Set explicit low temperature for chat completions (closes #103)#105
Open
vahid-ahmadi wants to merge 1 commit into
Open
Set explicit low temperature for chat completions (closes #103)#105vahid-ahmadi wants to merge 1 commit into
vahid-ahmadi wants to merge 1 commit into
Conversation
Add CHAT_TEMPERATURE (env ANTHROPIC_CHAT_TEMPERATURE, default 0.0) and pass it on the main streaming chat call. This is an analytical product where numbers come from model-generated run_python code, so a low temperature reduces run-to-run variance in the code the model writes. Closes #103 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
Beta preview is ready.
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Set an explicit, low, env-overridable
temperatureon the main chat completion call so results are more consistent run-to-run.The default is
0.0, overridable via theANTHROPIC_CHAT_TEMPERATUREenv var.Honest caveat:
temperature=0does not guarantee bit-for-bit determinism from the API — it reduces variance, it doesn't eliminate it. The larger source of run-to-run inconsistency is the model generating variablerun_pythoncode; that's addressed separately by typed tools (#81) and reform recipes (#85). This is the cheap complementary lever.Closes #103
🤖 Generated with Claude Code