Panel models in the fusion strategy must answer in prose. When the request carried tools or prior tool_calls/tool messages, agentic panel models kept emitting tool_calls instead of prose, so extractPanelText() returned empty and the engine fell into the 503 "All fusion panel models failed" branch. Panel fan-out now strips tools/tool_choice and flattens tool turns into assistant prose (instead of dropping them), so panels keep the context but cannot loop on tools. The judge still receives the unmodified history. Co-authored-by: warelik <warelik@WARELIK-MB.local> Co-authored-by: Cursor <cursoragent@cursor.com> |
||
|---|---|---|
| .. | ||
| tokenRefresh | ||
| usage | ||
| accountFallback.js | ||
| combo.js | ||
| compact.js | ||
| kiroModels.js | ||
| model.js | ||
| oauthCredentialManager.js | ||
| projectId.js | ||
| provider.js | ||
| qoderModels.js | ||
| tokenRefresh.js | ||
| usage.js | ||