microsoft / microsoft/copilot-for-eclipse
Many tasks failing due to reaching `org.eclipse.lsp4e` task queue limit
Nobody has claimed this yet.
- Dominant language
- Java
- Stars
- 126
- Forks
- 60
- Avg merge
- 2d 6h
- Merged PRs (30d)
- 5
Description
Copilot plugin version: 0.11.0.202508291001 com.microsoft.copilot.eclipse.feature.feature.group GitHub Copilot
Quite frequently, tasks executed by the Copilot plugin fail due to reaching task queue limit (which I think is different from LLM token limit). The LLM sometimes can work around this by running some alternative tasks, other times it states that the operation failed and it cannot continue.
In particular, it seems like most/all text searches (on a fairly large project) are affected by this. After a text search fails, Copilot sometimes tries to read individual directories, other times it just starts working on the files that I've provided as Context. In general:
- If I manually provide all relevant files as Context, Copilot is eventually able to answer my questions or make the requested changes, despite these errors
- If I don't manually provide all relevant files as Context, Copilot usually fails to answer my questions or make the requested changes when such errors occur
As an example, in one of my chats in Agent mode, I received the following error:
When the chat log shows such errors, my Eclipse log gets filled with these errors:
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
No source file or test is named. Start by reproducing the failure in Agent mode with a text search on a large project, then inspect the Eclipse log and the org.eclipse.lsp4e task queue limit errors. Done means the affected searches and Copilot tasks no longer fail because the task queue limit is reached.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- java
- Domain
- devtools
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 42/100