improve default model settings

[p-]

this change improves the default model settings as a first step.
in a second step we also might want to comment model_config.yaml to make it more clear how to change models and their settings for different steps.

[Copilot]

Pull request overview

Updates the repository’s model configuration defaults to use a newer code_analysis model and align default model settings across configs used by taskflows.

Changes:

• Update code_analysis model from gpt-5 to gpt-5.2 for the CodeQL Python model config.
• Add model_settings defaults (temperature + reasoning effort) to the main model_config.yaml.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
src/seclab_taskflows/configs/model_config_codeql_python.yaml	Bumps code_analysis to gpt-5.2 in the CodeQL Python-specific model config.
src/seclab_taskflows/configs/model_config.yaml	Adds default model_settings for code_analysis and normalizes the config structure.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

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