Repository navigation
Missing reasoning_content field in the assistant message for DeepSeek API implementation #17523
Description
Description
Description
When using DeepSeek models with thinking mode enabled (either via reasoner model IDs or thinking option), assistant messages after the last user message were not receiving an (empty) reasoning_content field. This caused issues with the DeepSeek API's thinking mode behavior, where every assistant message in thinking mode must provide a reasoning_content field, even if empty.
Steps to Reproduce
- Use a DeepSeek model with thinking mode enabled (e.g.,
deepseek-reasonermodel, or any DeepSeek model withthinking: { type: "enabled" }option) - Send a conversation with multiple turns (user -> assistant -> user -> assistant)
- Observe that assistant messages after the last user message do not have
reasoning_contentset, when previously empty. - The DeepSeek API returns error 400 in this scenario
Expected Behavior
ALL assistant messages after the last user message should have an empty reasoning_content field when thinking mode is enabled for DeepSeek models, to comply with API expectations.
Actual Behavior
Only assistant messages with non-empty reasoning content received the reasoning_content field. Assistant messages with empty reasoning content after the last user message did not have the field set.
Root Cause
The ProviderTransform.message function in packages/opencode/src/provider/transform.ts only added reasoning_content when there was actual reasoning text present, but deepseek requires also empty "" reasoning_content fields.
Solution
Modified the logic to:
- Detect when thinking mode is enabled for DeepSeek models (via model capabilities, model ID, or thinking option)
- Find the index of the last user message in the conversation
- For all assistant messages after that index, set an empty
reasoning_contentfield - Maintain backward compatibility for non-thinking mode usage
Affected Models
- All DeepSeek models when thinking mode is enabled
deepseek-reasonermodels- DeepSeek models with
thinking: { type: "enabled" }option
Related Issues/PRs
Plugins
No response
OpenCode version
No response
Steps to reproduce
No response
Screenshot and/or share link
No response
Operating System
No response
Terminal
No response
Activity
github-actions commentedon Mar 14, 2026
This issue might be a duplicate of existing issues. Please check:
reasoning_contentnot cleared from message history on new turns — covers the sametransform.tslogic for DeepSeek thinking mode in multi-turn conversationsYour issue describes a slightly different symptom (missing empty
reasoning_contenton assistant messages after the last user message), but it shares the same root area. Please review those issues and consider whether your fix addresses or overlaps with them. If this is a distinct problem, it may be worth clarifying how it differs.bilbillm commentedon Apr 24, 2026
I'm also experiencing this exact issue when using DeepSeek models (deepseek-v4-flash) with thinking mode enabled in OpenCode. The error "The reasoning_content in the thinking mode must be passed back to the API" occurs consistently after tool call rounds (e.g., file read/write operations).
This makes the DeepSeek thinking mode nearly unusable with tool-calling agents. Looking forward to seeing PR #17529 merged — any update on when it might be reviewed/merged?
Thanks for the fix!