Exiting plan mode not reliable with new GPT-5.6 models

### Describe the bug

When creating a plan with the new GPT-5.6 models (doesn't matter which one), often the interaction ends like this:

`Plan saved to plan.md, with implementation tasks tracked in the session database.`

And then nothing happens, what is expected is that the user is prompted with how to execute this plan, but this almost never happens. What works is to do prompt something like:

`Present me the plan, and ask me to implement with autopilot`

And after that implementation works as expected.

Other models (GPT-5.5, Anthropic, etc) do not have this issue.

### Affected version

`1.0.71`

### Steps to reproduce the behavior

See above

### Expected behavior

See above

### Additional context

N/A

Non vengono indicati file, test o punti di ingresso. Riproduci il problema nella versione 1.0.71 con un modello GPT-5.6, confrontalo con GPT-5.5 o Anthropic e traccia l’uscita da plan-mode; il lavoro è completato quando il prompt di implementazione previsto compare in modo affidabile dopo il salvataggio del piano.

Scritto dal modello di indicizzazione a partire dal testo della issue.