The AI Toolchain — issue -180, February 18, 2026

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 v2.1.47 adds new hook fields, keybindings, statusline data, and smarter background-agent lifecycle controls.

$ git clone --branch v2.1.47 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:
$ git checkout v2.1.47

$ # While Claude Code is running, press ctrl+f to terminate all background agents instantly.

• ›Adds last_assistant_message field to Stop and SubagentStop hook inputs, letting hooks read the final assistant response without parsing transcript files.
• ›Adds chat:newline keybinding action for configurable multi-line input.
• ›Adds added_dirs to the statusline JSON workspace section, exposing directories added via /add-dir to external scripts.
• ›New ctrl+f shortcut kills all background agents; pressing ESC now cancels only the main thread while background agents keep running, giving finer control over agent lifecycle.
• ›The /rename command now also updates the terminal tab title.

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

Cline CLI gains a /skills slash command for viewing and managing installed skills.

$ git clone --branch v3.65.0 https://github.com/cline/cline.git
# already have the repo? check out this version:
$ git checkout v3.65.0

$ /skills

• ›Adds /skills slash command to the CLI for viewing and managing installed skills.

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Goose v1.25.0 adds macOS sandboxing, unified summon extension, Claude Code streaming, MCP support for agentic CLI providers, and SLSA build provenance.

$ git clone --branch v1.25.0 https://github.com/block/goose.git
# already have the repo? check out this version:
$ git checkout v1.25.0

• ›Runs Goose Desktop inside a macOS sandbox for enhanced security isolation.
• ›Introduces a unified summon extension, replacing the separate subagent and skills extensions.
• ›Integrates MCP Apps UI via AppRenderer from the @mcp-ui/client SDK with fallback request handler support.
• ›Enables editing a recipe's model and extensions directly in the desktop GUI.
• ›Allows recipes to specify their own provider and model via recipe config.

Lightweight coding agent that runs in your terminal

Codex CLI gains WebSocket proxy support, thread archive notifications, and distinct command approval IDs.

$ git clone --branch rust-v0.104.0 https://github.com/openai/codex.git
# already have the repo? check out this version:
$ git checkout rust-v0.104.0

$ WS_PROXY=ws://proxy.corp.example.com:3128 codex

• ›Supports WS_PROXY/WSS_PROXY environment variables (and lowercase variants) for proxying WebSocket connections through the network proxy.
• ›App-server v2 now emits notifications when threads are archived or unarchived, so clients can react to state changes without polling.
• ›Core and protocol layers now carry distinct approval IDs per command approval, enabling multiple approvals within a single shell command execution flow.

OpenHands: AI-Driven Development

OpenHands 1.4.0 adds MiniMax-M2.5 model support.

$ git clone --branch 1.4.0 https://github.com/All-Hands-AI/OpenHands.git
# already have the repo? check out this version:
$ git checkout 1.4.0

• ›Adds MiniMax-M2.5 as a supported LLM backend.

Qwen Code v0.10.5 adds qwen3.5-plus model support for the Coding Plan feature.

$ git clone --branch v0.10.5 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.10.5

• ›Adds qwen3.5-plus as a supported model for the Coding Plan workflow.

$ git clone --branch v0.10.4-preview.0 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.10.4-preview.0

Zed v0.224.4 adds split diffs, LSP semantic tokens, per-tool Agent permissions, and folding range support.

$ git clone --branch v0.224.4 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.224.4

// In your language-specific settings block, e.g. for TypeScript:
{
  "languages": {
    "TypeScript": {
      "lsp_folding_ranges": "on"
    }
  }
}

{
  "global_lsp_settings": {
    "request_timeout": 30
  }
}

• ›Adds per-tool permission settings for the Agent, including regex-based rules for auto-allow, auto-deny, or always-require-confirmation on individual tools.
• ›Adds textDocument/foldingRange LSP support; set "lsp_folding_ranges": "on" in language settings to fetch and prefer LSP folds.
• ›Adds global_lsp_settings.request_timeout setting to configure the maximum timeout duration for LSP-related operations.
• ›Adds tab_switcher::OpenInActivePane action for a more vim-like tab switching experience.
• ›Adds alt-l as an alternate keybinding for agent::CycleFavoriteModels on Linux and Windows.

An open-source AI agent that brings the power of Gemini directly into your terminal.

gemini-cli v0.29.0 adds a /plan slash command, MCP admin allowlists, agent skill linking, Vim motions, and WebSocket network logging.

$ git clone --branch v0.29.0 https://github.com/google-gemini/gemini-cli.git
# already have the repo? check out this version:
$ git checkout v0.29.0

$ /plan Refactor the authentication module to use JWT tokens

$ gemini mcp list

• ›Adds /plan slash command to enter an interactive planning mode before execution.
• ›Adds enter_plan_mode tool so the agent can autonomously switch into plan mode.
• ›Supports the replace tool inside plan mode to edit plans in-place.
• ›Supports MCP servers within plan mode.
• ›Implements admin allowlist for MCP server configurations, now also applied to extensions.

KoboldCpp v1.108.2 adds Ollama /api/show emulation, image gen up to 2048x2048, multiple image LoRA support, and autofit improvements.

$ git clone --branch v1.108.2 https://github.com/LostRuins/koboldcpp.git
# already have the repo? check out this version:
$ git checkout v1.108.2

$ curl http://localhost:5001/api/show -d '{"name": "my-model"}'

• ›Adds Ollama /api/show endpoint emulation, extending API compatibility for tools that expect an Ollama-compatible server.
• ›Autofit is now triggered when -1 gpulayers (the default) is selected and no tensor splits or tensor overrides are set; setting explicit GPU layers overrides this behavior.
• ›--autofit mode now hides the GUI layers selector to reduce confusion when autofit is active.
• ›Autofit toggle is now accessible from the Quick Launch menu.
• ›Allows the Image Gen soft limit to be overridden up to 2048x2048 resolution when the user explicitly chooses to do so.

llama.cpp server now saves generated text in /slots endpoint when LLAMA_SERVER_SLOTS_DEBUG=1

$ git clone --branch b8094 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b8094

• ›Sets LLAMA_SERVER_SLOTS_DEBUG=1 to enable saving generated text in the /slots endpoint for server-side slot inspection and debugging.

$ git clone --branch b8091 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b8091

$ git clone --branch b8093 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b8093

LangChain text-splitters 1.1.1 adds model_kwargs support to SentenceTransformersTokenTextSplitter.

$ git clone --branch langchain-text-splitters==1.1.1 https://github.com/langchain-ai/langchain.git
# already have the repo? check out this version:
$ git checkout langchain-text-splitters==1.1.1

• ›Adds model_kwargs parameter to SentenceTransformersTokenTextSplitter, allowing callers to pass model-level arguments (e.g. device, trust_remote_code) directly to the underlying SentenceTransformers model at initialization.

LlamaIndex v0.14.15 adds multimodal prompt templates, AgentMesh trust layer, LayoutIR reader, OCI streaming, and more integrations.

$ git clone --branch v0.14.15 https://github.com/run-llama/llama_index.git
# already have the repo? check out this version:
$ git checkout v0.14.15

• ›Adds llama-index-agent-agentmesh [0.1.0], a new trust layer integration for LlamaIndex agents via AgentMesh.
• ›Adds multimodal prompt templates and a multimodal chat prompt helper to llama-index-core, enabling template variable formatting across multimodal types.
• ›Adds retry and error handling to BaseExtractor in llama-index-core.
• ›Adds support for the /predictWithStream endpoint in llama-index-llms-oci-data-science [1.0.0] for streaming use cases.
• ›Adds support for custom span processors in llama-index-observability-otel [0.3.0], with improved OpenTelemetry data serialization via dict flattening; refactored to use llama-index-instrumentation instead of llama-index-core.

Your own personal AI assistant. Any OS.

OpenClaw v2026.2.17 adds 1M-context Anthropic support, Slack streaming, Discord slash commands, cron webhooks, and dozens of new platform capabilities.

$ git clone --branch v2026.2.17 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.17

$ openclaw cron add --schedule "0 * * * *" --stagger 90s --delivery.mode webhook --webhook https://example.com/hook "Summarize overnight alerts"

• ›Adds opt-in 1M context beta header for Anthropic Opus/Sonnet via params.context1m: true (maps to anthropic-beta: context-1m-2025-08-07).
• ›Supports Anthropic Claude Sonnet 4.6 (anthropic/claude-sonnet-4-6) with forward-compat fallback to Sonnet 4.5.
• ›Adds /subagents spawn chat command for deterministic subagent activation.
• ›Adds iOS share extension forwarding shared URL/text/image content directly to gateway agent.request with delivery-route fallback and optional receipt acknowledgements.
• ›Adds iOS Talk Mode Background Listening toggle to keep Talk Mode active while the app is backgrounded.

PydanticAI v1.61.0 adds Python 3.14 support and Claude Sonnet 4.6 via updated Anthropic SDK.

$ git clone --branch v1.61.0 https://github.com/pydantic/pydantic-ai.git
# already have the repo? check out this version:
$ git checkout v1.61.0

• ›Supports Python 3.14.
• ›Adds Claude Sonnet 4.6 model availability via Anthropic SDK upgrade to 0.80.0.

Phoenix 13.1.0 adds session skills, dynamic markdown chat rendering, model display in evaluator details, and column resizing in evaluator tables.

$ git clone --branch arize-phoenix-v13.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.1.0

• ›Merges the phoenix-sdk-python skill into phoenix-evals, consolidating skill capabilities into the evals package.
• ›Adds session skills support via the new skills system, enabling skill-based session workflows.
• ›Adds model information display to evaluator details in the UI.
• ›Adds column resizing support to EvaluatorsTable and DatasetEvaluatorsTable for improved data exploration.
• ›Renders session chat using dynamic markdown content, enabling richer chat display in the session view.