But the whole point of this is to prevent the distillation and identify the list of blocked providers. If a provider is capturing the proxy, they can identify and modify that as well, so it only looks legitimate to the model. What am I missing here?
# userEmail
The user's email address is <my email>.
# currentDate
Today's date is 2026-06-30.
IMPORTANT: this context may or may not be relevant to your tasks. You should not respond to this context unless it is highly relevant to your task.
</system-reminder>
I also do not understand what's the point of this, because if I have a gateway that can detect it, then we can replace the text before forwarding to the model, so what's the catch?
So, how are you handling read/write caching? I mean, if I keep routing the next prompt based on the task weights? How about if I'm sending every 5th query to opus, which do expensive write cache?
I've been pondering over the same question, but also on an enterprise scale. For example, how could I scrub the customer data, like name, domain, etc., before sending it to LLM if my Claude code is using some MCP to fetch and debug an issue?
I mean, hooks are nice, but they are messy to manage/operate for many developers at a time.
Well, you will be paid for your subjective decision-making, what applies where, system design, and your calculation of trade-offs. Regardless of what scaling laws say, these will remain a problem for humans to solve because real-world systems are messy.
I've been thinking about and working on a solution to automatically resume a Claude code session in the same terminal when my quota resumes. I hate waking up and typing "please continue"
I use Claude Code for coding sessions. Sometimes I hit a usage/rate limit and the session stops before the task is finished. I am not trying to bypass the limit I want a automatic way to resume once the quota resets.
Wait, do the coding agents fire `kubectl get -o yaml`??? Most of the harness agents, like CC or codes, are very precise about command construction. For example, the harness add - o and look for the status, for example.