Going to RSA? We’re recording short, 15-minute Microsoft Security podcast conversations live at the conference- focused on real-world practitioner experience. No pitches, no slides, no marketing. Just an honest conversation about what you’re seeing, what’s changed, and what you’d tell a peer. If you’re doing the work and want to share your perspective, we’d love to hear from you.

 

Take the survey to let us know you are interested here!

 

2026-01-29

• Compaction messages show clearer command hints to view checkpoint summaries
• Press Ctrl+X then / to run slash commands without losing your input
• Improve /diff command with better visual indicators and scroll acceleration
• Add /allow-all and /yolo commands to auto-approve all permissions during a session
• Add Copilot option for agent creation wizard to generate name, description, and instructions based on initial agent description
• Add LSP (Language Server Protocol) tool for code intelligence (requires staff flag)
• Sessions get AI-generated names from first message
• Skills remain effective after conversation history is compacted
• /usage now includes token consumption from sub-agents (e.g., the general-purpose agent)
• Support .claude/commands/ single-file commands as simpler alternative to skills
• Skills load correctly on Windows
• Add /diff command to review session changes
• Undo/rewind to previous states with double-Esc

GitHub's new Agents tab centralizes Copilot coding agent sessions in a repository, making it easier to launch tasks, track progress, and review the resulting pull requests in standard tooling such as Visual Studio

On February 13, 2026, alongside the previously announced retirement⁠ of GPT‑5 (Instant, Thinking, and Pro), we will retire GPT‑4o, GPT‑4.1, GPT‑4.1 mini, and OpenAI o4-mini from ChatGPT. In the API, there are no changes at this time.

With Microsoft spending many billions on data centers, and rumors that no one is using its AI, CEO Satya Nadella shared some usage numbers.

Google has added hooks to Gemini CLI, its terminal-based competitor to Anthropic’s Claude Code.

Hooks ensure that Gemini CLI runs a given script or program inside of the agentic loop and bring a larger degree of control to the agentic development loop. These could be used, for example, to run security scanners or compliance checks, log tool interactions, inject relevant information into the context window, or even adjust the model’s parameters on the fly.

As the Gemini CLI team notes in the announcement, “efficiency in the age of agents isn’t just about writing code faster; it’s about building custom tools that adapt to your specific environment.”

While a developer could try to instruct the agent to run a specific script at certain times within the loop in the prompt or AGENTS.md file, given the non-deterministic nature of those agent models, there’s no guarantee that this will actually happen or that the agent won’t forget about this instruction over time.

Claude Code did it first

If this sounds familiar, it’s likely because you already know about Claude Code Hooks, which first introduced this idea last September (though there is also a GitHub issue from July 2025 that proposes this feature). Google’s implementation is not quite a one-to-one match to Anthropic’s, but it should only take a few minutes to adapt an existing Claude hook to Gemini CLI.

Setting up hooks

Like with hooks in Claude Code, Gemini CLI also implements roughly a dozen lifecycle events where a hook can fire. That may be right at the session start, after the user submits a prompt but before the agent starts planning (to add context, for example), before tools are selected (to optimize the tool selection or filter available tools), and similar moments in the agent loop.

The hooks are defined as JSON files that describe when they are invoked and which script they should run. Those scripts are standard Bash scripts and Google notes that it is essential to keep those hooks fast because they do run synchronously and delays in the script will also delay the agent response.

Google recommends that developers use parallel operations and caching when possible to keep the operations fast.

One interesting use case for hooks is to utilize the ‘AfterAgent’ hook, which fires when the agent loop ends, to force the agent into a continuous loop to work on a difficult task — while also refreshing the context between those runs to avoid context rot.

As for security, it’s important to stress that hooks will have the user’s privileges, and Google notes that developers should review the source code of any third-party hooks.

Hooks, which are now available as part of the Gemini CLI v0.26.0 update, can also be packaged inside Gemini CLI extensions. That’s Google’s format for packaging prompts, MCP servers, sub-agents, and agent skills — and now hooks — into a single sharable package.

The post Gemini CLI gets its hooks into the agentic development loop appeared first on The New Stack.