https://blog.cloudflare.com/code-mode/

Cloudflare’s blog post “Code Mode: the better way to use MCP,” authored by Kenton Varda and Sunil Pai, introduces a new approach to using the Model Context Protocol (MCP) that significantly improves AI agent performance. Traditional MCP usage involves directly exposing tools to large language models (LLMs), but this method faces limitations due to LLMs’ limited familiarity with tool-call tokens, resulting in difficulty with complex or numerous tools.

The new Code Mode approach converts MCP tools into a TypeScript API and instructs the LLM to write code that calls the API. This provides several advantages:

1. Improved Tool Handling: LLMs handle more tools and complex interactions better because they are extensively trained on real-world TypeScript code rather than synthetic tool-calling data.
2. Efficient Multi-Call Execution: Code Mode allows LLMs to chain multiple tool calls without looping every result back through the neural network, reducing token

argocd cluster add docker-desktop

https://registry.terraform.io/providers/oboukili/argocd/latest/docs/resources/cluster

• https://github.com/varmaprr/Confluent-Kafka-Certification
• https://github.com/afonsir/apacha-kafka-ccdak
• https://www.confluent.io/wp-content/uploads/confluent-kafka-definitive-guide-complete.pdf
• https://kafka.apache.org/documentation/
• https://docs.confluent.io/platform/current/platform.html
• Developer questions
• Administrator questions

• Histogram bucket for negative values ("(..., 0)")
• https://github.com/iovisor/bpftrace/blob/master/docs/reference_guide.md

• CKS
  • Helpful Tips
  • Introduction
  • Cloud Native Security
    • Area of Concern for Kubernetes Infrastructure
    • Area of Concern for Workload Security
    • Area of Concern for Containers
    • Area of Concern for Code
  • Pod Security Standards
• What's the difference between a security policy and a security context?

• Need to disable shared runner for new repository

One more thing to note about timeouts in Istio is that in addition to overriding them in route rules, as you did in this task, they can also be overridden on a per-request basis if the application adds an x-envoy-upstream-rq-timeout-ms header on outbound requests. In the header, the timeout is specified in milliseconds instead of seconds.

Doesn't work in istio-enabled GKE, as right after we try to modify ingressgateway GKE will try to revert that :(