Reuse terminal research AI jobs without duplicate model execution - #176
Merged
Conversation
Co-Authored-By: Codex <noreply@openai.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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Repeated submissions of the same research AI request now return its unexpired terminal job before quota admission, avoiding another model invocation after success or failure. Persisted request authority binds repository, run/attempt, actor, ref and workflow identities; different requests or identities do not share results. Restart-orphaned work retains its failure instead of being replayed.
This uses the existing job store and preserves active-only deduplication for other tasks. It addresses AI job recovery only; numeric-stage recovery and research promotion are unchanged.
Validation: the original implementation failed the three terminal-reuse regressions; the relevant combined suite passed 53 tests and 33 subtests (1 deselected). Ruff, compileall and diff checks passed. Eight expanded consumer tests fail identically on the base and patch with the local external QuantStrategyPlugins installation; required CI must validate the repository's pinned dependency environment. No real AI request was replayed.