Repository navigation
feat: add per-harness default effort settings - #204
Merged
Merged
Conversation
Signed-off-by: Tiberiu Socaci <tsocaci@makeitfuture.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Inherited harness runs currently have no configurable effort alongside their default model. Add default effort selectors for Claude, Codex and each Qwen provider, persisted and validated against the selected model. Fresh and resumed turns inherit these defaults after request/thread/channel choices; blank keeps the CLI default, and failover uses the destination harness default.
Validation: full
npm run test:coverage, real Chromium settings save/reload/clear,npm run check:static, secret scan and DCO. Security coverage and production dependency audit also passed (no high/critical findings). Regression coverage verifies actual Claude/Codex flags, precedence, clearing, atomic pair validation, model retries and failover. Live dual-engine acceptance is defined in TEST-PLAN.md and remains pending; stub/browser checks are not live engine passes.