Fix GPT-5 chat failures by stripping unsupported sampling params#539
Open
hershkop wants to merge 1 commit into
Open
Fix GPT-5 chat failures by stripping unsupported sampling params#539hershkop wants to merge 1 commit into
hershkop wants to merge 1 commit into
Conversation
…reasoning models Reasoning models (o1, o3, o4, gpt-5) reject frequency_penalty, presence_penalty, top_p, stop, and n. Clear these in the isReasoningModel branch so they aren't sent to the API. Also fix gpt-5-mini cost typo (0.25 - 6 → 0.25e-6). Fixes Ironclad#531
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
top_p,frequency_penalty,presence_penalty,stop,n) for reasoning models (o1, o3, o4, gpt-5) in theisReasoningModelbranch ofChatNodeBase.tsgpt-5-minicost typo:0.25 - 6(evaluates to-5.75) →0.25e-6Context
GPT-5 chat requests fail when a graph carries non-default sampling parameters from non-reasoning models. The OpenAI API rejects these with errors like
"Unsupported parameter: 'stop' is not supported with this model". The existingisReasoningModelbranch already correctly usesmax_completion_tokensinstead ofmax_tokensand omitstemperature, but does not clear the other unsupported parameters.Fixes #531
Test plan
yarn build— TypeScript compiles successfullyyarn test— all 63 existing tests passyarn lint— 0 errors (4 pre-existing warnings)🤖 Generated with Claude Code