fix: start agents before submitting intent to avoid SSE race#74
Merged
George-iam merged 1 commit intomainfrom Mar 24, 2026
Merged
fix: start agents before submitting intent to avoid SSE race#74George-iam merged 1 commit intomainfrom
George-iam merged 1 commit intomainfrom
Conversation
The SSE init phase skips all existing events to find the cursor. When the intent was created BEFORE agents started listening, the init phase would skip past the delivery event — causing the agent to never process it. This was especially visible on macOS where network latency to the cloud server is higher. Now agents start listening (step 3) before scenarios apply (step 4), with a 500ms settle time to ensure SSE connections are established.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
scenarios applycreates the intent (step 4)Test plan
axme examples run delivery/streamon macOS — completes without hangingaxme examples run full/multi-agenton macOS — both agents process promptlyaxme examples run human/cli— still works (has agent + human step)go test ./...passes