docs(vertex): document reasoning_effort -> thinking_level mapping for Gemini 3.x (#267)#509
Open
Anai-Guo wants to merge 1 commit into
Open
docs(vertex): document reasoning_effort -> thinking_level mapping for Gemini 3.x (#267)#509Anai-Guo wants to merge 1 commit into
Anai-Guo wants to merge 1 commit into
Conversation
… Gemini 3.x The Vertex AI Thinking section only covered the reasoning_effort -> thinkingBudget mapping used by older Gemini models. Gemini 3+ models map reasoning_effort to a thinkingLevel instead (see _map_reasoning_effort_to_thinking_level), with model-dependent results. Add a table for the Gemini 3.x thinking-level mapping so the docs match the current implementation. Closes BerriAI#267
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Documents the
reasoning_effort→thinking_levelmapping used for Gemini 3.x models on Vertex AI, closing #267.The existing "Thinking /
reasoning_content" section only covers the olderreasoning_effort→thinkingBudget(token-budget) mapping. Since then, LiteLLM added a separatereasoning_effort→thinkingLevelpath for Gemini 3+ models (_map_reasoning_effort_to_thinking_level), so the docs were out of sync with the implementation.Details
The new table mirrors the current logic in
vertex_and_google_ai_studio_gemini.py:*-flashmodels support theminimalthinking level; other Gemini 3+ models floor tolow.gemini-3.1-pro-previewmapsmedium→medium, whereas other non-flash Gemini 3+ models (e.g.gemini-3-pro) mapmedium→high.includeThoughts: true, exceptdisable/none, which setincludeThoughts: false(Gemini 3 cannot fully disable thinking, so the lowest level is used with thoughts hidden).Docs-only change; no code touched. The older thinkingBudget table is left unchanged.
Closes #267
🤖 Generated with Claude Code