openhuman/support · aayush · tinyhumansai/openhuman --:--:-- UTC
OpenHuman Support v0.1
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

windows-app model-routing web-search bug
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
TXT
message (1).txt 2.6 KB · text/plain
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
Controls
Details
reporter @.iphilo
email
ticket open ↗
priority HIGH
opened 2026-05-28 · 19:19
touched 2026-05-31 · 21:59
GitHub
issue #3094 ↗
pr none
Pulls PR/issue state. Merged PR → status: fixed. Open PR → pr_open.
Tags