-
Notifications
You must be signed in to change notification settings - Fork 3
Support Model #2
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.
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
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for adding the configurable model input and updating the action reference. I left two small, high-confidence suggestions focused on security and docs clarity.
| uses: augmentcode/augment-agent@6f08f56902d6728a0ffbbb2004c136c06fec8104 # v0.1.0 | ||
| uses: augmentcode/augment-agent@v0 | ||
| with: | ||
| augment_session_auth: ${{ inputs.augment_session_auth }} |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Using a mutable tag (@v0) makes the workflow susceptible to supply‑chain issues if the tag is moved. Consider pinning to an immutable commit SHA and keeping a comment for readability, for example:
uses: augmentcode/augment-agent@<commit_sha> # v0This preserves security while still signaling the intended major/minor version.
| | `repo_name` | The full name (owner/repo) of the repository | Yes | `${{ github.repository }}` | | ||
| | `custom_guidelines` | Custom guidelines for PR descriptions (optional) | No | See [Custom Guidelines](#custom-guidelines) section | | ||
| | `model` | Optional model to use for generation | No | e.g. `gpt-4o`, `claude-3-5-sonnet`, etc. | | ||
|
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nice addition. To improve discoverability, consider adding a quick usage example that shows how to set model in the workflow, e.g. in one of the examples:
with:
# ...existing inputs
model: gpt-4oThis helps users understand exactly where/how to pass the new input.
README.md
Outdated
| | `pull_number` | The number of the pull request being described | Yes | `${{ github.event.pull_request.number }}` | | ||
| | `repo_name` | The full name (owner/repo) of the repository | Yes | `${{ github.repository }}` | | ||
| | `custom_guidelines` | Custom guidelines for PR descriptions (optional) | No | See [Custom Guidelines](#custom-guidelines) section | | ||
| | `model` | Optional model to use for generation | No | e.g. `gpt-4o`, `claude-3-5-sonnet`, etc. | |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The example should probably be a model that's publicly available (sonnet4 or gpt5)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yup, I forgot to check this. Will update.
Add optional model selection for PR description generation
modelinput to the action. This value is passed through toaugmentcode/augment-agentto choose the LLM used for generation (e.g.,gpt-4o,claude-3-5-sonnet). When omitted, the agent’s default model is used.modelinput in the README inputs table with examples.augmentcode/augment-agentreference from a pinned commit to the@v0tag to track the latest minor updates of the agent.Impact
🤖 This description was generated automatically. Please react with 👍 if it's helpful or 👎 if it needs improvement.