The AI Toolchain — issue -175, February 23, 2026

GitHub Copilot CLI v0.0.415 adds model field for custom agents, show_file tool, and overhauled /mcp show grouping

$ git clone --branch v0.0.415 https://github.com/github/copilot-cli.git
# already have the repo? check out this version:
$ git checkout v0.0.415

$ /plugin install "/Users/analyst/My Plugins/vuln-scanner"

• ›Adds model field to custom agent configuration, letting practitioners specify which model powers a given agent.
• ›Adds show_file tool for presenting code and diffs to the user inline during a session.
• ›Adds /plugin marketplace add and /plugin install support for local paths that contain spaces.
• ›Upgrades /mcp show to group servers into User, Workspace, Plugins, and Built-in sections with full keyboard navigation.
• ›Plan approval menu now surfaces model-curated actions with a recommended option highlighted first, including autopilot+fleet for parallelizable work.

OpenAI Agents SDK v0.10.0 adds opt-in WebSocket mode for the Responses API with a reusable session helper.

$ git clone --branch v0.10.0 https://github.com/openai/openai-agents-python.git
# already have the repo? check out this version:
$ git checkout v0.10.0

import asyncio
from agents import Agent, responses_websocket_session

async def main():
    agent = Agent(name="Assistant", instructions="Be concise.")
    async with responses_websocket_session() as ws:
        first = ws.run_streamed(agent, "Say hello in one short sentence.")
        async for _event in first.stream_events():
            pass

        second = ws.run_streamed(
            agent,
            "Now say goodbye.",
            previous_response_id=first.last_response_id,
        )
        async for _event in second.stream_events():
            pass

asyncio.run(main())

• ›Adds set_default_openai_responses_transport('websocket') to switch all Responses API calls to WebSocket mode globally.
• ›Adds responses_websocket_session() async context manager for a reusable WebSocket connection across multiple streamed agent runs.
• ›Adds use_responses_websocket=True parameter to OpenAIProvider to enable WebSocket mode per-provider.

Your own personal AI assistant. Any OS.

OpenClaw v2026.2.22 adds Mistral provider support, Synology Chat channel, multilingual FTS memory, and a new --dry-run updater CLI.

$ git clone --branch v2026.2.22 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.22

$ openclaw update --dry-run

• ›Adds Mistral provider integration with memory embeddings and voice support.
• ›Adds native Synology Chat channel plugin with webhook ingress, DM routing, outbound send/media, per-account config, and DM policy controls.
• ›Adds optional built-in auto-updater (update.auto.*) with stable rollout delay/jitter and beta hourly cadence, default-off.
• ›Adds openclaw update --dry-run to preview channel/tag/target/restart actions without mutating config or installing.
• ›Adds Spanish and Portuguese stop-word filtering for FTS-only memory query expansion.

PydanticAI v1.63.0 adds args_validator for tools, Gemini 2.5 Pro Preview support, and Gemini logprob output.

$ git clone --branch v1.63.0 https://github.com/pydantic/pydantic-ai.git
# already have the repo? check out this version:
$ git checkout v1.63.0

• ›Adds args_validator parameter to tool definitions for pre-execution argument validation before a tool runs.
• ›Adds logprob support for Gemini models.

browser-use 0.11.12 adds Browser.from_system_chrome() for connecting to an already-running Chrome instance.

$ git clone --branch 0.11.12 https://github.com/browser-use/browser-use.git
# already have the repo? check out this version:
$ git checkout 0.11.12

• ›Adds Browser.from_system_chrome() class method to connect browser-use to an already-running system Chrome installation, enabling real-browser and authenticated-session workflows.

llama.cpp b8132: CLI now passes the model's text filename to the model context.

$ git clone --branch b8132 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b8132

• ›The CLI provides the model with its text filename, giving the model awareness of the file it was loaded from.

LanceDB python-v0.30.0-beta.1 adds background dataset update checks.

$ git clone --branch python-v0.30.0-beta.1 https://github.com/lancedb/lancedb.git
# already have the repo? check out this version:
$ git checkout python-v0.30.0-beta.1

• ›Adds background checking for dataset updates, enabling tables to stay consistent without blocking the main thread.

$ git clone --branch v0.27.0-beta.1 https://github.com/lancedb/lancedb.git
# already have the repo? check out this version:
$ git checkout v0.27.0-beta.1

Langfuse v3.155.1 adds an experiments section with routing and admin controls, plus evaluation prompt hover previews.

$ git clone --branch v3.155.1 https://github.com/langfuse/langfuse.git
# already have the repo? check out this version:
$ git checkout v3.155.1

• ›Adds experiments pages with routing and admin flag checks for access control.
• ›Shows evaluation prompts on hover in the evals UI for quick inspection without leaving the page.
• ›Improves chart loading states and failure hints in the web UI for clearer feedback when dashboards fail to load.
• ›Passes v2 metrics version to custom dashboard widgets, enabling accurate metric versioning in user-defined dashboard views.