fix(opencode): allow opt out of auto generated sampling parameters - #42780
Open
sobakasu wants to merge 2 commits into
Open
fix(opencode): allow opt out of auto generated sampling parameters#42780sobakasu wants to merge 2 commits into
sobakasu wants to merge 2 commits into
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Issue for this PR
Closes #42775
Type of change
What does this PR do?
Adds an experimental 'sampling_defaults' (default true, to keep existing behaviour) config setting.
This can be set to false to opt out of the automatic sampling parameters that are generated based on model id/name.
{ "$schema": "https://opencode.ai/config.json", "experimental": { "sampling_defaults": false }, }The second commit makes some changes to these automatically generated settings, e.g. so that Qwen 3 uses top_p 0.95 instead of 1.
How did you verify your code works?
I built opencode in my branch and tested it against a local
llama.cppserver. My opencode is configured with a model named "Qwen-3.8-27B" (see issue's how to reproduce section for details)Checklist