Uh oh!
There was an error while loading. Please reload this page.
fix(runtime): make task refusals actionable - #2527
Merged
Merged
Conversation
Astro-Han
approved these changes
Aug 8, 2026
Uh oh!
There was an error while loading. Please reload this page.
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 freeto 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes#2310.
What changed
pending -> completedrefusal now tells the model to mark the taskin_progressfirst, then retrycompletedwithcompletionEvidence.agent_spawncall now points toagent_list -> subagent_idand lists the legacy profiles available in the current composition.This keeps the current
subagent_id-first behavior: when both selectors are present,subagent_idstill wins andprofileis ignored.Verification
npm --workspace @maka/core test— 802 passednode --test packages/runtime/dist/__tests__/subagent-tools.test.js— 29 passednode --test packages/runtime/dist/__tests__/task-ledger-tools.test.js— 19 passednpm --workspace @maka/core run typechecknpm --workspace @maka/runtime run typecheckThe full runtime suite completed 3,251 tests locally: 3,221 passed, 3 skipped, and 27 failed in the untouched
model-factory-tool-call-index.test.json Node 26.3.0.