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 -058, June 22, 2026

THE AI TOOLCHAIN NO. -058
Tail
THE DAILY RELEASE FIREHOSE
PUBLISHED JUNE 22, 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   # 5 tools matched
AI & LLM Tooling
◆  AI Coding Agents

Anthropic Claude Code

Sources Release notes → v2.1.186 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 v2.1.186 adds CLI MCP auth, bash auto-response, SSH-friendly headless login, and richer workflow/plugin views.

└──▷ GET THIS VERSION
$ git clone --branch v2.1.186 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:
$ git checkout v2.1.186
└──▷ TRY IT
Authenticate a named MCP server over SSH without a browser pop-up.
$ claude mcp login my-server --no-browser
Keep the old context-only behavior for bash commands instead of having Claude auto-reply to their output.
json
# settings.json
{ "respondToBashCommands": false }
  • Adds claude mcp login <name> and claude mcp logout <name> to authenticate MCP servers directly from the CLI, with --no-browser stdin redirect for SSH sessions.
  • Adds ! bash command auto-response: Claude now automatically replies to bash command output; disable with "respondToBashCommands": false in settings.json.
  • Adds status filtering (press f) to the /workflows agent detail view.
  • Adds a 'Skills' section to the /plugin Installed tab.
  • Adds teammateMode: "iterm2" setting with a warning when auto mode cannot find the it2 CLI.
+6 moreshow less
  • Adds 'Claude Platform on AWS - refresh credentials' option to /login when awsAuthRefresh is configured.
  • Background subagents now surface permission prompts in the main session instead of auto-denying, showing which agent is asking; Esc denies just that tool.
  • Improves memory: the agent is now reminded to compact its MEMORY.md index when nearing the size limit.
  • Improves skill frontmatter to accept display-name, default-enabled, fallback, and metadata.* keys in kebab-case, snake_case, and camelCase.
  • Improves malformed SKILL.md YAML frontmatter handling: loads the skill body with empty metadata instead of failing silently.
  • Changes /review <pr> to use the same review engine as /code-review medium.
└──▷ BREAKING ON UPGRADE
  • !CLAUDE_CODE_MAX_RETRIES is now capped at 15; unattended sessions that relied on higher values must switch to CLAUDE_CODE_RETRY_WATCHDOG instead.
Was this useful?

OpenAI Codex CLI

Sources Release notes → rust-v0.142.0 NOTES

Lightweight coding agent that runs in your terminal

Codex CLI gains indexed web search, rollout token budgets, multi-agent delegation controls, plugin sections, and scheduled time reminders.

└──▷ GET THIS VERSION
$ git clone --branch rust-v0.142.0 https://github.com/openai/codex.git
# already have the repo? check out this version:
$ git checkout rust-v0.142.0
  • Adds /usage command support for viewing and redeeming earned usage-limit reset credits, with confirmation, retry, and refreshed availability states.
  • Organizes /plugins remote plugins into OpenAI Curated, Workspace, and Shared with me sections; eligible turns can now recommend and install relevant plugins.
  • Introduces configurable rollout token budgets that track usage across agent threads, surface remaining-budget reminders, and abort turns when the budget is exhausted.
  • Enables app-server clients to configure multi-agent delegation as disabled, explicit-request-only, or proactive at both the thread and turn level.
  • Adds an indexed web-search mode that allows live searches while restricting direct page access to server-approved URLs.
+1 moreshow less
  • Supports scheduled UTC time reminders and direct current-time queries, including through client-provided app-server clocks.
Was this useful?

Earendil Works Pi

Sources Release notes → v0.79.10 NOTES

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

Pi v0.79.10 adds compaction event context for extensions and a more predictable pi update flow.

└──▷ GET THIS VERSION
$ git clone --branch v0.79.10 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:
$ git checkout v0.79.10
└──▷ USE IT
React differently in an extension based on whether compaction was triggered manually or by an overflow retry.
javascript
// In your extension handler:
on('session_before_compact', ({ reason, willRetry }) => {
  if (reason === 'overflow' && willRetry) {
    console.log('Overflow compaction — another attempt will follow');
  } else if (reason === 'manual') {
    console.log('User triggered /compact manually');
  }
});
Upgrade Pi to the exact version the update check resolves, with the changelog URL shown in the notice.
$ pi update
  • Adds reason and willRetry fields to session_before_compact and session_compact extension events, letting extensions distinguish manual /compact, threshold auto-compaction, and overflow retry flows.
  • Enhances pi update to install the exact checked Pi version and display the changelog URL in update notices for more predictable upgrades.
Was this useful?
◆  Local LLM Runtimes

llama.cpp

Sources Release notes → b9763 3 RELEASES · 2026-06-22 NOTES STABLE

llama.cpp server now includes an id field in tool call responses.

└──▷ GET THIS VERSION
$ git clone --branch b9763 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9763
  • Adds id field to tool call responses in the server API, enabling callers to correlate tool call requests and responses.
2 more releases in this issue · 2026-06-22
b9761 NOTES STABLE

llama.cpp server gains real-time model download progress tracking via a new /models/sse SSE endpoint.

└──▷ GET THIS VERSION
$ git clone --branch b9761 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9761
└──▷ TRY IT
Stream live model download progress from the server without polling — useful in CI pipelines or admin dashboards that need to know when a model is ready.
$ curl -N http://localhost:8080/models/sse
  • Adds /models/sse Server-Sent Events endpoint to the llama.cpp server for real-time model load and download progress tracking.
  • Moves model downloading to a dedicated child process in the server router, isolating download work from the main server process.
b9760 NOTES STABLE

llama.cpp b9760 generalizes the server input file schema to support input_video and raw base64 intake.

└──▷ GET THIS VERSION
$ git clone --branch b9760 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9760
  • Adds input_video field to the server input file schema, enabling video input alongside existing file types.
  • Server now accepts raw base64-encoded input directly in the input file schema.
Was this useful?
Other / Uncategorized
◆  AI OBSERVABILITY

Arize Phoenix

Sources Release notes → arize-phoenix-v17.10.0 NOTES

Phoenix v17.10.0 surfaces trace-level annotations directly in the trace header UI.

└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-v17.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.10.0
  • Trace-level annotations are now displayed in the trace header, making annotation context visible without navigating into individual spans.
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 →