How do I test AI agent frontends without calling the API?

Capture prod streams as JSONL with AgentStreamRecorder. Replay via async generators in tests. Patch your agent—done.

What is AgentStreamRecorder?

Open-source tool logging AI agent event streams to JSONL. Timings, events, all preserved for replays.

Can JSONL replays handle parallel tools and errors?

Yes—real prod sequences include out-of-order arrivals, drops, everything. Perfect for edge cases.

Replay Hell: Testing AI Agent Frontends with Production Ghost Streams

AI agent UIs are flaky nightmares in tests. One dev's trick: hijack production streams as fixtures. No more real API hits, just pure, replayable determinism.

Open Source Beat Apr 03, 2026 4 min read 14 views

Code snippet replaying AI agent stream from JSONL fixture in pytest

⚡ Key Takeaways

Turn prod JSONL logs into deterministic test fixtures for AI agent streams—no API calls needed. 𝕏
Replays catch real-world timing bugs mocks miss, like out-of-order parallel tools. 𝕏
This is the VCR pattern reborn for AI; expect it to standardize fast. 𝕏

Published by

Open Source Beat

Community-driven. Code-first.

#AI agent testing #AgentStreamRecorder #JSONL replays #frontend testing

Worth sharing?

Get the best Open Source stories of the week in your inbox — no noise, no spam.

Originally reported by Dev.to

⚡ Key Takeaways

The 60-Second TL;DR

Open Source Beat

Share this article

Worth sharing?

Related Stories

95% of AI Projects Fail Because We're Using the Wrong Playbook

GPU Rowhammer Is No Longer Theory: How GPUHammer Breaks NVIDIA Graphics Memory

Opus 4.5 Just Rewired How Developers Code—And Nobody's Ready for What's Next

I Replaced $10/Day in API Costs With a Free Local Model—Here's How

Stay in the loop