Backfill issue -226 — The AI Toolchain

EDITIONS tail grep head diff uniq

The daily firehose — everything the toolchain shipped today, already filtered.

// HOW THIS ISSUE IS MADE

We read every release from the 174 tools on our watchlist at the source — GitHub and GitLab release notes, vendor release pages and changelogs, project blogs and feeds, vendor press releases, and the source code behind the tag. Bug-fix-only releases and non-product newsroom noise are dropped; what's left is summarized down to the new capability, how to try it, and any screenshots or videos the release itself published. Every entry links to the sources it was built from.

VIEW

ISSUE VIEW full issue

Do you prefer this view?

$ tct list   # 3 tools matched

AI & LLM Tooling

◆ AI Agent Frameworks

OpenClaw

v2.0.0-beta5 NOTES

Your own personal AI assistant. Any OS.

OpenClaw v2.0.0-beta5 adds Signal/iMessage providers, Talk Mode, Discord polls/threads/slash commands, and a full CLI onboarding wizard.

└──▷ GET THIS VERSION

$ git clone --branch v2.0.0-beta5 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2.0.0-beta5

└──▷ TRY IT

Run the new onboarding wizard to configure your gateway, providers, and skills from scratch.

$ clawdis configure

Check your current setup for config issues and migrate deprecated keys (e.g. routing.allowFrom → whatsapp.allowFrom) after upgrading.

$ clawdis doctor

Connect to your gateway from a remote terminal using the new TUI client.

$ clawdis tui

›Adds Signal provider via signal-cli JSON-RPC for send/receive messaging.
›Adds iMessage provider via imsg JSON-RPC integration (stdio) with chat_id routing and group chat support.
›Adds Talk Mode for continuous speech conversations (macOS/iOS/Android) with ElevenLabs TTS, reply directives, and optional interrupt-on-speech.
›Expands Discord tool actions to include reactions, stickers, polls, threads, search, and moderation gates.
›Adds Discord/Telegram reply tags ([[reply_to_current]], [[reply_to:<id>]]) with per-provider replyToMode (off|first|all) for native threaded replies.

+24 moreshow less

›Adds Discord user-installed slash command handling with per-user sessions and auto-registration.
›Adds Discord DM enable/allowlist plus guild channel/user/guild allowlists with id/name matching.
›Adds Discord guild routing config with per-guild/channel rules, slugged display names, and optional group DM support.
›Expands auto-reply queue modes (steer/followup/collect/steer-backlog) with debounce/cap/drop options and followup backlog handling.
›Adds Google Antigravity OAuth auth option for Claude Opus 4.5/Gemini 3 via CLI.
›Adds per-group mention gating defaults/overrides for Telegram/WhatsApp/iMessage via *.groups with "*" defaults; Discord supports discord.guilds."*" as a default.
›Adds Trello skill for board/list/card management.
›Adds things-mac skill (Things 3 CLI) for read/search plus add/update via URL scheme.
›Adds Apple Notes and Reminders skills via memo CLI.
›Adds tmux-first coding-agent skill with requires.anyBins gate for multi-CLI setup.
›Adds full CLI onboarding wizard (clawdis configure, doctor, update) covering gateway, workspace, skills, and daemon installers.
›Adds clawdis tui gateway-connected terminal UI (local or remote).
›Adds remote gateway client config (gateway.remote.*) with Bonjour-assisted discovery.
›Adds Signal CLI auto-install from GitHub releases in the onboarding wizard.
›Adds Nix mode: opt-in declarative config and read-only settings UI when CLAWDIS_NIX_MODE=1.
›Adds Docker containerized gateway/CLI setup via Dockerfile, compose, and setup script.
›Adds optional ui.seamColor accent to tint the Talk Mode side bubble (macOS/iOS/Android).
›Adds recent-session dropdown switcher in Chat UI (macOS/iOS/Android + Control UI).
›Adds Discord/Signal/iMessage connection panels in macOS and Control UI.
›Adds camera camera.list command and optional deviceId selection for snaps/clips.
›Adds remote CDP URL support and Linux launcher options (executablePath, noSandbox) for browser tools.
›Adds legacy Z_AI_API_KEY acceptance for Z.AI provider auth (maps to ZAI_API_KEY).
›Allows bun as a node manager for skill installs.
›Adds macOS debug log verbosity toggle and rolling file log toggle for swift-log-backed app logs.

└──▷ BREAKING ON UPGRADE

!Skills config schema reorganized: skillsLoad.extraDirs → skills.load.extraDirs, skillsInstall.* → skills.install.*, per-skill config map moved to skills.entries (e.g. skills.peekaboo.enabled → skills.entries.peekaboo.enabled), and new optional skills.allowBundled allowlist added.
!Session group keys now use surface:group:<id> / surface:channel:<id>; legacy group:* keys migrate on next message; groupdm keys are no longer recognized.
!Discord: discord.allowFrom, discord.guildAllowFrom, and discord.requireMention are removed; use discord.dm and discord.guilds instead.
!Discord/Telegram providers no longer auto-start from env tokens alone; discord: { enabled: true } / telegram: { enabled: true } must be added to config when using DISCORD_BOT_TOKEN / TELEGRAM_BOT_TOKEN.
!Config: routing.allowFrom is removed; use whatsapp.allowFrom instead (run clawdis doctor to migrate).
!Config: routing.groupChat.requireMention and telegram.requireMention are removed; use whatsapp.groups, imessage.groups, and telegram.groups defaults instead (run clawdis doctor to migrate).

Was this useful?

◆ AI Coding Agents

Earendil Works Pi

v0.32.2 3 RELEASES · 2026-01-03 NOTES STABLE

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

Pi v0.32.2 adds $ARGUMENTS syntax for slash commands and enables slash/hook commands during streaming.

└──▷ GET THIS VERSION

$ git clone --branch v0.32.2 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:
$ git checkout v0.32.2

└──▷ TRY IT

Use the new $ARGUMENTS syntax in a custom slash command definition to match Claude/Codex-style templates.

$ # In your slash command file:
echo 'Summarise the following: $ARGUMENTS' > ~/.pi/commands/summarise.txt

›Adds $ARGUMENTS as an alternative to $@ in custom slash commands, aligning with Claude, Codex, and OpenCode conventions — both syntaxes remain supported.
›Slash commands and hook commands now work during agent streaming: hook commands execute immediately, file-based slash commands are queued via steer/followUp.
›New streamingBehavior option ("steer" or "followUp") on prompt() lets callers specify queuing behavior when the agent is mid-stream.
›RPC prompt command now accepts an optional streamingBehavior field for remote streaming-state control.

2 more releases in this issue · 2026-01-03

v0.32.1 NOTES STABLE

Pi v0.32.1 adds !!command syntax to run shell commands hidden from LLM context.

└──▷ GET THIS VERSION

$ git clone --branch v0.32.1 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:
$ git checkout v0.32.1

└──▷ TRY IT

Run a command containing secrets or sensitive output without exposing it to the LLM's context window.

$ !!cat ~/.aws/credentials

›New !!command syntax executes bash commands that appear in the TUI and session history but are excluded from LLM context, keeping sensitive commands private from the AI.

v0.32.0 NOTES STABLE

Pi v0.32.0 adds Vertex AI support, proxy overrides in models.json, auto image resizing, and splits message delivery into steer/followUp APIs.

└──▷ GET THIS VERSION

$ git clone --branch v0.32.0 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:
$ git checkout v0.32.0

└──▷ USE IT

Proxy a built-in provider through an internal gateway without losing its model list, by overriding only baseUrl in models.json.

json

{
  "providers": {
    "openai": {
      "baseUrl": "https://my-internal-gateway.example.com/openai"
    }
  }
}

Enable automatic image resizing so large screenshots are down-sampled before being sent to the model, reducing token usage.

json

{
  "images": {
    "autoResize": true
  }
}

›Adds steer(text) and followUp(text) methods to AgentSession, replacing queueMessage(), with distinct delivery semantics: steer interrupts mid-run, followUp waits until the agent finishes.
›Adds steeringMode and followUpMode settings to settings.json, replacing queueMode, with automatic migration of existing settings files.
›Adds deliverAs: "followUp" option to pi.sendMessage() second parameter (now options?: { triggerTurn?, deliverAs? }), enabling follow-up delivery from hooks.
›Adds steer and follow_up RPC commands, set_steering_mode and set_follow_up_mode RPC commands, and steeringMode/followUpMode fields on RpcSessionState, replacing the old queue_message/set_queue_mode surface.
›Adds doubleEscapeAction key to settings.json (also configurable via /settings) to choose whether double-escape with empty editor opens /tree (default) or /branch.

+6 moreshow less

›Adds google-vertex provider for accessing Gemini models via Google Cloud Vertex AI using Application Default Credentials.
›Adds built-in provider overrides in models.json: set baseUrl to proxy a built-in provider while keeping its models, or define models to fully replace the provider.
›Adds images.autoResize key to settings.json (also configurable via /settings) to automatically resize images larger than 2000x2000 and inject original dimensions into the prompt.
›Adds Alt+Enter keybind to queue follow-up messages while the agent is streaming.
›Exports Theme and ThemeColor types for hooks using ctx.ui.custom().
›Terminal window title now displays 'pi - dirname' to identify which project session is active.

└──▷ BREAKING ON UPGRADE

!AgentSession.queueMessage() is removed; use steer() for mid-run interrupts or followUp() for post-run delivery.
!queueMode getter on AgentSession is replaced by steeringMode and followUpMode getters.
!setQueueMode() on AgentSession is replaced by setSteeringMode() and setFollowUpMode().
!queuedMessageCount on AgentSession is renamed to pendingMessageCount.
!getQueuedMessages() on AgentSession is replaced by getSteeringMessages() and getFollowUpMessages().
!clearQueue() on AgentSession now returns { steering: string[], followUp: string[] } instead of a flat array.
!hasQueuedMessages() on AgentSession is renamed to hasPendingMessages().
!pi.sendMessage() second parameter changed from triggerTurn?: boolean to options?: { triggerTurn?, deliverAs? }; callers passing a bare boolean must be updated.
!queue_message RPC command replaced by steer and follow_up commands.
!set_queue_mode RPC command replaced by set_steering_mode and set_follow_up_mode commands.
!RpcSessionState.queueMode field replaced by steeringMode and followUpMode fields.
!The 'Queue mode' settings UI entry is split into 'Steering mode' and 'Follow-up mode'.

Was this useful?

Alibaba Qwen Code

v0.6.0-nightly.20260103.105ad743 NOTES

Qwen Code v0.6.0-nightly adds locale-based LLM language auto-detection and merges ChatCompletionContentPart support.

└──▷ GET THIS VERSION

$ git clone --branch v0.6.0-nightly.20260103.105ad743 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.6.0-nightly.20260103.105ad743

›Supports merging ChatCompletionContentPart objects and filters empty messages in API requests.
›Auto-detects LLM output language from the system locale, removing the need to manually configure response language.

Was this useful?

// END OF TRANSMISSION

The AI Toolchain · curated daily · January 3, 2026
Releases & features from the open-source and commercial AI tools that practitioners actually run.

The AI Toolchain — issue -226, January 3, 2026

OpenClaw

Earendil Works Pi

Alibaba Qwen Code