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.
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 v2.1.9 adds auto:N MCP threshold syntax, plansDirectory setting, external editor in prompts, and richer hook/skill APIs.
└──▷ GET THIS VERSION
$ git clone --branch v2.1.9 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:$ git checkout v2.1.9
└──▷ USE IT
Store plan files in a project-local directory so plans are version-controlled alongside your code.
json
# In your Claude Code settings (settings.json)
{ "plansDirectory": ".claude/plans" }
Inject the current session ID into a skill command so downstream scripts can correlate activity back to the Claude session.
json
# In a skill definition
{ "command": "my-audit-tool --session ${CLAUDE_SESSION_ID}" }
›Adds auto:N syntax to set the MCP tool search auto-enable threshold as a context window percentage (0–100).
›Adds plansDirectory setting to customize where plan files are stored.
›Adds external editor support (Ctrl+G) inside AskUserQuestion "Other" input fields.
›Adds session URL attribution to commits and PRs created from web sessions.
›Enables PreToolUse hooks to return additionalContext directly to the model.
+1 moreshow less
›Adds ${CLAUDE_SESSION_ID} string substitution so skills can access the current session ID.
Lightweight coding agent that runs in your terminal
Codex CLI v0.87.0 adds multi-ID collaboration waits, user-snapshot shell execution, and TUI approval surfacing for spawned threads.
└──▷ GET THIS VERSION
$ git clone --branch rust-v0.87.0 https://github.com/openai/codex.git
# already have the repo? check out this version:$ git checkout rust-v0.87.0
›Enables collaboration wait calls to block on multiple IDs in a single request, simplifying multi-thread coordination.
›Runs user shell commands under the user snapshot so aliases and shell config are honored.
›Surfaces approval requests from spawned/unsubscribed threads directly in the TUI.
›Adds user message metadata (text elements and byte ranges) round-tripping through protocol, app-server, and core so UI annotations survive history rebuilds.
Codex CLI adds SKILL.toml metadata support and explicit web search disable control.
└──▷ GET THIS VERSION
$ git clone --branch rust-v0.86.0 https://github.com/openai/codex.git
# already have the repo? check out this version:$ git checkout rust-v0.86.0
└──▷ TRY IT
Define skill metadata for your project so it appears correctly in the Codex TUI and app server.
$ # Place SKILL.toml at your project root:
cat SKILL.toml
# name = "My Skill"
# description = "Does X and Y"
# icon = "🔍"
# brand_color = "#FF6600"
# default_prompt = "Start by summarizing the repo."
›Adds SKILL.toml support for defining skill metadata (names, descriptions, icons, brand color, default prompt) surfaced in the app server and TUI.
›Enables clients to explicitly disable web search and signal eligibility via a header to align with server-side rollout controls.
Pi v0.47.0 adds OpenAI Codex support, an extension input-intercept event, and Tree mode filter shortcuts.
└──▷ GET THIS VERSION
$ git clone --branch v0.47.0 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:$ git checkout v0.47.0
└──▷ TRY IT
Run Pi against OpenAI's Codex models for allowlisted environments with prompt caching across turns.
$ OPENAI_API_KEY=<your-key> pi --provider openai-codex 'Review this file for hardcoded credentials' src/config.ts
›Adds OpenAI Codex provider support (gpt-5.1, gpt-5.2, gpt-5.1-codex-mini, gpt-5.2-codex) with prompt caching via session ID and reasoning signature retention across turns — enable with --provider openai-codex.
›New pi-internal:// URL scheme in the read tool lets the model access internal coding-agent documentation, READMEs, and examples directly.
›New input event in the extension system allows intercepting, transforming, or fully handling user input before the agent processes it, with result types continue, transform, and handled.
›Adds input-transform.ts extension example demonstrating input interception patterns including quick mode, instant commands, and source routing.
›Custom tool HTML export: extensions implementing renderCall/renderResult now render with ANSI-to-HTML color conversion in /share and /export output.
+2 moreshow less
›Direct filter shortcuts in Tree mode: Ctrl+D (default), Ctrl+T (no-tools), Ctrl+U (user-only), Ctrl+L (labeled-only), Ctrl+A (all).
›Skill commands (/skill:name) now expand in AgentSession, enabling their use in RPC and print modes and allowing the input event to intercept them before expansion.
└──▷ BREAKING ON UPGRADE
!Extensions using Editor directly must now pass TUI as the first constructor argument: new Editor(tui, theme). The tui parameter is available in extension factory functions.
LangChain 1.2.5 updates the summarization prompt for improved results.
└──▷ GET THIS VERSION
$ git clone --branch langchain==1.2.5 https://github.com/langchain-ai/langchain.git
# already have the repo? check out this version:$ git checkout langchain==1.2.5
›Updates the summarization prompt with new default wording.
OpenAI Agents SDK v0.6.7 adds experimental Codex tool integration and enforces max_output_length on shell tool outputs.
└──▷ GET THIS VERSION
$ git clone --branch v0.6.7 https://github.com/openai/openai-agents-python.git
# already have the repo? check out this version:$ git checkout v0.6.7
└──▷ USE IT
Let an agent delegate coding tasks to Codex CLI on the host machine without any extra configuration.
python
from agents import Agent, Runner
from agents.extensions.experimental.codex import codex_tool
agent = Agent(
name="codex-agent",
tools=[codex_tool()],
)
result = Runner.run_sync(agent, "Refactor this function to use async/await")
print(result.final_output)
›Adds codex_tool() from agents.extensions.experimental.codex — an experimental tool that runs the Codex CLI as a subprocess, making all existing Codex configuration, skills, and capabilities available to agents without additional setup.
›Enforces max_output_length for shell tool outputs, capping runaway output from subprocess-based tools.
›Adds remoteCdpTimeoutMs and remoteCdpHandshakeTimeoutMs settings to tune remote CDP reachability timeouts.
›Preserves auth and query tokens for remote CDP endpoints and passes Basic auth for CDP HTTP/WS connections.
›Adds bidirectional Telegram reaction support with configurable notifications and agent guidance.
›Allows custom commands in the Telegram bot menu, merged with native commands.
›Adds system.which tool on macOS for prompt-free remote skill discovery with gateway fallback to system.run.
›Normalizes Slack/Discord message timestamps with timestampMs and timestampUtc fields while retaining raw provider fields.
›Adds a Current Date & Time system prompt section with configurable time format (auto/12/24) for agents.
›Debounces rapid inbound messages across channels with per-connector override support.
›Allows media-only sends via CLI/tool and shows Telegram voice recording status for voice notes.
›Surfaces provider usage headers in /status endpoint and clawdbot models status command.
›Microsoft Teams is now a plugin; must be installed via clawdbot plugins install @clawdbot/msteams.
›Supports CLAWDBOT_STATE_DIR environment variable for Windows task scripts.
›TUI now shows provider/model labels for the active session and default model.
›Allows Discord emoji and sticker uploads and channel actions in config defaults.
›Allows allowlisted Discord guilds without channel lists to receive messages when groupPolicy="allowlist".
›Auto-infers SSH targets in gateway status using ssh-config awareness on macOS.
└──▷ BREAKING ON UPGRADE
!iOS minimum version is now 18.0 (was lower); setups targeting older iOS versions will break.
!Microsoft Teams integration is now a plugin — existing setups will break until @clawdbot/msteams is installed via clawdbot plugins install @clawdbot/msteams.
llama.cpp b7756 replaces minja with a new built-from-scratch Jinja template engine for chat template rendering.
└──▷ GET THIS VERSION
$ git clone --branch b7756 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:$ git checkout b7756
›Introduces a new built-in Jinja template engine (lexer, parser, and runtime) in common, replacing the prior minja dependency — supports filters (selectattr, rejectattr, split/rsplit with maxsplit, trim with args, tojson with separators and indent), keyword arguments, array slicing, macros, and lstrip_block behavior matched to Hugging Face JS semantics.
›Adds support for rendering chat templates for additional model families including Gemma, MiniMax, GLM-4.5, Kimi-K2, Nemotron, IBM Granite, and Apertus through the new engine.
›Extends test-chat-template to consolidate Jinja rendering tests (absorbing the former test-chat-jinja target) with an --output flag for inspecting rendered results.
›Adds a fuzz test target for the Jinja engine covering both template rendering and function argument handling.
└──▷ BREAKING ON UPGRADE
!minja is removed and its call sites are replaced by the new Jinja runtime; any build or code that depended on minja headers or the test-chat-jinja CMake target will break.
!The test-chat-jinja CMake target is removed; tests previously run through it now run under test-chat-template.
THE AI TOOLCHAIN