chat: once its fix is in, the agent offers to resume the failed run - #72
Merged
Merged
Conversation
The fix task now tells the agent, when the runtime can resume, to call the `resume_failed_run` chat tool once its fix is applied. The tool asks the person (Resume / Not now) and, on Resume, reruns the workflow from the failed run's directory at its last completed step -- where it failed -- so what ran before is replayed from the journal rather than run again. The driver remembers the last failed run per workflow file (forgotten once that workflow runs clean); the tool falls back to the last failure, so a chat session opened on a nested workflow's file still finds it. Claude-Session: https://claude.ai/code/session_015VK7fH1c4aKbexnq2QcuKU
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follow-up to #71 (Fix with AI).
cliResumeArgs), to call the newresume_failed_runchat tool once its fix is applied.<runWorkflow>.resumeFailedcommand, which asks the person Resume / Not now. On Resume, it reruns from the failed run's directory at its last completed step (resumeStepForwithatLastStep), so what ran before is replayed rather than run again. The tool returns a text result the agent can relay.cliResumeArgs.Tests:
resume-failed-run.test.tscovers resume, decline, the nested-file fallback, clearing after a clean run, a runtime without resume, and the tool handler. The prompt assertions and the registered-command count are updated.https://claude.ai/code/session_015VK7fH1c4aKbexnq2QcuKU