moltbot/appcast.xml at main · luyinhua/moltbot

Repository navigation

History

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

<?xml version="1.0" standalone="yes"?>

<title>Moltbot</title>

<item>

<sparkle:version>7952</sparkle:version>

<sparkle:shortVersionString>2026.1.24-1</sparkle:shortVersionString>

<sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>

<description><![CDATA[<h2>Moltbot 2026.1.24-1</h2>

<h3>Fixes</h3>

<ul>

<li>Packaging: include dist/shared output in npm tarball (fixes missing reasoning-tags import on install).</li>

</ul>

<p><a href="https://github.com/moltbot/moltbot/blob/main/CHANGELOG.md">View full changelog</a></p>

]]></description>

</item>

<item>

<sparkle:version>7944</sparkle:version>

<sparkle:shortVersionString>2026.1.24</sparkle:shortVersionString>

<sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>

<description><![CDATA[<h2>Moltbot 2026.1.24</h2>

<h3>Highlights</h3>

<ul>

<li>Providers: Ollama discovery + docs; Venice guide upgrades + cross-links. (#1606) Thanks @abhaymundhara. https://docs.molt.bot/providers/ollama https://docs.molt.bot/providers/venice</li>

<li>Channels: LINE plugin (Messaging API) with rich replies + quick replies. (#1630) Thanks @plum-dawg.</li>

<li>TTS: Edge fallback (keyless) + <code>/tts</code> auto modes. (#1668, #1667) Thanks @steipete, @sebslight. https://docs.molt.bot/tts</li>

<li>Exec approvals: approve in-chat via <code>/approve</code> across all channels (including plugins). (#1621) Thanks @czekaj. https://docs.molt.bot/tools/exec-approvals https://docs.molt.bot/tools/slash-commands</li>

<li>Telegram: DM topics as separate sessions + outbound link preview toggle. (#1597, #1700) Thanks @rohannagpal, @zerone0x. https://docs.molt.bot/channels/telegram</li>

</ul>

<h3>Changes</h3>

<ul>

<li>Channels: add LINE plugin (Messaging API) with rich replies, quick replies, and plugin HTTP registry. (#1630) Thanks @plum-dawg.</li>

<li>TTS: add Edge TTS provider fallback, defaulting to keyless Edge with MP3 retry on format failures. (#1668) Thanks @steipete. https://docs.molt.bot/tts</li>

<li>TTS: add auto mode enum (off/always/inbound/tagged) with per-session <code>/tts</code> override. (#1667) Thanks @sebslight. https://docs.molt.bot/tts</li>

<li>Telegram: treat DM topics as separate sessions and keep DM history limits stable with thread suffixes. (#1597) Thanks @rohannagpal.</li>

<li>Telegram: add <code>channels.telegram.linkPreview</code> to toggle outbound link previews. (#1700) Thanks @zerone0x. https://docs.molt.bot/channels/telegram</li>

<li>Web search: add Brave freshness filter parameter for time-scoped results. (#1688) Thanks @JonUleis. https://docs.molt.bot/tools/web</li>

<li>UI: refresh Control UI dashboard design system (typography, colors, spacing). (#1786) Thanks @mousberg.</li>

<li>Exec approvals: forward approval prompts to chat with <code>/approve</code> for all channels (including plugins). (#1621) Thanks @czekaj. https://docs.molt.bot/tools/exec-approvals https://docs.molt.bot/tools/slash-commands</li>

<li>Gateway: expose config.patch in the gateway tool with safe partial updates + restart sentinel. (#1653) Thanks @Glucksberg.</li>

<li>Diagnostics: add diagnostic flags for targeted debug logs (config + env override). https://docs.molt.bot/diagnostics/flags</li>

<li>Docs: expand FAQ (migration, scheduling, concurrency, model recommendations, OpenAI subscription auth, Pi sizing, hackable install, docs SSL workaround).</li>

<li>Docs: add verbose installer troubleshooting guidance.</li>

<li>Docs: add macOS VM guide with local/hosted options + VPS/nodes guidance. (#1693) Thanks @f-trycua.</li>

<li>Docs: add Bedrock EC2 instance role setup + IAM steps. (#1625) Thanks @sergical. https://docs.molt.bot/bedrock</li>

<li>Docs: update Fly.io guide notes.</li>

<li>Dev: add prek pre-commit hooks + dependabot config for weekly updates. (#1720) Thanks @dguido.</li>

</ul>

<h3>Fixes</h3>

<ul>

<li>Web UI: fix config/debug layout overflow, scrolling, and code block sizing. (#1715) Thanks @saipreetham589.</li>

<li>Web UI: show Stop button during active runs, swap back to New session when idle. (#1664) Thanks @ndbroadbent.</li>

<li>Web UI: clear stale disconnect banners on reconnect; allow form saves with unsupported schema paths but block missing schema. (#1707) Thanks @Glucksberg.</li>

<li>Web UI: hide internal <code>message_id</code> hints in chat bubbles.</li>

<li>Gateway: allow Control UI token-only auth to skip device pairing even when device identity is present (<code>gateway.controlUi.allowInsecureAuth</code>). (#1679) Thanks @steipete.</li>

<li>Matrix: decrypt E2EE media attachments with preflight size guard. (#1744) Thanks @araa47.</li>

<li>BlueBubbles: route phone-number targets to DMs, avoid leaking routing IDs, and auto-create missing DMs (Private API required). (#1751) Thanks @tyler6204. https://docs.molt.bot/channels/bluebubbles</li>

<li>BlueBubbles: keep part-index GUIDs in reply tags when short IDs are missing.</li>

<li>Signal: repair reaction sends (group/UUID targets + CLI author flags). (#1651) Thanks @vilkasdev.</li>

<li>Signal: add configurable signal-cli startup timeout + external daemon mode docs. (#1677) https://docs.molt.bot/channels/signal</li>

<li>Telegram: set fetch duplex="half" for uploads on Node 22 to avoid sendPhoto failures. (#1684) Thanks @commdata2338.</li>

<li>Telegram: use wrapped fetch for long-polling on Node to normalize AbortSignal handling. (#1639)</li>

<li>Telegram: honor per-account proxy for outbound API calls. (#1774) Thanks @radek-paclt.</li>

<li>Telegram: fall back to text when voice notes are blocked by privacy settings. (#1725) Thanks @foeken.</li>

<li>Voice Call: return stream TwiML for outbound conversation calls on initial Twilio webhook. (#1634)</li>

<li>Voice Call: serialize Twilio TTS playback and cancel on barge-in to prevent overlap. (#1713) Thanks @dguido.</li>

<li>Google Chat: tighten email allowlist matching, typing cleanup, media caps, and onboarding/docs/tests. (#1635) Thanks @iHildy.</li>

<li>Google Chat: normalize space targets without double <code>spaces/</code> prefix.</li>

<li>Agents: auto-compact on context overflow prompt errors before failing. (#1627) Thanks @rodrigouroz.</li>

<li>Agents: use the active auth profile for auto-compaction recovery.</li>

<li>Media understanding: skip image understanding when the primary model already supports vision. (#1747) Thanks @tyler6204.</li>

<li>Models: default missing custom provider fields so minimal configs are accepted.</li>

<li>Messaging: keep newline chunking safe for fenced markdown blocks across channels.</li>

<li>TUI: reload history after gateway reconnect to restore session state. (#1663)</li>

<li>Heartbeat: normalize target identifiers for consistent routing.</li>

<li>Exec: keep approvals for elevated ask unless full mode. (#1616) Thanks @ivancasco.</li>

<li>Exec: treat Windows platform labels as Windows for node shell selection. (#1760) Thanks @ymat19.</li>

<li>Gateway: include inline config env vars in service install environments. (#1735) Thanks @Seredeep.</li>

<li>Gateway: skip Tailscale DNS probing when tailscale.mode is off. (#1671)</li>

<li>Gateway: reduce log noise for late invokes + remote node probes; debounce skills refresh. (#1607) Thanks @petter-b.</li>

<li>Gateway: clarify Control UI/WebChat auth error hints for missing tokens. (#1690)</li>

<li>Gateway: listen on IPv6 loopback when bound to 127.0.0.1 so localhost webhooks work.</li>

<li>Gateway: store lock files in the temp directory to avoid stale locks on persistent volumes. (#1676)</li>

<li>macOS: default direct-transport <code>ws://</code> URLs to port 18789; document <code>gateway.remote.transport</code>. (#1603) Thanks @ngutman.</li>

<li>Tests: cap Vitest workers on CI macOS to reduce timeouts. (#1597) Thanks @rohannagpal.</li>

<li>Tests: avoid fake-timer dependency in embedded runner stream mock to reduce CI flakes. (#1597) Thanks @rohannagpal.</li>

<li>Tests: increase embedded runner ordering test timeout to reduce CI flakes. (#1597) Thanks @rohannagpal.</li>

</ul>

<p><a href="https://github.com/moltbot/moltbot/blob/main/CHANGELOG.md">View full changelog</a></p>

]]></description>

</item>

<item>

<sparkle:version>7750</sparkle:version>

<sparkle:shortVersionString>2026.1.23</sparkle:shortVersionString>

<sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>

<description><![CDATA[<h2>Moltbot 2026.1.23</h2>

<h3>Highlights</h3>

<ul>

<li>TTS: allow model-driven TTS tags by default for expressive audio replies (laughter, singing cues, etc.).</li>

</ul>

<h3>Changes</h3>

<ul>

<li>Gateway: add /tools/invoke HTTP endpoint for direct tool calls and document it. (#1575) Thanks @vignesh07.</li>

<li>Agents: keep system prompt time zone-only and move current time to <code>session_status</code> for better cache hits.</li>

<li>Agents: remove redundant bash tool alias from tool registration/display. (#1571) Thanks @Takhoffman.</li>

<li>Browser: add node-host proxy auto-routing for remote gateways (configurable per gateway/node).</li>

<li>Heartbeat: add per-channel visibility controls (OK/alerts/indicator). (#1452) Thanks @dlauer.</li>

<li>Plugins: add optional llm-task JSON-only tool for workflows. (#1498) Thanks @vignesh07.</li>

<li>CLI: restart the gateway by default after <code>moltbot update</code>; add <code>--no-restart</code> to skip it.</li>

<li>CLI: add live auth probes to <code>moltbot models status</code> for per-profile verification.</li>

<li>CLI: add <code>moltbot system</code> for system events + heartbeat controls; remove standalone <code>wake</code>.</li>

<li>Agents: add Bedrock auto-discovery defaults + config overrides. (#1553) Thanks @fal3.</li>

<li>Docs: add cron vs heartbeat decision guide (with Lobster workflow notes). (#1533) Thanks @JustYannicc.</li>

<li>Docs: clarify HEARTBEAT.md empty file skips heartbeats, missing file still runs. (#1535) Thanks @JustYannicc.</li>

<li>Markdown: add per-channel table conversion (bullets for Signal/WhatsApp, code blocks elsewhere). (#1495) Thanks @odysseus0.</li>

<li>Tlon: add Urbit channel plugin (DMs, group mentions, thread replies). (#1544) Thanks @wca4a.</li>

<li>Channels: allow per-group tool allow/deny policies across built-in + plugin channels. (#1546) Thanks @adam91holt.</li>

<li>TTS: move Telegram TTS into core with auto-replies, commands, and gateway methods. (#1559) Thanks @Glucksberg.</li>

</ul>

<h3>Fixes</h3>

<ul>

<li>Sessions: accept non-UUID sessionIds for history/send/status while preserving agent scoping. (#1518)</li>

<li>Gateway: compare Linux process start time to avoid PID recycling lock loops; keep locks unless stale. (#1572) Thanks @steipete.</li>

<li>Messaging: mirror outbound sends into target session keys (threads + dmScope) and create session entries on send. (#1520)</li>

<li>Sessions: normalize session key casing to lowercase for consistent routing.</li>

<li>BlueBubbles: normalize group session keys for outbound mirroring. (#1520)</li>

<li>Skills: gate bird Homebrew install to macOS. (#1569) Thanks @bradleypriest.</li>

<li>Slack: honor open groupPolicy for unlisted channels in message + slash gating. (#1563) Thanks @itsjaydesu.</li>

<li>Agents: show tool error fallback when the last assistant turn only invoked tools (prevents silent stops).</li>

<li>Agents: ignore IDENTITY.md template placeholders when parsing identity to avoid placeholder replies. (#1556)</li>

<li>Agents: drop orphaned OpenAI Responses reasoning blocks on model switches. (#1562) Thanks @roshanasingh4.</li>

<li>Docker: update gateway command in docker-compose and Hetzner guide. (#1514)</li>

<li>Sessions: reject array-backed session stores to prevent silent wipes. (#1469)</li>

<li>Voice wake: auto-save wake words on blur/submit across iOS/Android and align limits with macOS.</li>

<li>UI: keep the Control UI sidebar visible while scrolling long pages. (#1515) Thanks @pookNast.</li>

<li>UI: cache Control UI markdown rendering + memoize chat text extraction to reduce Safari typing jank.</li>

<li>Tailscale: retry serve/funnel with sudo only for permission errors and keep original failure details. (#1551) Thanks @sweepies.</li>

<li>Agents: add CLI log hint to "agent failed before reply" messages. (#1550) Thanks @sweepies.</li>

<li>Discord: limit autoThread mention bypass to bot-owned threads; keep ack reactions mention-gated. (#1511) Thanks @pvoo.</li>

<li>Discord: retry rate-limited allowlist resolution + command deploy to avoid gateway crashes.</li>

<li>Mentions: ignore mentionPattern matches when another explicit mention is present in group chats (Slack/Discord/Telegram/WhatsApp).</li>

<li>Gateway: accept null optional fields in exec approval requests. (#1511) Thanks @pvoo.</li>

<li>Exec: honor tools.exec ask/security defaults for elevated approvals (avoid unwanted prompts).</li>

<li>TUI: forward unknown slash commands (for example, <code>/context</code>) to the Gateway.</li>

<li>TUI: include Gateway slash commands in autocomplete and <code>/help</code>.</li>

<li>CLI: skip usage lines in <code>moltbot models status</code> when provider usage is unavailable.</li>

<li>CLI: suppress diagnostic session/run noise during auth probes.</li>

<li>CLI: hide auth probe timeout warnings from embedded runs.</li>

<li>CLI: render auth probe results as a table in <code>moltbot models status</code>.</li>

<li>CLI: suppress probe-only embedded logs unless <code>--verbose</code> is set.</li>

<li>CLI: move auth probe errors below the table to reduce wrapping.</li>

<li>CLI: prevent ANSI color bleed when table cells wrap.</li>

<li>CLI: explain when auth profiles are excluded by auth.order in probe details.</li>

<li>CLI: drop the em dash when the banner tagline wraps to a second line.</li>

<li>CLI: inline auth probe errors in status rows to reduce wrapping.</li>

<li>Telegram: render markdown in media captions. (#1478)</li>

<li>Agents: honor enqueue overrides for embedded runs to avoid queue deadlocks in tests.</li>

<li>Agents: trigger model fallback when auth profiles are all in cooldown or unavailable. (#1522)</li>

<li>Daemon: use platform PATH delimiters when building minimal service paths.</li>

<li>Tests: skip embedded runner ordering assertion on Windows to avoid CI timeouts.</li>

<li>Linux: include env-configured user bin roots in systemd PATH and align PATH audits. (#1512) Thanks @robbyczgw-cla.</li>

<li>TUI: render Gateway slash-command replies as system output (for example, <code>/context</code>).</li>

<li>Media: only parse <code>MEDIA:</code> tags when they start the line to avoid stripping prose mentions. (#1206)</li>

<li>Media: preserve PNG alpha when possible; fall back to JPEG when still over size cap. (#1491) Thanks @robbyczgw-cla.</li>

<li>Agents: treat plugin-only tool allowlists as opt-ins; keep core tools enabled. (#1467)</li>

<li>Exec approvals: persist allowlist entry ids to keep macOS allowlist rows stable. (#1521) Thanks @ngutman.</li>

<li>MS Teams (plugin): remove <code>.default</code> suffix from Graph scopes to avoid double-appending. (#1507) Thanks @Evizero.</li>

<li>MS Teams (plugin): remove <code>.default</code> suffix from Bot Framework probe scope to avoid double-appending. (#1574) Thanks @Evizero.</li>

<li>Browser: keep extension relay tabs controllable when the extension reuses a session id after switching tabs. (#1160)</li>

<li>Agents: warn and ignore tool allowlists that only reference unknown or unloaded plugin tools. (#1566)</li>

</ul>

<p><a href="https://github.com/moltbot/moltbot/blob/main/CHANGELOG.md">View full changelog</a></p>

]]></description>

</item>

</channel>

</rss>

FilesExpand file tree

appcast.xml

Latest commit

History

appcast.xml

File metadata and controls