Conversation
The native tool-calling path (tooledStream/tooledComplete) never sent a temperature field, so the workspace temperature setting had no effect on @agent turns for OpenAI-compatible providers while normal chat honored it. Providers that rejected the workspace temperature saw intermittent empty completions from local backends (issue Mintplex-Labs#6091). Add an opt-in temperatureParam helper following the existing maxTokens/ serviceTier pattern and pass the workspace value from genericOpenAi. Fixes Mintplex-Labs#6091 Signed-off-by: wangzifei <wangzifei@cit.group.hk>
Member
|
#6285 is already the PR for this |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
tooledStream/tooledComplete) never sent atemperaturefield, so the workspace temperature setting had no effect on@agentturns for OpenAI-compatible providers, while normal chat honored it (issue [BUG]: Workspace LLM Temperature is not applied to agent sessions, and no agent-level temperature setting exists #6091, with measured repro against a local llama.cpp backend).Changes
temperatureParamhelper following the existingmaxTokensParam/serviceTierParampattern: only providers that pass a valid temperature get the field, all other providers keep their existing requests byte-identical.openAiTempfromgenericOpenAi(numeric strings from workspace settings are accepted).Fixes #6091