Codex: Refreshable OpenTelemetry HTTP Headers
Codex now automatically refreshes authentication headers for OpenTelemetry HTTP exporters, ensuring continuous telemetry without token expiration issues.
Loading launches from 4 labs
Topic
Writing, reviewing or running code; coding assistants and IDE features
Codex now automatically refreshes authentication headers for OpenTelemetry HTTP exporters, ensuring continuous telemetry without token expiration issues.
OpenAI released GPT-6.2 Astra for complex reasoning and GPT-6.2 Sol for everyday coding, both supporting the Responses and Chat Completions APIs.
Astra for Law is a legal intelligence tool that ranked first in evaluations across 24 areas of law. ChatGPT Enterprise customers can now request access.
Codex 0.169.0 introduces an opt-in Cloud connection to the terminal on macOS and Linux. Users can send images, select models and reasoning effort, and archive or restore Cloud conversations directly from the terminal.
OpenAI's Codex terminal workspace now lets users search through older agent tasks by name, prompt preview, or working directory.
Claude Code adds an experimental opt-in Code Mode where Claude writes JavaScript to call its tools.
OpenAI Codex 0.167.2 now sends tool updates incrementally by default when using Google Cloud Vertex AI. Users can opt out of this behavior in their configuration file.
AlphaProof Code agents generated 3 million lines of Lean proofs to formally verify Signal's core encryption protocols.
Gemini CLI v0.68.0 introduces a new extension validation command with evaluation tests to help developers verify their extensions work correctly.
OpenAI Supply Co. releases a retro handheld console with a Codex plugin for designing, animating, and playtesting games directly on the device.
Claude Code's remote-control command now accepts a --settings file flag that applies configuration to every session it starts. Changes to the file require a restart to take effect.
New CLI command identifies latency bottlenecks in Claude API code and tests faster configurations against your evals.
A new `permissions.denyInsteadOfPrompting` setting automatically denies tool calls that would otherwise pause for permission prompts, letting the turn continue without interruption.

OpenAI's GPT-6 Cyber model investigates vulnerabilities, reproduces them in authorized test environments, and verifies fixes. It is trained to stay within authorized scope.

Google's strongest frontier reasoning model for cybersecurity, long-horizon coding, and scientific research. It leads key vulnerability and coding benchmarks with a 1M-token unified context window.

Google announced Gemini 4 Argon, a new AI model featuring advanced reasoning, coding, and multimodal performance for complex long-horizon workflows.
Codex 0.169.0 lets users add or edit custom model providers from the terminal, create providers during sign-in, and use device codes for gateways.
Codex 0.169.0 adds support for multiple side-chat tabs in the terminal workspace. Users can navigate between them and restore saved chats after a restart.

Google is previewing /swarm in Google Antigravity, which turns one prompt into a coordinated team of AI agents for complex tasks like architectural design, coding, and auditing, with real-time tracking.
Claude Code now backgrounds MCP tool calls immediately and reports results when they finish, with an option to disable this behavior.