Hacker News Reader

Comment by hhh | Hacker News Reader

Seems a bit obvious all the information claude code would send to the llm would be sent to Anthropic no? Isn’t that the point of using it via Azure or AWS Bedrock, for the guarantees of secrecy they provide you?

View on HN

yes, it's obvious the data goes to Anthropic. What wasn't obvious to me was what exactly is included and how it's structured: system prompt size, full conversation replay, file contents, git history, tool calls. The goal was to understand how the wire level works. On Azure/Bedrock - good point! My understanding is that they route requests through their infrastructure rather than Anthropic directly, which does change the trust boundary, but my focus here was strictly on what the client sends, that payload structure is the same regardless of backend.

That makes sense :) Cool analysis!

thank you!

Specifically do you mean when you say git history is sent? How much of it is included in each request?

It's the last 5 commits, not the full history. Here's what actually gets sent in the system prompt:

  gitStatus: This is the git status at the start of the conversation...
  Current branch: main
  Main branch: main
  Status: (clean)

  Recent commits:
  6578431 chore: Update security contact email (#417)
  0dc71cd chore: Open source readiness fixes (#416)
  ...

Enough for Claude to understand what you've been working on without sending your entire repo history.

Reply on news.ycombinator.com