Repository navigation
Validate coding-task execution preferences before writes and launch - #654
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Coding assignments could persist agent/display labels as model IDs and
extra_high/extra-highas reasoning settings, then fail before coding began. Task creation, field updates and the worker now share a narrow token validator that rejects those demonstrated mistakes with corrective guidance before persistence or launch. Corrected retries create one canonical assignment; rejected field updates leave status and notes intact.Exact model IDs and other model-advertised reasoning tokens remain unchanged. This is deliberately not a frozen availability catalogue: provider/account availability and model-specific compatibility still belong to Codex. No model is inferred from an agent label, no default changes, and existing assignment authority remains unchanged. The worker binds its selected backend before importing validation, including on fresh release startup.
Validation: 192 targeted tests passed across task creation/recovery, service/routes, worker/inbox, coherent release installation and deployment rollback. This includes the ordinary-turn trusted payload and real handler/service path against an isolated native store, wrong-scope denials, duplicate/retry checks, no partial invalid updates, rejection without invoking Codex, and a fresh-process selected-release import with task-sourced Astra/xhigh. The affected replay fixture now binds the newer access read path to its isolated database. Formatting and diff checks passed.
Merge decision: ready; the demonstrated recurrence is covered without widening the task. JVNAUTOSCI-2750. Publication and deployment are authorised; the controller will receive the exact merged SHA for public deployment and coherent worker selection. The previously installed e596e18 release was independently observed in the scheduled runtime receipt and local health; this PR does not claim its own activation before controller deployment.