245 lines
26 KiB
XML
245 lines
26 KiB
XML
<?xml version="1.0" standalone="yes"?>
|
|
<rss xmlns:sparkle="http://www.andymatuschak.org/xml-namespaces/sparkle" version="2.0">
|
|
<channel>
|
|
<title>Clawdbot</title>
|
|
<item>
|
|
<title>2026.1.11-1</title>
|
|
<pubDate>Mon, 12 Jan 2026 09:53:46 +0000</pubDate>
|
|
<link>https://raw.githubusercontent.com/clawdbot/clawdbot/main/appcast.xml</link>
|
|
<sparkle:version>5207</sparkle:version>
|
|
<sparkle:shortVersionString>2026.1.11-1</sparkle:shortVersionString>
|
|
<sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
|
|
<description><![CDATA[<h2>Clawdbot 2026.1.11-1</h2>
|
|
<h3>Fixes</h3>
|
|
<ul>
|
|
<li>Installer: include <code>patches/</code> in the npm package so postinstall patching works for npm/bun installs.</li>
|
|
</ul>
|
|
<p><a href="https://github.com/clawdbot/clawdbot/blob/main/CHANGELOG.md">View full changelog</a></p>
|
|
]]></description>
|
|
<enclosure url="https://github.com/clawdbot/clawdbot/releases/download/v2026.1.11-1/Clawdbot-2026.1.11-1.zip" length="19860761" type="application/octet-stream" sparkle:edSignature="CXKzzha/s6cGBeF0TMz+cV8/pfqoAL9ZyNVacYRLnnHEwA1cMbOWRftpGRhYe4HknVQYYBgNQqZK2lBxpOZgBg=="/>
|
|
</item>
|
|
<item>
|
|
<title>2026.1.11</title>
|
|
<pubDate>Mon, 12 Jan 2026 09:37:49 +0000</pubDate>
|
|
<link>https://raw.githubusercontent.com/clawdbot/clawdbot/main/appcast.xml</link>
|
|
<sparkle:version>5205</sparkle:version>
|
|
<sparkle:shortVersionString>2026.1.11</sparkle:shortVersionString>
|
|
<sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
|
|
<description><![CDATA[<h2>Clawdbot 2026.1.11</h2>
|
|
<h3>Highlights</h3>
|
|
<ul>
|
|
<li>Plugins are now first-class: loader + CLI management, plus the new Voice Call plugin.</li>
|
|
<li>Config: modular <code>$include</code> support for split config files. (#731) — thanks @pasogott.</li>
|
|
<li>Agents/Pi: reserve compaction headroom so pre-compaction memory writes can run before auto-compaction.</li>
|
|
<li>Agents: automatic pre-compaction memory flush turn to store durable memories before compaction.</li>
|
|
</ul>
|
|
<h3>Changes</h3>
|
|
<ul>
|
|
<li>Deps: update pi-agent-core/pi-ai/pi-coding-agent/pi-tui and refresh the pi-ai patch.</li>
|
|
<li>Dev: bump @types/node.</li>
|
|
<li>macOS: add wizard debug CLI and share wizard parsing helpers.</li>
|
|
<li>CLI/Onboarding: simplify MiniMax auth choice to a single M2.1 option.</li>
|
|
<li>CLI: configure section selection now loops until Continue.</li>
|
|
<li>Docs: explain MiniMax vs MiniMax Lightning (speed vs cost) and restore LM Studio example.</li>
|
|
<li>Docs: add Cerebras GLM 4.6/4.7 config example (OpenAI-compatible endpoint).</li>
|
|
<li>Onboarding/CLI: group model/auth choice by provider and label Z.AI as GLM 4.7.</li>
|
|
<li>Onboarding/Docs: add Moonshot AI (Kimi K2) auth choice + config example.</li>
|
|
<li>CLI/Onboarding: prompt to reuse detected API keys for Moonshot/MiniMax/Z.AI/Gemini/Anthropic/OpenCode.</li>
|
|
<li>CLI/Onboarding: move MiniMax to the top of the provider list.</li>
|
|
<li>CLI/Onboarding: add MiniMax M2.1 Lightning auth choice.</li>
|
|
<li>CLI/Onboarding: show key previews when reusing detected API keys.</li>
|
|
<li>Auto-reply: add compact <code>/model</code> picker (models + available providers) and show provider endpoints in <code>/model status</code>.</li>
|
|
<li>Control UI: add Config tab model presets (MiniMax M2.1, GLM 4.7, Kimi) for one-click setup.</li>
|
|
<li>Plugins: add extension loader (tools/RPC/CLI/services), discovery paths, and config schema + Control UI labels (uiHints).</li>
|
|
<li>Plugins: add <code>clawdbot plugins install</code> (path/tgz/npm), plus <code>list|info|enable|disable|doctor</code> UX.</li>
|
|
<li>Plugins: voice-call plugin now real (Twilio/log), adds start/status RPC/CLI/tool + tests.</li>
|
|
<li>Docs: add plugins doc + cross-links from tools/skills/gateway config.</li>
|
|
<li>Docs: clarify memory flush behavior + writable workspace requirement in Memory/Session/FAQ.</li>
|
|
<li>Docs: add beginner-friendly plugin quick start + expand Voice Call plugin docs.</li>
|
|
<li>Tests: add Docker plugin loader + tgz-install smoke test.</li>
|
|
<li>Tests: extend Docker plugin E2E to cover installing from local folders (<code>plugins.load.paths</code>) and <code>file:</code> npm specs.</li>
|
|
<li>Tests: add coverage for pre-compaction memory flush settings (including read-only/CLI skips).</li>
|
|
<li>Tests: modernize live model smoke selection for current releases and enforce tools/images/thinking-high coverage. (#769) — thanks @steipete.</li>
|
|
<li>Agents/Tools: add <code>apply_patch</code> tool for multi-file edits (experimental; gated by tools.exec.applyPatch; OpenAI-only).</li>
|
|
<li>Agents/Tools: rename the bash tool to exec (config alias maintained). (#748) — thanks @myfunc.</li>
|
|
<li>Agents: add pre-compaction memory flush config (<code>agents.defaults.compaction.*</code>) with a soft threshold + system prompt.</li>
|
|
<li>Config: add <code>$include</code> directive for modular config files. (#731) — thanks @pasogott.</li>
|
|
<li>Build: set pnpm minimum release age to 2880 minutes (2 days). (#718) — thanks @dan-dr.</li>
|
|
<li>macOS: prompt to install the global <code>clawdbot</code> CLI when missing in local mode; install via <code>clawd.bot/install-cli.sh</code> (no onboarding) and use external launchd/CLI instead of the embedded gateway runtime.</li>
|
|
<li>Docs: add gog calendar event color IDs from <code>gog calendar colors</code>. (#715) — thanks @mjrussell.</li>
|
|
<li>Cron/CLI: add <code>--model</code> flag to cron add/edit commands. (#711) — thanks @mjrussell.</li>
|
|
<li>Cron/CLI: trim model overrides on cron edits and document main-session guidance. (#711) — thanks @mjrussell.</li>
|
|
<li>Skills: bundle <code>skill-creator</code> to guide creating and packaging skills.</li>
|
|
<li>Providers: add per-DM history limit overrides (<code>dmHistoryLimit</code>) with provider-level config. (#728) — thanks @pkrmf.</li>
|
|
<li>Discord: expose channel/category management actions in the message tool. (#730) — thanks @NicholasSpisak.</li>
|
|
<li>Docs: rename README “macOS app” section to “Apps”. (#733) — thanks @AbhisekBasu1.</li>
|
|
<li>Gateway: require <code>client.id</code> in WebSocket connect params; use <code>client.instanceId</code> for presence de-dupe; update docs/tests.</li>
|
|
<li>macOS: remove the attach-only gateway setting; local mode now always manages launchd while still attaching to an existing gateway if present.</li>
|
|
</ul>
|
|
<h3>Installer</h3>
|
|
<ul>
|
|
<li>Postinstall: replace <code>git apply</code> with builtin JS patcher (works npm/pnpm/bun; no git dependency) plus regression tests.</li>
|
|
<li>Postinstall: skip pnpm patch fallback when the new patcher is active.</li>
|
|
<li>Installer tests: add root+non-root docker smokes, CI workflow to fetch clawd.bot scripts and run install sh/cli with onboarding skipped.</li>
|
|
<li>Installer UX: support <code>CLAWDBOT_NO_ONBOARD=1</code> for non-interactive installs; fix npm prefix on Linux and auto-install git.</li>
|
|
<li>Installer UX: add <code>install.sh --help</code> with flags/env and git install hint.</li>
|
|
<li>Installer UX: add <code>--install-method git|npm</code> and auto-detect source checkouts (prompt to update git checkout vs migrate to npm).</li>
|
|
</ul>
|
|
<h3>Fixes</h3>
|
|
<ul>
|
|
<li>Control UI: flatten nav into a single horizontal scroll row on tablet/mobile (and always show collapsed group items). (#771) — thanks @carlulsoe.</li>
|
|
<li>macOS: start + await local gateway before onboarding wizard begins.</li>
|
|
<li>macOS: cancel onboarding wizard on close, recover if the gateway drops the session, and time out stalled gateway connects.</li>
|
|
<li>macOS: wizard debug CLI now surfaces error status instead of exiting as complete.</li>
|
|
<li>Models/Onboarding: configure MiniMax (minimax.io) via Anthropic-compatible <code>/anthropic</code> endpoint by default (keep <code>minimax-api</code> as a legacy alias).</li>
|
|
<li>Agents/Browser: cap Playwright AI snapshots for tool calls (maxChars); CLI snapshots remain full. (#763) — thanks @thesash.</li>
|
|
<li>Models: normalize Gemini 3 Pro/Flash IDs to preview names for live model lookups. (#769) — thanks @steipete.</li>
|
|
<li>CLI: fix guardCancel typing for configure prompts. (#769) — thanks @steipete.</li>
|
|
<li>Providers: default groupPolicy to allowlist across providers and warn in doctor when groups are open.</li>
|
|
<li>MS Teams: add groupPolicy/groupAllowFrom gating for group chats and warn when groups are open.</li>
|
|
<li>Providers: strip tool call/result ids from Gemini CLI payloads to avoid API 400s. (#756)</li>
|
|
<li>Gateway/WebChat: include handshake validation details in the WebSocket close reason for easier debugging; preserve close codes.</li>
|
|
<li>Gateway/Auth: send invalid connect responses before closing the handshake; stabilize invalid-connect auth test.</li>
|
|
<li>Gateway: tighten gateway listener detection.</li>
|
|
<li>Control UI: hide onboarding chat when configured and guard the mobile chat sidebar overlay.</li>
|
|
<li>Auth: read Codex keychain credentials and make the lookup platform-aware.</li>
|
|
<li>macOS/Release: avoid bundling dist artifacts in relay builds and generate appcasts from zip-only sources.</li>
|
|
<li>Doctor: surface plugin diagnostics in the report.</li>
|
|
<li>Plugins: treat <code>plugins.load.paths</code> directory entries as package roots when they contain <code>package.json</code> + <code>clawdbot.extensions</code>; load plugin packages from config dirs; extract archives without system tar.</li>
|
|
<li>Config: expand <code>~</code> in <code>CLAWDBOT_CONFIG_PATH</code> and common path-like config fields (including <code>plugins.load.paths</code>); guard invalid <code>$include</code> paths. (#731) — thanks @pasogott.</li>
|
|
<li>Agents: stop pre-creating session transcripts so first user messages persist in JSONL history.</li>
|
|
<li>Agents: skip pre-compaction memory flush when the session workspace is read-only.</li>
|
|
<li>Auto-reply: allow inline <code>/status</code> for allowlisted senders (stripped before the model); unauthorized senders see it as plain text.</li>
|
|
<li>Auto-reply: include config-only allowlisted models in <code>/model</code> even when the catalog is partial.</li>
|
|
<li>Auto-reply: allow fuzzy <code>/model</code> matches (e.g. <code>/model kimi</code> or <code>/model moonshot/kimi</code>) when unambiguous.</li>
|
|
<li>Auto-reply: ignore inline <code>/status</code> directives unless the message is directive-only.</li>
|
|
<li>CLI/Configure: enter the selected section immediately, then return to the section picker.</li>
|
|
<li>CLI/Configure: apply the chosen auth model as default (skip the extra picker) and refresh the model catalog for new providers.</li>
|
|
<li>Auto-reply: align <code>/think</code> default display with model reasoning defaults. (#751) — thanks @gabriel-trigo.</li>
|
|
<li>Auto-reply: flush block reply buffers on tool boundaries. (#750) — thanks @sebslight.</li>
|
|
<li>Auto-reply: allow sender fallback for command authorization when <code>SenderId</code> is empty (WhatsApp self-chat). (#755) — thanks @juanpablodlc.</li>
|
|
<li>Heartbeat: refresh prompt text for updated defaults.</li>
|
|
<li>Agents/Tools: use PowerShell on Windows to capture system utility output. (#748) — thanks @myfunc.</li>
|
|
<li>Agents/Tools: normalize Claude Code-style read/write/edit params (file_path/old_string/new_string) and keep sandbox guards in place. (#768) — thanks @hsrvc.</li>
|
|
<li>Docker: tolerate unset optional env vars in docker-setup.sh under strict mode. (#725) — thanks @petradonka.</li>
|
|
<li>CLI/Update: preserve base environment when passing overrides to update subprocesses. (#713) — thanks @danielz1z.</li>
|
|
<li>Agents: treat message tool errors as failures so fallback replies still send; require <code>to</code> + <code>message</code> for <code>action=send</code>. (#717) — thanks @theglove44.</li>
|
|
<li>Agents: preserve reasoning items on tool-only turns.</li>
|
|
<li>Agents: enforce <code><final></code> gating for reasoning-tag providers to prevent tag/reasoning leaks. (#754) — thanks @mcinteerj.</li>
|
|
<li>Agents/Subagents: wait for completion before announcing, align wait timeout with run timeout, and make announce prompts more emphatic.</li>
|
|
<li>Agents: route subagent transcripts to the target agent sessions directory and add regression coverage. (#708) — thanks @xMikeMickelson.</li>
|
|
<li>Agents/Tools: preserve action enums when flattening tool schemas. (#708) — thanks @xMikeMickelson.</li>
|
|
<li>Gateway/Agents: canonicalize main session aliases for store writes and add regression coverage. (#709) — thanks @xMikeMickelson.</li>
|
|
<li>Agents: reset sessions and retry when auto-compaction overflows instead of crashing the gateway.</li>
|
|
<li>Providers/Telegram: normalize command mentions for consistent parsing. (#729) — thanks @obviyus.</li>
|
|
<li>Providers: skip DM history limit handling for non-DM sessions. (#728) — thanks @pkrmf.</li>
|
|
<li>Sandbox: fix non-main mode incorrectly sandboxing the main DM session and align <code>/status</code> runtime reporting with effective sandbox state.</li>
|
|
<li>Sandbox/Gateway: treat <code>agent:<id>:main</code> as a main-session alias when <code>session.mainKey</code> is customized (backwards compatible).</li>
|
|
<li>Auto-reply: fast-path allowlisted slash commands (inline <code>/help</code>/<code>/commands</code>/<code>/status</code>/<code>/whoami</code> stripped before model).</li>
|
|
</ul>
|
|
<p><a href="https://github.com/clawdbot/clawdbot/blob/main/CHANGELOG.md">View full changelog</a></p>
|
|
]]></description>
|
|
<enclosure url="https://github.com/clawdbot/clawdbot/releases/download/v2026.1.11/Clawdbot-2026.1.11.zip" length="19860746" type="application/octet-stream" sparkle:edSignature="zmN6RovfpvPNm7PPYKDQ2c8nUtlq4k1+S6c3fvZwEHFRwKOxjhQtaW0phriDJwcqfguU3ibAQd/cpRtP4LYdCQ=="/>
|
|
</item>
|
|
<item>
|
|
<title>2026.1.10</title>
|
|
<pubDate>Sun, 11 Jan 2026 10:26:34 +0000</pubDate>
|
|
<link>https://raw.githubusercontent.com/clawdbot/clawdbot/main/appcast.xml</link>
|
|
<sparkle:version>4946</sparkle:version>
|
|
<sparkle:shortVersionString>2026.1.10</sparkle:shortVersionString>
|
|
<sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
|
|
<description><![CDATA[<h2>Clawdbot 2026.1.10</h2>
|
|
<h3>Highlights</h3>
|
|
<ul>
|
|
<li>CLI: <code>clawdbot status</code> now table-based + shows OS/update/gateway/daemon/agents/sessions; <code>status --all</code> adds a full read-only debug report (tables, log tails, Tailscale summary, and scan progress via OSC-9 + spinner).</li>
|
|
<li>CLI Backends: add Codex CLI fallback with resume support (text output) and JSONL parsing for new runs, plus a live CLI resume probe.</li>
|
|
<li>CLI: add <code>clawdbot update</code> (safe-ish git checkout update) + <code>--update</code> shorthand. (#673) — thanks @fm1randa.</li>
|
|
<li>Gateway: add OpenAI-compatible <code>/v1/chat/completions</code> HTTP endpoint (auth, SSE streaming, per-agent routing). (#680) — thanks @steipete.</li>
|
|
</ul>
|
|
<h3>Changes</h3>
|
|
<ul>
|
|
<li>Onboarding/Models: add first-class Z.AI (GLM) auth choice (<code>zai-api-key</code>) + <code>--zai-api-key</code> flag.</li>
|
|
<li>CLI/Onboarding: add OpenRouter API key auth option in configure/onboard. (#703) — thanks @mteam88.</li>
|
|
<li>Agents: add human-delay pacing between block replies (modes: off/natural/custom, per-agent configurable). (#446) — thanks @tony-freedomology.</li>
|
|
<li>Agents/Browser: add <code>browser.target</code> (sandbox/host/custom) with sandbox host-control gating via <code>agents.defaults.sandbox.browser.allowHostControl</code>, allowlists for custom control URLs/hosts/ports, and expand browser tool docs (remote control, profiles, internals).</li>
|
|
<li>Onboarding/Models: add catalog-backed default model picker to onboarding + configure. (#611) — thanks @jonasjancarik.</li>
|
|
<li>Agents/OpenCode Zen: update fallback models + defaults, keep legacy alias mappings. (#669) — thanks @magimetal.</li>
|
|
<li>Providers: unify group history context wrappers across providers with per-provider/per-account <code>historyLimit</code> overrides (fallback to <code>messages.groupChat.historyLimit</code>). Set <code>0</code> to disable. (#672) — thanks @steipete.</li>
|
|
<li>Gateway/Heartbeat: optionally deliver heartbeat <code>Reasoning:</code> output (<code>agents.defaults.heartbeat.includeReasoning</code>). (#690)</li>
|
|
<li>Docker: allow optional home volume + extra bind mounts in <code>docker-setup.sh</code>. (#679) — thanks @gabriel-trigo.</li>
|
|
</ul>
|
|
<h3>Fixes</h3>
|
|
<ul>
|
|
<li>CLI/Status: expand tables to full terminal width; clarify provider setup vs runtime warnings; richer per-provider detail; token previews in <code>status</code> while keeping <code>status --all</code> redacted; add troubleshooting link footer; keep log tails pasteable; show gateway auth used when reachable; surface provider runtime errors (Signal/iMessage/Slack); harden <code>tailscale status --json</code> parsing; make <code>status --all</code> scan progress determinate; and replace the footer with a 3-line “Next steps” recommendation (share/debug/probe).</li>
|
|
<li>CLI/Gateway: clarify that <code>clawdbot gateway status</code> reports RPC health (connect + RPC) and shows RPC failures separately from connect failures.</li>
|
|
<li>CLI/Update: gate progress spinner on stdout TTY and align clean-check step label. (#701) — thanks @bjesuiter.</li>
|
|
<li>Telegram: add <code>/whoami</code> + <code>/id</code> commands to reveal sender id for allowlists; allow <code>@username</code> and prefixed ids in <code>allowFrom</code> prompts (with stability warning).</li>
|
|
<li>Control UI: stop auto-writing <code>telegram.groups["*"]</code> and warn/confirm before enabling wildcard groups.</li>
|
|
<li>WhatsApp: send ack reactions only for handled messages and ignore legacy <code>messages.ackReaction</code> (doctor copies to <code>whatsapp.ackReaction</code>). (#629) — thanks @pasogott.</li>
|
|
<li>Sandbox/Skills: mirror skills into sandbox workspaces for read-only mounts so SKILL.md stays accessible.</li>
|
|
<li>Terminal/Table: ANSI-safe wrapping to prevent table clipping/color loss; add regression coverage.</li>
|
|
<li>Docker: allow optional apt packages during image build and document the build arg. (#697) — thanks @gabriel-trigo.</li>
|
|
<li>Gateway/Heartbeat: deliver reasoning even when the main heartbeat reply is <code>HEARTBEAT_OK</code>. (#694) — thanks @antons.</li>
|
|
<li>macOS: clear unsigned launchd overrides on signed restarts and warn via doctor when attach-only/disable markers are set. (#695) — thanks @jeffersonwarrior.</li>
|
|
<li>Agents: enforce single-writer session locks and drop orphan tool results to prevent tool-call ID failures (MiniMax/Anthropic-compatible APIs).</li>
|
|
<li>Docs: make <code>clawdbot status</code> the first diagnostic step, clarify <code>status --deep</code> behavior, and document <code>/whoami</code> + <code>/id</code>.</li>
|
|
<li>Docs/Testing: clarify live tool+image probes and how to list your testable <code>provider/model</code> ids.</li>
|
|
<li>Tests/Live: make gateway bash+read probes resilient to provider formatting while still validating real tool calls.</li>
|
|
<li>WhatsApp: detect @lid mentions in groups using authDir reverse mapping + resolve self JID E.164 for mention gating. (#692) — thanks @peschee.</li>
|
|
<li>Gateway/Auth: default to token auth on loopback during onboarding, add doctor token generation flow, and tighten audio transcription config to Whisper-only.</li>
|
|
<li>Providers: dedupe inbound messages across providers to avoid duplicate LLM runs on redeliveries/reconnects. (#689) — thanks @adam91holt.</li>
|
|
<li>Agents: strip <code><thought></code>/<code><antthinking></code> tags from hidden reasoning output and cover tag variants in tests. (#688) — thanks @theglove44.</li>
|
|
<li>macOS: save model picker selections as normalized provider/model IDs and keep manual entries aligned. (#683) — thanks @benithors.</li>
|
|
<li>Agents: recognize "usage limit" errors as rate limits for failover. (#687) — thanks @evalexpr.</li>
|
|
<li>CLI: avoid success message when daemon restart is skipped. (#685) — thanks @carlulsoe.</li>
|
|
<li>Commands: disable <code>/config</code> + <code>/debug</code> by default; gate via <code>commands.config</code>/<code>commands.debug</code> and hide from native registration/help output.</li>
|
|
<li>Agents/System: clarify that sub-agents remain sandboxed and cannot use elevated host access.</li>
|
|
<li>Gateway: disable the OpenAI-compatible <code>/v1/chat/completions</code> endpoint by default; enable via <code>gateway.http.endpoints.chatCompletions.enabled=true</code>.</li>
|
|
<li>macOS: stabilize bridge tunnels, guard invoke senders on disconnect, and drain stdout/stderr to avoid deadlocks. (#676) — thanks @ngutman.</li>
|
|
<li>Agents/System: clarify sandboxed runtime in system prompt and surface elevated availability when sandboxed.</li>
|
|
<li>Auto-reply: prefer <code>RawBody</code> for command/directive parsing (WhatsApp + Discord) and prevent fallback runs from clobbering concurrent session updates. (#643) — thanks @mcinteerj.</li>
|
|
<li>WhatsApp: fix group reactions by preserving message IDs and sender JIDs in history; normalize participant phone numbers to JIDs in outbound reactions. (#640) — thanks @mcinteerj.</li>
|
|
<li>WhatsApp: expose group participant IDs to the model so reactions can target the right sender.</li>
|
|
<li>Cron: <code>wakeMode: "now"</code> waits for heartbeat completion (and retries when the main lane is busy). (#666) — thanks @roshanasingh4.</li>
|
|
<li>Agents/OpenAI: fix Responses tool-only → follow-up turn handling (avoid standalone <code>reasoning</code> items that trigger 400 “required following item”) and replay reasoning items in Responses/Codex Responses history for tool-call-only turns.</li>
|
|
<li>Sandbox: add <code>clawdbot sandbox explain</code> (effective policy inspector + fix-it keys); improve “sandbox jail” tool-policy/elevated errors with actionable config key paths; link to docs.</li>
|
|
<li>Hooks/Gmail: keep Tailscale serve path at <code>/</code> while preserving the public path. (#668) — thanks @antons.</li>
|
|
<li>Hooks/Gmail: allow Tailscale target URLs to preserve internal serve paths.</li>
|
|
<li>Auth: update Claude Code keychain credentials in-place during refresh sync; share JSON file helpers; add CLI fallback coverage.</li>
|
|
<li>Auth: throttle external CLI credential syncs (Claude/Codex), reduce Keychain reads, and skip sync when cached credentials are still fresh.</li>
|
|
<li>CLI: respect <code>CLAWDBOT_STATE_DIR</code> for node pairing + voice wake settings storage. (#664) — thanks @azade-c.</li>
|
|
<li>Onboarding/Gateway: persist non-interactive gateway token auth in config; add WS wizard + gateway tool-calling regression coverage.</li>
|
|
<li>Gateway/Control UI: make <code>chat.send</code> non-blocking, wire Stop to <code>chat.abort</code>, and treat <code>/stop</code> as an out-of-band abort. (#653)</li>
|
|
<li>Gateway/Control UI: allow <code>chat.abort</code> without <code>runId</code> (abort active runs), suppress post-abort chat streaming, and prune stuck chat runs. (#653)</li>
|
|
<li>Gateway/Control UI: sniff image attachments for chat.send, drop non-images, and log mismatches. (#670) — thanks @cristip73.</li>
|
|
<li>macOS: force <code>restart-mac.sh --sign</code> to require identities and keep bundled Node signed for relay verification. (#580) — thanks @jeffersonwarrior.</li>
|
|
<li>Gateway/Agent: accept image attachments on <code>agent</code> (multimodal message) and add live gateway image probe (<code>CLAWDBOT_LIVE_GATEWAY_IMAGE_PROBE=1</code>).</li>
|
|
<li>CLI: <code>clawdbot sessions</code> now includes <code>elev:*</code> + <code>usage:*</code> flags in the table output.</li>
|
|
<li>CLI/Pairing: accept positional provider for <code>pairing list|approve</code> (npm-run compatible); update docs/bot hints.</li>
|
|
<li>Branding: normalize user-facing “ClawdBot”/“CLAWDBOT” → “Clawdbot” (CLI, status, docs).</li>
|
|
<li>Auto-reply: fix native <code>/model</code> not updating the actual chat session (Telegram/Slack/Discord). (#646)</li>
|
|
<li>Doctor: offer to run <code>clawdbot update</code> first on git installs (keeps doctor output aligned with latest).</li>
|
|
<li>Doctor: avoid false legacy workspace warning when install dir is <code>~/clawdbot</code>. (#660)</li>
|
|
<li>iMessage: fix reasoning persistence across DMs; avoid partial/duplicate replies when reasoning is enabled. (#655) — thanks @antons.</li>
|
|
<li>Models/Auth: allow MiniMax API configs without <code>models.providers.minimax.apiKey</code> (auth profiles / <code>MINIMAX_API_KEY</code>). (#656) — thanks @mneves75.</li>
|
|
<li>Agents: avoid duplicate replies when the message tool sends. (#659) — thanks @mickahouan.</li>
|
|
<li>Agents: harden Cloud Code Assist tool ID sanitization (toolUse/toolCall/toolResult) and scrub extra JSON Schema constraints. (#665) — thanks @sebslight.</li>
|
|
<li>Agents: sanitize tool results + Cloud Code Assist tool IDs at context-build time (prevents mid-run strict-provider request rejects).</li>
|
|
<li>Agents/Tools: resolve workspace-relative Read/Write/Edit paths; align bash default cwd. (#642) — thanks @mukhtharcm.</li>
|
|
<li>Discord: include forwarded message snapshots in agent session context. (#667) — thanks @rubyrunsstuff.</li>
|
|
<li>Telegram: add <code>telegram.draftChunk</code> to tune draft streaming chunking for <code>streamMode: "block"</code>. (#667) — thanks @rubyrunsstuff.</li>
|
|
<li>Tests/Agents: add regression coverage for workspace tool path resolution and bash cwd defaults.</li>
|
|
<li>iOS/Android: enable stricter concurrency/lint checks; fix Swift 6 strict concurrency issues + Android lint errors (ExifInterface, obsolete SDK check). (#662) — thanks @KristijanJovanovski.</li>
|
|
<li>iOS/macOS: share <code>AsyncTimeout</code>, require explicit <code>bridgeStableID</code> on connect, and harden tool display defaults (avoids missing-resource label fallbacks).</li>
|
|
<li>Telegram: serialize media-group processing to avoid missed albums under load.</li>
|
|
<li>Signal: handle <code>dataMessage.reaction</code> events (signal-cli SSE) to avoid broken attachment errors. (#637) — thanks @neist.</li>
|
|
<li>Docs: showcase entries for ParentPay, R2 Upload, iOS TestFlight, and Oura Health. (#650) — thanks @henrino3.</li>
|
|
<li>Agents: repair session transcripts by dropping duplicate tool results across the whole history (unblocks Anthropic-compatible APIs after retries).</li>
|
|
<li>Tests/Live: reset the gateway session between model runs to avoid cross-provider transcript incompatibilities (notably OpenAI Responses reasoning replay rules).</li>
|
|
</ul>
|
|
<p><a href="https://github.com/clawdbot/clawdbot/blob/main/CHANGELOG.md">View full changelog</a></p>
|
|
]]></description>
|
|
<enclosure url="https://github.com/clawdbot/clawdbot/releases/download/v2026.1.10/Clawdbot-2026.1.10.zip" length="199586798" type="application/octet-stream" sparkle:edSignature="Ntb22WL4b0Hu3Ntqm1iqnD+5bUqqa36iSQ8vbT/50C5FnL5IjF4GoHWrfanJ58JhBCQ4eKdK+K0U4OBZiSzZBw=="/>
|
|
</item>
|
|
</channel>
|
|
</rss> |