fix(recovery): preserve failed MCP state for deterministic retry (Phase 28-01) - #20
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
McpExceptionfailures inGsdStateMachinenow persist the actual failed state instead of rolling checkpoints back toIdle, soResumeAsyncretries the failing state once and then halts deterministically.planning/phases/28-fault-injection-recovery/28-01-SUMMARY.mdin the workstation repo)Provenance
Work was completed and verified 2026-07-07 but the branch was never pushed — caught by the Phase 36 doc-verifier refusing to document it as "in progress (PR #N)" when no PR existed. Rescued per workspace guardrails.
Merge order
Independent of #16 (coverage gates) and #18 (SHA pins); if CI conflicts arise on shared test files, land #16 first then
gh pr update-branch.🤖 Generated with Claude Code