Repository navigation
Inspect the current Codex candidate under its source credentials - #276
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Target probes can reject a candidate even after source acquisition completed. The existing diagnostic only selects targets, so it cannot distinguish a candidate that fails the source's own STATE check from one that fails after transfer to the target.
Allow the probe-only contract scenario to select a configured source for one plaintext Astra pair against the same source's current live candidate. It does not acquire a replacement or substitute another source, cannot enter generation or test a different source model, and preserves local tier-policy rejection. Results identify the subject as source or target and never publish business qualifications, usage success or account-health changes. Existing authentication, audit, cancellation, expiry and eight-request limits remain in place.
Validation: source ownership, one-pair request count, unchanged model/encoding, no generation or qualification writes, rejection of another model and missing candidates, plus the existing target comparison regression pass. This adds the missing observation; it does not claim the remaining live borrowing failure is fixed.