Repository navigation
Conversation
Contributor
|
No actionable findings. |
Author
|
@rekram1-node Thanks for merging our Drex 1.5 listing in #8896! Could you review this follow-up adding Drex 2.0? It adds canonical model metadata and fixes OpenRouter’s sync to preserve zero generated-output tokens for decision models. All checks pass. |
alisher-amantay
approved these changes
Oct 13, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Drex 2.0 currently exists only as an auto-synced OpenRouter entry, which labels it closed-weight, disables structured output and advertises 117,964 generated output tokens. Add canonical Nace AI metadata and make OpenRouter inherit it: open weights, typed decisions, 131,072-token maximum context and no generated output tokens. Provider pricing remains $0.06/M input and $0/M output.
OpenRouter's feed supplies a positive
max_completion_tokenseven foroutput_modalities = ["decisions"]. Normalize decision-model output limits to zero during sync so the incorrect limit is not restored. Chat-model output-limit handling is unchanged. Extend the existing decision tests and cover Drex 2.0 inheritance with both new and stale provider metadata.Sources:
private: false,gated: false, created October 6 and last modified October 12.Validation:
bun validatepasses.85382da(209 passed): Hyper reasoning, Eden AI reasoning, DeepInfra modalities, LLM Gateway case variants, and two Vercel description assertions.