Incident #027 · opened 2026-05-28 · 19:19 UTC
web-fetch fails with DeepSeek in thinking mode — reasoning_content not passed back between tool calls
new
close: support-only
Description
User Iphilo reports that triggering web-fetch consistently fails when using DeepSeek Flash (thinking mode) as the LLM provider. Logs provided with exact error.
Error (400 Bad Request from DeepSeek API)
The `reasoning_content` in the thinking mode must be passed back to the API.
Root cause
DeepSeek's thinking/reasoning models require the reasoning_content field from a previous assistant message to be echoed back in the next API request. OpenHuman's message-building logic does not currently preserve or replay this field when constructing subsequent requests, causing DeepSeek to reject the call with a 400. This affects the web-fetch tool and likely any multi-turn tool use with DeepSeek thinking models.
Environment
Provider: DeepSeek Flash (thinking mode via custom API)
Build path visible in logs: D:\a\openhuman\openhuman\src (Windows build)
Full logs in message.txt (3 KB) attached in Discord.
Attachments
screenshots · logs · files · 1 item
Notify the user
copy a Discord-ready message, then mark as notified
Interventions
refunds · credits · manual fixes
No interventions logged.
Activity
3 events
Pooja
pushed to GitHub → issue #3094
May 31 · 21:59
Pooja
attached message (1).txt
May 28 · 19:19
Pooja
created the incident priority=high
May 28 · 19:19