Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

Support Amazon Bedrock as a provider for OpenCode (via Converse through the AI Gateway)

Open
  • Is something wrong?
#482 0 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

@bjanssen11 is already working on this.

Since Sep 3, 2026.

  • #481 by @bjanssen11 — open

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
48/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Active
Tech stack
aws, python
Domain
ai, backend-api-design, cloud

Research direction

Start by tracing the existing Pi integration and the OpenCode provider declaration through launch-time configuration and the 30-minute token refresh. Check how @ai-sdk/amazon-bedrock and the per-model Databricks-Model-Provider-Service header are represented, then verify the generated config survives refresh and that opencode run returns Bedrock output through the gateway.

Written by the indexing model from the issue text.

Description

Request

Let OpenCode route to an Amazon Bedrock Model Provider Service (MPS) through the Databricks AI Gateway, the same way Pi does.

Approach

OpenCode declares providers by npm package. The @ai-sdk/amazon-bedrock provider, given a bearer apiKey (no AWS SigV4, no region) and a baseURL of {workspace}/ai-gateway, builds /model/{id}/converse-stream requests. That is the only dialect the gateway serves for the amazon_bedrock provider type, so it is the right fit. The Databricks-Model-Provider-Service header must ride per-model, since OpenCode overwrites provider-level headers.

The provider block also has to survive OpenCode's launch-time and 30-minute token refresh, which otherwise re-renders the config and drops it.

Verification

Confirmed end to end against a live gateway: OpenCode installs @ai-sdk/amazon-bedrock on first use, the generated config survives a token refresh, and opencode run returns real Bedrock output across Claude, Nova, GPT-family, Grok, and Qwen targets.

Notes

  • Codex cannot use Bedrock through the gateway (Converse-only), tracked separately in #476.
  • Per-model output-token caps are a known follow-up: some models reject a large maxTokens (for example Nova's 10k limit).
Dominant language
Python
Stars
108
Forks
88
Avg merge
1d 11h
Merged PRs (30d)
239

Getting set up

This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from databricks/unity-gateway

All issues in databricks/unity-gateway

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.