fix: rebuild tool catalog after wide-native rlm showcase - #656
Closed
justrach wants to merge 2 commits into
Closed
Conversation
ADR 0030 showcased rlm after a 4-wide read/bash batch and only invalidated the cached catalog. The next xAI Responses body was `"tools":,` (empty toolsJson printed after the field), so scatter-sum and multi-read 400'd mid-turn. Rebuild on showcase, ensure before every request, and write [] for an empty catalog so that shape cannot reach the wire.
justrach
marked this pull request as ready for review
August 28, 2026 02:05
Invalidate-only after a 4-wide native batch shipped `"tools":,` and xAI 400'd the rlm rematch. Comments at the call sites plus ADR 0030 name the failure so this does not get "simplified" back.
Owner
Author
|
280-port of the rlm catalog rebuild already on main. Closing as superseded. |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Cherry-pick of #655 onto
release/v0.0.280.ADR 0030 showcased
rlmafter a 4-wide native batch and only invalidated the cached catalog. The next xAI Responses body was"tools":,, soscatter-sumandmulti-read400'd mid-turn (rlm rematch 3/5). SWE was fine because those tasks never hit a 4-wide native batch.Same fix as #655: rebuild on showcase,
ensureRootToolsbefore every request, write[]for an empty catalog. Follow-up commit comments the call sites and ADR 0030 so later agents do not revert this to invalidate-only.Live rematch SuperGrok / grok-4.6 / grok-build 1.0.5:
Grok skips
schema-output(no structured-output capability). Graff missed that one this rep. Both still miss SWElabel-sort.