fix(session): preserve context after user interrupts #2563
+18
−3
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
ribelo
force-pushed
the
dev
branch
2 times, most recently
from
79acdc6 to
9d2ae75
Compare
|
This solution is a partial. We have a case with subagents. After interruption inside child conversation, it just finished and the main agent always thinking a delegated task was done. But for fixing this problem will need major refactoring I think |
ribelo
added a commit
to ribelo/opencode
that referenced
this pull request
Sep 12, 2025
When a subagent is interrupted (Ctrl+C), the Task tool was returning a successful result instead of propagating the error. This caused parent agents to incorrectly believe delegated tasks completed successfully. Changes: - Check result.info.error after subagent execution - Throw an error when subagent was interrupted or errored - Include partial output from interrupted subagents in error message - Distinguish between AbortedError and other errors This ensures parent agents correctly detect when delegated tasks are interrupted, fixing the edge case identified by NaikSoftware in PR sst#2563.
|
@NaikSoftware done |
kmk142789
approved these changes
Sep 13, 2025
…ption state This commit addresses two critical interruption handling issues: 1. Context preservation after interruption (fixes sst#2554): - Messages with AbortedError are preserved in context (already in prompt.ts) - filterSummarized() ignores errored summaries (message-v2.ts) - prune() ignores errored summaries when checking compaction (index.ts) 2. Subagent interruption propagation: - Task tool now checks result.info.error after subagent execution - Throws error when subagent was interrupted or errored - Includes partial output from interrupted subagents in error message - Parent agents correctly detect when delegated tasks are interrupted This ensures the model remembers work done before interruption and parent agents properly handle interrupted subagent tasks.
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.
#2554
Prior behavior dropped all assistant messages with any error flag, so Ctrl+C (AbortError) removed crucial context like read files and patches. This caused the model to ‘forget’ work after an interruption.
Change: when building provider messages, filter out assistant messages only if error exists and it is not MessageAbortedError. Aborted messages now remain in context; genuine failures (auth/output length/unknown) are still excluded. Also ensure summaries with errors are not treated as lastSummary anchors.
Includes: adjust lastSummary lookups to ignore errored summaries.
Edge cases considered: multiple interrupts, partial tool calls are marked error on parts but message retained; stopWhen short-circuits on permission rejects; compatibility with MessageV2.AbortedError schema.
It seems to help, but I don’t know if it breaks something else.