Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

What I learned by putting GitHub Copilot behind a MitM proxy

lighthousenewsletter.com

Post reply on HN
Print view View original

31–40 of 40 posts

Re: What I learned by putting GitHub Copilot behind a MitM proxy

#31

Post by theozero »

jiehong wrote: post #24
j0selit0 wrote: post #3

I was curious to understand how Copilot implements its harness, and also how I was exhausting my quota so quickly. End up going down a rabbit hole of intercepting its network traffic with mitmproxy. A few interesting things I found along the way: - watched model/capability discovery and routing happen in real time - looked at what gets injected into context and sent with ghost completions - found that recent edits ca…

How do you actually cleanly solve that .env issue? Anything cross platform and coding agent agnostic? I suppose that .env file should be removed, but then things aren’t easy: no native multiplatform secret manager, or the std lib of the language doesn’t offer an API over the native secret store, etc. Or a "secret injection proxy" for some cases could work I guess.

https://varlock.dev (free, open source) can pull secrets from many places, and has a credential broker (proxy) to inject placeholders, then replace with real secrets at the network boundary. There are a few other tools like this, but ours seems to be the most flexible so far.

Re: What I learned by putting GitHub Copilot behind a MitM proxy

#32

Post by YawningAngel »

Supermancho wrote: post #10

I wish copilot was better at coding Java. It's like using ChatGpt 5.1, even with Fable 5 or Opus 5 as models. The other issue with copilot is how episodic memory works. Copilot writes memories after a task is completed, which means a lot of context is lost from the intermediate exploration, success/failure steps (turns), for what? Codex's multithreaded model adds the turn outputs to episodic memory (both agents submi…

I have found beads works pretty well for this

Re: What I learned by putting GitHub Copilot behind a MitM proxy

#35

Post by wefollowfilings »

p1llus wrote: post #9

One thing I found that I thought was a fun addition, is using eBPF made this even easier. No need to fight with anyone that is using certificate pinning, mTLS or anything else, you just get the raw plaintext data straight of the wire (right before encryption and right after decryption) and works nicely for most of the agents and IDE's. That will in practice give you everything from telemetry to prompts, and its funny…

[dead]

Re: What I learned by putting GitHub Copilot behind a MitM proxy

#36

Post by Supermancho »

YawningAngel wrote: post #32
Supermancho wrote: post #10

I wish copilot was better at coding Java. It's like using ChatGpt 5.1, even with Fable 5 or Opus 5 as models. The other issue with copilot is how episodic memory works. Copilot writes memories after a task is completed, which means a lot of context is lost from the intermediate exploration, success/failure steps (turns), for what? Codex's multithreaded model adds the turn outputs to episodic memory (both agents submi…

I have found beads works pretty well for this

I will try it. npm install -g @beads/bd

Re: What I learned by putting GitHub Copilot behind a MitM proxy

#39

Post by nottorp »

_davide_ wrote: post #23
nottorp wrote: post #13

"Apps users love, made with Electron". Seriously? They use those apps either because of network effects or because there are few alternatives.

or completely deleting the app and use the browser version for desperation

Browser version eats about as much ram sadly. It’s not only about the Chrome dlls but also about the memory leaks, needlessly loaded resources etc etc.

Re: What I learned by putting GitHub Copilot behind a MitM proxy

#40

Post by rldjbpin »

while this approach gives much more insights on the various requests made, if you are mainly interested in the underlying harness and its moving parts, there is already an in-built feature.

to use it, open the meatballs menu (...) of your current copilot conversation and click "show agent debug logs". it opens a tab showing all the various tool calls and prompts being sent out behind the scenes and how model selection is happening (if auto). it also gives insights on token consumption as well. moreover, vscode has been quietly shipping updates and recently you can connect your own otel service to get this information in a way you can put to use yourself.

while copilot has turned me off post their pricing changes, they have been doing tons at their own pace. highly recommend going through this feature if you find the op interesting.

Post reply on HN