Repository navigation
feat(scan): choose model, reasoning effort and cost limit per scan - #37
Closed
strantalis wants to merge 1 commit into
Closed
strantalis wants to merge 1 commit into
strantalis wants to merge 1 commit into
Conversation
The scan review in the Desktop panel and the terminal, and the security_scan tool, accept a reasoning effort, a cost limit and a model for one scan. Unset values come from the config as before. Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016LiHJtDpo3TEPnWZ78vM2X
Owner
Author
|
Landed in main through #39, which carried this branch after the base of this PR was deleted. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Stacked on #36.
For one scan you can now set the reasoning effort, a cost limit and the model:
rreasoning,lcost limit,omodel.security_scanacceptsreasoningEffort,maxCostUsdandmodel. The approval preview shows the resolved model and effort.Anything left unset comes from the config. The values are kept with the scan, so "Run again" carries them over. Effort is passed to Codex as given; the forms offer low, medium, high and xhigh.
npm run checkpasses with a new test. I checked the Desktop form in the preview harness. Not checked: the terminal review in a real OpenCode, or a real scan started with an override.🤖 Generated with Claude Code
https://claude.ai/code/session_016LiHJtDpo3TEPnWZ78vM2X