Codex Knowledge Base
The Codex CLI Model Landscape in May 2026: A Practitioner's Routing Guide
Three months ago, Codex CLI users chose between GPT-5-Codex and its Spark variant. Today the model picker lists five production options — six if you count.
Running GPT-OSS with Codex CLI: A Complete Guide to Local Inference via Ollama, LM Studio, and MLX
OpenAI's release of GPT-OSS — two open-weight models under the Apache 2.0 licence — changed the economics of agentic coding overnight.
Goal Mode in Codex CLI: Persistent Objectives, Token Budgets, and the Shift to Agentic Loops
Until version 0.128.0, Codex CLI operated in a request-response paradigm: you typed a prompt, the agent executed, and it stopped. If the task wasn't.
Codex CLI Enterprise Observability: Choosing and Configuring Grafana Cloud, SigNoz, Dynatrace, and Opik
Codex CLI has shipped opt-in OpenTelemetry export since v0.107.0, but the documentation stops at heres how to configure an OTLP endpoint .
Codex CLI Through Databricks Unity AI Gateway: Enterprise Governance, Rate Limits, and Guardrails for Coding Agents
Enterprise teams adopting Codex CLI face a recurring governance challenge: how do you give fifty — or five thousand.
Anatomy of a Production AGENTS.md: What the openai/codex Repository Teaches About Agent-Aware Codebase Configuration
Most AGENTS.md guides tell you what sections to include. Few show you a battle-tested file from a codebase where agents write production code daily.
Spring 2026 AI Coding Agent Vulnerabilities: CVE-2026-26268, Comment-and-Control, and Codex CLI's Defence Posture
Two high-severity vulnerabilities disclosed in the final week of April 2026 demonstrate that AI coding agents remain soft targets.
Specification Drift and SLUMP: Why Codex CLI Loses Faithfulness in Long-Horizon Sessions and How to Fight Back
Every developer who has used a coding agent for a multi-hour session has felt it: somewhere around the thirtieth turn, the agent starts building something.
The Over-Mocking Problem: What 1.2 Million Commits Reveal About Agent-Generated Tests and How to Configure Codex CLI for Realistic Test Output
A new empirical study accepted at MSR 2026 analysed 1.2 million commits across 2,168 repositories and found that coding agents generate mocks in 36% of their.
Do Agent-Written Tests Actually Help? What Six LLMs on SWE-bench Reveal and How to Rethink Your Codex CLI Testing Strategy
The instinct to make coding agents write tests is strong — and understandable. Test-driven development has been a pillar of professional software.