Repository navigation
fix(review): gate direct text batch submission - #1242
Draft
seonghobae wants to merge 1 commit into
Draft
seonghobae wants to merge 1 commit into
seonghobae wants to merge 1 commit into
Conversation
|
Important Draft PR not reviewedDraft PRs are not automatically reviewed by default.
To automatically review draft PRs, update your CodeRabbit configuration: reviews:
auto_review:
drafts: trueThanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Scope
Issue #1106 follow-up stacked on Draft #1241. A direct
CostRoutingCoordinator.submit_batchcall could submit synthetic review text work to a batch backend while review allocation evidence was unavailable. The existing non-ZDR resolution returns requests unchanged, and the library API had no review preflight. The HTTP/api/v1/batch_routing_jobsroute shares that submission path.The change checks every batch item with the existing review allocation guard before target resolution or backend submission. The guard is outside the RuntimeError-to-BatchModelSelectionError conversion so its typed 400/503 response survives. Non-review coordinators retain the previous behavior.
RED and GREEN
c2c72b6d: synthetic explicit-model direct batch reached mocked backendsubmitand failed the no-send assertion.10133087: direct and HTTP batch requests return nonretryable 400review_model_not_allowedfor an explicit member or nonretryable 503allocation_evidence_unavailablefororchestrator/free; zero backend submissions.Ingress inventory before commit: HTTP media/rerank routes share
proxy_capability(#1240); sync/batch embedding HTTP uses_require_pool_model, and direct embedding batches usesubmit_embeddings_batch(#1241); text batch HTTP and direct library callers usesubmit_batch(this PR); synchronous Chat/Responses routes entercomplete/proxy_completionadmission (#1235). Retrieval/poll routes act on previously owned job handles and do not submit new work.Draft/HOLD. No real data, secrets, provider egress, merge, or deployment. Required hosted checks, independent approval, calibrated allocation release, and consumer migration remain open.