Bugs

Issue Summary The @taskade/automade-internalpiece-taskade/task.flow_triggered trigger has a schema validation mismatch that causes all workflows using this trigger to fail immediately with a validation error, preventing any workflow actions from executing. Bug Details Trigger Name: task.flow_triggered Piece: @taskade/automade-internalpiece-taskade Completely blocks workflow execution Expected Behavior When a user clicks the "Run Flow" button on a task in a project: The trigger should fire successfully The trigger should provide the full task data according to its resultSchema Workflow actions should execute normally Actual Behavior ❌ Immediate validation error before any actions execute ❌ All workflow actions show status: "pending" (never executed) ❌ Error message: "Expected object, received string" The trigger's declared resultSchema expects a rich object with properties like: nodeText (task content) nodeNote (task description) projectId nodeId startDate endDate assignees[] etc. But the actual trigger payload only provides: { "nodeId": "string", "projectId": "string" } Example Error Log { "trigger": { "type": "failed", "errorDesc": { "message": "[\n {\n \"code\": \"invalid_type\",\n \"expected\": \"object\",\n \"received\": \"string\",\n \"path\": [],\n \"message\": \"Expected object, received string\"\n }\n]" }, "input": { "data": { "nodeId": "65521979-bd4c-4b96-aa0b-b3e843aa5dd3", "projectId": "cNndNEeW94Mady3K" }, "type": "TRIGGER_PAYLOAD" } } }

I'm adding tasks with specific due dates, but some of them don't appear on the global calendar (the one where all projects are shown).

After either doing certain things or nothing at all, I can no longer see the cursor, cant click things, cant really do anything. Also adding custom fields to tables crashes taskade where everything is pretty much frozen. Constantly have to refresh the window.

I don't know what happened, but suddenly everytime I talk to my AI agent, the page freezes and crashes completely.

In the last few days I notice almost none of my agents are working (that I created prior or recently). They cannot even answer a simple question "Can you summarise what is in your instruction?" It used to answer it right away. Repeatedly deleted and recreated the agent, log out & in to Taskade, restarted browser but same issue occurs. A week ago I were able to automate task complete / Ask Agent / Create Project now it is or time out or say "Ask Agent Failed: 400 This Model's Maximum Context Length Is 128000 Tokens. However, Your Messages Resulted In 769997 Tokens (769928 In The Messages, 69 In The Functions). Please Reduce The Length Of The Messages Or Functions." but it is the same Agent that created for me many form of content in the past. When it does work, for example the new feature Multi agent mode in the Project /and call agent do not remember any of the customisation (neither the custom instruction nor the knowledge files.

Public agents are not able to inform today's date accurately. Even when a link for a real time clock is added to the KB, it will train once and never retrieve it again, therefore when the conversation involves date, it always gets wrong.

After the recent UI updates, I can't find the sidebar that lets me search AI agents across all projects. Has it been moved or changed? Any help would be great!

I have been trying to make several apps recently and the API/network connection errors are abundant to say the least and it seems the AI can't get past them and I end up rebuilding the app.