Backfill issue -143 — 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

v2026.3.28 NOTES

Your own personal AI assistant. Any OS.

OpenClaw v2026.3.28 adds xAI x_search, MiniMax image gen, async approval hooks, ACP channel binds, and a new config schema command.

└──▷ GET THIS VERSION

$ git clone --branch v2026.3.28 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.3.28

└──▷ TRY IT

Enable xAI web search during interactive onboarding to configure x_search with your shared xAI key and pick a model.

$ openclaw configure --section web

Print the full JSON schema for openclaw.json to validate your config file or generate editor autocompletion.

$ openclaw config schema

Turn the current Discord or iMessage conversation into a Codex-backed ACP workspace without spawning a child thread.

$ /acp spawn codex --bind here

›Adds first-class x_search tool for the xAI/Grok provider via the Responses API, auto-enabled from existing web-search and tool config with no manual plugin toggles required.
›Adds optional x_search setup (including model picker) during openclaw onboard and openclaw configure --section web for the bundled Grok web-search plugin.
›New MiniMax image generation provider supporting the image-01 model with generate, image-to-image editing, and aspect ratio control.
›Adds async requireApproval to before_tool_call plugin hooks, enabling plugins to pause tool execution and prompt for approval via the exec overlay, Telegram buttons, Discord interactions, or /approve.
›Adds ACP current-conversation binds for Discord, BlueBubbles, and iMessage so /acp spawn codex --bind here turns the active chat into a Codex-backed workspace without spawning a child thread.

+9 moreshow less

›Enables apply_patch by default for OpenAI and OpenAI Codex models, aligned with write sandbox permissions.
›Auto-loads bundled provider and CLI-backend plugins from explicit config refs, removing the need for manual plugins.allow entries for Claude CLI, Codex CLI, and Gemini CLI.
›New upload-file Slack action for routing file uploads through the Slack upload transport with optional filename, title, and comment overrides.
›Extends upload-file action with explicit Microsoft Teams and Google Chat support, and exposes BlueBubbles file sends through upload-file (legacy sendAttachment alias preserved).
›Matrix TTS auto-replies now sent as native Matrix voice bubbles instead of generic audio attachments.
›New openclaw config schema command prints the generated JSON schema for openclaw.json.
›Exposes runHeartbeatOnce in the plugin runtime system namespace so plugins can trigger a single heartbeat cycle with an explicit delivery target override.
›Simplifies Podman rootless container setup and documents the host-CLI openclaw --container <name> ... workflow.
›Outbound Tavily API requests now tagged with X-Client-Source: openclaw for traffic attribution.

└──▷ BREAKING ON UPGRADE

!The qwen-portal-auth OAuth integration for portal.qwen.ai is removed; migrate to Model Studio with openclaw onboard --auth-choice modelstudio-api-key.
!Automatic config migrations older than two months are dropped; very old legacy keys now fail validation instead of being rewritten on load or by openclaw doctor.
!MiniMax model catalog is trimmed to M2.7 only; legacy M2, M2.1, M2.5, and VL-01 models are removed.
!Regular-mode runtime fallback for old bundled tts.<provider> API-key shapes is removed (legacy diagnostics remain available via Doctor).

Was this useful?

◆ AI Coding Agents

SST OpenCode

v1.3.4 NOTES

The open source coding agent.

OpenCode v1.3.4 adds prompt slots, TUI plugins, AI SDK v6 support, and a GPT system prompt modeled after Codex CLI.

└──▷ GET THIS VERSION

$ git clone --branch v1.3.4 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.3.4

›Adds prompt slot feature for structured prompt composition.
›Adds TUI plugins support, enabling terminal UI extensibility.
›Adds support for AI SDK v6.
›Adds a GPT system prompt so non-Codex GPT models follow a Codex CLI-style prompt.
›Adds model variant selection dialog in TUI instead of cycling through variants.

+6 moreshow less

›Adds single target plugin entrypoints.
›Improves app startup performance.
›Closes MCP transport on failed or timed-out connections.
›Desktop: persists queued followups across project switches.
›Desktop: uses Azure Artifact Signing for Windows releases.
›Desktop: resizes layout viewport when mobile keyboard appears.

Was this useful?

Earendil Works Pi

v0.64.0 2 RELEASES · 2026-03-29 NOTES STABLE

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

Pi v0.64.0 adds a prepareArguments hook for tool schema migration and lets extensions customize the thinking block label.

└──▷ GET THIS VERSION

$ git clone --branch v0.64.0 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:
$ git checkout v0.64.0

└──▷ USE IT

When building an extension that uses chain-of-thought, replace the default collapsed thinking label with a domain-specific one.

typescript

export default function myExtension(ctx) {
  ctx.ui.setHiddenThinkingLabel("[Reasoning hidden — click to expand]");
}

›Adds ToolDefinition.prepareArguments hook so extensions and SDK callers can normalize or migrate raw model arguments before schema validation — enabling compatibility shims for resumed sessions with outdated tool schemas.
›Built-in edit tool uses prepareArguments to silently fold legacy top-level oldText/newText into edits[] when resuming old sessions.
›Adds ctx.ui.setHiddenThinkingLabel() so extensions can customize the collapsed thinking block label shown in interactive mode.

└──▷ BREAKING ON UPGRADE

!ModelRegistry no longer has a public constructor; direct new ModelRegistry(...) calls no longer compile. SDK callers and tests must use ModelRegistry.create(authStorage, modelsJsonPath?) for file-backed registries or ModelRegistry.inMemory(authStorage) for built-in-only registries.

1 more release in this issue · 2026-03-29

v0.63.2 NOTES STABLE

Pi v0.63.2 adds ctx.signal to ExtensionContext for propagating cancellation into nested model calls and fetch operations.

└──▷ GET THIS VERSION

$ git clone --branch v0.63.2 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:
$ git checkout v0.63.2

└──▷ TRY IT

Propagate agent turn cancellation into a downstream fetch inside a custom extension handler so it aborts cleanly when the user cancels.

$ // Inside your extension handler
async function myHandler(ctx) {
  const response = await fetch('https://api.example.com/data', {
    signal: ctx.signal
  });
  return response.json();
}

›Adds ctx.signal to ExtensionContext, letting extension handlers forward cancellation into nested model calls, fetch(), and other abort-aware work.

Was this useful?

// END OF TRANSMISSION

The AI Toolchain · curated daily · March 29, 2026
Releases & features from the open-source and commercial AI tools that practitioners actually run.

The AI Toolchain — issue -143, March 29, 2026

OpenClaw

SST OpenCode

Earendil Works Pi