fix: use correct thinking for Gemini 2.5 vs Gemini 3

This commit is contained in:
ElshadHu
2026-01-11 04:19:57 -05:00
parent 75e578b5fc
commit 72d438e53a
2 changed files with 8 additions and 8 deletions

View File

@@ -48,7 +48,7 @@ AI_MODEL=global.anthropic.claude-sonnet-4-5-20250929-v1:0
# GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json # Path to service account key file
# Note: When running on GCP (Cloud Run, GKE, Compute Engine), uses Application Default Credentials automatically
# GOOGLE_VERTEX_THINKING_BUDGET=8192 # Optional: Gemini 2.5 thinking budget in tokens (1024-100000)
# GOOGLE_VERTEX_THINKING_LEVEL=high # Optional: Gemini 3 thinking level (minimal/low/medium/high)
# GOOGLE_VERTEX_THINKING_LEVEL=high # Optional: Gemini 3 thinking level (low/high)
# Azure OpenAI Configuration
# Configure endpoint using ONE of these methods: