[Bug]: GENERATION_FAILED (fp: 69213336)

[abelzhang001]

Description

Error invoking remote method 'codesign:v1:generate': CodesignError: Generation aborted after 1200s (Settings → Advanced → Generation timeout).

Steps to reproduce

Error invoking remote method 'codesign:v1:generate': CodesignError: Generation aborted after 1200s (Settings → Advanced → Generation timeout).

Expected behavior

Error invoking remote method 'codesign:v1:generate': CodesignError: Generation aborted after 1200s (Settings → Advanced → Generation timeout).

Actual behavior

Error invoking remote method 'codesign:v1:generate': CodesignError: Generation aborted after 1200s (Settings → Advanced → Generation timeout).

open-codesign version

0.1.4

Platform

macOS

OS version

25.2.0

Model provider (if relevant)

None

Error code

GENERATION_FAILED

Diagnostics bundle

Bundle saved locally at ~/Downloads/open-codesign-diagnostics-2026-05-03T10-08-07.zip. Attach it to this issue after submitting.

Logs

after: 267608,
  blockLimit: 2048
}
[2026-05-03 17:58:07.391] [info]   (chat-messages-ipc) chat.append {
  designId: '3e35fb6f-1dd1-4bef-8ac9-05e549cd04ef',
  seq: 47,
  kind: 'tool_call'
}
[2026-05-03 18:00:25.804] [warn]   (main:ipc) generate.timeout.fired { runId: 'mopky533-uztktk', id: 'mopky533-uztktk', timeoutSec: 1200 }
[2026-05-03 18:00:25.811] [info]   (main:ipc) agent.turn_end {
  runId: 'mopky533-uztktk',
  generationId: 'mopky533-uztktk',
  deltas: 15,
  tools: 0
}
[2026-05-03 18:00:25.811] [info]   (main:ipc) agent.end { runId: 'mopky533-uztktk', generationId: 'mopky533-uztktk' }
[2026-05-03 18:00:25.812] [error]  (main:ipc) [generate] step=send_request.fail {
  runId: 'mopky533-uztktk',
  generationId: 'mopky533-uztktk',
  provider: 'claude-code-imported',
  modelId: 'claude-sonnet-4-6',
  ms: 1200010,
  stopReason: 'aborted'
}
[2026-05-03 18:00:25.813] [error]  (main:ipc) generate.fail {
  runId: 'mopky533-uztktk',
  generationId: 'mopky533-uztktk',
  ms: 1200013,
  provider: 'claude-code-imported',
  modelId: 'claude-sonnet-4-6',
  baseUrl: 'https://api.deepseek.com/anthropic',
  message: 'Generation aborted after 1200s (Settings → Advanced → Generation timeout).',
  code: 'GENERATION_TIMEOUT'
}
[2026-05-03 18:00:25.815] [info]   (chat-messages-ipc) chat.append {
  designId: '3e35fb6f-1dd1-4bef-8ac9-05e549cd04ef',
  seq: 48,
  kind: 'assistant_text'
}
[2026-05-03 18:00:25.818] [error]  (renderer:console) [store] applyGenerateError {"generationId":"mopky533-uztktk","designId":"3e35fb6f-1dd1-4bef-8ac9-05e549cd04ef","message":"Error invoking remote method 'codesign:v1:generate': CodesignError: Generation aborted after 1200s (Settings → Advanced → Generation timeout)."} {}
[2026-05-03 18:00:25.819] [info]   (chat-messages-ipc) chat.append {
  designId: '3e35fb6f-1dd1-4bef-8ac9-05e549cd04ef',
  seq: 49,
  kind: 'error'
}
[2026-05-03 18:00:25.835] [info]   (snapshots-ipc) snapshot.created {
  id: 'f7fb304e-43eb-45f5-9eed-0ba9736185c6',
  type: 'initial',
  designId: '3e35fb6f-1dd1-4bef-8ac9-05e549cd04ef'
}

[github-actions]

Thank you for the detailed report. Based on the logs you provided, the generation was aborted after 1200 seconds because it exceeded the generation timeout configured in Settings → Advanced → Generation timeout. The default is 1200s (20 minutes).

This is not a bug in the code — the app correctly timed out a long-running generation. However, if your prompt or model response takes longer, you can increase the timeout in Settings → Advanced to, say, 30m, 1h, or 2h.

A few observations from your logs:

• Provider: claude-code-imported → base URL https://api.deepseek.com/anthropic — you're routing Claude API calls through a DeepSeek endpoint, which may have slower response times or different timeout behaviors.
• Model: claude-sonnet-4-6 — a large model that can be slow on complex design tasks.
• The agent had processed 15 deltas and 0 tool calls before the timer fired, meaning the model was still responding (streaming) but hadn't finished within the limit.

Relevant code:

• apps/desktop/src/main/generate-ipc.ts — the timeout timer and abort logic.
• Recent changeset added more timeout presets (10m/20m/30m/1h/2h) — ensure you're on the latest release (v0.1.4 already includes the expanded dropdown).

Need more info (optional):

• What kind of design were you generating? Very long/complex prompts can extend generation time.
• Did you try increasing the timeout before reporting? It should resolve the issue.
• If the timeout keeps happening even with a generous limit, there may be a problem with the upstream provider (DeepSeek relay) stalling. A diagnostics bundle would help check for that.

You can also attach the diagnostics bundle you saved (open-codesign-diagnostics-2026-05-03T10-08-07.zip) — it will help maintainers see if there's an upstream issue.

---

Open-CoDesign Bot

[Sun-sunshine06]

Closing this timeout duplicate after #315 merged into main (768dc8b). GENERATION_TIMEOUT now has its own diagnostic category, localized copy, and a recovery action that opens Settings -> Advanced so the generation timeout can be adjusted.

The upcoming v0.2 packaged release will include this. The deeper provider/request-timeout follow-up remains tracked in #199 and #314.