Compare commits

..

29 Commits

Author SHA1 Message Date
Peter Steinberger bcedeb4e1f chore: bump 2026.1.24
Workflow Sanity / no-tabs (push) Failing after 31s
CI / install-check (push) Has been cancelled
CI / checks (bunx tsc -p tsconfig.json, bun, build) (push) Has been cancelled
CI / checks (bunx vitest run, bun, test) (push) Has been cancelled
CI / checks (pnpm build, node, build) (push) Has been cancelled
CI / checks (pnpm format, node, format) (push) Has been cancelled
CI / checks (pnpm lint, node, lint) (push) Has been cancelled
CI / checks (pnpm protocol:check, node, protocol) (push) Has been cancelled
CI / checks (pnpm test, node, test) (push) Has been cancelled
CI / secrets (push) Has been cancelled
CI / checks-windows (pnpm build, node, build) (push) Has been cancelled
CI / checks-windows (pnpm lint, node, lint) (push) Has been cancelled
CI / checks-windows (pnpm protocol:check, node, protocol) (push) Has been cancelled
CI / checks-windows (pnpm test, node, test) (push) Has been cancelled
CI / checks-macos (pnpm test, test) (push) Has been cancelled
CI / macos-app (set -euo pipefail for attempt in 1 2 3; do if swift build --package-path apps/macos --configuration release; then exit 0 fi echo "swift build failed (attempt $attempt/3). Retrying…" sleep $((attempt * 20)) done exit 1 , build) (push) Has been cancelled
CI / macos-app (set -euo pipefail for attempt in 1 2 3; do if swift test --package-path apps/macos --parallel --enable-code-coverage --show-codecov-path; then exit 0 fi echo "swift test failed (attempt $attempt/3). Retrying…" sleep $((attempt *… (push) Has been cancelled
CI / macos-app (swiftlint --config .swiftlint.yml swiftformat --lint apps/macos/Sources --config .swiftformat , lint) (push) Has been cancelled
CI / ios (push) Has been cancelled
CI / android (./gradlew --no-daemon :app:assembleDebug, build) (push) Has been cancelled
CI / android (./gradlew --no-daemon :app:testDebugUnitTest, test) (push) Has been cancelled
2026-01-24 15:00:00 +00:00
Peter Steinberger f076eba98a docs: add hackable install faq 2026-01-24 14:52:26 +00:00
Peter Steinberger f3bd6bf342 docs: add docs ssl error faq 2026-01-24 14:51:26 +00:00
Peter Steinberger c29c9a1e3e docs: add pi sizing guidance 2026-01-24 14:51:26 +00:00
Peter Steinberger 7a384ea07c docs: add update fly signal 2026-01-24 14:37:31 +00:00
Peter Steinberger 5fc866e8fe docs: add openai subscription faq 2026-01-24 14:37:17 +00:00
Peter Steinberger 437535ee94 docs: clarify gpt-5.2 vs glm 2026-01-24 14:37:17 +00:00
Peter Steinberger 3b929ff843 docs: add glm budget option 2026-01-24 14:37:17 +00:00
Peter Steinberger 93737ee152 test: align agent id normalization 2026-01-24 14:36:31 +00:00
Peter Steinberger 765626b492 test: trim cron agentId label 2026-01-24 14:36:31 +00:00
Peter Steinberger 42b8fce4e5 docs: link models concept in faq 2026-01-24 14:28:38 +00:00
Peter Steinberger c27294133e docs: add recommended models faq 2026-01-24 14:28:38 +00:00
Peter Steinberger 94095386b3 docs: add installer verbose troubleshooting 2026-01-24 14:25:29 +00:00
Peter Steinberger 7a524e8667 docs: add migration scheduling and concurrency faqs 2026-01-24 14:21:26 +00:00
Peter Steinberger 876bbb742a test: skip opencode alpha GLM in live suite 2026-01-24 14:08:16 +00:00
Peter Steinberger ef7971e3a4 fix: normalize heartbeat targets 2026-01-24 13:53:00 +00:00
Peter Steinberger 9d742ba51f fix: hide message_id hints in web chat 2026-01-24 13:52:31 +00:00
Peter Steinberger 386d21b6d1 fix: sync tests with config normalization 2026-01-24 13:32:26 +00:00
Peter Steinberger c8afa8207c chore: prepare 2026.1.23-1 2026-01-24 13:28:22 +00:00
Peter Steinberger d0e21f05a6 fix: drop opencode alpha GLM model 2026-01-24 13:19:55 +00:00
Peter Steinberger 11f039ef85 fix: include tts dist in npm package 2026-01-24 13:18:20 +00:00
Peter Steinberger e90e3ba954 docs: link macos node to cli node 2026-01-24 13:17:28 +00:00
Peter Steinberger 0de7852d46 docs: finalize 2026.1.23 changelog 2026-01-24 13:16:05 +00:00
Nicolas Zullo 834663dfef feat(templates): add emoji reactions guidance to AGENTS.md (#1591)
## What
Add emoji reactions guidance to the default AGENTS.md template.

## Why  
Reactions are a natural, human-like way to acknowledge messages without cluttering chat. This should be default behavior.

## Testing
- Tested locally on Discord DM 
- Tested locally on Discord guild channel 

## AI-Assisted
This change was drafted with help from my Clawdbot instance (Clawd 🦞). 
We tested the behavior together before submitting.
2026-01-24 13:12:16 +00:00
Peter Steinberger a72d7a9f36 docs: add vps install faq 2026-01-24 13:11:31 +00:00
Peter Steinberger 67e57e7c99 docs: add beta vs dev install faq 2026-01-24 13:11:31 +00:00
Peter Steinberger 4c98d6c121 docs: add latest version faq 2026-01-24 13:11:31 +00:00
Peter Steinberger 174a1cb68a docs: clarify mac mini + imessage ssh 2026-01-24 13:11:31 +00:00
Peter Steinberger a4d56bd06e docs: add mac mini faq 2026-01-24 13:11:31 +00:00
31 changed files with 508 additions and 140 deletions
+1
View File
@@ -106,6 +106,7 @@
## Agent-Specific Notes
- Vocabulary: "makeup" = "mac app".
- Never edit `node_modules` (global/Homebrew/npm/git installs too). Updates overwrite. Skill notes go in `tools.md` or `AGENTS.md`.
- Signal: "update fly" => `fly ssh console -a flawd-bot -C "bash -lc 'cd /data/clawd/clawdbot && git pull --rebase origin main'"` then `fly machines restart e825232f34d058 -a flawd-bot`.
- When working on a GitHub Issue or PR, print the full URL at the end of the task.
- When answering questions, respond with high-confidence answers only: verify in code; do not guess.
- Never update the Carbon dependency.
+63 -64
View File
@@ -2,81 +2,80 @@
Docs: https://docs.clawd.bot
## 2026.1.23 (Unreleased)
### Highlights
- TTS: allow model-driven TTS tags by default for expressive audio replies (laughter, singing cues, etc.).
## 2026.1.24
### Changes
- Gateway: add /tools/invoke HTTP endpoint for direct tool calls and document it. (#1575) Thanks @vignesh07.
- Agents: keep system prompt time zone-only and move current time to `session_status` for better cache hits.
- Agents: remove redundant bash tool alias from tool registration/display. (#1571) Thanks @Takhoffman.
- Browser: add node-host proxy auto-routing for remote gateways (configurable per gateway/node).
- Heartbeat: add per-channel visibility controls (OK/alerts/indicator). (#1452) Thanks @dlauer.
- Plugins: add optional llm-task JSON-only tool for workflows. (#1498) Thanks @vignesh07.
- CLI: restart the gateway by default after `clawdbot update`; add `--no-restart` to skip it.
- CLI: add live auth probes to `clawdbot models status` for per-profile verification.
- CLI: add `clawdbot system` for system events + heartbeat controls; remove standalone `wake`.
- Agents: add Bedrock auto-discovery defaults + config overrides. (#1553) Thanks @fal3.
- Docs: add cron vs heartbeat decision guide (with Lobster workflow notes). (#1533) Thanks @JustYannicc.
- Docs: clarify HEARTBEAT.md empty file skips heartbeats, missing file still runs. (#1535) Thanks @JustYannicc.
- Docs: expand FAQ (migration, scheduling, concurrency, model recommendations, OpenAI subscription auth, Pi sizing, hackable install, docs SSL workaround).
- Docs: add verbose installer troubleshooting guidance.
- Docs: update Fly.io guide notes.
### Fixes
- Web UI: hide internal `message_id` hints in chat bubbles.
- Heartbeat: normalize target identifiers for consistent routing.
## 2026.1.23-1
### Fixes
- Packaging: include dist/tts output in npm tarball (fixes missing dist/tts/tts.js).
## 2026.1.23
### Highlights
- TTS: move Telegram TTS into core + enable model-driven TTS tags by default for expressive audio replies. (#1559) Thanks @Glucksberg. https://docs.clawd.bot/tts
- Gateway: add `/tools/invoke` HTTP endpoint for direct tool calls (auth + tool policy enforced). (#1575) Thanks @vignesh07. https://docs.clawd.bot/gateway/tools-invoke-http-api
- Heartbeat: per-channel visibility controls (OK/alerts/indicator). (#1452) Thanks @dlauer. https://docs.clawd.bot/gateway/heartbeat
- Deploy: add Fly.io deployment support + guide. (#1570) https://docs.clawd.bot/platforms/fly
- Channels: add Tlon/Urbit channel plugin (DMs, group mentions, thread replies). (#1544) Thanks @wca4a. https://docs.clawd.bot/channels/tlon
### Changes
- Channels: allow per-group tool allow/deny policies across built-in + plugin channels. (#1546) Thanks @adam91holt. https://docs.clawd.bot/multi-agent-sandbox-tools
- Agents: add Bedrock auto-discovery defaults + config overrides. (#1553) Thanks @fal3. https://docs.clawd.bot/bedrock
- CLI: add `clawdbot system` for system events + heartbeat controls; remove standalone `wake`. (commit 71203829d) https://docs.clawd.bot/cli/system
- CLI: add live auth probes to `clawdbot models status` for per-profile verification. (commit 40181afde) https://docs.clawd.bot/cli/models
- CLI: restart the gateway by default after `clawdbot update`; add `--no-restart` to skip it. (commit 2c85b1b40)
- Browser: add node-host proxy auto-routing for remote gateways (configurable per gateway/node). (commit c3cb26f7c)
- Plugins: add optional `llm-task` JSON-only tool for workflows. (#1498) Thanks @vignesh07. https://docs.clawd.bot/tools/llm-task
- Markdown: add per-channel table conversion (bullets for Signal/WhatsApp, code blocks elsewhere). (#1495) Thanks @odysseus0.
- Tlon: add Urbit channel plugin (DMs, group mentions, thread replies). (#1544) Thanks @wca4a.
- Channels: allow per-group tool allow/deny policies across built-in + plugin channels. (#1546) Thanks @adam91holt.
- TTS: move Telegram TTS into core with auto-replies, commands, and gateway methods. (#1559) Thanks @Glucksberg.
- Agents: keep system prompt time zone-only and move current time to `session_status` for better cache hits. (commit 66eec295b)
- Agents: remove redundant bash tool alias from tool registration/display. (#1571) Thanks @Takhoffman.
- Docs: add cron vs heartbeat decision guide (with Lobster workflow notes). (#1533) Thanks @JustYannicc. https://docs.clawd.bot/automation/cron-vs-heartbeat
- Docs: clarify HEARTBEAT.md empty file skips heartbeats, missing file still runs. (#1535) Thanks @JustYannicc. https://docs.clawd.bot/gateway/heartbeat
### Fixes
- Sessions: accept non-UUID sessionIds for history/send/status while preserving agent scoping. (#1518)
- Gateway: compare Linux process start time to avoid PID recycling lock loops; keep locks unless stale. (#1572) Thanks @steipete.
- Messaging: mirror outbound sends into target session keys (threads + dmScope) and create session entries on send. (#1520)
- Sessions: normalize session key casing to lowercase for consistent routing.
- BlueBubbles: normalize group session keys for outbound mirroring. (#1520)
- Slack: match auto-thread mirroring channel ids case-insensitively. (#1520)
- Gateway: lowercase provided session keys when mirroring outbound sends. (#1520)
- Skills: gate bird Homebrew install to macOS. (#1569) Thanks @bradleypriest.
- Slack: honor open groupPolicy for unlisted channels in message + slash gating. (#1563) Thanks @itsjaydesu.
- Agents: show tool error fallback when the last assistant turn only invoked tools (prevents silent stops).
- Agents: ignore IDENTITY.md template placeholders when parsing identity to avoid placeholder replies. (#1556)
- Agents: drop orphaned OpenAI Responses reasoning blocks on model switches. (#1562) Thanks @roshanasingh4.
- Docker: update gateway command in docker-compose and Hetzner guide. (#1514)
- Heartbeat: accept plugin channel ids for heartbeat target validation + UI hints.
- Messaging/Sessions: mirror outbound sends into target session keys (threads + dmScope), create session entries on send, and normalize session key casing. (#1520, commit 4b6cdd1d3)
- Sessions: reject array-backed session stores to prevent silent wipes. (#1469)
- Voice wake: auto-save wake words on blur/submit across iOS/Android and align limits with macOS.
- UI: keep the Control UI sidebar visible while scrolling long pages. (#1515) Thanks @pookNast.
- UI: cache Control UI markdown rendering + memoize chat text extraction to reduce Safari typing jank.
- Tailscale: retry serve/funnel with sudo only for permission errors and keep original failure details. (#1551) Thanks @sweepies.
- Agents: add CLI log hint to "agent failed before reply" messages. (#1550) Thanks @sweepies.
- Discord: limit autoThread mention bypass to bot-owned threads; keep ack reactions mention-gated. (#1511) Thanks @pvoo.
- Discord: retry rate-limited allowlist resolution + command deploy to avoid gateway crashes.
- Mentions: ignore mentionPattern matches when another explicit mention is present in group chats (Slack/Discord/Telegram/WhatsApp).
- Gateway: compare Linux process start time to avoid PID recycling lock loops; keep locks unless stale. (#1572) Thanks @steipete.
- Gateway: accept null optional fields in exec approval requests. (#1511) Thanks @pvoo.
- Exec: honor tools.exec ask/security defaults for elevated approvals (avoid unwanted prompts).
- TUI: forward unknown slash commands (for example, `/context`) to the Gateway.
- TUI: include Gateway slash commands in autocomplete and `/help`.
- CLI: skip usage lines in `clawdbot models status` when provider usage is unavailable.
- CLI: suppress diagnostic session/run noise during auth probes.
- CLI: hide auth probe timeout warnings from embedded runs.
- CLI: render auth probe results as a table in `clawdbot models status`.
- CLI: suppress probe-only embedded logs unless `--verbose` is set.
- CLI: move auth probe errors below the table to reduce wrapping.
- CLI: prevent ANSI color bleed when table cells wrap.
- CLI: explain when auth profiles are excluded by auth.order in probe details.
- CLI: drop the em dash when the banner tagline wraps to a second line.
- CLI: inline auth probe errors in status rows to reduce wrapping.
- Telegram: render markdown in media captions. (#1478)
- Agents: honor enqueue overrides for embedded runs to avoid queue deadlocks in tests.
- Agents: trigger model fallback when auth profiles are all in cooldown or unavailable. (#1522)
- Daemon: use platform PATH delimiters when building minimal service paths.
- Tests: skip embedded runner ordering assertion on Windows to avoid CI timeouts.
- Exec approvals: persist allowlist entry ids to keep macOS allowlist rows stable. (#1521) Thanks @ngutman.
- Exec: honor tools.exec ask/security defaults for elevated approvals (avoid unwanted prompts). (commit 5662a9cdf)
- Daemon: use platform PATH delimiters when building minimal service paths. (commit a4e57d3ac)
- Linux: include env-configured user bin roots in systemd PATH and align PATH audits. (#1512) Thanks @robbyczgw-cla.
- TUI: render Gateway slash-command replies as system output (for example, `/context`).
- Tailscale: retry serve/funnel with sudo only for permission errors and keep original failure details. (#1551) Thanks @sweepies.
- Docker: update gateway command in docker-compose and Hetzner guide. (#1514)
- Agents: show tool error fallback when the last assistant turn only invoked tools (prevents silent stops). (commit 8ea8801d0)
- Agents: ignore IDENTITY.md template placeholders when parsing identity. (#1556)
- Agents: drop orphaned OpenAI Responses reasoning blocks on model switches. (#1562) Thanks @roshanasingh4.
- Agents: add CLI log hint to "agent failed before reply" messages. (#1550) Thanks @sweepies.
- Agents: warn and ignore tool allowlists that only reference unknown or unloaded plugin tools. (#1566)
- Agents: treat plugin-only tool allowlists as opt-ins; keep core tools enabled. (#1467)
- Agents: honor enqueue overrides for embedded runs to avoid queue deadlocks in tests. (commit 084002998)
- Slack: honor open groupPolicy for unlisted channels in message + slash gating. (#1563) Thanks @itsjaydesu.
- Discord: limit autoThread mention bypass to bot-owned threads; keep ack reactions mention-gated. (#1511) Thanks @pvoo.
- Discord: retry rate-limited allowlist resolution + command deploy to avoid gateway crashes. (commit f70ac0c7c)
- Mentions: ignore mentionPattern matches when another explicit mention is present in group chats (Slack/Discord/Telegram/WhatsApp). (commit d905ca0e0)
- Telegram: render markdown in media captions. (#1478)
- MS Teams: remove `.default` suffix from Graph scopes and Bot Framework probe scopes. (#1507, #1574) Thanks @Evizero.
- Browser: keep extension relay tabs controllable when the extension reuses a session id after switching tabs. (#1160)
- Voice wake: auto-save wake words on blur/submit across iOS/Android and align limits with macOS. (commit 69f645c66)
- UI: keep the Control UI sidebar visible while scrolling long pages. (#1515) Thanks @pookNast.
- UI: cache Control UI markdown rendering + memoize chat text extraction to reduce Safari typing jank. (commit d57cb2e1a)
- TUI: forward unknown slash commands, include Gateway commands in autocomplete, and render slash replies as system output. (commit 1af227b61, commit 8195497ce, commit 6fba598ea)
- CLI: auth probe output polish (table output, inline errors, reduced noise, and wrap fixes in `clawdbot models status`). (commit da3f2b489, commit 00ae21bed, commit 31e59cd58, commit f7dc27f2d, commit 438e782f8, commit 886752217, commit aabe0bed3, commit 81535d512, commit c63144ab1)
- Media: only parse `MEDIA:` tags when they start the line to avoid stripping prose mentions. (#1206)
- Media: preserve PNG alpha when possible; fall back to JPEG when still over size cap. (#1491) Thanks @robbyczgw-cla.
- Agents: treat plugin-only tool allowlists as opt-ins; keep core tools enabled. (#1467)
- Exec approvals: persist allowlist entry ids to keep macOS allowlist rows stable. (#1521) Thanks @ngutman.
- MS Teams (plugin): remove `.default` suffix from Graph scopes to avoid double-appending. (#1507) Thanks @Evizero.
- MS Teams (plugin): remove `.default` suffix from Bot Framework probe scope to avoid double-appending. (#1574) Thanks @Evizero.
- Browser: keep extension relay tabs controllable when the extension reuses a session id after switching tabs. (#1160)
- Agents: warn and ignore tool allowlists that only reference unknown or unloaded plugin tools. (#1566)
- Skills: gate bird Homebrew install to macOS. (#1569) Thanks @bradleypriest.
## 2026.1.22
+2 -2
View File
@@ -21,8 +21,8 @@ android {
applicationId = "com.clawdbot.android"
minSdk = 31
targetSdk = 36
versionCode = 202601230
versionName = "2026.1.23"
versionCode = 202601240
versionName = "2026.1.24"
}
buildTypes {
+2 -2
View File
@@ -19,9 +19,9 @@
<key>CFBundlePackageType</key>
<string>APPL</string>
<key>CFBundleShortVersionString</key>
<string>2026.1.23</string>
<string>2026.1.24</string>
<key>CFBundleVersion</key>
<string>20260123</string>
<string>20260124</string>
<key>NSAppTransportSecurity</key>
<dict>
<key>NSAllowsArbitraryLoadsInWebContent</key>
+2 -2
View File
@@ -17,8 +17,8 @@
<key>CFBundlePackageType</key>
<string>BNDL</string>
<key>CFBundleShortVersionString</key>
<string>2026.1.23</string>
<string>2026.1.24</string>
<key>CFBundleVersion</key>
<string>20260123</string>
<string>20260124</string>
</dict>
</plist>
+4 -4
View File
@@ -81,8 +81,8 @@ targets:
properties:
CFBundleDisplayName: Clawdbot
CFBundleIconName: AppIcon
CFBundleShortVersionString: "2026.1.23"
CFBundleVersion: "20260123"
CFBundleShortVersionString: "2026.1.24"
CFBundleVersion: "20260124"
UILaunchScreen: {}
UIApplicationSceneManifest:
UIApplicationSupportsMultipleScenes: false
@@ -130,5 +130,5 @@ targets:
path: Tests/Info.plist
properties:
CFBundleDisplayName: ClawdbotTests
CFBundleShortVersionString: "2026.1.23"
CFBundleVersion: "20260123"
CFBundleShortVersionString: "2026.1.24"
CFBundleVersion: "20260124"
@@ -15,9 +15,9 @@
<key>CFBundlePackageType</key>
<string>APPL</string>
<key>CFBundleShortVersionString</key>
<string>2026.1.23</string>
<string>2026.1.24</string>
<key>CFBundleVersion</key>
<string>202601230</string>
<string>202601240</string>
<key>CFBundleIconFile</key>
<string>Clawdbot</string>
<key>CFBundleURLTypes</key>
+1 -1
View File
@@ -82,7 +82,7 @@ and logged; a message that is only `HEARTBEAT_OK` is dropped.
every: "30m", // default: 30m (0m disables)
model: "anthropic/claude-opus-4-5",
includeReasoning: false, // default: false (deliver separate Reasoning: message when available)
target: "last", // last | whatsapp | telegram | discord | slack | signal | imessage | none
target: "last", // last | none | <channel id> (core or plugin, e.g. "bluebubbles")
to: "+15551234567", // optional channel-specific override
prompt: "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not infer or repeat old tasks from prior chats. If nothing needs attention, reply HEARTBEAT_OK.",
ackMaxChars: 300 // max chars allowed after HEARTBEAT_OK
+168 -1
View File
@@ -14,14 +14,24 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
- [How do I open the dashboard after onboarding?](#how-do-i-open-the-dashboard-after-onboarding)
- [How do I authenticate the dashboard (token) on localhost vs remote?](#how-do-i-authenticate-the-dashboard-token-on-localhost-vs-remote)
- [What runtime do I need?](#what-runtime-do-i-need)
- [Does it run on Raspberry Pi?](#does-it-run-on-raspberry-pi)
- [Can I migrate my setup to a new machine (Mac mini) without redoing onboarding?](#can-i-migrate-my-setup-to-a-new-machine-mac-mini-without-redoing-onboarding)
- [Where do I see whats new in the latest version?](#where-do-i-see-whats-new-in-the-latest-version)
- [I can't access docs.clawd.bot (SSL error). What now?](#i-cant-access-docsclawdbot-ssl-error-what-now)
- [How do I install the beta version, and whats the difference between beta and dev?](#how-do-i-install-the-beta-version-and-whats-the-difference-between-beta-and-dev)
- [The docs didnt answer my question — how do I get a better answer?](#the-docs-didnt-answer-my-question--how-do-i-get-a-better-answer)
- [How do I install Clawdbot on a VPS?](#how-do-i-install-clawdbot-on-a-vps)
- [What does the onboarding wizard actually do?](#what-does-the-onboarding-wizard-actually-do)
- [How does Anthropic "setup-token" auth work?](#how-does-anthropic-setup-token-auth-work)
- [Where do I find an Anthropic setup-token?](#where-do-i-find-an-anthropic-setup-token)
- [Do you support Claude subscription auth (Claude Code OAuth)?](#do-you-support-claude-subscription-auth-claude-code-oauth)
- [Why am I seeing `HTTP 429: rate_limit_error` from Anthropic?](#why-am-i-seeing-http-429-rate_limit_error-from-anthropic)
- [Is AWS Bedrock supported?](#is-aws-bedrock-supported)
- [How does Codex auth work?](#how-does-codex-auth-work)
- [Do you support OpenAI subscription auth (Codex OAuth)?](#do-you-support-openai-subscription-auth-codex-oauth)
- [Is a local model OK for casual chats?](#is-a-local-model-ok-for-casual-chats)
- [How do I keep hosted model traffic in a specific region?](#how-do-i-keep-hosted-model-traffic-in-a-specific-region)
- [Do I have to buy a Mac Mini to install this?](#do-i-have-to-buy-a-mac-mini-to-install-this)
- [Can I use Bun?](#can-i-use-bun)
- [Telegram: what goes in `allowFrom`?](#telegram-what-goes-in-allowfrom)
- [Can multiple people use one WhatsApp number with different Clawdbots?](#can-multiple-people-use-one-whatsapp-number-with-different-clawdbots)
@@ -34,6 +44,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
- [Can I load skills from a custom folder?](#can-i-load-skills-from-a-custom-folder)
- [How can I use different models for different tasks?](#how-can-i-use-different-models-for-different-tasks)
- [How do I install skills on Linux?](#how-do-i-install-skills-on-linux)
- [Can Clawdbot run tasks on a schedule or continuously in the background?](#can-clawdbot-run-tasks-on-a-schedule-or-continuously-in-the-background)
- [Can I run Apple/macOS-only skills from Linux?](#can-i-run-applemacos-only-skills-from-linux)
- [Do you have a Notion or HeyGen integration?](#do-you-have-a-notion-or-heygen-integration)
- [How do I install the Chrome extension for browser takeover?](#how-do-i-install-the-chrome-extension-for-browser-takeover)
@@ -81,8 +92,10 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
- [Why doesnt Clawdbot reply in a group?](#why-doesnt-clawdbot-reply-in-a-group)
- [Do groups/threads share context with DMs?](#do-groupsthreads-share-context-with-dms)
- [How many workspaces and agents can I create?](#how-many-workspaces-and-agents-can-i-create)
- [Can I run multiple bots or chats at the same time (Slack), and how should I set that up?](#can-i-run-multiple-bots-or-chats-at-the-same-time-slack-and-how-should-i-set-that-up)
- [Models: defaults, selection, aliases, switching](#models-defaults-selection-aliases-switching)
- [What is the “default model”?](#what-is-the-default-model)
- [What model do you recommend?](#what-model-do-you-recommend)
- [How do I switch models on the fly (without restarting)?](#how-do-i-switch-models-on-the-fly-without-restarting)
- [Why do I see “Model … is not allowed” and then no reply?](#why-do-i-see-model-is-not-allowed-and-then-no-reply)
- [Why do I see “Unknown model: minimax/MiniMax-M2.1”?](#why-do-i-see-unknown-model-minimaxminimax-m21)
@@ -231,6 +244,86 @@ See [Dashboard](/web/dashboard) and [Web surfaces](/web) for bind modes and auth
Node **>= 22** is required. `pnpm` is recommended. Bun is **not recommended** for the Gateway.
### Does it run on Raspberry Pi?
Yes. The Gateway is lightweight — docs list **512MB1GB RAM**, **1 core**, and about **500MB**
disk as enough for personal use, and note that a **Raspberry Pi 4 can run it**.
If you want extra headroom (logs, media, other services), **2GB is recommended**, but its
not a hard minimum.
### Can I migrate my setup to a new machine (Mac mini) without redoing onboarding?
Yes. Copy the **state directory** and **workspace**, then run Doctor once:
1) Install Clawdbot on the new machine.
2) Copy `$CLAWDBOT_STATE_DIR` (default: `~/.clawdbot`) from the old machine.
3) Copy your workspace (default: `~/clawd`).
4) Run `clawdbot doctor` and restart the Gateway service.
That preserves config, auth profiles, WhatsApp creds, sessions, and memory. If youre in
remote mode, remember the gateway host owns the session store and workspace.
Related: [Where things live on disk](/help/faq#where-does-clawdbot-store-its-data),
[Agent workspace](/concepts/agent-workspace), [Doctor](/gateway/doctor),
[Remote mode](/gateway/remote).
### Where do I see whats new in the latest version?
Check the GitHub changelog:
https://github.com/clawdbot/clawdbot/blob/main/CHANGELOG.md
Newest entries are at the top. If the top section is marked **Unreleased**, the next dated
section is the latest shipped version. Entries are grouped by **Highlights**, **Changes**, and
**Fixes** (plus docs/other sections when needed).
### I can't access docs.clawd.bot (SSL error). What now?
Some Comcast/Xfinity connections incorrectly block `docs.clawd.bot` via Xfinity
Advanced Security. Disable it or allowlist `docs.clawd.bot`, then retry. More
detail: [Troubleshooting](/help/troubleshooting#docsclawdbot-shows-an-ssl-error-comcastxfinity).
If you still can't reach the site, the docs are mirrored on GitHub:
https://github.com/clawdbot/clawdbot/tree/main/docs
### How do I install the beta version, and whats the difference between beta and dev?
**Beta** is a prerelease tag (`vYYYY.M.D-beta.N`) published to the npm disttag `beta`.
**Dev** is the moving head of `main` (git); when published, it uses the npm disttag `dev`.
Oneliners (macOS/Linux):
```bash
curl -fsSL --proto '=https' --tlsv1.2 https://clawd.bot/install.sh | bash -s -- --beta
```
```bash
curl -fsSL --proto '=https' --tlsv1.2 https://clawd.bot/install.sh | bash -s -- --install-method git
```
Windows installer (PowerShell):
https://clawd.bot/install.ps1
More detail: [Development channels](/install/development-channels) and [Installer flags](/install/installer).
### The docs didnt answer my question — how do I get a better answer?
Use the **hackable (git) install** so you have the full source and docs locally, then ask
your bot (or Claude/Codex) *from that folder* so it can read the repo and answer precisely.
```bash
curl -fsSL https://clawd.bot/install.sh | bash -s -- --install-method git
```
More detail: [Install](/install) and [Installer flags](/install/installer).
### How do I install Clawdbot on a VPS?
Any Linux VPS works. Install on the server, then use SSH/Tailscale to reach the Gateway.
Guides: [exe.dev](/platforms/exe-dev), [Hetzner](/platforms/hetzner), [Fly.io](/platforms/fly).
Remote access: [Gateway remote](/gateway/remote).
### What does the onboarding wizard actually do?
`clawdbot onboard` is the recommended setup path. In **local mode** it walks you through:
@@ -268,6 +361,16 @@ Yes. Clawdbot can **reuse Claude Code CLI credentials** (OAuth) and also support
Note: Claude subscription access is governed by Anthropics terms. For production or multiuser workloads, API keys are usually the safer choice.
### Why am I seeing `HTTP 429: rate_limit_error` from Anthropic?
That means your **Anthropic quota/rate limit** is exhausted for the current window. If you
use a **Claude subscription** (setuptoken or Claude Code OAuth), wait for the window to
reset or upgrade your plan. If you use an **Anthropic API key**, check the Anthropic Console
for usage/billing and raise limits as needed.
Tip: set a **fallback model** so Clawdbot can keep replying while a provider is ratelimited.
See [Models](/cli/models) and [OAuth](/concepts/oauth).
### Is AWS Bedrock supported?
Yes — via piais **Amazon Bedrock (Converse)** provider with **manual config**. You must supply AWS credentials/region on the gateway host and add a Bedrock provider entry in your models config. See [Amazon Bedrock](/bedrock) and [Model providers](/providers/models). If you prefer a managed key flow, an OpenAIcompatible proxy in front of Bedrock is still a valid option.
@@ -276,6 +379,14 @@ Yes — via piais **Amazon Bedrock (Converse)** provider with **manual con
Clawdbot supports **OpenAI Code (Codex)** via OAuth or by reusing your Codex CLI login (`~/.codex/auth.json`). The wizard can import the CLI login or run the OAuth flow and will set the default model to `openai-codex/gpt-5.2` when appropriate. See [Model providers](/concepts/model-providers) and [Wizard](/start/wizard).
### Do you support OpenAI subscription auth (Codex OAuth)?
Yes. Clawdbot fully supports **OpenAI Code (Codex) subscription OAuth** and can also reuse an
existing Codex CLI login (`~/.codex/auth.json`) on the gateway host. The onboarding wizard
can import the CLI login or run the OAuth flow for you.
See [OAuth](/concepts/oauth), [Model providers](/concepts/model-providers), and [Wizard](/start/wizard).
### Is a local model OK for casual chats?
Usually no. Clawdbot needs large context + strong safety; small cards truncate and leak. If you must, run the **largest** MiniMax M2.1 build you can locally (LM Studio) and see [/gateway/local-models](/gateway/local-models). Smaller/quantized models increase prompt-injection risk — see [Security](/gateway/security).
@@ -284,6 +395,17 @@ Usually no. Clawdbot needs large context + strong safety; small cards truncate a
Pick region-pinned endpoints. OpenRouter exposes US-hosted options for MiniMax, Kimi, and GLM; choose the US-hosted variant to keep data in-region. You can still list Anthropic/OpenAI alongside these by using `models.mode: "merge"` so fallbacks stay available while respecting the regioned provider you select.
### Do I have to buy a Mac Mini to install this?
No. Clawdbot runs on macOS or Linux (Windows via WSL2). A Mac mini is optional — some people
buy one as an alwayson host, but a small VPS, home server, or Raspberry Piclass box works too.
You only need a Mac **for macOSonly tools**. For iMessage, you can keep the Gateway on Linux
and run `imsg` on any Mac over SSH by pointing `channels.imessage.cliPath` at an SSH wrapper.
If you want other macOSonly tools, run the Gateway on a Mac or pair a macOS node.
Docs: [iMessage](/channels/imessage), [Nodes](/nodes), [Mac remote mode](/platforms/mac/remote).
### Can I use Bun?
Bun is **not recommended**. We see runtime bugs, especially with WhatsApp and Telegram.
@@ -405,6 +527,17 @@ npm i -g clawdhub
pnpm add -g clawdhub
```
### Can Clawdbot run tasks on a schedule or continuously in the background?
Yes. Use the Gateway scheduler:
- **Cron jobs** for scheduled or recurring tasks (persist across restarts).
- **Heartbeat** for “main session” periodic checks.
- **Isolated jobs** for autonomous agents that post summaries or deliver to chats.
Docs: [Cron jobs](/automation/cron-jobs), [Cron vs Heartbeat](/automation/cron-vs-heartbeat),
[Heartbeat](/gateway/heartbeat).
### Is there a way to run Apple/macOS-only skills if my Gateway runs on Linux?
Not directly. macOS skills are gated by `metadata.clawdbot.os` plus required binaries, and skills only appear in the system prompt when they are eligible on the **Gateway host**. On Linux, `darwin`-only skills (like `imsg`, `apple-notes`, `apple-reminders`) will not load unless you override the gating.
@@ -774,7 +907,8 @@ Docs: [Nodes](/nodes), [Nodes CLI](/cli/nodes), [Chrome extension](/tools/chrome
### 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).
to the gateway (iOS/Android nodes, or macOS “node mode” in the menubar app). For headless node
hosts and CLI control, see [Node host CLI](/cli/node).
A full restart is required for `gateway`, `discovery`, and `canvasHost` changes.
@@ -1041,6 +1175,24 @@ Tips:
- Prune old sessions (delete JSONL or store entries) if disk grows.
- Use `clawdbot doctor` to spot stray workspaces and profile mismatches.
### Can I run multiple bots or chats at the same time (Slack), and how should I set that up?
Yes. Use **MultiAgent Routing** to run multiple isolated agents and route inbound messages by
channel/account/peer. Slack is supported as a channel and can be bound to specific agents.
Browser access is powerful but not “do anything a human can” — antibot, CAPTCHAs, and MFA can
still block automation. For the most reliable browser control, use the Chrome extension relay
on the machine that runs the browser (and keep the Gateway anywhere).
Bestpractice setup:
- Alwayson Gateway host (VPS/Mac mini).
- One agent per role (bindings).
- Slack channel(s) bound to those agents.
- Local browser via extension relay (or a node) when needed.
Docs: [MultiAgent Routing](/concepts/multi-agent), [Slack](/channels/slack),
[Browser](/tools/browser), [Chrome extension](/tools/chrome-extension), [Nodes](/nodes).
## Models: defaults, selection, aliases, switching
### What is the “default model”?
@@ -1053,6 +1205,21 @@ agents.defaults.model.primary
Models are referenced as `provider/model` (example: `anthropic/claude-opus-4-5`). If you omit the provider, Clawdbot currently assumes `anthropic` as a temporary deprecation fallback — but you should still **explicitly** set `provider/model`.
### What model do you recommend?
**Recommended default:** `anthropic/claude-opus-4-5`.
**Good alternative:** `anthropic/claude-sonnet-4-5`.
**Reliable (less character):** `openai/gpt-5.2` — nearly as good as Opus, just less personality.
**Budget:** `zai/glm-4.7`.
MiniMax M2.1 has its own docs: [MiniMax](/providers/minimax) and
[Local models](/gateway/local-models).
Strong warning: weaker/over-quantized models are more vulnerable to prompt
injection and unsafe behavior. See [Security](/gateway/security).
More context: [Models](/concepts/models).
### How do I switch models on the fly (without restarting)?
Use the `/model` command as a standalone message:
+16
View File
@@ -33,6 +33,22 @@ Almost always a Node/npm PATH issue. Start here:
- [Install (Node/npm PATH sanity)](/install#nodejs--npm-path-sanity)
### Installer fails (or you need full logs)
Re-run the installer in verbose mode to see the full trace and npm output:
```bash
curl -fsSL https://clawd.bot/install.sh | bash -s -- --verbose
```
For beta installs:
```bash
curl -fsSL https://clawd.bot/install.sh | bash -s -- --beta --verbose
```
You can also set `CLAWDBOT_VERBOSE=1` instead of the flag.
### Gateway “unauthorized”, cant connect, or keeps reconnecting
- [Gateway troubleshooting](/gateway/troubleshooting)
+1 -1
View File
@@ -181,7 +181,7 @@ cat > /data/clawdbot.json << 'EOF'
"bind": "auto"
},
"meta": {
"lastTouchedVersion": "2026.1.23"
"lastTouchedVersion": "2026.1.24"
}
}
EOF
+7 -7
View File
@@ -30,17 +30,17 @@ Notes:
# From repo root; set release IDs so Sparkle feed is enabled.
# APP_BUILD must be numeric + monotonic for Sparkle compare.
BUNDLE_ID=com.clawdbot.mac \
APP_VERSION=2026.1.23 \
APP_VERSION=2026.1.24 \
APP_BUILD="$(git rev-list --count HEAD)" \
BUILD_CONFIG=release \
SIGN_IDENTITY="Developer ID Application: <Developer Name> (<TEAMID>)" \
scripts/package-mac-app.sh
# Zip for distribution (includes resource forks for Sparkle delta support)
ditto -c -k --sequesterRsrc --keepParent dist/Clawdbot.app dist/Clawdbot-2026.1.23.zip
ditto -c -k --sequesterRsrc --keepParent dist/Clawdbot.app dist/Clawdbot-2026.1.24.zip
# Optional: also build a styled DMG for humans (drag to /Applications)
scripts/create-dmg.sh dist/Clawdbot.app dist/Clawdbot-2026.1.23.dmg
scripts/create-dmg.sh dist/Clawdbot.app dist/Clawdbot-2026.1.24.dmg
# Recommended: build + notarize/staple zip + DMG
# First, create a keychain profile once:
@@ -48,26 +48,26 @@ scripts/create-dmg.sh dist/Clawdbot.app dist/Clawdbot-2026.1.23.dmg
# --apple-id "<apple-id>" --team-id "<team-id>" --password "<app-specific-password>"
NOTARIZE=1 NOTARYTOOL_PROFILE=clawdbot-notary \
BUNDLE_ID=com.clawdbot.mac \
APP_VERSION=2026.1.23 \
APP_VERSION=2026.1.24 \
APP_BUILD="$(git rev-list --count HEAD)" \
BUILD_CONFIG=release \
SIGN_IDENTITY="Developer ID Application: <Developer Name> (<TEAMID>)" \
scripts/package-mac-dist.sh
# Optional: ship dSYM alongside the release
ditto -c -k --keepParent apps/macos/.build/release/Clawdbot.app.dSYM dist/Clawdbot-2026.1.23.dSYM.zip
ditto -c -k --keepParent apps/macos/.build/release/Clawdbot.app.dSYM dist/Clawdbot-2026.1.24.dSYM.zip
```
## Appcast entry
Use the release note generator so Sparkle renders formatted HTML notes:
```bash
SPARKLE_PRIVATE_KEY_FILE=/path/to/ed25519-private-key scripts/make_appcast.sh dist/Clawdbot-2026.1.23.zip https://raw.githubusercontent.com/clawdbot/clawdbot/main/appcast.xml
SPARKLE_PRIVATE_KEY_FILE=/path/to/ed25519-private-key scripts/make_appcast.sh dist/Clawdbot-2026.1.24.zip https://raw.githubusercontent.com/clawdbot/clawdbot/main/appcast.xml
```
Generates HTML release notes from `CHANGELOG.md` (via [`scripts/changelog-to-html.sh`](https://github.com/clawdbot/clawdbot/blob/main/scripts/changelog-to-html.sh)) and embeds them in the appcast entry.
Commit the updated `appcast.xml` alongside the release assets (zip + dSYM) when publishing.
## Publish & verify
- Upload `Clawdbot-2026.1.23.zip` (and `Clawdbot-2026.1.23.dSYM.zip`) to the GitHub release for tag `v2026.1.23`.
- Upload `Clawdbot-2026.1.24.zip` (and `Clawdbot-2026.1.24.dSYM.zip`) to the GitHub release for tag `v2026.1.24`.
- Ensure the raw appcast URL matches the baked feed: `https://raw.githubusercontent.com/clawdbot/clawdbot/main/appcast.xml`.
- Sanity checks:
- `curl -I https://raw.githubusercontent.com/clawdbot/clawdbot/main/appcast.xml` returns 200.
+15
View File
@@ -92,6 +92,21 @@ In group chats where you receive every message, be **smart about when to contrib
Participate, don't dominate.
### 😊 React Like a Human!
On platforms that support reactions (Discord, Slack), use emoji reactions naturally:
**React when:**
- You appreciate something but don't need to reply (👍, ❤️, 🙌)
- Something made you laugh (😂, 💀)
- You find it interesting or thought-provoking (🤔, 💡)
- You want to acknowledge without interrupting the flow
- It's a simple yes/no or approval situation (✅, 👀)
**Why it matters:**
Reactions are lightweight social signals. Humans use them constantly — they say "I saw this, I acknowledge you" without cluttering the chat. You should too.
**Don't overdo it:** One reaction per message max. Pick the one that fits best.
## Tools
Skills provide your tools. When you need one, check its `SKILL.md`. Keep local notes (camera names, SSH details, voice preferences) in `TOOLS.md`.
+2 -1
View File
@@ -1,6 +1,6 @@
{
"name": "clawdbot",
"version": "2026.1.23",
"version": "2026.1.24-0",
"description": "WhatsApp gateway CLI (Baileys web) with Pi RPC agent",
"type": "module",
"main": "dist/index.js",
@@ -43,6 +43,7 @@
"dist/slack/**",
"dist/telegram/**",
"dist/tui/**",
"dist/tts/**",
"dist/web/**",
"dist/wizard/**",
"dist/*.js",
+3
View File
@@ -69,6 +69,9 @@ export function isModernModelRef(ref: ModelRef): boolean {
if (provider === "opencode" && id.endsWith("-free")) {
return false;
}
if (provider === "opencode" && id === "alpha-glm-4.7") {
return false;
}
if (provider === "openrouter" || provider === "opencode") {
return matchesAny(id, [
+1 -1
View File
@@ -54,7 +54,7 @@ describe("getOpencodeZenStaticFallbackModels", () => {
it("returns an array of models", () => {
const models = getOpencodeZenStaticFallbackModels();
expect(Array.isArray(models)).toBe(true);
expect(models.length).toBe(10);
expect(models.length).toBe(9);
});
it("includes Claude, GPT, Gemini, and GLM models", () => {
+1 -7
View File
@@ -67,10 +67,9 @@ export const OPENCODE_ZEN_MODEL_ALIASES: Record<string, string> = {
"gemini-2.5-pro": "gemini-3-pro",
"gemini-2.5-flash": "gemini-3-flash",
// GLM (free + alpha)
// GLM (free)
glm: "glm-4.7",
"glm-free": "glm-4.7",
"alpha-glm": "alpha-glm-4.7",
};
/**
@@ -122,7 +121,6 @@ const MODEL_COSTS: Record<
},
"claude-opus-4-5": { input: 5, output: 25, cacheRead: 0.5, cacheWrite: 6.25 },
"gemini-3-pro": { input: 2, output: 12, cacheRead: 0.2, cacheWrite: 0 },
"alpha-glm-4.7": { input: 0.6, output: 2.2, cacheRead: 0.6, cacheWrite: 0 },
"gpt-5.1-codex-mini": {
input: 0.25,
output: 2,
@@ -147,7 +145,6 @@ const MODEL_CONTEXT_WINDOWS: Record<string, number> = {
"gpt-5.1-codex": 400000,
"claude-opus-4-5": 200000,
"gemini-3-pro": 1048576,
"alpha-glm-4.7": 204800,
"gpt-5.1-codex-mini": 400000,
"gpt-5.1": 400000,
"glm-4.7": 204800,
@@ -164,7 +161,6 @@ const MODEL_MAX_TOKENS: Record<string, number> = {
"gpt-5.1-codex": 128000,
"claude-opus-4-5": 64000,
"gemini-3-pro": 65536,
"alpha-glm-4.7": 131072,
"gpt-5.1-codex-mini": 128000,
"gpt-5.1": 128000,
"glm-4.7": 131072,
@@ -201,7 +197,6 @@ const MODEL_NAMES: Record<string, string> = {
"gpt-5.1-codex": "GPT-5.1 Codex",
"claude-opus-4-5": "Claude Opus 4.5",
"gemini-3-pro": "Gemini 3 Pro",
"alpha-glm-4.7": "Alpha GLM-4.7",
"gpt-5.1-codex-mini": "GPT-5.1 Codex Mini",
"gpt-5.1": "GPT-5.1",
"glm-4.7": "GLM-4.7",
@@ -229,7 +224,6 @@ export function getOpencodeZenStaticFallbackModels(): ModelDefinitionConfig[] {
"gpt-5.1-codex",
"claude-opus-4-5",
"gemini-3-pro",
"alpha-glm-4.7",
"gpt-5.1-codex-mini",
"gpt-5.1",
"glm-4.7",
+4 -1
View File
@@ -2,6 +2,7 @@ import type { Command } from "commander";
import type { CronJob } from "../../cron/types.js";
import { danger } from "../../globals.js";
import { defaultRuntime } from "../../runtime.js";
import { normalizeAgentId } from "../../routing/session-key.js";
import type { GatewayRpcOpts } from "../gateway-rpc.js";
import { addGatewayClientOptions, callGatewayFromCli } from "../gateway-rpc.js";
import { parsePositiveIntOrUndefined } from "../program/helpers.js";
@@ -138,7 +139,9 @@ export function registerCronAddCommand(cron: Command) {
}
const agentId =
typeof opts.agent === "string" && opts.agent.trim() ? opts.agent.trim() : undefined;
typeof opts.agent === "string" && opts.agent.trim()
? normalizeAgentId(opts.agent.trim())
: undefined;
const payload = (() => {
const systemEvent = typeof opts.systemEvent === "string" ? opts.systemEvent.trim() : "";
+2 -1
View File
@@ -1,6 +1,7 @@
import type { Command } from "commander";
import { danger } from "../../globals.js";
import { defaultRuntime } from "../../runtime.js";
import { normalizeAgentId } from "../../routing/session-key.js";
import { addGatewayClientOptions, callGatewayFromCli } from "../gateway-rpc.js";
import {
getCronChannelOptions,
@@ -90,7 +91,7 @@ export function registerCronEditCommand(cron: Command) {
throw new Error("Use --agent or --clear-agent, not both");
}
if (typeof opts.agent === "string" && opts.agent.trim()) {
patch.agentId = opts.agent.trim();
patch.agentId = normalizeAgentId(opts.agent.trim());
}
if (opts.clearAgent) {
patch.agentId = null;
+48 -8
View File
@@ -9,6 +9,7 @@ async function writePluginFixture(params: {
dir: string;
id: string;
schema: Record<string, unknown>;
channels?: string[];
}) {
await fs.mkdir(params.dir, { recursive: true });
await fs.writeFile(
@@ -16,16 +17,16 @@ async function writePluginFixture(params: {
`export default { id: "${params.id}", register() {} };`,
"utf-8",
);
const manifest: Record<string, unknown> = {
id: params.id,
configSchema: params.schema,
};
if (params.channels) {
manifest.channels = params.channels;
}
await fs.writeFile(
path.join(params.dir, "clawdbot.plugin.json"),
JSON.stringify(
{
id: params.id,
configSchema: params.schema,
},
null,
2,
),
JSON.stringify(manifest, null, 2),
"utf-8",
);
}
@@ -149,4 +150,43 @@ describe("config plugin validation", () => {
expect(res.ok).toBe(true);
});
});
it("accepts plugin heartbeat targets", async () => {
await withTempHome(async (home) => {
process.env.CLAWDBOT_STATE_DIR = path.join(home, ".clawdbot");
const pluginDir = path.join(home, "bluebubbles-plugin");
await writePluginFixture({
dir: pluginDir,
id: "bluebubbles-plugin",
channels: ["bluebubbles"],
schema: { type: "object" },
});
vi.resetModules();
const { validateConfigObjectWithPlugins } = await import("./config.js");
const res = validateConfigObjectWithPlugins({
agents: { defaults: { heartbeat: { target: "bluebubbles" } }, list: [{ id: "pi" }] },
plugins: { enabled: false, load: { paths: [pluginDir] } },
});
expect(res.ok).toBe(true);
});
});
it("rejects unknown heartbeat targets", async () => {
await withTempHome(async (home) => {
process.env.CLAWDBOT_STATE_DIR = path.join(home, ".clawdbot");
vi.resetModules();
const { validateConfigObjectWithPlugins } = await import("./config.js");
const res = validateConfigObjectWithPlugins({
agents: { defaults: { heartbeat: { target: "not-a-channel" } }, list: [{ id: "pi" }] },
});
expect(res.ok).toBe(false);
if (!res.ok) {
expect(res.issues).toContainEqual({
path: "agents.defaults.heartbeat.target",
message: "unknown heartbeat target: not-a-channel",
});
}
});
});
});
+18
View File
@@ -84,4 +84,22 @@ describe("config schema", () => {
const channelProps = channelSchema?.properties as Record<string, unknown> | undefined;
expect(channelProps?.accessToken).toBeTruthy();
});
it("adds heartbeat target hints with dynamic channels", () => {
const res = buildConfigSchema({
channels: [
{
id: "bluebubbles",
label: "BlueBubbles",
configSchema: { type: "object" },
},
],
});
const defaultsHint = res.uiHints["agents.defaults.heartbeat.target"];
const listHint = res.uiHints["agents.list.*.heartbeat.target"];
expect(defaultsHint?.help).toContain("bluebubbles");
expect(defaultsHint?.help).toContain("last");
expect(listHint?.help).toContain("bluebubbles");
});
});
+43 -1
View File
@@ -1,3 +1,4 @@
import { CHANNEL_IDS } from "../channels/registry.js";
import { VERSION } from "../version.js";
import { ClawdbotSchema } from "./zod-schema.js";
@@ -807,6 +808,44 @@ function applyChannelHints(hints: ConfigUiHints, channels: ChannelUiMetadata[]):
return next;
}
function listHeartbeatTargetChannels(channels: ChannelUiMetadata[]): string[] {
const seen = new Set<string>();
const ordered: string[] = [];
for (const id of CHANNEL_IDS) {
const normalized = id.trim().toLowerCase();
if (!normalized || seen.has(normalized)) continue;
seen.add(normalized);
ordered.push(normalized);
}
for (const channel of channels) {
const normalized = channel.id.trim().toLowerCase();
if (!normalized || seen.has(normalized)) continue;
seen.add(normalized);
ordered.push(normalized);
}
return ordered;
}
function applyHeartbeatTargetHints(
hints: ConfigUiHints,
channels: ChannelUiMetadata[],
): ConfigUiHints {
const next: ConfigUiHints = { ...hints };
const channelList = listHeartbeatTargetChannels(channels);
const channelHelp = channelList.length ? ` Known channels: ${channelList.join(", ")}.` : "";
const help = `Delivery target ("last", "none", or a channel id).${channelHelp}`;
const paths = ["agents.defaults.heartbeat.target", "agents.list.*.heartbeat.target"];
for (const path of paths) {
const current = next[path] ?? {};
next[path] = {
...current,
help: current.help ?? help,
placeholder: current.placeholder ?? "last",
};
}
return next;
}
function applyPluginSchemas(schema: ConfigSchema, plugins: PluginUiMetadata[]): ConfigSchema {
const next = cloneSchema(schema);
const root = asSchemaObject(next);
@@ -908,7 +947,10 @@ export function buildConfigSchema(params?: {
const channels = params?.channels ?? [];
if (plugins.length === 0 && channels.length === 0) return base;
const mergedHints = applySensitiveHints(
applyChannelHints(applyPluginHints(base.uiHints, plugins), channels),
applyHeartbeatTargetHints(
applyChannelHints(applyPluginHints(base.uiHints, plugins), channels),
channels,
),
);
const mergedSchema = applyChannelSchemas(applyPluginSchemas(base.schema, plugins), channels);
return {
+3 -12
View File
@@ -4,6 +4,7 @@ import type {
HumanDelayConfig,
TypingMode,
} from "./types.base.js";
import type { ChannelId } from "../channels/plugins/types.js";
import type {
SandboxBrowserSettings,
SandboxDockerSettings,
@@ -177,18 +178,8 @@ export type AgentDefaultsConfig = {
model?: string;
/** Session key for heartbeat runs ("main" or explicit session key). */
session?: string;
/** Delivery target (last|whatsapp|telegram|discord|slack|mattermost|msteams|signal|imessage|none). */
target?:
| "last"
| "whatsapp"
| "telegram"
| "discord"
| "slack"
| "mattermost"
| "msteams"
| "signal"
| "imessage"
| "none";
/** Delivery target ("last", "none", or a channel id). */
target?: "last" | "none" | ChannelId;
/** Optional delivery override (E.164 for WhatsApp, chat id for Telegram). */
to?: string;
/** Override the heartbeat prompt body (default: "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not infer or repeat old tasks from prior chats. If nothing needs attention, reply HEARTBEAT_OK."). */
+36 -1
View File
@@ -1,7 +1,7 @@
import path from "node:path";
import { resolveAgentWorkspaceDir, resolveDefaultAgentId } from "../agents/agent-scope.js";
import { CHANNEL_IDS } from "../channels/registry.js";
import { CHANNEL_IDS, normalizeChatChannelId } from "../channels/registry.js";
import {
normalizePluginsConfig,
resolveEnableState,
@@ -226,6 +226,41 @@ export function validateConfigObjectWithPlugins(raw: unknown):
}
}
const heartbeatChannelIds = new Set<string>();
for (const channelId of CHANNEL_IDS) {
heartbeatChannelIds.add(channelId.toLowerCase());
}
for (const record of registry.plugins) {
for (const channelId of record.channels) {
const trimmed = channelId.trim();
if (trimmed) heartbeatChannelIds.add(trimmed.toLowerCase());
}
}
const validateHeartbeatTarget = (target: string | undefined, path: string) => {
if (typeof target !== "string") return;
const trimmed = target.trim();
if (!trimmed) {
issues.push({ path, message: "heartbeat target must not be empty" });
return;
}
const normalized = trimmed.toLowerCase();
if (normalized === "last" || normalized === "none") return;
if (normalizeChatChannelId(trimmed)) return;
if (heartbeatChannelIds.has(normalized)) return;
issues.push({ path, message: `unknown heartbeat target: ${target}` });
};
validateHeartbeatTarget(
config.agents?.defaults?.heartbeat?.target,
"agents.defaults.heartbeat.target",
);
if (Array.isArray(config.agents?.list)) {
for (const [index, entry] of config.agents.list.entries()) {
validateHeartbeatTarget(entry?.heartbeat?.target, `agents.list.${index}.heartbeat.target`);
}
}
let selectedMemoryPluginId: string | null = null;
const seenPlugins = new Set<string>();
for (const record of registry.plugins) {
+1 -13
View File
@@ -22,19 +22,7 @@ export const HeartbeatSchema = z
model: z.string().optional(),
session: z.string().optional(),
includeReasoning: z.boolean().optional(),
target: z
.union([
z.literal("last"),
z.literal("whatsapp"),
z.literal("telegram"),
z.literal("discord"),
z.literal("slack"),
z.literal("msteams"),
z.literal("signal"),
z.literal("imessage"),
z.literal("none"),
])
.optional(),
target: z.string().optional(),
to: z.string().optional(),
prompt: z.string().optional(),
ackMaxChars: z.number().int().nonnegative().optional(),
+1 -1
View File
@@ -24,7 +24,7 @@ describe("normalizeCronJobCreate", () => {
expect("provider" in payload).toBe(false);
});
it("normalizes agentId and drops null", () => {
it("trims agentId and drops null", () => {
const normalized = normalizeCronJobCreate({
name: "agent-set",
enabled: true,
+2 -1
View File
@@ -1,3 +1,4 @@
import { normalizeAgentId } from "../routing/session-key.js";
import { parseAbsoluteTimeMs } from "./parse.js";
import { migrateLegacyCronPayload } from "./payload-migration.js";
import type { CronJobCreate, CronJobPatch } from "./types.js";
@@ -75,7 +76,7 @@ export function normalizeCronJobInput(
next.agentId = null;
} else if (typeof agentId === "string") {
const trimmed = agentId.trim();
if (trimmed) next.agentId = trimmed;
if (trimmed) next.agentId = normalizeAgentId(trimmed);
else delete next.agentId;
}
}
+3 -1
View File
@@ -1,3 +1,4 @@
import { inspect } from "node:util";
import { Client } from "@buape/carbon";
import { GatewayIntents, GatewayPlugin } from "@buape/carbon/gateway";
import { Routes } from "discord-api-types/v10";
@@ -95,7 +96,8 @@ function formatDiscordDeployErrorDetails(err: unknown): string {
try {
bodyText = JSON.stringify(rawBody);
} catch {
bodyText = String(rawBody);
bodyText =
typeof rawBody === "string" ? rawBody : inspect(rawBody, { depth: 3, breakLength: 120 });
}
if (bodyText) {
const maxLen = 800;
+42
View File
@@ -0,0 +1,42 @@
import { describe, expect, test } from "vitest";
import { stripEnvelopeFromMessage } from "./chat-sanitize.js";
describe("stripEnvelopeFromMessage", () => {
test("removes message_id hint lines from user messages", () => {
const input = {
role: "user",
content: "[WhatsApp 2026-01-24 13:36] yolo\n[message_id: 7b8b]",
};
const result = stripEnvelopeFromMessage(input) as { content?: string };
expect(result.content).toBe("yolo");
});
test("removes message_id hint lines from text content arrays", () => {
const input = {
role: "user",
content: [{ type: "text", text: "hi\n[message_id: abc123]" }],
};
const result = stripEnvelopeFromMessage(input) as {
content?: Array<{ type: string; text?: string }>;
};
expect(result.content?.[0]?.text).toBe("hi");
});
test("does not strip inline message_id text that is part of a line", () => {
const input = {
role: "user",
content: "I typed [message_id: 123] on purpose",
};
const result = stripEnvelopeFromMessage(input) as { content?: string };
expect(result.content).toBe("I typed [message_id: 123] on purpose");
});
test("does not strip assistant messages", () => {
const input = {
role: "assistant",
content: "note\n[message_id: 123]",
};
const result = stripEnvelopeFromMessage(input) as { content?: string };
expect(result.content).toBe("note\n[message_id: 123]");
});
});
+12 -3
View File
@@ -14,6 +14,8 @@ const ENVELOPE_CHANNELS = [
"BlueBubbles",
];
const MESSAGE_ID_LINE = /^\s*\[message_id:\s*[^\]]+\]\s*$/i;
function looksLikeEnvelopeHeader(header: string): boolean {
if (/\d{4}-\d{2}-\d{2}T\d{2}:\d{2}Z\b/.test(header)) return true;
if (/\d{4}-\d{2}-\d{2} \d{2}:\d{2}\b/.test(header)) return true;
@@ -28,13 +30,20 @@ export function stripEnvelope(text: string): string {
return text.slice(match[0].length);
}
function stripMessageIdHints(text: string): string {
if (!text.includes("[message_id:")) return text;
const lines = text.split(/\r?\n/);
const filtered = lines.filter((line) => !MESSAGE_ID_LINE.test(line));
return filtered.length === lines.length ? text : filtered.join("\n");
}
function stripEnvelopeFromContent(content: unknown[]): { content: unknown[]; changed: boolean } {
let changed = false;
const next = content.map((item) => {
if (!item || typeof item !== "object") return item;
const entry = item as Record<string, unknown>;
if (entry.type !== "text" || typeof entry.text !== "string") return item;
const stripped = stripEnvelope(entry.text);
const stripped = stripMessageIdHints(stripEnvelope(entry.text));
if (stripped === entry.text) return item;
changed = true;
return {
@@ -55,7 +64,7 @@ export function stripEnvelopeFromMessage(message: unknown): unknown {
const next: Record<string, unknown> = { ...entry };
if (typeof entry.content === "string") {
const stripped = stripEnvelope(entry.content);
const stripped = stripMessageIdHints(stripEnvelope(entry.content));
if (stripped !== entry.content) {
next.content = stripped;
changed = true;
@@ -67,7 +76,7 @@ export function stripEnvelopeFromMessage(message: unknown): unknown {
changed = true;
}
} else if (typeof entry.text === "string") {
const stripped = stripEnvelope(entry.text);
const stripped = stripMessageIdHints(stripEnvelope(entry.text));
if (stripped !== entry.text) {
next.text = stripped;
changed = true;
+2 -2
View File
@@ -96,9 +96,9 @@ function pickFirstExistingAgentId(cfg: ClawdbotConfig, agentId: string): string
if (!trimmed) return normalizeAgentId(resolveDefaultAgentId(cfg));
const normalized = normalizeAgentId(trimmed);
const agents = listAgents(cfg);
if (agents.length === 0) return trimmed;
if (agents.length === 0) return normalized;
const match = agents.find((agent) => normalizeAgentId(agent.id) === normalized);
if (match?.id?.trim()) return match.id.trim();
if (match?.id?.trim()) return normalizeAgentId(match.id.trim());
return normalizeAgentId(resolveDefaultAgentId(cfg));
}