[Bug]: GENERATION_FAILED (fp: 69213336)

[fabianmcja]

Description

Hi awesome app trying to create content but my card are not so powerful sometimes take a lot o time to generate content maybe that create the time out in the app

Steps to reproduce

ask the ia y call ollama from a proxmox server runing in the 11434 port

Expected behavior

create a chat bot

Actual behavior

Error invoking remote method 'codesign:v1:generate': CodesignError: Generation aborted after 1200s (Settings → Advanced → Generation timeout). — user notes: 2 RTX 5060 TI 16 GB TIME OUT OF RESPONCE

open-codesign version

0.1.4

Platform

Windows

OS version

Windows 11 (10.0.26200)

Model provider (if relevant)

None

Error code

GENERATION_FAILED

Diagnostics bundle

Bundle saved locally at ~\Downloads\open-codesign-diagnostics-2026-05-04T01-16-43.zip. Attach it to this issue after submitting.

Logs

}
[2026-05-03 20:16:30.405] [info]   (chat-messages-ipc) chat.append {
  designId: '739dbd64-92f7-4300-b9b1-027a2a448e39',
  seq: 106,
  kind: 'tool_call'
}
[2026-05-03 20:16:30.405] [info]   (chat-messages-ipc) chat.append {
  designId: '739dbd64-92f7-4300-b9b1-027a2a448e39',
  seq: 107,
  kind: 'assistant_text'
}
[2026-05-03 20:16:40.378] [info]   (main:ipc) agent.tool_start {
  runId: 'moqicqna-3b92mr',
  generationId: 'moqicqna-3b92mr',
  tool: 'str_replace_based_edit_tool'
}
[2026-05-03 20:16:40.379] [info]   (main:ipc) agent.tool_end {
  runId: 'moqicqna-3b92mr',
  generationId: 'moqicqna-3b92mr',
  tool: 'str_replace_based_edit_tool',
  isError: true
}
[2026-05-03 20:16:40.380] [info]   (main:ipc) agent.turn_end {
  runId: 'moqicqna-3b92mr',
  generationId: 'moqicqna-3b92mr',
  deltas: 17,
  tools: 1
}
[2026-05-03 20:16:40.381] [info]   (main:ipc) agent.turn_start { runId: 'moqicqna-3b92mr', generationId: 'moqicqna-3b92mr' }
[2026-05-03 20:16:40.382] [info]   (main:ipc) [context-prune] step=caps {
  runId: 'moqicqna-3b92mr',
  generationId: 'moqicqna-3b92mr',
  messages: 29,
  before: 55289,
  after: 45699,
  textLimit: 8192,
  toolInputLimit: 24576,
  toolResultLimit: 8192,
  window: 3
}
[2026-05-03 20:16:40.386] [info]   (chat-messages-ipc) chat.append {
  designId: '739dbd64-92f7-4300-b9b1-027a2a448e39',
  seq: 108,
  kind: 'tool_call'
}
[2026-05-03 20:16:40.387] [info]   (chat-messages-ipc) chat.append {
  designId: '739dbd64-92f7-4300-b9b1-027a2a448e39',
  seq: 109,
  kind: 'assistant_text'
}

[github-actions]

Thanks for reporting, @fabianmcja. The error you're seeing — Generation aborted after 1200s — is the default 20-minute generation timeout. You can increase this in Settings → Advanced → Generation timeout (available choices: 10m, 20m, 30m, 1h, 2h).

Since you're running Ollama on a remote Proxmox server, network latency and model size can significantly affect generation speed. I'd suggest:

1. Increase the timeout to 30m or 1h and try again.
2. Try a smaller/faster model (e.g., llama3.2:3b or qwen2.5:7b) to verify connectivity first.
3. Check the Ollama server's response times — curl -X POST http://<proxmox-ip>:11434/api/generate -d '{"model":"<your-model>","prompt":"hello","stream":false}' — and see how long a single inference takes.

Relevant code:

• apps/desktop/src/main/generate.ts — the IPC handler that enforces the timeout and surfaces GENERATION_TIMEOUT errors (see .changeset/fix-generation-timeout-reason.md for context).

Need more info:

• Which Ollama model are you using? (e.g., llama3.1:70b, qwq:32b, etc.)
• Have you been able to complete any shorter generations with the same setup?

---

Open-CoDesign Bot