Repository navigation
Preserve shared-turn context and verify task creation (JVNAUTOSCI-2739) - #610
Merged
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Outcome
Shared turns retain accepted participants, exact speaker identities, and the source actor/org scope of historical observations. Task creation is treated as a valid outcome, separate from executing the work recorded in a task.
Smallest adequate changes
Validation and release decision
Merge decision changes — ready, subject to required CI. 122 affected-path tests and 25 focused adaptive-turn tests pass. New-file Ruff, affected-file fatal Ruff and diff checks pass. Coverage includes accepted/pending/revoked/foreign participants, no profile lookup for nonparticipants, preserved source history, actual provider text projection, window scope, private-task denials, verified pending records, partial/wrong-ID read-backs, and retry reconciliation.
Three bounded synthetic gpt-5.6-luna checks proposed a fresh exact task read after a scope change, proposed only task creation for an explicit task-only request, and resolved participant IDs correctly. Tool proposals were not dispatched. These are bounded observations, not a guarantee for arbitrary prompts.
No real user tasks, messages, authority grants, or deployments changed. Stop-ship conditions are leaked private metadata, lost source text, changed authority, or falsely verified task creation.
Tracking: https://naoinstitute.atlassian.net/browse/JVNAUTOSCI-2739