FeaturedDev & IT Ops#OpenCode#GitHub#Pull Request#DevOps#Coding Agent

OpenCode Go PR Fix Agent

Send a coding task to OpenCode Go, open a review-ready pull request, and return the implementation result.

Workflow at a glance

The full canvas, before you import it

Click any node to see its config.

#OpenCode#GitHub#Pull Request#DevOps#Coding Agent

Click a node to select it — same as the Heym editor; the panel shows its settings.

3 nodes · Free & source-available

OpenCode Go PR Fix Agent

This template runs a coding request through the OpenCode Go node. Heym clones the configured GitHub repository, prepares it with the setup command, runs OpenCode inside the isolated runner, and opens a review-ready pull request.

What this workflow does

  1. CodeTask receives the coding request
  2. OpenCodeFix runs the OpenCode CLI against the configured repository
  3. FixResult returns the summary, validation notes, changed files, diff, and pull request URL

Use cases

  • Turn issue triage results into focused pull requests
  • Fix failing tests from a plain-English engineering request
  • Run repository maintenance tasks with a provider-agnostic coding agent

Setup

Create an OpenCode Go credential with a gateway API key and a GitHub credential with repository access. In OpenCodeFix, set the repository URL, base branch, model, setup command, and publish mode.

Notes

The template uses open_pr mode. Switch to draft_pr, diff_only, or patch_artifact if you want a different delivery flow. Model IDs use the opencode/model format and Heym can load the current model list from the OpenCode Go gateway.

Read the OpenCode Go node documentation for credentials, isolation, publish modes, and outputs.

How to import this template

  1. 1Click Import → Copy JSON on this page.
  2. 2Open your Heym and navigate to a workflow canvas.
  3. 3PressCmd+V/Ctrl+V— nodes appear instantly.
  4. 4Add your API keys in the node config panels and click Run.
More workflow templates
View all templates
Heym
incident analysis · production AI
Observed across 100s of AI rollouts

AI workflows don't fail because of prompts.
They fail because of orchestration.

symptom · glue code01
5 tools
Scripts, vector DB, approval bot, tracing, browser runner — none of them talk.
symptom · visibility02
~0%
Observable behavior across the stack. Debugging is guesswork.
with heym · one runtime
1 canvas
Agents, RAG, HITL, MCP, traces & evals. Self-hosted. Observable.
AI-Native RuntimeProduction-Grade
github.com/heymrun/heym