Repository navigation
fix(decisions): gemini-decision-1 needs a description on every choice and level - #117
Merged
Merged
Conversation
… and level Gemini Decision 1 refuses a choice or score level without a description string (the gateway answers 400 before payment: "questions[0].choices[0].description must be a string (it may be empty)", probed on sol.blockrun.ai 2026-11-18). build_decisions_body now raises ValueError for it before sending, naming the item. gpt-6-luna is unchanged. README and docstring examples give every choice and level a description, so they work on both models (live-run on sol).
added 2 commits
November 18, 2026 11:13
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
gemini-decision-1launched on sol.blockrun.ai and blockrun.ai on 2026-11-18. It needs adescriptionstring on everychoiceand every scorelevel. An empty string is fine.Without one, the gateway answers 400 before payment, so nothing is charged. The call still fails, though. Every
decisions()example in this SDK leavesdescriptionout, so copying an example and passingmodel="gemini-decision-1"fails.Probed on sol, 2026-11-18. All of these are refused before payment, so they cost nothing.
questions[0].choices[0].description must be a string (it may be empty)questions[0].levels[0].description must be a string (it may be empty)Change
build_decisions_bodyraisesValueErrorbefore sending when the model isgemini-decision-1orgoogle/gemini-decision-1and any choice or level lacks adescriptionstring. The message names the exact item.decisions()docstrings give every choice and level a description. They now work on both models.Tests
TestGeminiDecisionDescriptions. Four of its cases failed before the fix:openai/id, does not require descriptions.pytest tests/unit: 1612 passed.ruff checkandruff format: clean.gemini-decision-1and ongpt-6-luna;ValueErrorbefore anything was sent.Noticed, not changed here
On the same input, Gemini returns
scoreas a decimal (1.43) and luna returns an integer index (1). The README says the score is the "index on the rubric". The docs orDecisionsResponsemay need a note. That is a separate decision.🤖 Generated with Claude Code