Heads up This site is currently under heavy development.
Subscribe Get it delivered — the daily firehose, filtered to the tools you run, plus the documentation changes vendors never announce. Compare plans →

The AI Toolchain — issue -076, June 4, 2026

THE AI TOOLCHAIN NO. -076
Tail
THE DAILY RELEASE FIREHOSE
PUBLISHED JUNE 4, 2026 · EVERY WEEKDAY
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   # 7 tools matched
AI & LLM Tooling
◆  AI Coding Agents

Anthropic Claude Code

Sources Release notes → v2.1.163 NOTES

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

Claude Code v2.1.163 adds version enforcement settings, /plugin list, hook feedback context, and stdio MCP session IDs.

└──▷ GET THIS VERSION
$ git clone --branch v2.1.163 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:
$ git checkout v2.1.163
└──▷ USE IT
Enforce an approved version range across a managed fleet so users on out-of-range builds are blocked at startup.
json
{
  "requiredMinimumVersion": "2.1.163",
  "requiredMaximumVersion": "2.1.999"
}
Audit which plugins are active in the current session — useful after an update or policy change.
$ /plugin list --enabled
Surface stop-hook diagnostics back to Claude (e.g. a linter summary) so it can react without the run being marked as a hook error.
json
{
  "hookSpecificOutput": {
    "additionalContext": "Linter found 3 warnings in src/main.ts — please review before finishing."
  }
}
  • Adds requiredMinimumVersion and requiredMaximumVersion managed settings to enforce a permitted Claude Code version range, refusing startup if the installed version falls outside it.
  • New /plugin list command lists installed plugins, with --enabled/--disabled filters to narrow results.
  • Adds a 'c to copy' shortcut in /btw that copies the raw markdown answer to the clipboard, preserving formatting on paste.
  • Skills: new \$ escape syntax lets command bodies include a literal $ before a digit.
  • stdio MCP servers now receive the same CLAUDE_CODE_SESSION_ID environment variable as hooks and Bash when using --resume.
+1 moreshow less
  • Background agent sessions now update to a new Claude Code version silently in the background, eliminating cold-restart wait times when reopening a session after an update.
Was this useful?

Cline

Sources Release notes → cli-v3.0.17 NOTES

Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

Cline CLI v3.0.17 adds --allowed-user-id flag to restrict Telegram connector access by user ID.

└──▷ GET THIS VERSION
$ git clone --branch cli-v3.0.17 https://github.com/cline/cline.git
# already have the repo? check out this version:
$ git checkout cli-v3.0.17
  • Adds --allowed-user-id flag to the Telegram connector to restrict which Telegram users are authorized to interact with the agent.
Was this useful?

OpenAI Codex CLI

Sources Release notes → rust-v0.137.0 NOTES

Lightweight coding agent that runs in your terminal

Codex CLI gains F13-F24 keybindings, codex plugin list --json, remote-control pairing RPCs, and multi-agent v2 per-thread runtimes.

└──▷ GET THIS VERSION
$ git clone --branch rust-v0.137.0 https://github.com/openai/codex.git
# already have the repo? check out this version:
$ git checkout rust-v0.137.0
└──▷ TRY IT
Get a machine-readable list of all installed plugins for scripting or audit pipelines.
$ codex plugin list --json
  • Adds F13-F24 function key support in TUI keymaps for extended keyboard bindings.
  • Enables paste in searchable selection menus within the TUI.
  • Adds a compact reasoning-only status/title item to the TUI status surface.
  • Adds codex plugin list --json for machine-readable plugin inventory output.
  • Caches remote plugin catalog suggestions for faster plugin discovery.
+9 moreshow less
  • Adds remote-control pairing start and client management RPCs (list/revoke controller grants) via app-server v2.
  • Shows enterprise monthly credit limits in the status display for admin/enterprise flows.
  • Supports applying cloud-managed config bundles, including EDU workspace accounts.
  • Enables parallel standalone web search calls in code-mode flows.
  • Exposes standalone image generation and hosted web/image tools in code-only mode.
  • Multi-agent v2 keeps runtime choice per-thread and exposes cleaner follow-up and metadata defaults for spawned agents.
  • Adds skills extension scaffold with per-turn catalog resolution and v1 prompt injection.
  • Keys request-permission grants by environment identity for scoped approvals.
  • Exports readable CA bundles to child commands when managed MITM proxying is active.
└──▷ BREAKING ON UPGRADE
  • !The persist_extended_history bool flag is removed from app-server (the experimental flag no longer exists).
  • !The multi-agent v2 assign_task field is renamed to followup_task.
  • !hide_spawn_agent_metadata now defaults to true, changing the default metadata visibility for spawned agents.
Was this useful?

Earendil Works Pi

Sources Release notes → v0.78.1 NOTES

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

Pi v0.78.1 adds Ant Ling, NVIDIA NIM, and MiniMax-M3 provider support plus richer extension context APIs.

└──▷ GET THIS VERSION
$ git clone --branch v0.78.1 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:
$ git checkout v0.78.1
└──▷ USE IT
Adapt an extension's behavior based on whether Pi is running in TUI, RPC, JSON, or print mode — for example, suppressing interactive prompts in JSON mode.
javascript
// Inside an extension command handler
if (ctx.mode === 'json') {
  // emit structured output only
} else {
  // render rich TUI output
}
Inspect the current base system prompt inputs from within an extension command to tailor or augment the prompt context.
javascript
// Inside an extension command handler
const promptOptions = ctx.getSystemPromptOptions();
console.log(promptOptions);
  • Adds Ant Ling provider selection and setup support.
  • Adds NVIDIA NIM provider selection, setup, and direct NIM request attribution headers.
  • Adds MiniMax-M3 model support for the minimax and minimax-cn direct providers.
  • Adds ctx.mode to extension contexts so extensions can distinguish TUI, RPC, JSON, and print modes.
  • Adds ctx.getSystemPromptOptions() for extension commands to inspect current base system prompt inputs.
+1 moreshow less
  • Adds containerization documentation and a Gondolin extension example for routing built-in tools into a local micro-VM.
Was this useful?
◆  AI Model & Data Infrastructure

Ollama

Sources Release notes → v0.30.5 NOTES

Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

ollama launch hermes-desktop skips rebuilds on installed apps; native Windows support added for ollama launch hermes.

└──▷ GET THIS VERSION
$ git clone --branch v0.30.5 https://github.com/ollama/ollama.git
# already have the repo? check out this version:
$ git checkout v0.30.5
└──▷ TRY IT
Launch Hermes Desktop on a machine where it's already installed, bypassing a slow rebuild step.
$ ollama launch hermes-desktop
Install and launch the Hermes assistant on a native Windows system using the PowerShell installer path.
$ ollama launch hermes
  • Supports skipping rebuild in ollama launch hermes-desktop when a packaged desktop app is already installed.
  • Enables native Windows installs via the Hermes PowerShell installer with ollama launch hermes.
Was this useful?
◆  Local LLM Runtimes

llama.cpp

Sources Release notes → b9499 NOTES

llama.cpp b9499 refactors WebGPU FlashAttention and standardizes quantization support for k/v tensors on the tile path.

└──▷ GET THIS VERSION
$ git clone --branch b9499 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9499
  • Refactors the WebGPU FlashAttention implementation with split k/v quantization and abstracted quantization logic shared between flash_attn and mul_mat operations.
  • Adds quantization support to the WebGPU tile path for FlashAttention, broadening the model formats that can run accelerated attention on WebGPU backends.
Was this useful?
Other / Uncategorized
◆  VECTOR DB RAG

LanceDB

Sources Release notes → python-v0.33.1-beta.2 2 RELEASES · 2026-06-04 NOTES STABLE

LanceDB python-v0.33.1-beta.2 adds DataFusion expression support for merge insert predicates.

└──▷ GET THIS VERSION
$ git clone --branch python-v0.33.1-beta.2 https://github.com/lancedb/lancedb.git
# already have the repo? check out this version:
$ git checkout python-v0.33.1-beta.2
  • Supports DataFusion expressions as predicates in merge insert operations, enabling richer conditional logic when upserting records.
1 more release in this issue · 2026-06-04
v0.30.1-beta.2 NOTES STABLE

LanceDB v0.30.1-beta.2 adds DataFusion expression support for merge insert predicates in Rust.

└──▷ GET THIS VERSION
$ git clone --branch v0.30.1-beta.2 https://github.com/lancedb/lancedb.git
# already have the repo? check out this version:
$ git checkout v0.30.1-beta.2
  • Supports DataFusion expressions as predicates in merge insert operations via the Rust API.
Was this useful?
my-toolchain — 0 tools
paste an install list to detect your tools

A brew list, a Brewfile, requirements.txt, a Dockerfile — or just the product names, free-form. Nothing leaves your browser.

    browse all tools →