Skip to content

Remove hard-coded models from examples #103

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
kevinbackhouse merged 3 commits into from
Dec 2, 2025
+7 −6
Merged

Remove hard-coded models from examples #103

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
96c2af9
Remove hardcoded models from examples.
kevinbackhouse Dec 2, 2025
780ef2a
Use gpt_default
kevinbackhouse Dec 2, 2025
0315a96
Merge branch 'main' into remove-hardcoded-models
kevinbackhouse Dec 2, 2025
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
1 change: 0 additions & 1 deletion examples/taskflows/echo.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,6 @@ seclab-taskflow-agent:

taskflow:
- task:
model: claude-3.5-sonnet
max_steps: 5
must_complete: true
agents:
Expand Down
6 changes: 4 additions & 2 deletions examples/taskflows/example.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,13 @@ seclab-taskflow-agent:
version: 1
filetype: taskflow

# Import settings from a model_config file.
model_config: examples.model_configs.model_config

taskflow:
- task:
# taskflows can optionally choose any of the support CAPI models for a task
model: gpt-4.1
model: gpt_default
# taskflows can optionally limit the max allowed number of Agent task loop
# iterations to complete a task, this defaults to 50 when not provided
max_steps: 20
Expand Down Expand Up @@ -41,7 +44,6 @@ taskflow:
- seclab_taskflow_agent.toolboxes.codeql
- task:
must_complete: true
model: gpt-4.1
agents:
- seclab_taskflow_agent.personalities.c_auditer
user_prompt: |
Expand Down
4 changes: 3 additions & 1 deletion examples/taskflows/example_reusable_taskflows.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,9 +5,11 @@ seclab-taskflow-agent:
version: 1
filetype: taskflow

model_config: examples.model_configs.model_config

taskflow:
- task:
# with the `uses` directive we can reuse single task taskflows
uses: examples.taskflows.single_step_taskflow
# and optionally override any of its configurations
model: gpt-4o
model: gpt_latest
1 change: 0 additions & 1 deletion examples/taskflows/example_triage_taskflow.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,6 @@ taskflow:
toolboxes:
- seclab_taskflow_agent.toolboxes.memcache
- task:
model: gpt-4.1
repeat_prompt: true
agents:
# primary agent for this task
Expand Down
1 change: 0 additions & 1 deletion examples/taskflows/single_step_taskflow.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,6 @@ seclab-taskflow-agent:

taskflow:
- task:
Comment on lines 8 to 9
Copy link

Copilot AI Dec 2, 2025

Choose a reason for hiding this comment

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

The model reference was removed, but this file is being reused in example_reusable_taskflows.yaml which now references model_config: examples.model_configs.model_config and overrides with model: gpt_latest. However, single_step_taskflow.yaml itself doesn't have the model_config import. Consider adding model_config: examples.model_configs.model_config to this file for consistency and clarity, especially if it's meant to be reusable.

See below for a potential fix:

  filetype: taskflow
  model_config: examples.model_configs.model_config

Copilot uses AI. Check for mistakes.
model: gpt-4.1
agents:
- seclab_taskflow_agent.personalities.assistant
user_prompt: |
Expand Down