anomalyco / anomalyco/opencode

PyCharm 2026.2 AI Assistant spawns 15-22 opencode.exe acp processes on startup, causing memory exhaustion and crash (0xC0000409)

Open
#40,696 4 comments 0 reactions 1 assignee View on GitHub

@Hona is already working on this.

Since Aug 5, 2026.

Dominant language
TypeScript
Stars
209k
Forks
27.5k
PR merge metrics
PR metrics pending

Description

Description

When PyCharm 2026.2 starts with the AI Assistant configured to use opencode as an ACP provider, the AI Assistant bulk-creates 15-22 chat sessions during IDE initialization. Each session independently spawns a separate opencode.exe acp process, and each process goes through full initialization (model loading, MCP server connections, etc.). This causes memory usage to spike to 100%, eventually crashing PyCharm with exit code 0xC0000409 (STATUS_STACK_BUFFER_OVERRUN).
The following workarounds are NOT acceptable:

  • Disabling JetBrains Client Protocol (JCP)
  • Uninstalling the ml-llm plugin
    Requirement: keep opencode usable inside the IDE via AI Assistant's ACP integration, while preventing the startup-time chat/process explosion.
Plugins
  • JetBrains AI Assistant (bundled with PyCharm 2026.2) - opencode ACP integration (configured as AI Assistant ACP provider)
OpenCode version

1.18.12

Steps to reproduce
  1. Install PyCharm 2026.2, configure AI Assistant to use opencode as ACP provider
  2. Start PyCharm
  3. Observe in Task Manager: opencode.exe acp process count rapidly grows from 0 to 15-22
  4. Memory usage climbs to near 100%
  5. PyCharm crashes; Event Viewer shows exception code 0xC0000409
Screenshot and/or share link
Image

hs_err_pid8612.log

Operating System

Windows 10 home 22h2 (64-bit)

Terminal

N/A — crash occurs when PyCharm IDE start for a few seconds, not in a terminal

Contributor guide

Open the contributing guide

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.