THE AI TOOLCHAIN NO. -183 The daily firehose — everything the toolchain shipped today, already filtered.
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.
$ tct list # 4 tools matched
Agno v2.5.1 adds CodingTools and UserFeedbackTools toolkits for agents.
$ git clone --branch v2.5.1 https://github.com/agno-agi/agno.git # already have the repo? check out this version: $ git checkout v2.5.1
CodingTools toolkit for code-related operations in agents.UserFeedbackTools toolkit for collecting user feedback from within agents.LangChain Anthropic 1.3.3 adds ContextOverflowError and model-profile text I/O fields.
$ git clone --branch langchain-anthropic==1.3.3 https://github.com/langchain-ai/langchain.git # already have the repo? check out this version: $ git checkout langchain-anthropic==1.3.3
from langchain_core.errors import ContextOverflowError
from langchain_anthropic import ChatAnthropic
llm = ChatAnthropic(model='claude-opus-4-5')
try:
result = llm.invoke(very_long_messages)
except ContextOverflowError:
result = llm.invoke(truncated_messages) ContextOverflowError to langchain_core, raised automatically by the Anthropic (and OpenAI) integrations when a request exceeds the model's context window.text_inputs and text_outputs fields to model profiles, enabling finer-grained capability description for models.langchain-openai 1.1.9 adds ContextOverflowError and text_inputs/text_outputs model profile fields
$ git clone --branch langchain-openai==1.1.9 https://github.com/langchain-ai/langchain.git # already have the repo? check out this version: $ git checkout langchain-openai==1.1.9
from langchain_core.exceptions import ContextOverflowError
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(model="gpt-4o")
try:
response = llm.invoke(very_long_messages)
except ContextOverflowError as e:
print(f"Prompt too long for model context: {e}")
# truncate or switch models ContextOverflowError exception class (in langchain_core) raised by OpenAI and Anthropic integrations when a prompt exceeds the model's context window, enabling callers to catch this specific error type.text_inputs and text_outputs fields to model profiles, surfacing structured token-type metadata for models.langchain-standard-tests 1.1.4 adds standard tests for sandbox providers.
$ git clone --branch langchain-standard-tests==1.1.4 https://github.com/langchain-ai/langchain.git # already have the repo? check out this version: $ git checkout langchain-standard-tests==1.1.4
langchain-groq 1.1.2 adds native LangChain image type support for vision inputs to Groq models.
$ git clone --branch langchain-groq==1.1.2 https://github.com/langchain-ai/langchain.git # already have the repo? check out this version: $ git checkout langchain-groq==1.1.2
LangChain Core 1.2.13 adds the langchain-openrouter provider package for OpenRouter integration.
$ git clone --branch langchain-core==1.2.13 https://github.com/langchain-ai/langchain.git # already have the repo? check out this version: $ git checkout langchain-core==1.2.13
langchain-openrouter provider package, enabling OpenRouter as a new LLM provider integration.Your own personal AI assistant. Any OS.
OpenClaw v2026.2.14 adds Telegram poll sending, DM access-control config aliases, Discord exec-approval channel targeting, and browser-container bind mounts.
$ git clone --branch v2026.2.14 https://github.com/openclaw/openclaw.git # already have the repo? check out this version: $ git checkout v2026.2.14
# in your openclaw config
channels:
discord:
execApprovals:
target: channel $ openclaw doctor --fix
openclaw message poll subcommand for Telegram with duration, silent delivery, and anonymity controls.dmPolicy and allowFrom config aliases for Slack/Discord DM access control; legacy dm.policy/dm.allowFrom keys remain supported and openclaw doctor --fix can migrate them.channels.discord.execApprovals.target to route Discord exec approval prompts to a channel, or both DM and channel simultaneously.sandbox.browser.binds to configure browser-container bind mounts independently from exec containers.--debug tracing output.The open source coding agent.
OpenCode v1.2.5 adds Shift+Tab shortcut and GeistMono Nerd Font option to the desktop app.
$ git clone --branch v1.2.5 https://github.com/sst/opencode.git # already have the repo? check out this version: $ git checkout v1.2.5
OpenCode v1.2.4 adds a db command for database inspection and querying plus a clear-notifications action in the desktop UI.
$ git clone --branch v1.2.4 https://github.com/sst/opencode.git # already have the repo? check out this version: $ git checkout v1.2.4
$ opencode db db command for database inspection and querying.