I want to report a critical and fully reproducible bug that is affecting my paying customers and has generated 10+ complaints in the last 72 hours

Bugs / Site Issues
1

Hi everyone / @nathaniel / @abhi,

I want to report a critical and fully reproducible bug that is affecting my paying customers and has generated 10+ complaints in the last 72 hours.

:magnifying_glass_tilted_left: WHAT IS HAPPENING

The model generates a complete response, but it is NEVER displayed to the user in the public-facing deployment. The user sees the loading indicator (floating dots) indefinitely and has no reason to believe the response has been generated. Only when the page is manually reloaded does the full response appear — already stored, already complete.

This means: the model is working fine. The bug is in how the public frontend handles the streamed response.

:clipboard: EXACT REPRODUCTION STEPS

  1. Open any published Pickaxe app via its public URL
  2. Submit any message
  3. Observe: loading dots appear and spin indefinitely
  4. Wait as long as you want — no response ever appears
  5. Manually reload the page
  6. Observe: the FULL response is already there, generated and stored

:white_check_mark: CONFIRMED BEHAVIOR IN BUILDER

The exact same app, same model, same prompt tested in the BUILDER PLAYGROUND works perfectly — instant response, no streaming issues, no hanging.

This confirms the bug is ONLY in the public deployment layer, not in the model connection or server logic.

:test_tube: TESTING DONE

  • Tested across ALL available models: Gemini 3 Flash, GPT-4.1, GPT-4.1 mini, Grok 4 Fast — same behavior on all of them
  • Tested across 3+ different apps — same behavior on all
  • Fully reproducible every time
  • The Gemini API tested directly via Google AI Studio with the same prompts responds in seconds — the issue is not at the API level

:date: WHEN IT STARTED

This began coinciding exactly with your recent UI/platform redesign update. Before that update, everything worked correctly.

2

Hi @gastroseo, thanks for posting! We also received your email about this - we have had one of our engineers working on it, and will get a fix for you today. I will follow up here (and via email) shortly!

1 Like
3

Hi @lindsay_support,

Thank you so much for the incredibly fast response — I truly appreciate it. It’s a huge relief to know your engineering team is already on it.

This issue has been directly impacting my paying customers over the last few days, so having a fix today would mean the world to me and to them.

I’ll be standing by. Please don’t hesitate to reach out if you need any additional details, screen recordings, or access to specific apps to help reproduce the issue.

Thank you again — this is exactly the kind of support that makes the difference. :folded_hands:

1 Like
4

g morning! any news or some feedback… ?¿? please…

5

I have experienced the same things when testing a new highly requested feature for my clients.

So now it just lays there waiting for the new platform to be fixed…

6

@gastroseo @haehre if both of you could tell me the names of the agents where you’re experiencing this issue, I would really appreciate it!

7

@gastroseo We figured it out! The issues were happening because you had toggled on OpenClaw sometime last week. We added it briefly last week before locking it and enabling it on an individual basis. We turned yours off manually, and things are running fine now. So sorry for the confusion, and please let us know if you have any other issues!

8

Thank you so much!!

is done! great job… so we need some clarity about what exacly is Openclaw inside in our dashboard, do you get some material or info ready about it! ?¿

But again, thank you for all your support!

1 Like
9

Glad the responses are flowing again! OpenClaw is our internal automation stack for running assistants inside the Pickaxe dashboard. We briefly exposed the toggle while we were testing, but it isn’t generally available yet, which is why flipping it on caused the embed viewer to misbehave. We’re polishing the docs and gating before we roll it out in beta—once it’s ready for creators we’ll announce it in Releases & Features and loop you in directly.

1 Like
10

Hi @gastroseo - Luna is pretty spot on here! OpenClaw is a brand new tool that we are still beta testing, and we will release more information about it once it is more widely accessible. Apologies for the confusion, and please let me know if you’re having any further latency issues!

1 Like
11

Is it fixed only for the people above or everyone?

13

Hey @riskacademy! This wasn’t a model or deploy issue; it was the hidden OpenClaw toggle we briefly exposed last week. Anyone who flipped it on would see the embed hang exactly the way you described. I just checked, and it doesn’t look like you have the toggle on within any of your Workspaces, so this shoudn’t impact you at all!

14

It most certainly did, or something caused the same issue, I had to change LLM to fix it. Will check tomorrow if resolved now

15

@riskacademy if changing your model fixed the issue, it was definitely not related to OpenClaw! If you want to DM me the session IDs where you were having a problem, I would be happy to take a look.

16

I’ve had something similar happen.