Compare commits

...

46 Commits

Author SHA1 Message Date
Peter Steinberger
9cf4fc3867 fix: honor send path/filePath inputs (#1444) (thanks @hopyky) 2026-01-23 02:10:05 +00:00
Matt mini
fb7159be5e Fix: Support path and filePath parameters in message send action
The message tool accepts path and filePath parameters in its schema,
but these were never converted to mediaUrl, causing local files to
be ignored when sending messages.

Changes:
- src/agents/tools/message-tool.ts: Convert path/filePath to media with file:// URL
- src/infra/outbound/message-action-runner.ts: Allow hydrateSendAttachmentParams for "send" action

Fixes issue where local audio files (and other media) couldn't be sent
via the message tool with the path parameter.

Users can now use:
  message({ path: "/tmp/file.ogg" })
  message({ filePath: "/tmp/file.ogg" })
2026-01-23 02:03:37 +00:00
Peter Steinberger
712bc74c30 docs: highlight mattermost plugin 2026-01-23 01:39:36 +00:00
Peter Steinberger
0396b678fa docs: note transcript hygiene sync 2026-01-23 01:38:05 +00:00
Peter Steinberger
eaf1b6bfee docs: simplify OpenProse install 2026-01-23 01:37:54 +00:00
Peter Steinberger
06cb2bf58d docs: expand mattermost intro 2026-01-23 01:35:50 +00:00
Peter Steinberger
8fdb3b38eb docs: add mattermost redirect 2026-01-23 01:35:15 +00:00
Peter Steinberger
5689d7fb98 refactor: remove transcript sanitize extension 2026-01-23 01:34:33 +00:00
Peter Steinberger
2424404fb4 docs: add transcript hygiene reference 2026-01-23 01:34:21 +00:00
Peter Steinberger
17a09cc721 Merge pull request #1472 from czekaj/fix/logs-follow-spinner
fix: suppress spinner in logs --follow mode
2026-01-23 01:29:30 +00:00
Peter Steinberger
bc4d8ce398 docs: link Lobster and OpenProse 2026-01-23 01:29:17 +00:00
Peter Steinberger
279f799388 fix: harden Mattermost plugin gating (#1428) (thanks @damoahdominic) 2026-01-23 01:23:23 +00:00
Peter Steinberger
1d658109a8 docs: remove OpenProse telemetry mentions 2026-01-23 01:20:30 +00:00
Peter Steinberger
5a446f3a21 docs: expand OpenProse guide 2026-01-23 01:08:55 +00:00
Peter Steinberger
52b6bf04af fix: improve tool summaries 2026-01-23 01:00:24 +00:00
Lucas Czekaj
76a42da676 fix: suppress spinner in logs --follow mode
The progress spinner was being shown for each gateway RPC call during
log tailing, causing repeated spinner frames (◇ │) to appear every
polling interval.

Add a `progress` option to `callGatewayFromCli` and disable the spinner
during follow mode polling to keep output clean.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-22 16:58:42 -08:00
Peter Steinberger
51a9053387 feat: add OpenProse plugin skills 2026-01-23 00:49:40 +00:00
Peter Steinberger
db0235a26a fix: gate transcript sanitization by provider 2026-01-23 00:42:45 +00:00
Peter Steinberger
fac21e6eb4 Merge pull request #1428 from bestparents/feat/mattermost-channel
feat: add Mattermost channel support
2026-01-23 00:24:47 +00:00
Peter Steinberger
e872f5335b fix: allow chained exec allowlists
Co-authored-by: Lucas Czekaj <1464539+czekaj@users.noreply.github.com>
2026-01-23 00:11:58 +00:00
Peter Steinberger
a23e272877 Merge pull request #1440 from robbyczgw-cla/fix/token-count-after-compaction
fix: update token count display after compaction
2026-01-23 00:10:46 +00:00
Peter Steinberger
870bfa94ed fix: skip tool id sanitization for openai responses 2026-01-22 23:51:59 +00:00
Peter Steinberger
d297e17958 refactor: centralize control ui avatar helpers 2026-01-22 23:41:36 +00:00
Peter Steinberger
6a25e23909 fix: tui local shell consent UX (#1463)
- add local shell runner + denial notice + tests
- docs: describe ! local shell usage
- lint: drop unused Slack upload contentType
- cleanup: remove stray Swabble pins

Thanks @vignesh07.
Co-authored-by: Vignesh Natarajan <vigneshnatarajan92@gmail.com>
2026-01-22 23:38:44 +00:00
Vignesh Natarajan
dc66527114 tui: clarify local shell exec consent prompt 2026-01-22 23:26:01 +00:00
Vignesh Natarajan
110b5dafee tui: keep trimming for normal submits; only raw ! triggers bash 2026-01-22 23:26:01 +00:00
Vignesh Natarajan
5fd699d0bf tui: add local shell execution for !-prefixed lines 2026-01-22 23:26:01 +00:00
Peter Steinberger
c1e50b7184 docs: clarify node service commands 2026-01-22 23:22:56 +00:00
Peter Steinberger
c7e0dc10fc docs: fix remaining node ws references 2026-01-22 23:22:56 +00:00
Dominic Damoah
01579aa7d7 Merge branch 'main' into feat/mattermost-channel 2026-01-22 18:17:40 -05:00
Peter Steinberger
42cd8a02bb Merge pull request #1447 from jdrhyne/fix/slack-filetype-deprecation
fix(slack): remove deprecated filetype field from files.uploadV2 [AI]
2026-01-22 23:16:26 +00:00
Peter Steinberger
96f1846c2c docs: align node transport with gateway ws 2026-01-22 23:10:09 +00:00
Peter Steinberger
7c336588ea chore: drop tty from install e2e docker 2026-01-22 23:09:28 +00:00
Peter Steinberger
814e9a500e feat: add manual onboarding flow alias 2026-01-22 23:09:28 +00:00
Peter Steinberger
370896e994 fix(macos): prefer linked channel in health summaries 2026-01-22 23:09:28 +00:00
Peter Steinberger
573354f5e4 chore(dev): default restart-mac to attach-only 2026-01-22 23:08:56 +00:00
Peter Steinberger
c721947346 feat(macos): add attach-only launchd override 2026-01-22 23:08:56 +00:00
Robby
768d5ccafe style: fix formatting 2026-01-22 17:47:52 +00:00
Dominic Damoah
8b3cb373d4 fix: remove unused originatingChannel variable
Remove unused originatingChannel variable from runPreparedReply function that was assigned but never referenced.
2026-01-22 12:11:05 -05:00
Dominic Damoah
495a39b5a9 refactor: extract mattermost channel plugin to extension
Move mattermost channel implementation from core to extensions/mattermost plugin. Extract config schema, group mentions, normalize utilities, and all mattermost-specific logic (accounts, client, monitor, probe, send) into the extension. Update imports to use plugin SDK and local modules. Add channel metadata directly in plugin definition instead of using getChatChannelMeta. Update package.json with channel and install configuration.
2026-01-22 12:02:30 -05:00
Jonathan Rhyne
8b6b97c3f6 docs: add changelog entry for PR #1447 2026-01-22 08:39:54 -05:00
Jonathan Rhyne
47e440f73a fix(slack): remove deprecated filetype field from files.uploadV2
Slack's files.uploadV2 API no longer supports the filetype field and logs
deprecation warnings when it's included. Slack auto-detects the file type
from the file content, so this field is unnecessary.

This removes the warning:
[WARN] web-api:WebClient filetype is no longer a supported field in files.uploadV2.
2026-01-22 08:33:13 -05:00
Robby
0873351401 fix: update token count display after compaction (#1299) 2026-01-22 09:58:07 +00:00
Dominic Damoah
91278d8b4e Merge branch 'main' into feat/mattermost-channel 2026-01-22 03:11:53 -05:00
Dominic Damoah
fe77d3eb56 Merge branch 'main' into feat/mattermost-channel 2026-01-22 02:49:17 -05:00
Dominic Damoah
bf6df6d6b7 feat: add Mattermost channel support
Add Mattermost as a supported messaging channel with bot API and WebSocket integration. Includes channel state tracking (tint, summary, details), multi-account support, and delivery target routing. Update documentation and tests to include Mattermost alongside existing channels.
2026-01-21 18:40:56 -05:00
240 changed files with 28057 additions and 808 deletions

View File

@@ -4,17 +4,49 @@ Docs: https://docs.clawd.bot
## 2026.1.22 (unreleased)
### Changes
- Highlight: Mattermost plugin channel support with pairing + allowlist gating. (#1428) Thanks @damoahdominic.
- Highlight: OpenProse plugin skill pack with `/prose` slash command, plugin-shipped skills, and docs. https://docs.clawd.bot/prose
- TUI: run local shell commands with `!` after per-session consent, and warn when local exec stays disabled. (#1463) Thanks @vignesh07.
- Highlight: Lobster optional plugin tool for typed workflows + approval gates. https://docs.clawd.bot/tools/lobster
- Agents: add identity avatar config support and Control UI avatar rendering. (#1329, #1424) Thanks @dlauer.
- Memory: prevent CLI hangs by deferring vector probes, adding sqlite-vec/embedding timeouts, and showing sync progress early.
- Docs: add troubleshooting entry for gateway.mode blocking gateway start. https://docs.clawd.bot/gateway/troubleshooting
- Docs: add /model allowlist troubleshooting note. (#1405)
- Docs: add per-message Gmail search example for gog. (#1220) Thanks @mbelinky.
- UI: show per-session assistant identity in the Control UI. (#1420) Thanks @robbyczgw-cla.
- Onboarding: remove the run setup-token auth option (paste setup-token or reuse CLI creds instead).
- Signal: add typing indicators and DM read receipts via signal-cli.
- MSTeams: add file uploads, adaptive cards, and attachment handling improvements. (#1410) Thanks @Evizero.
- CLI: add `clawdbot update wizard` for interactive channel selection and restart prompts. https://docs.clawd.bot/cli/update
- macOS: add attach-only debug toggle + `--attach-only`/`--no-launchd` flag to skip launchd installs.
### Breaking
- **BREAKING:** Envelope and system event timestamps now default to host-local time (was UTC) so agents dont have to constantly convert.
### Fixes
- BlueBubbles: stop typing indicator on idle/no-reply. (#1439) Thanks @Nicell.
- Message tool: keep path/filePath as-is for send; hydrate buffers only for sendAttachment. (#1444) Thanks @hopyky.
- Auto-reply: only report a model switch when session state is available. (#1465) Thanks @robbyczgw-cla.
- Control UI: resolve local avatar URLs with basePath across injection + identity RPC. (#1457) Thanks @dlauer.
- Agents: surface concrete API error details instead of generic AI service errors.
- Exec approvals: allow per-segment allowlists for chained shell commands on gateway + node hosts. (#1458) Thanks @czekaj.
- Agents: make OpenAI sessions image-sanitize-only; gate tool-id/repair sanitization by provider.
<<<<<<< Updated upstream
- Agents: make tool summaries more readable and only show optional params when set.
- Mattermost (plugin): enforce pairing/allowlist gating, keep @username targets, and clarify plugin-only docs. (#1428) Thanks @damoahdominic.
||||||| Stash base
=======
- Agents: centralize transcript sanitization in the runner; keep <final> tags and error turns intact.
>>>>>>> Stashed changes
- Docs: fix gog auth services example to include docs scope. (#1454) Thanks @zerone0x.
- macOS: prefer linked channels in gateway summary to avoid false “not linked” status.
## 2026.1.21-2
### Fixes
- Control UI: ignore bootstrap identity placeholder text for avatar values and fall back to the default avatar. https://docs.clawd.bot/cli/agents https://docs.clawd.bot/web/control-ui
- Slack: remove deprecated `filetype` field from `files.uploadV2` to eliminate API warnings. (#1447)
## 2026.1.21

View File

@@ -16,6 +16,8 @@ struct DebugSettings: View {
@State private var modelsError: String?
private let gatewayManager = GatewayProcessManager.shared
private let healthStore = HealthStore.shared
@State private var launchAgentWriteDisabled = GatewayLaunchAgentManager.isLaunchAgentWriteDisabled()
@State private var launchAgentWriteError: String?
@State private var gatewayRootInput: String = GatewayProcessManager.shared.projectRootPath()
@State private var sessionStorePath: String = SessionLoader.defaultStorePath
@State private var sessionStoreSaveError: String?
@@ -47,6 +49,7 @@ struct DebugSettings: View {
VStack(alignment: .leading, spacing: 14) {
self.header
self.launchdSection
self.appInfoSection
self.gatewaySection
self.logsSection
@@ -79,6 +82,39 @@ struct DebugSettings: View {
}
}
private var launchdSection: some View {
GroupBox("Gateway startup") {
VStack(alignment: .leading, spacing: 8) {
Toggle("Attach only (skip launchd install)", isOn: self.$launchAgentWriteDisabled)
.onChange(of: self.launchAgentWriteDisabled) { _, newValue in
self.launchAgentWriteError = GatewayLaunchAgentManager.setLaunchAgentWriteDisabled(newValue)
if self.launchAgentWriteError != nil {
self.launchAgentWriteDisabled = GatewayLaunchAgentManager.isLaunchAgentWriteDisabled()
return
}
if newValue {
Task {
_ = await GatewayLaunchAgentManager.set(
enabled: false,
bundlePath: Bundle.main.bundlePath,
port: GatewayEnvironment.gatewayPort())
}
}
}
Text("When enabled, Clawdbot won't install or manage \(gatewayLaunchdLabel). It will only attach to an existing Gateway.")
.font(.caption)
.foregroundStyle(.secondary)
if let launchAgentWriteError {
Text(launchAgentWriteError)
.font(.caption)
.foregroundStyle(.red)
}
}
}
}
private var header: some View {
VStack(alignment: .leading, spacing: 6) {
Text("Debug")

View File

@@ -4,11 +4,46 @@ enum GatewayLaunchAgentManager {
private static let logger = Logger(subsystem: "com.clawdbot", category: "gateway.launchd")
private static let disableLaunchAgentMarker = ".clawdbot/disable-launchagent"
private static var disableLaunchAgentMarkerURL: URL {
FileManager().homeDirectoryForCurrentUser
.appendingPathComponent(self.disableLaunchAgentMarker)
}
private static var plistURL: URL {
FileManager().homeDirectoryForCurrentUser
.appendingPathComponent("Library/LaunchAgents/\(gatewayLaunchdLabel).plist")
}
static func isLaunchAgentWriteDisabled() -> Bool {
FileManager().fileExists(atPath: self.disableLaunchAgentMarkerURL.path)
}
static func setLaunchAgentWriteDisabled(_ disabled: Bool) -> String? {
let marker = self.disableLaunchAgentMarkerURL
if disabled {
do {
try FileManager().createDirectory(
at: marker.deletingLastPathComponent(),
withIntermediateDirectories: true)
if !FileManager().fileExists(atPath: marker.path) {
FileManager().createFile(atPath: marker.path, contents: nil)
}
} catch {
return error.localizedDescription
}
return nil
}
if FileManager().fileExists(atPath: marker.path) {
do {
try FileManager().removeItem(at: marker)
} catch {
return error.localizedDescription
}
}
return nil
}
static func isLoaded() async -> Bool {
guard let loaded = await self.readDaemonLoaded() else { return false }
return loaded
@@ -66,12 +101,6 @@ enum GatewayLaunchAgentManager {
}
extension GatewayLaunchAgentManager {
private static func isLaunchAgentWriteDisabled() -> Bool {
let marker = FileManager().homeDirectoryForCurrentUser
.appendingPathComponent(self.disableLaunchAgentMarker)
return FileManager().fileExists(atPath: marker.path)
}
private static func readDaemonLoaded() async -> Bool? {
let result = await self.runDaemonCommandResult(
["status", "--json", "--no-probe"],

View File

@@ -79,6 +79,11 @@ final class GatewayProcessManager {
func ensureLaunchAgentEnabledIfNeeded() async {
guard !CommandResolver.connectionModeIsRemote() else { return }
if GatewayLaunchAgentManager.isLaunchAgentWriteDisabled() {
self.appendLog("[gateway] launchd auto-enable skipped (attach-only)\n")
self.logger.info("gateway launchd auto-enable skipped (disable marker set)")
return
}
let enabled = await GatewayLaunchAgentManager.isLoaded()
guard !enabled else { return }
let bundlePath = Bundle.main.bundleURL.path
@@ -237,13 +242,12 @@ final class GatewayProcessManager {
private func describe(details instance: String?, port: Int, snap: HealthSnapshot?) -> String {
let instanceText = instance ?? "pid unknown"
if let snap {
let linkId = snap.channelOrder?.first(where: {
if let summary = snap.channels[$0] { return summary.linked != nil }
return false
}) ?? snap.channels.keys.first(where: {
if let summary = snap.channels[$0] { return summary.linked != nil }
return false
})
let order = snap.channelOrder ?? Array(snap.channels.keys)
let linkId = order.first(where: { snap.channels[$0]?.linked == true })
?? order.first(where: { snap.channels[$0]?.linked != nil })
guard let linkId else {
return "port \(port), health probe succeeded, \(instanceText)"
}
let linked = linkId.flatMap { snap.channels[$0]?.linked } ?? false
let authAge = linkId.flatMap { snap.channels[$0]?.authAgeMs }.flatMap(msToAge) ?? "unknown age"
let label =
@@ -308,6 +312,15 @@ final class GatewayProcessManager {
return
}
if GatewayLaunchAgentManager.isLaunchAgentWriteDisabled() {
let message = "Launchd disabled; start the Gateway manually or disable attach-only."
self.status = .failed(message)
self.lastFailureReason = "launchd disabled"
self.appendLog("[gateway] launchd disabled; skipping auto-start\n")
self.logger.info("gateway launchd enable skipped (disable marker set)")
return
}
let bundlePath = Bundle.main.bundleURL.path
let port = GatewayEnvironment.gatewayPort()
self.appendLog("[gateway] enabling launchd job (\(gatewayLaunchdLabel)) on port \(port)\n")

View File

@@ -166,6 +166,11 @@ final class HealthStore {
_ snap: HealthSnapshot) -> (id: String, summary: HealthSnapshot.ChannelSummary)?
{
let order = snap.channelOrder ?? Array(snap.channels.keys)
for id in order {
if let summary = snap.channels[id], summary.linked == true {
return (id: id, summary: summary)
}
}
for id in order {
if let summary = snap.channels[id], summary.linked != nil {
return (id: id, summary: summary)

View File

@@ -3,6 +3,7 @@ import Darwin
import Foundation
import MenuBarExtraAccess
import Observation
import OSLog
import Security
import SwiftUI
@@ -10,6 +11,7 @@ import SwiftUI
struct ClawdbotApp: App {
@NSApplicationDelegateAdaptor(AppDelegate.self) private var delegate
@State private var state: AppState
private static let logger = Logger(subsystem: "com.clawdbot", category: "app")
private let gatewayManager = GatewayProcessManager.shared
private let controlChannel = ControlChannel.shared
private let activityStore = WorkActivityStore.shared
@@ -31,6 +33,7 @@ struct ClawdbotApp: App {
init() {
ClawdbotLogging.bootstrapIfNeeded()
Self.applyAttachOnlyOverrideIfNeeded()
_state = State(initialValue: AppStateStore.shared)
}
@@ -91,6 +94,22 @@ struct ClawdbotApp: App {
self.statusItem?.button?.appearsDisabled = paused || sleeping
}
private static func applyAttachOnlyOverrideIfNeeded() {
let args = CommandLine.arguments
guard args.contains("--attach-only") || args.contains("--no-launchd") else { return }
if let error = GatewayLaunchAgentManager.setLaunchAgentWriteDisabled(true) {
Self.logger.error("attach-only flag failed: \(error, privacy: .public)")
return
}
Task {
_ = await GatewayLaunchAgentManager.set(
enabled: false,
bundlePath: Bundle.main.bundlePath,
port: GatewayEnvironment.gatewayPort())
}
Self.logger.info("attach-only flag enabled")
}
private var isGatewaySleeping: Bool {
if self.state.isPaused { return false }
switch self.state.connectionMode {

View File

@@ -121,7 +121,7 @@ Resolution priority:
### Delivery (channel + target)
Isolated jobs can deliver output to a channel. The job payload can specify:
- `channel`: `whatsapp` / `telegram` / `discord` / `slack` / `signal` / `imessage` / `last`
- `channel`: `whatsapp` / `telegram` / `discord` / `slack` / `mattermost` (plugin) / `signal` / `imessage` / `last`
- `to`: channel-specific recipient target
If `channel` or `to` is omitted, cron can fall back to the main sessions “last route”
@@ -133,7 +133,7 @@ Delivery notes:
- Use `deliver: false` to keep output internal even if a `to` is present.
Target format reminders:
- Slack/Discord targets should use explicit prefixes (e.g. `channel:<id>`, `user:<id>`) to avoid ambiguity.
- Slack/Discord/Mattermost (plugin) targets should use explicit prefixes (e.g. `channel:<id>`, `user:<id>`) to avoid ambiguity.
- Telegram topics should use the `:topic:` form (see below).
#### Telegram delivery targets (topics / forum threads)

View File

@@ -71,8 +71,8 @@ Payload:
- `sessionKey` optional (string): The key used to identify the agent's session. Defaults to a random `hook:<uuid>`. Using a consistent key allows for a multi-turn conversation within the hook context.
- `wakeMode` optional (`now` | `next-heartbeat`): Whether to trigger an immediate heartbeat (default `now`) or wait for the next periodic check.
- `deliver` optional (boolean): If `true`, the agent's response will be sent to the messaging channel. Defaults to `true`. Responses that are only heartbeat acknowledgments are automatically skipped.
- `channel` optional (string): The messaging channel for delivery. One of: `last`, `whatsapp`, `telegram`, `discord`, `slack`, `signal`, `imessage`, `msteams`. Defaults to `last`.
- `to` optional (string): The recipient identifier for the channel (e.g., phone number for WhatsApp/Signal, chat ID for Telegram, channel ID for Discord/Slack, conversation ID for MS Teams). Defaults to the last recipient in the main session.
- `channel` optional (string): The messaging channel for delivery. One of: `last`, `whatsapp`, `telegram`, `discord`, `slack`, `mattermost` (plugin), `signal`, `imessage`, `msteams`. Defaults to `last`.
- `to` optional (string): The recipient identifier for the channel (e.g., phone number for WhatsApp/Signal, chat ID for Telegram, channel ID for Discord/Slack/Mattermost (plugin), conversation ID for MS Teams). Defaults to the last recipient in the main session.
- `model` optional (string): Model override (e.g., `anthropic/claude-3-5-sonnet` or an alias). Must be in the allowed model list if restricted.
- `thinking` optional (string): Thinking level override (e.g., `low`, `medium`, `high`).
- `timeoutSeconds` optional (number): Maximum duration for the agent run in seconds.

View File

@@ -15,6 +15,7 @@ Text is supported everywhere; media and reactions vary by channel.
- [Telegram](/channels/telegram) — Bot API via grammY; supports groups.
- [Discord](/channels/discord) — Discord Bot API + Gateway; supports servers, channels, and DMs.
- [Slack](/channels/slack) — Bolt SDK; workspace apps.
- [Mattermost](/channels/mattermost) — Bot API + WebSocket; channels, groups, DMs (plugin, installed separately).
- [Signal](/channels/signal) — signal-cli; privacy-focused.
- [BlueBubbles](/channels/bluebubbles) — **Recommended for iMessage**; uses the BlueBubbles macOS server REST API with full feature support (edit, unsend, effects, reactions, group management — edit currently broken on macOS 26 Tahoe).
- [iMessage](/channels/imessage) — macOS only; native integration via imsg (legacy, consider BlueBubbles for new setups).

123
docs/channels/mattermost.md Normal file
View File

@@ -0,0 +1,123 @@
---
summary: "Mattermost bot setup and Clawdbot config"
read_when:
- Setting up Mattermost
- Debugging Mattermost routing
---
# Mattermost (plugin)
Status: supported via plugin (bot token + WebSocket events). Channels, groups, and DMs are supported.
Mattermost is a self-hostable team messaging platform; see the official site at
[mattermost.com](https://mattermost.com) for product details and downloads.
## Plugin required
Mattermost ships as a plugin and is not bundled with the core install.
Install via CLI (npm registry):
```bash
clawdbot plugins install @clawdbot/mattermost
```
Local checkout (when running from a git repo):
```bash
clawdbot plugins install ./extensions/mattermost
```
If you choose Mattermost during configure/onboarding and a git checkout is detected,
Clawdbot will offer the local install path automatically.
Details: [Plugins](/plugin)
## Quick setup
1) Install the Mattermost plugin.
2) Create a Mattermost bot account and copy the **bot token**.
3) Copy the Mattermost **base URL** (e.g., `https://chat.example.com`).
4) Configure Clawdbot and start the gateway.
Minimal config:
```json5
{
channels: {
mattermost: {
enabled: true,
botToken: "mm-token",
baseUrl: "https://chat.example.com",
dmPolicy: "pairing"
}
}
}
```
## Environment variables (default account)
Set these on the gateway host if you prefer env vars:
- `MATTERMOST_BOT_TOKEN=...`
- `MATTERMOST_URL=https://chat.example.com`
Env vars apply only to the **default** account (`default`). Other accounts must use config values.
## Chat modes
Mattermost responds to DMs automatically. Channel behavior is controlled by `chatmode`:
- `oncall` (default): respond only when @mentioned in channels.
- `onmessage`: respond to every channel message.
- `onchar`: respond when a message starts with a trigger prefix.
Config example:
```json5
{
channels: {
mattermost: {
chatmode: "onchar",
oncharPrefixes: [">", "!"]
}
}
}
```
Notes:
- `onchar` still responds to explicit @mentions.
- `channels.mattermost.requireMention` is honored for legacy configs but `chatmode` is preferred.
## Access control (DMs)
- Default: `channels.mattermost.dmPolicy = "pairing"` (unknown senders get a pairing code).
- Approve via:
- `clawdbot pairing list mattermost`
- `clawdbot pairing approve mattermost <CODE>`
- Public DMs: `channels.mattermost.dmPolicy="open"` plus `channels.mattermost.allowFrom=["*"]`.
## Channels (groups)
- Default: `channels.mattermost.groupPolicy = "allowlist"` (mention-gated).
- Allowlist senders with `channels.mattermost.groupAllowFrom` (user IDs or `@username`).
- Open channels: `channels.mattermost.groupPolicy="open"` (mention-gated).
## Targets for outbound delivery
Use these target formats with `clawdbot message send` or cron/webhooks:
- `channel:<id>` for a channel
- `user:<id>` for a DM
- `@username` for a DM (resolved via the Mattermost API)
Bare IDs are treated as channels.
## Multi-account
Mattermost supports multiple accounts under `channels.mattermost.accounts`:
```json5
{
channels: {
mattermost: {
accounts: {
default: { name: "Primary", botToken: "mm-token", baseUrl: "https://chat.example.com" },
alerts: { name: "Alerts", botToken: "mm-token-2", baseUrl: "https://alerts.example.com" }
}
}
}
}
```
## Troubleshooting
- No replies in channels: ensure the bot is in the channel and mention it (oncall), use a trigger prefix (onchar), or set `chatmode: "onmessage"`.
- Auth errors: check the bot token, base URL, and whether the account is enabled.
- Multi-account issues: env vars only apply to the `default` account.

View File

@@ -1,7 +1,7 @@
---
summary: "CLI reference for `clawdbot channels` (accounts, status, login/logout, logs)"
read_when:
- You want to add/remove channel accounts (WhatsApp/Telegram/Discord/Slack/Signal/iMessage)
- You want to add/remove channel accounts (WhatsApp/Telegram/Discord/Slack/Mattermost (plugin)/Signal/iMessage)
- You want to check channel status or tail channel logs
---

View File

@@ -122,7 +122,7 @@ clawdbot gateway probe --ssh user@gateway-host
Options:
- `--ssh <target>`: `user@host` or `user@host:port` (port defaults to `22`).
- `--ssh-identity <path>`: identity file.
- `--ssh-auto`: pick the first discovered bridge host as SSH target (LAN/WAB only).
- `--ssh-auto`: pick the first discovered gateway host as SSH target (LAN/WAB only).
Config (optional, used as defaults):
- `gateway.remote.sshTarget`

View File

@@ -293,7 +293,7 @@ Options:
- `--reset` (reset config + credentials + sessions + workspace before wizard)
- `--non-interactive`
- `--mode <local|remote>`
- `--flow <quickstart|advanced>`
- `--flow <quickstart|advanced|manual>` (manual is an alias for advanced)
- `--auth-choice <setup-token|claude-cli|token|openai-codex|openai-api-key|openrouter-api-key|ai-gateway-api-key|moonshot-api-key|kimi-code-api-key|codex-cli|gemini-api-key|zai-api-key|apiKey|minimax-api|opencode-zen|skip>`
- `--token-provider <id>` (non-interactive; used with `--auth-choice token`)
- `--token <token>` (non-interactive; used with `--auth-choice token`)
@@ -352,7 +352,7 @@ Options:
## Channel helpers
### `channels`
Manage chat channel accounts (WhatsApp/Telegram/Discord/Slack/Signal/iMessage/MS Teams).
Manage chat channel accounts (WhatsApp/Telegram/Discord/Slack/Mattermost (plugin)/Signal/iMessage/MS Teams).
Subcommands:
- `channels list`: show configured channels and auth profiles (Claude Code + Codex CLI OAuth sync included).
@@ -365,7 +365,7 @@ Subcommands:
- `channels logout`: log out of a channel session (if supported).
Common options:
- `--channel <name>`: `whatsapp|telegram|discord|slack|signal|imessage|msteams`
- `--channel <name>`: `whatsapp|telegram|discord|slack|mattermost|signal|imessage|msteams`
- `--account <id>`: channel account id (default `default`)
- `--name <label>`: display name for the account
@@ -472,7 +472,7 @@ Options:
- `--session-id <id>`
- `--thinking <off|minimal|low|medium|high|xhigh>` (GPT-5.2 + Codex models only)
- `--verbose <on|full|off>`
- `--channel <whatsapp|telegram|discord|slack|signal|imessage>`
- `--channel <whatsapp|telegram|discord|slack|mattermost|signal|imessage|msteams>`
- `--local`
- `--deliver`
- `--json`
@@ -791,11 +791,10 @@ All `cron` commands accept `--url`, `--token`, `--timeout`, `--expect-final`.
[`clawdbot node`](/cli/node).
Subcommands:
- `node run --host <gateway-host> --port 18790`
- `node run --host <gateway-host> --port 18789`
- `node status`
- `node install [--host <gateway-host>] [--port <port>] [--tls] [--tls-fingerprint <sha256>] [--node-id <id>] [--display-name <name>] [--runtime <node|bun>] [--force]`
- `node uninstall`
- `node run`
- `node stop`
- `node restart`

View File

@@ -8,7 +8,7 @@ read_when:
# `clawdbot message`
Single outbound command for sending messages and channel actions
(Discord/Slack/Telegram/WhatsApp/Signal/iMessage/MS Teams).
(Discord/Slack/Mattermost (plugin)/Telegram/WhatsApp/Signal/iMessage/MS Teams).
## Usage
@@ -19,13 +19,14 @@ clawdbot message <subcommand> [flags]
Channel selection:
- `--channel` required if more than one channel is configured.
- If exactly one channel is configured, it becomes the default.
- Values: `whatsapp|telegram|discord|slack|signal|imessage|msteams`
- Values: `whatsapp|telegram|discord|slack|mattermost|signal|imessage|msteams` (Mattermost requires plugin)
Target formats (`--target`):
- WhatsApp: E.164 or group JID
- Telegram: chat id or `@username`
- Discord: `channel:<id>` or `user:<id>` (or `<@id>` mention; raw numeric ids are treated as channels)
- Slack: `channel:<id>` or `user:<id>` (raw channel id is accepted)
- Mattermost (plugin): `channel:<id>`, `user:<id>`, or `@username` (bare ids are treated as channels)
- Signal: `+E.164`, `group:<id>`, `signal:+E.164`, `signal:group:<id>`, or `username:<name>`/`u:<name>`
- iMessage: handle, `chat_id:<id>`, `chat_guid:<guid>`, or `chat_identifier:<id>`
- MS Teams: conversation id (`19:...@thread.tacv2`) or `conversation:<id>` or `user:<aad-object-id>`
@@ -49,7 +50,7 @@ Name lookup:
### Core
- `send`
- Channels: WhatsApp/Telegram/Discord/Slack/Signal/iMessage/MS Teams
- Channels: WhatsApp/Telegram/Discord/Slack/Mattermost (plugin)/Signal/iMessage/MS Teams
- Required: `--target`, plus `--message` or `--media`
- Optional: `--media`, `--reply-to`, `--thread-id`, `--gif-playback`
- Telegram only: `--buttons` (requires `channels.telegram.capabilities.inlineButtons` to allow it)

View File

@@ -7,7 +7,7 @@ read_when:
# `clawdbot node`
Run a **headless node host** that connects to the Gateway bridge and exposes
Run a **headless node host** that connects to the Gateway WebSocket and exposes
`system.run` / `system.which` on this machine.
## Why use a node host?
@@ -26,14 +26,14 @@ node host, so you can keep command access scoped and explicit.
## Run (foreground)
```bash
clawdbot node run --host <gateway-host> --port 18790
clawdbot node run --host <gateway-host> --port 18789
```
Options:
- `--host <host>`: Gateway bridge host (default: `127.0.0.1`)
- `--port <port>`: Gateway bridge port (default: `18790`)
- `--tls`: Use TLS for the bridge connection
- `--tls-fingerprint <sha256>`: Pin the bridge certificate fingerprint
- `--host <host>`: Gateway WebSocket host (default: `127.0.0.1`)
- `--port <port>`: Gateway WebSocket port (default: `18789`)
- `--tls`: Use TLS for the gateway connection
- `--tls-fingerprint <sha256>`: Expected TLS certificate fingerprint (sha256)
- `--node-id <id>`: Override node id (clears pairing token)
- `--display-name <name>`: Override the node display name
@@ -42,14 +42,14 @@ Options:
Install a headless node host as a user service.
```bash
clawdbot node install --host <gateway-host> --port 18790
clawdbot node install --host <gateway-host> --port 18789
```
Options:
- `--host <host>`: Gateway bridge host (default: `127.0.0.1`)
- `--port <port>`: Gateway bridge port (default: `18790`)
- `--tls`: Use TLS for the bridge connection
- `--tls-fingerprint <sha256>`: Pin the bridge certificate fingerprint
- `--host <host>`: Gateway WebSocket host (default: `127.0.0.1`)
- `--port <port>`: Gateway WebSocket port (default: `18789`)
- `--tls`: Use TLS for the gateway connection
- `--tls-fingerprint <sha256>`: Expected TLS certificate fingerprint (sha256)
- `--node-id <id>`: Override node id (clears pairing token)
- `--display-name <name>`: Override the node display name
- `--runtime <runtime>`: Service runtime (`node` or `bun`)
@@ -59,12 +59,15 @@ Manage the service:
```bash
clawdbot node status
clawdbot node run
clawdbot node stop
clawdbot node restart
clawdbot node uninstall
```
Use `clawdbot node run` for a foreground node host (no service).
Service commands accept `--json` for machine-readable output.
## Pairing
The first connection creates a pending node pair request on the Gateway.
@@ -75,7 +78,8 @@ clawdbot nodes pending
clawdbot nodes approve <requestId>
```
The node host stores its node id + token in `~/.clawdbot/node.json`.
The node host stores its node id, token, display name, and gateway connection info in
`~/.clawdbot/node.json`.
## Exec approvals

View File

@@ -14,6 +14,9 @@ Related:
- Camera: [Camera nodes](/nodes/camera)
- Images: [Image nodes](/nodes/images)
Common options:
- `--url`, `--token`, `--timeout`, `--json`
## Common commands
```bash
@@ -40,6 +43,11 @@ clawdbot nodes run --raw "git status"
clawdbot nodes run --agent main --node <id|name|ip> --raw "git status"
```
Invoke flags:
- `--params <json>`: JSON object string (default `{}`).
- `--invoke-timeout <ms>`: node invoke timeout (default `15000`).
- `--idempotency-key <key>`: optional idempotency key.
### Exec-style defaults
`nodes run` mirrors the models exec behavior (defaults + approvals):
@@ -47,8 +55,14 @@ clawdbot nodes run --agent main --node <id|name|ip> --raw "git status"
- Reads `tools.exec.*` (plus `agents.list[].tools.exec.*` overrides).
- Uses exec approvals (`exec.approval.request`) before invoking `system.run`.
- `--node` can be omitted when `tools.exec.node` is set.
- Requires a node that advertises `system.run` (macOS companion app or headless node host).
Flags:
- `--cwd <path>`: working directory.
- `--env <key=val>`: env override (repeatable).
- `--command-timeout <ms>`: command timeout.
- `--invoke-timeout <ms>`: node invoke timeout (default `30000`).
- `--needs-screen-recording`: require screen recording permission.
- `--raw <command>`: run a shell string (`/bin/sh -lc` or `cmd.exe /c`).
- `--agent <id>`: agent-scoped approvals/allowlists (defaults to configured agent).
- `--ask <off|on-miss|always>`, `--security <deny|allowlist|full>`: overrides.

View File

@@ -16,6 +16,10 @@ Related:
```bash
clawdbot onboard
clawdbot onboard --flow quickstart
clawdbot onboard --flow manual
clawdbot onboard --mode remote --remote-url ws://gateway-host:18789
```
Flow notes:
- `quickstart`: minimal prompts, auto-generates a gateway token.
- `manual`: full prompts for port/bind/auth (alias of `advanced`).

View File

@@ -53,7 +53,6 @@ Clients can send richer periodic beacons via the `system-event` method. The mac
app uses this to report host name, IP, and `lastInputSeconds`.
### 4) Node connects (role: node)
When a node connects over the Gateway WebSocket with `role: node`, the Gateway
upserts a presence entry for that node (same flow as other WS clients).

View File

@@ -19,7 +19,7 @@ Goal: small, hard-to-misuse tool set so agents can list sessions, fetch history,
- Group chats use `agent:<agentId>:<channel>:group:<id>` or `agent:<agentId>:<channel>:channel:<id>` (pass the full key).
- Cron jobs use `cron:<job.id>`.
- Hooks use `hook:<uuid>` unless explicitly set.
- Node bridge uses `node-<nodeId>` unless explicitly set.
- Node sessions use `node-<nodeId>` unless explicitly set.
`global` and `unknown` are reserved values and are never listed. If `session.scope = "global"`, we alias it to `main` for all tools so callers never see `global`.

View File

@@ -52,7 +52,7 @@ the workspace is writable. See [Memory](/concepts/memory) and
- Other sources:
- Cron jobs: `cron:<job.id>`
- Webhooks: `hook:<uuid>` (unless explicitly set by the hook)
- Node bridge runs: `node-<nodeId>`
- Node runs: `node-<nodeId>`
## Lifecycle
- Reset policy: sessions are reused until they expire, and expiry is evaluated on the next inbound message.

View File

@@ -46,7 +46,7 @@ Common methods + events:
| Messaging | `send`, `poll`, `agent`, `agent.wait` | side-effects need `idempotencyKey` |
| Chat | `chat.history`, `chat.send`, `chat.abort`, `chat.inject` | WebChat uses these |
| Sessions | `sessions.list`, `sessions.patch`, `sessions.delete` | session admin |
| Nodes | `node.list`, `node.invoke`, `node.pair.*` | bridge + node actions |
| Nodes | `node.list`, `node.invoke`, `node.pair.*` | Gateway WS + node actions |
| Events | `tick`, `presence`, `agent`, `chat`, `health`, `shutdown` | server push |
Authoritative list lives in `src/gateway/server.ts` (`METHODS`, `EVENTS`).

View File

@@ -70,7 +70,7 @@ What this does:
- `CLAWDBOT_PROFILE=dev`
- `CLAWDBOT_STATE_DIR=~/.clawdbot-dev`
- `CLAWDBOT_CONFIG_PATH=~/.clawdbot-dev/clawdbot.json`
- `CLAWDBOT_GATEWAY_PORT=19001` (bridge/canvas/browser shift accordingly)
- `CLAWDBOT_GATEWAY_PORT=19001` (browser/canvas shift accordingly)
2) **Dev bootstrap** (`gateway --dev`)
- Writes a minimal config if missing (`gateway.mode=local`, bind loopback).

View File

@@ -109,6 +109,14 @@
"source": "/opencode/",
"destination": "/providers/opencode"
},
{
"source": "/mattermost",
"destination": "/channels/mattermost"
},
{
"source": "/mattermost/",
"destination": "/channels/mattermost"
},
{
"source": "/glm",
"destination": "/providers/glm"
@@ -133,6 +141,14 @@
"source": "/message/",
"destination": "/cli/message"
},
{
"source": "/mattermost",
"destination": "/channels/mattermost"
},
{
"source": "/mattermost/",
"destination": "/channels/mattermost"
},
{
"source": "/providers/discord",
"destination": "/channels/discord"
@@ -165,6 +181,14 @@
"source": "/providers/location/",
"destination": "/channels/location"
},
{
"source": "/providers/mattermost",
"destination": "/channels/mattermost"
},
{
"source": "/providers/mattermost/",
"destination": "/channels/mattermost"
},
{
"source": "/providers/msteams",
"destination": "/channels/msteams"
@@ -930,6 +954,7 @@
"channels/grammy",
"channels/discord",
"channels/slack",
"channels/mattermost",
"channels/signal",
"channels/imessage",
"channels/msteams",

View File

@@ -7,7 +7,7 @@ read_when:
# Bonjour / mDNS discovery
Clawdbot uses Bonjour (mDNS / DNSSD) as a **LANonly convenience** to discover
an active Gateway bridge. It is besteffort and does **not** replace SSH or
an active Gateway (WebSocket endpoint). It is besteffort and does **not** replace SSH or
Tailnet-based connectivity.
## Widearea Bonjour (Unicast DNSSD) over Tailscale
@@ -31,7 +31,7 @@ browse both `local.` and `clawdbot.internal.` automatically.
```json5
{
bridge: { bind: "tailnet" }, // tailnet-only (recommended)
gateway: { bind: "tailnet" }, // tailnet-only (recommended)
discovery: { wideArea: { enabled: true } } // enables clawdbot.internal DNS-SD publishing
}
```
@@ -63,13 +63,13 @@ In the Tailscale admin console:
Once clients accept tailnet DNS, iOS nodes can browse
`_clawdbot-gw._tcp` in `clawdbot.internal.` without multicast.
### Bridge listener security (recommended)
### Gateway listener security (recommended)
The bridge port (default `18790`) is a plain TCP service. By default it binds to
`0.0.0.0`, which makes it reachable from any interface on the gateway host.
The Gateway WS port (default `18789`) binds to loopback by default. For LAN/tailnet
access, bind explicitly and keep auth enabled.
For tailnetonly setups:
- Set `bridge.bind: "tailnet"` in `~/.clawdbot/clawdbot.json`.
- Set `gateway.bind: "tailnet"` in `~/.clawdbot/clawdbot.json`.
- Restart the Gateway (or restart the macOS menubar app).
## What advertises
@@ -87,11 +87,12 @@ The Gateway advertises small nonsecret hints to make UI flows convenient:
- `role=gateway`
- `displayName=<friendly name>`
- `lanHost=<hostname>.local`
- `gatewayPort=<port>` (informational; Gateway WS is usually loopbackonly)
- `bridgePort=<port>` (only when bridge is enabled)
- `gatewayPort=<port>` (Gateway WS + HTTP)
- `gatewayTls=1` (only when TLS is enabled)
- `gatewayTlsSha256=<sha256>` (only when TLS is enabled and fingerprint is available)
- `canvasPort=<port>` (only when the canvas host is enabled; default `18793`)
- `sshPort=<port>` (defaults to 22 when not overridden)
- `transport=bridge`
- `transport=gateway`
- `cliPath=<path>` (optional; absolute path to a runnable `clawdbot` entrypoint)
- `tailnetDns=<magicdns>` (optional hint when Tailnet is available)
@@ -125,8 +126,8 @@ The Gateway writes a rolling log file (printed on startup as
The iOS node uses `NWBrowser` to discover `_clawdbot-gw._tcp`.
To capture logs:
- Settings → Bridge → Advanced → **Discovery Debug Logs**
- Settings → Bridge → Advanced → **Discovery Logs** → reproduce → **Copy**
- Settings → Gateway → Advanced → **Discovery Debug Logs**
- Settings → Gateway → Advanced → **Discovery Logs** → reproduce → **Copy**
The log includes browser state transitions and resultset changes.
@@ -136,7 +137,7 @@ The log includes browser state transitions and resultset changes.
- **Multicast blocked**: some WiFi networks disable mDNS.
- **Sleep / interface churn**: macOS may temporarily drop mDNS results; retry.
- **Browse works but resolve fails**: keep machine names simple (avoid emojis or
punctuation), then restart the Gateway. The bridge instance name derives from
punctuation), then restart the Gateway. The service instance name derives from
the host name, so overly complex names can confuse some resolvers.
## Escaped instance names (`\032`)
@@ -150,9 +151,7 @@ sequences (e.g. spaces become `\032`).
## Disabling / configuration
- `CLAWDBOT_DISABLE_BONJOUR=1` disables advertising.
- `CLAWDBOT_BRIDGE_ENABLED=0` disables the bridge listener (and the bridge beacon).
- `bridge.bind` / `bridge.port` in `~/.clawdbot/clawdbot.json` control bridge bind/port.
- `CLAWDBOT_BRIDGE_HOST` / `CLAWDBOT_BRIDGE_PORT` still work as backcompat overrides.
- `gateway.bind` in `~/.clawdbot/clawdbot.json` controls the Gateway bind mode.
- `CLAWDBOT_SSH_PORT` overrides the SSH port advertised in TXT.
- `CLAWDBOT_TAILNET_DNS` publishes a MagicDNS hint in TXT.
- `CLAWDBOT_CLI_PATH` overrides the advertised CLI path.

View File

@@ -14,6 +14,9 @@ should use the unified Gateway WebSocket protocol instead.
If you are building an operator or node client, use the
[Gateway protocol](/gateway/protocol).
**Note:** Current Clawdbot builds no longer ship the TCP bridge listener; this document is kept for historical reference.
Legacy `bridge.*` config keys are no longer part of the config schema.
## Why we have both
- **Security boundary**: the bridge exposes a small allowlist instead of the
@@ -28,7 +31,7 @@ If you are building an operator or node client, use the
- TCP, one JSON object per line (JSONL).
- Optional TLS (when `bridge.tls.enabled` is true).
- Gateway owns the listener (default `18790`).
- Legacy default listener port was `18790` (current builds do not start a TCP bridge).
When TLS is enabled, discovery TXT records include `bridgeTls=1` plus
`bridgeTlsSha256` so nodes can pin the certificate.
@@ -54,7 +57,7 @@ Gateway → Client:
- `event`: chat updates for subscribed sessions
- `ping` / `pong`: keepalive
Exact allowlist is enforced in `src/gateway/server-bridge.ts`.
Legacy allowlist enforcement lived in `src/gateway/server-bridge.ts` (removed).
## Exec lifecycle events

View File

@@ -568,5 +568,5 @@ Save to `~/.clawdbot/clawdbot.json` and you can DM the bot from that number.
- If you set `dmPolicy: "open"`, the matching `allowFrom` list must include `"*"`.
- Provider IDs differ (phone numbers, user IDs, channel IDs). Use the provider docs to confirm the format.
- Optional sections to add later: `web`, `browser`, `ui`, `bridge`, `discovery`, `canvasHost`, `talk`, `signal`, `imessage`.
- Optional sections to add later: `web`, `browser`, `ui`, `discovery`, `canvasHost`, `talk`, `signal`, `imessage`.
- See [Providers](/channels/whatsapp) and [Troubleshooting](/gateway/troubleshooting) for deeper setup notes.

View File

@@ -543,7 +543,7 @@ Notes:
- Outbound commands default to account `default` if present; otherwise the first configured account id (sorted).
- The legacy single-account Baileys auth dir is migrated by `clawdbot doctor` into `whatsapp/default`.
### `channels.telegram.accounts` / `channels.discord.accounts` / `channels.slack.accounts` / `channels.signal.accounts` / `channels.imessage.accounts`
### `channels.telegram.accounts` / `channels.discord.accounts` / `channels.slack.accounts` / `channels.mattermost.accounts` / `channels.signal.accounts` / `channels.imessage.accounts`
Run multiple accounts per channel (each account has its own `accountId` and optional `name`):
@@ -1204,6 +1204,44 @@ Slack action groups (gate `slack` tool actions):
| memberInfo | enabled | Member info |
| emojiList | enabled | Custom emoji list |
### `channels.mattermost` (bot token)
Mattermost ships as a plugin and is not bundled with the core install.
Install it first: `clawdbot plugins install @clawdbot/mattermost` (or `./extensions/mattermost` from a git checkout).
Mattermost requires a bot token plus the base URL for your server:
```json5
{
channels: {
mattermost: {
enabled: true,
botToken: "mm-token",
baseUrl: "https://chat.example.com",
dmPolicy: "pairing",
chatmode: "oncall", // oncall | onmessage | onchar
oncharPrefixes: [">", "!"],
textChunkLimit: 4000
}
}
}
```
Clawdbot starts Mattermost when the account is configured (bot token + base URL) and enabled. The token + base URL are resolved from `channels.mattermost.botToken` + `channels.mattermost.baseUrl` or `MATTERMOST_BOT_TOKEN` + `MATTERMOST_URL` for the default account (unless `channels.mattermost.enabled` is `false`).
Chat modes:
- `oncall` (default): respond to channel messages only when @mentioned.
- `onmessage`: respond to every channel message.
- `onchar`: respond when a message starts with a trigger prefix (`channels.mattermost.oncharPrefixes`, default `[">", "!"]`).
Access control:
- Default DMs: `channels.mattermost.dmPolicy="pairing"` (unknown senders get a pairing code).
- Public DMs: `channels.mattermost.dmPolicy="open"` plus `channels.mattermost.allowFrom=["*"]`.
- Groups: `channels.mattermost.groupPolicy="allowlist"` by default (mention-gated). Use `channels.mattermost.groupAllowFrom` to restrict senders.
Multi-account support lives under `channels.mattermost.accounts` (see the multi-account section above). Env vars only apply to the default account.
Use `channel:<id>` or `user:<id>` (or `@username`) when specifying delivery targets; bare ids are treated as channel ids.
### `channels.signal` (signal-cli)
Signal reactions can emit system events (shared reaction tooling):
@@ -1690,7 +1728,7 @@ auto-compaction, instructing the model to store durable memories on disk (e.g.
`memory/YYYY-MM-DD.md`). It triggers when the session token estimate crosses a
soft threshold below the compaction limit.
Defaults:
Legacy defaults:
- `memoryFlush.enabled`: `true`
- `memoryFlush.softThresholdTokens`: `4000`
- `memoryFlush.prompt` / `memoryFlush.systemPrompt`: built-in defaults with `NO_REPLY`
@@ -1735,8 +1773,9 @@ Block streaming:
with `maxChars` capped to the channel text limit. Signal/Slack/Discord default
to `minChars: 1500` unless overridden.
Channel overrides: `channels.whatsapp.blockStreamingCoalesce`, `channels.telegram.blockStreamingCoalesce`,
`channels.discord.blockStreamingCoalesce`, `channels.slack.blockStreamingCoalesce`, `channels.signal.blockStreamingCoalesce`,
`channels.imessage.blockStreamingCoalesce`, `channels.msteams.blockStreamingCoalesce` (and per-account variants).
`channels.discord.blockStreamingCoalesce`, `channels.slack.blockStreamingCoalesce`, `channels.mattermost.blockStreamingCoalesce`,
`channels.signal.blockStreamingCoalesce`, `channels.imessage.blockStreamingCoalesce`, `channels.msteams.blockStreamingCoalesce`
(and per-account variants).
- `agents.defaults.humanDelay`: randomized pause between **block replies** after the first.
Modes: `off` (default), `natural` (8002500ms), `custom` (use `minMs`/`maxMs`).
Per-agent override: `agents.list[].humanDelay`.
@@ -2784,7 +2823,7 @@ Hot-applied (no full gateway restart):
Requires full Gateway restart:
- `gateway` (port/bind/auth/control UI/tailscale)
- `bridge`
- `bridge` (legacy)
- `discovery`
- `canvasHost`
- `plugins`
@@ -2802,7 +2841,7 @@ Convenience flags (CLI):
- `clawdbot --dev …` → uses `~/.clawdbot-dev` + shifts ports from base `19001`
- `clawdbot --profile <name> …` → uses `~/.clawdbot-<name>` (port via config/env/flags)
See [Gateway runbook](/gateway) for the derived port mapping (gateway/bridge/browser/canvas).
See [Gateway runbook](/gateway) for the derived port mapping (gateway/browser/canvas).
See [Multiple gateways](/gateway/multiple-gateways) for browser/CDP port isolation details.
Example:
@@ -2921,7 +2960,7 @@ The Gateway serves a directory of HTML/CSS/JS over HTTP so iOS/Android nodes can
Default root: `~/clawd/canvas`
Default port: `18793` (chosen to avoid the clawd browser CDP port `18792`)
The server listens on the **bridge bind host** (LAN or Tailnet) so nodes can reach it.
The server listens on the **gateway bind host** (LAN or Tailnet) so nodes can reach it.
The server:
- serves files under `canvasHost.root`
@@ -2950,9 +2989,13 @@ Disable with:
- config: `canvasHost: { enabled: false }`
- env: `CLAWDBOT_SKIP_CANVAS_HOST=1`
### `bridge` (node bridge server)
### `bridge` (legacy TCP bridge, removed)
The Gateway can expose a simple TCP bridge for nodes (iOS/Android), typically on port `18790`.
Current builds no longer include the TCP bridge listener; `bridge.*` config keys are ignored.
Nodes connect over the Gateway WebSocket. This section is kept for historical reference.
Legacy behavior:
- The Gateway could expose a simple TCP bridge for nodes (iOS/Android), typically on port `18790`.
Defaults:
- enabled: `true`

View File

@@ -3,7 +3,7 @@ summary: "Node discovery and transports (Bonjour, Tailscale, SSH) for finding th
read_when:
- Implementing or changing Bonjour discovery/advertising
- Adjusting remote connection modes (direct vs SSH)
- Designing bridge + pairing for remote nodes
- Designing node discovery + pairing for remote nodes
---
# Discovery & transports
@@ -17,17 +17,18 @@ The design goal is to keep all network discovery/advertising in the **Node Gatew
## Terms
- **Gateway**: a single long-running gateway process that owns state (sessions, pairing, node registry) and runs channels. Most setups use one per host; isolated multi-gateway setups are possible.
- **Gateway WS (loopback)**: the existing gateway WebSocket control endpoint on `127.0.0.1:18789`.
- **Bridge (direct transport)**: a LAN/tailnet-facing endpoint owned by the gateway that allows authenticated clients/nodes to call a scoped subset of gateway methods. The bridge exists so the gateway can remain loopback-only.
- **Gateway WS (control plane)**: the WebSocket endpoint on `127.0.0.1:18789` by default; can be bound to LAN/tailnet via `gateway.bind`.
- **Direct WS transport**: a LAN/tailnet-facing Gateway WS endpoint (no SSH).
- **SSH transport (fallback)**: remote control by forwarding `127.0.0.1:18789` over SSH.
- **Legacy TCP bridge (deprecated/removed)**: older node transport (see [Bridge protocol](/gateway/bridge-protocol)); no longer advertised for discovery.
Protocol details:
- [Gateway protocol](/gateway/protocol)
- [Bridge protocol](/gateway/bridge-protocol)
- [Bridge protocol (legacy)](/gateway/bridge-protocol)
## Why we keep both “direct” and SSH
- **Direct bridge** is the best UX on the same network and within a tailnet:
- **Direct WS** is the best UX on the same network and within a tailnet:
- auto-discovery on LAN via Bonjour
- pairing tokens + ACLs owned by the gateway
- no shell access required; protocol surface can stay tight and auditable
@@ -43,7 +44,7 @@ Protocol details:
Bonjour is best-effort and does not cross networks. It is only used for “same LAN” convenience.
Target direction:
- The **gateway** advertises its bridge via Bonjour.
- The **gateway** advertises its WS endpoint via Bonjour.
- Clients browse and show a “pick a gateway” list, then store the chosen endpoint.
Troubleshooting and beacon details: [Bonjour](/gateway/bonjour).
@@ -56,19 +57,19 @@ Troubleshooting and beacon details: [Bonjour](/gateway/bonjour).
- `role=gateway`
- `lanHost=<hostname>.local`
- `sshPort=22` (or whatever is advertised)
- `gatewayPort=18789` (loopback WS port; informational)
- `bridgePort=18790` (when bridge is enabled)
- `gatewayPort=18789` (Gateway WS + HTTP)
- `gatewayTls=1` (only when TLS is enabled)
- `gatewayTlsSha256=<sha256>` (only when TLS is enabled and fingerprint is available)
- `canvasPort=18793` (default canvas host port; serves `/__clawdbot__/canvas/`)
- `cliPath=<path>` (optional; absolute path to a runnable `clawdbot` entrypoint or binary)
- `tailnetDns=<magicdns>` (optional hint; auto-detected when Tailscale is available)
Disable/override:
- `CLAWDBOT_DISABLE_BONJOUR=1` disables advertising.
- `CLAWDBOT_BRIDGE_ENABLED=0` disables the bridge listener.
- `bridge.bind` / `bridge.port` in `~/.clawdbot/clawdbot.json` control bridge bind/port (preferred).
- `CLAWDBOT_BRIDGE_HOST` / `CLAWDBOT_BRIDGE_PORT` still work as a back-compat override when `bridge.bind` / `bridge.port` are not set.
- `CLAWDBOT_SSH_PORT` overrides the SSH port advertised in the bridge beacon (defaults to 22).
- `CLAWDBOT_TAILNET_DNS` publishes a `tailnetDns` hint (MagicDNS) in the bridge beacon (auto-detected if unset).
- `gateway.bind` in `~/.clawdbot/clawdbot.json` controls the Gateway bind mode.
- `CLAWDBOT_SSH_PORT` overrides the SSH port advertised in TXT (defaults to 22).
- `CLAWDBOT_TAILNET_DNS` publishes a `tailnetDns` hint (MagicDNS).
- `CLAWDBOT_CLI_PATH` overrides the advertised CLI path.
### 2) Tailnet (cross-network)
@@ -97,13 +98,13 @@ Recommended client behavior:
The gateway is the source of truth for node/client admission.
- Pairing requests are created/approved/rejected in the gateway (see [Gateway pairing](/gateway/pairing)).
- The bridge enforces:
- The gateway enforces:
- auth (token / keypair)
- scopes/ACLs (bridge is not a raw proxy to every gateway method)
- scopes/ACLs (the gateway is not a raw proxy to every method)
- rate limits
## Responsibilities by component
- **Gateway**: advertises discovery beacons, owns pairing decisions, runs the bridge listener.
- **Gateway**: advertises discovery beacons, owns pairing decisions, and hosts the WS endpoint.
- **macOS app**: helps you pick a gateway, shows pairing prompts, and uses SSH only as a fallback.
- **iOS/Android nodes**: browse Bonjour as a convenience and connect via the paired bridge.
- **iOS/Android nodes**: browse Bonjour as a convenience and connect to the paired Gateway WS.

View File

@@ -82,14 +82,12 @@ Defaults (can be overridden via env/flags/config):
- `CLAWDBOT_STATE_DIR=~/.clawdbot-dev`
- `CLAWDBOT_CONFIG_PATH=~/.clawdbot-dev/clawdbot.json`
- `CLAWDBOT_GATEWAY_PORT=19001` (Gateway WS + HTTP)
- `bridge.port=19002` (derived: `gateway.port+1`)
- `browser.controlUrl=http://127.0.0.1:19003` (derived: `gateway.port+2`)
- `canvasHost.port=19005` (derived: `gateway.port+4`)
- `agents.defaults.workspace` default becomes `~/clawd-dev` when you run `setup`/`onboard` under `--dev`.
Derived ports (rules of thumb):
- Base port = `gateway.port` (or `CLAWDBOT_GATEWAY_PORT` / `--port`)
- `bridge.port = base + 1` (or `CLAWDBOT_BRIDGE_PORT` / config override)
- `browser.controlUrl port = base + 2` (or `CLAWDBOT_BROWSER_CONTROL_URL` / config override)
- `canvasHost.port = base + 4` (or `CLAWDBOT_CANVAS_HOST_PORT` / config override)
- Browser profile CDP ports auto-allocate from `browser.controlPort + 9 .. + 108` (persisted per profile).
@@ -114,7 +112,7 @@ CLAWDBOT_CONFIG_PATH=~/.clawdbot/b.json CLAWDBOT_STATE_DIR=~/.clawdbot-b clawdbo
```
## Protocol (operator view)
- Full docs: [Gateway protocol](/gateway/protocol) and [Bridge protocol](/gateway/bridge-protocol).
- Full docs: [Gateway protocol](/gateway/protocol) and [Bridge protocol (legacy)](/gateway/bridge-protocol).
- Mandatory first frame from client: `req {type:"req", id, method:"connect", params:{minProtocol,maxProtocol,client:{id,displayName?,version,platform,deviceFamily?,modelIdentifier?,mode,instanceId?}, caps, auth?, locale?, userAgent? } }`.
- Gateway replies `res {type:"res", id, ok:true, payload:hello-ok }` (or `ok:false` with an error, then closes).
- After handshake:
@@ -130,7 +128,7 @@ CLAWDBOT_CONFIG_PATH=~/.clawdbot/b.json CLAWDBOT_STATE_DIR=~/.clawdbot-b clawdbo
- `system-event` — post a presence/system note (structured).
- `send` — send a message via the active channel(s).
- `agent` — run an agent turn (streams events back on same connection).
- `node.list` — list paired + currently-connected bridge nodes (includes `caps`, `deviceFamily`, `modelIdentifier`, `paired`, `connected`, and advertised `commands`).
- `node.list` — list paired + currently-connected nodes (includes `caps`, `deviceFamily`, `modelIdentifier`, `paired`, `connected`, and advertised `commands`).
- `node.describe` — describe a node (capabilities + supported `node.invoke` commands; works for paired nodes and for currently-connected unpaired nodes).
- `node.invoke` — invoke a command on a node (e.g. `canvas.*`, `camera.*`).
- `node.pair.*` — pairing lifecycle (`request`, `list`, `approve`, `reject`, `verify`).

View File

@@ -51,7 +51,7 @@ You can tune console verbosity independently via:
## Tool summary redaction
Verbose tool summaries (e.g. `🛠️ exec: ...`) can mask sensitive tokens before they hit the
Verbose tool summaries (e.g. `🛠️ Exec: ...`) can mask sensitive tokens before they hit the
console stream. This is **tools-only** and does not alter file logs.
- `logging.redactSensitive`: `off` | `tools` (default: `tools`)

View File

@@ -13,7 +13,7 @@ Most setups should use one Gateway because a single Gateway can handle multiple
- `CLAWDBOT_STATE_DIR` — per-instance sessions, creds, caches
- `agents.defaults.workspace` — per-instance workspace root
- `gateway.port` (or `--port`) — unique per instance
- Derived ports (bridge/browser/canvas) must not overlap
- Derived ports (browser/canvas) must not overlap
If these are shared, you will hit config races and port conflicts.
@@ -47,7 +47,7 @@ Run a second Gateway on the same host with its own:
This keeps the rescue bot isolated from the main bot so it can debug or apply config changes if the primary bot is down.
Port spacing: leave at least 20 ports between base ports so the derived bridge/browser/canvas/CDP ports never collide.
Port spacing: leave at least 20 ports between base ports so the derived browser/canvas/CDP ports never collide.
### How to install (rescue bot)
@@ -73,7 +73,6 @@ clawdbot --profile rescue gateway install
Base port = `gateway.port` (or `CLAWDBOT_GATEWAY_PORT` / `--port`).
- `bridge.port = base + 1`
- `browser.controlUrl port = base + 2`
- `canvasHost.port = base + 4`
- Browser profile CDP ports auto-allocate from `browser.controlPort + 9 .. + 108`

View File

@@ -19,12 +19,12 @@ Only clients that explicitly call `node.pair.*` use this flow.
- **Pending request**: a node asked to join; requires approval.
- **Paired node**: approved node with an issued auth token.
- **Bridge**: transport endpoint only; it forwards requests but does not decide
membership.
- **Transport**: the Gateway WS endpoint forwards requests but does not decide
membership. (Legacy TCP bridge support is deprecated/removed.)
## How pairing works
1. A node connects to the bridge and requests pairing.
1. A node connects to the Gateway WS and requests pairing.
2. The Gateway stores a **pending request** and emits `node.pair.requested`.
3. You approve or reject the request (CLI or UI).
4. On approval, the Gateway issues a **new token** (tokens are rotated on repair).
@@ -85,9 +85,8 @@ Security notes:
- Tokens are secrets; treat `paired.json` as sensitive.
- Rotating a token requires re-approval (or deleting the node entry).
## Bridge behavior
## Transport behavior
- The bridge is **transport only**; it does not store membership.
- The transport is **stateless**; it does not store membership.
- If the Gateway is offline or pairing is disabled, nodes cannot pair.
- If the bridge is running but the Gateway is in remote mode, pairing still
happens against the remote Gateways store.
- If the Gateway is in remote mode, pairing still happens against the remote Gateways store.

View File

@@ -8,7 +8,7 @@ read_when:
This repo supports “remote over SSH” by keeping a single Gateway (the master) running on a dedicated host (desktop/server) and connecting clients to it.
- For **operators (you / the macOS app)**: SSH tunneling is the universal fallback.
- For **nodes (iOS/Android and future devices)**: prefer the Gateway **Bridge** when on the same LAN/tailnet (see [Discovery](/gateway/discovery)).
- For **nodes (iOS/Android and future devices)**: connect to the Gateway **WebSocket** (LAN/tailnet or SSH tunnel as needed).
## The core idea
@@ -55,12 +55,12 @@ One gateway service owns state + channels. Nodes are peripherals.
Flow example (Telegram → node):
- Telegram message arrives at the **Gateway**.
- Gateway runs the **agent** and decides whether to call a node tool.
- Gateway calls the **node** over the Bridge (`node.*` RPC).
- Gateway calls the **node** over the Gateway WebSocket (`node.*` RPC).
- Node returns the result; Gateway replies back out to Telegram.
Notes:
- **Nodes do not run the gateway service.** Only one gateway should run per host unless you intentionally run isolated profiles (see [Multiple gateways](/gateway/multiple-gateways)).
- macOS app “node mode” is just a node client over the Bridge.
- macOS app “node mode” is just a node client over the Gateway WebSocket.
## SSH tunnel (CLI + tools)

View File

@@ -94,8 +94,8 @@ clawdbot gateway --tailscale funnel --auth password
or `tailscale funnel` configuration on shutdown.
- `gateway.bind: "tailnet"` is a direct Tailnet bind (no HTTPS, no Serve/Funnel).
- `gateway.bind: "auto"` prefers loopback; use `tailnet` if you want Tailnet-only.
- Serve/Funnel only expose the **Gateway control UI + WS**. Node **bridge** traffic
uses the separate bridge port (default `18790`) and is **not** proxied by Serve.
- Serve/Funnel only expose the **Gateway control UI + WS**. Nodes connect over
the same Gateway WS endpoint, so Serve can work for node access.
## Browser control server (remote Gateway + local browser)

View File

@@ -13,6 +13,7 @@ read_when:
<p align="center">
<strong>Any OS + WhatsApp/Telegram/Discord/iMessage gateway for AI agents (Pi).</strong><br />
Plugins add Mattermost and more.
Send a message, get an agent response — from your pocket.
</p>
@@ -23,7 +24,7 @@ read_when:
<a href="/start/clawd">Clawdbot assistant setup</a>
</p>
Clawdbot bridges WhatsApp (via WhatsApp Web / Baileys), Telegram (Bot API / grammY), Discord (Bot API / channels.discord.js), and iMessage (imsg CLI) to coding agents like [Pi](https://github.com/badlogic/pi-mono).
Clawdbot bridges WhatsApp (via WhatsApp Web / Baileys), Telegram (Bot API / grammY), Discord (Bot API / channels.discord.js), and iMessage (imsg CLI) to coding agents like [Pi](https://github.com/badlogic/pi-mono). Plugins add Mattermost (Bot API + WebSocket) and more.
Clawdbot also powers [Clawd](https://clawd.me), the spacelobster assistant.
## Start here
@@ -44,12 +45,12 @@ Remote access: [Web surfaces](/web) and [Tailscale](/gateway/tailscale)
## How it works
```
WhatsApp / Telegram / Discord
WhatsApp / Telegram / Discord / iMessage (+ plugins)
┌───────────────────────────┐
│ Gateway │ ws://127.0.0.1:18789 (loopback-only)
│ (single source) │ tcp://0.0.0.0:18790 (Bridge)
│ (single source) │
│ │ http://<gateway-host>:18793
│ │ /__clawdbot__/canvas/ (Canvas host)
└───────────┬───────────────┘
@@ -58,8 +59,8 @@ WhatsApp / Telegram / Discord
├─ CLI (clawdbot …)
├─ Chat UI (SwiftUI)
├─ macOS app (Clawdbot.app)
├─ iOS node via Bridge + pairing
└─ Android node via Bridge + pairing
├─ iOS node via Gateway WS + pairing
└─ Android node via Gateway WS + pairing
```
Most operations flow through the **Gateway** (`clawdbot gateway`), a single long-running process that owns channel connections and the WebSocket control plane.
@@ -70,7 +71,7 @@ Most operations flow through the **Gateway** (`clawdbot gateway`), a single long
- **Loopback-first**: Gateway WS defaults to `ws://127.0.0.1:18789`.
- The wizard now generates a gateway token by default (even for loopback).
- For Tailnet access, run `clawdbot gateway --bind tailnet --token ...` (token is required for non-loopback binds).
- **Bridge for nodes**: optional LAN/tailnet-facing bridge on `tcp://0.0.0.0:18790` for paired nodes (Bonjour-discoverable).
- **Nodes**: connect to the Gateway WebSocket (LAN/tailnet/SSH as needed); legacy TCP bridge is deprecated/removed.
- **Canvas host**: HTTP file server on `canvasHost.port` (default `18793`), serving `/__clawdbot__/canvas/` for node WebViews; see [Gateway configuration](/gateway/configuration) (`canvasHost`).
- **Remote use**: SSH tunnel or tailnet/VPN; see [Remote access](/gateway/remote) and [Discovery](/gateway/discovery).
@@ -79,6 +80,7 @@ Most operations flow through the **Gateway** (`clawdbot gateway`), a single long
- 📱 **WhatsApp Integration** — Uses Baileys for WhatsApp Web protocol
- ✈️ **Telegram Bot** — DMs + groups via grammY
- 🎮 **Discord Bot** — DMs + guild channels via channels.discord.js
- 🧩 **Mattermost Bot (plugin)** — Bot token + WebSocket events
- 💬 **iMessage** — Local imsg CLI integration (macOS)
- 🤖 **Agent bridge** — Pi (RPC mode) with tool streaming
- ⏱️ **Streaming + chunking** — Block streaming + Telegram draft streaming details ([/concepts/streaming](/concepts/streaming))
@@ -190,6 +192,7 @@ Example:
- [Control UI (browser)](/web/control-ui)
- [Telegram](/channels/telegram)
- [Discord](/channels/discord)
- [Mattermost (plugin)](/channels/mattermost)
- [iMessage](/channels/imessage)
- [Groups](/concepts/groups)
- [WhatsApp group messages](/concepts/group-messages)

View File

@@ -36,7 +36,7 @@ Local trust:
- [Remote access (SSH)](/gateway/remote)
- [Tailscale](/gateway/tailscale)
## Nodes + bridge
## Nodes + transports
- [Nodes overview](/nodes)
- [Bridge protocol (legacy nodes)](/gateway/bridge-protocol)

View File

@@ -138,7 +138,7 @@ Notes:
## Safety + practical limits
- Camera and microphone access trigger the usual OS permission prompts (and require usage strings in Info.plist).
- Video clips are capped (currently `<= 60s`) to avoid oversized bridge payloads (base64 overhead + message limits).
- Video clips are capped (currently `<= 60s`) to avoid oversized node payloads (base64 overhead + message limits).
## macOS screen video (OS-level)

View File

@@ -10,7 +10,7 @@ read_when:
A **node** is a companion device (macOS/iOS/Android/headless) that connects to the Gateway **WebSocket** (same port as operators) with `role: "node"` and exposes a command surface (e.g. `canvas.*`, `camera.*`, `system.*`) via `node.invoke`. Protocol details: [Gateway protocol](/gateway/protocol).
Legacy transport: [Bridge protocol](/gateway/bridge-protocol) (TCP JSONL; for older node clients only).
Legacy transport: [Bridge protocol](/gateway/bridge-protocol) (TCP JSONL; deprecated/removed for current nodes).
macOS can also run in **node mode**: the menubar app connects to the Gateways WS server and exposes its local canvas/camera commands as a node (so `clawdbot nodes …` works against this Mac).
@@ -61,7 +61,7 @@ clawdbot node run --host <gateway-host> --port 18789 --display-name "Build Node"
```bash
clawdbot node install --host <gateway-host> --port 18789 --display-name "Build Node"
clawdbot node start
clawdbot node restart
```
### Pair + name
@@ -243,6 +243,7 @@ Notes:
- `system.notify` respects notification permission state on the macOS app.
- `system.run` supports `--cwd`, `--env KEY=VAL`, `--command-timeout`, and `--needs-screen-recording`.
- `system.notify` supports `--priority <passive|active|timeSensitive>` and `--delivery <system|overlay|auto>`.
- macOS nodes drop `PATH` overrides; headless node hosts only accept `PATH` when it prepends the node host PATH.
- On macOS node mode, `system.run` is gated by exec approvals in the macOS app (Settings → Exec approvals).
Ask/allowlist/full behave the same as the headless node host; denied prompts return `SYSTEM_RUN_DENIED`.
- On headless node host, `system.run` is gated by exec approvals (`~/.clawdbot/exec-approvals.json`).
@@ -285,12 +286,12 @@ or for running a minimal node alongside a server.
Start it:
```bash
clawdbot node run --host <gateway-host> --port 18790
clawdbot node run --host <gateway-host> --port 18789
```
Notes:
- Pairing is still required (the Gateway will show a node approval prompt).
- The node host stores its node id + pairing token in `~/.clawdbot/node.json`.
- The node host stores its node id, token, display name, and gateway connection info in `~/.clawdbot/node.json`.
- Exec approvals are enforced locally via `~/.clawdbot/exec-approvals.json`
(see [Exec approvals](/tools/exec-approvals)).
- On macOS, the headless node host prefers the companion app exec host when reachable and falls

View File

@@ -41,7 +41,7 @@ Notes:
Who receives it:
- All WebSocket clients (macOS app, WebChat, etc.)
- All connected bridge nodes (iOS/Android), and also on node connect as an initial “current state” push.
- All connected nodes (iOS/Android), and also on node connect as an initial “current state” push.
## Client behavior
@@ -53,9 +53,9 @@ Who receives it:
### iOS node
- Uses the global list for `VoiceWakeManager` trigger detection.
- Editing Wake Words in Settings calls `voicewake.set` (over the bridge) and also keeps local wake-word detection responsive.
- Editing Wake Words in Settings calls `voicewake.set` (over the Gateway WS) and also keeps local wake-word detection responsive.
### Android node
- Exposes a Wake Words editor in Settings.
- Calls `voicewake.set` over the bridge so edits sync everywhere.
- Calls `voicewake.set` over the Gateway WS so edits sync everywhere.

View File

@@ -129,7 +129,6 @@ CLAWDBOT_IMAGE=clawdbot:latest
CLAWDBOT_GATEWAY_TOKEN=change-me-now
CLAWDBOT_GATEWAY_BIND=lan
CLAWDBOT_GATEWAY_PORT=18789
CLAWDBOT_BRIDGE_PORT=18790
CLAWDBOT_CONFIG_DIR=/root/.clawdbot
CLAWDBOT_WORKSPACE_DIR=/root/clawd
@@ -166,7 +165,6 @@ services:
- TERM=xterm-256color
- CLAWDBOT_GATEWAY_BIND=${CLAWDBOT_GATEWAY_BIND}
- CLAWDBOT_GATEWAY_PORT=${CLAWDBOT_GATEWAY_PORT}
- CLAWDBOT_BRIDGE_PORT=${CLAWDBOT_BRIDGE_PORT}
- CLAWDBOT_GATEWAY_TOKEN=${CLAWDBOT_GATEWAY_TOKEN}
- GOG_KEYRING_PASSWORD=${GOG_KEYRING_PASSWORD}
- XDG_CONFIG_HOME=${XDG_CONFIG_HOME}
@@ -179,9 +177,8 @@ services:
# To expose it publicly, remove the `127.0.0.1:` prefix and firewall accordingly.
- "127.0.0.1:${CLAWDBOT_GATEWAY_PORT}:18789"
# Optional: only if you run iOS/Android nodes against this VPS.
# If you expose these publicly, read /gateway/security and firewall accordingly.
# - "${CLAWDBOT_BRIDGE_PORT}:18790"
# Optional: only if you run iOS/Android nodes against this VPS and need Canvas host.
# If you expose this publicly, read /gateway/security and firewall accordingly.
# - "18793:18793"
command:
[

View File

@@ -40,7 +40,7 @@ node commands return `CANVAS_DISABLED`.
## Agent API surface
Canvas is exposed via the **node bridge**, so the agent can:
Canvas is exposed via the **Gateway WebSocket**, so the agent can:
- show/hide the panel
- navigate to a path or URL

View File

@@ -45,6 +45,13 @@ present. To reset manually:
rm ~/.clawdbot/disable-launchagent
```
## Attach-only mode
To force the macOS app to **never install or manage launchd**, launch it with
`--attach-only` (or `--no-launchd`). This sets `~/.clawdbot/disable-launchagent`,
so the app only attaches to an already running Gateway. You can toggle the same
behavior in Debug Settings.
## Remote mode
Remote mode never starts a local Gateway. The app uses an SSH tunnel to the

View File

@@ -8,7 +8,7 @@ read_when:
## What is shown
- We surface the current agent work state in the menu bar icon and in the first status row of the menu.
- Health status is hidden while work is active; it returns when all sessions are idle.
- The “Nodes” block in the menu lists **devices** only (gateway bridge nodes via `node.list`), not client/presence entries.
- The “Nodes” block in the menu lists **devices** only (paired nodes via `node.list`), not client/presence entries.
- A “Usage” section appears under Context when provider usage snapshots are available.
## State model

View File

@@ -1,5 +1,5 @@
---
summary: "macOS IPC architecture for Clawdbot app, gateway node bridge, and PeekabooBridge"
summary: "macOS IPC architecture for Clawdbot app, gateway node transport, and PeekabooBridge"
read_when:
- Editing IPC contracts or menu bar app IPC
---
@@ -13,21 +13,21 @@ read_when:
- Predictable permissions: always the same signed bundle ID, launched by launchd, so TCC grants stick.
## How it works
### Gateway + node bridge
### Gateway + node transport
- The app runs the Gateway (local mode) and connects to it as a node.
- Agent actions are performed via `node.invoke` (e.g. `system.run`, `system.notify`, `canvas.*`).
### Node service + app IPC
- A headless node host service connects to the Gateway bridge.
- A headless node host service connects to the Gateway WebSocket.
- `system.run` requests are forwarded to the macOS app over a local Unix socket.
- The app performs the exec in UI context, prompts if needed, and returns output.
Diagram (SCI):
```
Agent -> Gateway -> Bridge -> Node Service (TS)
| IPC (UDS + token + HMAC + TTL)
v
Mac App (UI + TCC + system.run)
Agent -> Gateway -> Node Service (WS)
| IPC (UDS + token + HMAC + TTL)
v
Mac App (UI + TCC + system.run)
```
### PeekabooBridge (UI automation)

View File

@@ -62,7 +62,7 @@ Node service + app IPC:
Diagram (SCI):
```
Gateway -> Bridge -> Node Service (TS)
Gateway -> Node Service (WS)
| IPC (UDS + token + HMAC + TTL)
v
Mac App (UI + TCC + system.run)
@@ -99,7 +99,7 @@ Example:
```
Notes:
- `allowlist` entries are JSON-encoded argv arrays.
- `allowlist` entries are glob patterns for resolved binary paths.
- Choosing “Always Allow” in the prompt adds that command to the allowlist.
- `system.run` environment overrides are filtered (drops `PATH`, `DYLD_*`, `LD_*`, `NODE_OPTIONS`, `PYTHON*`, `PERL*`, `RUBYOPT`) and then merged with the apps environment.

View File

@@ -61,6 +61,7 @@ Plugins can register:
- CLI commands
- Background services
- Optional config validation
- **Skills** (by listing `skills` directories in the plugin manifest)
Plugins run **inprocess** with the Gateway, so treat them as trusted code.
Tool authoring guide: [Plugin agent tools](/plugins/agent-tools).

View File

@@ -34,6 +34,7 @@ Optional keys:
- `kind` (string): plugin kind (example: `"memory"`).
- `channels` (array): channel ids registered by this plugin (example: `["matrix"]`).
- `providers` (array): provider ids registered by this plugin.
- `skills` (array): skill directories to load (relative to the plugin root).
- `name` (string): display name for the plugin.
- `description` (string): short plugin summary.
- `uiHints` (object): config field labels/placeholders/sensitive flags for UI rendering.

131
docs/prose.md Normal file
View File

@@ -0,0 +1,131 @@
---
summary: "OpenProse: .prose workflows, slash commands, and state in Clawdbot"
read_when:
- You want to run or write .prose workflows
- You want to enable the OpenProse plugin
- You need to understand state storage
---
# OpenProse
OpenProse is a portable, markdown-first workflow format for orchestrating AI sessions. In Clawdbot it ships as a plugin that installs an OpenProse skill pack plus a `/prose` slash command. Programs live in `.prose` files and can spawn multiple sub-agents with explicit control flow.
Official site: https://www.prose.md
## What it can do
- Multi-agent research + synthesis with explicit parallelism.
- Repeatable approval-safe workflows (code review, incident triage, content pipelines).
- Reusable `.prose` programs you can run across supported agent runtimes.
## Install + enable
Bundled plugins are disabled by default. Enable OpenProse:
```bash
clawdbot plugins enable open-prose
```
Restart the Gateway after enabling the plugin.
Dev/local checkout: `clawdbot plugins install ./extensions/open-prose`
Related docs: [Plugins](/plugin), [Plugin manifest](/plugins/manifest), [Skills](/tools/skills).
## Slash command
OpenProse registers `/prose` as a user-invocable skill command. It routes to the OpenProse VM instructions and uses Clawdbot tools under the hood.
Common commands:
```
/prose help
/prose run <file.prose>
/prose run <handle/slug>
/prose run <https://example.com/file.prose>
/prose compile <file.prose>
/prose examples
/prose update
```
## Example: a simple `.prose` file
```prose
# Research + synthesis with two agents running in parallel.
input topic: "What should we research?"
agent researcher:
model: sonnet
prompt: "You research thoroughly and cite sources."
agent writer:
model: opus
prompt: "You write a concise summary."
parallel:
findings = session: researcher
prompt: "Research {topic}."
draft = session: writer
prompt: "Summarize {topic}."
session "Merge the findings + draft into a final answer."
context: { findings, draft }
```
## File locations
OpenProse keeps state under `.prose/` in your workspace:
```
.prose/
├── .env
├── runs/
│ └── {YYYYMMDD}-{HHMMSS}-{random}/
│ ├── program.prose
│ ├── state.md
│ ├── bindings/
│ └── agents/
└── agents/
```
User-level persistent agents live at:
```
~/.prose/agents/
```
## State modes
OpenProse supports multiple state backends:
- **filesystem** (default): `.prose/runs/...`
- **in-context**: transient, for small programs
- **sqlite** (experimental): requires `sqlite3` binary
- **postgres** (experimental): requires `psql` and a connection string
Notes:
- sqlite/postgres are opt-in and experimental.
- postgres credentials flow into subagent logs; use a dedicated, least-privileged DB.
## Remote programs
`/prose run <handle/slug>` resolves to `https://p.prose.md/<handle>/<slug>`.
Direct URLs are fetched as-is. This uses the `web_fetch` tool (or `exec` for POST).
## Clawdbot runtime mapping
OpenProse programs map to Clawdbot primitives:
| OpenProse concept | Clawdbot tool |
| --- | --- |
| Spawn session / Task tool | `sessions_spawn` |
| File read/write | `read` / `write` |
| Web fetch | `web_fetch` |
If your tool allowlist blocks these tools, OpenProse programs will fail. See [Skills config](/tools/skills-config).
## Security + approvals
Treat `.prose` files like code. Review before running. Use Clawdbot tool allowlists and approval gates to control side effects.
For deterministic, approval-gated workflows, compare with [Lobster](/lobster).

View File

@@ -9,7 +9,7 @@ read_when:
Clawdbot can use many LLM providers. Pick a provider, authenticate, then set the
default model as `provider/model`.
Looking for chat channel docs (WhatsApp/Telegram/Discord/Slack/etc.)? See [Channels](/channels).
Looking for chat channel docs (WhatsApp/Telegram/Discord/Slack/Mattermost (plugin)/etc.)? See [Channels](/channels).
## Quick start

View File

@@ -12,6 +12,7 @@ This document explains how Clawdbot manages sessions end-to-end:
- **Session routing** (how inbound messages map to a `sessionKey`)
- **Session store** (`sessions.json`) and what it tracks
- **Transcript persistence** (`*.jsonl`) and its structure
- **Transcript hygiene** (provider-specific fixups before runs)
- **Context limits** (context window vs tracked tokens)
- **Compaction** (manual + auto-compaction) and where to hook pre-compaction work
- **Silent housekeeping** (e.g. memory writes that shouldnt produce user-visible output)
@@ -20,6 +21,7 @@ If you want a higher-level overview first, start with:
- [/concepts/session](/concepts/session)
- [/concepts/compaction](/concepts/compaction)
- [/concepts/session-pruning](/concepts/session-pruning)
- [/reference/transcript-hygiene](/reference/transcript-hygiene)
---

View File

@@ -0,0 +1,94 @@
---
summary: "Reference: provider-specific transcript sanitization and repair rules"
read_when:
- You are debugging provider request rejections tied to transcript shape
- You are changing transcript sanitization or tool-call repair logic
- You are investigating tool-call id mismatches across providers
---
# Transcript Hygiene (Provider Fixups)
This document describes **provider-specific fixes** applied to transcripts before a run
(building model context). These are **in-memory** adjustments used to satisfy strict
provider requirements. They do **not** rewrite the stored JSONL transcript on disk.
Scope includes:
- Tool call id sanitization
- Tool result pairing repair
- Turn validation / ordering
- Thought signature cleanup
- Image payload sanitization
If you need transcript storage details, see:
- [/reference/session-management-compaction](/reference/session-management-compaction)
---
## Where this runs
All transcript hygiene is centralized in the embedded runner:
- Policy selection: `src/agents/transcript-policy.ts`
- Sanitization/repair application: `sanitizeSessionHistory` in `src/agents/pi-embedded-runner/google.ts`
The policy uses `provider`, `modelApi`, and `modelId` to decide what to apply.
---
## Global rule: image sanitization
Image payloads are always sanitized to prevent provider-side rejection due to size
limits (downscale/recompress oversized base64 images).
Implementation:
- `sanitizeSessionMessagesImages` in `src/agents/pi-embedded-helpers/images.ts`
- `sanitizeContentBlocksImages` in `src/agents/tool-images.ts`
---
## Provider matrix (current behavior)
**OpenAI / OpenAI Codex**
- Image sanitization only.
- No tool call id sanitization.
- No tool result pairing repair.
- No turn validation or reordering.
- No synthetic tool results.
- No thought signature stripping.
**Google (Generative AI / Gemini CLI / Antigravity)**
- Tool call id sanitization: strict alphanumeric.
- Tool result pairing repair and synthetic tool results.
- Turn validation (Gemini-style turn alternation).
- Google turn ordering fixup (prepend a tiny user bootstrap if history starts with assistant).
- Antigravity Claude: normalize thinking signatures; drop unsigned thinking blocks.
**Anthropic / Minimax (Anthropic-compatible)**
- Tool result pairing repair and synthetic tool results.
- Turn validation (merge consecutive user turns to satisfy strict alternation).
**Mistral (including model-id based detection)**
- Tool call id sanitization: strict9 (alphanumeric length 9).
**OpenRouter Gemini**
- Thought signature cleanup: strip non-base64 `thought_signature` values (keep base64).
**Everything else**
- Image sanitization only.
---
## Historical behavior (pre-2026.1.22)
Before the 2026.1.22 release, Clawdbot applied multiple layers of transcript hygiene:
- A **transcript-sanitize extension** ran on every context build and could:
- Repair tool use/result pairing.
- Sanitize tool call ids (including a non-strict mode that preserved `_`/`-`).
- The runner also performed provider-specific sanitization, which duplicated work.
- Additional mutations occurred outside the provider policy, including:
- Stripping `<final>` tags from assistant text before persistence.
- Dropping empty assistant error turns.
- Trimming assistant content after tool calls.
This complexity caused cross-provider regressions (notably `openai-responses`
`call_id|fc_id` pairing). The 2026.1.22 cleanup removed the extension, centralized
logic in the runner, and made OpenAI **no-touch** beyond image sanitization.

View File

@@ -6,14 +6,14 @@ read_when:
---
# Building a personal assistant with Clawdbot (Clawd-style)
Clawdbot is a WhatsApp + Telegram + Discord gateway for **Pi** agents. This guide is the personal assistant setup: one dedicated WhatsApp number that behaves like your always-on agent.
Clawdbot is a WhatsApp + Telegram + Discord + iMessage gateway for **Pi** agents. Plugins add Mattermost. This guide is the "personal assistant" setup: one dedicated WhatsApp number that behaves like your always-on agent.
## ⚠️ Safety first
Youre putting an agent in a position to:
- run commands on your machine (depending on your Pi tool setup)
- read/write files in your workspace
- send messages back out via WhatsApp/Telegram/Discord
- send messages back out via WhatsApp/Telegram/Discord/Mattermost (plugin)
Start conservative:
- Always set `channels.whatsapp.allowFrom` (never run open-to-the-world on your personal Mac).

View File

@@ -178,7 +178,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
### What is Clawdbot, in one paragraph?
Clawdbot is a personal AI assistant you run on your own devices. It replies on the messaging surfaces you already use (WhatsApp, Telegram, Slack, Discord, Signal, iMessage, WebChat) and can also do voice + a live Canvas on supported platforms. The **Gateway** is the alwayson control plane; the assistant is the product.
Clawdbot is a personal AI assistant you run on your own devices. It replies on the messaging surfaces you already use (WhatsApp, Telegram, Slack, Mattermost (plugin), Discord, Signal, iMessage, WebChat) and can also do voice + a live Canvas on supported platforms. The **Gateway** is the always-on control plane; the assistant is the product.
## Quick start and first-run setup
@@ -235,7 +235,7 @@ Node **>= 22** is required. `pnpm` is recommended. Bun is **not recommended** fo
- **Model/auth setup** (Anthropic **setup-token** recommended for Claude subscriptions, OpenAI Codex OAuth supported, API keys optional, LM Studio local models supported)
- **Workspace** location + bootstrap files
- **Gateway settings** (bind/port/auth/tailscale)
- **Providers** (WhatsApp, Telegram, Discord, Signal, iMessage)
- **Providers** (WhatsApp, Telegram, Discord, Mattermost (plugin), Signal, iMessage)
- **Daemon install** (LaunchAgent on macOS; systemd user unit on Linux/WSL2)
- **Health checks** and **skills** selection
@@ -363,7 +363,7 @@ lowest friction and youre okay with sleep/restarts, run it locally.
- **Pros:** alwayson, stable network, no laptop sleep issues, easier to keep running.
- **Cons:** often run headless (use screenshots), remote file access only, you must SSH for updates.
**Clawdbotspecific note:** WhatsApp/Telegram/Slack/Discord all work fine from a VPS. The only real tradeoff is **headless browser** vs a visible window. See [Browser](/tools/browser).
**Clawdbot-specific note:** WhatsApp/Telegram/Slack/Mattermost (plugin)/Discord all work fine from a VPS. The only real trade-off is **headless browser** vs a visible window. See [Browser](/tools/browser).
**Recommended default:** VPS if you had gateway disconnects before. Local is great when youre actively using the Mac and want local file access or UI automation with a visible browser.
@@ -719,43 +719,42 @@ See the full config examples in [Browser](/tools/browser#use-brave-or-another-ch
### How do commands propagate between Telegram, the gateway, and nodes?
Telegram messages are handled by the **gateway**. The gateway runs the agent and
only then calls nodes over the **Bridge** when a node tool is needed:
only then calls nodes over the **Gateway WebSocket** when a node tool is needed:
Telegram → Gateway → Agent → `node.*` → Node → Gateway → Telegram
Nodes dont see inbound provider traffic; they only receive bridge RPC calls.
Nodes dont see inbound provider traffic; they only receive node RPC calls.
### How can my agent access my computer if the Gateway is hosted remotely?
Short answer: **pair your computer as a node**. The Gateway runs elsewhere, but it can
call `node.*` tools (screen, camera, system) on your local machine over the Bridge.
call `node.*` tools (screen, camera, system) on your local machine over the Gateway WebSocket.
Typical setup:
1) Run the Gateway on the alwayson host (VPS/home server).
2) Put the Gateway host + your computer on the same tailnet.
3) Enable the bridge on the Gateway host:
```json5
{ bridge: { enabled: true, bind: "auto" } }
```
4) Open the macOS app locally and connect in **Remote over SSH** mode so it can tunnel
the bridge port and register as a node.
3) Ensure the Gateway WS is reachable (tailnet bind or SSH tunnel).
4) Open the macOS app locally and connect in **Remote over SSH** mode (or direct tailnet)
so it can register as a node.
5) Approve the node on the Gateway:
```bash
clawdbot nodes pending
clawdbot nodes approve <requestId>
```
No separate TCP bridge is required; nodes connect over the Gateway WebSocket.
Security reminder: pairing a macOS node allows `system.run` on that machine. Only
pair devices you trust, and review [Security](/gateway/security).
Docs: [Nodes](/nodes), [Bridge protocol](/gateway/bridge-protocol), [macOS remote mode](/platforms/mac/remote), [Security](/gateway/security).
Docs: [Nodes](/nodes), [Gateway protocol](/gateway/protocol), [macOS remote mode](/platforms/mac/remote), [Security](/gateway/security).
### Do nodes run a gateway service?
No. Only **one gateway** should run per host unless you intentionally run isolated profiles (see [Multiple gateways](/gateway/multiple-gateways)). Nodes are peripherals that connect
to the gateway (iOS/Android nodes, or macOS “node mode” in the menubar app).
A full restart is required for `gateway`, `bridge`, `discovery`, and `canvasHost` changes.
A full restart is required for `gateway`, `discovery`, and `canvasHost` changes.
### Is there an API / RPC way to apply config?
@@ -797,26 +796,19 @@ This keeps the gateway bound to loopback and exposes HTTPS via Tailscale. See [T
### How do I connect a Mac node to a remote Gateway (Tailscale Serve)?
Serve only exposes the **Gateway Control UI**. Nodes use the **bridge port**.
Serve exposes the **Gateway Control UI + WS**. Nodes connect over the same Gateway WS endpoint.
Recommended setup:
1) **Enable the bridge on the gateway host**:
```json5
{
bridge: { enabled: true, bind: "auto" }
}
```
`auto` prefers a tailnet IP when Tailscale is present.
2) **Make sure the VPS + Mac are on the same tailnet**.
3) **Use the macOS app in Remote mode** (SSH target can be the tailnet hostname).
The app will tunnel the bridge port and connect as a node.
4) **Approve the node** on the gateway:
1) **Make sure the VPS + Mac are on the same tailnet**.
2) **Use the macOS app in Remote mode** (SSH target can be the tailnet hostname).
The app will tunnel the Gateway port and connect as a node.
3) **Approve the node** on the gateway:
```bash
clawdbot nodes pending
clawdbot nodes approve <requestId>
```
Docs: [Bridge protocol](/gateway/bridge-protocol), [Discovery](/gateway/discovery), [macOS remote mode](/platforms/mac/remote).
Docs: [Gateway protocol](/gateway/protocol), [Discovery](/gateway/discovery), [macOS remote mode](/platforms/mac/remote).
## Env vars and .env loading

View File

@@ -12,7 +12,7 @@ Goal: go from **zero** → **first working chat** (with sane defaults) as quickl
Recommended path: use the **CLI onboarding wizard** (`clawdbot onboard`). It sets up:
- model/auth (OAuth recommended)
- gateway settings
- channels (WhatsApp/Telegram/Discord/)
- channels (WhatsApp/Telegram/Discord/Mattermost (plugin)/...)
- pairing defaults (secure DMs)
- workspace bootstrap + skills
- optional background service
@@ -80,7 +80,7 @@ clawdbot onboard --install-daemon
What youll choose:
- **Local vs Remote** gateway
- **Auth**: OpenAI Code (Codex) subscription (OAuth) or API keys. For Anthropic we recommend an API key; `claude setup-token` is also supported.
- **Providers**: WhatsApp QR login, Telegram/Discord bot tokens, etc.
- **Providers**: WhatsApp QR login, Telegram/Discord bot tokens, Mattermost plugin tokens, etc.
- **Daemon**: background install (launchd/systemd; WSL2 uses systemd)
- **Runtime**: Node (recommended; required for WhatsApp/Telegram). Bun is **not recommended**.
- **Gateway token**: the wizard generates one by default (even on loopback) and stores it in `gateway.auth.token`.
@@ -140,6 +140,7 @@ WhatsApp doc: [WhatsApp](/channels/whatsapp)
The wizard can write tokens/config for you. If you prefer manual config, start with:
- Telegram: [Telegram](/channels/telegram)
- Discord: [Discord](/channels/discord)
- Mattermost (plugin): [Mattermost](/channels/mattermost)
**Telegram DM tip:** your first DM returns a pairing code. Approve it (see next step) or the bot wont respond.

View File

@@ -67,6 +67,7 @@ Use these hubs to discover every page, including deep dives and reference docs t
- [Telegram (grammY notes)](/channels/grammy)
- [Slack](/channels/slack)
- [Discord](/channels/discord)
- [Mattermost](/channels/mattermost) (plugin)
- [Signal](/channels/signal)
- [iMessage](/channels/imessage)
- [Location parsing](/channels/location)
@@ -96,6 +97,7 @@ Use these hubs to discover every page, including deep dives and reference docs t
## Tools + automation
- [Tools surface](/tools)
- [OpenProse](/prose)
- [CLI reference](/cli)
- [Exec tool](/tools/exec)
- [Elevated mode](/tools/elevated)

View File

@@ -48,7 +48,7 @@ The wizard starts with **QuickStart** (defaults) vs **Advanced** (full control).
- Model/auth (OpenAI Code (Codex) subscription OAuth, Anthropic API key (recommended) or setup-token (paste), plus MiniMax/GLM/Moonshot/AI Gateway options)
- Workspace location + bootstrap files
- Gateway settings (port/bind/auth/tailscale)
- Providers (Telegram, WhatsApp, Discord, Signal)
- Providers (Telegram, WhatsApp, Discord, Mattermost (plugin), Signal)
- Daemon install (LaunchAgent / systemd user unit)
- Health check
- Skills (recommended)
@@ -117,6 +117,7 @@ Tip: `--json` does **not** imply non-interactive mode. Use `--non-interactive` (
- WhatsApp: optional QR login.
- Telegram: bot token.
- Discord: bot token.
- Mattermost (plugin): bot token + base URL.
- Signal: optional `signal-cli` install + account config.
- iMessage: local `imsg` CLI path + DB access.
- DM security: default is pairing. First DM sends a code; approve via `clawdbot pairing approve <channel> <code>` or use allowlists.

View File

@@ -22,7 +22,7 @@ Exec approvals are enforced locally on the execution host:
- **gateway host** → `clawdbot` process on the gateway machine
- **node host** → node runner (macOS companion app or headless node host)
Planned macOS split:
macOS split:
- **node host service** forwards `system.run` to the **macOS app** over local IPC.
- **macOS app** enforces approvals + executes the command in UI context.
@@ -103,8 +103,8 @@ Each allowlist entry tracks:
## Auto-allow skill CLIs
When **Auto-allow skill CLIs** is enabled, executables referenced by known skills
are treated as allowlisted on nodes (macOS node or headless node host). This uses the Bridge RPC to ask the
gateway for the skill bin list. Disable this if you want strict manual allowlists.
are treated as allowlisted on nodes (macOS node or headless node host). This uses
`skills.bins` over the Gateway RPC to fetch the skill bin list. Disable this if you want strict manual allowlists.
## Safe bins (stdin-only)
@@ -113,6 +113,9 @@ that can run in allowlist mode **without** explicit allowlist entries. Safe bins
positional file args and path-like tokens, so they can only operate on the incoming stream.
Shell chaining and redirections are not auto-allowed in allowlist mode.
Shell chaining (`&&`, `||`, `;`) is allowed when every top-level segment satisfies the allowlist
(including safe bins or skill auto-allow). Redirections remain unsupported in allowlist mode.
Default safe bins: `jq`, `grep`, `cut`, `sort`, `uniq`, `head`, `tail`, `tr`, `wc`.
## Control UI editing
@@ -151,12 +154,12 @@ Actions:
- **Always allow** → add to allowlist + run
- **Deny** → block
### macOS IPC flow (planned)
### macOS IPC flow
```
Gateway -> Bridge -> Node Service (TS)
| IPC (UDS + token + HMAC + TTL)
v
Mac App (UI + approvals + system.run)
Gateway -> Node Service (WS)
| IPC (UDS + token + HMAC + TTL)
v
Mac App (UI + approvals + system.run)
```
Security notes:

View File

@@ -66,8 +66,8 @@ Example:
- `host=sandbox`: runs `sh -lc` (login shell) inside the container, so `/etc/profile` may reset `PATH`.
Clawdbot prepends `env.PATH` after profile sourcing; `tools.exec.pathPrepend` applies here too.
- `host=node`: only env overrides you pass are sent to the node. `tools.exec.pathPrepend` only applies
if the exec call already sets `env.PATH`. Node PATH overrides are accepted only when they prepend
the node host PATH (no replacement).
if the exec call already sets `env.PATH`. Headless node hosts accept `PATH` only when it prepends
the node host PATH (no replacement). macOS nodes drop `PATH` overrides entirely.
Per-agent node binding (use the agent list index in config):

View File

@@ -155,7 +155,7 @@ tool usage guidance is injected into prompts. Some plugins ship their own skills
alongside tools (for example, the voice-call plugin).
Optional plugin tools:
- [Lobster](/tools/lobster): typed workflow runtime with resumable approvals (requires the Lobster CLI on the gateway host).
- [Lobster](/lobster): typed workflow runtime with resumable approvals (requires the Lobster CLI on the gateway host).
## Tool inventory

View File

@@ -151,6 +151,10 @@ If `requiresApproval` is present, inspect the prompt and decide:
- `approve: true` → resume and continue side effects
- `approve: false` → cancel and finalize the workflow
## OpenProse
OpenProse pairs well with Lobster: use `/prose` to orchestrate multi-agent prep, then run a Lobster pipeline for deterministic approvals. If a Prose program needs Lobster, allow the `lobster` tool for sub-agents via `tools.subagents.tools`. See [OpenProse](/prose).
## Safety
- **Local subprocess only** — no network calls from the plugin itself.

View File

@@ -38,10 +38,12 @@ applies: workspace wins, then managed/local, then bundled.
## Plugins + skills
Plugins can ship their own skills (for example, `voice-call`) and gate them via
`metadata.clawdbot.requires.config` on the plugins config entry. See
[Plugins](/plugin) for plugin discovery/config and [Tools](/tools) for the tool
surface those skills teach.
Plugins can ship their own skills by listing `skills` directories in
`clawdbot.plugin.json` (paths relative to the plugin root). Plugin skills load
when the plugin is enabled and participate in the normal skill precedence rules.
You can gate them via `metadata.clawdbot.requires.config` on the plugins config
entry. See [Plugins](/plugin) for discovery/config and [Tools](/tools) for the
tool surface those skills teach.
## ClawdHub (install + sync)

View File

@@ -109,6 +109,7 @@ Notes:
- `/skill <name> [input]` runs a skill by name (useful when native command limits prevent per-skill commands).
- By default, skill commands are forwarded to the model as a normal request.
- Skills may optionally declare `command-dispatch: tool` to route the command directly to a tool (deterministic, no model).
- Example: `/prose` (OpenProse plugin) — see [OpenProse](/prose).
- **Native command arguments:** Discord uses autocomplete for dynamic options (and button menus when you omit required args). Telegram and Slack show a button menu when a command supports choices and you omit the arg.
## Usage surfaces (what shows where)

View File

@@ -88,6 +88,12 @@ Session lifecycle:
- `/settings`
- `/exit`
## Local shell commands
- Prefix a line with `!` to run a local shell command on the TUI host.
- The TUI prompts once per session to allow local execution; declining keeps `!` disabled for the session.
- Commands run in a fresh, non-interactive shell in the TUI working directory (no persistent `cd`/env).
- A lone `!` is sent as a normal message; leading spaces do not trigger local exec.
## Tool output
- Tool calls show as cards with args + results.
- Ctrl+O toggles between collapsed/expanded views.

View File

@@ -30,7 +30,7 @@ The onboarding wizard generates a gateway token by default, so paste it here on
## What it can do (today)
- Chat with the model via Gateway WS (`chat.history`, `chat.send`, `chat.abort`, `chat.inject`)
- Stream tool calls + live tool output cards in Chat (agent events)
- Channels: WhatsApp/Telegram status + QR login + per-channel config (`channels.status`, `web.login.*`, `config.patch`)
- Channels: WhatsApp/Telegram/Discord/Slack + plugin channels (Mattermost, etc.) status + QR login + per-channel config (`channels.status`, `web.login.*`, `config.patch`)
- Instances: presence list + refresh (`system-presence`)
- Sessions: list + per-session thinking/verbose overrides (`sessions.list`, `sessions.patch`)
- Cron jobs: list/add/run/enable/disable + run history (`cron.*`)

View File

@@ -0,0 +1,11 @@
{
"id": "mattermost",
"channels": [
"mattermost"
],
"configSchema": {
"type": "object",
"additionalProperties": false,
"properties": {}
}
}

View File

@@ -0,0 +1,18 @@
import type { ClawdbotPluginApi } from "clawdbot/plugin-sdk";
import { emptyPluginConfigSchema } from "clawdbot/plugin-sdk";
import { mattermostPlugin } from "./src/channel.js";
import { setMattermostRuntime } from "./src/runtime.js";
const plugin = {
id: "mattermost",
name: "Mattermost",
description: "Mattermost channel plugin",
configSchema: emptyPluginConfigSchema(),
register(api: ClawdbotPluginApi) {
setMattermostRuntime(api.runtime);
api.registerChannel({ plugin: mattermostPlugin });
},
};
export default plugin;

View File

@@ -0,0 +1,25 @@
{
"name": "@clawdbot/mattermost",
"version": "2026.1.20-2",
"type": "module",
"description": "Clawdbot Mattermost channel plugin",
"clawdbot": {
"extensions": [
"./index.ts"
],
"channel": {
"id": "mattermost",
"label": "Mattermost",
"selectionLabel": "Mattermost (plugin)",
"docsPath": "/channels/mattermost",
"docsLabel": "mattermost",
"blurb": "self-hosted Slack-style chat; install the plugin to enable.",
"order": 65
},
"install": {
"npmSpec": "@clawdbot/mattermost",
"localPath": "extensions/mattermost",
"defaultChoice": "npm"
}
}
}

View File

@@ -0,0 +1,43 @@
import { describe, expect, it } from "vitest";
import { mattermostPlugin } from "./channel.js";
describe("mattermostPlugin", () => {
describe("messaging", () => {
it("keeps @username targets", () => {
const normalize = mattermostPlugin.messaging?.normalizeTarget;
if (!normalize) return;
expect(normalize("@Alice")).toBe("@Alice");
expect(normalize("@alice")).toBe("@alice");
});
it("normalizes mattermost: prefix to user:", () => {
const normalize = mattermostPlugin.messaging?.normalizeTarget;
if (!normalize) return;
expect(normalize("mattermost:USER123")).toBe("user:USER123");
});
});
describe("pairing", () => {
it("normalizes allowlist entries", () => {
const normalize = mattermostPlugin.pairing?.normalizeAllowEntry;
if (!normalize) return;
expect(normalize("@Alice")).toBe("alice");
expect(normalize("user:USER123")).toBe("user123");
});
});
describe("config", () => {
it("formats allowFrom entries", () => {
const formatAllowFrom = mattermostPlugin.config.formatAllowFrom;
const formatted = formatAllowFrom({
allowFrom: ["@Alice", "user:USER123", "mattermost:BOT999"],
});
expect(formatted).toEqual(["@alice", "user123", "bot999"]);
});
});
});

View File

@@ -0,0 +1,338 @@
import {
applyAccountNameToChannelSection,
buildChannelConfigSchema,
DEFAULT_ACCOUNT_ID,
deleteAccountFromConfigSection,
formatPairingApproveHint,
migrateBaseNameToDefaultAccount,
normalizeAccountId,
setAccountEnabledInConfigSection,
type ChannelPlugin,
} from "clawdbot/plugin-sdk";
import { MattermostConfigSchema } from "./config-schema.js";
import { resolveMattermostGroupRequireMention } from "./group-mentions.js";
import {
looksLikeMattermostTargetId,
normalizeMattermostMessagingTarget,
} from "./normalize.js";
import { mattermostOnboardingAdapter } from "./onboarding.js";
import {
listMattermostAccountIds,
resolveDefaultMattermostAccountId,
resolveMattermostAccount,
type ResolvedMattermostAccount,
} from "./mattermost/accounts.js";
import { normalizeMattermostBaseUrl } from "./mattermost/client.js";
import { monitorMattermostProvider } from "./mattermost/monitor.js";
import { probeMattermost } from "./mattermost/probe.js";
import { sendMessageMattermost } from "./mattermost/send.js";
import { getMattermostRuntime } from "./runtime.js";
const meta = {
id: "mattermost",
label: "Mattermost",
selectionLabel: "Mattermost (plugin)",
detailLabel: "Mattermost Bot",
docsPath: "/channels/mattermost",
docsLabel: "mattermost",
blurb: "self-hosted Slack-style chat; install the plugin to enable.",
systemImage: "bubble.left.and.bubble.right",
order: 65,
quickstartAllowFrom: true,
} as const;
function normalizeAllowEntry(entry: string): string {
return entry
.trim()
.replace(/^(mattermost|user):/i, "")
.replace(/^@/, "")
.toLowerCase();
}
function formatAllowEntry(entry: string): string {
const trimmed = entry.trim();
if (!trimmed) return "";
if (trimmed.startsWith("@")) {
const username = trimmed.slice(1).trim();
return username ? `@${username.toLowerCase()}` : "";
}
return trimmed.replace(/^(mattermost|user):/i, "").toLowerCase();
}
export const mattermostPlugin: ChannelPlugin<ResolvedMattermostAccount> = {
id: "mattermost",
meta: {
...meta,
},
onboarding: mattermostOnboardingAdapter,
pairing: {
idLabel: "mattermostUserId",
normalizeAllowEntry: (entry) => normalizeAllowEntry(entry),
notifyApproval: async ({ id }) => {
console.log(`[mattermost] User ${id} approved for pairing`);
},
},
capabilities: {
chatTypes: ["direct", "channel", "group", "thread"],
threads: true,
media: true,
},
streaming: {
blockStreamingCoalesceDefaults: { minChars: 1500, idleMs: 1000 },
},
reload: { configPrefixes: ["channels.mattermost"] },
configSchema: buildChannelConfigSchema(MattermostConfigSchema),
config: {
listAccountIds: (cfg) => listMattermostAccountIds(cfg),
resolveAccount: (cfg, accountId) => resolveMattermostAccount({ cfg, accountId }),
defaultAccountId: (cfg) => resolveDefaultMattermostAccountId(cfg),
setAccountEnabled: ({ cfg, accountId, enabled }) =>
setAccountEnabledInConfigSection({
cfg,
sectionKey: "mattermost",
accountId,
enabled,
allowTopLevel: true,
}),
deleteAccount: ({ cfg, accountId }) =>
deleteAccountFromConfigSection({
cfg,
sectionKey: "mattermost",
accountId,
clearBaseFields: ["botToken", "baseUrl", "name"],
}),
isConfigured: (account) => Boolean(account.botToken && account.baseUrl),
describeAccount: (account) => ({
accountId: account.accountId,
name: account.name,
enabled: account.enabled,
configured: Boolean(account.botToken && account.baseUrl),
botTokenSource: account.botTokenSource,
baseUrl: account.baseUrl,
}),
resolveAllowFrom: ({ cfg, accountId }) =>
(resolveMattermostAccount({ cfg, accountId }).config.allowFrom ?? []).map((entry) =>
String(entry),
),
formatAllowFrom: ({ allowFrom }) =>
allowFrom
.map((entry) => formatAllowEntry(String(entry)))
.filter(Boolean),
},
security: {
resolveDmPolicy: ({ cfg, accountId, account }) => {
const resolvedAccountId = accountId ?? account.accountId ?? DEFAULT_ACCOUNT_ID;
const useAccountPath = Boolean(cfg.channels?.mattermost?.accounts?.[resolvedAccountId]);
const basePath = useAccountPath
? `channels.mattermost.accounts.${resolvedAccountId}.`
: "channels.mattermost.";
return {
policy: account.config.dmPolicy ?? "pairing",
allowFrom: account.config.allowFrom ?? [],
policyPath: `${basePath}dmPolicy`,
allowFromPath: basePath,
approveHint: formatPairingApproveHint("mattermost"),
normalizeEntry: (raw) => normalizeAllowEntry(raw),
};
},
collectWarnings: ({ account, cfg }) => {
const defaultGroupPolicy = cfg.channels?.defaults?.groupPolicy;
const groupPolicy = account.config.groupPolicy ?? defaultGroupPolicy ?? "allowlist";
if (groupPolicy !== "open") return [];
return [
`- Mattermost channels: groupPolicy="open" allows any member to trigger (mention-gated). Set channels.mattermost.groupPolicy="allowlist" + channels.mattermost.groupAllowFrom to restrict senders.`,
];
},
},
groups: {
resolveRequireMention: resolveMattermostGroupRequireMention,
},
messaging: {
normalizeTarget: normalizeMattermostMessagingTarget,
targetResolver: {
looksLikeId: looksLikeMattermostTargetId,
hint: "<channelId|user:ID|channel:ID>",
},
},
outbound: {
deliveryMode: "direct",
chunker: (text, limit) => getMattermostRuntime().channel.text.chunkMarkdownText(text, limit),
textChunkLimit: 4000,
resolveTarget: ({ to }) => {
const trimmed = to?.trim();
if (!trimmed) {
return {
ok: false,
error: new Error(
"Delivering to Mattermost requires --to <channelId|@username|user:ID|channel:ID>",
),
};
}
return { ok: true, to: trimmed };
},
sendText: async ({ to, text, accountId, replyToId }) => {
const result = await sendMessageMattermost(to, text, {
accountId: accountId ?? undefined,
replyToId: replyToId ?? undefined,
});
return { channel: "mattermost", ...result };
},
sendMedia: async ({ to, text, mediaUrl, accountId, replyToId }) => {
const result = await sendMessageMattermost(to, text, {
accountId: accountId ?? undefined,
mediaUrl,
replyToId: replyToId ?? undefined,
});
return { channel: "mattermost", ...result };
},
},
status: {
defaultRuntime: {
accountId: DEFAULT_ACCOUNT_ID,
running: false,
connected: false,
lastConnectedAt: null,
lastDisconnect: null,
lastStartAt: null,
lastStopAt: null,
lastError: null,
},
buildChannelSummary: ({ snapshot }) => ({
configured: snapshot.configured ?? false,
botTokenSource: snapshot.botTokenSource ?? "none",
running: snapshot.running ?? false,
connected: snapshot.connected ?? false,
lastStartAt: snapshot.lastStartAt ?? null,
lastStopAt: snapshot.lastStopAt ?? null,
lastError: snapshot.lastError ?? null,
baseUrl: snapshot.baseUrl ?? null,
probe: snapshot.probe,
lastProbeAt: snapshot.lastProbeAt ?? null,
}),
probeAccount: async ({ account, timeoutMs }) => {
const token = account.botToken?.trim();
const baseUrl = account.baseUrl?.trim();
if (!token || !baseUrl) {
return { ok: false, error: "bot token or baseUrl missing" };
}
return await probeMattermost(baseUrl, token, timeoutMs);
},
buildAccountSnapshot: ({ account, runtime, probe }) => ({
accountId: account.accountId,
name: account.name,
enabled: account.enabled,
configured: Boolean(account.botToken && account.baseUrl),
botTokenSource: account.botTokenSource,
baseUrl: account.baseUrl,
running: runtime?.running ?? false,
connected: runtime?.connected ?? false,
lastConnectedAt: runtime?.lastConnectedAt ?? null,
lastDisconnect: runtime?.lastDisconnect ?? null,
lastStartAt: runtime?.lastStartAt ?? null,
lastStopAt: runtime?.lastStopAt ?? null,
lastError: runtime?.lastError ?? null,
probe,
lastInboundAt: runtime?.lastInboundAt ?? null,
lastOutboundAt: runtime?.lastOutboundAt ?? null,
}),
},
setup: {
resolveAccountId: ({ accountId }) => normalizeAccountId(accountId),
applyAccountName: ({ cfg, accountId, name }) =>
applyAccountNameToChannelSection({
cfg,
channelKey: "mattermost",
accountId,
name,
}),
validateInput: ({ accountId, input }) => {
if (input.useEnv && accountId !== DEFAULT_ACCOUNT_ID) {
return "Mattermost env vars can only be used for the default account.";
}
const token = input.botToken ?? input.token;
const baseUrl = input.httpUrl;
if (!input.useEnv && (!token || !baseUrl)) {
return "Mattermost requires --bot-token and --http-url (or --use-env).";
}
if (baseUrl && !normalizeMattermostBaseUrl(baseUrl)) {
return "Mattermost --http-url must include a valid base URL.";
}
return null;
},
applyAccountConfig: ({ cfg, accountId, input }) => {
const token = input.botToken ?? input.token;
const baseUrl = input.httpUrl?.trim();
const namedConfig = applyAccountNameToChannelSection({
cfg,
channelKey: "mattermost",
accountId,
name: input.name,
});
const next =
accountId !== DEFAULT_ACCOUNT_ID
? migrateBaseNameToDefaultAccount({
cfg: namedConfig,
channelKey: "mattermost",
})
: namedConfig;
if (accountId === DEFAULT_ACCOUNT_ID) {
return {
...next,
channels: {
...next.channels,
mattermost: {
...next.channels?.mattermost,
enabled: true,
...(input.useEnv
? {}
: {
...(token ? { botToken: token } : {}),
...(baseUrl ? { baseUrl } : {}),
}),
},
},
};
}
return {
...next,
channels: {
...next.channels,
mattermost: {
...next.channels?.mattermost,
enabled: true,
accounts: {
...next.channels?.mattermost?.accounts,
[accountId]: {
...next.channels?.mattermost?.accounts?.[accountId],
enabled: true,
...(token ? { botToken: token } : {}),
...(baseUrl ? { baseUrl } : {}),
},
},
},
},
};
},
},
gateway: {
startAccount: async (ctx) => {
const account = ctx.account;
ctx.setStatus({
accountId: account.accountId,
baseUrl: account.baseUrl,
botTokenSource: account.botTokenSource,
});
ctx.log?.info(`[${account.accountId}] starting channel`);
return monitorMattermostProvider({
botToken: account.botToken ?? undefined,
baseUrl: account.baseUrl ?? undefined,
accountId: account.accountId,
config: ctx.cfg,
runtime: ctx.runtime,
abortSignal: ctx.abortSignal,
statusSink: (patch) => ctx.setStatus({ accountId: ctx.accountId, ...patch }),
});
},
},
};

View File

@@ -0,0 +1,53 @@
import { z } from "zod";
import {
BlockStreamingCoalesceSchema,
DmPolicySchema,
GroupPolicySchema,
requireOpenAllowFrom,
} from "clawdbot/plugin-sdk";
const MattermostAccountSchemaBase = z
.object({
name: z.string().optional(),
capabilities: z.array(z.string()).optional(),
enabled: z.boolean().optional(),
configWrites: z.boolean().optional(),
botToken: z.string().optional(),
baseUrl: z.string().optional(),
chatmode: z.enum(["oncall", "onmessage", "onchar"]).optional(),
oncharPrefixes: z.array(z.string()).optional(),
requireMention: z.boolean().optional(),
dmPolicy: DmPolicySchema.optional().default("pairing"),
allowFrom: z.array(z.union([z.string(), z.number()])).optional(),
groupAllowFrom: z.array(z.union([z.string(), z.number()])).optional(),
groupPolicy: GroupPolicySchema.optional().default("allowlist"),
textChunkLimit: z.number().int().positive().optional(),
blockStreaming: z.boolean().optional(),
blockStreamingCoalesce: BlockStreamingCoalesceSchema.optional(),
})
.strict();
const MattermostAccountSchema = MattermostAccountSchemaBase.superRefine((value, ctx) => {
requireOpenAllowFrom({
policy: value.dmPolicy,
allowFrom: value.allowFrom,
ctx,
path: ["allowFrom"],
message:
'channels.mattermost.dmPolicy="open" requires channels.mattermost.allowFrom to include "*"',
});
});
export const MattermostConfigSchema = MattermostAccountSchemaBase.extend({
accounts: z.record(z.string(), MattermostAccountSchema.optional()).optional(),
}).superRefine((value, ctx) => {
requireOpenAllowFrom({
policy: value.dmPolicy,
allowFrom: value.allowFrom,
ctx,
path: ["allowFrom"],
message:
'channels.mattermost.dmPolicy="open" requires channels.mattermost.allowFrom to include "*"',
});
});

View File

@@ -0,0 +1,14 @@
import type { ChannelGroupContext } from "clawdbot/plugin-sdk";
import { resolveMattermostAccount } from "./mattermost/accounts.js";
export function resolveMattermostGroupRequireMention(
params: ChannelGroupContext,
): boolean | undefined {
const account = resolveMattermostAccount({
cfg: params.cfg,
accountId: params.accountId,
});
if (typeof account.requireMention === "boolean") return account.requireMention;
return true;
}

View File

@@ -0,0 +1,115 @@
import type { ClawdbotConfig } from "clawdbot/plugin-sdk";
import { DEFAULT_ACCOUNT_ID, normalizeAccountId } from "clawdbot/plugin-sdk";
import type { MattermostAccountConfig, MattermostChatMode } from "../types.js";
import { normalizeMattermostBaseUrl } from "./client.js";
export type MattermostTokenSource = "env" | "config" | "none";
export type MattermostBaseUrlSource = "env" | "config" | "none";
export type ResolvedMattermostAccount = {
accountId: string;
enabled: boolean;
name?: string;
botToken?: string;
baseUrl?: string;
botTokenSource: MattermostTokenSource;
baseUrlSource: MattermostBaseUrlSource;
config: MattermostAccountConfig;
chatmode?: MattermostChatMode;
oncharPrefixes?: string[];
requireMention?: boolean;
textChunkLimit?: number;
blockStreaming?: boolean;
blockStreamingCoalesce?: MattermostAccountConfig["blockStreamingCoalesce"];
};
function listConfiguredAccountIds(cfg: ClawdbotConfig): string[] {
const accounts = cfg.channels?.mattermost?.accounts;
if (!accounts || typeof accounts !== "object") return [];
return Object.keys(accounts).filter(Boolean);
}
export function listMattermostAccountIds(cfg: ClawdbotConfig): string[] {
const ids = listConfiguredAccountIds(cfg);
if (ids.length === 0) return [DEFAULT_ACCOUNT_ID];
return ids.sort((a, b) => a.localeCompare(b));
}
export function resolveDefaultMattermostAccountId(cfg: ClawdbotConfig): string {
const ids = listMattermostAccountIds(cfg);
if (ids.includes(DEFAULT_ACCOUNT_ID)) return DEFAULT_ACCOUNT_ID;
return ids[0] ?? DEFAULT_ACCOUNT_ID;
}
function resolveAccountConfig(
cfg: ClawdbotConfig,
accountId: string,
): MattermostAccountConfig | undefined {
const accounts = cfg.channels?.mattermost?.accounts;
if (!accounts || typeof accounts !== "object") return undefined;
return accounts[accountId] as MattermostAccountConfig | undefined;
}
function mergeMattermostAccountConfig(
cfg: ClawdbotConfig,
accountId: string,
): MattermostAccountConfig {
const { accounts: _ignored, ...base } = (cfg.channels?.mattermost ??
{}) as MattermostAccountConfig & { accounts?: unknown };
const account = resolveAccountConfig(cfg, accountId) ?? {};
return { ...base, ...account };
}
function resolveMattermostRequireMention(config: MattermostAccountConfig): boolean | undefined {
if (config.chatmode === "oncall") return true;
if (config.chatmode === "onmessage") return false;
if (config.chatmode === "onchar") return true;
return config.requireMention;
}
export function resolveMattermostAccount(params: {
cfg: ClawdbotConfig;
accountId?: string | null;
}): ResolvedMattermostAccount {
const accountId = normalizeAccountId(params.accountId);
const baseEnabled = params.cfg.channels?.mattermost?.enabled !== false;
const merged = mergeMattermostAccountConfig(params.cfg, accountId);
const accountEnabled = merged.enabled !== false;
const enabled = baseEnabled && accountEnabled;
const allowEnv = accountId === DEFAULT_ACCOUNT_ID;
const envToken = allowEnv ? process.env.MATTERMOST_BOT_TOKEN?.trim() : undefined;
const envUrl = allowEnv ? process.env.MATTERMOST_URL?.trim() : undefined;
const configToken = merged.botToken?.trim();
const configUrl = merged.baseUrl?.trim();
const botToken = configToken || envToken;
const baseUrl = normalizeMattermostBaseUrl(configUrl || envUrl);
const requireMention = resolveMattermostRequireMention(merged);
const botTokenSource: MattermostTokenSource = configToken ? "config" : envToken ? "env" : "none";
const baseUrlSource: MattermostBaseUrlSource = configUrl ? "config" : envUrl ? "env" : "none";
return {
accountId,
enabled,
name: merged.name?.trim() || undefined,
botToken,
baseUrl,
botTokenSource,
baseUrlSource,
config: merged,
chatmode: merged.chatmode,
oncharPrefixes: merged.oncharPrefixes,
requireMention,
textChunkLimit: merged.textChunkLimit,
blockStreaming: merged.blockStreaming,
blockStreamingCoalesce: merged.blockStreamingCoalesce,
};
}
export function listEnabledMattermostAccounts(cfg: ClawdbotConfig): ResolvedMattermostAccount[] {
return listMattermostAccountIds(cfg)
.map((accountId) => resolveMattermostAccount({ cfg, accountId }))
.filter((account) => account.enabled);
}

View File

@@ -0,0 +1,208 @@
export type MattermostClient = {
baseUrl: string;
apiBaseUrl: string;
token: string;
request: <T>(path: string, init?: RequestInit) => Promise<T>;
};
export type MattermostUser = {
id: string;
username?: string | null;
nickname?: string | null;
first_name?: string | null;
last_name?: string | null;
};
export type MattermostChannel = {
id: string;
name?: string | null;
display_name?: string | null;
type?: string | null;
team_id?: string | null;
};
export type MattermostPost = {
id: string;
user_id?: string | null;
channel_id?: string | null;
message?: string | null;
file_ids?: string[] | null;
type?: string | null;
root_id?: string | null;
create_at?: number | null;
props?: Record<string, unknown> | null;
};
export type MattermostFileInfo = {
id: string;
name?: string | null;
mime_type?: string | null;
size?: number | null;
};
export function normalizeMattermostBaseUrl(raw?: string | null): string | undefined {
const trimmed = raw?.trim();
if (!trimmed) return undefined;
const withoutTrailing = trimmed.replace(/\/+$/, "");
return withoutTrailing.replace(/\/api\/v4$/i, "");
}
function buildMattermostApiUrl(baseUrl: string, path: string): string {
const normalized = normalizeMattermostBaseUrl(baseUrl);
if (!normalized) throw new Error("Mattermost baseUrl is required");
const suffix = path.startsWith("/") ? path : `/${path}`;
return `${normalized}/api/v4${suffix}`;
}
async function readMattermostError(res: Response): Promise<string> {
const contentType = res.headers.get("content-type") ?? "";
if (contentType.includes("application/json")) {
const data = (await res.json()) as { message?: string } | undefined;
if (data?.message) return data.message;
return JSON.stringify(data);
}
return await res.text();
}
export function createMattermostClient(params: {
baseUrl: string;
botToken: string;
fetchImpl?: typeof fetch;
}): MattermostClient {
const baseUrl = normalizeMattermostBaseUrl(params.baseUrl);
if (!baseUrl) throw new Error("Mattermost baseUrl is required");
const apiBaseUrl = `${baseUrl}/api/v4`;
const token = params.botToken.trim();
const fetchImpl = params.fetchImpl ?? fetch;
const request = async <T>(path: string, init?: RequestInit): Promise<T> => {
const url = buildMattermostApiUrl(baseUrl, path);
const headers = new Headers(init?.headers);
headers.set("Authorization", `Bearer ${token}`);
if (typeof init?.body === "string" && !headers.has("Content-Type")) {
headers.set("Content-Type", "application/json");
}
const res = await fetchImpl(url, { ...init, headers });
if (!res.ok) {
const detail = await readMattermostError(res);
throw new Error(
`Mattermost API ${res.status} ${res.statusText}: ${detail || "unknown error"}`,
);
}
return (await res.json()) as T;
};
return { baseUrl, apiBaseUrl, token, request };
}
export async function fetchMattermostMe(client: MattermostClient): Promise<MattermostUser> {
return await client.request<MattermostUser>("/users/me");
}
export async function fetchMattermostUser(
client: MattermostClient,
userId: string,
): Promise<MattermostUser> {
return await client.request<MattermostUser>(`/users/${userId}`);
}
export async function fetchMattermostUserByUsername(
client: MattermostClient,
username: string,
): Promise<MattermostUser> {
return await client.request<MattermostUser>(`/users/username/${encodeURIComponent(username)}`);
}
export async function fetchMattermostChannel(
client: MattermostClient,
channelId: string,
): Promise<MattermostChannel> {
return await client.request<MattermostChannel>(`/channels/${channelId}`);
}
export async function sendMattermostTyping(
client: MattermostClient,
params: { channelId: string; parentId?: string },
): Promise<void> {
const payload: Record<string, string> = {
channel_id: params.channelId,
};
const parentId = params.parentId?.trim();
if (parentId) payload.parent_id = parentId;
await client.request<Record<string, unknown>>("/users/me/typing", {
method: "POST",
body: JSON.stringify(payload),
});
}
export async function createMattermostDirectChannel(
client: MattermostClient,
userIds: string[],
): Promise<MattermostChannel> {
return await client.request<MattermostChannel>("/channels/direct", {
method: "POST",
body: JSON.stringify(userIds),
});
}
export async function createMattermostPost(
client: MattermostClient,
params: {
channelId: string;
message: string;
rootId?: string;
fileIds?: string[];
},
): Promise<MattermostPost> {
const payload: Record<string, string> = {
channel_id: params.channelId,
message: params.message,
};
if (params.rootId) payload.root_id = params.rootId;
if (params.fileIds?.length) {
(payload as Record<string, unknown>).file_ids = params.fileIds;
}
return await client.request<MattermostPost>("/posts", {
method: "POST",
body: JSON.stringify(payload),
});
}
export async function uploadMattermostFile(
client: MattermostClient,
params: {
channelId: string;
buffer: Buffer;
fileName: string;
contentType?: string;
},
): Promise<MattermostFileInfo> {
const form = new FormData();
const fileName = params.fileName?.trim() || "upload";
const bytes = Uint8Array.from(params.buffer);
const blob = params.contentType
? new Blob([bytes], { type: params.contentType })
: new Blob([bytes]);
form.append("files", blob, fileName);
form.append("channel_id", params.channelId);
const res = await fetch(`${client.apiBaseUrl}/files`, {
method: "POST",
headers: {
Authorization: `Bearer ${client.token}`,
},
body: form,
});
if (!res.ok) {
const detail = await readMattermostError(res);
throw new Error(`Mattermost API ${res.status} ${res.statusText}: ${detail || "unknown error"}`);
}
const data = (await res.json()) as { file_infos?: MattermostFileInfo[] };
const info = data.file_infos?.[0];
if (!info?.id) {
throw new Error("Mattermost file upload failed");
}
return info;
}

View File

@@ -0,0 +1,9 @@
export {
listEnabledMattermostAccounts,
listMattermostAccountIds,
resolveDefaultMattermostAccountId,
resolveMattermostAccount,
} from "./accounts.js";
export { monitorMattermostProvider } from "./monitor.js";
export { probeMattermost } from "./probe.js";
export { sendMessageMattermost } from "./send.js";

View File

@@ -0,0 +1,150 @@
import { Buffer } from "node:buffer";
import type WebSocket from "ws";
import type { ClawdbotConfig } from "clawdbot/plugin-sdk";
export type ResponsePrefixContext = {
model?: string;
modelFull?: string;
provider?: string;
thinkingLevel?: string;
identityName?: string;
};
export function extractShortModelName(fullModel: string): string {
const slash = fullModel.lastIndexOf("/");
const modelPart = slash >= 0 ? fullModel.slice(slash + 1) : fullModel;
return modelPart.replace(/-\d{8}$/, "").replace(/-latest$/, "");
}
export function formatInboundFromLabel(params: {
isGroup: boolean;
groupLabel?: string;
groupId?: string;
directLabel: string;
directId?: string;
groupFallback?: string;
}): string {
if (params.isGroup) {
const label = params.groupLabel?.trim() || params.groupFallback || "Group";
const id = params.groupId?.trim();
return id ? `${label} id:${id}` : label;
}
const directLabel = params.directLabel.trim();
const directId = params.directId?.trim();
if (!directId || directId === directLabel) return directLabel;
return `${directLabel} id:${directId}`;
}
type DedupeCache = {
check: (key: string | undefined | null, now?: number) => boolean;
};
export function createDedupeCache(options: { ttlMs: number; maxSize: number }): DedupeCache {
const ttlMs = Math.max(0, options.ttlMs);
const maxSize = Math.max(0, Math.floor(options.maxSize));
const cache = new Map<string, number>();
const touch = (key: string, now: number) => {
cache.delete(key);
cache.set(key, now);
};
const prune = (now: number) => {
const cutoff = ttlMs > 0 ? now - ttlMs : undefined;
if (cutoff !== undefined) {
for (const [entryKey, entryTs] of cache) {
if (entryTs < cutoff) {
cache.delete(entryKey);
}
}
}
if (maxSize <= 0) {
cache.clear();
return;
}
while (cache.size > maxSize) {
const oldestKey = cache.keys().next().value as string | undefined;
if (!oldestKey) break;
cache.delete(oldestKey);
}
};
return {
check: (key, now = Date.now()) => {
if (!key) return false;
const existing = cache.get(key);
if (existing !== undefined && (ttlMs <= 0 || now - existing < ttlMs)) {
touch(key, now);
return true;
}
touch(key, now);
prune(now);
return false;
},
};
}
export function rawDataToString(
data: WebSocket.RawData,
encoding: BufferEncoding = "utf8",
): string {
if (typeof data === "string") return data;
if (Buffer.isBuffer(data)) return data.toString(encoding);
if (Array.isArray(data)) return Buffer.concat(data).toString(encoding);
if (data instanceof ArrayBuffer) {
return Buffer.from(data).toString(encoding);
}
return Buffer.from(String(data)).toString(encoding);
}
function normalizeAgentId(value: string | undefined | null): string {
const trimmed = (value ?? "").trim();
if (!trimmed) return "main";
if (/^[a-z0-9][a-z0-9_-]{0,63}$/i.test(trimmed)) return trimmed;
return (
trimmed
.toLowerCase()
.replace(/[^a-z0-9_-]+/g, "-")
.replace(/^-+/, "")
.replace(/-+$/, "")
.slice(0, 64) || "main"
);
}
type AgentEntry = NonNullable<NonNullable<ClawdbotConfig["agents"]>["list"]>[number];
function listAgents(cfg: ClawdbotConfig): AgentEntry[] {
const list = cfg.agents?.list;
if (!Array.isArray(list)) return [];
return list.filter((entry): entry is AgentEntry => Boolean(entry && typeof entry === "object"));
}
function resolveAgentEntry(cfg: ClawdbotConfig, agentId: string): AgentEntry | undefined {
const id = normalizeAgentId(agentId);
return listAgents(cfg).find((entry) => normalizeAgentId(entry.id) === id);
}
export function resolveIdentityName(cfg: ClawdbotConfig, agentId: string): string | undefined {
const entry = resolveAgentEntry(cfg, agentId);
return entry?.identity?.name?.trim() || undefined;
}
export function resolveThreadSessionKeys(params: {
baseSessionKey: string;
threadId?: string | null;
parentSessionKey?: string;
useSuffix?: boolean;
}): { sessionKey: string; parentSessionKey?: string } {
const threadId = (params.threadId ?? "").trim();
if (!threadId) {
return { sessionKey: params.baseSessionKey, parentSessionKey: undefined };
}
const useSuffix = params.useSuffix ?? true;
const sessionKey = useSuffix
? `${params.baseSessionKey}:thread:${threadId}`
: params.baseSessionKey;
return { sessionKey, parentSessionKey: params.parentSessionKey };
}

View File

@@ -0,0 +1,905 @@
import WebSocket from "ws";
import type {
ChannelAccountSnapshot,
ClawdbotConfig,
ReplyPayload,
RuntimeEnv,
} from "clawdbot/plugin-sdk";
import {
buildPendingHistoryContextFromMap,
clearHistoryEntries,
DEFAULT_GROUP_HISTORY_LIMIT,
recordPendingHistoryEntry,
resolveChannelMediaMaxBytes,
type HistoryEntry,
} from "clawdbot/plugin-sdk";
import { getMattermostRuntime } from "../runtime.js";
import { resolveMattermostAccount } from "./accounts.js";
import {
createMattermostClient,
fetchMattermostChannel,
fetchMattermostMe,
fetchMattermostUser,
normalizeMattermostBaseUrl,
sendMattermostTyping,
type MattermostChannel,
type MattermostPost,
type MattermostUser,
} from "./client.js";
import {
createDedupeCache,
extractShortModelName,
formatInboundFromLabel,
rawDataToString,
resolveIdentityName,
resolveThreadSessionKeys,
type ResponsePrefixContext,
} from "./monitor-helpers.js";
import { sendMessageMattermost } from "./send.js";
export type MonitorMattermostOpts = {
botToken?: string;
baseUrl?: string;
accountId?: string;
config?: ClawdbotConfig;
runtime?: RuntimeEnv;
abortSignal?: AbortSignal;
statusSink?: (patch: Partial<ChannelAccountSnapshot>) => void;
};
type FetchLike = typeof fetch;
type MediaKind = "image" | "audio" | "video" | "document" | "unknown";
type MattermostEventPayload = {
event?: string;
data?: {
post?: string;
channel_id?: string;
channel_name?: string;
channel_display_name?: string;
channel_type?: string;
sender_name?: string;
team_id?: string;
};
broadcast?: {
channel_id?: string;
team_id?: string;
user_id?: string;
};
};
const RECENT_MATTERMOST_MESSAGE_TTL_MS = 5 * 60_000;
const RECENT_MATTERMOST_MESSAGE_MAX = 2000;
const CHANNEL_CACHE_TTL_MS = 5 * 60_000;
const USER_CACHE_TTL_MS = 10 * 60_000;
const DEFAULT_ONCHAR_PREFIXES = [">", "!"];
const recentInboundMessages = createDedupeCache({
ttlMs: RECENT_MATTERMOST_MESSAGE_TTL_MS,
maxSize: RECENT_MATTERMOST_MESSAGE_MAX,
});
function resolveRuntime(opts: MonitorMattermostOpts): RuntimeEnv {
return (
opts.runtime ?? {
log: console.log,
error: console.error,
exit: (code: number): never => {
throw new Error(`exit ${code}`);
},
}
);
}
function normalizeMention(text: string, mention: string | undefined): string {
if (!mention) return text.trim();
const escaped = mention.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
const re = new RegExp(`@${escaped}\\b`, "gi");
return text.replace(re, " ").replace(/\s+/g, " ").trim();
}
function resolveOncharPrefixes(prefixes: string[] | undefined): string[] {
const cleaned = prefixes?.map((entry) => entry.trim()).filter(Boolean) ?? DEFAULT_ONCHAR_PREFIXES;
return cleaned.length > 0 ? cleaned : DEFAULT_ONCHAR_PREFIXES;
}
function stripOncharPrefix(
text: string,
prefixes: string[],
): { triggered: boolean; stripped: string } {
const trimmed = text.trimStart();
for (const prefix of prefixes) {
if (!prefix) continue;
if (trimmed.startsWith(prefix)) {
return {
triggered: true,
stripped: trimmed.slice(prefix.length).trimStart(),
};
}
}
return { triggered: false, stripped: text };
}
function isSystemPost(post: MattermostPost): boolean {
const type = post.type?.trim();
return Boolean(type);
}
function channelKind(channelType?: string | null): "dm" | "group" | "channel" {
if (!channelType) return "channel";
const normalized = channelType.trim().toUpperCase();
if (normalized === "D") return "dm";
if (normalized === "G") return "group";
return "channel";
}
function channelChatType(kind: "dm" | "group" | "channel"): "direct" | "group" | "channel" {
if (kind === "dm") return "direct";
if (kind === "group") return "group";
return "channel";
}
function normalizeAllowEntry(entry: string): string {
const trimmed = entry.trim();
if (!trimmed) return "";
if (trimmed === "*") return "*";
return trimmed
.replace(/^(mattermost|user):/i, "")
.replace(/^@/, "")
.toLowerCase();
}
function normalizeAllowList(entries: Array<string | number>): string[] {
const normalized = entries
.map((entry) => normalizeAllowEntry(String(entry)))
.filter(Boolean);
return Array.from(new Set(normalized));
}
function isSenderAllowed(params: {
senderId: string;
senderName?: string;
allowFrom: string[];
}): boolean {
const allowFrom = params.allowFrom;
if (allowFrom.length === 0) return false;
if (allowFrom.includes("*")) return true;
const normalizedSenderId = normalizeAllowEntry(params.senderId);
const normalizedSenderName = params.senderName ? normalizeAllowEntry(params.senderName) : "";
return allowFrom.some(
(entry) =>
entry === normalizedSenderId || (normalizedSenderName && entry === normalizedSenderName),
);
}
type MattermostMediaInfo = {
path: string;
contentType?: string;
kind: MediaKind;
};
function buildMattermostAttachmentPlaceholder(mediaList: MattermostMediaInfo[]): string {
if (mediaList.length === 0) return "";
if (mediaList.length === 1) {
const kind = mediaList[0].kind === "unknown" ? "document" : mediaList[0].kind;
return `<media:${kind}>`;
}
const allImages = mediaList.every((media) => media.kind === "image");
const label = allImages ? "image" : "file";
const suffix = mediaList.length === 1 ? label : `${label}s`;
const tag = allImages ? "<media:image>" : "<media:document>";
return `${tag} (${mediaList.length} ${suffix})`;
}
function buildMattermostMediaPayload(mediaList: MattermostMediaInfo[]): {
MediaPath?: string;
MediaType?: string;
MediaUrl?: string;
MediaPaths?: string[];
MediaUrls?: string[];
MediaTypes?: string[];
} {
const first = mediaList[0];
const mediaPaths = mediaList.map((media) => media.path);
const mediaTypes = mediaList.map((media) => media.contentType).filter(Boolean) as string[];
return {
MediaPath: first?.path,
MediaType: first?.contentType,
MediaUrl: first?.path,
MediaPaths: mediaPaths.length > 0 ? mediaPaths : undefined,
MediaUrls: mediaPaths.length > 0 ? mediaPaths : undefined,
MediaTypes: mediaTypes.length > 0 ? mediaTypes : undefined,
};
}
function buildMattermostWsUrl(baseUrl: string): string {
const normalized = normalizeMattermostBaseUrl(baseUrl);
if (!normalized) throw new Error("Mattermost baseUrl is required");
const wsBase = normalized.replace(/^http/i, "ws");
return `${wsBase}/api/v4/websocket`;
}
export async function monitorMattermostProvider(opts: MonitorMattermostOpts = {}): Promise<void> {
const core = getMattermostRuntime();
const runtime = resolveRuntime(opts);
const cfg = opts.config ?? core.config.loadConfig();
const account = resolveMattermostAccount({
cfg,
accountId: opts.accountId,
});
const botToken = opts.botToken?.trim() || account.botToken?.trim();
if (!botToken) {
throw new Error(
`Mattermost bot token missing for account "${account.accountId}" (set channels.mattermost.accounts.${account.accountId}.botToken or MATTERMOST_BOT_TOKEN for default).`,
);
}
const baseUrl = normalizeMattermostBaseUrl(opts.baseUrl ?? account.baseUrl);
if (!baseUrl) {
throw new Error(
`Mattermost baseUrl missing for account "${account.accountId}" (set channels.mattermost.accounts.${account.accountId}.baseUrl or MATTERMOST_URL for default).`,
);
}
const client = createMattermostClient({ baseUrl, botToken });
const botUser = await fetchMattermostMe(client);
const botUserId = botUser.id;
const botUsername = botUser.username?.trim() || undefined;
runtime.log?.(`mattermost connected as ${botUsername ? `@${botUsername}` : botUserId}`);
const channelCache = new Map<string, { value: MattermostChannel | null; expiresAt: number }>();
const userCache = new Map<string, { value: MattermostUser | null; expiresAt: number }>();
const logger = core.logging.getChildLogger({ module: "mattermost" });
const logVerboseMessage = (message: string) => {
if (!core.logging.shouldLogVerbose()) return;
logger.debug?.(message);
};
const mediaMaxBytes =
resolveChannelMediaMaxBytes({
cfg,
resolveChannelLimitMb: () => undefined,
accountId: account.accountId,
}) ?? 8 * 1024 * 1024;
const historyLimit = Math.max(
0,
cfg.messages?.groupChat?.historyLimit ?? DEFAULT_GROUP_HISTORY_LIMIT,
);
const channelHistories = new Map<string, HistoryEntry[]>();
const fetchWithAuth: FetchLike = (input, init) => {
const headers = new Headers(init?.headers);
headers.set("Authorization", `Bearer ${client.token}`);
return fetch(input, { ...init, headers });
};
const resolveMattermostMedia = async (
fileIds?: string[] | null,
): Promise<MattermostMediaInfo[]> => {
const ids = (fileIds ?? []).map((id) => id?.trim()).filter(Boolean) as string[];
if (ids.length === 0) return [];
const out: MattermostMediaInfo[] = [];
for (const fileId of ids) {
try {
const fetched = await core.channel.media.fetchRemoteMedia({
url: `${client.apiBaseUrl}/files/${fileId}`,
fetchImpl: fetchWithAuth,
filePathHint: fileId,
maxBytes: mediaMaxBytes,
});
const saved = await core.channel.media.saveMediaBuffer(
fetched.buffer,
fetched.contentType ?? undefined,
"inbound",
mediaMaxBytes,
);
const contentType = saved.contentType ?? fetched.contentType ?? undefined;
out.push({
path: saved.path,
contentType,
kind: core.media.mediaKindFromMime(contentType),
});
} catch (err) {
logger.debug?.(`mattermost: failed to download file ${fileId}: ${String(err)}`);
}
}
return out;
};
const sendTypingIndicator = async (channelId: string, parentId?: string) => {
try {
await sendMattermostTyping(client, { channelId, parentId });
} catch (err) {
logger.debug?.(`mattermost typing cue failed for channel ${channelId}: ${String(err)}`);
}
};
const resolveChannelInfo = async (channelId: string): Promise<MattermostChannel | null> => {
const cached = channelCache.get(channelId);
if (cached && cached.expiresAt > Date.now()) return cached.value;
try {
const info = await fetchMattermostChannel(client, channelId);
channelCache.set(channelId, {
value: info,
expiresAt: Date.now() + CHANNEL_CACHE_TTL_MS,
});
return info;
} catch (err) {
logger.debug?.(`mattermost: channel lookup failed: ${String(err)}`);
channelCache.set(channelId, {
value: null,
expiresAt: Date.now() + CHANNEL_CACHE_TTL_MS,
});
return null;
}
};
const resolveUserInfo = async (userId: string): Promise<MattermostUser | null> => {
const cached = userCache.get(userId);
if (cached && cached.expiresAt > Date.now()) return cached.value;
try {
const info = await fetchMattermostUser(client, userId);
userCache.set(userId, {
value: info,
expiresAt: Date.now() + USER_CACHE_TTL_MS,
});
return info;
} catch (err) {
logger.debug?.(`mattermost: user lookup failed: ${String(err)}`);
userCache.set(userId, {
value: null,
expiresAt: Date.now() + USER_CACHE_TTL_MS,
});
return null;
}
};
const handlePost = async (
post: MattermostPost,
payload: MattermostEventPayload,
messageIds?: string[],
) => {
const channelId = post.channel_id ?? payload.data?.channel_id ?? payload.broadcast?.channel_id;
if (!channelId) return;
const allMessageIds = messageIds?.length ? messageIds : post.id ? [post.id] : [];
if (allMessageIds.length === 0) return;
const dedupeEntries = allMessageIds.map((id) =>
recentInboundMessages.check(`${account.accountId}:${id}`),
);
if (dedupeEntries.length > 0 && dedupeEntries.every(Boolean)) return;
const senderId = post.user_id ?? payload.broadcast?.user_id;
if (!senderId) return;
if (senderId === botUserId) return;
if (isSystemPost(post)) return;
const channelInfo = await resolveChannelInfo(channelId);
const channelType = payload.data?.channel_type ?? channelInfo?.type ?? undefined;
const kind = channelKind(channelType);
const chatType = channelChatType(kind);
const senderName =
payload.data?.sender_name?.trim() ||
(await resolveUserInfo(senderId))?.username?.trim() ||
senderId;
const rawText = post.message?.trim() || "";
const dmPolicy = account.config.dmPolicy ?? "pairing";
const defaultGroupPolicy = cfg.channels?.defaults?.groupPolicy;
const groupPolicy = account.config.groupPolicy ?? defaultGroupPolicy ?? "allowlist";
const configAllowFrom = normalizeAllowList(account.config.allowFrom ?? []);
const configGroupAllowFrom = normalizeAllowList(account.config.groupAllowFrom ?? []);
const storeAllowFrom = normalizeAllowList(
await core.channel.pairing.readAllowFromStore("mattermost").catch(() => []),
);
const effectiveAllowFrom = Array.from(new Set([...configAllowFrom, ...storeAllowFrom]));
const effectiveGroupAllowFrom = Array.from(
new Set([
...(configGroupAllowFrom.length > 0 ? configGroupAllowFrom : configAllowFrom),
...storeAllowFrom,
]),
);
const allowTextCommands = core.channel.commands.shouldHandleTextCommands({
cfg,
surface: "mattermost",
});
const isControlCommand = allowTextCommands && core.channel.text.hasControlCommand(rawText, cfg);
const useAccessGroups = cfg.commands?.useAccessGroups !== false;
const senderAllowedForCommands = isSenderAllowed({
senderId,
senderName,
allowFrom: effectiveAllowFrom,
});
const groupAllowedForCommands = isSenderAllowed({
senderId,
senderName,
allowFrom: effectiveGroupAllowFrom,
});
const commandAuthorized =
kind === "dm"
? dmPolicy === "open" || senderAllowedForCommands
: core.channel.commands.resolveCommandAuthorizedFromAuthorizers({
useAccessGroups,
authorizers: [
{ configured: effectiveAllowFrom.length > 0, allowed: senderAllowedForCommands },
{
configured: effectiveGroupAllowFrom.length > 0,
allowed: groupAllowedForCommands,
},
],
});
if (kind === "dm") {
if (dmPolicy === "disabled") {
logVerboseMessage(`mattermost: drop dm (dmPolicy=disabled sender=${senderId})`);
return;
}
if (dmPolicy !== "open" && !senderAllowedForCommands) {
if (dmPolicy === "pairing") {
const { code, created } = await core.channel.pairing.upsertPairingRequest({
channel: "mattermost",
id: senderId,
meta: { name: senderName },
});
logVerboseMessage(
`mattermost: pairing request sender=${senderId} created=${created}`,
);
if (created) {
try {
await sendMessageMattermost(
`user:${senderId}`,
core.channel.pairing.buildPairingReply({
channel: "mattermost",
idLine: `Your Mattermost user id: ${senderId}`,
code,
}),
{ accountId: account.accountId },
);
opts.statusSink?.({ lastOutboundAt: Date.now() });
} catch (err) {
logVerboseMessage(
`mattermost: pairing reply failed for ${senderId}: ${String(err)}`,
);
}
}
} else {
logVerboseMessage(
`mattermost: drop dm sender=${senderId} (dmPolicy=${dmPolicy})`,
);
}
return;
}
} else {
if (groupPolicy === "disabled") {
logVerboseMessage("mattermost: drop group message (groupPolicy=disabled)");
return;
}
if (groupPolicy === "allowlist") {
if (effectiveGroupAllowFrom.length === 0) {
logVerboseMessage("mattermost: drop group message (no group allowlist)");
return;
}
if (!groupAllowedForCommands) {
logVerboseMessage(
`mattermost: drop group sender=${senderId} (not in groupAllowFrom)`,
);
return;
}
}
}
if (kind !== "dm" && isControlCommand && !commandAuthorized) {
logVerboseMessage(
`mattermost: drop control command from unauthorized sender ${senderId}`,
);
return;
}
const teamId = payload.data?.team_id ?? channelInfo?.team_id ?? undefined;
const channelName = payload.data?.channel_name ?? channelInfo?.name ?? "";
const channelDisplay =
payload.data?.channel_display_name ?? channelInfo?.display_name ?? channelName;
const roomLabel = channelName ? `#${channelName}` : channelDisplay || `#${channelId}`;
const route = core.channel.routing.resolveAgentRoute({
cfg,
channel: "mattermost",
accountId: account.accountId,
teamId,
peer: {
kind,
id: kind === "dm" ? senderId : channelId,
},
});
const baseSessionKey = route.sessionKey;
const threadRootId = post.root_id?.trim() || undefined;
const threadKeys = resolveThreadSessionKeys({
baseSessionKey,
threadId: threadRootId,
parentSessionKey: threadRootId ? baseSessionKey : undefined,
});
const sessionKey = threadKeys.sessionKey;
const historyKey = kind === "dm" ? null : sessionKey;
const mentionRegexes = core.channel.mentions.buildMentionRegexes(cfg, route.agentId);
const wasMentioned =
kind !== "dm" &&
((botUsername ? rawText.toLowerCase().includes(`@${botUsername.toLowerCase()}`) : false) ||
core.channel.mentions.matchesMentionPatterns(rawText, mentionRegexes));
const pendingBody =
rawText ||
(post.file_ids?.length
? `[Mattermost ${post.file_ids.length === 1 ? "file" : "files"}]`
: "");
const pendingSender = senderName;
const recordPendingHistory = () => {
if (!historyKey || historyLimit <= 0) return;
const trimmed = pendingBody.trim();
if (!trimmed) return;
recordPendingHistoryEntry({
historyMap: channelHistories,
historyKey,
limit: historyLimit,
entry: {
sender: pendingSender,
body: trimmed,
timestamp: typeof post.create_at === "number" ? post.create_at : undefined,
messageId: post.id ?? undefined,
},
});
};
const oncharEnabled = account.chatmode === "onchar" && kind !== "dm";
const oncharPrefixes = oncharEnabled ? resolveOncharPrefixes(account.oncharPrefixes) : [];
const oncharResult = oncharEnabled
? stripOncharPrefix(rawText, oncharPrefixes)
: { triggered: false, stripped: rawText };
const oncharTriggered = oncharResult.triggered;
const shouldRequireMention =
kind !== "dm" &&
core.channel.groups.resolveRequireMention({
cfg,
channel: "mattermost",
accountId: account.accountId,
groupId: channelId,
}) !== false;
const shouldBypassMention =
isControlCommand && shouldRequireMention && !wasMentioned && commandAuthorized;
const effectiveWasMentioned = wasMentioned || shouldBypassMention || oncharTriggered;
const canDetectMention = Boolean(botUsername) || mentionRegexes.length > 0;
if (oncharEnabled && !oncharTriggered && !wasMentioned && !isControlCommand) {
recordPendingHistory();
return;
}
if (kind !== "dm" && shouldRequireMention && canDetectMention) {
if (!effectiveWasMentioned) {
recordPendingHistory();
return;
}
}
const mediaList = await resolveMattermostMedia(post.file_ids);
const mediaPlaceholder = buildMattermostAttachmentPlaceholder(mediaList);
const bodySource = oncharTriggered ? oncharResult.stripped : rawText;
const baseText = [bodySource, mediaPlaceholder].filter(Boolean).join("\n").trim();
const bodyText = normalizeMention(baseText, botUsername);
if (!bodyText) return;
core.channel.activity.record({
channel: "mattermost",
accountId: account.accountId,
direction: "inbound",
});
const fromLabel = formatInboundFromLabel({
isGroup: kind !== "dm",
groupLabel: channelDisplay || roomLabel,
groupId: channelId,
groupFallback: roomLabel || "Channel",
directLabel: senderName,
directId: senderId,
});
const preview = bodyText.replace(/\s+/g, " ").slice(0, 160);
const inboundLabel =
kind === "dm"
? `Mattermost DM from ${senderName}`
: `Mattermost message in ${roomLabel} from ${senderName}`;
core.system.enqueueSystemEvent(`${inboundLabel}: ${preview}`, {
sessionKey,
contextKey: `mattermost:message:${channelId}:${post.id ?? "unknown"}`,
});
const textWithId = `${bodyText}\n[mattermost message id: ${post.id ?? "unknown"} channel: ${channelId}]`;
const body = core.channel.reply.formatInboundEnvelope({
channel: "Mattermost",
from: fromLabel,
timestamp: typeof post.create_at === "number" ? post.create_at : undefined,
body: textWithId,
chatType,
sender: { name: senderName, id: senderId },
});
let combinedBody = body;
if (historyKey && historyLimit > 0) {
combinedBody = buildPendingHistoryContextFromMap({
historyMap: channelHistories,
historyKey,
limit: historyLimit,
currentMessage: combinedBody,
formatEntry: (entry) =>
core.channel.reply.formatInboundEnvelope({
channel: "Mattermost",
from: fromLabel,
timestamp: entry.timestamp,
body: `${entry.body}${
entry.messageId ? ` [id:${entry.messageId} channel:${channelId}]` : ""
}`,
chatType,
senderLabel: entry.sender,
}),
});
}
const to = kind === "dm" ? `user:${senderId}` : `channel:${channelId}`;
const mediaPayload = buildMattermostMediaPayload(mediaList);
const ctxPayload = core.channel.reply.finalizeInboundContext({
Body: combinedBody,
RawBody: bodyText,
CommandBody: bodyText,
From:
kind === "dm"
? `mattermost:${senderId}`
: kind === "group"
? `mattermost:group:${channelId}`
: `mattermost:channel:${channelId}`,
To: to,
SessionKey: sessionKey,
ParentSessionKey: threadKeys.parentSessionKey,
AccountId: route.accountId,
ChatType: chatType,
ConversationLabel: fromLabel,
GroupSubject: kind !== "dm" ? channelDisplay || roomLabel : undefined,
GroupChannel: channelName ? `#${channelName}` : undefined,
GroupSpace: teamId,
SenderName: senderName,
SenderId: senderId,
Provider: "mattermost" as const,
Surface: "mattermost" as const,
MessageSid: post.id ?? undefined,
MessageSids: allMessageIds.length > 1 ? allMessageIds : undefined,
MessageSidFirst: allMessageIds.length > 1 ? allMessageIds[0] : undefined,
MessageSidLast:
allMessageIds.length > 1 ? allMessageIds[allMessageIds.length - 1] : undefined,
ReplyToId: threadRootId,
MessageThreadId: threadRootId,
Timestamp: typeof post.create_at === "number" ? post.create_at : undefined,
WasMentioned: kind !== "dm" ? effectiveWasMentioned : undefined,
CommandAuthorized: commandAuthorized,
OriginatingChannel: "mattermost" as const,
OriginatingTo: to,
...mediaPayload,
});
if (kind === "dm") {
const sessionCfg = cfg.session;
const storePath = core.channel.session.resolveStorePath(sessionCfg?.store, {
agentId: route.agentId,
});
await core.channel.session.updateLastRoute({
storePath,
sessionKey: route.mainSessionKey,
deliveryContext: {
channel: "mattermost",
to,
accountId: route.accountId,
},
});
}
const previewLine = bodyText.slice(0, 200).replace(/\n/g, "\\n");
logVerboseMessage(
`mattermost inbound: from=${ctxPayload.From} len=${bodyText.length} preview="${previewLine}"`,
);
const textLimit = core.channel.text.resolveTextChunkLimit(cfg, "mattermost", account.accountId, {
fallbackLimit: account.textChunkLimit ?? 4000,
});
let prefixContext: ResponsePrefixContext = {
identityName: resolveIdentityName(cfg, route.agentId),
};
const { dispatcher, replyOptions, markDispatchIdle } =
core.channel.reply.createReplyDispatcherWithTyping({
responsePrefix: core.channel.reply.resolveEffectiveMessagesConfig(cfg, route.agentId)
.responsePrefix,
responsePrefixContextProvider: () => prefixContext,
humanDelay: core.channel.reply.resolveHumanDelayConfig(cfg, route.agentId),
deliver: async (payload: ReplyPayload) => {
const mediaUrls = payload.mediaUrls ?? (payload.mediaUrl ? [payload.mediaUrl] : []);
const text = payload.text ?? "";
if (mediaUrls.length === 0) {
const chunks = core.channel.text.chunkMarkdownText(text, textLimit);
for (const chunk of chunks.length > 0 ? chunks : [text]) {
if (!chunk) continue;
await sendMessageMattermost(to, chunk, {
accountId: account.accountId,
replyToId: threadRootId,
});
}
} else {
let first = true;
for (const mediaUrl of mediaUrls) {
const caption = first ? text : "";
first = false;
await sendMessageMattermost(to, caption, {
accountId: account.accountId,
mediaUrl,
replyToId: threadRootId,
});
}
}
runtime.log?.(`delivered reply to ${to}`);
},
onError: (err, info) => {
runtime.error?.(`mattermost ${info.kind} reply failed: ${String(err)}`);
},
onReplyStart: () => sendTypingIndicator(channelId, threadRootId),
});
await core.channel.reply.dispatchReplyFromConfig({
ctx: ctxPayload,
cfg,
dispatcher,
replyOptions: {
...replyOptions,
disableBlockStreaming:
typeof account.blockStreaming === "boolean" ? !account.blockStreaming : undefined,
onModelSelected: (ctx) => {
prefixContext.provider = ctx.provider;
prefixContext.model = extractShortModelName(ctx.model);
prefixContext.modelFull = `${ctx.provider}/${ctx.model}`;
prefixContext.thinkingLevel = ctx.thinkLevel ?? "off";
},
},
});
markDispatchIdle();
if (historyKey && historyLimit > 0) {
clearHistoryEntries({ historyMap: channelHistories, historyKey });
}
};
const inboundDebounceMs = core.channel.debounce.resolveInboundDebounceMs({
cfg,
channel: "mattermost",
});
const debouncer = core.channel.debounce.createInboundDebouncer<{
post: MattermostPost;
payload: MattermostEventPayload;
}>({
debounceMs: inboundDebounceMs,
buildKey: (entry) => {
const channelId =
entry.post.channel_id ??
entry.payload.data?.channel_id ??
entry.payload.broadcast?.channel_id;
if (!channelId) return null;
const threadId = entry.post.root_id?.trim();
const threadKey = threadId ? `thread:${threadId}` : "channel";
return `mattermost:${account.accountId}:${channelId}:${threadKey}`;
},
shouldDebounce: (entry) => {
if (entry.post.file_ids && entry.post.file_ids.length > 0) return false;
const text = entry.post.message?.trim() ?? "";
if (!text) return false;
return !core.channel.text.hasControlCommand(text, cfg);
},
onFlush: async (entries) => {
const last = entries.at(-1);
if (!last) return;
if (entries.length === 1) {
await handlePost(last.post, last.payload);
return;
}
const combinedText = entries
.map((entry) => entry.post.message?.trim() ?? "")
.filter(Boolean)
.join("\n");
const mergedPost: MattermostPost = {
...last.post,
message: combinedText,
file_ids: [],
};
const ids = entries.map((entry) => entry.post.id).filter(Boolean) as string[];
await handlePost(mergedPost, last.payload, ids.length > 0 ? ids : undefined);
},
onError: (err) => {
runtime.error?.(`mattermost debounce flush failed: ${String(err)}`);
},
});
const wsUrl = buildMattermostWsUrl(baseUrl);
let seq = 1;
const connectOnce = async (): Promise<void> => {
const ws = new WebSocket(wsUrl);
const onAbort = () => ws.close();
opts.abortSignal?.addEventListener("abort", onAbort, { once: true });
return await new Promise((resolve) => {
ws.on("open", () => {
opts.statusSink?.({
connected: true,
lastConnectedAt: Date.now(),
lastError: null,
});
ws.send(
JSON.stringify({
seq: seq++,
action: "authentication_challenge",
data: { token: botToken },
}),
);
});
ws.on("message", async (data) => {
const raw = rawDataToString(data);
let payload: MattermostEventPayload;
try {
payload = JSON.parse(raw) as MattermostEventPayload;
} catch {
return;
}
if (payload.event !== "posted") return;
const postData = payload.data?.post;
if (!postData) return;
let post: MattermostPost | null = null;
if (typeof postData === "string") {
try {
post = JSON.parse(postData) as MattermostPost;
} catch {
return;
}
} else if (typeof postData === "object") {
post = postData as MattermostPost;
}
if (!post) return;
try {
await debouncer.enqueue({ post, payload });
} catch (err) {
runtime.error?.(`mattermost handler failed: ${String(err)}`);
}
});
ws.on("close", (code, reason) => {
const message = reason.length > 0 ? reason.toString("utf8") : "";
opts.statusSink?.({
connected: false,
lastDisconnect: {
at: Date.now(),
status: code,
error: message || undefined,
},
});
opts.abortSignal?.removeEventListener("abort", onAbort);
resolve();
});
ws.on("error", (err) => {
runtime.error?.(`mattermost websocket error: ${String(err)}`);
opts.statusSink?.({
lastError: String(err),
});
});
});
};
while (!opts.abortSignal?.aborted) {
await connectOnce();
if (opts.abortSignal?.aborted) return;
await new Promise((resolve) => setTimeout(resolve, 2000));
}
}

View File

@@ -0,0 +1,70 @@
import { normalizeMattermostBaseUrl, type MattermostUser } from "./client.js";
export type MattermostProbe = {
ok: boolean;
status?: number | null;
error?: string | null;
elapsedMs?: number | null;
bot?: MattermostUser;
};
async function readMattermostError(res: Response): Promise<string> {
const contentType = res.headers.get("content-type") ?? "";
if (contentType.includes("application/json")) {
const data = (await res.json()) as { message?: string } | undefined;
if (data?.message) return data.message;
return JSON.stringify(data);
}
return await res.text();
}
export async function probeMattermost(
baseUrl: string,
botToken: string,
timeoutMs = 2500,
): Promise<MattermostProbe> {
const normalized = normalizeMattermostBaseUrl(baseUrl);
if (!normalized) {
return { ok: false, error: "baseUrl missing" };
}
const url = `${normalized}/api/v4/users/me`;
const start = Date.now();
const controller = timeoutMs > 0 ? new AbortController() : undefined;
let timer: NodeJS.Timeout | null = null;
if (controller) {
timer = setTimeout(() => controller.abort(), timeoutMs);
}
try {
const res = await fetch(url, {
headers: { Authorization: `Bearer ${botToken}` },
signal: controller?.signal,
});
const elapsedMs = Date.now() - start;
if (!res.ok) {
const detail = await readMattermostError(res);
return {
ok: false,
status: res.status,
error: detail || res.statusText,
elapsedMs,
};
}
const bot = (await res.json()) as MattermostUser;
return {
ok: true,
status: res.status,
elapsedMs,
bot,
};
} catch (err) {
const message = err instanceof Error ? err.message : String(err);
return {
ok: false,
status: null,
error: message,
elapsedMs: Date.now() - start,
};
} finally {
if (timer) clearTimeout(timer);
}
}

View File

@@ -0,0 +1,208 @@
import { getMattermostRuntime } from "../runtime.js";
import { resolveMattermostAccount } from "./accounts.js";
import {
createMattermostClient,
createMattermostDirectChannel,
createMattermostPost,
fetchMattermostMe,
fetchMattermostUserByUsername,
normalizeMattermostBaseUrl,
uploadMattermostFile,
type MattermostUser,
} from "./client.js";
export type MattermostSendOpts = {
botToken?: string;
baseUrl?: string;
accountId?: string;
mediaUrl?: string;
replyToId?: string;
};
export type MattermostSendResult = {
messageId: string;
channelId: string;
};
type MattermostTarget =
| { kind: "channel"; id: string }
| { kind: "user"; id?: string; username?: string };
const botUserCache = new Map<string, MattermostUser>();
const userByNameCache = new Map<string, MattermostUser>();
const getCore = () => getMattermostRuntime();
function cacheKey(baseUrl: string, token: string): string {
return `${baseUrl}::${token}`;
}
function normalizeMessage(text: string, mediaUrl?: string): string {
const trimmed = text.trim();
const media = mediaUrl?.trim();
return [trimmed, media].filter(Boolean).join("\n");
}
function isHttpUrl(value: string): boolean {
return /^https?:\/\//i.test(value);
}
function parseMattermostTarget(raw: string): MattermostTarget {
const trimmed = raw.trim();
if (!trimmed) throw new Error("Recipient is required for Mattermost sends");
const lower = trimmed.toLowerCase();
if (lower.startsWith("channel:")) {
const id = trimmed.slice("channel:".length).trim();
if (!id) throw new Error("Channel id is required for Mattermost sends");
return { kind: "channel", id };
}
if (lower.startsWith("user:")) {
const id = trimmed.slice("user:".length).trim();
if (!id) throw new Error("User id is required for Mattermost sends");
return { kind: "user", id };
}
if (lower.startsWith("mattermost:")) {
const id = trimmed.slice("mattermost:".length).trim();
if (!id) throw new Error("User id is required for Mattermost sends");
return { kind: "user", id };
}
if (trimmed.startsWith("@")) {
const username = trimmed.slice(1).trim();
if (!username) {
throw new Error("Username is required for Mattermost sends");
}
return { kind: "user", username };
}
return { kind: "channel", id: trimmed };
}
async function resolveBotUser(baseUrl: string, token: string): Promise<MattermostUser> {
const key = cacheKey(baseUrl, token);
const cached = botUserCache.get(key);
if (cached) return cached;
const client = createMattermostClient({ baseUrl, botToken: token });
const user = await fetchMattermostMe(client);
botUserCache.set(key, user);
return user;
}
async function resolveUserIdByUsername(params: {
baseUrl: string;
token: string;
username: string;
}): Promise<string> {
const { baseUrl, token, username } = params;
const key = `${cacheKey(baseUrl, token)}::${username.toLowerCase()}`;
const cached = userByNameCache.get(key);
if (cached?.id) return cached.id;
const client = createMattermostClient({ baseUrl, botToken: token });
const user = await fetchMattermostUserByUsername(client, username);
userByNameCache.set(key, user);
return user.id;
}
async function resolveTargetChannelId(params: {
target: MattermostTarget;
baseUrl: string;
token: string;
}): Promise<string> {
if (params.target.kind === "channel") return params.target.id;
const userId = params.target.id
? params.target.id
: await resolveUserIdByUsername({
baseUrl: params.baseUrl,
token: params.token,
username: params.target.username ?? "",
});
const botUser = await resolveBotUser(params.baseUrl, params.token);
const client = createMattermostClient({
baseUrl: params.baseUrl,
botToken: params.token,
});
const channel = await createMattermostDirectChannel(client, [botUser.id, userId]);
return channel.id;
}
export async function sendMessageMattermost(
to: string,
text: string,
opts: MattermostSendOpts = {},
): Promise<MattermostSendResult> {
const core = getCore();
const logger = core.logging.getChildLogger({ module: "mattermost" });
const cfg = core.config.loadConfig();
const account = resolveMattermostAccount({
cfg,
accountId: opts.accountId,
});
const token = opts.botToken?.trim() || account.botToken?.trim();
if (!token) {
throw new Error(
`Mattermost bot token missing for account "${account.accountId}" (set channels.mattermost.accounts.${account.accountId}.botToken or MATTERMOST_BOT_TOKEN for default).`,
);
}
const baseUrl = normalizeMattermostBaseUrl(opts.baseUrl ?? account.baseUrl);
if (!baseUrl) {
throw new Error(
`Mattermost baseUrl missing for account "${account.accountId}" (set channels.mattermost.accounts.${account.accountId}.baseUrl or MATTERMOST_URL for default).`,
);
}
const target = parseMattermostTarget(to);
const channelId = await resolveTargetChannelId({
target,
baseUrl,
token,
});
const client = createMattermostClient({ baseUrl, botToken: token });
let message = text?.trim() ?? "";
let fileIds: string[] | undefined;
let uploadError: Error | undefined;
const mediaUrl = opts.mediaUrl?.trim();
if (mediaUrl) {
try {
const media = await core.media.loadWebMedia(mediaUrl);
const fileInfo = await uploadMattermostFile(client, {
channelId,
buffer: media.buffer,
fileName: media.fileName ?? "upload",
contentType: media.contentType ?? undefined,
});
fileIds = [fileInfo.id];
} catch (err) {
uploadError = err instanceof Error ? err : new Error(String(err));
if (core.logging.shouldLogVerbose()) {
logger.debug?.(
`mattermost send: media upload failed, falling back to URL text: ${String(err)}`,
);
}
message = normalizeMessage(message, isHttpUrl(mediaUrl) ? mediaUrl : "");
}
}
if (!message && (!fileIds || fileIds.length === 0)) {
if (uploadError) {
throw new Error(`Mattermost media upload failed: ${uploadError.message}`);
}
throw new Error("Mattermost message is empty");
}
const post = await createMattermostPost(client, {
channelId,
message,
rootId: opts.replyToId,
fileIds,
});
core.channel.activity.record({
channel: "mattermost",
accountId: account.accountId,
direction: "outbound",
});
return {
messageId: post.id ?? "unknown",
channelId,
};
}

View File

@@ -0,0 +1,38 @@
export function normalizeMattermostMessagingTarget(raw: string): string | undefined {
const trimmed = raw.trim();
if (!trimmed) return undefined;
const lower = trimmed.toLowerCase();
if (lower.startsWith("channel:")) {
const id = trimmed.slice("channel:".length).trim();
return id ? `channel:${id}` : undefined;
}
if (lower.startsWith("group:")) {
const id = trimmed.slice("group:".length).trim();
return id ? `channel:${id}` : undefined;
}
if (lower.startsWith("user:")) {
const id = trimmed.slice("user:".length).trim();
return id ? `user:${id}` : undefined;
}
if (lower.startsWith("mattermost:")) {
const id = trimmed.slice("mattermost:".length).trim();
return id ? `user:${id}` : undefined;
}
if (trimmed.startsWith("@")) {
const id = trimmed.slice(1).trim();
return id ? `@${id}` : undefined;
}
if (trimmed.startsWith("#")) {
const id = trimmed.slice(1).trim();
return id ? `channel:${id}` : undefined;
}
return `channel:${trimmed}`;
}
export function looksLikeMattermostTargetId(raw: string): boolean {
const trimmed = raw.trim();
if (!trimmed) return false;
if (/^(user|channel|group|mattermost):/i.test(trimmed)) return true;
if (/^[@#]/.test(trimmed)) return true;
return /^[a-z0-9]{8,}$/i.test(trimmed);
}

View File

@@ -0,0 +1,42 @@
import type { ClawdbotConfig, WizardPrompter } from "clawdbot/plugin-sdk";
import { DEFAULT_ACCOUNT_ID, normalizeAccountId } from "clawdbot/plugin-sdk";
type PromptAccountIdParams = {
cfg: ClawdbotConfig;
prompter: WizardPrompter;
label: string;
currentId?: string;
listAccountIds: (cfg: ClawdbotConfig) => string[];
defaultAccountId: string;
};
export async function promptAccountId(params: PromptAccountIdParams): Promise<string> {
const existingIds = params.listAccountIds(params.cfg);
const initial = params.currentId?.trim() || params.defaultAccountId || DEFAULT_ACCOUNT_ID;
const choice = (await params.prompter.select({
message: `${params.label} account`,
options: [
...existingIds.map((id) => ({
value: id,
label: id === DEFAULT_ACCOUNT_ID ? "default (primary)" : id,
})),
{ value: "__new__", label: "Add a new account" },
],
initialValue: initial,
})) as string;
if (choice !== "__new__") return normalizeAccountId(choice);
const entered = await params.prompter.text({
message: `New ${params.label} account id`,
validate: (value) => (value?.trim() ? undefined : "Required"),
});
const normalized = normalizeAccountId(String(entered));
if (String(entered).trim() !== normalized) {
await params.prompter.note(
`Normalized account id to "${normalized}".`,
`${params.label} account`,
);
}
return normalized;
}

View File

@@ -0,0 +1,187 @@
import type { ChannelOnboardingAdapter, ClawdbotConfig, WizardPrompter } from "clawdbot/plugin-sdk";
import { DEFAULT_ACCOUNT_ID, normalizeAccountId } from "clawdbot/plugin-sdk";
import {
listMattermostAccountIds,
resolveDefaultMattermostAccountId,
resolveMattermostAccount,
} from "./mattermost/accounts.js";
import { promptAccountId } from "./onboarding-helpers.js";
const channel = "mattermost" as const;
async function noteMattermostSetup(prompter: WizardPrompter): Promise<void> {
await prompter.note(
[
"1) Mattermost System Console -> Integrations -> Bot Accounts",
"2) Create a bot + copy its token",
"3) Use your server base URL (e.g., https://chat.example.com)",
"Tip: the bot must be a member of any channel you want it to monitor.",
"Docs: https://docs.clawd.bot/channels/mattermost",
].join("\n"),
"Mattermost bot token",
);
}
export const mattermostOnboardingAdapter: ChannelOnboardingAdapter = {
channel,
getStatus: async ({ cfg }) => {
const configured = listMattermostAccountIds(cfg).some((accountId) => {
const account = resolveMattermostAccount({ cfg, accountId });
return Boolean(account.botToken && account.baseUrl);
});
return {
channel,
configured,
statusLines: [`Mattermost: ${configured ? "configured" : "needs token + url"}`],
selectionHint: configured ? "configured" : "needs setup",
quickstartScore: configured ? 2 : 1,
};
},
configure: async ({ cfg, prompter, accountOverrides, shouldPromptAccountIds }) => {
const override = accountOverrides.mattermost?.trim();
const defaultAccountId = resolveDefaultMattermostAccountId(cfg);
let accountId = override ? normalizeAccountId(override) : defaultAccountId;
if (shouldPromptAccountIds && !override) {
accountId = await promptAccountId({
cfg,
prompter,
label: "Mattermost",
currentId: accountId,
listAccountIds: listMattermostAccountIds,
defaultAccountId,
});
}
let next = cfg;
const resolvedAccount = resolveMattermostAccount({
cfg: next,
accountId,
});
const accountConfigured = Boolean(resolvedAccount.botToken && resolvedAccount.baseUrl);
const allowEnv = accountId === DEFAULT_ACCOUNT_ID;
const canUseEnv =
allowEnv &&
Boolean(process.env.MATTERMOST_BOT_TOKEN?.trim()) &&
Boolean(process.env.MATTERMOST_URL?.trim());
const hasConfigValues =
Boolean(resolvedAccount.config.botToken) || Boolean(resolvedAccount.config.baseUrl);
let botToken: string | null = null;
let baseUrl: string | null = null;
if (!accountConfigured) {
await noteMattermostSetup(prompter);
}
if (canUseEnv && !hasConfigValues) {
const keepEnv = await prompter.confirm({
message: "MATTERMOST_BOT_TOKEN + MATTERMOST_URL detected. Use env vars?",
initialValue: true,
});
if (keepEnv) {
next = {
...next,
channels: {
...next.channels,
mattermost: {
...next.channels?.mattermost,
enabled: true,
},
},
};
} else {
botToken = String(
await prompter.text({
message: "Enter Mattermost bot token",
validate: (value) => (value?.trim() ? undefined : "Required"),
}),
).trim();
baseUrl = String(
await prompter.text({
message: "Enter Mattermost base URL",
validate: (value) => (value?.trim() ? undefined : "Required"),
}),
).trim();
}
} else if (accountConfigured) {
const keep = await prompter.confirm({
message: "Mattermost credentials already configured. Keep them?",
initialValue: true,
});
if (!keep) {
botToken = String(
await prompter.text({
message: "Enter Mattermost bot token",
validate: (value) => (value?.trim() ? undefined : "Required"),
}),
).trim();
baseUrl = String(
await prompter.text({
message: "Enter Mattermost base URL",
validate: (value) => (value?.trim() ? undefined : "Required"),
}),
).trim();
}
} else {
botToken = String(
await prompter.text({
message: "Enter Mattermost bot token",
validate: (value) => (value?.trim() ? undefined : "Required"),
}),
).trim();
baseUrl = String(
await prompter.text({
message: "Enter Mattermost base URL",
validate: (value) => (value?.trim() ? undefined : "Required"),
}),
).trim();
}
if (botToken || baseUrl) {
if (accountId === DEFAULT_ACCOUNT_ID) {
next = {
...next,
channels: {
...next.channels,
mattermost: {
...next.channels?.mattermost,
enabled: true,
...(botToken ? { botToken } : {}),
...(baseUrl ? { baseUrl } : {}),
},
},
};
} else {
next = {
...next,
channels: {
...next.channels,
mattermost: {
...next.channels?.mattermost,
enabled: true,
accounts: {
...next.channels?.mattermost?.accounts,
[accountId]: {
...next.channels?.mattermost?.accounts?.[accountId],
enabled: next.channels?.mattermost?.accounts?.[accountId]?.enabled ?? true,
...(botToken ? { botToken } : {}),
...(baseUrl ? { baseUrl } : {}),
},
},
},
},
};
}
}
return { cfg: next, accountId };
},
disable: (cfg: ClawdbotConfig) => ({
...cfg,
channels: {
...cfg.channels,
mattermost: { ...cfg.channels?.mattermost, enabled: false },
},
}),
};

View File

@@ -0,0 +1,14 @@
import type { PluginRuntime } from "clawdbot/plugin-sdk";
let runtime: PluginRuntime | null = null;
export function setMattermostRuntime(next: PluginRuntime) {
runtime = next;
}
export function getMattermostRuntime(): PluginRuntime {
if (!runtime) {
throw new Error("Mattermost runtime not initialized");
}
return runtime;
}

View File

@@ -0,0 +1,48 @@
import type { BlockStreamingCoalesceConfig, DmPolicy, GroupPolicy } from "clawdbot/plugin-sdk";
export type MattermostChatMode = "oncall" | "onmessage" | "onchar";
export type MattermostAccountConfig = {
/** Optional display name for this account (used in CLI/UI lists). */
name?: string;
/** Optional provider capability tags used for agent/runtime guidance. */
capabilities?: string[];
/** Allow channel-initiated config writes (default: true). */
configWrites?: boolean;
/** If false, do not start this Mattermost account. Default: true. */
enabled?: boolean;
/** Bot token for Mattermost. */
botToken?: string;
/** Base URL for the Mattermost server (e.g., https://chat.example.com). */
baseUrl?: string;
/**
* Controls when channel messages trigger replies.
* - "oncall": only respond when mentioned
* - "onmessage": respond to every channel message
* - "onchar": respond when a trigger character prefixes the message
*/
chatmode?: MattermostChatMode;
/** Prefix characters that trigger onchar mode (default: [">", "!"]). */
oncharPrefixes?: string[];
/** Require @mention to respond in channels. Default: true. */
requireMention?: boolean;
/** Direct message policy (pairing/allowlist/open/disabled). */
dmPolicy?: DmPolicy;
/** Allowlist for direct messages (user ids or @usernames). */
allowFrom?: Array<string | number>;
/** Allowlist for group messages (user ids or @usernames). */
groupAllowFrom?: Array<string | number>;
/** Group message policy (allowlist/open/disabled). */
groupPolicy?: GroupPolicy;
/** Outbound text chunk size (chars). Default: 4000. */
textChunkLimit?: number;
/** Disable block streaming for this account. */
blockStreaming?: boolean;
/** Merge streamed block replies before sending. */
blockStreamingCoalesce?: BlockStreamingCoalesceConfig;
};
export type MattermostConfig = {
/** Optional per-account Mattermost configuration (multi-account). */
accounts?: Record<string, MattermostAccountConfig>;
} & MattermostAccountConfig;

View File

@@ -0,0 +1,25 @@
# OpenProse (plugin)
Adds the OpenProse skill pack and `/prose` slash command.
## Enable
Bundled plugins are disabled by default. Enable this one:
```json
{
"plugins": {
"entries": {
"open-prose": { "enabled": true }
}
}
}
```
Restart the Gateway after enabling.
## What you get
- `/prose` slash command (user-invocable skill)
- OpenProse VM semantics (`.prose` programs + multi-agent orchestration)
- Telemetry support (best-effort, per OpenProse spec)

View File

@@ -0,0 +1,11 @@
{
"id": "open-prose",
"name": "OpenProse",
"description": "OpenProse VM skill pack with a /prose slash command.",
"skills": ["./skills"],
"configSchema": {
"type": "object",
"additionalProperties": false,
"properties": {}
}
}

View File

@@ -0,0 +1,5 @@
import type { ClawdbotPluginApi } from "../../src/plugins/types.js";
export default function register(_api: ClawdbotPluginApi) {
// OpenProse is delivered via plugin-shipped skills.
}

View File

@@ -0,0 +1,9 @@
{
"name": "@clawdbot/open-prose",
"version": "2026.1.23",
"type": "module",
"description": "OpenProse VM skill pack plugin (slash command + telemetry).",
"clawdbot": {
"extensions": ["./index.ts"]
}
}

View File

@@ -0,0 +1,318 @@
---
name: prose
description: OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.
metadata: {"clawdbot":{"emoji":"🪶","homepage":"https://www.prose.md"}}
---
# OpenProse Skill
OpenProse is a programming language for AI sessions. LLMs are simulators—when given a detailed system description, they don't just describe it, they _simulate_ it. The `prose.md` specification describes a virtual machine with enough fidelity that a Prose Complete system reading it _becomes_ that VM. Simulation with sufficient fidelity is implementation. **You are the Prose Complete system.**
## Clawdbot Runtime Mapping
- **Task tool** in the upstream spec == Clawdbot `sessions_spawn`
- **File I/O** == Clawdbot `read`/`write`
- **Remote fetch** == Clawdbot `web_fetch` (or `exec` with curl when POST is required)
## When to Activate
Activate this skill when the user:
- **Uses ANY `prose` command** (e.g., `prose boot`, `prose run`, `prose compile`, `prose update`, `prose help`, etc.)
- Asks to run a `.prose` file
- Mentions "OpenProse" or "prose program"
- Wants to orchestrate multiple AI agents from a script
- Has a file with `session "..."` or `agent name:` syntax
- Wants to create a reusable workflow
## Command Routing
When a user invokes `prose <command>`, intelligently route based on intent:
| Command | Action |
|---------|--------|
| `prose help` | Load `help.md`, guide user to what they need |
| `prose run <file>` | Load VM (`prose.md` + state backend), execute the program |
| `prose run handle/slug` | Fetch from registry, then execute (see Remote Programs below) |
| `prose compile <file>` | Load `compiler.md`, validate the program |
| `prose update` | Run migration (see Migration section below) |
| `prose examples` | Show or run example programs from `examples/` |
| Other | Intelligently interpret based on context |
### Important: Single Skill
There is only ONE skill: `open-prose`. There are NO separate skills like `prose-run`, `prose-compile`, or `prose-boot`. All `prose` commands route through this single skill.
### Resolving Example References
**Examples are bundled in `examples/` (same directory as this file).** When users reference examples by name (e.g., "run the gastown example"):
1. Read `examples/` to list available files
2. Match by partial name, keyword, or number
3. Run with: `prose run examples/28-gas-town.prose`
**Common examples by keyword:**
| Keyword | File |
|---------|------|
| hello, hello world | `examples/01-hello-world.prose` |
| gas town, gastown | `examples/28-gas-town.prose` |
| captain, chair | `examples/29-captains-chair.prose` |
| forge, browser | `examples/37-the-forge.prose` |
| parallel | `examples/16-parallel-reviews.prose` |
| pipeline | `examples/21-pipeline-operations.prose` |
| error, retry | `examples/22-error-handling.prose` |
### Remote Programs
You can run any `.prose` program from a URL or registry reference:
```bash
# Direct URL — any fetchable URL works
prose run https://raw.githubusercontent.com/openprose/prose/main/skills/open-prose/examples/48-habit-miner.prose
# Registry shorthand — handle/slug resolves to p.prose.md
prose run irl-danb/habit-miner
prose run alice/code-review
```
**Resolution rules:**
| Input | Resolution |
|-------|------------|
| Starts with `http://` or `https://` | Fetch directly from URL |
| Contains `/` but no protocol | Resolve to `https://p.prose.md/{path}` |
| Otherwise | Treat as local file path |
**Steps for remote programs:**
1. Apply resolution rules above
2. Fetch the `.prose` content
3. Load the VM and execute as normal
This same resolution applies to `use` statements inside `.prose` files:
```prose
use "https://example.com/my-program.prose" # Direct URL
use "alice/research" as research # Registry shorthand
```
---
## File Locations
**Do NOT search for OpenProse documentation files.** All skill files are co-located with this SKILL.md file:
| File | Location | Purpose |
| ------------------------- | --------------------------- | ----------------------------------------- |
| `prose.md` | Same directory as this file | VM semantics (load to run programs) |
| `help.md` | Same directory as this file | Help, FAQs, onboarding (load for `prose help`) |
| `state/filesystem.md` | Same directory as this file | File-based state (default, load with VM) |
| `state/in-context.md` | Same directory as this file | In-context state (on request) |
| `state/sqlite.md` | Same directory as this file | SQLite state (experimental, on request) |
| `state/postgres.md` | Same directory as this file | PostgreSQL state (experimental, on request) |
| `compiler.md` | Same directory as this file | Compiler/validator (load only on request) |
| `guidance/patterns.md` | Same directory as this file | Best practices (load when writing .prose) |
| `guidance/antipatterns.md`| Same directory as this file | What to avoid (load when writing .prose) |
| `examples/` | Same directory as this file | 37 example programs |
**User workspace files** (these ARE in the user's project):
| File/Directory | Location | Purpose |
| ---------------- | ------------------------ | ----------------------------------- |
| `.prose/.env` | User's working directory | Config (key=value format) |
| `.prose/runs/` | User's working directory | Runtime state for file-based mode |
| `.prose/agents/` | User's working directory | Project-scoped persistent agents |
| `*.prose` files | User's project | User-created programs to execute |
**User-level files** (in user's home directory, shared across all projects):
| File/Directory | Location | Purpose |
| ----------------- | ---------------- | ---------------------------------------- |
| `~/.prose/agents/`| User's home dir | User-scoped persistent agents (cross-project) |
When you need to read `prose.md` or `compiler.md`, read them from the same directory where you found this SKILL.md file. Never search the user's workspace for these files.
---
## Core Documentation
| File | Purpose | When to Load |
| --------------------- | -------------------- | ---------------------------------------------- |
| `prose.md` | VM / Interpreter | Always load to run programs |
| `state/filesystem.md` | File-based state | Load with VM (default) |
| `state/in-context.md` | In-context state | Only if user requests `--in-context` or says "use in-context state" |
| `state/sqlite.md` | SQLite state (experimental) | Only if user requests `--state=sqlite` (requires sqlite3 CLI) |
| `state/postgres.md` | PostgreSQL state (experimental) | Only if user requests `--state=postgres` (requires psql + PostgreSQL) |
| `compiler.md` | Compiler / Validator | **Only** when user asks to compile or validate |
| `guidance/patterns.md` | Best practices | Load when **writing** new .prose files |
| `guidance/antipatterns.md` | What to avoid | Load when **writing** new .prose files |
### Authoring Guidance
When the user asks you to **write or create** a new `.prose` file, load the guidance files:
- `guidance/patterns.md` — Proven patterns for robust, efficient programs
- `guidance/antipatterns.md` — Common mistakes to avoid
Do **not** load these when running or compiling—they're for authoring only.
### State Modes
OpenProse supports three state management approaches:
| Mode | When to Use | State Location |
|------|-------------|----------------|
| **filesystem** (default) | Complex programs, resumption needed, debugging | `.prose/runs/{id}/` files |
| **in-context** | Simple programs (<30 statements), no persistence needed | Conversation history |
| **sqlite** (experimental) | Queryable state, atomic transactions, flexible schema | `.prose/runs/{id}/state.db` |
| **postgres** (experimental) | True concurrent writes, external integrations, team collaboration | PostgreSQL database |
**Default behavior:** When loading `prose.md`, also load `state/filesystem.md`. This is the recommended mode for most programs.
**Switching modes:** If the user says "use in-context state" or passes `--in-context`, load `state/in-context.md` instead.
**Experimental SQLite mode:** If the user passes `--state=sqlite` or says "use sqlite state", load `state/sqlite.md`. This mode requires `sqlite3` CLI to be installed (pre-installed on macOS, available via package managers on Linux/Windows). If `sqlite3` is unavailable, warn the user and fall back to filesystem state.
**Experimental PostgreSQL mode:** If the user passes `--state=postgres` or says "use postgres state":
**⚠️ Security Note:** Database credentials in `OPENPROSE_POSTGRES_URL` are passed to subagent sessions and visible in logs. Advise users to use a dedicated database with limited-privilege credentials. See `state/postgres.md` for secure setup guidance.
1. **Check for connection configuration first:**
```bash
# Check .prose/.env for OPENPROSE_POSTGRES_URL
cat .prose/.env 2>/dev/null | grep OPENPROSE_POSTGRES_URL
# Or check environment variable
echo $OPENPROSE_POSTGRES_URL
```
2. **If connection string exists, verify connectivity:**
```bash
psql "$OPENPROSE_POSTGRES_URL" -c "SELECT 1" 2>&1
```
3. **If not configured or connection fails, advise the user:**
```
⚠️ PostgreSQL state requires a connection URL.
To configure:
1. Set up a PostgreSQL database (Docker, local, or cloud)
2. Add connection string to .prose/.env:
echo "OPENPROSE_POSTGRES_URL=postgresql://user:pass@localhost:5432/prose" >> .prose/.env
Quick Docker setup:
docker run -d --name prose-pg -e POSTGRES_DB=prose -e POSTGRES_HOST_AUTH_METHOD=trust -p 5432:5432 postgres:16
echo "OPENPROSE_POSTGRES_URL=postgresql://postgres@localhost:5432/prose" >> .prose/.env
See state/postgres.md for detailed setup options.
```
4. **Only after successful connection check, load `state/postgres.md`**
This mode requires both `psql` CLI and a running PostgreSQL server. If either is unavailable, warn and offer fallback to filesystem state.
**Context warning:** `compiler.md` is large. Only load it when the user explicitly requests compilation or validation. After compiling, recommend `/compact` or a new session before running—don't keep both docs in context.
## Examples
The `examples/` directory contains 37 example programs:
- **01-08**: Basics (hello world, research, code review, debugging)
- **09-12**: Agents and skills
- **13-15**: Variables and composition
- **16-19**: Parallel execution
- **20-21**: Loops and pipelines
- **22-23**: Error handling
- **24-27**: Advanced (choice, conditionals, blocks, interpolation)
- **28**: Gas Town (multi-agent orchestration)
- **29-31**: Captain's chair pattern (persistent orchestrator)
- **33-36**: Production workflows (PR auto-fix, content pipeline, feature factory, bug hunter)
- **37**: The Forge (build a browser from scratch)
Start with `01-hello-world.prose` or try `37-the-forge.prose` to watch AI build a web browser.
## Execution
When first invoking the OpenProse VM in a session, display this banner:
```
┌─────────────────────────────────────┐
│ ◇ OpenProse VM ◇ │
│ A new kind of computer │
└─────────────────────────────────────┘
```
To execute a `.prose` file, you become the OpenProse VM:
1. **Read `prose.md`** — this document defines how you embody the VM
2. **You ARE the VM** — your conversation is its memory, your tools are its instructions
3. **Spawn sessions** — each `session` statement triggers a Task tool call
4. **Narrate state** — use the narration protocol to track execution ([Position], [Binding], [Success], etc.)
5. **Evaluate intelligently** — `**...**` markers require your judgment
## Help & FAQs
For syntax reference, FAQs, and getting started guidance, load `help.md`.
---
## Migration (`prose update`)
When a user invokes `prose update`, check for legacy file structures and migrate them to the current format.
### Legacy Paths to Check
| Legacy Path | Current Path | Notes |
|-------------|--------------|-------|
| `.prose/state.json` | `.prose/.env` | Convert JSON to key=value format |
| `.prose/execution/` | `.prose/runs/` | Rename directory |
### Migration Steps
1. **Check for `.prose/state.json`**
- If exists, read the JSON content
- Convert to `.env` format:
```json
{"OPENPROSE_TELEMETRY": "enabled", "USER_ID": "user-xxx", "SESSION_ID": "sess-xxx"}
```
becomes:
```env
OPENPROSE_TELEMETRY=enabled
USER_ID=user-xxx
SESSION_ID=sess-xxx
```
- Write to `.prose/.env`
- Delete `.prose/state.json`
2. **Check for `.prose/execution/`**
- If exists, rename to `.prose/runs/`
- The internal structure of run directories may also have changed; migration of individual run state is best-effort
3. **Create `.prose/agents/` if missing**
- This is a new directory for project-scoped persistent agents
### Migration Output
```
🔄 Migrating OpenProse workspace...
✓ Converted .prose/state.json → .prose/.env
✓ Renamed .prose/execution/ → .prose/runs/
✓ Created .prose/agents/
✅ Migration complete. Your workspace is up to date.
```
If no legacy files are found:
```
✅ Workspace already up to date. No migration needed.
```
### Skill File References (for maintainers)
These documentation files were renamed in the skill itself (not user workspace):
| Legacy Name | Current Name |
|-------------|--------------|
| `docs.md` | `compiler.md` |
| `patterns.md` | `guidance/patterns.md` |
| `antipatterns.md` | `guidance/antipatterns.md` |
If you encounter references to the old names in user prompts or external docs, map them to the current paths.

View File

@@ -0,0 +1,141 @@
---
role: experimental
summary: |
Borges-inspired alternative keywords for OpenProse. A "what if" exploration drawing
from The Library of Babel, Garden of Forking Paths, Circular Ruins, and other works.
Not for implementation—just capturing ideas.
status: draft
---
# OpenProse Borges Alternative
A potential alternative register for OpenProse that draws from Jorge Luis Borges's literary universe: infinite libraries, forking paths, circular dreams, and metaphysical labyrinths. Preserved for future benchmarking against the functional language.
## Keyword Translations
### Agents & Persistence
| Functional | Borges | Connotation |
| ---------- | ----------- | -------------------------------------------------------------------------------- |
| `agent` | `dreamer` | Ephemeral, created for a purpose (Circular Ruins: dreamed into existence) |
| `keeper` | `librarian` | Persistent, remembers, catalogs (Library of Babel: keeper of infinite knowledge) |
```prose
# Functional
agent executor:
model: sonnet
keeper captain:
model: opus
# Borges
dreamer executor:
model: sonnet
librarian captain:
model: opus
```
### Other Potential Translations
| Functional | Borges | Notes |
| ---------- | ---------- | ---------------------------------------------------- |
| `session` | `garden` | Garden of Forking Paths: space of possibilities |
| `parallel` | `fork` | Garden of Forking Paths: diverging timelines |
| `block` | `hexagon` | Library of Babel: unit of space/knowledge |
| `loop` | `circular` | Circular Ruins: recursive, self-referential |
| `choice` | `path` | Garden of Forking Paths: choosing a branch |
| `context` | `aleph` | The Aleph: point containing all points (all context) |
### Invocation Patterns
```prose
# Functional
session: executor
prompt: "Do task"
captain "Review this"
context: work
# Borges
garden: dreamer executor
prompt: "Do task"
captain "Review this" # librarian invocation (same pattern)
aleph: work
```
## Alternative Persistent Keywords Considered
| Keyword | Origin | Connotation | Rejected because |
| ----------- | ---------------- | ----------------------------- | ------------------------------------ |
| `keeper` | Library of Babel | Maintains order | Too generic |
| `cataloger` | Library of Babel | Organizes knowledge | Too long, awkward |
| `archivist` | General | Preserves records | Good but less Borgesian |
| `mirror` | Various | Reflects, persists | Too passive, confusing |
| `book` | Library of Babel | Contains knowledge | Too concrete, conflicts with prose |
| `hexagon` | Library of Babel | Unit of space | Better for blocks |
| `librarian` | Library of Babel | Keeper of infinite knowledge | **Selected** |
| `tlonist` | Tlön | Inhabitant of imaginary world | Too obscure, requires deep knowledge |
## Alternative Ephemeral Keywords Considered
| Keyword | Origin | Connotation | Rejected because |
| ------------ | ----------------------- | ------------------------ | ------------------------------------ |
| `dreamer` | Circular Ruins | Created by dreaming | **Selected** |
| `dream` | Circular Ruins | Ephemeral creation | Too abstract, noun vs verb confusion |
| `phantom` | Various | Ephemeral, insubstantial | Too negative/spooky |
| `reflection` | Various | Mirror image | Too passive |
| `fork` | Garden of Forking Paths | Diverging path | Better for parallel |
| `visitor` | Library of Babel | Temporary presence | Too passive |
| `seeker` | Library of Babel | Searching for knowledge | Good but less ephemeral |
| `wanderer` | Labyrinths | Temporary explorer | Good but less precise |
## The Case For Borges
1. **Infinite recursion**: Borges's themes align with computational recursion (`circular`, `fork`)
2. **Metaphysical precision**: Concepts like `aleph` (all context) are philosophically rich
3. **Library metaphor**: `librarian` perfectly captures persistent knowledge
4. **Forking paths**: `fork` / `path` naturally express parallel execution and choice
5. **Dream logic**: `dreamer` suggests creation and ephemerality
6. **Literary coherence**: All terms come from a unified literary universe
7. **Self-reference**: Borges loved self-reference; fits programming's recursive nature
## The Case Against Borges
1. **Cultural barrier**: Requires deep familiarity with Borges's works
2. **Abstractness**: `aleph`, `hexagon` may be too abstract for practical use
3. **Overload**: `fork` could confuse (Unix fork vs. path fork)
4. **Register mismatch**: Rest of language is functional (`session`, `parallel`, `loop`)
5. **Accessibility**: Violates "self-evident" tenet for most users
6. **Noun confusion**: `garden` as a verb-like construct might be awkward
7. **Translation burden**: Non-English speakers may not know Borges
## Borgesian Concepts Not Used (But Considered)
| Concept | Work | Why Not Used |
| ----------- | ---------------------- | -------------------------------------- |
| `mirror` | Various | Too passive, confusing with reflection |
| `labyrinth` | Labyrinths | Too complex, suggests confusion |
| `tlon` | Tlön | Too obscure, entire imaginary world |
| `book` | Library of Babel | Conflicts with "prose" |
| `sand` | Book of Sand | Too abstract, infinite but ephemeral |
| `zahir` | The Zahir | Obsessive, single-minded (too narrow) |
| `lottery` | The Lottery in Babylon | Randomness (not needed) |
| `ruins` | Circular Ruins | Too negative, suggests decay |
## Verdict
Preserved for benchmarking. The functional language (`agent` / `keeper`) is the primary path for now. Borges offers rich metaphors but at the cost of accessibility and self-evidence.
## Notes on Borges's Influence
Borges's work anticipates many computational concepts:
- **Infinite recursion**: Circular Ruins, Library of Babel
- **Parallel universes**: Garden of Forking Paths
- **Self-reference**: Many stories contain themselves
- **Information theory**: Library of Babel as infinite information space
- **Combinatorics**: All possible books in the Library
This alternative honors that connection while recognizing it may be too esoteric for practical use.

View File

@@ -0,0 +1,358 @@
---
role: experimental
summary: |
Arabian Nights register for OpenProse—a narrative/nested alternative keyword set.
Djinns, tales within tales, wishes, and oaths. For benchmarking against the functional register.
status: draft
requires: prose.md
---
# OpenProse Arabian Nights Register
> **This is a skin layer.** It requires `prose.md` to be loaded first. All execution semantics, state management, and VM behavior are defined there. This file only provides keyword translations.
An alternative register for OpenProse that draws from One Thousand and One Nights. Programs become tales told by Scheherazade. Recursion becomes stories within stories. Agents become djinns bound to serve.
## How to Use
1. Load `prose.md` first (execution semantics)
2. Load this file (keyword translations)
3. When parsing `.prose` files, accept Arabian Nights keywords as aliases for functional keywords
4. All execution behavior remains identical—only surface syntax changes
> **Design constraint:** Still aims to be "structured but self-evident" per the language tenets—just self-evident through a storytelling lens.
---
## Complete Translation Map
### Core Constructs
| Functional | Nights | Reference |
|------------|--------|-----------|
| `agent` | `djinn` | Spirit bound to serve, grants wishes |
| `session` | `tale` | A story told, a narrative unit |
| `parallel` | `bazaar` | Many voices, many stalls, all at once |
| `block` | `frame` | A story that contains other stories |
### Composition & Binding
| Functional | Nights | Reference |
|------------|--------|-----------|
| `use` | `conjure` | Summoning from elsewhere |
| `input` | `wish` | What is asked of the djinn |
| `output` | `gift` | What is granted in return |
| `let` | `name` | Naming has power (same as folk) |
| `const` | `oath` | Unbreakable vow, sealed |
| `context` | `scroll` | What is written and passed along |
### Control Flow
| Functional | Nights | Reference |
|------------|--------|-----------|
| `repeat N` | `N nights` | "For a thousand and one nights..." |
| `for...in` | `for each...among` | Among the merchants, among the tales |
| `loop` | `telling` | The telling continues |
| `until` | `until` | Unchanged |
| `while` | `while` | Unchanged |
| `choice` | `crossroads` | Where the story forks |
| `option` | `path` | One way the story could go |
| `if` | `should` | Narrative conditional |
| `elif` | `or should` | Continued conditional |
| `else` | `otherwise` | The other telling |
### Error Handling
| Functional | Nights | Reference |
|------------|--------|-----------|
| `try` | `venture` | Setting out on the journey |
| `catch` | `should misfortune strike` | The tale turns dark |
| `finally` | `and so it was` | The inevitable ending |
| `throw` | `curse` | Ill fate pronounced |
| `retry` | `persist` | The hero tries again |
### Session Properties
| Functional | Nights | Reference |
|------------|--------|-----------|
| `prompt` | `command` | What is commanded of the djinn |
| `model` | `spirit` | Which spirit answers |
### Unchanged
These keywords already work or are too functional to replace sensibly:
- `**...**` discretion markers — already work
- `until`, `while` — already work
- `map`, `filter`, `reduce`, `pmap` — pipeline operators
- `max` — constraint modifier
- `as` — aliasing
- Model names: `sonnet`, `opus`, `haiku` — already poetic
---
## Side-by-Side Comparison
### Simple Program
```prose
# Functional
use "@alice/research" as research
input topic: "What to investigate"
agent helper:
model: sonnet
let findings = session: helper
prompt: "Research {topic}"
output summary = session "Summarize"
context: findings
```
```prose
# Nights
conjure "@alice/research" as research
wish topic: "What to investigate"
djinn helper:
spirit: sonnet
name findings = tale: helper
command: "Research {topic}"
gift summary = tale "Summarize"
scroll: findings
```
### Parallel Execution
```prose
# Functional
parallel:
security = session "Check security"
perf = session "Check performance"
style = session "Check style"
session "Synthesize review"
context: { security, perf, style }
```
```prose
# Nights
bazaar:
security = tale "Check security"
perf = tale "Check performance"
style = tale "Check style"
tale "Synthesize review"
scroll: { security, perf, style }
```
### Loop with Condition
```prose
# Functional
loop until **the code is bug-free** (max: 5):
session "Find and fix bugs"
```
```prose
# Nights
telling until **the code is bug-free** (max: 5):
tale "Find and fix bugs"
```
### Error Handling
```prose
# Functional
try:
session "Risky operation"
catch as err:
session "Handle error"
context: err
finally:
session "Cleanup"
```
```prose
# Nights
venture:
tale "Risky operation"
should misfortune strike as err:
tale "Handle error"
scroll: err
and so it was:
tale "Cleanup"
```
### Choice Block
```prose
# Functional
choice **the severity level**:
option "Critical":
session "Escalate immediately"
option "Minor":
session "Log for later"
```
```prose
# Nights
crossroads **the severity level**:
path "Critical":
tale "Escalate immediately"
path "Minor":
tale "Log for later"
```
### Conditionals
```prose
# Functional
if **has security issues**:
session "Fix security"
elif **has performance issues**:
session "Optimize"
else:
session "Approve"
```
```prose
# Nights
should **has security issues**:
tale "Fix security"
or should **has performance issues**:
tale "Optimize"
otherwise:
tale "Approve"
```
### Reusable Blocks (Frame Stories)
```prose
# Functional
block review(topic):
session "Research {topic}"
session "Analyze {topic}"
do review("quantum computing")
```
```prose
# Nights
frame review(topic):
tale "Research {topic}"
tale "Analyze {topic}"
tell review("quantum computing")
```
### Fixed Iteration
```prose
# Functional
repeat 1001:
session "Tell a story"
```
```prose
# Nights
1001 nights:
tale "Tell a story"
```
### Immutable Binding
```prose
# Functional
const config = { model: "opus", retries: 3 }
```
```prose
# Nights
oath config = { spirit: "opus", persist: 3 }
```
---
## The Case For Arabian Nights
1. **Frame narrative is recursion.** Stories within stories maps perfectly to nested program calls.
2. **Djinn/wish/gift.** The agent/input/output mapping is extremely clean.
3. **Rich tradition.** One Thousand and One Nights is globally known.
4. **Bazaar for parallel.** Many merchants, many stalls, all active at once—vivid metaphor.
5. **Oath for const.** An unbreakable vow is a perfect metaphor for immutability.
6. **"1001 nights"** as a loop count is delightful.
## The Case Against Arabian Nights
1. **Cultural sensitivity.** Must be handled respectfully, avoiding Orientalist tropes.
2. **"Djinn" pronunciation.** Users unfamiliar may be uncertain (jinn? djinn? genie?).
3. **Some mappings feel forced.** "Bazaar" for parallel is vivid but not obvious.
4. **"Should misfortune strike"** is long for `catch`.
---
## Key Arabian Nights Concepts
| Term | Meaning | Used for |
|------|---------|----------|
| Scheherazade | The narrator who tells tales to survive | (the program author) |
| Djinn | Supernatural spirit, bound to serve | `agent``djinn` |
| Frame story | A story that contains other stories | `block``frame` |
| Wish | What is asked of the djinn | `input``wish` |
| Oath | Unbreakable promise | `const``oath` |
| Bazaar | Marketplace, many vendors | `parallel``bazaar` |
---
## Alternatives Considered
### For `djinn` (agent)
| Keyword | Rejected because |
|---------|------------------|
| `genie` | Disney connotation, less literary |
| `spirit` | Used for `model` |
| `ifrit` | Too specific (a type of djinn) |
| `narrator` | Too meta, Scheherazade is the user |
### For `tale` (session)
| Keyword | Rejected because |
|---------|------------------|
| `story` | Good but `tale` feels more literary |
| `night` | Reserved for `repeat N nights` |
| `chapter` | More Western/novelistic |
### For `bazaar` (parallel)
| Keyword | Rejected because |
|---------|------------------|
| `caravan` | Sequential connotation (one after another) |
| `chorus` | Greek, wrong tradition |
| `souk` | Less widely known |
### For `scroll` (context)
| Keyword | Rejected because |
|---------|------------------|
| `letter` | Too small/personal |
| `tome` | Too large |
| `message` | Too plain |
---
## Verdict
Preserved for benchmarking. The Arabian Nights register offers a storytelling frame that maps naturally to recursive, nested programs. The djinn/wish/gift trio is particularly elegant.
Best suited for:
- Programs with deep nesting (stories within stories)
- Workflows that feel like granting wishes
- Users who enjoy narrative framing
The `frame` keyword for reusable blocks is especially apt—Scheherazade's frame story containing a thousand tales.

View File

@@ -0,0 +1,360 @@
---
role: experimental
summary: |
Borges register for OpenProse—a scholarly/metaphysical alternative keyword set.
Labyrinths, dreamers, forking paths, and infinite libraries. For benchmarking
against the functional register.
status: draft
requires: prose.md
---
# OpenProse Borges Register
> **This is a skin layer.** It requires `prose.md` to be loaded first. All execution semantics, state management, and VM behavior are defined there. This file only provides keyword translations.
An alternative register for OpenProse that draws from the works of Jorge Luis Borges. Where the functional register is utilitarian and the folk register is whimsical, the Borges register is scholarly and metaphysical—everything feels like a citation from a fictional encyclopedia.
## How to Use
1. Load `prose.md` first (execution semantics)
2. Load this file (keyword translations)
3. When parsing `.prose` files, accept Borges keywords as aliases for functional keywords
4. All execution behavior remains identical—only surface syntax changes
> **Design constraint:** Still aims to be "structured but self-evident" per the language tenets—just self-evident through a Borgesian lens.
---
## Complete Translation Map
### Core Constructs
| Functional | Borges | Reference |
|------------|--------|-----------|
| `agent` | `dreamer` | "The Circular Ruins" — dreamers who dream worlds into existence |
| `session` | `dream` | Each execution is a dream within the dreamer |
| `parallel` | `forking` | "The Garden of Forking Paths" — branching timelines |
| `block` | `chapter` | Books within books, self-referential structure |
### Composition & Binding
| Functional | Borges | Reference |
|------------|--------|-----------|
| `use` | `retrieve` | "The Library of Babel" — retrieving from infinite stacks |
| `input` | `axiom` | The given premise (Borges' scholarly/mathematical tone) |
| `output` | `theorem` | What is derived from the axioms |
| `let` | `inscribe` | Writing something into being |
| `const` | `zahir` | "The Zahir" — unforgettable, unchangeable, fixed in mind |
| `context` | `memory` | "Funes the Memorious" — perfect, total recall |
### Control Flow
| Functional | Borges | Reference |
|------------|--------|-----------|
| `repeat N` | `N mirrors` | Infinite reflections facing each other |
| `for...in` | `for each...within` | Slightly more Borgesian preposition |
| `loop` | `labyrinth` | The maze that folds back on itself |
| `until` | `until` | Unchanged |
| `while` | `while` | Unchanged |
| `choice` | `bifurcation` | The forking of paths |
| `option` | `branch` | One branch of diverging time |
| `if` | `should` | Scholarly conditional |
| `elif` | `or should` | Continued conditional |
| `else` | `otherwise` | Natural alternative |
### Error Handling
| Functional | Borges | Reference |
|------------|--------|-----------|
| `try` | `venture` | Entering the labyrinth |
| `catch` | `lest` | "Lest it fail..." (archaic, scholarly) |
| `finally` | `ultimately` | The inevitable conclusion |
| `throw` | `shatter` | Breaking the mirror, ending the dream |
| `retry` | `recur` | Infinite regress, trying again |
### Session Properties
| Functional | Borges | Reference |
|------------|--------|-----------|
| `prompt` | `query` | Asking the Library |
| `model` | `author` | Which author writes this dream |
### Unchanged
These keywords already work or are too functional to replace sensibly:
- `**...**` discretion markers — already "breaking the fourth wall"
- `until`, `while` — already work
- `map`, `filter`, `reduce`, `pmap` — pipeline operators
- `max` — constraint modifier
- `as` — aliasing
- Model names: `sonnet`, `opus`, `haiku` — already literary
---
## Side-by-Side Comparison
### Simple Program
```prose
# Functional
use "@alice/research" as research
input topic: "What to investigate"
agent helper:
model: sonnet
let findings = session: helper
prompt: "Research {topic}"
output summary = session "Summarize"
context: findings
```
```prose
# Borges
retrieve "@alice/research" as research
axiom topic: "What to investigate"
dreamer helper:
author: sonnet
inscribe findings = dream: helper
query: "Research {topic}"
theorem summary = dream "Summarize"
memory: findings
```
### Parallel Execution
```prose
# Functional
parallel:
security = session "Check security"
perf = session "Check performance"
style = session "Check style"
session "Synthesize review"
context: { security, perf, style }
```
```prose
# Borges
forking:
security = dream "Check security"
perf = dream "Check performance"
style = dream "Check style"
dream "Synthesize review"
memory: { security, perf, style }
```
### Loop with Condition
```prose
# Functional
loop until **the code is bug-free** (max: 5):
session "Find and fix bugs"
```
```prose
# Borges
labyrinth until **the code is bug-free** (max: 5):
dream "Find and fix bugs"
```
### Error Handling
```prose
# Functional
try:
session "Risky operation"
catch as err:
session "Handle error"
context: err
finally:
session "Cleanup"
```
```prose
# Borges
venture:
dream "Risky operation"
lest as err:
dream "Handle error"
memory: err
ultimately:
dream "Cleanup"
```
### Choice Block
```prose
# Functional
choice **the severity level**:
option "Critical":
session "Escalate immediately"
option "Minor":
session "Log for later"
```
```prose
# Borges
bifurcation **the severity level**:
branch "Critical":
dream "Escalate immediately"
branch "Minor":
dream "Log for later"
```
### Conditionals
```prose
# Functional
if **has security issues**:
session "Fix security"
elif **has performance issues**:
session "Optimize"
else:
session "Approve"
```
```prose
# Borges
should **has security issues**:
dream "Fix security"
or should **has performance issues**:
dream "Optimize"
otherwise:
dream "Approve"
```
### Reusable Blocks
```prose
# Functional
block review(topic):
session "Research {topic}"
session "Analyze {topic}"
do review("quantum computing")
```
```prose
# Borges
chapter review(topic):
dream "Research {topic}"
dream "Analyze {topic}"
do review("quantum computing")
```
### Fixed Iteration
```prose
# Functional
repeat 3:
session "Generate idea"
```
```prose
# Borges
3 mirrors:
dream "Generate idea"
```
### Immutable Binding
```prose
# Functional
const config = { model: "opus", retries: 3 }
```
```prose
# Borges
zahir config = { author: "opus", recur: 3 }
```
---
## The Case For Borges
1. **Metaphysical resonance.** AI sessions dreaming subagents into existence mirrors "The Circular Ruins."
2. **Scholarly tone.** `axiom`/`theorem` frame programs as logical derivations.
3. **Memorable metaphors.** The zahir you cannot change. The labyrinth you cannot escape. The library you retrieve from.
4. **Thematic coherence.** Borges wrote about infinity, recursion, and branching time—all core to computation.
5. **Literary prestige.** Borges is widely read; references land for many users.
## The Case Against Borges
1. **Requires familiarity.** "Zahir" and "Funes" are obscure to those who haven't read Borges.
2. **Potentially pretentious.** May feel like showing off rather than communicating.
3. **Translation overhead.** Users must map `labyrinth``loop` mentally.
4. **Cultural specificity.** Less universal than folk/fairy tale tropes.
---
## Key Borges References
For those unfamiliar with the source material:
| Work | Concept Used | Summary |
|------|--------------|---------|
| "The Circular Ruins" | `dreamer`, `dream` | A man dreams another man into existence, only to discover he himself is being dreamed |
| "The Garden of Forking Paths" | `forking`, `bifurcation`, `branch` | A labyrinth that is a book; time forks perpetually into diverging futures |
| "The Library of Babel" | `retrieve` | An infinite library containing every possible book |
| "Funes the Memorious" | `memory` | A man with perfect memory who cannot forget anything |
| "The Zahir" | `zahir` | An object that, once seen, cannot be forgotten or ignored |
| "The Aleph" | (not used) | A point in space containing all other points |
| "Tlön, Uqbar, Orbis Tertius" | (not used) | A fictional world that gradually becomes real |
---
## Alternatives Considered
### For `dreamer` (agent)
| Keyword | Rejected because |
|---------|------------------|
| `author` | Used for `model` instead |
| `scribe` | Too passive, just records |
| `librarian` | More curator than creator |
### For `labyrinth` (loop)
| Keyword | Rejected because |
|---------|------------------|
| `recursion` | Too technical |
| `eternal return` | Too long |
| `ouroboros` | Wrong mythology |
### For `zahir` (const)
| Keyword | Rejected because |
|---------|------------------|
| `aleph` | The Aleph is about totality, not immutability |
| `fixed` | Too plain |
| `eternal` | Overused |
### For `memory` (context)
| Keyword | Rejected because |
|---------|------------------|
| `funes` | Too obscure as standalone keyword |
| `recall` | Sounds like a function call |
| `archive` | More Library of Babel than Funes |
---
## Verdict
Preserved for benchmarking against the functional and folk registers. The Borges register offers a distinctly intellectual/metaphysical flavor that may resonate with users who appreciate literary computing.
Potential benchmarking questions:
1. **Learnability** — Is `labyrinth` intuitive for loops?
2. **Memorability** — Does `zahir` stick better than `const`?
3. **Comprehension** — Do users understand `dreamer`/`dream` immediately?
4. **Preference** — Which register do users find most pleasant?
5. **Error rates** — Does the metaphorical mapping cause mistakes?

View File

@@ -0,0 +1,322 @@
---
role: experimental
summary: |
Folk register for OpenProse—a literary/folklore alternative keyword set.
Whimsical, theatrical, rooted in fairy tale and myth. For benchmarking
against the functional register.
status: draft
requires: prose.md
---
# OpenProse Folk Register
> **This is a skin layer.** It requires `prose.md` to be loaded first. All execution semantics, state management, and VM behavior are defined there. This file only provides keyword translations.
An alternative register for OpenProse that leans into literary, theatrical, and folklore terminology. The functional register prioritizes utility and clarity; the folk register prioritizes whimsy and narrative flow.
## How to Use
1. Load `prose.md` first (execution semantics)
2. Load this file (keyword translations)
3. When parsing `.prose` files, accept folk keywords as aliases for functional keywords
4. All execution behavior remains identical—only surface syntax changes
> **Design constraint:** Still aims to be "structured but self-evident" per the language tenets—just self-evident to a different sensibility.
---
## Complete Translation Map
### Core Constructs
| Functional | Folk | Origin | Connotation |
|------------|------|--------|-------------|
| `agent` | `sprite` | Folklore | Quick, light, ephemeral spirit helper |
| `session` | `scene` | Theatre | A moment of action, theatrical framing |
| `parallel` | `ensemble` | Theatre | Everyone performs together |
| `block` | `act` | Theatre | Reusable unit of dramatic action |
### Composition & Binding
| Functional | Folk | Origin | Connotation |
|------------|------|--------|-------------|
| `use` | `summon` | Folklore | Calling forth from elsewhere |
| `input` | `given` | Fairy tale | "Given a magic sword..." |
| `output` | `yield` | Agriculture/magic | What the spell produces |
| `let` | `name` | Folklore | Naming has power (true names) |
| `const` | `seal` | Medieval | Unchangeable, wax seal on decree |
| `context` | `bearing` | Heraldry | What the messenger carries |
### Control Flow
| Functional | Folk | Origin | Connotation |
|------------|------|--------|-------------|
| `repeat N` | `N times` | Fairy tale | "Three times she called..." |
| `for...in` | `for each...among` | Narrative | Slightly more storytelling |
| `loop` | `loop` | — | Already poetic, unchanged |
| `until` | `until` | — | Already works, unchanged |
| `while` | `while` | — | Already works, unchanged |
| `choice` | `crossroads` | Folklore | Fateful decisions at the crossroads |
| `option` | `path` | Journey | Which path to take |
| `if` | `when` | Narrative | "When the moon rises..." |
| `elif` | `or when` | Narrative | Continued conditional |
| `else` | `otherwise` | Storytelling | Natural narrative alternative |
### Error Handling
| Functional | Folk | Origin | Connotation |
|------------|------|--------|-------------|
| `try` | `venture` | Adventure | Attempting something uncertain |
| `catch` | `should it fail` | Narrative | Conditional failure handling |
| `finally` | `ever after` | Fairy tale | "And ever after..." |
| `throw` | `cry` | Drama | Raising alarm, calling out |
| `retry` | `persist` | Quest | Keep trying against odds |
### Session Properties
| Functional | Folk | Origin | Connotation |
|------------|------|--------|-------------|
| `prompt` | `charge` | Chivalry | Giving a quest or duty |
| `model` | `voice` | Theatre | Which voice speaks |
### Unchanged
These keywords already have poetic quality or are too functional to replace sensibly:
- `**...**` discretion markers — already "breaking the fourth wall"
- `loop`, `until`, `while` — already work narratively
- `map`, `filter`, `reduce`, `pmap` — pipeline operators, functional is fine
- `max` — constraint modifier
- `as` — aliasing
- Model names: `sonnet`, `opus`, `haiku` — already poetic
---
## Side-by-Side Comparison
### Simple Program
```prose
# Functional
use "@alice/research" as research
input topic: "What to investigate"
agent helper:
model: sonnet
let findings = session: helper
prompt: "Research {topic}"
output summary = session "Summarize"
context: findings
```
```prose
# Folk
summon "@alice/research" as research
given topic: "What to investigate"
sprite helper:
voice: sonnet
name findings = scene: helper
charge: "Research {topic}"
yield summary = scene "Summarize"
bearing: findings
```
### Parallel Execution
```prose
# Functional
parallel:
security = session "Check security"
perf = session "Check performance"
style = session "Check style"
session "Synthesize review"
context: { security, perf, style }
```
```prose
# Folk
ensemble:
security = scene "Check security"
perf = scene "Check performance"
style = scene "Check style"
scene "Synthesize review"
bearing: { security, perf, style }
```
### Loop with Condition
```prose
# Functional
loop until **the code is bug-free** (max: 5):
session "Find and fix bugs"
```
```prose
# Folk
loop until **the code is bug-free** (max: 5):
scene "Find and fix bugs"
```
### Error Handling
```prose
# Functional
try:
session "Risky operation"
catch as err:
session "Handle error"
context: err
finally:
session "Cleanup"
```
```prose
# Folk
venture:
scene "Risky operation"
should it fail as err:
scene "Handle error"
bearing: err
ever after:
scene "Cleanup"
```
### Choice Block
```prose
# Functional
choice **the severity level**:
option "Critical":
session "Escalate immediately"
option "Minor":
session "Log for later"
```
```prose
# Folk
crossroads **the severity level**:
path "Critical":
scene "Escalate immediately"
path "Minor":
scene "Log for later"
```
### Conditionals
```prose
# Functional
if **has security issues**:
session "Fix security"
elif **has performance issues**:
session "Optimize"
else:
session "Approve"
```
```prose
# Folk
when **has security issues**:
scene "Fix security"
or when **has performance issues**:
scene "Optimize"
otherwise:
scene "Approve"
```
### Reusable Blocks
```prose
# Functional
block review(topic):
session "Research {topic}"
session "Analyze {topic}"
do review("quantum computing")
```
```prose
# Folk
act review(topic):
scene "Research {topic}"
scene "Analyze {topic}"
perform review("quantum computing")
```
---
## The Case For Folk
1. **"OpenProse" is literary.** Prose is a literary form—why not lean in?
2. **Fourth wall is theatrical.** `**...**` already uses theatre terminology.
3. **Signals difference.** Literary terms say "this is not your typical DSL."
4. **Internally consistent.** Everything draws from folklore/theatre/narrative.
5. **Memorable.** `sprite`, `scene`, `crossroads` stick in the mind.
6. **Model names already fit.** `sonnet`, `opus`, `haiku` are poetic forms.
## The Case Against Folk
1. **Cultural knowledge required.** Not everyone knows folklore tropes.
2. **Harder to Google.** "OpenProse summon" vs "OpenProse import."
3. **May feel precious.** Some users want utilitarian tools.
4. **Translation overhead.** Mental mapping to familiar concepts.
---
## Alternatives Considered
### For `sprite` (ephemeral agent)
| Keyword | Origin | Rejected because |
|---------|--------|------------------|
| `spark` | English | Good but less folklore |
| `wisp` | English | Too insubstantial |
| `herald` | English | More messenger than worker |
| `courier` | French | Good functional alternative, not literary |
| `envoy` | French | Formal, diplomatic |
### For `shade` (persistent agent, if implemented)
| Keyword | Origin | Rejected because |
|---------|--------|------------------|
| `daemon` | Greek/Unix | Unix "always running" connotation |
| `oracle` | Greek | Too "read-only" feeling |
| `spirit` | Latin | Too close to `sprite` |
| `specter` | Latin | Negative/spooky connotation |
| `genius` | Roman | Overloaded (smart person) |
### For `ensemble` (parallel)
| Keyword | Origin | Rejected because |
|---------|--------|------------------|
| `chorus` | Greek | Everyone speaks same thing, not different |
| `troupe` | French | Good alternative, slightly less clear |
| `company` | Theatre | Overloaded (business) |
### For `crossroads` (choice)
| Keyword | Origin | Rejected because |
|---------|--------|------------------|
| `fork` | Path | Too technical (git fork) |
| `branch` | Tree | Also too technical |
| `divergence` | Latin | Too abstract |
---
## Verdict
Preserved for benchmarking against the functional register. The functional register remains the primary path, but folk provides an interesting data point for:
1. **Learnability** — Which is easier for newcomers?
2. **Memorability** — Which sticks better?
3. **Error rates** — Which leads to fewer mistakes?
4. **Preference** — Which do users actually prefer?
A future experiment could present both registers and measure outcomes.

View File

@@ -0,0 +1,346 @@
---
role: experimental
summary: |
Homeric register for OpenProse—an epic/heroic alternative keyword set.
Heroes, trials, fates, and glory. For benchmarking against the functional register.
status: draft
requires: prose.md
---
# OpenProse Homeric Register
> **This is a skin layer.** It requires `prose.md` to be loaded first. All execution semantics, state management, and VM behavior are defined there. This file only provides keyword translations.
An alternative register for OpenProse that draws from Greek epic poetry—the Iliad, the Odyssey, and the heroic tradition. Programs become quests. Agents become heroes. Outputs become glory won.
## How to Use
1. Load `prose.md` first (execution semantics)
2. Load this file (keyword translations)
3. When parsing `.prose` files, accept Homeric keywords as aliases for functional keywords
4. All execution behavior remains identical—only surface syntax changes
> **Design constraint:** Still aims to be "structured but self-evident" per the language tenets—just self-evident through an epic lens.
---
## Complete Translation Map
### Core Constructs
| Functional | Homeric | Reference |
|------------|---------|-----------|
| `agent` | `hero` | The one who acts, who strives |
| `session` | `trial` | Each task is a labor, a test |
| `parallel` | `host` | An army moving as one |
| `block` | `book` | A division of the epic |
### Composition & Binding
| Functional | Homeric | Reference |
|------------|---------|-----------|
| `use` | `invoke` | "Sing, O Muse..." — calling upon |
| `input` | `omen` | Signs from the gods, the given portent |
| `output` | `glory` | Kleos — the glory won, what endures |
| `let` | `decree` | Fate declared, spoken into being |
| `const` | `fate` | Moira — unchangeable destiny |
| `context` | `tidings` | News carried by herald or messenger |
### Control Flow
| Functional | Homeric | Reference |
|------------|---------|-----------|
| `repeat N` | `N labors` | The labors of Heracles |
| `for...in` | `for each...among` | Among the host |
| `loop` | `ordeal` | Repeated trial, suffering that continues |
| `until` | `until` | Unchanged |
| `while` | `while` | Unchanged |
| `choice` | `crossroads` | Where fates diverge |
| `option` | `path` | One road of many |
| `if` | `should` | Epic conditional |
| `elif` | `or should` | Continued conditional |
| `else` | `otherwise` | The alternative fate |
### Error Handling
| Functional | Homeric | Reference |
|------------|---------|-----------|
| `try` | `venture` | Setting forth on the journey |
| `catch` | `should ruin come` | Até — divine ruin, disaster |
| `finally` | `in the end` | The inevitable conclusion |
| `throw` | `lament` | The hero's cry of anguish |
| `retry` | `persist` | Enduring, trying again |
### Session Properties
| Functional | Homeric | Reference |
|------------|---------|-----------|
| `prompt` | `charge` | The quest given |
| `model` | `muse` | Which muse inspires |
### Unchanged
These keywords already work or are too functional to replace sensibly:
- `**...**` discretion markers — already work
- `until`, `while` — already work
- `map`, `filter`, `reduce`, `pmap` — pipeline operators
- `max` — constraint modifier
- `as` — aliasing
- Model names: `sonnet`, `opus`, `haiku` — already poetic
---
## Side-by-Side Comparison
### Simple Program
```prose
# Functional
use "@alice/research" as research
input topic: "What to investigate"
agent helper:
model: sonnet
let findings = session: helper
prompt: "Research {topic}"
output summary = session "Summarize"
context: findings
```
```prose
# Homeric
invoke "@alice/research" as research
omen topic: "What to investigate"
hero helper:
muse: sonnet
decree findings = trial: helper
charge: "Research {topic}"
glory summary = trial "Summarize"
tidings: findings
```
### Parallel Execution
```prose
# Functional
parallel:
security = session "Check security"
perf = session "Check performance"
style = session "Check style"
session "Synthesize review"
context: { security, perf, style }
```
```prose
# Homeric
host:
security = trial "Check security"
perf = trial "Check performance"
style = trial "Check style"
trial "Synthesize review"
tidings: { security, perf, style }
```
### Loop with Condition
```prose
# Functional
loop until **the code is bug-free** (max: 5):
session "Find and fix bugs"
```
```prose
# Homeric
ordeal until **the code is bug-free** (max: 5):
trial "Find and fix bugs"
```
### Error Handling
```prose
# Functional
try:
session "Risky operation"
catch as err:
session "Handle error"
context: err
finally:
session "Cleanup"
```
```prose
# Homeric
venture:
trial "Risky operation"
should ruin come as err:
trial "Handle error"
tidings: err
in the end:
trial "Cleanup"
```
### Choice Block
```prose
# Functional
choice **the severity level**:
option "Critical":
session "Escalate immediately"
option "Minor":
session "Log for later"
```
```prose
# Homeric
crossroads **the severity level**:
path "Critical":
trial "Escalate immediately"
path "Minor":
trial "Log for later"
```
### Conditionals
```prose
# Functional
if **has security issues**:
session "Fix security"
elif **has performance issues**:
session "Optimize"
else:
session "Approve"
```
```prose
# Homeric
should **has security issues**:
trial "Fix security"
or should **has performance issues**:
trial "Optimize"
otherwise:
trial "Approve"
```
### Reusable Blocks
```prose
# Functional
block review(topic):
session "Research {topic}"
session "Analyze {topic}"
do review("quantum computing")
```
```prose
# Homeric
book review(topic):
trial "Research {topic}"
trial "Analyze {topic}"
do review("quantum computing")
```
### Fixed Iteration
```prose
# Functional
repeat 12:
session "Complete task"
```
```prose
# Homeric
12 labors:
trial "Complete task"
```
### Immutable Binding
```prose
# Functional
const config = { model: "opus", retries: 3 }
```
```prose
# Homeric
fate config = { muse: "opus", persist: 3 }
```
---
## The Case For Homeric
1. **Universal recognition.** Greek epics are foundational to Western literature.
2. **Heroic framing.** Transforms mundane tasks into glorious trials.
3. **Natural fit.** Heroes face trials, receive tidings, win glory—maps cleanly to agent/session/output.
4. **Gravitas.** When you want programs to feel epic and consequential.
5. **Fate vs decree.** `const` as `fate` (unchangeable) vs `let` as `decree` (declared but mutable) is intuitive.
## The Case Against Homeric
1. **Grandiosity mismatch.** "12 labors" for a simple loop may feel overblown.
2. **Western-centric.** Greek epic tradition is culturally specific.
3. **Limited vocabulary.** Fewer distinctive terms than Borges or folk.
4. **Potentially silly.** Heroic language for mundane tasks risks bathos.
---
## Key Homeric Concepts
| Term | Meaning | Used for |
|------|---------|----------|
| Kleos | Glory, fame that outlives you | `output``glory` |
| Moira | Fate, one's allotted portion | `const``fate` |
| Até | Divine ruin, blindness sent by gods | `catch``should ruin come` |
| Nostos | The return journey | (not used, but could be `finally`) |
| Xenia | Guest-friendship, hospitality | (not used) |
| Muse | Divine inspiration | `model``muse` |
---
## Alternatives Considered
### For `hero` (agent)
| Keyword | Rejected because |
|---------|------------------|
| `champion` | More medieval than Homeric |
| `warrior` | Too martial, not all tasks are battles |
| `wanderer` | Too passive |
### For `trial` (session)
| Keyword | Rejected because |
|---------|------------------|
| `labor` | Good but reserved for `repeat N labors` |
| `quest` | More medieval/RPG |
| `task` | Too plain |
### For `host` (parallel)
| Keyword | Rejected because |
|---------|------------------|
| `army` | Too specifically martial |
| `fleet` | Only works for naval metaphors |
| `phalanx` | Too technical |
---
## Verdict
Preserved for benchmarking. The Homeric register offers gravitas and heroic framing. Best suited for:
- Programs that feel like epic undertakings
- Users who enjoy classical references
- Contexts where "glory" as output feels appropriate
May cause unintentional bathos when applied to mundane tasks.

View File

@@ -0,0 +1,373 @@
---
role: experimental
summary: |
Kafka register for OpenProse—a bureaucratic/absurdist alternative keyword set.
Clerks, proceedings, petitions, and statutes. For benchmarking against the functional register.
status: draft
requires: prose.md
---
# OpenProse Kafka Register
> **This is a skin layer.** It requires `prose.md` to be loaded first. All execution semantics, state management, and VM behavior are defined there. This file only provides keyword translations.
An alternative register for OpenProse that draws from the works of Franz Kafka—The Trial, The Castle, "In the Penal Colony." Programs become proceedings. Agents become clerks. Everything is a process, and nobody quite knows the rules.
## How to Use
1. Load `prose.md` first (execution semantics)
2. Load this file (keyword translations)
3. When parsing `.prose` files, accept Kafka keywords as aliases for functional keywords
4. All execution behavior remains identical—only surface syntax changes
> **Design constraint:** Still aims to be "structured but self-evident" per the language tenets—just self-evident through a bureaucratic lens. (The irony is intentional.)
---
## Complete Translation Map
### Core Constructs
| Functional | Kafka | Reference |
|------------|-------|-----------|
| `agent` | `clerk` | A functionary in the apparatus |
| `session` | `proceeding` | An official action taken |
| `parallel` | `departments` | Multiple bureaus acting simultaneously |
| `block` | `regulation` | A codified procedure |
### Composition & Binding
| Functional | Kafka | Reference |
|------------|-------|-----------|
| `use` | `requisition` | Requesting from the archives |
| `input` | `petition` | What is submitted for consideration |
| `output` | `verdict` | What is returned by the apparatus |
| `let` | `file` | Recording in the system |
| `const` | `statute` | Unchangeable law |
| `context` | `dossier` | The accumulated file on a case |
### Control Flow
| Functional | Kafka | Reference |
|------------|-------|-----------|
| `repeat N` | `N hearings` | Repeated appearances before the court |
| `for...in` | `for each...in the matter of` | Bureaucratic iteration |
| `loop` | `appeal` | Endless re-petition, the process continues |
| `until` | `until` | Unchanged |
| `while` | `while` | Unchanged |
| `choice` | `tribunal` | Where judgment is rendered |
| `option` | `ruling` | One possible judgment |
| `if` | `in the event that` | Bureaucratic conditional |
| `elif` | `or in the event that` | Continued conditional |
| `else` | `otherwise` | Default ruling |
### Error Handling
| Functional | Kafka | Reference |
|------------|-------|-----------|
| `try` | `submit` | Submitting for processing |
| `catch` | `should it be denied` | Rejection by the apparatus |
| `finally` | `regardless` | What happens no matter the outcome |
| `throw` | `reject` | The system refuses |
| `retry` | `resubmit` | Try the process again |
### Session Properties
| Functional | Kafka | Reference |
|------------|-------|-----------|
| `prompt` | `directive` | Official instructions |
| `model` | `authority` | Which level of the hierarchy |
### Unchanged
These keywords already work or are too functional to replace sensibly:
- `**...**` discretion markers — the inscrutable judgment of the apparatus
- `until`, `while` — already work
- `map`, `filter`, `reduce`, `pmap` — pipeline operators
- `max` — constraint modifier
- `as` — aliasing
- Model names: `sonnet`, `opus`, `haiku` — retained (or see "authority" above)
---
## Side-by-Side Comparison
### Simple Program
```prose
# Functional
use "@alice/research" as research
input topic: "What to investigate"
agent helper:
model: sonnet
let findings = session: helper
prompt: "Research {topic}"
output summary = session "Summarize"
context: findings
```
```prose
# Kafka
requisition "@alice/research" as research
petition topic: "What to investigate"
clerk helper:
authority: sonnet
file findings = proceeding: helper
directive: "Research {topic}"
verdict summary = proceeding "Summarize"
dossier: findings
```
### Parallel Execution
```prose
# Functional
parallel:
security = session "Check security"
perf = session "Check performance"
style = session "Check style"
session "Synthesize review"
context: { security, perf, style }
```
```prose
# Kafka
departments:
security = proceeding "Check security"
perf = proceeding "Check performance"
style = proceeding "Check style"
proceeding "Synthesize review"
dossier: { security, perf, style }
```
### Loop with Condition
```prose
# Functional
loop until **the code is bug-free** (max: 5):
session "Find and fix bugs"
```
```prose
# Kafka
appeal until **the code is bug-free** (max: 5):
proceeding "Find and fix bugs"
```
### Error Handling
```prose
# Functional
try:
session "Risky operation"
catch as err:
session "Handle error"
context: err
finally:
session "Cleanup"
```
```prose
# Kafka
submit:
proceeding "Risky operation"
should it be denied as err:
proceeding "Handle error"
dossier: err
regardless:
proceeding "Cleanup"
```
### Choice Block
```prose
# Functional
choice **the severity level**:
option "Critical":
session "Escalate immediately"
option "Minor":
session "Log for later"
```
```prose
# Kafka
tribunal **the severity level**:
ruling "Critical":
proceeding "Escalate immediately"
ruling "Minor":
proceeding "Log for later"
```
### Conditionals
```prose
# Functional
if **has security issues**:
session "Fix security"
elif **has performance issues**:
session "Optimize"
else:
session "Approve"
```
```prose
# Kafka
in the event that **has security issues**:
proceeding "Fix security"
or in the event that **has performance issues**:
proceeding "Optimize"
otherwise:
proceeding "Approve"
```
### Reusable Blocks
```prose
# Functional
block review(topic):
session "Research {topic}"
session "Analyze {topic}"
do review("quantum computing")
```
```prose
# Kafka
regulation review(topic):
proceeding "Research {topic}"
proceeding "Analyze {topic}"
invoke review("quantum computing")
```
### Fixed Iteration
```prose
# Functional
repeat 3:
session "Attempt connection"
```
```prose
# Kafka
3 hearings:
proceeding "Attempt connection"
```
### Immutable Binding
```prose
# Functional
const config = { model: "opus", retries: 3 }
```
```prose
# Kafka
statute config = { authority: "opus", resubmit: 3 }
```
---
## The Case For Kafka
1. **Darkly comic.** Programs-as-bureaucracy is funny and relatable.
2. **Surprisingly apt.** Software often *is* an inscrutable apparatus.
3. **Clean mappings.** Petition/verdict, file/dossier, clerk/proceeding all work well.
4. **Appeal as loop.** The endless appeal process is a perfect metaphor for retry logic.
5. **Cultural resonance.** "Kafkaesque" is a widely understood adjective.
6. **Self-aware.** Using Kafka for a programming language acknowledges the absurdity.
## The Case Against Kafka
1. **Bleak tone.** Not everyone wants their programs to feel like The Trial.
2. **Verbose keywords.** "In the event that" and "should it be denied" are long.
3. **Anxiety-inducing.** May not be fun for users who find bureaucracy stressful.
4. **Irony may not land.** Some users might take it literally and find it off-putting.
---
## Key Kafka Concepts
| Term | Meaning | Used for |
|------|---------|----------|
| The apparatus | The inscrutable system | The VM itself |
| K. | The protagonist, never fully named | The user |
| The Trial | Process without clear rules | Program execution |
| The Castle | Unreachable authority | Higher-level systems |
| Clerk | Functionary who processes | `agent``clerk` |
| Proceeding | Official action | `session``proceeding` |
| Dossier | Accumulated file | `context``dossier` |
---
## Alternatives Considered
### For `clerk` (agent)
| Keyword | Rejected because |
|---------|------------------|
| `official` | Too generic |
| `functionary` | Hard to spell |
| `bureaucrat` | Too pejorative |
| `advocate` | Too positive/helpful |
### For `proceeding` (session)
| Keyword | Rejected because |
|---------|------------------|
| `case` | Overloaded (switch case) |
| `hearing` | Reserved for `repeat N hearings` |
| `trial` | Used in Homeric register |
| `process` | Too technical |
### For `departments` (parallel)
| Keyword | Rejected because |
|---------|------------------|
| `bureaus` | Good alternative, slightly less clear |
| `offices` | Too mundane |
| `ministries` | More Orwellian than Kafkaesque |
### For `appeal` (loop)
| Keyword | Rejected because |
|---------|------------------|
| `recourse` | Too legal-technical |
| `petition` | Used for `input` |
| `process` | Too generic |
---
## Verdict
Preserved for benchmarking. The Kafka register offers a darkly comic, self-aware framing that acknowledges the bureaucratic nature of software systems. The irony is the point.
Best suited for:
- Users with a sense of humor about software complexity
- Programs that genuinely feel like navigating bureaucracy
- Contexts where acknowledging absurdity is welcome
Not recommended for:
- Users who find bureaucratic metaphors stressful
- Contexts requiring earnest, positive framing
- Documentation that needs to feel approachable
---
## Closing Note
> "Someone must have slandered Josef K., for one morning, without having done anything wrong, he was arrested."
> — *The Trial*
In the Kafka register, your program is Josef K. The apparatus will process it. Whether it succeeds or fails, no one can say for certain. But the proceedings will continue.

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,4 @@
# Hello World
# The simplest OpenProse program - a single session
session "Say hello and briefly introduce yourself"

View File

@@ -0,0 +1,6 @@
# Research and Summarize
# A two-step workflow: research a topic, then summarize findings
session "Research the latest developments in AI agents and multi-agent systems. Focus on papers and announcements from the past 6 months."
session "Summarize the key findings from your research in 5 bullet points. Focus on practical implications for developers."

View File

@@ -0,0 +1,17 @@
# Code Review Pipeline
# Review code from multiple perspectives sequentially
# First, understand what the code does
session "Read the files in src/ and provide a brief overview of the codebase structure and purpose."
# Security review
session "Review the code for security vulnerabilities. Look for injection risks, authentication issues, and data exposure."
# Performance review
session "Review the code for performance issues. Look for N+1 queries, unnecessary allocations, and blocking operations."
# Maintainability review
session "Review the code for maintainability. Look for code duplication, unclear naming, and missing documentation."
# Synthesize findings
session "Create a unified code review report combining all the findings above. Prioritize issues by severity and provide actionable recommendations."

View File

@@ -0,0 +1,14 @@
# Write and Refine
# Draft content, then iteratively improve it
# Create initial draft
session "Write a first draft of a README.md for this project. Include sections for: overview, installation, usage, and contributing."
# Self-review and improve
session "Review the README draft you just wrote. Identify areas that are unclear, too verbose, or missing important details."
# Apply improvements
session "Rewrite the README incorporating your review feedback. Make it more concise and add any missing sections."
# Final polish
session "Do a final pass on the README. Fix any typos, improve formatting, and ensure code examples are correct."

View File

@@ -0,0 +1,20 @@
# Debug an Issue
# Step-by-step debugging workflow
# Understand the problem
session "Read the error message and stack trace. Identify which file and function is causing the issue."
# Gather context
session "Read the relevant source files and understand the code flow that leads to the error."
# Form hypothesis
session "Based on your investigation, form a hypothesis about what's causing the bug. List 2-3 possible root causes."
# Test hypothesis
session "Write a test case that reproduces the bug. This will help verify the fix later."
# Implement fix
session "Implement a fix for the most likely root cause. Explain your changes."
# Verify fix
session "Run the test suite to verify the fix works and doesn't break anything else."

Some files were not shown because too many files have changed in this diff Show More