Merged
Conversation
Models like kimi-k2.5 only accept temperature=1, causing repeated 400 errors and mock fallback. Add llm_temperature to Settings, admin config, and the staff dashboard so operators can set the value per-instance. OpenAICompatibleChatClient uses the configured default (falling back to 0.2) instead of a hardcoded value. The automatic temperature=1 retry remains as a safety net. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
llm_temperatureconfig field across Settings, admin API, and staff dashboard UI — lets operators set the sampling temperature for models that require specific values (e.g. kimi-k2.5 only acceptstemperature=1)OpenAICompatibleChatClientuses the configured default instead of hardcoded0.2, while keeping the automatictemperature=1retry as a safety net for unrecognized errorsDIBBLE_LLM_TEMPERATURE, TOML:[llm] temperature, Default:null(uses 0.2)Test plan
llm_temperature = 1in config, verify kimi-k2.5 no longer falls back to mock🤖 Generated with Claude Code