Repository navigation
AI Assistant response error #1567
Description
Description
I'm getting this error when I run a chat message:
Error getting AI response: HTTP 400 (invalid_request_error: invalid_request_error)
Error from provider (DeepSeek): The reasoning_content in the thinking mode must be passed back to the API.
I'm using a custom (OpenAI compatible) provider:
url: https://opencode.ai/zen/v1
model: big-pickle
It seems to only effect this model; there are a few free ones available that I've been testing.
Documentation can be found here: https://opencode.ai/docs/zen/
Tabular Editor 3 Version
3.26.1
Screenshots
Steps to Reproduce
No response
Expected behavior
No response
Crash Report
No response
Windows Version
Windows 11
Activity
otykier commentedon May 4, 2026
Hi @samaguire
Thanks for reporting this. We'll investigate and get back to you.
otykier commentedon May 4, 2026
Thanks for the detailed report, including the screenshots and provider link. That made it quick to track down.
What's happening
The "big-pickle" model on opencode.ai's Zen gateway is a thinking-mode model that exposes its reasoning via a
reasoning_contentfield on assistant messages, and requires that field to be echoed back on subsequent turns. If it isn't, the API returns the 400 you're seeing.The catch is that
reasoning_contentis not part of the OpenAI Chat Completions specification, it's a non-standard extension popularised by DeepSeek and adopted by some compatible gateways. OpenAI's own reasoning models (o1/o3/o4) don't use this field at all; their reasoning state is handled differently, on a separate API. So strictly speaking, the model isn't fully OpenAI-compatible despite being served over an OpenAI-compatible endpoint.That said, the underlying .NET AI library Tabular Editor 3 uses on the Custom provider already reads
reasoning_contentfrom responses - it just doesn't write it back out on the next request. So it's also a gap on our side that we can close.Workarounds for now
Plan
We'll add explicit handling for
reasoning_contentround-tripping on the Custom (OpenAI-compatible) provider in an upcoming release, gated so it doesn't break providers like DeepSeek R1 that forbid the echo. I'll link the fix to this issue when it lands.Thanks again for flagging it. The fix will benefit anyone using a thinking-mode model behind an OpenAI-compatible endpoint.
samaguire commentedon May 4, 2026
No problem. And I'm glade there is a solve for this; the more I play with this feature, the more I like using it.
Curiously, are there any plans to add a dropdown to select/control the level of thinking to use?
otykier commentedon May 5, 2026
That's really great to hear, thank you!
Not currently. We would have to map out the spec for this per provider/model, as there is no standardized way in the .NET library (Microsoft.Extensions.AI), as far as I know.
MariaJoseFF commentedon Jul 6, 2026
Hi @samaguire, I looked into this further and couldn't reproduce the issue with the same setup anymore.
Testing against
big-pickleonopencode.ai/zen, the prompts (like "list the measures in this model" or "Use the Semantic Model Organization Skill") now complete without theHTTP 400 ... reasoning_content ... must be passed backerror.The model still emits reasoning content, but the provider no longer rejects the follow-up request when it isn't echoed back.
big-pickleis a preview/"stealth" model, and its behavior appears to have changed since you filed this, so the specific condition that triggered the error no longer seems to be enforced on the provider side.Can you confirm if you can still reproduce the error with
big-pickle(or any other model)? A confirmation from your side would help us close this out with confidence.mlonsk commentedon Sep 24, 2026
Hi
This issue was fixed in our latest release of Tabular Editor 3 (27.0.0). Please let us know if it works or if you have any other feedback.