fix: add NVIDIA API host to reasoning_content allowlist for DeepSeek V4 models#914
fix: add NVIDIA API host to reasoning_content allowlist for DeepSeek V4 models#914SnotacusNexus wants to merge 3 commits intoGitlawb:mainfrom
Conversation
|
#910 adds per provider/gateway flags for this i think. or at least has the framework to adapt it cleanly. |
gnanam1990
left a comment
There was a problem hiding this comment.
Nice — adding NVIDIA's integrate.api.nvidia.com to the allowlist and the unified providerSupportsReasoning() helper is a clean refactor. Explicit api.openai.com carve-out to avoid false positives is a good touch.
LGTM. Once the bun:bundle smoke is unblocked, a small unit test for hasThinkingBlockInHistory would be a nice follow-up.
|
hello bro @SnotacusNexus we just merged the registry PR for providers, kindly fix conflicts and this is good to go |
Vasanthdev2004
left a comment
There was a problem hiding this comment.
Targeted maintainer triage review of the current head ($short).
Verdict: Needs changes
Blocking issue:
- GitHub reports this branch as DIRTY / conflicting with main, so it cannot be merged or final-approved as-is. Please rebase or merge latest main, resolve the conflicts, and rerun the relevant checks.
I did not do a full code review because the current branch state is not mergeable. Happy to re-review once the branch is clean.
Summary
integrate.api.nvidia.comto thereasoning_contentallowlist so DeepSeek models (deepseek-ai/deepseek-v4-flash,deepseek-ai/deepseek-v4-pro) hosted on NVIDIA's API don't get a 400 error on tool-call roundshasThinkingBlockInHistory) so unlisted providers that already returned athinkingblock continue to echoreasoning_contentcorrectlyproviderSupportsReasoning()as a unified entry point combining explicit host matching + history detection, with a carve-out forapi.openai.comto avoid false positivesImpact
API Error: 400 {"error":{"message":"The reasoning_content in the thinking mode must be passed back to the API."}}when using DeepSeek models (deepseek-ai/deepseek-v4-flash,deepseek-ai/deepseek-v4-pro) throughintegrate.api.nvidia.comthinkingblock on the first responseTesting
bun run buildbun run smokebun test src/services/api/openaiShim.test.ts— blocked by pre-existingbun:bundleimport issue inslowOperations.tsNotes
integrate.api.nvidia.com) withdeepseek-ai/deepseek-v4-flashanddeepseek-ai/deepseek-v4-pro