Repository navigation
Default agent is brittle against local OpenAI-compatible tool-call quirks #20669
Closed as not planned
Description
Summary
When the default OpenCode agent talks to local OpenAI-compatible backends, two brittle cases can break or stall normal tool use:
- the bash tool can fail hard if the model omits
descriptionbut provides a validcommand - some local backends return
finish_reason: "tool_calls"together withtool_calls: [], which should not be treated as a real tool-call turn
Reproduction
Use the default build agent against a local OpenAI-compatible backend such as llama.cpp or LM Studio.
Observed failures:
The bash tool was called with invalid arguments ... expected string, received undefinedondescription- session loop/hang behavior when empty
tool_calls: []is returned
Expected
- harmless missing bash descriptions should be normalized or defaulted
- empty
tool_callsarrays should be treated like a normal stop completion
Verification
This was reproduced against a local llama.cpp backend with the default agent/tool stack.
Metadata
Metadata
Assignees
Labels
No labels
Activity
github-actions commentedon Apr 2, 2026
This issue might be a duplicate of existing issues. Please check:
tool_calls: []causing a session loop/hangfinish_reason=stop— also covers the session continuing when no tool calls are presentThe first part of this issue (bash tool failing on missing
description) may be distinct, but please review those issues to see if your second symptom is already tracked.ByteBand1t commentedon Apr 2, 2026
This also fixes #20719 — our Paperclip + LiteLLM + Ollama setup where agents stop after first LLM call. Please prioritize merging
daniel-farina commentedon Apr 3, 2026
I tested this and helped get gemma working with open code
https://gist.github.com/daniel-farina/87dc1c394b94e45bb700d27e9ea03193
github-actions commentedon Jul 3, 2026
To stay organized issues are automatically closed after 60 days of no activity. If the issue is still relevant please open a new one.