Repository navigation
Conversations hang after first response when provider returns a reasoning field (using Ollama/Qwen3) #34798
Closed as not planned
Description
Description
When using local thinking models on Ollama (e.g. Qwen3.6-35b), the model appears
to think but then stops and returns no response.
The @ai-sdk/openai-compatible SDK extracts the reasoning field from the response and re-sends it as reasoning_content in message history on the next turn. Ollama does not accept reasoning_content in
message history, causing the conversation to hang with no output returned to the user.
Plugins
None
OpenCode version
1.17.13
Steps to reproduce
- Configure an Ollama provider with a thinking model (e.g. Qwen3.6-35b)
- Start a session and send a message, like: "Explain in detail how distributed consensus algorithms work. Compare PBFT, Tendermint, and Raft protocols, their tradeoffs, fault tolerance models, and real-world applications. Walk through a concrete example of message ordering in each protocol."
- Note that opencode just ends - as if it responded to you.
Screenshot and/or share link
No response
Operating System
Ubuntu 24.04 LTS
Terminal
Ghostty
Reacted by twhittock
Metadata
Metadata
Assignees
Labels
No labels
Activity
github-actions commentedon Jul 1, 2026
This issue might be a duplicate of existing issues. Please check:
reasoning_contentin assistant message history rejected on follow-up turns by providers that don't support it (Cerebras)reasoning_contentmust/must-not be replayed in history depending on the provider; multi-turn failures with OpenAI-compatible providersreasoning/reasoning_contentfields from prior turns are sent back in history to providers that reject themThe underlying issue (the AI SDK's
@ai-sdk/openai-compatiblere-injectingreasoning_contentinto subsequent message history for providers that don't accept it) appears to be the same problem described in those issues, just observed with Ollama instead of Cerebras/DeepSeek/Kimi.[-]Multi-turn conversations fail with Openai-compatible providers that return a reasoning field (e.g. Ollama/Qwen3)[/-][+]Conversations hang after first response when provider returns a reasoning field (using Ollama/Qwen3)[/+]twhittock commentedon Jul 9, 2026
This breaks all usage of reasoning models in my ollama-based environment - I am running a patched build (#36068) locally to work around this.
github-actions commentedon Sep 8, 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.