tailscale / tailscale/aperture-cli
feature: Looking for protocol conversion and docs suggestion
Nobody has claimed this yet.
- Dominant language
- Go
- Stars
- 74
- Forks
- 13
- Avg merge
- 1h
- Merged PRs (30d)
- 7
Description
The Problem
Currently, the documentation does not clearly state whether Aperture translates between different LLM API formats (e.g., OpenAI /v1/chat/completions ↔ Anthropic /v1/messages).
I mistakenly assumed Aperture could accept an OpenAI-style request and convert it to an Anthropic-style request before forwarding it to the backend. However, after testing, it seems Aperture simply acts as a passthrough proxy and forwards the request as-is. This leads to confusion and failed requests when the client format doesn't match the backend format.
The Request
- Docs Update (Primary): Please add a prominent note in the documentation explaining that Aperture is a passthrough proxy and does not perform protocol conversion. Clients must use the native request format of the target provider (e.g., Anthropic format for Anthropic backends, OpenAI format for OpenAI backends).
- Feature Request (Secondary): As a future enhancement, it would be great if Aperture could optionally translate request/response formats (e.g., accept OpenAI input, convert and forward as Anthropic). This would allow tools locked to a specific API format (like Claude Code or OpenAI Codex CLI) to seamlessly use different backends without needing an external conversion proxy.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by locating the project documentation entry point and the existing explanation of Aperture's proxy behavior. Add a prominent note that it is a passthrough proxy and does not convert request or response formats, including the native-format examples from the issue. Done means the documentation clearly sets this expectation; the protocol-conversion enhancement is a separate future feature.
Written by the indexing model from the issue text.
Assessment
- Domain
- api, documentation
- Issue type
- Documentation
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 68/100