned: String, images: [InlineImage]) {
let pattern = #"!\[([^\]]*)\]\((data:image\/[^;]+;base64,[^)]+)\)"#
guard let re = try? NSRegularExpression(pattern: pattern) else {
return (raw, [])
}
let ns = raw as NSString
let matches = re.matches(in: raw, range: NSRange(location: 0, length: ns.length))
if matches.isEmpty { return (raw, []) }
var images: [InlineImage] = []
var cleaned = raw
for match in matches.reversed() {
guard match.numberOfRanges >= 3 else { continue }
let label = ns.substring(with: match.range(at: 1))
let dataURL = ns.substring(with: match.range(at: 2))
let image: ClawdbotPlatformImage? = {
guard let comma = dataURL.firstIndex(of: ",") else { return nil }
let b64 = String(dataURL[dataURL.index(after: comma)...])
guard let data = Data(base64Encoded: b64) else { return nil }
return ClawdbotPlatformImage(data: data)
}()
images.append(InlineImage(label: label, image: image))
let start = cleaned.index(cleaned.startIndex, offsetBy: match.range.location)
let end = cleaned.index(start, offsetBy: match.range.length)
cleaned.replaceSubrange(start..<end, with: "")
}
let normalized = cleaned
.replacingOccurrences(of: "\n\n\n", with: "\n\n")
.trimmingCharacters(in: .whitespacesAndNewlines)
return (normalized, images.reversed())
}
}
@@ -137,16 +137,10 @@ private struct ChatBubbleShape: InsettableShape {
struct ChatMessageBubble: View {
let message: ClawdbotChatMessage
let style: ClawdbotChatView.Style
let markdownVariant: ChatMarkdownVariant
let userAccent: Color?
var body: some View {
ChatMessageBody(
message: self.message,
isUser: self.isUser,
style: self.style,
markdownVariant: self.markdownVariant,
userAccent: self.userAccent)
ChatMessageBody(message: self.message, isUser: self.isUser, style: self.style, userAccent: self.userAccent)
.frame(maxWidth: ChatUIConstants.bubbleMaxWidth, alignment: self.isUser ? .trailing : .leading)
.frame(maxWidth: .infinity, alignment: self.isUser ? .trailing : .leading)
.padding(.horizontal, 2)
@@ -160,7 +154,6 @@ private struct ChatMessageBody: View {
let message: ClawdbotChatMessage
let isUser: Bool
let style: ClawdbotChatView.Style
let markdownVariant: ChatMarkdownVariant
let userAccent: Color?
var body: some View {
@@ -176,14 +169,39 @@ private struct ChatMessageBody: View {
isUser: self.isUser)
}
} else if self.isUser {
ChatMarkdownRenderer(
text: text,
context: .user,
variant: self.markdownVariant,
font: .system(size: 14),
textColor: textColor)
let split = ChatMarkdownSplitter.split(markdown: text)
ForEach(split.blocks) { block in
switch block.kind {
case .text:
MarkdownTextView(text: block.text, textColor: textColor, font: .system(size: 14))
case let .code(language):
CodeBlockView(code: block.text, language: language, isUser: self.isUser)
}
}
if !split.images.isEmpty {
ForEach(
split.images,
id: \ChatMarkdownSplitter.InlineImage.id)
{ (item: ChatMarkdownSplitter.InlineImage) in
if let img = item.image {
ClawdbotPlatformImageFactory.image(img)
.resizable()
.scaledToFit()
.frame(maxHeight: 260)
.clipShape(RoundedRectangle(cornerRadius: 12, style: .continuous))
.overlay(
RoundedRectangle(cornerRadius: 12, style: .continuous)
.strokeBorder(Color.white.opacity(0.12), lineWidth: 1))
} else {
Text(item.label.isEmpty ? "Image" : item.label)
.font(.footnote)
.foregroundStyle(.secondary)
}
}
}
} else {
ChatAssistantTextBody(text: text, markdownVariant: self.markdownVariant)
ChatAssistantTextBody(text: text)
}
if !self.inlineAttachments.isEmpty {
@@ -487,11 +505,10 @@ extension ChatTypingIndicatorBubble: @MainActor Equatable {
@MainActor
struct ChatStreamingAssistantBubble: View {
let text: String
let markdownVariant: ChatMarkdownVariant
var body: some View {
VStack(alignment: .leading, spacing: 10) {
ChatAssistantTextBody(text: self.text, markdownVariant: self.markdownVariant)
ChatAssistantTextBody(text: self.text)
}
.padding(12)
.background(
@@ -595,22 +612,114 @@ private struct TypingDots: View {
}
}
@MainActor
private struct MarkdownTextView: View {
let text: String
let textColor: Color
let font: Font
var body: some View {
let normalized = self.text.replacingOccurrences(
of: "(?<!\\n)\\n(?!\\n)",
with: " ",
options: .regularExpression)
let options = AttributedString.MarkdownParsingOptions(
interpretedSyntax: .inlineOnlyPreservingWhitespace)
if let attributed = try? AttributedString(markdown: normalized, options: options) {
Text(attributed)
.font(self.font)
.foregroundStyle(self.textColor)
} else {
Text(normalized)
.font(self.font)
.foregroundStyle(self.textColor)
}
}
}
@MainActor
private struct ChatAssistantTextBody: View {
let text: String
let markdownVariant: ChatMarkdownVariant
var body: some View {
let segments = AssistantTextParser.segments(from: self.text)
VStack(alignment: .leading, spacing: 10) {
ForEach(segments) { segment in
let font = segment.kind == .thinking ? Font.system(size: 14).italic() : Font.system(size: 14)
ChatMarkdownRenderer(
text: segment.text,
context: .assistant,
variant: self.markdownVariant,
font: font,
textColor: ClawdbotChatTheme.assistantText)
ChatMarkdownBody(text: segment.text, textColor: ClawdbotChatTheme.assistantText, font: font)
}
}
}
}
@MainActor
private struct ChatMarkdownBody: View {
let text: String
let textColor: Color
let font: Font
var body: some View {
let split = ChatMarkdownSplitter.split(markdown: self.text)
VStack(alignment: .leading, spacing: 10) {
ForEach(split.blocks) { block in
switch block.kind {
case .text:
MarkdownTextView(text: block.text, textColor: self.textColor, font: self.font)
case let .code(language):
CodeBlockView(code: block.text, language: language, isUser: false)
}
}
if !split.images.isEmpty {
ForEach(
split.images,
id: \ChatMarkdownSplitter.InlineImage.id)
{ (item: ChatMarkdownSplitter.InlineImage) in
if let img = item.image {
ClawdbotPlatformImageFactory.image(img)
.resizable()
.scaledToFit()
.frame(maxHeight: 260)
.clipShape(RoundedRectangle(cornerRadius: 12, style: .continuous))
.overlay(
RoundedRectangle(cornerRadius: 12, style: .continuous)
.strokeBorder(Color.white.opacity(0.12), lineWidth: 1))
} else {
Text(item.label.isEmpty ? "Image" : item.label)
.font(.footnote)
.foregroundStyle(.secondary)
}
}
}
}
.textSelection(.enabled)
}
}
@MainActor
private struct CodeBlockView: View {
let code: String
let language: String?
let isUser: Bool
var body: some View {
VStack(alignment: .leading, spacing: 8) {
if let language, !language.isEmpty {
Text(language)
.font(.caption2.monospaced())
.foregroundStyle(.secondary)
}
Text(self.code)
.font(.system(size: 13, weight: .regular, design: .monospaced))
.foregroundStyle(self.isUser ? .white : .primary)
.textSelection(.enabled)
}
.padding(12)
.frame(maxWidth: .infinity, alignment: .leading)
.background(self.isUser ? Color.white.opacity(0.16) : Color.black.opacity(0.06))
.overlay(
RoundedRectangle(cornerRadius: 12, style: .continuous)
.strokeBorder(Color.black.opacity(0.08), lineWidth: 1))
.clipShape(RoundedRectangle(cornerRadius: 12, style: .continuous))
}
}
@@ -14,7 +14,6 @@ public struct ClawdbotChatView: View {
@State private var hasPerformedInitialScroll = false
private let showsSessionSwitcher: Bool
private let style: Style
private let markdownVariant: ChatMarkdownVariant
private let userAccent: Color?
private enum Layout {
@@ -43,13 +42,11 @@ public struct ClawdbotChatView: View {
viewModel: ClawdbotChatViewModel,
showsSessionSwitcher: Bool = false,
style: Style = .standard,
markdownVariant: ChatMarkdownVariant = .standard,
userAccent: Color? = nil)
{
self._viewModel = State(initialValue: viewModel)
self.showsSessionSwitcher = showsSessionSwitcher
self.style = style
self.markdownVariant = markdownVariant
self.userAccent = userAccent
}
@@ -154,11 +151,7 @@ public struct ClawdbotChatView: View {
@ViewBuilder
private var messageListRows: some View {
ForEach(self.visibleMessages) { msg in
ChatMessageBubble(
message: msg,
style: self.style,
markdownVariant: self.markdownVariant,
userAccent: self.userAccent)
ChatMessageBubble(message: msg, style: self.style, userAccent: self.userAccent)
.frame(
maxWidth: .infinity,
alignment: msg.role.lowercased() == "user" ? .trailing : .leading)
@@ -179,7 +172,7 @@ public struct ClawdbotChatView: View {
}
if let text = self.viewModel.streamingAssistantText, AssistantTextParser.hasVisibleContent(in: text) {
ChatStreamingAssistantBubble(text: text, markdownVariant: self.markdownVariant)
ChatStreamingAssistantBubble(text: text)
.frame(maxWidth: .infinity, alignment: .leading)
}
}
@@ -2,7 +2,6 @@ import Foundation
public enum ClawdbotSystemCommand: String, Codable, Sendable {
case run = "system.run"
case which = "system.which"
case notify = "system.notify"
}
@@ -40,14 +39,6 @@ public struct ClawdbotSystemRunParams: Codable, Sendable, Equatable {
}
}
public struct ClawdbotSystemWhichParams: Codable, Sendable, Equatable {
public var bins: [String]
public init(bins: [String]) {
self.bins = bins
}
}
public struct ClawdbotSystemNotifyParams: Codable, Sendable, Equatable {
public var title: String
public var body: String
@@ -1,20 +0,0 @@
import Testing
@testable import ClawdbotChatUI
@Suite("ChatMarkdownPreprocessor")
struct ChatMarkdownPreprocessorTests {
@Test func extractsDataURLImages() {
let base64 = "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVQIHWP4////GQAJ+wP/2hN8NwAAAABJRU5ErkJggg=="
let markdown = """
Hello
![Pixel](data:image/png;base64,\(base64))
"""
let result = ChatMarkdownPreprocessor.preprocess(markdown: markdown)
#expect(result.cleaned == "Hello")
#expect(result.images.count == 1)
#expect(result.images.first?.image != nil)
}
}
+1 -8
View File
@@ -227,8 +227,6 @@ Outbound Discord API calls retry on rate limits (429) using Discord `retry_after
actions: {
reactions: true,
stickers: true,
emojiUploads: true,
stickerUploads: true,
polls: true,
permissions: true,
messages: true,
@@ -239,7 +237,6 @@ Outbound Discord API calls retry on rate limits (429) using Discord `retry_after
roleInfo: true,
roles: false,
channelInfo: true,
channels: true,
voiceStatus: true,
events: true,
moderation: false
@@ -307,9 +304,8 @@ ack reaction after the bot replies.
- `retry`: retry policy for outbound Discord API calls (attempts, minDelayMs, maxDelayMs, jitter).
- `actions`: per-action tool gates; omit to allow all (set `false` to disable).
- `reactions` (covers react + read reactions)
- `stickers`, `emojiUploads`, `stickerUploads`, `polls`, `permissions`, `messages`, `threads`, `pins`, `search`
- `stickers`, `polls`, `permissions`, `messages`, `threads`, `pins`, `search`
- `memberInfo`, `roleInfo`, `channelInfo`, `voiceStatus`, `events`
- `channels` (create/edit/delete channels + categories + permissions)
- `roles` (role add/remove, default `false`)
- `moderation` (timeout/kick/ban, default `false`)
@@ -325,8 +321,6 @@ Reaction notifications use `guilds.<id>.reactionNotifications`:
| --- | --- | --- |
| reactions | enabled | React + list reactions + emojiList |
| stickers | enabled | Send stickers |
| emojiUploads | enabled | Upload emojis |
| stickerUploads | enabled | Upload stickers |
| polls | enabled | Create polls |
| permissions | enabled | Channel permission snapshot |
| messages | enabled | Read/send/edit/delete |
@@ -336,7 +330,6 @@ Reaction notifications use `guilds.<id>.reactionNotifications`:
| memberInfo | enabled | Member info |
| roleInfo | enabled | Role list |
| channelInfo | enabled | Channel info + list |
| channels | enabled | Channel/category management |
| voiceStatus | enabled | Voice state lookup |
| events | enabled | List/create scheduled events |
| roles | disabled | Role add/remove |
-23
View File
@@ -101,29 +101,6 @@ group messages, so use admin if you need full visibility.
- Raw HTML from models is escaped to avoid Telegram parse errors.
- If Telegram rejects the HTML payload, Clawdbot retries the same message as plain text.
## Commands (native + custom)
Clawdbot registers native commands (like `/status`, `/reset`, `/model`) with Telegram’s bot menu on startup.
You can add custom commands to the menu via config:
```json5
{
channels: {
telegram: {
customCommands: [
{ command: "backup", description: "Git backup" },
{ command: "generate", description: "Create an image" }
]
}
}
}
```
Notes:
- Custom commands are **menu entries only**; Clawdbot does not implement them unless you handle them elsewhere.
- Command names are normalized (leading `/` stripped, lowercased) and must match `a-z`, `0-9`, `_` (1–32 chars).
- Custom commands **cannot override native commands**. Conflicts are ignored and logged.
- If `commands.native` is disabled, only custom commands are registered (or cleared if none).
## Limits
- Outbound text is chunked to `channels.telegram.textChunkLimit` (default 4000).
- Media downloads/uploads are capped by `channels.telegram.mediaMaxMb` (default 5).
-41
View File
@@ -1,41 +0,0 @@
---
summary: "CLI reference for `clawdbot config` (get/set/unset config values)"
read_when:
- You want to read or edit config non-interactively
---
# `clawdbot config`
Config helpers: get/set/unset values by path. Run without a subcommand to open
the configure wizard (same as `clawdbot configure`).
## Examples
```bash
clawdbot config get browser.executablePath
clawdbot config set browser.executablePath "/usr/bin/google-chrome"
clawdbot config set agents.defaults.heartbeat.every "2h"
clawdbot config unset tools.web.search.apiKey
```
## Paths
Paths use dot or bracket notation:
```bash
clawdbot config get agents.defaults.workspace
clawdbot config get agents.list[0].id
```
## Values
Values are parsed as JSON5 when possible; otherwise they are treated as strings.
Use `--json` to require JSON5 parsing.
```bash
clawdbot config set agents.defaults.heartbeat.every "0m"
clawdbot config set gateway.port 19001 --json
clawdbot config set channels.whatsapp.groups '["*"]' --json
```
Restart the gateway after edits.
+2 -6
View File
@@ -1,19 +1,15 @@
---
summary: "CLI reference for `clawdbot configure` (interactive configuration prompts)"
summary: "CLI reference for `clawdbot configure` / `clawdbot config` (interactive configuration prompts)"
read_when:
- You want to tweak credentials, devices, or agent defaults interactively
---
# `clawdbot configure`
# `clawdbot configure` (alias: `config`)
Interactive prompt to set up credentials, devices, and agent defaults.
Tip: `clawdbot config` without a subcommand opens the same wizard. Use
`clawdbot config get|set|unset` for non-interactive edits.
Related:
- Gateway configuration reference: [Configuration](/gateway/configuration)
- Config CLI: [Config](/cli/config)
Notes:
- Choosing where the Gateway runs always updates `gateway.mode`. You can select "Continue" without other sections if that is all you need.
-3
View File
@@ -15,6 +15,3 @@ Related:
Tip: run `clawdbot daemon --help` for platform-specific flags.
Notes:
- `daemon status` supports `--json` for scripting.
- `daemon install|uninstall|start|stop|restart` support `--json` for scripting (default output stays human-friendly).
+4 -19
View File
@@ -13,8 +13,7 @@ This page describes the current CLI behavior. If commands change, update this do
- [`setup`](/cli/setup)
- [`onboard`](/cli/onboard)
- [`configure`](/cli/configure)
- [`config`](/cli/config)
- [`configure`](/cli/configure) (alias: `config`)
- [`doctor`](/cli/doctor)
- [`dashboard`](/cli/dashboard)
- [`reset`](/cli/reset)
@@ -84,11 +83,7 @@ Palette source of truth: `src/terminal/palette.ts` (aka “lobster seam”).
clawdbot [--dev] [--profile <name>] <command>
setup
onboard
configure
config
get
set
unset
configure (alias: config)
doctor
security
audit
@@ -315,18 +310,9 @@ Options:
- `--node-manager <npm|pnpm|bun>` (pnpm recommended; bun not recommended for Gateway runtime)
- `--json`
### `configure`
### `configure` / `config`
Interactive configuration wizard (models, channels, skills, gateway).
### `config`
Non-interactive config helpers (get/set/unset). Running `clawdbot config` with no
subcommand launches the wizard.
Subcommands:
- `config get <path>`: print a config value (dot/bracket path).
- `config set <path> <value>`: set a value (JSON5 or raw string).
- `config unset <path>`: remove a value.
### `doctor`
Health checks + quick fixes (config + gateway + legacy services).
@@ -608,9 +594,8 @@ Notes:
- `daemon status` supports `--no-probe`, `--deep`, and `--json` for scripting.
- `daemon status` also surfaces legacy or extra gateway services when it can detect them (`--deep` adds system-level scans). Profile-named Clawdbot services are treated as first-class and aren't flagged as "extra".
- `daemon status` prints which config path the CLI uses vs which config the daemon likely uses (service env), plus the resolved probe target URL.
- `daemon install|uninstall|start|stop|restart` support `--json` for scripting (default output stays human-friendly).
- `daemon install` defaults to Node runtime; bun is **not recommended** (WhatsApp/Telegram bugs).
- `daemon install` options: `--port`, `--runtime`, `--token`, `--force`, `--json`.
- `daemon install` options: `--port`, `--runtime`, `--token`, `--force`.
### `logs`
Tail Gateway file logs via RPC.
-11
View File
@@ -21,8 +21,6 @@ clawdbot plugins info <id>
clawdbot plugins enable <id>
clawdbot plugins disable <id>
clawdbot plugins doctor
clawdbot plugins update <id>
clawdbot plugins update --all
```
### Install
@@ -33,12 +31,3 @@ clawdbot plugins install <npm-spec>
Security note: treat plugin installs like running code. Prefer pinned versions.
### Update
```bash
clawdbot plugins update <id>
clawdbot plugins update --all
clawdbot plugins update <id> --dry-run
```
Updates only apply to plugins installed from npm (tracked in `plugins.installs`).
-5
View File
@@ -871,7 +871,6 @@ Notes:
- `commands.text: false` disables parsing chat messages for commands.
- `commands.native: "auto"` (default) turns on native commands for Discord/Telegram and leaves Slack off; unsupported channels stay text-only.
- Set `commands.native: true|false` to force all, or override per channel with `channels.discord.commands.native`, `channels.telegram.commands.native`, `channels.slack.commands.native` (bool or `"auto"`). `false` clears previously registered commands on Discord/Telegram at startup; Slack commands are managed in the Slack app.
- `channels.telegram.customCommands` adds extra Telegram bot menu entries. Names are normalized; conflicts with native commands are ignored.
- `commands.bash: true` enables `! <cmd>` to run host shell commands (`/bash <cmd>` also works as an alias). Requires `tools.elevated.enabled` and allowlisting the sender in `tools.elevated.allowFrom.<channel>`.
- `commands.bashForegroundMs` controls how long bash waits before backgrounding. While a bash job is running, new `! <cmd>` requests are rejected (one at a time).
- `commands.config: true` enables `/config` (reads/writes `clawdbot.json`).
@@ -930,10 +929,6 @@ Set `channels.telegram.configWrites: false` to block Telegram-initiated config w
}
}
},
customCommands: [
{ command: "backup", description: "Git backup" },
{ command: "generate", description: "Create an image" }
],
historyLimit: 50, // include last N group messages as context (0 disables)
replyToMode: "first", // off | first | all
streamMode: "partial", // off | partial | block (draft streaming; separate from block streaming)
-9
View File
@@ -161,15 +161,6 @@ Even with strong system prompts, **prompt injection is not solved**. What helps
- Run sensitive tool execution in a sandbox; keep secrets out of the agent’s reachable filesystem.
- **Model choice matters:** older/legacy models can be less robust against prompt injection and tool misuse. Prefer modern, instruction-hardened models for any bot with tools. We recommend Anthropic Opus 4.5 because it’s quite good at recognizing prompt injections (see [“A step forward on safety”](https://www.anthropic.com/news/claude-opus-4-5)).
### Model strength (security note)
Prompt injection resistance is **not** uniform across model tiers. Smaller/cheaper models are generally more susceptible to tool misuse and instruction hijacking, especially under adversarial prompts.
Recommendations:
- **Use the latest generation, best-tier model** for any bot that can run tools or touch files/networks.
- **Avoid weaker tiers** (for example, Sonnet or Haiku) for tool-enabled agents or untrusted inboxes.
- If you must use a smaller model, **reduce blast radius** (read-only tools, strong sandboxing, minimal filesystem access, strict allowlists).
## Reasoning & verbose output in groups
`/reasoning` and `/verbose` can expose internal reasoning or tool output that
-147
View File
@@ -169,20 +169,6 @@ The agent was interrupted mid-response.
**Fix:** Just send another message. The session continues.
### "Agent failed before reply: Unknown model: anthropic/claude-haiku-3-5"
Clawdbot intentionally rejects **older/insecure models** (especially those more
vulnerable to prompt injection). If you see this error, the model name is no
longer supported.
**Fix:**
- Pick a **latest** model for the provider and update your config or model alias.
- If you’re unsure which models are available, run `clawdbot models list` or
`clawdbot models scan` and choose a supported one.
- Check gateway logs for the detailed failure reason.
See also: [Models CLI](/cli/models) and [Model providers](/concepts/model-providers).
### Messages Not Triggering
**Check 1:** Is the sender allowlisted?
@@ -320,139 +306,6 @@ Clawdbot keeps conversation history in memory.
}
```
## Common troubleshooting
### “All models failed” — what should I check first?
- **Credentials** present for the provider(s) being tried (auth profiles + env vars).
- **Model routing**: confirm `agents.defaults.model.primary` and fallbacks are models you can access.
- **Gateway logs** in `/tmp/clawdbot/…` for the exact provider error.
- **Model status**: use `/model status` (chat) or `clawdbot models status` (CLI).
### I’m running on my personal WhatsApp number — why is self-chat weird?
Enable self-chat mode and allowlist your own number:
```json5
{
channels: {
whatsapp: {
selfChatMode: true,
dmPolicy: "allowlist",
allowFrom: ["+15555550123"]
}
}
}
```
See [WhatsApp setup](/channels/whatsapp).
### WhatsApp logged me out. How do I re‑auth?
Run the login command again and scan the QR code:
```bash
clawdbot channels login
```
### Build errors on `main` — what’s the standard fix path?
1) `git pull origin main && pnpm install`
2) `pnpm clawdbot doctor`
3) Check GitHub issues or Discord
4) Temporary workaround: check out an older commit
### npm install fails (allow-build-scripts / missing tar or yargs). What now?
If you’re running from source, use the repo’s package manager: **pnpm** (preferred).
The repo declares `packageManager: "pnpm@…"`, and pnpm patches are tracked in `pnpm.patchedDependencies`.
Typical recovery:
```bash
git status # ensure you’re in the repo root
pnpm install
pnpm build
pnpm clawdbot doctor
clawdbot daemon restart
```
Why: pnpm is the configured package manager for this repo, and the dependency
patching workflow relies on it.
### How do I switch between git installs and npm installs?
Use the **website installer** and select the install method with a flag. It
upgrades in place and rewrites the gateway service to point at the new install.
Switch **to git install**:
```bash
curl -fsSL https://clawd.bot/install.sh | bash -s -- --install-method git --no-onboard
```
Switch **to npm global**:
```bash
curl -fsSL https://clawd.bot/install.sh | bash
```
Notes:
- The git flow only rebases if the repo is clean. Commit or stash changes first.
- After switching, run:
```bash
clawdbot doctor
clawdbot daemon restart
```
### Telegram block streaming isn’t splitting text between tool calls. Why?
Block streaming only sends **completed text blocks**. Common reasons you see a single message:
- `agents.defaults.blockStreamingDefault` is still `"off"`.
- `channels.telegram.blockStreaming` is set to `false`.
- `channels.telegram.streamMode` is `partial` or `block` **and draft streaming is active**
(private chat + topics). Draft streaming disables block streaming in that case.
- Your `minChars` / coalesce settings are too high, so chunks get merged.
- The model emits one large text block (no mid‑reply flush points).
Fix checklist:
1) Put block streaming settings under `agents.defaults`, not the root.
2) Set `channels.telegram.streamMode: "off"` if you want real multi‑message block replies.
3) Use smaller chunk/coalesce thresholds while debugging.
See [Streaming](/concepts/streaming).
### Discord doesn’t reply in my server even with `requireMention: false`. Why?
`requireMention` only controls mention‑gating **after** the channel passes allowlists.
By default `channels.discord.groupPolicy` is **allowlist**, so guilds must be explicitly enabled.
If you set `channels.discord.guilds.<guildId>.channels`, only the listed channels are allowed; omit it to allow all channels in the guild.
Fix checklist:
1) Set `channels.discord.groupPolicy: "open"` **or** add a guild allowlist entry (and optionally a channel allowlist).
2) Use **numeric channel IDs** in `channels.discord.guilds.<guildId>.channels`.
3) Put `requireMention: false` **under** `channels.discord.guilds` (global or per‑channel).
Top‑level `channels.discord.requireMention` is not a supported key.
4) Ensure the bot has **Message Content Intent** and channel permissions.
5) Run `clawdbot channels status --probe` for audit hints.
Docs: [Discord](/channels/discord), [Channels troubleshooting](/channels/troubleshooting).
### Cloud Code Assist API error: invalid tool schema (400). What now?
This is almost always a **tool schema compatibility** issue. The Cloud Code Assist
endpoint accepts a strict subset of JSON Schema. Clawdbot scrubs/normalizes tool
schemas in current `main`, but the fix is not in the last release yet (as of
January 13, 2026).
Fix checklist:
1) **Update Clawdbot**:
- If you can run from source, pull `main` and restart the gateway.
- Otherwise, wait for the next release that includes the schema scrubber.
2) Avoid unsupported keywords like `anyOf/oneOf/allOf`, `patternProperties`,
`additionalProperties`, `minLength`, `maxLength`, `format`, etc.
3) If you define custom tools, keep the top‑level schema as `type: "object"` with
`properties` and simple enums.
See [Tools](/tools) and [TypeBox schemas](/concepts/typebox).
## macOS Specific Issues
### App Crashes when Granting Permissions (Speech/Mic)
-4
View File
@@ -160,15 +160,11 @@ clawdbot plugins install <path> # add a local file/dir to plugins.l
clawdbot plugins install ./extensions/voice-call # relative path ok
clawdbot plugins install ./plugin.tgz # install from a local tarball
clawdbot plugins install @clawdbot/voice-call # install from npm
clawdbot plugins update <id>
clawdbot plugins update --all
clawdbot plugins enable <id>
clawdbot plugins disable <id>
clawdbot plugins doctor
```
`plugins update` only works for npm installs tracked under `plugins.installs`.
Plugins may also register their own top‑level commands (example: `clawdbot voicecall`).
## Plugin API (overview)
+146 -80
View File
@@ -70,14 +70,11 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
- [I set `COPILOT_GITHUB_TOKEN`, but models status shows “Shell env: off.” Why?](#i-set-copilot_github_token-but-models-status-shows-shell-env-off-why)
- [Sessions & multiple chats](#sessions-multiple-chats)
- [How do I start a fresh conversation?](#how-do-i-start-a-fresh-conversation)
- [Do sessions reset automatically if I never send `/new`?](#do-sessions-reset-automatically-if-i-never-send-new)
- [How do I completely reset Clawdbot but keep it installed?](#how-do-i-completely-reset-clawdbot-but-keep-it-installed)
- [How do I completely reset Clawdbot (but keep it installed)?](#how-do-i-completely-reset-clawdbot-but-keep-it-installed)
- [I’m getting “context too large” errors — how do I reset or compact?](#im-getting-context-too-large-errors-how-do-i-reset-or-compact)
- [Why am I getting heartbeat messages every 30 minutes?](#why-am-i-getting-heartbeat-messages-every-30-minutes)
- [Do I need to add a “bot account” to a WhatsApp group?](#do-i-need-to-add-a-bot-account-to-a-whatsapp-group)
- [Why doesn’t Clawdbot reply in a group?](#why-doesnt-clawdbot-reply-in-a-group)
- [Do groups/threads share context with DMs?](#do-groupsthreads-share-context-with-dms)
- [How many workspaces and agents can I create?](#how-many-workspaces-and-agents-can-i-create)
- [Models: defaults, selection, aliases, switching](#models-defaults-selection-aliases-switching)
- [What is the “default model”?](#what-is-the-default-model)
- [How do I switch models on the fly (without restarting)?](#how-do-i-switch-models-on-the-fly-without-restarting)
@@ -110,17 +107,25 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
- [Logging and debugging](#logging-and-debugging)
- [Where are logs?](#where-are-logs)
- [How do I start/stop/restart the Gateway daemon?](#how-do-i-startstoprestart-the-gateway-daemon)
- [ELI5: `clawdbot daemon restart` vs `clawdbot gateway`](#eli5-clawdbot-daemon-restart-vs-clawdbot-gateway)
- [What’s the fastest way to get more details when something fails?](#whats-the-fastest-way-to-get-more-details-when-something-fails)
- [Media & attachments](#media-attachments)
- [My skill generated an image/PDF, but nothing was sent](#my-skill-generated-an-imagepdf-but-nothing-was-sent)
- [Security and access control](#security-and-access-control)
- [Is it safe to expose Clawdbot to inbound DMs?](#is-it-safe-to-expose-clawdbot-to-inbound-dms)
- [I ran `/start` in Telegram but didn’t get a pairing code](#i-ran-start-in-telegram-but-didnt-get-a-pairing-code)
- [WhatsApp: will it message my contacts? How does pairing work?](#whatsapp-will-it-message-my-contacts-how-does-pairing-work)
- [Chat commands, aborting tasks, and “it won’t stop”](#chat-commands-aborting-tasks-and-it-wont-stop)
- [How do I stop/cancel a running task?](#how-do-i-stopcancel-a-running-task)
- [Why does it feel like the bot “ignores” rapid‑fire messages?](#why-does-it-feel-like-the-bot-ignores-rapidfire-messages)
- [Common troubleshooting](#common-troubleshooting)
- [“All models failed” — what should I check first?](#all-models-failed-what-should-i-check-first)
- [I’m running on my personal WhatsApp number — why is self-chat weird?](#im-running-on-my-personal-whatsapp-number-why-is-self-chat-weird)
- [WhatsApp logged me out. How do I re‑auth?](#whatsapp-logged-me-out-how-do-i-reauth)
- [Build errors on `main` — what’s the standard fix path?](#build-errors-on-main-whats-the-standard-fix-path)
- [npm install fails (allow-build-scripts / missing tar or yargs). What now?](#npm-install-fails-allow-build-scripts--missing-tar-or-yargs-what-now)
- [How do I switch between git installs and npm installs?](#how-do-i-switch-between-git-installs-and-npm-installs)
- [Telegram block streaming isn’t splitting text between tool calls. Why?](#telegram-block-streaming-isnt-splitting-text-between-tool-calls-why)
- [Discord doesn’t reply in my server even with `requireMention: false`. Why?](#discord-doesnt-reply-in-my-server-even-with-requiremention-false-why)
- [Cloud Code Assist API error: invalid tool schema (400). What now?](#cloud-code-assist-api-error-invalid-tool-schema-400-what-now)
## First 60 seconds if something's broken
@@ -853,21 +858,7 @@ See [/concepts/model-providers](/concepts/model-providers) and [/environment](/e
Send `/new` or `/reset` as a standalone message. See [Session management](/concepts/session).
### Do sessions reset automatically if I never send `/new`?
Yes. Sessions expire after `session.idleMinutes` (default **60**). The **next**
message starts a fresh session id for that chat key. This does not delete
transcripts — it just starts a new session.
```json5
{
session: {
idleMinutes: 240
}
}
```
### How do I completely reset Clawdbot but keep it installed?
### How do I completely reset Clawdbot (but keep it installed)?
Use the reset command:
@@ -914,24 +905,6 @@ If it keeps happening:
Docs: [Compaction](/concepts/compaction), [Session pruning](/concepts/session-pruning), [Session management](/concepts/session).
### Why am I getting heartbeat messages every 30 minutes?
Heartbeats run every **30m** by default. Tune or disable them:
```json5
{
agents: {
defaults: {
heartbeat: {
every: "2h" // or "0m" to disable
}
}
}
}
```
Per-agent overrides use `agents.list[].heartbeat`. Docs: [Heartbeat](/gateway/heartbeat).
### Do I need to add a “bot account” to a WhatsApp group?
No. Clawdbot runs on **your own account**, so if you’re in the group, Clawdbot can see it.
@@ -962,19 +935,6 @@ See [Groups](/concepts/groups) and [Group messages](/concepts/group-messages).
Direct chats collapse to the main session by default. Groups/channels have their own session keys, and Telegram topics / Discord threads are separate sessions. See [Groups](/concepts/groups) and [Group messages](/concepts/group-messages).
### How many workspaces and agents can I create?
No hard limits. Dozens (even hundreds) are fine, but watch for:
- **Disk growth:** sessions + transcripts live under `~/.clawdbot/agents/<agentId>/sessions/`.
- **Token cost:** more agents means more concurrent model usage.
- **Ops overhead:** per-agent auth profiles, workspaces, and channel routing.
Tips:
- Keep one **active** workspace per agent (`agents.defaults.workspace`).
- Prune old sessions (delete JSONL or store entries) if disk grows.
- Use `clawdbot doctor` to spot stray workspaces and profile mismatches.
## Models: defaults, selection, aliases, switching
### What is the “default model”?
@@ -1355,11 +1315,9 @@ Facts (from code):
Fix:
- Fastest: `clawdbot dashboard` (prints + copies tokenized link, tries to open; shows SSH hint if headless).
- If you don’t have a token yet: `clawdbot doctor --generate-gateway-token`.
- If remote, tunnel first: `ssh -N -L 18789:127.0.0.1:18789 user@host` then open `http://127.0.0.1:18789/?token=...`.
- Set `gateway.auth.token` (or `CLAWDBOT_GATEWAY_TOKEN`) on the gateway host.
- In the Control UI settings, paste the same token (or refresh with a one-time `?token=...` link).
- Still stuck? Run `clawdbot status --all` and follow [Troubleshooting](/gateway/troubleshooting). See [Dashboard](/web/dashboard) for auth details.
### I set `gateway.bind: "tailnet"` but it can’t bind / nothing listens
@@ -1449,14 +1407,6 @@ clawdbot daemon restart
If you run the gateway manually, `clawdbot gateway --force` can reclaim the port. See [Gateway](/gateway).
### ELI5: `clawdbot daemon restart` vs `clawdbot gateway`
- `clawdbot daemon restart`: restarts the **background service** (launchd/systemd).
- `clawdbot gateway`: runs the gateway **in the foreground** for this terminal session.
If you installed the daemon, use the daemon commands. Use `clawdbot gateway` when
you want a one-off, foreground run.
### What’s the fastest way to get more details when something fails?
Start the Gateway with `--verbose` to get more console detail. Then inspect the log file for channel auth, model routing, and RPC errors.
@@ -1473,11 +1423,7 @@ CLI sending:
clawdbot message send --to +15555550123 --message "Here you go" --media /path/to/file.png
```
Also check:
- The target channel supports outbound media and isn’t blocked by allowlists.
- The file is within the provider’s size limits (images are resized to max 2048px).
See [Images](/nodes/images).
Note: images are resized/recompressed (max side 2048px) to hit size limits. See [Images](/nodes/images).
## Security and access control
@@ -1493,19 +1439,6 @@ Treat inbound DMs as untrusted input. Defaults are designed to reduce risk:
Run `clawdbot doctor` to surface risky DM policies.
### I ran `/start` in Telegram but didn’t get a pairing code
Pairing codes are sent **only** when an unknown sender messages the bot and
`dmPolicy: "pairing"` is enabled. `/start` by itself doesn’t generate a code.
Check pending requests:
```bash
clawdbot pairing list telegram
```
If you want immediate access, allowlist your sender id or set `dmPolicy: "open"`
for that account.
### WhatsApp: will it message my contacts? How does pairing work?
No. Default WhatsApp DM policy is **pairing**. Unknown senders only get a pairing code and their message is **not processed**. Clawdbot only replies to chats it receives or to explicit sends you trigger.
@@ -1563,6 +1496,139 @@ Queue mode controls how new messages interact with an in‑flight run. Use `/que
You can add options like `debounce:2s cap:25 drop:summarize` for followup modes.
## Common troubleshooting
### “All models failed” — what should I check first?
- **Credentials** present for the provider(s) being tried (auth profiles + env vars).
- **Model routing**: confirm `agents.defaults.model.primary` and fallbacks are models you can access.
- **Gateway logs** in `/tmp/clawdbot/…` for the exact provider error.
- **`/model status`** to see current configured models + shorthands.
### I’m running on my personal WhatsApp number — why is self-chat weird?
Enable self-chat mode and allowlist your own number:
```json5
{
channels: {
whatsapp: {
selfChatMode: true,
dmPolicy: "allowlist",
allowFrom: ["+15555550123"]
}
}
}
```
See [WhatsApp setup](/channels/whatsapp).
### WhatsApp logged me out. How do I re‑auth?
Run the login command again and scan the QR code:
```bash
clawdbot channels login
```
### Build errors on `main` — what’s the standard fix path?
1) `git pull origin main && pnpm install`
2) `pnpm clawdbot doctor`
3) Check GitHub issues or Discord
4) Temporary workaround: check out an older commit
### npm install fails (allow-build-scripts / missing tar or yargs). What now?
If you’re running from source, use the repo’s package manager: **pnpm** (preferred).
The repo declares `packageManager: "pnpm@…"`, and pnpm patches are tracked in `pnpm.patchedDependencies`.
Typical recovery:
```bash
git status # ensure you’re in the repo root
pnpm install
pnpm build
pnpm clawdbot doctor
clawdbot daemon restart
```
Why: pnpm is the configured package manager for this repo, and the dependency
patching workflow relies on it.
### How do I switch between git installs and npm installs?
Use the **website installer** and select the install method with a flag. It
upgrades in place and rewrites the gateway service to point at the new install.
Switch **to git install**:
```bash
curl -fsSL https://clawd.bot/install.sh | bash -s -- --install-method git --no-onboard
```
Switch **to npm global**:
```bash
curl -fsSL https://clawd.bot/install.sh | bash
```
Notes:
- The git flow only rebases if the repo is clean. Commit or stash changes first.
- After switching, run:
```bash
clawdbot doctor
clawdbot daemon restart
```
### Telegram block streaming isn’t splitting text between tool calls. Why?
Block streaming only sends **completed text blocks**. Common reasons you see a single message:
- `agents.defaults.blockStreamingDefault` is still `"off"`.
- `channels.telegram.blockStreaming` is set to `false`.
- `channels.telegram.streamMode` is `partial` or `block` **and draft streaming is active**
(private chat + topics). Draft streaming disables block streaming in that case.
- Your `minChars` / coalesce settings are too high, so chunks get merged.
- The model emits one large text block (no mid‑reply flush points).
Fix checklist:
1) Put block streaming settings under `agents.defaults`, not the root.
2) Set `channels.telegram.streamMode: "off"` if you want real multi‑message block replies.
3) Use smaller chunk/coalesce thresholds while debugging.
See [Streaming](/concepts/streaming).
### Discord doesn’t reply in my server even with `requireMention: false`. Why?
`requireMention` only controls mention‑gating **after** the channel passes allowlists.
By default `channels.discord.groupPolicy` is **allowlist**, so guilds must be explicitly enabled.
If you set `channels.discord.guilds.<guildId>.channels`, only the listed channels are allowed; omit it to allow all channels in the guild.
Fix checklist:
1) Set `channels.discord.groupPolicy: "open"` **or** add a guild allowlist entry (and optionally a channel allowlist).
2) Use **numeric channel IDs** in `channels.discord.guilds.<guildId>.channels`.
3) Put `requireMention: false` **under** `channels.discord.guilds` (global or per‑channel).
Top‑level `channels.discord.requireMention` is not a supported key.
4) Ensure the bot has **Message Content Intent** and channel permissions.
5) Run `clawdbot channels status --probe` for audit hints.
Docs: [Discord](/channels/discord), [Channels troubleshooting](/channels/troubleshooting).
### Cloud Code Assist API error: invalid tool schema (400). What now?
This is almost always a **tool schema compatibility** issue. The Cloud Code Assist
endpoint accepts a strict subset of JSON Schema. Clawdbot scrubs/normalizes tool
schemas in current `main`, but the fix is not in the last release yet (as of
January 13, 2026).
Fix checklist:
1) **Update Clawdbot**:
- If you can run from source, pull `main` and restart the gateway.
- Otherwise, wait for the next release that includes the schema scrubber.
2) Avoid unsupported keywords like `anyOf/oneOf/allOf`, `patternProperties`,
`additionalProperties`, `minLength`, `maxLength`, `format`, etc.
3) If you define custom tools, keep the top‑level schema as `type: "object"` with
`properties` and simple enums.
See [Tools](/tools) and [TypeBox schemas](/concepts/typebox).
## Answer the exact question from the screenshot/chat log
**Q: “What’s the default model for Anthropic with an API key?”**
-2
View File
@@ -68,8 +68,6 @@ Tip: `--json` does **not** imply non-interactive mode. Use `--non-interactive` (
1) **Existing config detection**
- If `~/.clawdbot/clawdbot.json` exists, choose **Keep / Modify / Reset**.
- Re-running the wizard does **not** wipe anything unless you explicitly choose **Reset**
(or pass `--reset`).
- If the config is invalid or contains legacy keys, the wizard stops and asks
you to run `clawdbot doctor` before continuing.
- Reset uses `trash` (never `rm`) and offers scopes:
@@ -112,18 +112,3 @@ curl -s http://127.0.0.1:18791/tabs
| `browser.noSandbox` | Add `--no-sandbox` flag (needed for some Linux setups) | `false` |
| `browser.attachOnly` | Don't launch browser, only attach to existing | `false` |
| `browser.cdpPort` | Chrome DevTools Protocol port | `18800` |
### Problem: "Chrome extension relay is running, but no tab is connected"
You’re using the `chrome` profile (extension relay). It expects the Clawdbot
browser extension to be attached to a live tab.
Fix options:
1. **Use the managed browser:** `clawdbot browser start --browser-profile clawd`
(or set `browser.defaultProfile: "clawd"`).
2. **Use the extension relay:** install the extension, open a tab, and click the
Clawdbot extension icon to attach it.
Notes:
- The `chrome` profile uses your **system default Chromium browser** when possible.
- Local `clawd` profiles auto-assign `cdpPort`/`cdpUrl`; only set those for remote CDP.
+3 -67
View File
@@ -14,10 +14,8 @@ control server.
Beginner view:
- Think of it as a **separate, agent-only browser**.
- The `clawd` profile does **not** touch your personal browser profile.
- It does **not** touch your personal browser profile.
- The agent can **open tabs, read pages, click, and type** in a safe lane.
- The default `chrome` profile uses the **system default Chromium browser** via the
extension relay; switch to `clawd` for the isolated managed browser.
## What you get
@@ -41,14 +39,6 @@ clawdbot browser --browser-profile clawd snapshot
If you get “Browser disabled”, enable it in config (see below) and restart the
Gateway.
## Profiles: `clawd` vs `chrome`
- `clawd`: managed, isolated browser (no extension required).
- `chrome`: extension relay to your **system browser** (requires the Clawdbot
extension to be attached to a tab).
Set `browser.defaultProfile: "clawd"` if you want managed mode by default.
## Configuration
Browser settings live in `~/.clawdbot/clawdbot.json`.
@@ -59,8 +49,6 @@ Browser settings live in `~/.clawdbot/clawdbot.json`.
enabled: true, // default: true
controlUrl: "http://127.0.0.1:18791",
cdpUrl: "http://127.0.0.1:18792", // defaults to controlUrl + 1
remoteCdpTimeoutMs: 1500, // remote CDP HTTP timeout (ms)
remoteCdpHandshakeTimeoutMs: 3000, // remote CDP WebSocket handshake timeout (ms)
defaultProfile: "chrome",
color: "#FF4500",
headless: false,
@@ -81,25 +69,13 @@ Notes:
- If you override the Gateway port (`gateway.port` or `CLAWDBOT_GATEWAY_PORT`),
the default browser ports shift to stay in the same “family” (control = gateway + 2).
- `cdpUrl` defaults to `controlUrl + 1` when unset.
- `remoteCdpTimeoutMs` applies to remote (non-loopback) CDP reachability checks.
- `remoteCdpHandshakeTimeoutMs` applies to remote CDP WebSocket reachability checks.
- `attachOnly: true` means “never launch a local browser; only attach if it is already running.”
- `color` + per-profile `color` tint the browser UI so you can see which profile is active.
- Default profile is `chrome` (extension relay). Use `defaultProfile: "clawd"` for the managed browser.
- Auto-detect order: system default browser if Chromium-based; otherwise Chrome → Brave → Edge → Chromium → Chrome Canary.
- Local `clawd` profiles auto-assign `cdpPort`/`cdpUrl` — set those only for remote CDP.
- Auto-detect order: default browser if Chromium-based; otherwise Chrome → Brave → Edge → Chromium → Chrome Canary.
## Use Brave (or another Chromium-based browser)
If your **system default** browser is Chromium-based (Chrome/Brave/Edge/etc),
Clawdbot uses it automatically. Set `browser.executablePath` to override
auto-detection:
CLI example:
```bash
clawdbot config set browser.executablePath "/usr/bin/google-chrome"
```
Set `browser.executablePath` to override auto-detection:
```json5
// macOS
@@ -158,42 +134,6 @@ Example:
Use `profiles.<name>.cdpUrl` for **remote CDP** if you want the Gateway to talk
directly to a Chromium-based browser instance without a remote control server.
Remote CDP URLs can include auth:
- Query tokens (e.g., `https://provider.example?token=<token>`)
- HTTP Basic auth (e.g., `https://user:pass@provider.example`)
Clawdbot preserves the auth when calling `/json/*` endpoints and when connecting
to the CDP WebSocket. Prefer environment variables or secrets managers for
tokens instead of committing them to config files.
### Browserless (hosted remote CDP)
[Browserless](https://browserless.io) is a hosted Chromium service that exposes
CDP endpoints over HTTPS. You can point a Clawdbot browser profile at a
Browserless region endpoint and authenticate with your API key.
Example:
```json5
{
browser: {
enabled: true,
defaultProfile: "browserless",
remoteCdpTimeoutMs: 2000,
remoteCdpHandshakeTimeoutMs: 4000,
profiles: {
browserless: {
cdpUrl: "https://production-sfo.browserless.io?token=<BROWSERLESS_API_KEY>",
color: "#00AA00"
}
}
}
}
```
Notes:
- Replace `<BROWSERLESS_API_KEY>` with your real Browserless token.
- Choose the region endpoint that matches your Browserless account (see their docs).
### Running the control server on the browser machine
Run a standalone browser control server (recommended when your Gateway is remote):
@@ -399,10 +339,6 @@ Playwright. If Playwright isn’t installed, those endpoints return a clear 501
error. ARIA snapshots and basic screenshots still work for clawd-managed Chrome.
For the Chrome extension relay driver, ARIA snapshots and screenshots require Playwright.
If you see `Playwright is not available in this gateway build`, install the full
Playwright package (not `playwright-core`) and restart the gateway, or reinstall
Clawdbot with browser support.
## How it works (internal)
High-level flow:
+7 -25
View File
@@ -206,31 +206,6 @@ if [[ "$NO_SIGN" -ne 1 && -f "${LAUNCHAGENT_DISABLE_MARKER}" ]]; then
run_step "clear launchagent disable marker" /bin/rm -f "${LAUNCHAGENT_DISABLE_MARKER}"
fi
# When unsigned, ensure the gateway LaunchAgent targets the repo CLI (before the app launches).
# This reduces noisy "could not connect" errors during app startup.
if [ "$NO_SIGN" -eq 1 ]; then
run_step "install gateway launch agent (unsigned)" bash -lc "cd '${ROOT_DIR}' && node dist/entry.js daemon install --force --runtime node"
run_step "restart gateway daemon (unsigned)" bash -lc "cd '${ROOT_DIR}' && node dist/entry.js daemon restart"
if [[ "${GATEWAY_WAIT_SECONDS}" -gt 0 ]]; then
run_step "wait for gateway (unsigned)" sleep "${GATEWAY_WAIT_SECONDS}"
fi
GATEWAY_PORT="$(
node -e '
const fs = require("node:fs");
const path = require("node:path");
try {
const raw = fs.readFileSync(path.join(process.env.HOME, ".clawdbot", "clawdbot.json"), "utf8");
const cfg = JSON.parse(raw);
const port = cfg && cfg.gateway && typeof cfg.gateway.port === "number" ? cfg.gateway.port : 18789;
process.stdout.write(String(port));
} catch {
process.stdout.write("18789");
}
'
)"
run_step "verify gateway port ${GATEWAY_PORT} (unsigned)" bash -lc "lsof -iTCP:${GATEWAY_PORT} -sTCP:LISTEN | head -n 5 || true"
fi
# 4) Launch the installed app in the foreground so the menu bar extra appears.
# LaunchServices can inherit a huge environment from this shell (secrets, prompt vars, etc.).
# That can cause launchd spawn failures and is undesirable for a GUI app anyway.
@@ -251,6 +226,13 @@ else
fail "App exited immediately. Check ${LOG_PATH} or Console.app (User Reports)."
fi
# When unsigned, ensure the gateway LaunchAgent targets the repo CLI (after the app launches).
if [ "$NO_SIGN" -eq 1 ]; then
run_step "install gateway launch agent (unsigned)" bash -lc "cd '${ROOT_DIR}' && node dist/entry.js daemon install --force --runtime node"
run_step "restart gateway daemon (unsigned)" bash -lc "cd '${ROOT_DIR}' && node dist/entry.js daemon restart"
if [[ "${GATEWAY_WAIT_SECONDS}" -gt 0 ]]; then
run_step "wait for gateway (unsigned)" sleep "${GATEWAY_WAIT_SECONDS}"
fi
run_step "verify gateway port 18789 (unsigned)" bash -lc "lsof -iTCP:18789 -sTCP:LISTEN | head -n 5 || true"
run_step "show gateway launch agent args (unsigned)" bash -lc "/usr/bin/plutil -p '${HOME}/Library/LaunchAgents/com.clawdbot.gateway.plist' | head -n 40 || true"
fi
+1 -41
View File
@@ -19,53 +19,13 @@ open ~/Projects/tmp/openai-image-gen-*/index.html # if ~/Projects/tmp exists; e
Useful flags:
```bash
# GPT image models with various options
python3 {baseDir}/scripts/gen.py --count 16 --model gpt-image-1
python3 {baseDir}/scripts/gen.py --prompt "ultra-detailed studio photo of a lobster astronaut" --count 4
python3 {baseDir}/scripts/gen.py --size 1536x1024 --quality high --out-dir ./out/images
python3 {baseDir}/scripts/gen.py --model gpt-image-1.5 --background transparent --output-format webp
# DALL-E 3 (note: count is automatically limited to 1)
python3 {baseDir}/scripts/gen.py --model dall-e-3 --quality hd --size 1792x1024 --style vivid
python3 {baseDir}/scripts/gen.py --model dall-e-3 --style natural --prompt "serene mountain landscape"
# DALL-E 2
python3 {baseDir}/scripts/gen.py --model dall-e-2 --size 512x512 --count 4
```
## Model-Specific Parameters
Different models support different parameter values. The script automatically selects appropriate defaults based on the model.
### Size
- **GPT image models** (`gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`): `1024x1024`, `1536x1024` (landscape), `1024x1536` (portrait), or `auto`
- Default: `1024x1024`
- **dall-e-3**: `1024x1024`, `1792x1024`, or `1024x1792`
- Default: `1024x1024`
- **dall-e-2**: `256x256`, `512x512`, or `1024x1024`
- Default: `1024x1024`
### Quality
- **GPT image models**: `auto`, `high`, `medium`, or `low`
- Default: `high`
- **dall-e-3**: `hd` or `standard`
- Default: `standard`
- **dall-e-2**: `standard` only
- Default: `standard`
### Other Notable Differences
- **dall-e-3** only supports generating 1 image at a time (`n=1`). The script automatically limits count to 1 when using this model.
- **GPT image models** support additional parameters:
- `--background`: `transparent`, `opaque`, or `auto` (default)
- `--output-format`: `png` (default), `jpeg`, or `webp`
- Note: `stream` and `moderation` are available via API but not yet implemented in this script
- **dall-e-3** has a `--style` parameter: `vivid` (hyper-real, dramatic) or `natural` (more natural looking)
## Output
- `*.png`, `*.jpeg`, or `*.webp` images (output format depends on model + `--output-format`)
- `*.png` images
- `prompts.json` (prompt → file mapping)
- `index.html` (thumbnail gallery)
+17 -74
View File
@@ -62,53 +62,24 @@ def pick_prompts(count: int) -> list[str]:
return prompts
def get_model_defaults(model: str) -> tuple[str, str]:
"""Return (default_size, default_quality) for the given model."""
if model == "dall-e-2":
# quality will be ignored
return ("1024x1024", "standard")
elif model == "dall-e-3":
return ("1024x1024", "standard")
else:
# GPT image or future models
return ("1024x1024", "high")
def request_images(
api_key: str,
prompt: str,
model: str,
size: str,
quality: str,
background: str = "",
output_format: str = "",
style: str = "",
) -> dict:
url = "https://api.openai.com/v1/images/generations"
args = {
"model": model,
"prompt": prompt,
"size": size,
"n": 1,
}
# Quality parameter - dall-e-2 doesn't accept this parameter
if model != "dall-e-2":
args["quality"] = quality
if model.startswith("dall-e"):
args["response_format"] = "b64_json"
if model.startswith("gpt-image"):
if background:
args["background"] = background
if output_format:
args["output_format"] = output_format
if model == "dall-e-3" and style:
args["style"] = style
body = json.dumps(args).encode("utf-8")
body = json.dumps(
{
"model": model,
"prompt": prompt,
"size": size,
"quality": quality,
"n": 1,
"response_format": "b64_json",
}
).encode("utf-8")
req = urllib.request.Request(
url,
method="POST",
@@ -165,11 +136,8 @@ def main() -> int:
ap.add_argument("--prompt", help="Single prompt. If omitted, random prompts are generated.")
ap.add_argument("--count", type=int, default=8, help="How many images to generate.")
ap.add_argument("--model", default="gpt-image-1", help="Image model id.")
ap.add_argument("--size", default="", help="Image size (e.g. 1024x1024, 1536x1024). Defaults based on model if not specified.")
ap.add_argument("--quality", default="", help="Image quality (e.g. high, standard). Defaults based on model if not specified.")
ap.add_argument("--background", default="", help="Background transparency (GPT models only): transparent, opaque, or auto.")
ap.add_argument("--output-format", default="", help="Output format (GPT models only): png, jpeg, or webp.")
ap.add_argument("--style", default="", help="Image style (dall-e-3 only): vivid or natural.")
ap.add_argument("--size", default="1024x1024", help="Image size (e.g. 1024x1024, 1536x1024).")
ap.add_argument("--quality", default="high", help="Image quality (varies by model).")
ap.add_argument("--out-dir", default="", help="Output directory (default: ./tmp/openai-image-gen-<ts>).")
args = ap.parse_args()
@@ -178,46 +146,21 @@ def main() -> int:
print("Missing OPENAI_API_KEY", file=sys.stderr)
return 2
# Apply model-specific defaults if not specified
default_size, default_quality = get_model_defaults(args.model)
size = args.size or default_size
quality = args.quality or default_quality
count = args.count
if args.model == "dall-e-3" and count > 1:
print(f"Warning: dall-e-3 only supports generating 1 image at a time. Reducing count from {count} to 1.", file=sys.stderr)
count = 1
out_dir = Path(args.out_dir).expanduser() if args.out_dir else default_out_dir()
out_dir.mkdir(parents=True, exist_ok=True)
prompts = [args.prompt] * count if args.prompt else pick_prompts(count)
# Determine file extension based on output format
if args.model.startswith("gpt-image") and args.output_format:
file_ext = args.output_format
else:
file_ext = "png"
prompts = [args.prompt] * args.count if args.prompt else pick_prompts(args.count)
items: list[dict] = []
for idx, prompt in enumerate(prompts, start=1):
print(f"[{idx}/{len(prompts)}] {prompt}")
res = request_images(
api_key,
prompt,
args.model,
size,
quality,
args.background,
args.output_format,
args.style,
)
res = request_images(api_key, prompt, args.model, args.size, args.quality)
b64 = res.get("data", [{}])[0].get("b64_json")
if not b64:
raise RuntimeError(f"Unexpected response: {json.dumps(res)[:400]}")
image_bytes = base64.b64decode(b64)
filename = f"{idx:03d}-{slugify(prompt)[:40]}.{file_ext}"
(out_dir / filename).write_bytes(image_bytes)
png = base64.b64decode(b64)
filename = f"{idx:03d}-{slugify(prompt)[:40]}.png"
(out_dir / filename).write_bytes(png)
items.append({"prompt": prompt, "file": filename})
(out_dir / "prompts.json").write_text(json.dumps(items, indent=2), encoding="utf-8")
@@ -99,7 +99,6 @@ describe("session_status tool", () => {
expect(details.ok).toBe(true);
expect(details.statusText).toContain("Clawdbot");
expect(details.statusText).toContain("🧠 Model:");
expect(details.statusText).not.toContain("OAuth/token status");
});
it("errors for unknown session keys", async () => {
+1
View File
@@ -77,6 +77,7 @@ export function createClawdbotTools(options?: {
createNodesTool(),
createCronTool({
agentSessionKey: options?.agentSessionKey,
config: options?.config,
}),
createMessageTool({
agentAccountId: options?.agentAccountId,
+5 -42
View File
@@ -9,63 +9,26 @@ import type { EmbeddedContextFile } from "./types.js";
type ContentBlockWithSignature = {
thought_signature?: unknown;
thoughtSignature?: unknown;
[key: string]: unknown;
};
type ThoughtSignatureSanitizeOptions = {
allowBase64Only?: boolean;
includeCamelCase?: boolean;
};
function isBase64Signature(value: string): boolean {
const trimmed = value.trim();
if (!trimmed) return false;
const compact = trimmed.replace(/\s+/g, "");
if (!/^[A-Za-z0-9+/=_-]+$/.test(compact)) return false;
const isUrl = compact.includes("-") || compact.includes("_");
try {
const buf = Buffer.from(compact, isUrl ? "base64url" : "base64");
if (buf.length === 0) return false;
const encoded = buf.toString(isUrl ? "base64url" : "base64");
const normalize = (input: string) => input.replace(/=+$/g, "");
return normalize(encoded) === normalize(compact);
} catch {
return false;
}
}
/**
* Strips Claude-style thought_signature fields from content blocks.
*
* Gemini expects thought signatures as base64-encoded bytes, but Claude stores message ids
* like "msg_abc123...". We only strip "msg_*" to preserve any provider-valid signatures.
*/
export function stripThoughtSignatures<T>(
content: T,
options?: ThoughtSignatureSanitizeOptions,
): T {
export function stripThoughtSignatures<T>(content: T): T {
if (!Array.isArray(content)) return content;
const allowBase64Only = options?.allowBase64Only ?? false;
const includeCamelCase = options?.includeCamelCase ?? false;
const shouldStripSignature = (value: unknown): boolean => {
if (!allowBase64Only) {
return typeof value === "string" && value.startsWith("msg_");
}
return typeof value !== "string" || !isBase64Signature(value);
};
return content.map((block) => {
if (!block || typeof block !== "object") return block;
const rec = block as ContentBlockWithSignature;
const stripSnake = shouldStripSignature(rec.thought_signature);
const stripCamel = includeCamelCase ? shouldStripSignature(rec.thoughtSignature) : false;
if (!stripSnake && !stripCamel) {
const signature = rec.thought_signature;
if (typeof signature !== "string" || !signature.startsWith("msg_")) {
return block;
}
const next = { ...rec };
if (stripSnake) delete next.thought_signature;
if (stripCamel) delete next.thoughtSignature;
return next;
const { thought_signature: _signature, ...rest } = rec;
return rest;
}) as T;
}
+1 -3
View File
@@ -23,7 +23,6 @@ export { sanitizeGoogleTurnOrdering };
type GeminiToolCallBlock = {
type?: unknown;
thought_signature?: unknown;
thoughtSignature?: unknown;
id?: unknown;
toolCallId?: unknown;
name?: unknown;
@@ -119,8 +118,7 @@ export function downgradeGeminiHistory(messages: AgentMessage[]): AgentMessage[]
const blockRecord = block as GeminiToolCallBlock;
const type = blockRecord.type;
if (type === "toolCall" || type === "functionCall" || type === "toolUse") {
const signature = blockRecord.thought_signature ?? blockRecord.thoughtSignature;
const hasSignature = Boolean(signature);
const hasSignature = Boolean(blockRecord.thought_signature);
if (!hasSignature) {
const id =
typeof blockRecord.id === "string"
+1 -5
View File
@@ -34,10 +34,6 @@ export async function sanitizeSessionMessagesImages(
sanitizeToolCallIds?: boolean;
enforceToolCallLast?: boolean;
preserveSignatures?: boolean;
sanitizeThoughtSignatures?: {
allowBase64Only?: boolean;
includeCamelCase?: boolean;
};
},
): Promise<AgentMessage[]> {
// We sanitize historical session messages because Anthropic can reject a request
@@ -86,7 +82,7 @@ export async function sanitizeSessionMessagesImages(
if (Array.isArray(content)) {
const strippedContent = options?.preserveSignatures
? content // Keep signatures for Antigravity Claude
: stripThoughtSignatures(content, options?.sanitizeThoughtSignatures); // Strip for Gemini
: stripThoughtSignatures(content); // Strip for Gemini
const filteredContent = strippedContent.filter((block) => {
if (!block || typeof block !== "object") return true;
@@ -145,65 +145,6 @@ describe("sanitizeSessionHistory (google thinking)", () => {
expect(assistant.content?.[1]?.text).toBe("internal note");
});
it("strips non-base64 thought signatures for OpenRouter Gemini", async () => {
const sessionManager = SessionManager.inMemory();
const input = [
{
role: "user",
content: "hi",
},
{
role: "assistant",
content: [
{ type: "text", text: "hello", thought_signature: "msg_abc123" },
{ type: "thinking", thinking: "ok", thought_signature: "c2ln" },
{
type: "toolCall",
id: "call_1",
name: "read",
arguments: { path: "/tmp/foo" },
thoughtSignature: '{"id":1}',
},
{
type: "toolCall",
id: "call_2",
name: "read",
arguments: { path: "/tmp/bar" },
thoughtSignature: "c2ln",
},
],
},
] satisfies AgentMessage[];
const out = await sanitizeSessionHistory({
messages: input,
modelApi: "openrouter",
provider: "openrouter",
modelId: "google/gemini-1.5-pro",
sessionManager,
sessionId: "session:openrouter-gemini",
});
const assistant = out.find((msg) => (msg as { role?: string }).role === "assistant") as {
content?: Array<{ type?: string; thought_signature?: string; thoughtSignature?: string }>;
};
expect(assistant.content).toEqual([
{ type: "text", text: "hello" },
{ type: "text", text: "ok" },
{
type: "text",
text: '[Tool Call: read (ID: call_1)]\nArguments: {\n "path": "/tmp/foo"\n}',
},
{
type: "toolCall",
id: "call_2",
name: "read",
arguments: { path: "/tmp/bar" },
thoughtSignature: "c2ln",
},
]);
});
it("downgrades only unsigned thinking blocks when mixed with signed ones", async () => {
const sessionManager = SessionManager.inMemory();
const input = [
@@ -261,64 +261,4 @@ describe("runEmbeddedPiAgent", () => {
expect(secondUserIndex).toBeGreaterThan(firstAssistantIndex);
expect(secondAssistantIndex).toBeGreaterThan(secondUserIndex);
}, 20_000);
it("returns role ordering error when session ends with a user turn", async () => {
const { SessionManager } = await import("@mariozechner/pi-coding-agent");
const agentDir = await fs.mkdtemp(path.join(os.tmpdir(), "clawdbot-agent-"));
const workspaceDir = await fs.mkdtemp(path.join(os.tmpdir(), "clawdbot-workspace-"));
const sessionFile = path.join(workspaceDir, "session.jsonl");
const sessionManager = SessionManager.open(sessionFile);
sessionManager.appendMessage({
role: "user",
content: [{ type: "text", text: "seed user 1" }],
});
sessionManager.appendMessage({
role: "assistant",
content: [{ type: "text", text: "seed assistant" }],
stopReason: "stop",
api: "openai-responses",
provider: "openai",
model: "mock-1",
usage: {
input: 1,
output: 1,
cacheRead: 0,
cacheWrite: 0,
totalTokens: 2,
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
total: 0,
},
},
timestamp: Date.now(),
});
sessionManager.appendMessage({
role: "user",
content: [{ type: "text", text: "seed user 2" }],
});
const cfg = makeOpenAiConfig(["mock-1"]);
await ensureModels(cfg, agentDir);
const result = await runEmbeddedPiAgent({
sessionId: "session:test",
sessionKey: "agent:main:main",
sessionFile,
workspaceDir,
config: cfg,
prompt: "hello",
provider: "openai",
model: "mock-1",
timeoutMs: 5_000,
agentDir,
});
expect(result.meta.error?.kind).toBe("role_ordering");
expect(result.meta.error?.message).toMatch(/incorrect role information|roles must alternate/i);
expect(result.payloads?.[0]?.text).toContain("Message ordering conflict");
});
});
@@ -1,105 +0,0 @@
import type { AgentMessage } from "@mariozechner/pi-agent-core";
import type { SessionManager } from "@mariozechner/pi-coding-agent";
import { beforeEach, describe, expect, it, vi } from "vitest";
import * as helpers from "./pi-embedded-helpers.js";
import { sanitizeSessionHistory } from "./pi-embedded-runner/google.js";
// Mock dependencies
vi.mock("./pi-embedded-helpers.js", async () => {
const actual = await vi.importActual("./pi-embedded-helpers.js");
return {
...actual,
isGoogleModelApi: vi.fn(),
downgradeGeminiHistory: vi.fn(),
sanitizeSessionMessagesImages: vi.fn().mockImplementation(async (msgs) => msgs),
};
});
// We don't mock session-transcript-repair.js as it is a pure function and complicates mocking.
// We rely on the real implementation which should pass through our simple messages.
describe("sanitizeSessionHistory", () => {
const mockSessionManager = {
getEntries: vi.fn().mockReturnValue([]),
appendCustomEntry: vi.fn(),
} as unknown as SessionManager;
const mockMessages: AgentMessage[] = [{ role: "user", content: "hello" }];
beforeEach(() => {
vi.resetAllMocks();
vi.mocked(helpers.sanitizeSessionMessagesImages).mockImplementation(async (msgs) => msgs);
// Default mock implementation
vi.mocked(helpers.downgradeGeminiHistory).mockImplementation((msgs) => {
if (!msgs) return [];
return [...msgs, { role: "system", content: "downgraded" }];
});
});
it("should downgrade history for Google models if provider is not google-antigravity", async () => {
vi.mocked(helpers.isGoogleModelApi).mockReturnValue(true);
const result = await sanitizeSessionHistory({
messages: mockMessages,
modelApi: "google-gemini",
provider: "google-vertex",
sessionManager: mockSessionManager,
sessionId: "test-session",
});
expect(helpers.isGoogleModelApi).toHaveBeenCalledWith("google-gemini");
expect(helpers.downgradeGeminiHistory).toHaveBeenCalled();
// Check if the result contains the downgraded message
expect(result).toContainEqual({ role: "system", content: "downgraded" });
});
it("should NOT downgrade history for google-antigravity provider", async () => {
vi.mocked(helpers.isGoogleModelApi).mockReturnValue(true);
const result = await sanitizeSessionHistory({
messages: mockMessages,
modelApi: "google-gemini",
provider: "google-antigravity",
sessionManager: mockSessionManager,
sessionId: "test-session",
});
expect(helpers.isGoogleModelApi).toHaveBeenCalledWith("google-gemini");
expect(helpers.downgradeGeminiHistory).not.toHaveBeenCalled();
// Result should not contain the downgraded message
expect(result).not.toContainEqual({
role: "system",
content: "downgraded",
});
});
it("should NOT downgrade history for non-Google models", async () => {
vi.mocked(helpers.isGoogleModelApi).mockReturnValue(false);
const _result = await sanitizeSessionHistory({
messages: mockMessages,
modelApi: "anthropic-messages",
provider: "anthropic",
sessionManager: mockSessionManager,
sessionId: "test-session",
});
expect(helpers.isGoogleModelApi).toHaveBeenCalledWith("anthropic-messages");
expect(helpers.downgradeGeminiHistory).not.toHaveBeenCalled();
});
it("should downgrade history if provider is undefined but model is Google", async () => {
vi.mocked(helpers.isGoogleModelApi).mockReturnValue(true);
const _result = await sanitizeSessionHistory({
messages: mockMessages,
modelApi: "google-gemini",
provider: undefined,
sessionManager: mockSessionManager,
sessionId: "test-session",
});
expect(helpers.isGoogleModelApi).toHaveBeenCalledWith("google-gemini");
expect(helpers.downgradeGeminiHistory).toHaveBeenCalled();
});
});
+2 -8
View File
@@ -44,11 +44,7 @@ import {
} from "../skills.js";
import { filterBootstrapFilesForSession, loadWorkspaceBootstrapFiles } from "../workspace.js";
import { buildEmbeddedExtensionPaths } from "./extensions.js";
import {
logToolSchemasForGoogle,
sanitizeSessionHistory,
sanitizeToolsForGoogle,
} from "./google.js";
import { logToolSchemasForGoogle, sanitizeSessionHistory } from "./google.js";
import { getDmHistoryLimitFromSessionKey, limitHistoryTurns } from "./history.js";
import { resolveGlobalLane, resolveSessionLane } from "./lanes.js";
import { log } from "./logger.js";
@@ -187,7 +183,7 @@ export async function compactEmbeddedPiSession(params: {
warn: (message) => log.warn(`${message} (sessionKey=${sessionLabel})`),
});
const runAbortController = new AbortController();
const toolsRaw = createClawdbotCodingTools({
const tools = createClawdbotCodingTools({
exec: {
...resolveExecToolDefaults(params.config),
elevated: params.bashElevated,
@@ -204,7 +200,6 @@ export async function compactEmbeddedPiSession(params: {
modelId,
modelAuthMode: resolveModelAuthMode(model.provider, params.config),
});
const tools = sanitizeToolsForGoogle({ tools: toolsRaw, provider });
logToolSchemasForGoogle({ tools, provider });
const machineName = await getMachineDisplayName();
const runtimeChannel = normalizeMessageChannel(
@@ -308,7 +303,6 @@ export async function compactEmbeddedPiSession(params: {
messages: session.messages,
modelApi: model.api,
modelId,
provider,
sessionManager,
sessionId: params.sessionId,
});
@@ -1,37 +0,0 @@
import { describe, expect, it } from "vitest";
import type { AgentTool } from "@mariozechner/pi-agent-core";
import { sanitizeToolsForGoogle } from "./google.js";
describe("sanitizeToolsForGoogle", () => {
it("strips unsupported schema keywords for Google providers", () => {
const tool = {
name: "test",
description: "test",
parameters: {
type: "object",
additionalProperties: false,
properties: {
foo: {
type: "string",
format: "uuid",
},
},
},
execute: async () => ({ ok: true, content: [] }),
} as unknown as AgentTool;
const [sanitized] = sanitizeToolsForGoogle({
tools: [tool],
provider: "google-gemini-cli",
});
const params = sanitized.parameters as {
additionalProperties?: unknown;
properties?: Record<string, { format?: unknown }>;
};
expect(params.additionalProperties).toBeUndefined();
expect(params.properties?.foo?.format).toBeUndefined();
});
});
+5 -41
View File
@@ -1,5 +1,4 @@
import type { AgentMessage, AgentTool } from "@mariozechner/pi-agent-core";
import type { TSchema } from "@sinclair/typebox";
import type { SessionManager } from "@mariozechner/pi-coding-agent";
import { registerUnhandledRejectionHandler } from "../../infra/unhandled-rejections.js";
@@ -15,7 +14,6 @@ import { sanitizeToolUseResultPairing } from "../session-transcript-repair.js";
import { log } from "./logger.js";
import { describeUnknownError } from "./utils.js";
import { isAntigravityClaude } from "../pi-embedded-helpers/google.js";
import { cleanToolSchemaForGemini } from "../pi-tools.schema.js";
const GOOGLE_TURN_ORDERING_CUSTOM_TYPE = "google-turn-ordering-bootstrap";
const GOOGLE_SCHEMA_UNSUPPORTED_KEYWORDS = new Set([
@@ -82,39 +80,17 @@ function findUnsupportedSchemaKeywords(schema: unknown, path: string): string[]
return violations;
}
export function sanitizeToolsForGoogle<
TSchemaType extends TSchema = TSchema,
TResult = unknown,
>(params: {
tools: AgentTool<TSchemaType, TResult>[];
provider: string;
}): AgentTool<TSchemaType, TResult>[] {
if (params.provider !== "google-antigravity" && params.provider !== "google-gemini-cli") {
return params.tools;
}
return params.tools.map((tool) => {
if (!tool.parameters || typeof tool.parameters !== "object") return tool;
return {
...tool,
parameters: cleanToolSchemaForGemini(
tool.parameters as Record<string, unknown>,
) as TSchemaType,
};
});
}
export function logToolSchemasForGoogle(params: { tools: AgentTool[]; provider: string }) {
if (params.provider !== "google-antigravity" && params.provider !== "google-gemini-cli") {
return;
}
const toolNames = params.tools.map((tool, index) => `${index}:${tool.name}`);
const tools = sanitizeToolsForGoogle(params);
log.info("google tool schema snapshot", {
provider: params.provider,
toolCount: tools.length,
toolCount: params.tools.length,
tools: toolNames,
});
for (const [index, tool] of tools.entries()) {
for (const [index, tool] of params.tools.entries()) {
const violations = findUnsupportedSchemaKeywords(tool.parameters, `${tool.name}.parameters`);
if (violations.length > 0) {
log.warn("google tool schema has unsupported keywords", {
@@ -188,34 +164,22 @@ export async function sanitizeSessionHistory(params: {
messages: AgentMessage[];
modelApi?: string | null;
modelId?: string;
provider?: string;
sessionManager: SessionManager;
sessionId: string;
}): Promise<AgentMessage[]> {
const isAntigravityClaudeModel = isAntigravityClaude(params.modelApi, params.modelId);
const provider = (params.provider ?? "").toLowerCase();
const modelId = (params.modelId ?? "").toLowerCase();
const isOpenRouterGemini =
(provider === "openrouter" || provider === "opencode") && modelId.includes("gemini");
const isGeminiLike = isGoogleModelApi(params.modelApi) || isOpenRouterGemini;
const sanitizedImages = await sanitizeSessionMessagesImages(params.messages, "session:history", {
sanitizeToolCallIds: shouldSanitizeToolCallIds(params.modelApi),
enforceToolCallLast: params.modelApi === "anthropic-messages",
preserveSignatures: params.modelApi === "google-antigravity" && isAntigravityClaudeModel,
sanitizeThoughtSignatures: isOpenRouterGemini
? { allowBase64Only: true, includeCamelCase: true }
: undefined,
});
const repairedTools = sanitizeToolUseResultPairing(sanitizedImages);
const isAntigravityProvider =
provider === "google-antigravity" || params.modelApi === "google-antigravity";
const shouldDowngradeThinking = isGeminiLike && !isAntigravityClaudeModel;
const shouldDowngradeGemini = isGoogleModelApi(params.modelApi) && !isAntigravityClaudeModel;
// Gemini rejects unsigned thinking blocks; downgrade them before send to avoid INVALID_ARGUMENT.
const downgradedThinking = shouldDowngradeThinking
const downgradedThinking = shouldDowngradeGemini
? downgradeGeminiThinkingBlocks(repairedTools)
: repairedTools;
const shouldDowngradeHistory = shouldDowngradeThinking && !isAntigravityProvider;
const downgraded = shouldDowngradeHistory
const downgraded = shouldDowngradeGemini
? downgradeGeminiHistory(downgradedThinking)
: downgradedThinking;
-2
View File
@@ -274,8 +274,6 @@ export async function runEmbeddedPiAgent(
provider,
model: model.id,
},
systemPromptReport: attempt.systemPromptReport,
error: { kind: "role_ordering", message: errorText },
},
};
}
+2 -8
View File
@@ -45,11 +45,7 @@ import { filterBootstrapFilesForSession, loadWorkspaceBootstrapFiles } from "../
import { isAbortError } from "../abort.js";
import { buildEmbeddedExtensionPaths } from "../extensions.js";
import { applyExtraParamsToAgent } from "../extra-params.js";
import {
logToolSchemasForGoogle,
sanitizeSessionHistory,
sanitizeToolsForGoogle,
} from "../google.js";
import { logToolSchemasForGoogle, sanitizeSessionHistory } from "../google.js";
import { getDmHistoryLimitFromSessionKey, limitHistoryTurns } from "../history.js";
import { log } from "../logger.js";
import { buildModelAliasLines } from "../model.js";
@@ -131,7 +127,7 @@ export async function runEmbeddedAttempt(
const agentDir = params.agentDir ?? resolveClawdbotAgentDir();
const toolsRaw = createClawdbotCodingTools({
const tools = createClawdbotCodingTools({
exec: {
...resolveExecToolDefaults(params.config),
elevated: params.bashElevated,
@@ -152,7 +148,6 @@ export async function runEmbeddedAttempt(
replyToMode: params.replyToMode,
hasRepliedRef: params.hasRepliedRef,
});
const tools = sanitizeToolsForGoogle({ tools: toolsRaw, provider: params.provider });
logToolSchemasForGoogle({ tools, provider: params.provider });
const machineName = await getMachineDisplayName();
@@ -323,7 +318,6 @@ export async function runEmbeddedAttempt(
messages: activeSession.messages,
modelApi: params.model.api,
modelId: params.modelId,
provider: params.provider,
sessionManager,
sessionId: params.sessionId,
});
+1 -1
View File
@@ -20,7 +20,7 @@ export type EmbeddedPiRunMeta = {
aborted?: boolean;
systemPromptReport?: SessionSystemPromptReport;
error?: {
kind: "context_overflow" | "compaction_failure" | "role_ordering";
kind: "context_overflow" | "compaction_failure";
message: string;
};
};
@@ -14,7 +14,7 @@ export function handleAgentStart(ctx: EmbeddedPiSubscribeContext) {
startedAt: Date.now(),
},
});
void ctx.params.onAgentEvent?.({
ctx.params.onAgentEvent?.({
stream: "lifecycle",
data: { phase: "start" },
});
@@ -24,7 +24,7 @@ export function handleAutoCompactionStart(ctx: EmbeddedPiSubscribeContext) {
ctx.state.compactionInFlight = true;
ctx.ensureCompactionPromise();
ctx.log.debug(`embedded run compaction start: runId=${ctx.params.runId}`);
void ctx.params.onAgentEvent?.({
ctx.params.onAgentEvent?.({
stream: "compaction",
data: { phase: "start" },
});
@@ -43,7 +43,7 @@ export function handleAutoCompactionEnd(
} else {
ctx.maybeResolveCompactionWait();
}
void ctx.params.onAgentEvent?.({
ctx.params.onAgentEvent?.({
stream: "compaction",
data: { phase: "end", willRetry },
});
@@ -59,7 +59,7 @@ export function handleAgentEnd(ctx: EmbeddedPiSubscribeContext) {
endedAt: Date.now(),
},
});
void ctx.params.onAgentEvent?.({
ctx.params.onAgentEvent?.({
stream: "lifecycle",
data: { phase: "end" },
});
@@ -118,7 +118,7 @@ export function handleMessageUpdate(
mediaUrls: mediaUrls?.length ? mediaUrls : undefined,
},
});
void ctx.params.onAgentEvent?.({
ctx.params.onAgentEvent?.({
stream: "assistant",
data: {
text: cleanedText,
@@ -11,7 +11,7 @@ import {
} from "./pi-embedded-subscribe.tools.js";
import { inferToolMetaFromArgs } from "./pi-embedded-utils.js";
export async function handleToolExecutionStart(
export function handleToolExecutionStart(
ctx: EmbeddedPiSubscribeContext,
evt: AgentEvent & { toolName: string; toolCallId: string; args: unknown },
) {
@@ -53,8 +53,7 @@ export async function handleToolExecutionStart(
args: args as Record<string, unknown>,
},
});
// Await onAgentEvent to ensure typing indicator starts before tool summaries are emitted.
await ctx.params.onAgentEvent?.({
ctx.params.onAgentEvent?.({
stream: "tool",
data: { phase: "start", name: toolName, toolCallId },
});
@@ -109,7 +108,7 @@ export function handleToolExecutionUpdate(
partialResult: sanitized,
},
});
void ctx.params.onAgentEvent?.({
ctx.params.onAgentEvent?.({
stream: "tool",
data: {
phase: "update",
@@ -171,7 +170,7 @@ export function handleToolExecutionEnd(
result: sanitizedResult,
},
});
void ctx.params.onAgentEvent?.({
ctx.params.onAgentEvent?.({
stream: "tool",
data: {
phase: "result",
+1 -5
View File
@@ -32,11 +32,7 @@ export function createEmbeddedPiSessionEventHandler(ctx: EmbeddedPiSubscribeCont
handleMessageEnd(ctx, evt as never);
return;
case "tool_execution_start":
// Async handler - awaits typing indicator before emitting tool summaries.
// Catch rejections to avoid unhandled promise rejection crashes.
handleToolExecutionStart(ctx, evt as never).catch((err) => {
ctx.log.debug(`tool_execution_start handler failed: ${String(err)}`);
});
handleToolExecutionStart(ctx, evt as never);
return;
case "tool_execution_update":
handleToolExecutionUpdate(ctx, evt as never);
@@ -13,7 +13,7 @@ describe("subscribeEmbeddedPiSession", () => {
{ tag: "antthinking", open: "<antthinking>", close: "</antthinking>" },
] as const;
it("includes canvas action metadata in tool summaries", async () => {
it("includes canvas action metadata in tool summaries", () => {
let handler: ((evt: unknown) => void) | undefined;
const session: StubSession = {
subscribe: (fn) => {
@@ -38,9 +38,6 @@ describe("subscribeEmbeddedPiSession", () => {
args: { action: "a2ui_push", jsonlPath: "/tmp/a2ui.jsonl" },
});
// Wait for async handler to complete
await Promise.resolve();
expect(onToolResult).toHaveBeenCalledTimes(1);
const payload = onToolResult.mock.calls[0][0];
expect(payload.text).toContain("🖼️");
@@ -75,7 +72,7 @@ describe("subscribeEmbeddedPiSession", () => {
expect(onToolResult).not.toHaveBeenCalled();
});
it("emits tool summaries when shouldEmitToolResult overrides verbose", async () => {
it("emits tool summaries when shouldEmitToolResult overrides verbose", () => {
let handler: ((evt: unknown) => void) | undefined;
const session: StubSession = {
subscribe: (fn) => {
@@ -101,9 +98,6 @@ describe("subscribeEmbeddedPiSession", () => {
args: { path: "/tmp/c.txt" },
});
// Wait for async handler to complete
await Promise.resolve();
expect(onToolResult).toHaveBeenCalledTimes(1);
});
});
@@ -14,7 +14,7 @@ describe("subscribeEmbeddedPiSession", () => {
{ tag: "antthinking", open: "<antthinking>", close: "</antthinking>" },
] as const;
it("suppresses message_end block replies when the message tool already sent", async () => {
it("suppresses message_end block replies when the message tool already sent", () => {
let handler: ((evt: unknown) => void) | undefined;
const session: StubSession = {
subscribe: (fn) => {
@@ -41,9 +41,6 @@ describe("subscribeEmbeddedPiSession", () => {
args: { action: "send", to: "+1555", message: messageText },
});
// Wait for async handler to complete
await Promise.resolve();
handler?.({
type: "tool_execution_end",
toolName: "message",
@@ -61,7 +58,7 @@ describe("subscribeEmbeddedPiSession", () => {
expect(onBlockReply).not.toHaveBeenCalled();
});
it("does not suppress message_end replies when message tool reports error", async () => {
it("does not suppress message_end replies when message tool reports error", () => {
let handler: ((evt: unknown) => void) | undefined;
const session: StubSession = {
subscribe: (fn) => {
@@ -88,9 +85,6 @@ describe("subscribeEmbeddedPiSession", () => {
args: { action: "send", to: "+1555", message: messageText },
});
// Wait for async handler to complete
await Promise.resolve();
handler?.({
type: "tool_execution_end",
toolName: "message",
@@ -54,7 +54,7 @@ describe("subscribeEmbeddedPiSession", () => {
await waitPromise;
expect(resolved).toBe(true);
});
it("emits tool summaries at tool start when verbose is on", async () => {
it("emits tool summaries at tool start when verbose is on", () => {
let handler: ((evt: unknown) => void) | undefined;
const session: StubSession = {
subscribe: (fn) => {
@@ -79,9 +79,6 @@ describe("subscribeEmbeddedPiSession", () => {
args: { path: "/tmp/a.txt" },
});
// Wait for async handler to complete
await Promise.resolve();
expect(onToolResult).toHaveBeenCalledTimes(1);
const payload = onToolResult.mock.calls[0][0];
expect(payload.text).toContain("/tmp/a.txt");
@@ -96,7 +93,7 @@ describe("subscribeEmbeddedPiSession", () => {
expect(onToolResult).toHaveBeenCalledTimes(1);
});
it("includes browser action metadata in tool summaries", async () => {
it("includes browser action metadata in tool summaries", () => {
let handler: ((evt: unknown) => void) | undefined;
const session: StubSession = {
subscribe: (fn) => {
@@ -121,9 +118,6 @@ describe("subscribeEmbeddedPiSession", () => {
args: { action: "snapshot", targetUrl: "https://example.com" },
});
// Wait for async handler to complete
await Promise.resolve();
expect(onToolResult).toHaveBeenCalledTimes(1);
const payload = onToolResult.mock.calls[0][0];
expect(payload.text).toContain("🌐");
+1 -1
View File
@@ -22,7 +22,7 @@ export type SubscribeEmbeddedPiSessionParams = {
blockReplyChunking?: BlockReplyChunking;
onPartialReply?: (payload: { text?: string; mediaUrls?: string[] }) => void | Promise<void>;
onAssistantMessageStart?: () => void | Promise<void>;
onAgentEvent?: (evt: { stream: string; data: Record<string, unknown> }) => void | Promise<void>;
onAgentEvent?: (evt: { stream: string; data: Record<string, unknown> }) => void;
enforceFinalTag?: boolean;
};
-2
View File
@@ -51,8 +51,6 @@ function buildSandboxBrowserResolvedConfig(params: {
cdpProtocol: "http",
cdpHost,
cdpIsLoopback: true,
remoteCdpTimeoutMs: 1500,
remoteCdpHandshakeTimeoutMs: 3000,
color: DEFAULT_CLAWD_BROWSER_COLOR,
executablePath: undefined,
headless: params.headless,
+2 -2
View File
@@ -102,7 +102,7 @@ export function ensureSkillsWatcher(params: { workspaceDir: string; config?: Cla
if (!watchEnabled) {
if (existing) {
watchers.delete(workspaceDir);
if (existing.timer) clearTimeout(existing.timer);
existing.timer && clearTimeout(existing.timer);
void existing.watcher.close().catch(() => {});
}
return;
@@ -115,7 +115,7 @@ export function ensureSkillsWatcher(params: { workspaceDir: string; config?: Cla
}
if (existing) {
watchers.delete(workspaceDir);
if (existing.timer) clearTimeout(existing.timer);
existing.timer && clearTimeout(existing.timer);
void existing.watcher.close().catch(() => {});
}
+1 -1
View File
@@ -99,7 +99,7 @@ describe("cron tool", () => {
})
.mockResolvedValueOnce({ ok: true });
const tool = createCronTool({ agentSessionKey: "main" });
const tool = createCronTool({ agentSessionKey: "main", config: {} });
await tool.execute("call3", {
action: "add",
job: {
+5 -2
View File
@@ -1,6 +1,6 @@
import { Type } from "@sinclair/typebox";
import { normalizeCronJobCreate, normalizeCronJobPatch } from "../../cron/normalize.js";
import { loadConfig } from "../../config/config.js";
import { loadConfig, type ClawdbotConfig } from "../../config/config.js";
import { truncateUtf16Safe } from "../../utils.js";
import { optionalStringEnum, stringEnum } from "../schema/typebox.js";
import { type AnyAgentTool, jsonResult, readStringParam } from "./common.js";
@@ -38,6 +38,7 @@ const CronToolSchema = Type.Object({
type CronToolOptions = {
agentSessionKey?: string;
config?: ClawdbotConfig;
};
type ChatMessage = {
@@ -86,10 +87,11 @@ function extractMessageText(message: ChatMessage): { role: string; text: string
async function buildReminderContextLines(params: {
agentSessionKey?: string;
gatewayOpts: GatewayCallOptions;
config?: ClawdbotConfig;
}) {
const sessionKey = params.agentSessionKey?.trim();
if (!sessionKey) return [];
const cfg = loadConfig();
const cfg = params.config ?? loadConfig();
const { mainKey, alias } = resolveMainSessionAlias(cfg);
const resolvedKey = resolveInternalSessionKey({ key: sessionKey, alias, mainKey });
try {
@@ -160,6 +162,7 @@ export function createCronTool(opts?: CronToolOptions): AnyAgentTool {
const contextLines = await buildReminderContextLines({
agentSessionKey: opts?.agentSessionKey,
gatewayOpts,
config: opts?.config,
});
if (contextLines.length > 0) {
const baseText = stripExistingContext(payload.text);
+9 -9
View File
@@ -219,7 +219,7 @@ export async function handleDiscordGuildAction(
return jsonResult({ ok: true, event });
}
case "channelCreate": {
if (!isActionEnabled("channels")) {
if (!isActionEnabled("channels", false)) {
throw new Error("Discord channel management is disabled.");
}
const guildId = readStringParam(params, "guildId", { required: true });
@@ -241,7 +241,7 @@ export async function handleDiscordGuildAction(
return jsonResult({ ok: true, channel });
}
case "channelEdit": {
if (!isActionEnabled("channels")) {
if (!isActionEnabled("channels", false)) {
throw new Error("Discord channel management is disabled.");
}
const channelId = readStringParam(params, "channelId", {
@@ -267,7 +267,7 @@ export async function handleDiscordGuildAction(
return jsonResult({ ok: true, channel });
}
case "channelDelete": {
if (!isActionEnabled("channels")) {
if (!isActionEnabled("channels", false)) {
throw new Error("Discord channel management is disabled.");
}
const channelId = readStringParam(params, "channelId", {
@@ -277,7 +277,7 @@ export async function handleDiscordGuildAction(
return jsonResult(result);
}
case "channelMove": {
if (!isActionEnabled("channels")) {
if (!isActionEnabled("channels", false)) {
throw new Error("Discord channel management is disabled.");
}
const guildId = readStringParam(params, "guildId", { required: true });
@@ -295,7 +295,7 @@ export async function handleDiscordGuildAction(
return jsonResult({ ok: true });
}
case "categoryCreate": {
if (!isActionEnabled("channels")) {
if (!isActionEnabled("channels", false)) {
throw new Error("Discord channel management is disabled.");
}
const guildId = readStringParam(params, "guildId", { required: true });
@@ -310,7 +310,7 @@ export async function handleDiscordGuildAction(
return jsonResult({ ok: true, category: channel });
}
case "categoryEdit": {
if (!isActionEnabled("channels")) {
if (!isActionEnabled("channels", false)) {
throw new Error("Discord channel management is disabled.");
}
const categoryId = readStringParam(params, "categoryId", {
@@ -326,7 +326,7 @@ export async function handleDiscordGuildAction(
return jsonResult({ ok: true, category: channel });
}
case "categoryDelete": {
if (!isActionEnabled("channels")) {
if (!isActionEnabled("channels", false)) {
throw new Error("Discord channel management is disabled.");
}
const categoryId = readStringParam(params, "categoryId", {
@@ -336,7 +336,7 @@ export async function handleDiscordGuildAction(
return jsonResult(result);
}
case "channelPermissionSet": {
if (!isActionEnabled("channels")) {
if (!isActionEnabled("channels", false)) {
throw new Error("Discord channel management is disabled.");
}
const channelId = readStringParam(params, "channelId", {
@@ -359,7 +359,7 @@ export async function handleDiscordGuildAction(
return jsonResult({ ok: true });
}
case "channelPermissionRemove": {
if (!isActionEnabled("channels")) {
if (!isActionEnabled("channels", false)) {
throw new Error("Discord channel management is disabled.");
}
const channelId = readStringParam(params, "channelId", {
+71 -14
View File
@@ -1,5 +1,6 @@
import { Type } from "@sinclair/typebox";
import { resolveAgentDir } from "../../agents/agent-scope.js";
import { buildAuthHealthSummary, formatRemainingShort } from "../../agents/auth-health.js";
import {
ensureAuthProfileStore,
resolveAuthProfileDisplayLabel,
@@ -31,6 +32,7 @@ import {
formatUsageWindowSummary,
loadProviderUsageSummary,
resolveUsageProviderId,
type UsageProviderId,
} from "../../infra/provider-usage.js";
import {
buildAgentMainSessionKey,
@@ -281,33 +283,48 @@ export function createSessionStatusTool(opts?: {
defaultModel: DEFAULT_MODEL,
});
const providerForCard = resolved.entry.providerOverride?.trim() || configured.provider;
const usageProvider = resolveUsageProviderId(providerForCard);
let usageLine: string | undefined;
if (usageProvider) {
const authStore = ensureAuthProfileStore(agentDir, { allowKeychainPrompt: false });
const authHealth = buildAuthHealthSummary({
store: authStore,
cfg,
});
const oauthProfiles = authHealth.profiles.filter(
(profile) => profile.type === "oauth" || profile.type === "token",
);
const usageProviders = Array.from(
new Set(
oauthProfiles
.map((profile) => resolveUsageProviderId(profile.provider))
.filter((provider): provider is UsageProviderId => Boolean(provider)),
),
);
const usageByProvider = new Map<string, string>();
if (usageProviders.length > 0) {
try {
const usageSummary = await loadProviderUsageSummary({
timeoutMs: 3500,
providers: [usageProvider],
providers: usageProviders,
agentDir,
});
const snapshot = usageSummary.providers.find(
(entry) => entry.provider === usageProvider,
);
if (snapshot) {
for (const snapshot of usageSummary.providers) {
const formatted = formatUsageWindowSummary(snapshot, {
now: Date.now(),
maxWindows: 2,
includeResets: true,
});
if (formatted && !formatted.startsWith("error:")) {
usageLine = `📊 Usage: ${formatted}`;
}
if (formatted) usageByProvider.set(snapshot.provider, formatted);
}
} catch {
// ignore
}
}
const usageProvider = resolveUsageProviderId(providerForCard);
const usageLine =
oauthProfiles.length === 0 && usageProvider && usageByProvider.has(usageProvider)
? `📊 Usage: ${usageByProvider.get(usageProvider)}`
: undefined;
const isGroup =
resolved.entry.chatType === "group" ||
resolved.entry.chatType === "room" ||
@@ -353,13 +370,53 @@ export function createSessionStatusTool(opts?: {
includeTranscriptUsage: false,
});
const authStatusLines = (() => {
if (oauthProfiles.length === 0) return [];
const formatStatus = (status: string) => {
if (status === "ok") return "ok";
if (status === "static") return "static";
if (status === "expiring") return "expiring";
if (status === "missing") return "unknown";
return "expired";
};
const profilesByProvider = new Map<string, typeof oauthProfiles>();
for (const profile of oauthProfiles) {
const current = profilesByProvider.get(profile.provider);
if (current) current.push(profile);
else profilesByProvider.set(profile.provider, [profile]);
}
const lines: string[] = ["OAuth/token status"];
for (const [provider, profiles] of profilesByProvider) {
const usageKey = resolveUsageProviderId(provider);
const usage = usageKey ? usageByProvider.get(usageKey) : undefined;
const usageSuffix = usage ? ` — usage: ${usage}` : "";
lines.push(`- ${provider}${usageSuffix}`);
for (const profile of profiles) {
const labelText = profile.label || profile.profileId;
const status = formatStatus(profile.status);
const expiry =
profile.status === "static"
? ""
: profile.expiresAt
? ` expires in ${formatRemainingShort(profile.remainingMs)}`
: " expires unknown";
const source = profile.source !== "store" ? ` (${profile.source})` : "";
lines.push(` - ${labelText} ${status}${expiry}${source}`);
}
}
return lines;
})();
const fullStatusText =
authStatusLines.length > 0 ? `${statusText}\n\n${authStatusLines.join("\n")}` : statusText;
return {
content: [{ type: "text", text: statusText }],
content: [{ type: "text", text: fullStatusText }],
details: {
ok: true,
sessionKey: resolved.key,
changedModel,
statusText,
statusText: fullStatusText,
},
};
},
+51 -90
View File
@@ -26,7 +26,7 @@ import type { VerboseLevel } from "../thinking.js";
import { isSilentReplyText, SILENT_REPLY_TOKEN } from "../tokens.js";
import type { GetReplyOptions, ReplyPayload } from "../types.js";
import { buildThreadingToolContext, resolveEnforceFinalTag } from "./agent-runner-utils.js";
import { createBlockReplyPayloadKey, type BlockReplyPipeline } from "./block-reply-pipeline.js";
import type { BlockReplyPipeline } from "./block-reply-pipeline.js";
import type { FollowupRun } from "./queue.js";
import { parseReplyDirectives } from "./reply-directives.js";
import { applyReplyTagsToPayload, isRenderablePayload } from "./reply-payloads.js";
@@ -40,8 +40,6 @@ export type AgentRunLoopResult =
fallbackModel?: string;
didLogHeartbeatStrip: boolean;
autoCompactionCompleted: boolean;
/** Payload keys sent directly (not via pipeline) during tool flush. */
directlySentBlockKeys?: Set<string>;
}
| { kind: "final"; payload: ReplyPayload };
@@ -63,7 +61,6 @@ export async function runAgentTurnWithFallback(params: {
shouldEmitToolResult: () => boolean;
pendingToolTasks: Set<Promise<void>>;
resetSessionAfterCompactionFailure: (reason: string) => Promise<boolean>;
resetSessionAfterRoleOrderingConflict: (reason: string) => Promise<boolean>;
isHeartbeat: boolean;
sessionKey?: string;
getActiveSessionEntry: () => SessionEntry | undefined;
@@ -73,8 +70,6 @@ export async function runAgentTurnWithFallback(params: {
}): Promise<AgentRunLoopResult> {
let didLogHeartbeatStrip = false;
let autoCompactionCompleted = false;
// Track payloads sent directly (not via pipeline) during tool flush to avoid duplicates.
const directlySentBlockKeys = new Set<string>();
const runId = crypto.randomUUID();
if (params.sessionKey) {
@@ -249,13 +244,12 @@ export async function runAgentTurnWithFallback(params: {
});
}
: undefined,
onAgentEvent: async (evt) => {
// Trigger typing when tools start executing.
// Must await to ensure typing indicator starts before tool summaries are emitted.
onAgentEvent: (evt) => {
// Trigger typing when tools start executing
if (evt.stream === "tool") {
const phase = typeof evt.data.phase === "string" ? evt.data.phase : "";
if (phase === "start" || phase === "update") {
await params.typingSignals.signalToolStart();
void params.typingSignals.signalToolStart();
}
}
// Track auto-compaction completion
@@ -267,67 +261,57 @@ export async function runAgentTurnWithFallback(params: {
}
}
},
// Always pass onBlockReply so flushBlockReplyBuffer works before tool execution,
// even when regular block streaming is disabled. The handler sends directly
// via opts.onBlockReply when the pipeline isn't available.
onBlockReply: params.opts?.onBlockReply
? async (payload) => {
const { text, skip } = normalizeStreamingText(payload);
const hasPayloadMedia = (payload.mediaUrls?.length ?? 0) > 0;
if (skip && !hasPayloadMedia) return;
const taggedPayload = applyReplyTagsToPayload(
{
text,
mediaUrls: payload.mediaUrls,
mediaUrl: payload.mediaUrls?.[0],
},
params.sessionCtx.MessageSid,
);
// Let through payloads with audioAsVoice flag even if empty (need to track it)
if (!isRenderablePayload(taggedPayload) && !payload.audioAsVoice) return;
const parsed = parseReplyDirectives(taggedPayload.text ?? "", {
currentMessageId: params.sessionCtx.MessageSid,
silentToken: SILENT_REPLY_TOKEN,
});
const cleaned = parsed.text || undefined;
const hasRenderableMedia =
Boolean(taggedPayload.mediaUrl) || (taggedPayload.mediaUrls?.length ?? 0) > 0;
// Skip empty payloads unless they have audioAsVoice flag (need to track it)
if (
!cleaned &&
!hasRenderableMedia &&
!payload.audioAsVoice &&
!parsed.audioAsVoice
)
return;
if (parsed.isSilent && !hasRenderableMedia) return;
onBlockReply:
params.blockStreamingEnabled && params.opts?.onBlockReply
? async (payload) => {
const { text, skip } = normalizeStreamingText(payload);
const hasPayloadMedia = (payload.mediaUrls?.length ?? 0) > 0;
if (skip && !hasPayloadMedia) return;
const taggedPayload = applyReplyTagsToPayload(
{
text,
mediaUrls: payload.mediaUrls,
mediaUrl: payload.mediaUrls?.[0],
},
params.sessionCtx.MessageSid,
);
// Let through payloads with audioAsVoice flag even if empty (need to track it)
if (!isRenderablePayload(taggedPayload) && !payload.audioAsVoice) return;
const parsed = parseReplyDirectives(taggedPayload.text ?? "", {
currentMessageId: params.sessionCtx.MessageSid,
silentToken: SILENT_REPLY_TOKEN,
});
const cleaned = parsed.text || undefined;
const hasRenderableMedia =
Boolean(taggedPayload.mediaUrl) || (taggedPayload.mediaUrls?.length ?? 0) > 0;
// Skip empty payloads unless they have audioAsVoice flag (need to track it)
if (
!cleaned &&
!hasRenderableMedia &&
!payload.audioAsVoice &&
!parsed.audioAsVoice
)
return;
if (parsed.isSilent && !hasRenderableMedia) return;
const blockPayload: ReplyPayload = params.applyReplyToMode({
...taggedPayload,
text: cleaned,
audioAsVoice: Boolean(parsed.audioAsVoice || payload.audioAsVoice),
replyToId: taggedPayload.replyToId ?? parsed.replyToId,
replyToTag: taggedPayload.replyToTag || parsed.replyToTag,
replyToCurrent: taggedPayload.replyToCurrent || parsed.replyToCurrent,
});
void params.typingSignals
.signalTextDelta(cleaned ?? taggedPayload.text)
.catch((err) => {
logVerbose(`block reply typing signal failed: ${String(err)}`);
const blockPayload: ReplyPayload = params.applyReplyToMode({
...taggedPayload,
text: cleaned,
audioAsVoice: Boolean(parsed.audioAsVoice || payload.audioAsVoice),
replyToId: taggedPayload.replyToId ?? parsed.replyToId,
replyToTag: taggedPayload.replyToTag || parsed.replyToTag,
replyToCurrent: taggedPayload.replyToCurrent || parsed.replyToCurrent,
});
// Use pipeline if available (block streaming enabled), otherwise send directly
if (params.blockStreamingEnabled && params.blockReplyPipeline) {
params.blockReplyPipeline.enqueue(blockPayload);
} else {
// Send directly when flushing before tool execution (no streaming).
// Track sent key to avoid duplicate in final payloads.
directlySentBlockKeys.add(createBlockReplyPayloadKey(blockPayload));
await params.opts?.onBlockReply?.(blockPayload);
void params.typingSignals
.signalTextDelta(cleaned ?? taggedPayload.text)
.catch((err) => {
logVerbose(`block reply typing signal failed: ${String(err)}`);
});
params.blockReplyPipeline?.enqueue(blockPayload);
}
}
: undefined,
: undefined,
onBlockReplyFlush:
params.blockStreamingEnabled && blockReplyPipeline
? async () => {
@@ -377,17 +361,6 @@ export async function runAgentTurnWithFallback(params: {
didResetAfterCompactionFailure = true;
continue;
}
if (embeddedError?.kind === "role_ordering") {
const didReset = await params.resetSessionAfterRoleOrderingConflict(embeddedError.message);
if (didReset) {
return {
kind: "final",
payload: {
text: "⚠️ Message ordering conflict. I've reset the conversation - please try again.",
},
};
}
}
break;
} catch (err) {
@@ -407,17 +380,6 @@ export async function runAgentTurnWithFallback(params: {
didResetAfterCompactionFailure = true;
continue;
}
if (isRoleOrderingError) {
const didReset = await params.resetSessionAfterRoleOrderingConflict(message);
if (didReset) {
return {
kind: "final",
payload: {
text: "⚠️ Message ordering conflict. I've reset the conversation - please try again.",
},
};
}
}
// Auto-recover from Gemini session corruption by resetting the session
if (
@@ -485,6 +447,5 @@ export async function runAgentTurnWithFallback(params: {
fallbackModel,
didLogHeartbeatStrip,
autoCompactionCompleted,
directlySentBlockKeys: directlySentBlockKeys.size > 0 ? directlySentBlockKeys : undefined,
};
}
@@ -5,7 +5,7 @@ import type { OriginatingChannelType } from "../templating.js";
import { SILENT_REPLY_TOKEN } from "../tokens.js";
import type { ReplyPayload } from "../types.js";
import { formatBunFetchSocketError, isBunFetchSocketError } from "./agent-runner-utils.js";
import { createBlockReplyPayloadKey, type BlockReplyPipeline } from "./block-reply-pipeline.js";
import type { BlockReplyPipeline } from "./block-reply-pipeline.js";
import { parseReplyDirectives } from "./reply-directives.js";
import {
applyReplyThreading,
@@ -20,8 +20,6 @@ export function buildReplyPayloads(params: {
didLogHeartbeatStrip: boolean;
blockStreamingEnabled: boolean;
blockReplyPipeline: BlockReplyPipeline | null;
/** Payload keys sent directly (not via pipeline) during tool flush. */
directlySentBlockKeys?: Set<string>;
replyToMode: ReplyToMode;
replyToChannel?: OriginatingChannelType;
currentMessageId?: string;
@@ -100,16 +98,11 @@ export function buildReplyPayloads(params: {
payloads: replyTaggedPayloads,
sentTexts: messagingToolSentTexts,
});
// Filter out payloads already sent via pipeline or directly during tool flush.
const filteredPayloads = shouldDropFinalPayloads
? []
: params.blockStreamingEnabled
? dedupedPayloads.filter((payload) => !params.blockReplyPipeline?.hasSentPayload(payload))
: params.directlySentBlockKeys?.size
? dedupedPayloads.filter(
(payload) => !params.directlySentBlockKeys!.has(createBlockReplyPayloadKey(payload)),
)
: dedupedPayloads;
: dedupedPayloads;
const replyPayloads = suppressMessagingToolReplies ? [] : filteredPayloads;
return {
@@ -3,7 +3,6 @@ import { tmpdir } from "node:os";
import path from "node:path";
import { describe, expect, it, vi } from "vitest";
import type { SessionEntry } from "../../config/sessions.js";
import * as sessions from "../../config/sessions.js";
import type { TypingMode } from "../../config/types.js";
import type { TemplateContext } from "../templating.js";
import type { GetReplyOptions } from "../types.js";
@@ -128,14 +127,11 @@ describe("runReplyAgent typing (heartbeat)", () => {
try {
const sessionId = "session";
const storePath = path.join(stateDir, "sessions", "sessions.json");
const transcriptPath = sessions.resolveSessionTranscriptPath(sessionId);
const sessionEntry = { sessionId, updatedAt: Date.now(), sessionFile: transcriptPath };
const sessionEntry = { sessionId, updatedAt: Date.now() };
const sessionStore = { main: sessionEntry };
await fs.mkdir(path.dirname(storePath), { recursive: true });
await fs.writeFile(storePath, JSON.stringify(sessionStore), "utf-8");
await fs.mkdir(path.dirname(transcriptPath), { recursive: true });
await fs.writeFile(transcriptPath, "ok", "utf-8");
runEmbeddedPiAgentMock
.mockImplementationOnce(async () => {
@@ -179,14 +175,11 @@ describe("runReplyAgent typing (heartbeat)", () => {
try {
const sessionId = "session";
const storePath = path.join(stateDir, "sessions", "sessions.json");
const transcriptPath = sessions.resolveSessionTranscriptPath(sessionId);
const sessionEntry = { sessionId, updatedAt: Date.now(), sessionFile: transcriptPath };
const sessionEntry = { sessionId, updatedAt: Date.now() };
const sessionStore = { main: sessionEntry };
await fs.mkdir(path.dirname(storePath), { recursive: true });
await fs.writeFile(storePath, JSON.stringify(sessionStore), "utf-8");
await fs.mkdir(path.dirname(transcriptPath), { recursive: true });
await fs.writeFile(transcriptPath, "ok", "utf-8");
runEmbeddedPiAgentMock
.mockImplementationOnce(async () => ({
@@ -219,59 +212,6 @@ describe("runReplyAgent typing (heartbeat)", () => {
expect(payload).toMatchObject({ text: "ok" });
expect(sessionStore.main.sessionId).not.toBe(sessionId);
const persisted = JSON.parse(await fs.readFile(storePath, "utf-8"));
expect(persisted.main.sessionId).toBe(sessionStore.main.sessionId);
} finally {
if (prevStateDir) {
process.env.CLAWDBOT_STATE_DIR = prevStateDir;
} else {
delete process.env.CLAWDBOT_STATE_DIR;
}
}
});
it("resets the session after role ordering payloads", async () => {
const prevStateDir = process.env.CLAWDBOT_STATE_DIR;
const stateDir = await fs.mkdtemp(path.join(tmpdir(), "clawdbot-session-role-ordering-"));
process.env.CLAWDBOT_STATE_DIR = stateDir;
try {
const sessionId = "session";
const storePath = path.join(stateDir, "sessions", "sessions.json");
const transcriptPath = sessions.resolveSessionTranscriptPath(sessionId);
const sessionEntry = { sessionId, updatedAt: Date.now(), sessionFile: transcriptPath };
const sessionStore = { main: sessionEntry };
await fs.mkdir(path.dirname(storePath), { recursive: true });
await fs.writeFile(storePath, JSON.stringify(sessionStore), "utf-8");
await fs.mkdir(path.dirname(transcriptPath), { recursive: true });
await fs.writeFile(transcriptPath, "ok", "utf-8");
runEmbeddedPiAgentMock.mockImplementationOnce(async () => ({
payloads: [{ text: "Message ordering conflict - please try again.", isError: true }],
meta: {
durationMs: 1,
error: {
kind: "role_ordering",
message: 'messages: roles must alternate between "user" and "assistant"',
},
},
}));
const { run } = createMinimalRun({
sessionEntry,
sessionStore,
sessionKey: "main",
storePath,
});
const res = await run();
const payload = Array.isArray(res) ? res[0] : res;
expect(payload).toMatchObject({
text: expect.stringContaining("Message ordering conflict"),
});
expect(payload.text?.toLowerCase()).toContain("reset");
expect(sessionStore.main.sessionId).not.toBe(sessionId);
await expect(fs.access(transcriptPath)).rejects.toBeDefined();
const persisted = JSON.parse(await fs.readFile(storePath, "utf-8"));
expect(persisted.main.sessionId).toBe(sessionStore.main.sessionId);
} finally {
+7 -47
View File
@@ -1,5 +1,4 @@
import crypto from "node:crypto";
import fs from "node:fs";
import { setCliSessionId } from "../../agents/cli-session.js";
import { lookupContextTokens } from "../../agents/context.js";
import { DEFAULT_CONTEXT_TOKENS } from "../../agents/defaults.js";
@@ -9,7 +8,6 @@ import { queueEmbeddedPiMessage } from "../../agents/pi-embedded.js";
import { hasNonzeroUsage } from "../../agents/usage.js";
import {
resolveAgentIdFromSessionKey,
resolveSessionFilePath,
resolveSessionTranscriptPath,
type SessionEntry,
updateSessionStore,
@@ -211,23 +209,11 @@ export async function runReplyAgent(params: {
});
let responseUsageLine: string | undefined;
type SessionResetOptions = {
failureLabel: string;
buildLogMessage: (nextSessionId: string) => string;
cleanupTranscripts?: boolean;
};
const resetSession = async ({
failureLabel,
buildLogMessage,
cleanupTranscripts,
}: SessionResetOptions): Promise<boolean> => {
const resetSessionAfterCompactionFailure = async (reason: string): Promise<boolean> => {
if (!sessionKey || !activeSessionStore || !storePath) return false;
const prevEntry = activeSessionStore[sessionKey] ?? activeSessionEntry;
if (!prevEntry) return false;
const prevSessionId = cleanupTranscripts ? prevEntry.sessionId : undefined;
const nextSessionId = crypto.randomUUID();
const nextEntry: SessionEntry = {
...prevEntry,
...(activeSessionStore[sessionKey] ?? activeSessionEntry),
sessionId: nextSessionId,
updatedAt: Date.now(),
systemSent: false,
@@ -247,42 +233,18 @@ export async function runReplyAgent(params: {
});
} catch (err) {
defaultRuntime.error(
`Failed to persist session reset after ${failureLabel} (${sessionKey}): ${String(err)}`,
`Failed to persist session reset after compaction failure (${sessionKey}): ${String(err)}`,
);
}
followupRun.run.sessionId = nextSessionId;
followupRun.run.sessionFile = nextSessionFile;
activeSessionEntry = nextEntry;
activeIsNewSession = true;
defaultRuntime.error(buildLogMessage(nextSessionId));
if (cleanupTranscripts && prevSessionId) {
const transcriptCandidates = new Set<string>();
const resolved = resolveSessionFilePath(prevSessionId, prevEntry, { agentId });
if (resolved) transcriptCandidates.add(resolved);
transcriptCandidates.add(resolveSessionTranscriptPath(prevSessionId, agentId));
for (const candidate of transcriptCandidates) {
try {
fs.unlinkSync(candidate);
} catch {
// Best-effort cleanup.
}
}
}
defaultRuntime.error(
`Auto-compaction failed (${reason}). Restarting session ${sessionKey} -> ${nextSessionId} and retrying.`,
);
return true;
};
const resetSessionAfterCompactionFailure = async (reason: string): Promise<boolean> =>
resetSession({
failureLabel: "compaction failure",
buildLogMessage: (nextSessionId) =>
`Auto-compaction failed (${reason}). Restarting session ${sessionKey} -> ${nextSessionId} and retrying.`,
});
const resetSessionAfterRoleOrderingConflict = async (reason: string): Promise<boolean> =>
resetSession({
failureLabel: "role ordering conflict",
buildLogMessage: (nextSessionId) =>
`Role ordering conflict (${reason}). Restarting session ${sessionKey} -> ${nextSessionId}.`,
cleanupTranscripts: true,
});
try {
const runOutcome = await runAgentTurnWithFallback({
commandBody,
@@ -298,7 +260,6 @@ export async function runReplyAgent(params: {
shouldEmitToolResult,
pendingToolTasks,
resetSessionAfterCompactionFailure,
resetSessionAfterRoleOrderingConflict,
isHeartbeat,
sessionKey,
getActiveSessionEntry: () => activeSessionEntry,
@@ -311,7 +272,7 @@ export async function runReplyAgent(params: {
return finalizeWithFollowup(runOutcome.payload, queueKey, runFollowupTurn);
}
const { runResult, fallbackProvider, fallbackModel, directlySentBlockKeys } = runOutcome;
const { runResult, fallbackProvider, fallbackModel } = runOutcome;
let { didLogHeartbeatStrip, autoCompactionCompleted } = runOutcome;
if (
@@ -353,7 +314,6 @@ export async function runReplyAgent(params: {
didLogHeartbeatStrip,
blockStreamingEnabled,
blockReplyPipeline,
directlySentBlockKeys,
replyToMode,
replyToChannel,
currentMessageId: sessionCtx.MessageSid,
-1
View File
@@ -168,7 +168,6 @@ export async function buildStatusReply(params: {
const formatted = formatUsageWindowSummary(snapshot, {
now: Date.now(),
maxWindows: 2,
includeResets: true,
});
if (formatted) usageByProvider.set(snapshot.provider, formatted);
}
-27
View File
@@ -1,27 +0,0 @@
import { describe, expect, it } from "vitest";
import { appendCdpPath, getHeadersWithAuth } from "./cdp.helpers.js";
describe("cdp.helpers", () => {
it("preserves query params when appending CDP paths", () => {
const url = appendCdpPath("https://example.com?token=abc", "/json/version");
expect(url).toBe("https://example.com/json/version?token=abc");
});
it("appends paths under a base prefix", () => {
const url = appendCdpPath("https://example.com/chrome/?token=abc", "json/list");
expect(url).toBe("https://example.com/chrome/json/list?token=abc");
});
it("adds basic auth headers when credentials are present", () => {
const headers = getHeadersWithAuth("https://user:pass@example.com");
expect(headers.Authorization).toBe(`Basic ${Buffer.from("user:pass").toString("base64")}`);
});
it("keeps preexisting authorization headers", () => {
const headers = getHeadersWithAuth("https://user:pass@example.com", {
Authorization: "Bearer token",
});
expect(headers.Authorization).toBe("Bearer token");
});
});
+3 -44
View File
@@ -28,29 +28,6 @@ export function isLoopbackHost(host: string) {
);
}
export function getHeadersWithAuth(url: string, headers: Record<string, string> = {}) {
try {
const parsed = new URL(url);
const hasAuthHeader = Object.keys(headers).some((key) => key.toLowerCase() === "authorization");
if (hasAuthHeader) return headers;
if (parsed.username || parsed.password) {
const auth = Buffer.from(`${parsed.username}:${parsed.password}`).toString("base64");
return { ...headers, Authorization: `Basic ${auth}` };
}
} catch {
// ignore
}
return headers;
}
export function appendCdpPath(cdpUrl: string, path: string): string {
const url = new URL(cdpUrl);
const basePath = url.pathname.replace(/\/$/, "");
const suffix = path.startsWith("/") ? path : `/${path}`;
url.pathname = `${basePath}${suffix}`;
return url.toString();
}
function createCdpSender(ws: WebSocket) {
let nextId = 1;
const pending = new Map<number, Pending>();
@@ -98,12 +75,11 @@ function createCdpSender(ws: WebSocket) {
return { send, closeWithError };
}
export async function fetchJson<T>(url: string, timeoutMs = 1500, init?: RequestInit): Promise<T> {
export async function fetchJson<T>(url: string, timeoutMs = 1500): Promise<T> {
const ctrl = new AbortController();
const t = setTimeout(() => ctrl.abort(), timeoutMs);
try {
const headers = getHeadersWithAuth(url, (init?.headers as Record<string, string>) || {});
const res = await fetch(url, { ...init, headers, signal: ctrl.signal });
const res = await fetch(url, { signal: ctrl.signal });
if (!res.ok) throw new Error(`HTTP ${res.status}`);
return (await res.json()) as T;
} finally {
@@ -111,28 +87,11 @@ export async function fetchJson<T>(url: string, timeoutMs = 1500, init?: Request
}
}
export async function fetchOk(url: string, timeoutMs = 1500, init?: RequestInit): Promise<void> {
const ctrl = new AbortController();
const t = setTimeout(() => ctrl.abort(), timeoutMs);
try {
const headers = getHeadersWithAuth(url, (init?.headers as Record<string, string>) || {});
const res = await fetch(url, { ...init, headers, signal: ctrl.signal });
if (!res.ok) throw new Error(`HTTP ${res.status}`);
} finally {
clearTimeout(t);
}
}
export async function withCdpSocket<T>(
wsUrl: string,
fn: (send: CdpSendFn) => Promise<T>,
opts?: { headers?: Record<string, string> },
): Promise<T> {
const headers = getHeadersWithAuth(wsUrl, opts?.headers ?? {});
const ws = new WebSocket(wsUrl, {
handshakeTimeout: 5000,
...(Object.keys(headers).length ? { headers } : {}),
});
const ws = new WebSocket(wsUrl, { handshakeTimeout: 5000 });
const { send, closeWithError } = createCdpSender(ws);
const openPromise = new Promise<void>((resolve, reject) => {
-16
View File
@@ -165,20 +165,4 @@ describe("cdp", () => {
);
expect(normalized).toBe("ws://example.com:9222/devtools/browser/ABC");
});
it("propagates auth and query params onto normalized websocket URLs", () => {
const normalized = normalizeCdpWsUrl(
"ws://127.0.0.1:9222/devtools/browser/ABC",
"https://user:pass@example.com?token=abc",
);
expect(normalized).toBe("wss://user:pass@example.com/devtools/browser/ABC?token=abc");
});
it("upgrades ws to wss when CDP uses https", () => {
const normalized = normalizeCdpWsUrl(
"ws://production-sfo.browserless.io",
"https://production-sfo.browserless.io?token=abc",
);
expect(normalized).toBe("wss://production-sfo.browserless.io/?token=abc");
});
});
+3 -17
View File
@@ -1,6 +1,4 @@
import { appendCdpPath, fetchJson, isLoopbackHost, withCdpSocket } from "./cdp.helpers.js";
export { appendCdpPath, fetchJson, fetchOk, getHeadersWithAuth } from "./cdp.helpers.js";
import { fetchJson, isLoopbackHost, withCdpSocket } from "./cdp.helpers.js";
export function normalizeCdpWsUrl(wsUrl: string, cdpUrl: string): string {
const ws = new URL(wsUrl);
@@ -11,16 +9,6 @@ export function normalizeCdpWsUrl(wsUrl: string, cdpUrl: string): string {
if (cdpPort) ws.port = cdpPort;
ws.protocol = cdp.protocol === "https:" ? "wss:" : "ws:";
}
if (cdp.protocol === "https:" && ws.protocol === "ws:") {
ws.protocol = "wss:";
}
if (!ws.username && !ws.password && (cdp.username || cdp.password)) {
ws.username = cdp.username;
ws.password = cdp.password;
}
for (const [key, value] of cdp.searchParams.entries()) {
if (!ws.searchParams.has(key)) ws.searchParams.append(key, value);
}
return ws.toString();
}
@@ -80,10 +68,8 @@ export async function createTargetViaCdp(opts: {
cdpUrl: string;
url: string;
}): Promise<{ targetId: string }> {
const version = await fetchJson<{ webSocketDebuggerUrl?: string }>(
appendCdpPath(opts.cdpUrl, "/json/version"),
1500,
);
const base = opts.cdpUrl.replace(/\/$/, "");
const version = await fetchJson<{ webSocketDebuggerUrl?: string }>(`${base}/json/version`, 1500);
const wsUrlRaw = String(version?.webSocketDebuggerUrl ?? "").trim();
const wsUrl = wsUrlRaw ? normalizeCdpWsUrl(wsUrlRaw, opts.cdpUrl) : "";
if (!wsUrl) throw new Error("CDP /json/version missing webSocketDebuggerUrl");
Loaded 100 of 177 files, more files were not shown because too many files have changed in this diff. Show more