[HN Gopher] What Claude Code Sends to the Cloud
___________________________________________________________________
What Claude Code Sends to the Cloud
Author : rastriga
Score : 15 points
Date : 2026-01-10 15:07 UTC (7 hours ago)
(HTM) web link (rastrigin.systems)
(TXT) w3m dump (rastrigin.systems)
| rastriga wrote:
| I built a MITM proxy to inspect Claude Code's network traffic and
| was surprised by how much context is sent on every request. This
| is Part 1 of a 4-part series focusing only on the wire format and
| transport layer. Happy to answer technical questions.
| hhh wrote:
| 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?
| rastriga wrote:
| 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.
| hhh wrote:
| That makes sense :) Cool analysis!
| crbelaus wrote:
| This is great! Would love to see if Opencode sends different
| payloads and hoe they differ.
| mikro wrote:
| I've been waiting for someone to dig into this more deeply!
| Looking forward to Part 2!
|
| I use both Claude Code and Xcode with a local LLM (running with
| LM Studio) and I noticed they both have system prompts that make
| it work like magic.
|
| If anyone reading this interested in setting up Claude Code to
| run offline, I followed these instructions:
|
| https://medium.com/@luongnv89/setting-up-claude-code-locally...
|
| My personal LLM preference is for Qwen3-Next-80B with 4bit
| quantization, about ~45GB in ram.
| MuffinFlavored wrote:
| I am surprised that... if they have a session ID of some sort for
| your chat that they make you re-send the entire message history
| each time? Not a single kind of cache or stateful proxy/buffering
| mechanism? Guessing that extra cost in bandwidth is cheaper than
| having to develop and maintain that? Seems kind of like an
| obvious optimization/design tradeoff they could eventually decide
| to change one day?
___________________________________________________________________
(page generated 2026-01-10 23:01 UTC)