Repository navigation
Keep checkpoints usable after token counting outages - #21
Merged
Merged
Conversation
This was referenced Oct 8, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When a provider input-token counting outage occurs during context preparation, preserve the existing checkpoint and propagate the counting diagnostic. Do not record it as a permanent summary failure: that latch otherwise prevents continuation even after counting recovers. Actual compaction failures retain their existing handling.
Validation in the project-owned DTU: the 453-test context suite passed; the final focused continuity tests passed at initial measurement, compaction measurement, and post-compaction measurement. Each verifies unchanged canonical history and checkpoint after failure, no foreground generation, and successful later continuation and checkpoint restoration.
Recognizes the optional OpenAI provider counting exception without importing the provider SDK. Companion provider PR supplies bounded retries and sanitized diagnostics; loop-live and Unified changes display those diagnostics.
Related changes: provider #123, context #21, loop #14, Unified #468. Deploy the context and loop changes before or alongside the provider change.