Kernel: silent fallback on pre-execution compile failures - #353
Merged
Conversation
Compile-stage failures happen before any timeline mutation, so the legacy loop can still serve the request; the failure detail stays in the KernelGateway log. Honest user-facing failures remain reserved for post-execution states (deferred rollback, fingerprint mismatch). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Deploying masterselects with
|
| Latest commit: |
e4735b1
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://f8986ea5.masterselects.pages.dev |
| Branch Preview URL: | https://staging.masterselects.pages.dev |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Compile-stage kernel failures (before any timeline mutation) now fall back to the legacy chat loop instead of surfacing an opaque error; details stay in the KernelGateway log.
Pairs with kernel-side fixes already deployed: cut-count requests ("mache N schnitte" / "make N cuts") compile mechanically as N+1 even clips with zero provider cost, and story runs whose assembly beats all collide fail honestly with a recovery hint instead of succeeding without a winner.
🤖 Generated with Claude Code