Bug: `beforeSubmitPrompt` hook `updated_input` is silently stripped — modified prompt never reaches the model

[Bogdan_Parhomenko (Богдан Пархоменко)]

Fantastic write-up and minimal reproducer!

I want to flag for the Cursor team that this is clearly part of a much broader, systemic issue with the hook architecture’s context-injection pipeline.

We are seeing the exact same “silently stripped / discarded output” behavior across other hooks, most notably postToolUse and sessionStart. Just like your case, the hooks fire, valid JSON is returned and logged by Cursor, but the injected context is completely dropped before it ever reaches the Agent’s context window.

It seems the plumbing between the hook manager and the model prompt builder is broken across the board, regardless of the hook type.

Here is the related thread detailing the exact same failure pattern for postToolUse:

Native postToolUse hooks accept and log additional_context successfully, but the injected context is not surfaced to the model

Adding data points on Cursor 3.1.15 (macOS, 2026-04-21). The postToolUse input side also looks unpopulated, on the same path where the response is discarded — so even fixing the output plumbing wouldn’t be sufficient on its own. Hook script logs process.argv, CURSOR_* env vars, and stdin length on every invocation. Representative entries: [2026-04-21T21:53:59.071Z] spawn pid=25047 argv=[] env= [2026-04-21T21:53:59.077Z] stdin-end bytes=0 [2026-04-21T21:55:37.036Z] spawn pid=26394 argv=[] env…

Hopefully, highlighting that this affects beforeSubmitPrompt, postToolUse, and sessionStart will help the engineering team track down the shared root cause in the prompt pipeline.