Skip to content

improve default model settings #61

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
p- merged 1 commit into from
Mar 7, 2026
Merged

improve default model settings #61

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion src/seclab_taskflows/configs/model_config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,4 +7,9 @@ seclab-taskflow-agent:
models:
code_analysis: gpt-5.2
general_tasks: gpt-4o
triage: claude-sonnet-4
triage: claude-sonnet-4
model_settings:
code_analysis:
temperature: 1
reasoning:
effort: high
2 changes: 1 addition & 1 deletion src/seclab_taskflows/configs/model_config_codeql_python.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ seclab-taskflow-agent:
version: "1.0"
filetype: model_config
models:
code_analysis: gpt-5
code_analysis: gpt-5.2
general_tasks: gpt-4o
Comment on lines 7 to 9
Copy link

Copilot AI Mar 7, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

model_config_codeql_python.yaml is now identical to the default model_config.yaml (same models and model_settings). If there are no CodeQL-specific overrides, consider removing this duplicate config and updating taskflows to reference seclab_taskflows.configs.model_config to avoid future drift; otherwise, document/introduce the intended differences here.

See below for a potential fix:

   codeql_python_code_analysis: gpt-4o-mini
model_settings:
  code_analysis:
    temperature: 1
    reasoning:
      effort: high
  codeql_python_code_analysis:
    temperature: 0
    reasoning:
      effort: medium

Copilot uses AI. Check for mistakes.
triage: claude-sonnet-4
model_settings:
Expand Down