xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-08 14:50:40 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1605 from KennyDizi/main

Browse Source 
Support extended thinking for model `claude-3-7-sonnet-20250219`
This commit is contained in:
Tal
2025-03-09 17:03:37 +02:00
committed by GitHub
parent 2619ff3eb3 222155e4f2
commit 52c99e3f7b
4 changed files with 65 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
docs/docs/usage-guide/changing_a_model.md
View File

@ -234,3 +234,10 @@ To bypass chat templates and temperature controls, set `config.custom_reasoning_
reasoning_efffort= = "medium" # "low", "medium", "high"
With the OpenAI models that support reasoning effort (eg: o3-mini), you can specify its reasoning effort via `config` section. The default value is `medium`. You can change it to `high` or `low` based on your usage.
### Anthropic models
[config]
enable_claude_extended_thinking = false # Set to true to enable extended thinking feature
extended_thinking_budget_tokens = 2048
extended_thinking_max_output_tokens = 2048