fix: replace 'minimal' with 'low' reasoning effort for gpt-5.4-mini#1395
Open
sgaluza wants to merge 2 commits intogetzep:mainfrom
Open
fix: replace 'minimal' with 'low' reasoning effort for gpt-5.4-mini#1395sgaluza wants to merge 2 commits intogetzep:mainfrom
sgaluza wants to merge 2 commits intogetzep:mainfrom
Conversation
gpt-5.4-mini does not support 'minimal' reasoning effort value. Supported values are: 'none', 'low', 'medium', 'high', 'xhigh'. - Update DEFAULT_REASONING constant from 'minimal' to 'low' - Add VALID_REASONING_VALUES and VALID_VERBOSITY_VALUES validation in BaseOpenAIClient constructor for early error detection - Update tests to use valid reasoning/verbosity values - Add parametrized tests for validation of both parameters
…oning values
Allow legacy reasoning values ('minimal', 'intense') in validation
to avoid breaking existing users on older models.
Built [OnSteroids](https://onsteroids.ai)
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
gpt-5.4-minidoes not supportreasoning.effort: "minimal". The supported values are:none,low,medium,high,xhigh.This PR:
DEFAULT_REASONINGfrom'minimal'to'low'inopenai_base_client.pyVALID_REASONING_VALUESandVALID_VERBOSITY_VALUESconstants with early validation inBaseOpenAIClientconstructor — invalid values now raiseValueErrorimmediately instead of failing at API call time'minimal'→'low','intense'→'high')reasoningandverbosityparametersMotivation
When using
gpt-5.4-minias the extraction model, batch operations fail with:'low'was chosen over'none'because edge extraction and node deduplication require minimal reasoning for quality results.Test plan