Conversation
…ng levels The capability metadata that ships with the provider predated several model ids, so anything published after the last refresh fell back to the unknown-model defaults: reasoning: false and no thinkingLevelMap. pi hides every thinking level for non-reasoning models, so deepseek/deepseek-v4.1-flash offered only "off" and dropped reasoning_effort from the request. Refreshed the metadata with the repository's own catalog sync script. The newer ids now report their image, reasoning, effort, and output-limit support, and deepseek/deepseek-v4.1-flash exposes low/high/max, which matches the public model reference. The obsolete manual effort overrides are dropped because the refreshed catalog carries those levels itself.
SamYue1
force-pushed
the
fix/sync-commandcode-catalog-1-54
branch
from
September 14, 2026 06:06
50ba4fc to
2e257a9
Compare
SamYue1
changed the title
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
The model metadata shipped with the provider predates several model ids, so those ids fall back to the unknown-model defaults (
reasoning: false, nothinkingLevelMap). pi returns["off"]for non-reasoning models, sodeepseek/deepseek-v4.1-flashexposed no selectable thinking level and droppedreasoning_effortfrom requests.Change
Refreshed the shipped metadata with the repository's own catalog sync script:
deepseek/deepseek-v4.1-flash— image + reasoning, effortslow/high/maxgpt-6-astra— image + reasoning, effortslow…maxinclusionai/ling-3.0-flash-sante:free— reasoning + output limitMiniMaxAI/MiniMax-M3and the Muse Spark models — effort levelsVerification
bun test ./tests/test-models.ts ./tests/test-model-metadata-check.ts→ 30 pass / 0 failpi --list-models commandcode→ 69 models;deepseek/deepseek-v4.1-flashreportsthinking: yesoff/low/high/max, matching the public model reference